diff options
1026 files changed, 33252 insertions, 12790 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events new file mode 100644 index 0000000..0adeb52 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events @@ -0,0 +1,62 @@ +What: /sys/devices/cpu/events/ + /sys/devices/cpu/events/branch-misses + /sys/devices/cpu/events/cache-references + /sys/devices/cpu/events/cache-misses + /sys/devices/cpu/events/stalled-cycles-frontend + /sys/devices/cpu/events/branch-instructions + /sys/devices/cpu/events/stalled-cycles-backend + /sys/devices/cpu/events/instructions + /sys/devices/cpu/events/cpu-cycles + +Date: 2013/01/08 + +Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> + +Description: Generic performance monitoring events + + A collection of performance monitoring events that may be + supported by many/most CPUs. These events can be monitored + using the 'perf(1)' tool. + + The contents of each file would look like: + + event=0xNNNN + + where 'N' is a hex digit and the number '0xNNNN' shows the + "raw code" for the perf event identified by the file's + "basename". + + +What: /sys/devices/cpu/events/PM_LD_MISS_L1 + /sys/devices/cpu/events/PM_LD_REF_L1 + /sys/devices/cpu/events/PM_CYC + /sys/devices/cpu/events/PM_BRU_FIN + /sys/devices/cpu/events/PM_GCT_NOSLOT_CYC + /sys/devices/cpu/events/PM_BRU_MPRED + /sys/devices/cpu/events/PM_INST_CMPL + /sys/devices/cpu/events/PM_CMPLU_STALL + +Date: 2013/01/08 + +Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> + Linux Powerpc mailing list <linuxppc-dev@ozlabs.org> + +Description: POWER-systems specific performance monitoring events + + A collection of performance monitoring events that may be + supported by the POWER CPU. These events can be monitored + using the 'perf(1)' tool. + + These events may not be supported by other CPUs. + + The contents of each file would look like: + + event=0xNNNN + + where 'N' is a hex digit and the number '0xNNNN' shows the + "raw code" for the perf event identified by the file's + "basename". + + Further, multiple terms like 'event=0xNNNN' can be specified + and separated with comma. All available terms are defined in + the /sys/bus/event_source/devices/<dev>/format file. diff --git a/Documentation/ABI/testing/sysfs-platform-ts5500 b/Documentation/ABI/testing/sysfs-platform-ts5500 new file mode 100644 index 0000000..c88375a --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-ts5500 @@ -0,0 +1,47 @@ +What: /sys/devices/platform/ts5500/adc +Date: January 2013 +KernelVersion: 3.7 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Indicates the presence of an A/D Converter. If it is present, + it will display "1", otherwise "0". + +What: /sys/devices/platform/ts5500/ereset +Date: January 2013 +KernelVersion: 3.7 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Indicates the presence of an external reset. If it is present, + it will display "1", otherwise "0". + +What: /sys/devices/platform/ts5500/id +Date: January 2013 +KernelVersion: 3.7 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Product ID of the TS board. TS-5500 ID is 0x60. + +What: /sys/devices/platform/ts5500/jumpers +Date: January 2013 +KernelVersion: 3.7 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Bitfield showing the jumpers' state. If a jumper is present, + the corresponding bit is set. For instance, 0x0e means jumpers + 2, 3 and 4 are set. + +What: /sys/devices/platform/ts5500/rs485 +Date: January 2013 +KernelVersion: 3.7 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Indicates the presence of the RS485 option. If it is present, + it will display "1", otherwise "0". + +What: /sys/devices/platform/ts5500/sram +Date: January 2013 +KernelVersion: 3.7 +Contact: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> +Description: + Indicates the presence of the SRAM option. If it is present, + it will display "1", otherwise "0". diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index 53e6fca..a091780 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -127,15 +127,42 @@ on the number of vectors that can be allocated; pci_enable_msi_block() returns as soon as it finds any constraint that doesn't allow the call to succeed. -4.2.3 pci_disable_msi +4.2.3 pci_enable_msi_block_auto + +int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *count) + +This variation on pci_enable_msi() call allows a device driver to request +the maximum possible number of MSIs. The MSI specification only allows +interrupts to be allocated in powers of two, up to a maximum of 2^5 (32). + +If this function returns a positive number, it indicates that it has +succeeded and the returned value is the number of allocated interrupts. In +this case, the function enables MSI on this device and updates dev->irq to +be the lowest of the new interrupts assigned to it. The other interrupts +assigned to the device are in the range dev->irq to dev->irq + returned +value - 1. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to request any more MSI interrupts for +this device. + +If the device driver needs to know the number of interrupts the device +supports it can pass the pointer count where that number is stored. The +device driver must decide what action to take if pci_enable_msi_block_auto() +succeeds, but returns a value less than the number of interrupts supported. +If the device driver does not need to know the number of interrupts +supported, it can set the pointer count to NULL. + +4.2.4 pci_disable_msi void pci_disable_msi(struct pci_dev *dev) This function should be used to undo the effect of pci_enable_msi() or -pci_enable_msi_block(). Calling it restores dev->irq to the pin-based -interrupt number and frees the previously allocated message signaled -interrupt(s). The interrupt may subsequently be assigned to another -device, so drivers should not cache the value of dev->irq. +pci_enable_msi_block() or pci_enable_msi_block_auto(). Calling it restores +dev->irq to the pin-based interrupt number and frees the previously +allocated message signaled interrupt(s). The interrupt may subsequently be +assigned to another device, so drivers should not cache the value of +dev->irq. Before calling this function, a device driver must always call free_irq() on any interrupt for which it previously called request_irq(). diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt index 27f2b21..d9ca5be 100644 --- a/Documentation/atomic_ops.txt +++ b/Documentation/atomic_ops.txt @@ -253,6 +253,8 @@ This performs an atomic exchange operation on the atomic variable v, setting the given new value. It returns the old value that the atomic variable v had just before the operation. +atomic_xchg requires explicit memory barriers around the operation. + int atomic_cmpxchg(atomic_t *v, int old, int new); This performs an atomic compare exchange operation on the atomic value v, diff --git a/Documentation/cgroups/00-INDEX b/Documentation/cgroups/00-INDEX index f78b90a..f5635a0 100644 --- a/Documentation/cgroups/00-INDEX +++ b/Documentation/cgroups/00-INDEX @@ -4,8 +4,6 @@ blkio-controller.txt - Description for Block IO Controller, implementation and usage details. cgroups.txt - Control Groups definition, implementation details, examples and API. -cgroup_event_listener.c - - A user program for cgroup listener. cpuacct.txt - CPU Accounting Controller; account CPU usage for groups of tasks. cpusets.txt diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index fc8fa97..ce94a83 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -399,8 +399,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. 9.10 Memory thresholds Memory controller implements memory thresholds using cgroups notification - API. You can use Documentation/cgroups/cgroup_event_listener.c to test - it. + API. You can use tools/cgroup/cgroup_event_listener.c to test it. (Shell-A) Create cgroup and run event listener # mkdir /cgroup/A diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 728c38c..56fb62b 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -141,3 +141,4 @@ Version History 1.2.0 Handle creation of arrays that contain failed devices. 1.3.0 Added support for RAID 10 1.3.1 Allow device replacement/rebuild for RAID 10 +1.3.2 Fix/improve redundancy checking for RAID10 diff --git a/Documentation/devicetree/bindings/mfd/tps6507x.txt b/Documentation/devicetree/bindings/mfd/tps6507x.txt new file mode 100755 index 0000000..8fffa3c --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/tps6507x.txt @@ -0,0 +1,91 @@ +TPS6507x Power Management Integrated Circuit + +Required properties: +- compatible: "ti,tps6507x" +- reg: I2C slave address +- regulators: This is the list of child nodes that specify the regulator + initialization data for defined regulators. Not all regulators for the + given device need to be present. The definition for each of these nodes + is defined using the standard binding for regulators found at + Documentation/devicetree/bindings/regulator/regulator.txt. + The regulator is matched with the regulator-compatible. + + The valid regulator-compatible values are: + tps6507x: vdcdc1, vdcdc2, vdcdc3, vldo1, vldo2 +- xxx-supply: Input voltage supply regulator. + These entries are required if regulators are enabled for a device. + Missing of these properties can cause the regulator registration + fails. + If some of input supply is powered through battery or always-on + supply then also it is require to have these parameters with proper + node handle of always on power supply. + tps6507x: + vindcdc1_2-supply: VDCDC1 and VDCDC2 input. + vindcdc3-supply : VDCDC3 input. + vldo1_2-supply : VLDO1 and VLDO2 input. + +Regulator Optional properties: +- defdcdc_default: It's property of DCDC2 and DCDC3 regulators. + 0: If defdcdc pin of DCDC2/DCDC3 is pulled to GND. + 1: If defdcdc pin of DCDC2/DCDC3 is driven HIGH. + If this property is not defined, it defaults to 0 (not enabled). + +Example: + + pmu: tps6507x@48 { + compatible = "ti,tps6507x"; + reg = <0x48>; + + vindcdc1_2-supply = <&vbat>; + vindcdc3-supply = <...>; + vinldo1_2-supply = <...>; + + regulators { + #address-cells = <1>; + #size-cells = <0>; + + vdcdc1_reg: regulator@0 { + regulator-compatible = "VDCDC1"; + reg = <0>; + regulator-min-microvolt = <3150000>; + regulator-max-microvolt = <3450000>; + regulator-always-on; + regulator-boot-on; + }; + vdcdc2_reg: regulator@1 { + regulator-compatible = "VDCDC2"; + reg = <1>; + regulator-min-microvolt = <1710000>; + regulator-max-microvolt = <3450000>; + regulator-always-on; + regulator-boot-on; + defdcdc_default = <1>; + }; + vdcdc3_reg: regulator@2 { + regulator-compatible = "VDCDC3"; + reg = <2>; + regulator-min-microvolt = <950000> + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + defdcdc_default = <1>; + }; + ldo1_reg: regulator@3 { + regulator-compatible = "LDO1"; + reg = <3>; + regulator-min-microvolt = <1710000>; + regulator-max-microvolt = <1890000>; + regulator-always-on; + regulator-boot-on; + }; + ldo2_reg: regulator@4 { + regulator-compatible = "LDO2"; + reg = <4>; + regulator-min-microvolt = <1140000>; + regulator-max-microvolt = <1320000>; + regulator-always-on; + regulator-boot-on; + }; + }; + + }; diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt new file mode 100644 index 0000000..dff0e5f --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt @@ -0,0 +1,60 @@ +* Allwinner A1X Pin Controller + +The pins controlled by sunXi pin controller are organized in banks, +each bank has 32 pins. Each pin has 7 multiplexing functions, with +the first two functions being GPIO in and out. The configuration on +the pins includes drive strength and pull-up. + +Required properties: +- compatible: "allwinner,<soc>-pinctrl". Supported SoCs for now are: + sun5i-a13. +- reg: Should contain the register physical address and length for the + pin controller. + +Please refer to pinctrl-bindings.txt in this directory for details of the +common pinctrl bindings used by client devices. + +A pinctrl node should contain at least one subnodes representing the +pinctrl groups available on the machine. Each subnode will list the +pins it needs, and how they should be configured, with regard to muxer +configuration, drive strength and pullups. If one of these options is +not set, its actual value will be unspecified. + +Required subnode-properties: + +- allwinner,pins: List of strings containing the pin name. +- allwinner,function: Function to mux the pins listed above to. + +Optional subnode-properties: +- allwinner,drive: Integer. Represents the current sent to the pin + 0: 10 mA + 1: 20 mA + 2: 30 mA + 3: 40 mA +- allwinner,pull: Integer. + 0: No resistor + 1: Pull-up resistor + 2: Pull-down resistor + +Examples: + +pinctrl@01c20800 { + compatible = "allwinner,sun5i-a13-pinctrl"; + reg = <0x01c20800 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + uart1_pins_a: uart1@0 { + allwinner,pins = "PE10", "PE11"; + allwinner,function = "uart1"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; + + uart1_pins_b: uart1@1 { + allwinner,pins = "PG3", "PG4"; + allwinner,function = "uart1"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; +}; diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt new file mode 100644 index 0000000..e204d00 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra114-pinmux.txt @@ -0,0 +1,120 @@ +NVIDIA Tegra114 pinmux controller + +The Tegra114 pinctrl binding is very similar to the Tegra20 and Tegra30 +pinctrl binding, as described in nvidia,tegra20-pinmux.txt and +nvidia,tegra30-pinmux.txt. In fact, this document assumes that binding as +a baseline, and only documents the differences between the two bindings. + +Required properties: +- compatible: "nvidia,tegra114-pinmux" +- reg: Should contain the register physical address and length for each of + the pad control and mux registers. The first bank of address must be the + driver strength pad control register address and second bank address must + be pinmux register address. + +Tegra114 adds the following optional properties for pin configuration subnodes: +- nvidia,enable-input: Integer. Enable the pin's input path. 0: no, 1: yes. +- nvidia,open-drain: Integer. Enable open drain mode. 0: no, 1: yes. +- nvidia,lock: Integer. Lock the pin configuration against further changes + until reset. 0: no, 1: yes. +- nvidia,io-reset: Integer. Reset the IO path. 0: no, 1: yes. +- nvidia,rcv-sel: Integer. Select VIL/VIH receivers. 0: normal, 1: high. +- nvidia,drive-type: Integer. Valid range 0...3. + +As with Tegra20 and Terga30, see the Tegra TRM for complete details regarding +which groups support which functionality. + +Valid values for pin and group names are: + + per-pin mux groups: + + These all support nvidia,function, nvidia,tristate, nvidia,pull, + nvidia,enable-input, nvidia,lock. Some support nvidia,open-drain, + nvidia,io-reset and nvidia,rcv-sel. + + ulpi_data0_po1, ulpi_data1_po2, ulpi_data2_po3, ulpi_data3_po4, + ulpi_data4_po5, ulpi_data5_po6, ulpi_data6_po7, ulpi_data7_po0, + ulpi_clk_py0, ulpi_dir_py1, ulpi_nxt_py2, ulpi_stp_py3, dap3_fs_pp0, + dap3_din_pp1, dap3_dout_pp2, dap3_sclk_pp3, pv0, pv1, sdmmc1_clk_pz0, + sdmmc1_cmd_pz1, sdmmc1_dat3_py4, sdmmc1_dat2_py5, sdmmc1_dat1_py6, + sdmmc1_dat0_py7, clk2_out_pw5, clk2_req_pcc5, hdmi_int_pn7, ddc_scl_pv4, + ddc_sda_pv5, uart2_rxd_pc3, uart2_txd_pc2, uart2_rts_n_pj6, + uart2_cts_n_pj5, uart3_txd_pw6, uart3_rxd_pw7, uart3_cts_n_pa1, + uart3_rts_n_pc0, pu0, pu1, pu2, pu3, pu4, pu5, pu6, gen1_i2c_sda_pc5, + gen1_i2c_scl_pc4, dap4_fs_pp4, dap4_din_pp5, dap4_dout_pp6, dap4_sclk_pp7, + clk3_out_pee0, clk3_req_pee1, gmi_wp_n_pc7, gmi_iordy_pi5, gmi_wait_pi7, + gmi_adv_n_pk0, gmi_clk_pk1, gmi_cs0_n_pj0, gmi_cs1_n_pj2, gmi_cs2_n_pk3, + gmi_cs3_n_pk4, gmi_cs4_n_pk2, gmi_cs6_n_pi3, gmi_cs7_n_pi6, gmi_ad0_pg0, + gmi_ad1_pg1, gmi_ad2_pg2, gmi_ad3_pg3, gmi_ad4_pg4, gmi_ad5_pg5, + gmi_ad6_pg6, gmi_ad7_pg7, gmi_ad8_ph0, gmi_ad9_ph1, gmi_ad10_ph2, + gmi_ad11_ph3, gmi_ad12_ph4, gmi_ad13_ph5, gmi_ad14_ph6, gmi_ad15_ph7, + gmi_a16_pj7, gmi_a17_pb0, gmi_a18_pb1, gmi_a19_pk7, gmi_wr_n_pi0, + gmi_oe_n_pi1, gmi_dqs_p_pj3, gmi_rst_n_pi4, gen2_i2c_scl_pt5, + gen2_i2c_sda_pt6, sdmmc4_clk_pcc4, sdmmc4_cmd_pt7, sdmmc4_dat0_paa0, + sdmmc4_dat1_paa1, sdmmc4_dat2_paa2, sdmmc4_dat3_paa3, sdmmc4_dat4_paa4, + sdmmc4_dat5_paa5, sdmmc4_dat6_paa6, sdmmc4_dat7_paa7, cam_mclk_pcc0, + pcc1, pbb0, cam_i2c_scl_pbb1, cam_i2c_sda_pbb2, pbb3, pbb4, pbb5, pbb6, + pbb7, pcc2, pwr_i2c_scl_pz6, pwr_i2c_sda_pz7, kb_row0_pr0, kb_row1_pr1, + kb_row2_pr2, kb_row3_pr3, kb_row4_pr4, kb_row5_pr5, kb_row6_pr6, + kb_row7_pr7, kb_row8_ps0, kb_row9_ps1, kb_row10_ps2, kb_col0_pq0, + kb_col1_pq1, kb_col2_pq2, kb_col3_pq3, kb_col4_pq4, kb_col5_pq5, + kb_col6_pq6, kb_col7_pq7, clk_32k_out_pa0, sys_clk_req_pz5, core_pwr_req, + cpu_pwr_req, pwr_int_n, owr, dap1_fs_pn0, dap1_din_pn1, dap1_dout_pn2, + dap1_sclk_pn3, clk1_req_pee2, clk1_out_pw4, spdif_in_pk6, spdif_out_pk5, + dap2_fs_pa2, dap2_din_pa4, dap2_dout_pa5, dap2_sclk_pa3, dvfs_pwm_px0, + gpio_x1_aud_px1, gpio_x3_aud_px3, dvfs_clk_px2, gpio_x4_aud_px4, + gpio_x5_aud_px5, gpio_x6_aud_px6, gpio_x7_aud_px7, sdmmc3_clk_pa6, + sdmmc3_cmd_pa7, sdmmc3_dat0_pb7, sdmmc3_dat1_pb6, sdmmc3_dat2_pb5, + sdmmc3_dat3_pb4, hdmi_cec_pee3, sdmmc1_wp_n_pv3, sdmmc3_cd_n_pv2, + gpio_w2_aud_pw2, gpio_w3_aud_pw3, usb_vbus_en0_pn4, usb_vbus_en1_pn5, + sdmmc3_clk_lb_in_pee5, sdmmc3_clk_lb_out_pee4, reset_out_n. + + drive groups: + + These all support nvidia,pull-down-strength, nvidia,pull-up-strength, + nvidia,slew-rate-rising, nvidia,slew-rate-falling. Most but not all + support nvidia,high-speed-mode, nvidia,schmitt, nvidia,low-power-mode + and nvidia,drive-type. + + ao1, ao2, at1, at2, at3, at4, at5, cdev1, cdev2, dap1, dap2, dap3, dap4, + dbg, sdio3, spi, uaa, uab, uart2, uart3, sdio1, ddc, gma, gme, gmf, gmg, + gmh, owr, uda. + +Example: + + pinmux: pinmux { + compatible = "nvidia,tegra114-pinmux"; + reg = <0x70000868 0x148 /* Pad control registers */ + 0x70003000 0x40c>; /* PinMux registers */ + }; + +Example board file extract: + + pinctrl { + sdmmc4_default: pinmux { + sdmmc4_clk_pcc4 { + nvidia,pins = "sdmmc4_clk_pcc4", + nvidia,function = "sdmmc4"; + nvidia,pull = <0>; + nvidia,tristate = <0>; + }; + sdmmc4_dat0_paa0 { + nvidia,pins = "sdmmc4_dat0_paa0", + "sdmmc4_dat1_paa1", + "sdmmc4_dat2_paa2", + "sdmmc4_dat3_paa3", + "sdmmc4_dat4_paa4", + "sdmmc4_dat5_paa5", + "sdmmc4_dat6_paa6", + "sdmmc4_dat7_paa7"; + nvidia,function = "sdmmc4"; + nvidia,pull = <2>; + nvidia,tristate = <0>; + }; + }; + }; + + sdhci@78000400 { + pinctrl-names = "default"; + pinctrl-0 = <&sdmmc4_default>; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt b/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt new file mode 100644 index 0000000..9a2f3f4 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/ste,nomadik.txt @@ -0,0 +1,140 @@ +ST Ericsson Nomadik pinmux controller + +Required properties: +- compatible: "stericsson,nmk-pinctrl", "stericsson,nmk-pinctrl-db8540", + "stericsson,nmk-pinctrl-stn8815" +- reg: Should contain the register physical address and length of the PRCMU. + +Please refer to pinctrl-bindings.txt in this directory for details of the +common pinctrl bindings used by client devices, including the meaning of the +phrase "pin configuration node". + +ST Ericsson's pin configuration nodes act as a container for an arbitrary number of +subnodes. Each of these subnodes represents some desired configuration for a +pin, a group, or a list of pins or groups. This configuration can include the +mux function to select on those pin(s)/group(s), and various pin configuration +parameters, such as input, output, pull up, pull down... + +The name of each subnode is not important; all subnodes should be enumerated +and processed purely based on their content. + +Required subnode-properties: +- ste,pins : An array of strings. Each string contains the name of a pin or + group. + +Optional subnode-properties: +- ste,function: A string containing the name of the function to mux to the + pin or group. + +- ste,config: Handle of pin configuration node (e.g. ste,config = <&slpm_in_wkup_pdis>) + +- ste,input : <0/1/2> + 0: input with no pull + 1: input with pull up, + 2: input with pull down, + +- ste,output: <0/1/2> + 0: output low, + 1: output high, + 2: output (value is not specified). + +- ste,sleep: <0/1> + 0: sleep mode disable, + 1: sleep mode enable. + +- ste,sleep-input: <0/1/2/3> + 0: sleep input with no pull, + 1: sleep input with pull up, + 2: sleep input with pull down. + 3: sleep input and keep last input configuration (no pull, pull up or pull down). + +- ste,sleep-output: <0/1/2> + 0: sleep output low, + 1: sleep output high, + 2: sleep output (value is not specified). + +- ste,sleep-gpio: <0/1> + 0: disable sleep gpio mode, + 1: enable sleep gpio mode. + +- ste,sleep-wakeup: <0/1> + 0: wake-up detection enabled, + 1: wake-up detection disabled. + +- ste,sleep-pull-disable: <0/1> + 0: GPIO pull-up or pull-down resistor is enabled, when pin is an input, + 1: GPIO pull-up and pull-down resistor are disabled. + +Example board file extract: + + pinctrl@80157000 { + compatible = "stericsson,nmk-pinctrl"; + reg = <0x80157000 0x2000>; + + pinctrl-names = "default"; + + slpm_in_wkup_pdis: slpm_in_wkup_pdis { + ste,sleep = <1>; + ste,sleep-input = <3>; + ste,sleep-wakeup = <1>; + ste,sleep-pull-disable = <0>; + }; + + slpm_out_hi_wkup_pdis: slpm_out_hi_wkup_pdis { + ste,sleep = <1>; + ste,sleep-output = <1>; + ste,sleep-wakeup = <1>; + ste,sleep-pull-disable = <0>; + }; + + slpm_out_wkup_pdis: slpm_out_wkup_pdis { + ste,sleep = <1>; + ste,sleep-output = <2>; + ste,sleep-wakeup = <1>; + ste,sleep-pull-disable = <0>; + }; + + uart0 { + uart0_default_mux: uart0_mux { + u0_default_mux { + ste,function = "u0"; + ste,pins = "u0_a_1"; + }; + }; + uart0_default_mode: uart0_default { + uart0_default_cfg1 { + ste,pins = "GPIO0", "GPIO2"; + ste,input = <1>; + }; + + uart0_default_cfg2 { + ste,pins = "GPIO1", "GPIO3"; + ste,output = <1>; + }; + }; + uart0_sleep_mode: uart0_sleep { + uart0_sleep_cfg1 { + ste,pins = "GPIO0", "GPIO2"; + ste,config = <&slpm_in_wkup_pdis>; + }; + uart0_sleep_cfg2 { + ste,pins = "GPIO1"; + ste,config = <&slpm_out_hi_wkup_pdis>; + }; + uart0_sleep_cfg3 { + ste,pins = "GPIO3"; + ste,config = <&slpm_out_wkup_pdis>; + }; + }; + }; + }; + + uart@80120000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x80120000 0x1000>; + interrupts = <0 11 0x4>; + + pinctrl-names = "default","sleep"; + pinctrl-0 = <&uart0_default_mux>, <&uart0_default_mode>; + pinctrl-1 = <&uart0_sleep_mode>; + }; diff --git a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt index 357758c..758eae2 100644 --- a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt @@ -9,6 +9,11 @@ Required properties: - anatop-min-voltage: Minimum voltage of this regulator - anatop-max-voltage: Maximum voltage of this regulator +Optional properties: +- anatop-delay-reg-offset: Anatop MFD step time register offset +- anatop-delay-bit-shift: Bit shift for the step time register +- anatop-delay-bit-width: Number of bits used in the step time register + Any property defined as part of the core regulator binding, defined in regulator.txt, can also be used. @@ -23,6 +28,9 @@ Example: anatop-reg-offset = <0x140>; anatop-vol-bit-shift = <9>; anatop-vol-bit-width = <5>; + anatop-delay-reg-offset = <0x170>; + anatop-delay-bit-shift = <24>; + anatop-delay-bit-width = <2>; anatop-min-bit-val = <1>; anatop-min-voltage = <725000>; anatop-max-voltage = <1300000>; diff --git a/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt b/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt new file mode 100644 index 0000000..a35ff99 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt @@ -0,0 +1,152 @@ +* Samsung S5M8767 Voltage and Current Regulator + +The Samsung S5M8767 is a multi-function device which includes volatage and +current regulators, rtc, charger controller and other sub-blocks. It is +interfaced to the host controller using a i2c interface. Each sub-block is +addressed by the host system using different i2c slave address. This document +describes the bindings for 'pmic' sub-block of s5m8767. + +Required properties: +- compatible: Should be "samsung,s5m8767-pmic". +- reg: Specifies the i2c slave address of the pmic block. It should be 0x66. + +- s5m8767,pmic-buck2-dvs-voltage: A set of 8 voltage values in micro-volt (uV) + units for buck2 when changing voltage using gpio dvs. Refer to [1] below + for additional information. + +- s5m8767,pmic-buck3-dvs-voltage: A set of 8 voltage values in micro-volt (uV) + units for buck3 when changing voltage using gpio dvs. Refer to [1] below + for additional information. + +- s5m8767,pmic-buck4-dvs-voltage: A set of 8 voltage values in micro-volt (uV) + units for buck4 when changing voltage using gpio dvs. Refer to [1] below + for additional information. + +- s5m8767,pmic-buck-ds-gpios: GPIO specifiers for three host gpio's used + for selecting GPIO DVS lines. It is one-to-one mapped to dvs gpio lines. + +[1] If none of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional + property is specified, the 's5m8767,pmic-buck[2/3/4]-dvs-voltage' + property should specify atleast one voltage level (which would be a + safe operating voltage). + + If either of the 's5m8767,pmic-buck[2/3/4]-uses-gpio-dvs' optional + property is specified, then all the eight voltage values for the + 's5m8767,pmic-buck[2/3/4]-dvs-voltage' should be specified. + +Optional properties: +- interrupt-parent: Specifies the phandle of the interrupt controller to which + the interrupts from s5m8767 are delivered to. +- interrupts: Interrupt specifiers for two interrupt sources. + - First interrupt specifier is for 'irq1' interrupt. + - Second interrupt specifier is for 'alert' interrupt. +- s5m8767,pmic-buck2-uses-gpio-dvs: 'buck2' can be controlled by gpio dvs. +- s5m8767,pmic-buck3-uses-gpio-dvs: 'buck3' can be controlled by gpio dvs. +- s5m8767,pmic-buck4-uses-gpio-dvs: 'buck4' can be controlled by gpio dvs. + +Additional properties required if either of the optional properties are used: + +- s5m8767,pmic-buck234-default-dvs-idx: Default voltage setting selected from + the possible 8 options selectable by the dvs gpios. The value of this + property should be between 0 and 7. If not specified or if out of range, the + default value of this property is set to 0. + +- s5m8767,pmic-buck-dvs-gpios: GPIO specifiers for three host gpio's used + for dvs. The format of the gpio specifier depends in the gpio controller. + +Regulators: The regulators of s5m8767 that have to be instantiated should be +included in a sub-node named 'regulators'. Regulator nodes included in this +sub-node should be of the format as listed below. + + regulator_name { + ldo1_reg: LDO1 { + regulator-name = "VDD_ALIVE_1.0V"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + regulator-boot-on; + op_mode = <1>; /* Normal Mode */ + }; + }; +The above regulator entries are defined in regulator bindings documentation +except op_mode description. + - op_mode: describes the different operating modes of the LDO's with + power mode change in SOC. The different possible values are, + 0 - always off mode + 1 - on in normal mode + 2 - low power mode + 3 - suspend mode + +The following are the names of the regulators that the s5m8767 pmic block +supports. Note: The 'n' in LDOn and BUCKn represents the LDO or BUCK number +as per the datasheet of s5m8767. + + - LDOn + - valid values for n are 1 to 28 + - Example: LDO0, LD01, LDO28 + - BUCKn + - valid values for n are 1 to 9. + - Example: BUCK1, BUCK2, BUCK9 + +The bindings inside the regulator nodes use the standard regulator bindings +which are documented elsewhere. + +Example: + + s5m8767_pmic@66 { + compatible = "samsung,s5m8767-pmic"; + reg = <0x66>; + + s5m8767,pmic-buck2-uses-gpio-dvs; + s5m8767,pmic-buck3-uses-gpio-dvs; + s5m8767,pmic-buck4-uses-gpio-dvs; + + s5m8767,pmic-buck-default-dvs-idx = <0>; + + s5m8767,pmic-buck-dvs-gpios = <&gpx0 0 1 0 0>, /* DVS1 */ + <&gpx0 1 1 0 0>, /* DVS2 */ + <&gpx0 2 1 0 0>; /* DVS3 */ + + s5m8767,pmic-buck-ds-gpios = <&gpx2 3 1 0 0>, /* SET1 */ + <&gpx2 4 1 0 0>, /* SET2 */ + <&gpx2 5 1 0 0>; /* SET3 */ + + s5m8767,pmic-buck2-dvs-voltage = <1350000>, <1300000>, + <1250000>, <1200000>, + <1150000>, <1100000>, + <1000000>, <950000>; + + s5m8767,pmic-buck3-dvs-voltage = <1100000>, <1100000>, + <1100000>, <1100000>, + <1000000>, <1000000>, + <1000000>, <1000000>; + + s5m8767,pmic-buck4-dvs-voltage = <1200000>, <1200000>, + <1200000>, <1200000>, + <1200000>, <1200000>, + <1200000>, <1200000>; + + regulators { + ldo1_reg: LDO1 { + regulator-name = "VDD_ABB_3.3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + op_mode = <1>; /* Normal Mode */ + }; + + ldo2_reg: LDO2 { + regulator-name = "VDD_ALIVE_1.1V"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + regulator-always-on; + }; + + buck1_reg: BUCK1 { + regulator-name = "VDD_MIF_1.2V"; + regulator-min-microvolt = <950000>; + regulator-max-microvolt = <1350000>; + regulator-always-on; + regulator-boot-on; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/regulator/tps51632-regulator.txt b/Documentation/devicetree/bindings/regulator/tps51632-regulator.txt new file mode 100644 index 0000000..2f7e44a --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/tps51632-regulator.txt @@ -0,0 +1,27 @@ +TPS51632 Voltage regulators + +Required properties: +- compatible: Must be "ti,tps51632" +- reg: I2C slave address + +Optional properties: +- ti,enable-pwm-dvfs: Enable the DVFS voltage control through the PWM interface. +- ti,dvfs-step-20mV: The 20mV step voltage when PWM DVFS enabled. Missing this + will set 10mV step voltage in PWM DVFS mode. In normal mode, the voltage + step is 10mV as per datasheet. + +Any property defined as part of the core regulator binding, defined in +regulator.txt, can also be used. + +Example: + + tps51632 { + compatible = "ti,tps51632"; + reg = <0x43>; + regulator-name = "tps51632-vout"; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1500000>; + regulator-boot-on; + ti,enable-pwm-dvfs; + ti,dvfs-step-20mV; + }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 902b1b1..1532137 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -50,6 +50,7 @@ simtek sirf SiRF Technology, Inc. snps Synopsys, Inc. st STMicroelectronics +ste ST-Ericsson stericsson ST-Ericsson ti Texas Instruments via VIA Technologies, Inc. diff --git a/Documentation/hid/hid-sensor.txt b/Documentation/hid/hid-sensor.txt index 948b098..948b098 100755..100644 --- a/Documentation/hid/hid-sensor.txt +++ b/Documentation/hid/hid-sensor.txt diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 363e348..6c72381 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2438,7 +2438,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. real-time workloads. It can also improve energy efficiency for asymmetric multiprocessors. - rcu_nocbs_poll [KNL,BOOT] + rcu_nocb_poll [KNL,BOOT] Rather than requiring that offloaded CPUs (specified by rcu_nocbs= above) explicitly awaken the corresponding "rcuoN" kthreads, diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 3c4e1b3..fa5d8a9 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1685,6 +1685,7 @@ explicit lock operations, described later). These include: xchg(); cmpxchg(); + atomic_xchg(); atomic_cmpxchg(); atomic_inc_return(); atomic_dec_return(); diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt index da40efb..a2b57e0 100644 --- a/Documentation/pinctrl.txt +++ b/Documentation/pinctrl.txt @@ -972,6 +972,18 @@ pinmux core. Pin control requests from drivers ================================= +When a device driver is about to probe the device core will automatically +attempt to issue pinctrl_get_select_default() on these devices. +This way driver writers do not need to add any of the boilerplate code +of the type found below. However when doing fine-grained state selection +and not using the "default" state, you may have to do some device driver +handling of the pinctrl handles and states. + +So if you just want to put the pins for a certain device into the default +state and be done with it, there is nothing you need to do besides +providing the proper mapping table. The device core will take care of +the rest. + Generally it is discouraged to let individual drivers get and enable pin control. So if possible, handle the pin control in platform code or some other place where you have access to all the affected struct device * pointers. In @@ -1097,9 +1109,9 @@ situations that can be electrically unpleasant, you will certainly want to mux in and bias pins in a certain way before the GPIO subsystems starts to deal with them. -The above can be hidden: using pinctrl hogs, the pin control driver may be -setting up the config and muxing for the pins when it is probing, -nevertheless orthogonal to the GPIO subsystem. +The above can be hidden: using the device core, the pinctrl core may be +setting up the config and muxing for the pins right before the device is +probing, nevertheless orthogonal to the GPIO subsystem. But there are also situations where it makes sense for the GPIO subsystem to communicate directly with with the pinctrl subsystem, using the latter diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 6f51fed..53d6a3c 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -1842,6 +1842,89 @@ an error. # cat buffer_size_kb 85 +Snapshot +-------- +CONFIG_TRACER_SNAPSHOT makes a generic snapshot feature +available to all non latency tracers. (Latency tracers which +record max latency, such as "irqsoff" or "wakeup", can't use +this feature, since those are already using the snapshot +mechanism internally.) + +Snapshot preserves a current trace buffer at a particular point +in time without stopping tracing. Ftrace swaps the current +buffer with a spare buffer, and tracing continues in the new +current (=previous spare) buffer. + +The following debugfs files in "tracing" are related to this +feature: + + snapshot: + + This is used to take a snapshot and to read the output + of the snapshot. Echo 1 into this file to allocate a + spare buffer and to take a snapshot (swap), then read + the snapshot from this file in the same format as + "trace" (described above in the section "The File + System"). Both reads snapshot and tracing are executable + in parallel. When the spare buffer is allocated, echoing + 0 frees it, and echoing else (positive) values clear the + snapshot contents. + More details are shown in the table below. + + status\input | 0 | 1 | else | + --------------+------------+------------+------------+ + not allocated |(do nothing)| alloc+swap | EINVAL | + --------------+------------+------------+------------+ + allocated | free | swap | clear | + --------------+------------+------------+------------+ + +Here is an example of using the snapshot feature. + + # echo 1 > events/sched/enable + # echo 1 > snapshot + # cat snapshot +# tracer: nop +# +# entries-in-buffer/entries-written: 71/71 #P:8 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + <idle>-0 [005] d... 2440.603828: sched_switch: prev_comm=swapper/5 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2242 next_prio=120 + sleep-2242 [005] d... 2440.603846: sched_switch: prev_comm=snapshot-test-2 prev_pid=2242 prev_prio=120 prev_state=R ==> next_comm=kworker/5:1 next_pid=60 next_prio=120 +[...] + <idle>-0 [002] d... 2440.707230: sched_switch: prev_comm=swapper/2 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2229 next_prio=120 + + # cat trace +# tracer: nop +# +# entries-in-buffer/entries-written: 77/77 #P:8 +# +# _-----=> irqs-off +# / _----=> need-resched +# | / _---=> hardirq/softirq +# || / _--=> preempt-depth +# ||| / delay +# TASK-PID CPU# |||| TIMESTAMP FUNCTION +# | | | |||| | | + <idle>-0 [007] d... 2440.707395: sched_switch: prev_comm=swapper/7 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=snapshot-test-2 next_pid=2243 next_prio=120 + snapshot-test-2-2229 [002] d... 2440.707438: sched_switch: prev_comm=snapshot-test-2 prev_pid=2229 prev_prio=120 prev_state=S ==> next_comm=swapper/2 next_pid=0 next_prio=120 +[...] + + +If you try to use this snapshot feature when current tracer is +one of the latency tracers, you will get the following results. + + # echo wakeup > current_tracer + # echo 1 > snapshot +bash: echo: write error: Device or resource busy + # cat snapshot +cat: snapshot: Device or resource busy + ----------- More details can be found in the source code, in the diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 406d82d..b443f1d 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -57,6 +57,10 @@ Protocol 2.10: (Kernel 2.6.31) Added a protocol for relaxed alignment Protocol 2.11: (Kernel 3.6) Added a field for offset of EFI handover protocol entry point. +Protocol 2.12: (Kernel 3.8) Added the xloadflags field and extension fields + to struct boot_params for for loading bzImage and ramdisk + above 4G in 64bit. + **** MEMORY LAYOUT The traditional memory map for the kernel loader, used for Image or @@ -182,7 +186,7 @@ Offset Proto Name Meaning 0230/4 2.05+ kernel_alignment Physical addr alignment required for kernel 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not 0235/1 2.10+ min_alignment Minimum alignment, as a power of two -0236/2 N/A pad3 Unused +0236/2 2.12+ xloadflags Boot protocol option flags 0238/4 2.06+ cmdline_size Maximum size of the kernel command line 023C/4 2.07+ hardware_subarch Hardware subarchitecture 0240/8 2.07+ hardware_subarch_data Subarchitecture-specific data @@ -386,6 +390,7 @@ Protocol: 2.00+ F Special (0xFF = undefined) 10 Reserved 11 Minimal Linux Bootloader <http://sebastian-plotz.blogspot.de> + 12 OVMF UEFI virtualization stack Please contact <hpa@zytor.com> if you need a bootloader ID value assigned. @@ -582,6 +587,27 @@ Protocol: 2.10+ misaligned kernel. Therefore, a loader should typically try each power-of-two alignment from kernel_alignment down to this alignment. +Field name: xloadflags +Type: read +Offset/size: 0x236/2 +Protocol: 2.12+ + + This field is a bitmask. + + Bit 0 (read): XLF_KERNEL_64 + - If 1, this kernel has the legacy 64-bit entry point at 0x200. + + Bit 1 (read): XLF_CAN_BE_LOADED_ABOVE_4G + - If 1, kernel/boot_params/cmdline/ramdisk can be above 4G. + + Bit 2 (read): XLF_EFI_HANDOVER_32 + - If 1, the kernel supports the 32-bit EFI handoff entry point + given at handover_offset. + + Bit 3 (read): XLF_EFI_HANDOVER_64 + - If 1, the kernel supports the 64-bit EFI handoff entry point + given at handover_offset + 0x200. + Field name: cmdline_size Type: read Offset/size: 0x238/4 diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index cf5437d..199f453 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -19,6 +19,9 @@ Offset Proto Name Meaning 090/010 ALL hd1_info hd1 disk parameter, OBSOLETE!! 0A0/010 ALL sys_desc_table System description table (struct sys_desc_table) 0B0/010 ALL olpc_ofw_header OLPC's OpenFirmware CIF and friends +0C0/004 ALL ext_ramdisk_image ramdisk_image high 32bits +0C4/004 ALL ext_ramdisk_size ramdisk_size high 32bits +0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits 140/080 ALL edid_info Video mode setup (struct edid_info) 1C0/020 ALL efi_info EFI 32 information (struct efi_info) 1E0/004 ALL alk_mem_k Alternative mem check, in KB @@ -27,6 +30,7 @@ Offset Proto Name Meaning 1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below) 1EA/001 ALL edd_mbr_sig_buf_entries Number of entries in edd_mbr_sig_buffer (below) +1EF/001 ALL sentinel Used to detect broken bootloaders 290/040 ALL edd_mbr_sig_buffer EDD MBR signatures 2D0/A00 ALL e820_map E820 memory map table (array of struct e820entry) diff --git a/MAINTAINERS b/MAINTAINERS index 8ae709e..b7013e4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1303,7 +1303,7 @@ F: include/linux/dmaengine.h F: include/linux/async_tx.h AT24 EEPROM DRIVER -M: Wolfram Sang <w.sang@pengutronix.de> +M: Wolfram Sang <wsa@the-dreams.de> L: linux-i2c@vger.kernel.org S: Maintained F: drivers/misc/eeprom/at24.c @@ -1489,7 +1489,7 @@ AVR32 ARCHITECTURE M: Haavard Skinnemoen <hskinnemoen@gmail.com> M: Hans-Christian Egtvedt <egtvedt@samfundet.no> W: http://www.atmel.com/products/AVR32/ -W: http://avr32linux.org/ +W: http://mirror.egtvedt.no/avr32linux.org/ W: http://avrfreaks.net/ S: Maintained F: arch/avr32/ @@ -2140,10 +2140,10 @@ S: Maintained F: tools/power/cpupower CPUSETS -M: Paul Menage <paul@paulmenage.org> +M: Li Zefan <lizefan@huawei.com> W: http://www.bullopensource.org/cpuset/ W: http://oss.sgi.com/projects/cpusets/ -S: Supported +S: Maintained F: Documentation/cgroups/cpusets.txt F: include/linux/cpuset.h F: kernel/cpuset.c @@ -2966,7 +2966,7 @@ S: Maintained F: drivers/net/ethernet/i825xx/eexpress.* ETHERNET BRIDGE -M: Stephen Hemminger <shemminger@vyatta.com> +M: Stephen Hemminger <stephen@networkplumber.org> L: bridge@lists.linux-foundation.org L: netdev@vger.kernel.org W: http://www.linuxfoundation.org/en/Net:Bridge @@ -3757,12 +3757,11 @@ S: Maintained F: drivers/i2c/i2c-stub.c I2C SUBSYSTEM -M: Wolfram Sang <w.sang@pengutronix.de> +M: Wolfram Sang <wsa@the-dreams.de> M: "Ben Dooks (embedded platforms)" <ben-linux@fluff.org> L: linux-i2c@vger.kernel.org W: http://i2c.wiki.kernel.org/ -T: quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-i2c/ -T: git git://git.pengutronix.de/git/wsa/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git S: Maintained F: Documentation/i2c/ F: drivers/i2c/ @@ -4905,7 +4904,7 @@ S: Maintained MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) M: Mirko Lindner <mlindner@marvell.com> -M: Stephen Hemminger <shemminger@vyatta.com> +M: Stephen Hemminger <stephen@networkplumber.org> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/marvell/sk* @@ -5180,7 +5179,7 @@ S: Supported F: drivers/infiniband/hw/nes/ NETEM NETWORK EMULATOR -M: Stephen Hemminger <shemminger@vyatta.com> +M: Stephen Hemminger <stephen@networkplumber.org> L: netem@lists.linux-foundation.org S: Maintained F: net/sched/sch_netem.c @@ -5778,15 +5777,6 @@ L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/muxes/i2c-mux-pca9541.c -PCA9564/PCA9665 I2C BUS DRIVER -M: Wolfram Sang <w.sang@pengutronix.de> -L: linux-i2c@vger.kernel.org -S: Maintained -F: drivers/i2c/algos/i2c-algo-pca.c -F: drivers/i2c/busses/i2c-pca-* -F: include/linux/i2c-algo-pca.h -F: include/linux/i2c-pca-platform.h - PCDP - PRIMARY CONSOLE AND DEBUG PORT M: Khalid Aziz <khalid@gonehiking.org> S: Maintained @@ -6598,7 +6588,7 @@ F: drivers/dma/dw_dmac_regs.h F: drivers/dma/dw_dmac.c TIMEKEEPING, NTP -M: John Stultz <johnstul@us.ibm.com> +M: John Stultz <john.stultz@linaro.org> M: Thomas Gleixner <tglx@linutronix.de> T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core S: Supported @@ -7088,7 +7078,7 @@ F: include/uapi/sound/ F: sound/ SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC) -M: Liam Girdwood <lrg@ti.com> +M: Liam Girdwood <lgirdwood@gmail.com> M: Mark Brown <broonie@opensource.wolfsonmicro.com> T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git L: alsa-devel@alsa-project.org (moderated for non-subscribers) @@ -7543,6 +7533,11 @@ F: drivers/net/team/ F: include/linux/if_team.h F: include/uapi/linux/if_team.h +TECHNOLOGIC SYSTEMS TS-5500 PLATFORM SUPPORT +M: Savoir-faire Linux Inc. <kernel@savoirfairelinux.com> +S: Maintained +F: arch/x86/platform/ts5500/ + TECHNOTREND USB IR RECEIVER M: Sean Young <sean@mess.org> L: linux-media@vger.kernel.org @@ -1,8 +1,8 @@ VERSION = 3 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc5 -NAME = Terrified Chipmunk +EXTRAVERSION = +NAME = Unicycling Gorilla # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -165,7 +165,8 @@ export srctree objtree VPATH # then ARCH is assigned, getting whatever value it gets normally, and # SUBARCH is subsequently ignored. -SUBARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ +SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ + -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ diff --git a/arch/Kconfig b/arch/Kconfig index 7f8f281..97fb7d0 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -76,6 +76,15 @@ config OPTPROBES depends on KPROBES && HAVE_OPTPROBES depends on !PREEMPT +config KPROBES_ON_FTRACE + def_bool y + depends on KPROBES && HAVE_KPROBES_ON_FTRACE + depends on DYNAMIC_FTRACE_WITH_REGS + help + If function tracer is enabled and the arch supports full + passing of pt_regs to function tracing, then kprobes can + optimize on top of function tracing. + config UPROBES bool "Transparent user-space probes (EXPERIMENTAL)" depends on UPROBE_EVENT && PERF_EVENTS @@ -158,6 +167,9 @@ config HAVE_KRETPROBES config HAVE_OPTPROBES bool +config HAVE_KPROBES_ON_FTRACE + bool + config HAVE_NMI_WATCHDOG bool # diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 9d5904c..9b504af 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -5,7 +5,6 @@ config ALPHA select HAVE_IDE select HAVE_OPROFILE select HAVE_SYSCALL_WRAPPERS - select HAVE_IRQ_WORK select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_DMA_ATTRS diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 14db93e..dbc1760 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1139,6 +1139,7 @@ struct rusage32 { SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) { struct rusage32 r; + cputime_t utime, stime; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN) return -EINVAL; @@ -1146,8 +1147,9 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) memset(&r, 0, sizeof(r)); switch (who) { case RUSAGE_SELF: - jiffies_to_timeval32(current->utime, &r.ru_utime); - jiffies_to_timeval32(current->stime, &r.ru_stime); + task_cputime(current, &utime, &stime); + jiffies_to_timeval32(utime, &r.ru_utime); + jiffies_to_timeval32(stime, &r.ru_stime); r.ru_minflt = current->min_flt; r.ru_majflt = current->maj_flt; break; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 67874b8..6c0900a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -36,7 +36,6 @@ config ARM select HAVE_GENERIC_HARDIRQS select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)) select HAVE_IDE if PCI || ISA || PCMCIA - select HAVE_IRQ_WORK select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZMA select HAVE_KERNEL_LZO @@ -1637,7 +1636,7 @@ config ARCH_NR_GPIO default 355 if ARCH_U8500 default 264 if MACH_H4700 default 512 if SOC_OMAP5 - default 288 if ARCH_VT8500 + default 288 if ARCH_VT8500 || ARCH_SUNXI default 0 help Maximum number of GPIOs in the system. diff --git a/arch/arm/boot/dts/dbx5x0.dtsi b/arch/arm/boot/dts/dbx5x0.dtsi index 63f2fbc..69140ba 100644 --- a/arch/arm/boot/dts/dbx5x0.dtsi +++ b/arch/arm/boot/dts/dbx5x0.dtsi @@ -170,10 +170,9 @@ gpio-bank = <8>; }; - pinctrl@80157000 { - // This is actually the PRCMU base address - reg = <0x80157000 0x2000>; - compatible = "stericsson,nmk_pinctrl"; + pinctrl { + compatible = "stericsson,nmk-pinctrl"; + prcm = <&prcmu>; }; usb@a03e0000 { @@ -190,9 +189,10 @@ interrupts = <0 25 0x4>; }; - prcmu@80157000 { + prcmu: prcmu@80157000 { compatible = "stericsson,db8500-prcmu"; reg = <0x80157000 0x1000>; + reg-names = "prcmu"; interrupts = <0 47 0x4>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index e61fdd4..f99f60d 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -16,4 +16,34 @@ memory { reg = <0x40000000 0x80000000>; }; + + soc { + pinctrl@01c20800 { + compatible = "allwinner,sun4i-a10-pinctrl"; + reg = <0x01c20800 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + uart0_pins_a: uart0@0 { + allwinner,pins = "PB22", "PB23"; + allwinner,function = "uart0"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; + + uart0_pins_b: uart0@1 { + allwinner,pins = "PF2", "PF4"; + allwinner,function = "uart0"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; + + uart1_pins_a: uart1@0 { + allwinner,pins = "PA10", "PA11"; + allwinner,function = "uart1"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; + }; + }; }; diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts index 498a091..4a1e45d 100644 --- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts +++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts @@ -24,6 +24,8 @@ soc { uart1: uart@01c28400 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_pins_b>; status = "okay"; }; }; diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi index 59a2d26..e112189 100644 --- a/arch/arm/boot/dts/sun5i-a13.dtsi +++ b/arch/arm/boot/dts/sun5i-a13.dtsi @@ -17,4 +17,27 @@ memory { reg = <0x40000000 0x20000000>; }; + + soc { + pinctrl@01c20800 { + compatible = "allwinner,sun5i-a13-pinctrl"; + reg = <0x01c20800 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + uart1_pins_a: uart1@0 { + allwinner,pins = "PE10", "PE11"; + allwinner,function = "uart1"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; + + uart1_pins_b: uart1@1 { + allwinner,pins = "PG3", "PG4"; + allwinner,function = "uart1"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; + }; + }; }; diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 36ae03a..87dfa90 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -351,6 +351,25 @@ void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq) irq_set_chained_handler(irq, gic_handle_cascade_irq); } +static u8 gic_get_cpumask(struct gic_chip_data *gic) +{ + void __iomem *base = gic_data_dist_base(gic); + u32 mask, i; + + for (i = mask = 0; i < 32; i += 4) { + mask = readl_relaxed(base + GIC_DIST_TARGET + i); + mask |= mask >> 16; + mask |= mask >> 8; + if (mask) + break; + } + + if (!mask) + pr_crit("GIC CPU mask not found - kernel will fail to boot.\n"); + + return mask; +} + static void __init gic_dist_init(struct gic_chip_data *gic) { unsigned int i; @@ -369,7 +388,9 @@ static void __init gic_dist_init(struct gic_chip_data *gic) /* * Set all global interrupts to this CPU only. */ - cpumask = readl_relaxed(base + GIC_DIST_TARGET + 0); + cpumask = gic_get_cpumask(gic); + cpumask |= cpumask << 8; + cpumask |= cpumask << 16; for (i = 32; i < gic_irqs; i += 4) writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4); @@ -400,7 +421,7 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic) * Get what the GIC says our CPU mask is. */ BUG_ON(cpu >= NR_GIC_CPU_IF); - cpu_mask = readl_relaxed(dist_base + GIC_DIST_TARGET + 0); + cpu_mask = gic_get_cpumask(gic); gic_cpu_map[cpu] = cpu_mask; /* diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 73cf03a..1c4df27 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -37,7 +37,7 @@ */ #define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) #define TASK_SIZE (UL(CONFIG_PAGE_OFFSET) - UL(0x01000000)) -#define TASK_UNMAPPED_BASE (UL(CONFIG_PAGE_OFFSET) / 3) +#define TASK_UNMAPPED_BASE ALIGN(TASK_SIZE / 3, SZ_16M) /* * The maximum size of a 26-bit user space task. diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h index 4eb6d00..86dff32 100644 --- a/arch/arm/include/asm/smp_scu.h +++ b/arch/arm/include/asm/smp_scu.h @@ -7,8 +7,14 @@ #ifndef __ASSEMBLER__ unsigned int scu_get_core_count(void __iomem *); -void scu_enable(void __iomem *); int scu_power_mode(void __iomem *, unsigned int); + +#ifdef CONFIG_SMP +void scu_enable(void __iomem *scu_base); +#else +static inline void scu_enable(void __iomem *scu_base) {} +#endif + #endif #endif diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index b9f015e..45eac87 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -75,7 +75,7 @@ void scu_enable(void __iomem *scu_base) int scu_power_mode(void __iomem *scu_base, unsigned int mode) { unsigned int val; - int cpu = cpu_logical_map(smp_processor_id()); + int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0); if (mode > 3 || mode == 1 || cpu > 3) return -EINVAL; diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index e103c29..85afb03 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -414,7 +414,7 @@ config MACH_EXYNOS4_DT select CPU_EXYNOS4210 select HAVE_SAMSUNG_KEYPAD if INPUT_KEYBOARD select PINCTRL - select PINCTRL_EXYNOS4 + select PINCTRL_EXYNOS select USE_OF help Machine support for Samsung Exynos4 machine with device tree enabled. diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index 981dc1e..e6c0612 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -28,6 +28,7 @@ #include <asm/arch_timer.h> #include <asm/cacheflush.h> +#include <asm/cputype.h> #include <asm/smp_plat.h> #include <asm/smp_twd.h> #include <asm/hardware/arm_timer.h> @@ -59,7 +60,7 @@ static void __init highbank_scu_map_io(void) void highbank_set_cpu_jump(int cpu, void *jump_addr) { - cpu = cpu_logical_map(cpu); + cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 0); writel(virt_to_phys(jump_addr), HB_JUMP_TABLE_VIRT(cpu)); __cpuc_flush_dcache_area(HB_JUMP_TABLE_VIRT(cpu), 16); outer_clean_range(HB_JUMP_TABLE_PHYS(cpu), diff --git a/arch/arm/mach-highbank/sysregs.h b/arch/arm/mach-highbank/sysregs.h index 70af9d1..5995df7 100644 --- a/arch/arm/mach-highbank/sysregs.h +++ b/arch/arm/mach-highbank/sysregs.h @@ -37,7 +37,7 @@ extern void __iomem *sregs_base; static inline void highbank_set_core_pwr(void) { - int cpu = cpu_logical_map(smp_processor_id()); + int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0); if (scu_base_addr) scu_power_mode(scu_base_addr, SCU_PM_POWEROFF); else @@ -46,7 +46,7 @@ static inline void highbank_set_core_pwr(void) static inline void highbank_clear_core_pwr(void) { - int cpu = cpu_logical_map(smp_processor_id()); + int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(smp_processor_id()), 0); if (scu_base_addr) scu_power_mode(scu_base_addr, SCU_PM_NORMAL); else diff --git a/arch/arm/mach-realview/include/mach/irqs-eb.h b/arch/arm/mach-realview/include/mach/irqs-eb.h index d6b5073..4475423 100644 --- a/arch/arm/mach-realview/include/mach/irqs-eb.h +++ b/arch/arm/mach-realview/include/mach/irqs-eb.h @@ -115,7 +115,7 @@ /* * Only define NR_IRQS if less than NR_IRQS_EB */ -#define NR_IRQS_EB (IRQ_EB_GIC_START + 96) +#define NR_IRQS_EB (IRQ_EB_GIC_START + 128) #if defined(CONFIG_MACH_REALVIEW_EB) \ && (!defined(NR_IRQS) || (NR_IRQS < NR_IRQS_EB)) diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig index 3fdd008..8709a39 100644 --- a/arch/arm/mach-sunxi/Kconfig +++ b/arch/arm/mach-sunxi/Kconfig @@ -7,3 +7,4 @@ config ARCH_SUNXI select PINCTRL select SPARSE_IRQ select SUNXI_TIMER + select PINCTRL_SUNXI
\ No newline at end of file diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig index 5dea906..3e5bbd0 100644 --- a/arch/arm/mach-ux500/Kconfig +++ b/arch/arm/mach-ux500/Kconfig @@ -11,6 +11,7 @@ config UX500_SOC_COMMON select COMMON_CLK select PINCTRL select PINCTRL_NOMADIK + select PINCTRL_ABX500 select PL310_ERRATA_753970 if CACHE_PL310 config UX500_SOC_DB8500 @@ -18,6 +19,11 @@ config UX500_SOC_DB8500 select CPU_FREQ_TABLE if CPU_FREQ select MFD_DB8500_PRCMU select PINCTRL_DB8500 + select PINCTRL_DB8540 + select PINCTRL_AB8500 + select PINCTRL_AB8505 + select PINCTRL_AB9540 + select PINCTRL_AB8540 select REGULATOR select REGULATOR_DB8500_PRCMU diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index d453522..b8781ca 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -90,26 +90,8 @@ static struct platform_device snowball_gpio_en_3v3_regulator_dev = { }, }; -static struct ab8500_gpio_platform_data ab8500_gpio_pdata = { +static struct abx500_gpio_platform_data ab8500_gpio_pdata = { .gpio_base = MOP500_AB8500_PIN_GPIO(1), - .irq_base = MOP500_AB8500_VIR_GPIO_IRQ_BASE, - /* config_reg is the initial configuration of ab8500 pins. - * The pins can be configured as GPIO or alt functions based - * on value present in GpioSel1 to GpioSel6 and AlternatFunction - * register. This is the array of 7 configuration settings. - * One has to compile time decide these settings. Below is the - * explanation of these setting - * GpioSel1 = 0x00 => Pins GPIO1 to GPIO8 are not used as GPIO - * GpioSel2 = 0x1E => Pins GPIO10 to GPIO13 are configured as GPIO - * GpioSel3 = 0x80 => Pin GPIO24 is configured as GPIO - * GpioSel4 = 0x01 => Pin GPIo25 is configured as GPIO - * GpioSel5 = 0x7A => Pins GPIO34, GPIO36 to GPIO39 are conf as GPIO - * GpioSel6 = 0x00 => Pins GPIO41 & GPIo42 are not configured as GPIO - * AlternaFunction = 0x00 => If Pins GPIO10 to 13 are not configured - * as GPIO then this register selectes the alternate fucntions - */ - .config_reg = {0x00, 0x1E, 0x80, 0x01, - 0x7A, 0x00, 0x00}, }; /* ab8500-codec */ diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 5b286e0..b80ad96 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -285,7 +285,7 @@ static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("st,nomadik-i2c", 0x80110000, "nmk-i2c.3", NULL), OF_DEV_AUXDATA("st,nomadik-i2c", 0x8012a000, "nmk-i2c.4", NULL), /* Requires device name bindings. */ - OF_DEV_AUXDATA("stericsson,nmk_pinctrl", U8500_PRCMU_BASE, + OF_DEV_AUXDATA("stericsson,nmk-pinctrl", U8500_PRCMU_BASE, "pinctrl-db8500", NULL), /* Requires clock name and DMA bindings. */ OF_DEV_AUXDATA("stericsson,ux500-msp-i2s", 0x80123000, diff --git a/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h b/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h index 7d34c52..d526dd8 100644 --- a/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h +++ b/arch/arm/mach-ux500/include/mach/irqs-board-mop500.h @@ -38,15 +38,7 @@ #define MOP500_STMPE1601_IRQ_END \ MOP500_STMPE1601_IRQ(STMPE_NR_INTERNAL_IRQS) -/* AB8500 virtual gpio IRQ */ -#define AB8500_VIR_GPIO_NR_IRQS 16 - -#define MOP500_AB8500_VIR_GPIO_IRQ_BASE \ - MOP500_STMPE1601_IRQ_END -#define MOP500_AB8500_VIR_GPIO_IRQ_END \ - (MOP500_AB8500_VIR_GPIO_IRQ_BASE + AB8500_VIR_GPIO_NR_IRQS) - -#define MOP500_NR_IRQS MOP500_AB8500_VIR_GPIO_IRQ_END +#define MOP500_NR_IRQS MOP500_STMPE1601_IRQ_END #define MOP500_IRQ_END MOP500_NR_IRQS diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 076c26d..dda3904 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -640,7 +640,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, if (is_coherent || nommu()) addr = __alloc_simple_buffer(dev, size, gfp, &page); - else if (gfp & GFP_ATOMIC) + else if (!(gfp & __GFP_WAIT)) addr = __alloc_from_pool(size, &page); else if (!IS_ENABLED(CONFIG_CMA)) addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f8f362a..75e915b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -21,7 +21,6 @@ config ARM64 select HAVE_GENERIC_DMA_COHERENT select HAVE_GENERIC_HARDIRQS select HAVE_HW_BREAKPOINT if PERF_EVENTS - select HAVE_IRQ_WORK select HAVE_MEMBLOCK select HAVE_PERF_EVENTS select IRQ_DOMAIN diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h index aaf5199..b3d18f9 100644 --- a/arch/avr32/include/asm/dma-mapping.h +++ b/arch/avr32/include/asm/dma-mapping.h @@ -336,4 +336,14 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) +/* drivers/base/dma-mapping.c */ +extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size); +extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size); + +#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s) +#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s) + #endif /* __ASM_AVR32_DMA_MAPPING_H */ diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index b6f3ad5..67e4aaa 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -24,7 +24,6 @@ config BLACKFIN select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_IDE - select HAVE_IRQ_WORK select HAVE_KERNEL_GZIP if RAMKERNEL select HAVE_KERNEL_BZIP2 if RAMKERNEL select HAVE_KERNEL_LZMA if RAMKERNEL @@ -38,7 +37,6 @@ config BLACKFIN select HAVE_GENERIC_HARDIRQS select GENERIC_ATOMIC64 select GENERIC_IRQ_PROBE - select IRQ_PER_CPU if SMP select USE_GENERIC_SMP_HELPERS if SMP select HAVE_NMI_WATCHDOG if NMI_WATCHDOG select GENERIC_SMP_IDLE_THREAD diff --git a/arch/blackfin/include/asm/dma-mapping.h b/arch/blackfin/include/asm/dma-mapping.h index bbf4610..054d9ec 100644 --- a/arch/blackfin/include/asm/dma-mapping.h +++ b/arch/blackfin/include/asm/dma-mapping.h @@ -154,4 +154,14 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, _dma_sync((dma_addr_t)vaddr, size, dir); } +/* drivers/base/dma-mapping.c */ +extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size); +extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size); + +#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s) +#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s) + #endif /* _BLACKFIN_DMA_MAPPING_H */ diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h index 3c69406..88bd0d8 100644 --- a/arch/c6x/include/asm/dma-mapping.h +++ b/arch/c6x/include/asm/dma-mapping.h @@ -89,4 +89,19 @@ extern void dma_free_coherent(struct device *, size_t, void *, dma_addr_t); #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent((d), (s), (h), (f)) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent((d), (s), (v), (h)) +/* Not supported for now */ +static inline int dma_mmap_coherent(struct device *dev, + struct vm_area_struct *vma, void *cpu_addr, + dma_addr_t dma_addr, size_t size) +{ + return -EINVAL; +} + +static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size) +{ + return -EINVAL; +} + #endif /* _ASM_C6X_DMA_MAPPING_H */ diff --git a/arch/cris/include/asm/dma-mapping.h b/arch/cris/include/asm/dma-mapping.h index 8588b2c..2f0f654 100644 --- a/arch/cris/include/asm/dma-mapping.h +++ b/arch/cris/include/asm/dma-mapping.h @@ -158,5 +158,15 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, { } +/* drivers/base/dma-mapping.c */ +extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size); +extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size); + +#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s) +#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s) + #endif diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig index 9d26264..17df48f 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -3,7 +3,6 @@ config FRV default y select HAVE_IDE select HAVE_ARCH_TRACEHOOK - select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select HAVE_UID16 select HAVE_GENERIC_HARDIRQS diff --git a/arch/frv/include/asm/dma-mapping.h b/arch/frv/include/asm/dma-mapping.h index dfb8110..1746a2b 100644 --- a/arch/frv/include/asm/dma-mapping.h +++ b/arch/frv/include/asm/dma-mapping.h @@ -132,4 +132,19 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size, flush_write_buffers(); } +/* Not supported for now */ +static inline int dma_mmap_coherent(struct device *dev, + struct vm_area_struct *vma, void *cpu_addr, + dma_addr_t dma_addr, size_t size) +{ + return -EINVAL; +} + +static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size) +{ + return -EINVAL; +} + #endif /* _ASM_DMA_MAPPING_H */ diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 0744f7d..e4decc6 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -12,9 +12,7 @@ config HEXAGON # select ARCH_WANT_OPTIONAL_GPIOLIB # select ARCH_REQUIRE_GPIOLIB # select HAVE_CLK - # select IRQ_PER_CPU # select GENERIC_PENDING_IRQ if SMP - select HAVE_IRQ_WORK select GENERIC_ATOMIC64 select HAVE_PERF_EVENTS select HAVE_GENERIC_HARDIRQS diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 3279646..00c2e88 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -29,7 +29,6 @@ config IA64 select ARCH_DISCARD_MEMBLOCK select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP - select IRQ_PER_CPU select GENERIC_IRQ_SHOW select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_HAVE_NMI_SAFE_CMPXCHG diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h index 7fcf7f0..e2d3f5b 100644 --- a/arch/ia64/include/asm/cputime.h +++ b/arch/ia64/include/asm/cputime.h @@ -11,99 +11,19 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * If we have CONFIG_VIRT_CPU_ACCOUNTING, we measure cpu time in nsec. + * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in nsec. * Otherwise we measure cpu time in jiffies using the generic definitions. */ #ifndef __IA64_CPUTIME_H #define __IA64_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING -#include <asm-generic/cputime.h> +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +# include <asm-generic/cputime.h> #else - -#include <linux/time.h> -#include <linux/jiffies.h> -#include <asm/processor.h> - -typedef u64 __nocast cputime_t; -typedef u64 __nocast cputime64_t; - -#define cputime_one_jiffy jiffies_to_cputime(1) - -/* - * Convert cputime <-> jiffies (HZ) - */ -#define cputime_to_jiffies(__ct) \ - ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) -#define jiffies_to_cputime(__jif) \ - (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ)) -#define cputime64_to_jiffies64(__ct) \ - ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) -#define jiffies64_to_cputime64(__jif) \ - (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ)) - -/* - * Convert cputime <-> microseconds - */ -#define cputime_to_usecs(__ct) \ - ((__force u64)(__ct) / NSEC_PER_USEC) -#define usecs_to_cputime(__usecs) \ - (__force cputime_t)((__usecs) * NSEC_PER_USEC) -#define usecs_to_cputime64(__usecs) \ - (__force cputime64_t)((__usecs) * NSEC_PER_USEC) - -/* - * Convert cputime <-> seconds - */ -#define cputime_to_secs(__ct) \ - ((__force u64)(__ct) / NSEC_PER_SEC) -#define secs_to_cputime(__secs) \ - (__force cputime_t)((__secs) * NSEC_PER_SEC) - -/* - * Convert cputime <-> timespec (nsec) - */ -static inline cputime_t timespec_to_cputime(const struct timespec *val) -{ - u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec; - return (__force cputime_t) ret; -} -static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) -{ - val->tv_sec = (__force u64) ct / NSEC_PER_SEC; - val->tv_nsec = (__force u64) ct % NSEC_PER_SEC; -} - -/* - * Convert cputime <-> timeval (msec) - */ -static inline cputime_t timeval_to_cputime(struct timeval *val) -{ - u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC; - return (__force cputime_t) ret; -} -static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) -{ - val->tv_sec = (__force u64) ct / NSEC_PER_SEC; - val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC; -} - -/* - * Convert cputime <-> clock (USER_HZ) - */ -#define cputime_to_clock_t(__ct) \ - ((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ)) -#define clock_t_to_cputime(__x) \ - (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ)) - -/* - * Convert cputime64 to clock. - */ -#define cputime64_to_clock_t(__ct) \ - cputime_to_clock_t((__force cputime_t)__ct) - +# include <asm/processor.h> +# include <asm-generic/cputime_nsecs.h> extern void arch_vtime_task_switch(struct task_struct *tsk); +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ #endif /* __IA64_CPUTIME_H */ diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index ff2ae41..020d655 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -31,7 +31,7 @@ struct thread_info { mm_segment_t addr_limit; /* user-level address space limit */ int preempt_count; /* 0=premptable, <0=BUG; will also serve as bh-counter */ struct restart_block restart_block; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE __u64 ac_stamp; __u64 ac_leave; __u64 ac_stime; @@ -69,7 +69,7 @@ struct thread_info { #define task_stack_page(tsk) ((void *)(tsk)) #define __HAVE_THREAD_FUNCTIONS -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #define setup_thread_stack(p, org) \ *task_thread_info(p) = *task_thread_info(org); \ task_thread_info(p)->ac_stime = 0; \ diff --git a/arch/ia64/include/asm/xen/minstate.h b/arch/ia64/include/asm/xen/minstate.h index c57fa91..00cf03e 100644 --- a/arch/ia64/include/asm/xen/minstate.h +++ b/arch/ia64/include/asm/xen/minstate.h @@ -1,5 +1,5 @@ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* read ar.itc in advance, and use it before leaving bank 0 */ #define XEN_ACCOUNT_GET_STAMP \ MOV_FROM_ITC(pUStk, p6, r20, r2); diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c index a48bd9a..46c9e30 100644 --- a/arch/ia64/kernel/asm-offsets.c +++ b/arch/ia64/kernel/asm-offsets.c @@ -41,7 +41,7 @@ void foo(void) DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count)); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE DEFINE(TI_AC_STAMP, offsetof(struct thread_info, ac_stamp)); DEFINE(TI_AC_LEAVE, offsetof(struct thread_info, ac_leave)); DEFINE(TI_AC_STIME, offsetof(struct thread_info, ac_stime)); diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 6bfd842..7a53530 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -724,7 +724,7 @@ GLOBAL_ENTRY(__paravirt_leave_syscall) #endif .global __paravirt_work_processed_syscall; __paravirt_work_processed_syscall: -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE adds r2=PT(LOADRS)+16,r12 MOV_FROM_ITC(pUStk, p9, r22, r19) // fetch time at leave adds r18=TI_FLAGS+IA64_TASK_SIZE,r13 @@ -762,7 +762,7 @@ __paravirt_work_processed_syscall: ld8 r29=[r2],16 // M0|1 load cr.ipsr ld8 r28=[r3],16 // M0|1 load cr.iip -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) add r14=TI_AC_LEAVE+IA64_TASK_SIZE,r13 ;; ld8 r30=[r2],16 // M0|1 load cr.ifs @@ -793,7 +793,7 @@ __paravirt_work_processed_syscall: ld8.fill r1=[r3],16 // M0|1 load r1 (pUStk) mov r17=1 // A ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) st1 [r15]=r17 // M2|3 #else (pUStk) st1 [r14]=r17 // M2|3 @@ -813,7 +813,7 @@ __paravirt_work_processed_syscall: shr.u r18=r19,16 // I0|1 get byte size of existing "dirty" partition COVER // B add current frame into dirty partition & set cr.ifs ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE mov r19=ar.bsp // M2 get new backing store pointer st8 [r14]=r22 // M save time at leave mov f10=f0 // F clear f10 @@ -948,7 +948,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) adds r16=PT(CR_IPSR)+16,r12 adds r17=PT(CR_IIP)+16,r12 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE .pred.rel.mutex pUStk,pKStk MOV_FROM_PSR(pKStk, r22, r29) // M2 read PSR now that interrupts are disabled MOV_FROM_ITC(pUStk, p9, r22, r29) // M fetch time at leave @@ -981,7 +981,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) ;; ld8.fill r12=[r16],16 ld8.fill r13=[r17],16 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) adds r3=TI_AC_LEAVE+IA64_TASK_SIZE,r18 #else (pUStk) adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18 @@ -989,7 +989,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) ;; ld8 r20=[r16],16 // ar.fpsr ld8.fill r15=[r17],16 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE (pUStk) adds r18=IA64_TASK_THREAD_ON_USTACK_OFFSET,r18 // deferred #endif ;; @@ -997,7 +997,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel) ld8.fill r2=[r17] (pUStk) mov r17=1 ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE // mmi_ : ld8 st1 shr;; mmi_ : st8 st1 shr;; // mib : mov add br -> mib : ld8 add br // bbb_ : br nop cover;; mbb_ : mov br cover;; diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index e662f17..c4cd45d 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -529,7 +529,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down) nop.i 0 ;; mov ar.rsc=0 // M2 set enforced lazy mode, pl 0, LE, loadrs=0 -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE MOV_FROM_ITC(p0, p6, r30, r23) // M get cycle for accounting #else nop.m 0 @@ -555,7 +555,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down) cmp.ne pKStk,pUStk=r0,r0 // A set pKStk <- 0, pUStk <- 1 br.call.sptk.many b7=ia64_syscall_setup // B ;; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE // mov.m r30=ar.itc is called in advance add r16=TI_AC_STAMP+IA64_TASK_SIZE,r2 add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r2 diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S index 4738ff7..9be4e49 100644 --- a/arch/ia64/kernel/head.S +++ b/arch/ia64/kernel/head.S @@ -1073,7 +1073,7 @@ END(ia64_native_sched_clock) sched_clock = ia64_native_sched_clock #endif -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE GLOBAL_ENTRY(cycle_to_cputime) alloc r16=ar.pfs,1,0,0,0 addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0 @@ -1091,7 +1091,7 @@ GLOBAL_ENTRY(cycle_to_cputime) shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT br.ret.sptk.many rp END(cycle_to_cputime) -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_IA64_BRL_EMU diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S index fa25689..689ffca 100644 --- a/arch/ia64/kernel/ivt.S +++ b/arch/ia64/kernel/ivt.S @@ -784,7 +784,7 @@ ENTRY(break_fault) (p8) adds r28=16,r28 // A switch cr.iip to next bundle (p9) adds r8=1,r8 // A increment ei to next slot -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE ;; mov b6=r30 // I0 setup syscall handler branch reg early #else @@ -801,7 +801,7 @@ ENTRY(break_fault) // /////////////////////////////////////////////////////////////////////// st1 [r16]=r0 // M2|3 clear current->thread.on_ustack flag -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE MOV_FROM_ITC(p0, p14, r30, r18) // M get cycle for accounting #else mov b6=r30 // I0 setup syscall handler branch reg early @@ -817,7 +817,7 @@ ENTRY(break_fault) cmp.eq p14,p0=r9,r0 // A are syscalls being traced/audited? br.call.sptk.many b7=ia64_syscall_setup // B 1: -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE // mov.m r30=ar.itc is called in advance, and r13 is current add r16=TI_AC_STAMP+IA64_TASK_SIZE,r13 // A add r17=TI_AC_LEAVE+IA64_TASK_SIZE,r13 // A @@ -1043,7 +1043,7 @@ END(ia64_syscall_setup) DBG_FAULT(16) FAULT(16) -#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE) +#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE) /* * There is no particular reason for this code to be here, other than * that there happens to be space here that would go unused otherwise. diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h index d56753a..cc82a7d 100644 --- a/arch/ia64/kernel/minstate.h +++ b/arch/ia64/kernel/minstate.h @@ -4,7 +4,7 @@ #include "entry.h" #include "paravirt_inst.h" -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* read ar.itc in advance, and use it before leaving bank 0 */ #define ACCOUNT_GET_STAMP \ (pUStk) mov.m r20=ar.itc; diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 88a7945..fbaac1a 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -77,7 +77,7 @@ static struct clocksource clocksource_itc = { }; static struct clocksource *itc_clocksource; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <linux/kernel_stat.h> @@ -136,13 +136,14 @@ void vtime_account_system(struct task_struct *tsk) account_system_time(tsk, 0, delta, delta); } +EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { account_idle_time(vtime_delta(tsk)); } -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static irqreturn_t timer_interrupt (int irq, void *dev_id) diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h index 3e6b844..292805f 100644 --- a/arch/m68k/include/asm/dma-mapping.h +++ b/arch/m68k/include/asm/dma-mapping.h @@ -115,4 +115,14 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t handle) #include <asm-generic/dma-mapping-broken.h> #endif +/* drivers/base/dma-mapping.c */ +extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size); +extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size); + +#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s) +#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s) + #endif /* _M68K_DMA_MAPPING_H */ diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index ae700f4..b0768a6 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -130,7 +130,6 @@ extern int handle_kernel_fault(struct pt_regs *regs); #define start_thread(_regs, _pc, _usp) \ do { \ (_regs)->pc = (_pc); \ - ((struct switch_stack *)(_regs))[-1].a6 = 0; \ setframeformat(_regs); \ if (current->mm) \ (_regs)->d5 = current->mm->start_data; \ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 2ac626a..9becc44 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,7 +4,6 @@ config MIPS select HAVE_GENERIC_DMA_COHERENT select HAVE_IDE select HAVE_OPROFILE - select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC select HAVE_ARCH_KGDB @@ -2161,7 +2160,6 @@ source "mm/Kconfig" config SMP bool "Multi-Processing support" depends on SYS_SUPPORTS_SMP - select IRQ_PER_CPU select USE_GENERIC_SMP_HELPERS help This enables support for systems with more than one CPU. If you have diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig index d7af29f..ba61192 100644 --- a/arch/mips/bcm47xx/Kconfig +++ b/arch/mips/bcm47xx/Kconfig @@ -8,8 +8,10 @@ config BCM47XX_SSB select SSB_DRIVER_EXTIF select SSB_EMBEDDED select SSB_B43_PCI_BRIDGE if PCI + select SSB_DRIVER_PCICORE if PCI select SSB_PCICORE_HOSTMODE if PCI select SSB_DRIVER_GPIO + select GPIOLIB default y help Add support for old Broadcom BCM47xx boards with Sonics Silicon Backplane support. @@ -25,6 +27,7 @@ config BCM47XX_BCMA select BCMA_HOST_PCI if PCI select BCMA_DRIVER_PCI_HOSTMODE if PCI select BCMA_DRIVER_GPIO + select GPIOLIB default y help Add support for new Broadcom BCM47xx boards with Broadcom specific Advanced Microcontroller Bus. diff --git a/arch/mips/cavium-octeon/executive/cvmx-l2c.c b/arch/mips/cavium-octeon/executive/cvmx-l2c.c index 9f883bf..33b7214 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-l2c.c +++ b/arch/mips/cavium-octeon/executive/cvmx-l2c.c @@ -30,6 +30,7 @@ * measurement, and debugging facilities. */ +#include <linux/compiler.h> #include <linux/irqflags.h> #include <asm/octeon/cvmx.h> #include <asm/octeon/cvmx-l2c.h> @@ -285,22 +286,22 @@ uint64_t cvmx_l2c_read_perf(uint32_t counter) */ static void fault_in(uint64_t addr, int len) { - volatile char *ptr; - volatile char dummy; + char *ptr; + /* * Adjust addr and length so we get all cache lines even for * small ranges spanning two cache lines. */ len += addr & CVMX_CACHE_LINE_MASK; addr &= ~CVMX_CACHE_LINE_MASK; - ptr = (volatile char *)cvmx_phys_to_ptr(addr); + ptr = cvmx_phys_to_ptr(addr); /* * Invalidate L1 cache to make sure all loads result in data * being in L2. */ CVMX_DCACHE_INVALIDATE; while (len > 0) { - dummy += *ptr; + ACCESS_ONCE(*ptr); len -= CVMX_CACHE_LINE_SIZE; ptr += CVMX_CACHE_LINE_SIZE; } diff --git a/arch/mips/include/asm/dsp.h b/arch/mips/include/asm/dsp.h index e9bfc08..7bfad05 100644 --- a/arch/mips/include/asm/dsp.h +++ b/arch/mips/include/asm/dsp.h @@ -16,7 +16,7 @@ #include <asm/mipsregs.h> #define DSP_DEFAULT 0x00000000 -#define DSP_MASK 0x3ff +#define DSP_MASK 0x3f #define __enable_dsp_hazard() \ do { \ diff --git a/arch/mips/include/asm/inst.h b/arch/mips/include/asm/inst.h index ab84064..33c34adb 100644 --- a/arch/mips/include/asm/inst.h +++ b/arch/mips/include/asm/inst.h @@ -353,6 +353,7 @@ union mips_instruction { struct u_format u_format; struct c_format c_format; struct r_format r_format; + struct p_format p_format; struct f_format f_format; struct ma_format ma_format; struct b_format b_format; diff --git a/arch/mips/include/asm/mach-pnx833x/war.h b/arch/mips/include/asm/mach-pnx833x/war.h index edaa06d..e410df4 100644 --- a/arch/mips/include/asm/mach-pnx833x/war.h +++ b/arch/mips/include/asm/mach-pnx833x/war.h @@ -21,4 +21,4 @@ #define R10000_LLSC_WAR 0 #define MIPS34K_MISSED_ITLB_WAR 0 -#endif /* __ASM_MIPS_MACH_PNX8550_WAR_H */ +#endif /* __ASM_MIPS_MACH_PNX833X_WAR_H */ diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index c631910..013d5f7 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -230,6 +230,7 @@ static inline void pud_clear(pud_t *pudp) #else #define pte_pfn(x) ((unsigned long)((x).pte >> _PFN_SHIFT)) #define pfn_pte(pfn, prot) __pte(((pfn) << _PFN_SHIFT) | pgprot_val(prot)) +#define pfn_pmd(pfn, prot) __pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot)) #endif #define __pgd_offset(address) pgd_index(address) diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild index a1a0452..77d4fb3 100644 --- a/arch/mips/include/uapi/asm/Kbuild +++ b/arch/mips/include/uapi/asm/Kbuild @@ -3,6 +3,7 @@ include include/uapi/asm-generic/Kbuild.asm header-y += auxvec.h header-y += bitsperlong.h +header-y += break.h header-y += byteorder.h header-y += cachectl.h header-y += errno.h diff --git a/arch/mips/include/asm/break.h b/arch/mips/include/uapi/asm/break.h index 9161e68..9161e68 100644 --- a/arch/mips/include/asm/break.h +++ b/arch/mips/include/uapi/asm/break.h diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 6a2d758..83fa146 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -25,6 +25,12 @@ #define MCOUNT_OFFSET_INSNS 4 #endif +/* Arch override because MIPS doesn't need to run this from stop_machine() */ +void arch_ftrace_update_code(int command) +{ + ftrace_modify_all_code(command); +} + /* * Check if the address is in kernel space * @@ -89,6 +95,24 @@ static int ftrace_modify_code(unsigned long ip, unsigned int new_code) return 0; } +#ifndef CONFIG_64BIT +static int ftrace_modify_code_2(unsigned long ip, unsigned int new_code1, + unsigned int new_code2) +{ + int faulted; + + safe_store_code(new_code1, ip, faulted); + if (unlikely(faulted)) + return -EFAULT; + ip += 4; + safe_store_code(new_code2, ip, faulted); + if (unlikely(faulted)) + return -EFAULT; + flush_icache_range(ip, ip + 8); /* original ip + 12 */ + return 0; +} +#endif + /* * The details about the calling site of mcount on MIPS * @@ -131,8 +155,18 @@ int ftrace_make_nop(struct module *mod, * needed. */ new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F; - +#ifdef CONFIG_64BIT return ftrace_modify_code(ip, new); +#else + /* + * On 32 bit MIPS platforms, gcc adds a stack adjust + * instruction in the delay slot after the branch to + * mcount and expects mcount to restore the sp on return. + * This is based on a legacy API and does nothing but + * waste instructions so it's being removed at runtime. + */ + return ftrace_modify_code_2(ip, new, INSN_NOP); +#endif } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 4c968e7..1658676 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -46,9 +46,8 @@ PTR_L a5, PT_R9(sp) PTR_L a6, PT_R10(sp) PTR_L a7, PT_R11(sp) - PTR_ADDIU sp, PT_SIZE #else - PTR_ADDIU sp, (PT_SIZE + 8) + PTR_ADDIU sp, PT_SIZE #endif .endm @@ -69,7 +68,9 @@ NESTED(ftrace_caller, PT_SIZE, ra) .globl _mcount _mcount: b ftrace_stub - nop + addiu sp,sp,8 + + /* When tracing is activated, it calls ftrace_caller+8 (aka here) */ lw t1, function_trace_stop bnez t1, ftrace_stub nop diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index eec690a..147cec1 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -705,7 +705,7 @@ static int vpe_run(struct vpe * v) printk(KERN_WARNING "VPE loader: TC %d is already in use.\n", - t->index); + v->tc->index); return -ENOEXEC; } } else { diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index f36acd1..a7935bf 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -408,7 +408,7 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent) #endif /* tell oprofile which irq to use */ - cp0_perfcount_irq = LTQ_PERF_IRQ; + cp0_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ); /* * if the timer irq is not one of the mips irqs we need to diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c index dc81ca8..288f795 100644 --- a/arch/mips/lib/delay.c +++ b/arch/mips/lib/delay.c @@ -21,7 +21,7 @@ void __delay(unsigned long loops) " .set noreorder \n" " .align 3 \n" "1: bnez %0, 1b \n" -#if __SIZEOF_LONG__ == 4 +#if BITS_PER_LONG == 32 " subu %0, 1 \n" #else " dsubu %0, 1 \n" diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c index 7657fd2..cacfd31 100644 --- a/arch/mips/mm/ioremap.c +++ b/arch/mips/mm/ioremap.c @@ -190,9 +190,3 @@ void __iounmap(const volatile void __iomem *addr) EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(__iounmap); - -int __virt_addr_valid(const volatile void *kaddr) -{ - return pfn_valid(PFN_DOWN(virt_to_phys(kaddr))); -} -EXPORT_SYMBOL_GPL(__virt_addr_valid); diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index d9be754..7e5fe27 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -192,3 +192,9 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return ret; } + +int __virt_addr_valid(const volatile void *kaddr) +{ + return pfn_valid(PFN_DOWN(virt_to_phys(kaddr))); +} +EXPORT_SYMBOL_GPL(__virt_addr_valid); diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c index 4e7f49d..c5ce699 100644 --- a/arch/mips/netlogic/xlr/setup.c +++ b/arch/mips/netlogic/xlr/setup.c @@ -193,8 +193,11 @@ static void nlm_init_node(void) void __init prom_init(void) { - int i, *argv, *envp; /* passed as 32 bit ptrs */ + int *argv, *envp; /* passed as 32 bit ptrs */ struct psb_info *prom_infop; +#ifdef CONFIG_SMP + int i; +#endif /* truncate to 32 bit and sign extend all args */ argv = (int *)(long)(int)fw_arg1; diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c index 1552522..6eaa4f2 100644 --- a/arch/mips/pci/pci-ar71xx.c +++ b/arch/mips/pci/pci-ar71xx.c @@ -24,7 +24,7 @@ #include <asm/mach-ath79/pci.h> #define AR71XX_PCI_MEM_BASE 0x10000000 -#define AR71XX_PCI_MEM_SIZE 0x08000000 +#define AR71XX_PCI_MEM_SIZE 0x07000000 #define AR71XX_PCI_WIN0_OFFS 0x10000000 #define AR71XX_PCI_WIN1_OFFS 0x11000000 diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c index 86d77a6..c11c75b 100644 --- a/arch/mips/pci/pci-ar724x.c +++ b/arch/mips/pci/pci-ar724x.c @@ -21,7 +21,7 @@ #define AR724X_PCI_CTRL_SIZE 0x100 #define AR724X_PCI_MEM_BASE 0x10000000 -#define AR724X_PCI_MEM_SIZE 0x08000000 +#define AR724X_PCI_MEM_SIZE 0x04000000 #define AR724X_PCI_REG_RESET 0x18 #define AR724X_PCI_REG_INT_STATUS 0x4c diff --git a/arch/mn10300/include/asm/dma-mapping.h b/arch/mn10300/include/asm/dma-mapping.h index c1be439..a18abfc 100644 --- a/arch/mn10300/include/asm/dma-mapping.h +++ b/arch/mn10300/include/asm/dma-mapping.h @@ -168,4 +168,19 @@ void dma_cache_sync(void *vaddr, size_t size, mn10300_dcache_flush_inv(); } +/* Not supported for now */ +static inline int dma_mmap_coherent(struct device *dev, + struct vm_area_struct *vma, void *cpu_addr, + dma_addr_t dma_addr, size_t size) +{ + return -EINVAL; +} + +static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size) +{ + return -EINVAL; +} + #endif diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index b77feff..a32e34e 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -9,14 +9,12 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG - select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select GENERIC_ATOMIC64 if !64BIT select HAVE_GENERIC_HARDIRQS select BROKEN_RODATA select GENERIC_IRQ_PROBE select GENERIC_PCI_IOMAP - select IRQ_PER_CPU select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_STRNCPY_FROM_USER diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index 467bbd5..106b395 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -238,4 +238,19 @@ void * sba_get_iommu(struct parisc_device *dev); /* At the moment, we panic on error for IOMMU resource exaustion */ #define dma_mapping_error(dev, x) 0 +/* This API cannot be supported on PA-RISC */ +static inline int dma_mmap_coherent(struct device *dev, + struct vm_area_struct *vma, void *cpu_addr, + dma_addr_t dma_addr, size_t size) +{ + return -EINVAL; +} + +static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size) +{ + return -EINVAL; +} + #endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 17903f1..561ccca 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -118,14 +118,12 @@ config PPC select HAVE_SYSCALL_WRAPPERS if PPC64 select GENERIC_ATOMIC64 if PPC32 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64 select HAVE_GENERIC_HARDIRQS select ARCH_WANT_IPC_PARSE_VERSION select SPARSE_IRQ - select IRQ_PER_CPU select IRQ_DOMAIN select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig index 29bb11e..4f35fc4 100644 --- a/arch/powerpc/configs/chroma_defconfig +++ b/arch/powerpc/configs/chroma_defconfig @@ -1,6 +1,6 @@ CONFIG_PPC64=y CONFIG_PPC_BOOK3E_64=y -# CONFIG_VIRT_CPU_ACCOUNTING is not set +# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set CONFIG_SMP=y CONFIG_NR_CPUS=256 CONFIG_EXPERIMENTAL=y diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig index 88fa5c4..f7df836 100644 --- a/arch/powerpc/configs/corenet64_smp_defconfig +++ b/arch/powerpc/configs/corenet64_smp_defconfig @@ -1,6 +1,6 @@ CONFIG_PPC64=y CONFIG_PPC_BOOK3E_64=y -# CONFIG_VIRT_CPU_ACCOUNTING is not set +# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set CONFIG_SMP=y CONFIG_NR_CPUS=2 CONFIG_EXPERIMENTAL=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 840a2c2..bcedeea 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -1,6 +1,6 @@ CONFIG_PPC64=y CONFIG_ALTIVEC=y -# CONFIG_VIRT_CPU_ACCOUNTING is not set +# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set CONFIG_SMP=y CONFIG_NR_CPUS=2 CONFIG_EXPERIMENTAL=y diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 483733b..607559a 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -8,7 +8,7 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * If we have CONFIG_VIRT_CPU_ACCOUNTING, we measure cpu time in + * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in * the same units as the timebase. Otherwise we measure cpu time * in jiffies using the generic definitions. */ @@ -16,7 +16,7 @@ #ifndef __POWERPC_CPUTIME_H #define __POWERPC_CPUTIME_H -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #include <asm-generic/cputime.h> #ifdef __KERNEL__ static inline void setup_cputime_one_jiffy(void) { } @@ -231,5 +231,5 @@ static inline cputime_t clock_t_to_cputime(const unsigned long clk) static inline void arch_vtime_task_switch(struct task_struct *tsk) { } #endif /* __KERNEL__ */ -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #endif /* __POWERPC_CPUTIME_H */ diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 531fe0c..b1e7f2a 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -145,7 +145,7 @@ struct dtl_entry { extern struct kmem_cache *dtl_cache; /* - * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls + * When CONFIG_VIRT_CPU_ACCOUNTING_NATIVE = y, the cpu accounting code controls * reading from the dispatch trace log. If other code wants to consume * DTL entries, it can set this pointer to a function that will get * called once for each DTL entry that gets processed. diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 9710be3..136bba6 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -11,6 +11,7 @@ #include <linux/types.h> #include <asm/hw_irq.h> +#include <linux/device.h> #define MAX_HWEVENTS 8 #define MAX_EVENT_ALTERNATIVES 8 @@ -35,6 +36,7 @@ struct power_pmu { void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); int (*limited_pmc_event)(u64 event_id); u32 flags; + const struct attribute_group **attr_groups; int n_generic; int *generic_events; int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] @@ -109,3 +111,27 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs); * If an event_id is not subject to the constraint expressed by a particular * field, then it will have 0 in both the mask and value for that field. */ + +extern ssize_t power_events_sysfs_show(struct device *dev, + struct device_attribute *attr, char *page); + +/* + * EVENT_VAR() is same as PMU_EVENT_VAR with a suffix. + * + * Having a suffix allows us to have aliases in sysfs - eg: the generic + * event 'cpu-cycles' can have two entries in sysfs: 'cpu-cycles' and + * 'PM_CYC' where the latter is the name by which the event is known in + * POWER CPU specification. + */ +#define EVENT_VAR(_id, _suffix) event_attr_##_id##_suffix +#define EVENT_PTR(_id, _suffix) &EVENT_VAR(_id, _suffix).attr.attr + +#define EVENT_ATTR(_name, _id, _suffix) \ + PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id, \ + power_events_sysfs_show) + +#define GENERIC_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _g) +#define GENERIC_EVENT_PTR(_id) EVENT_PTR(_id, _g) + +#define POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(PM_##_name, _id, _p) +#define POWER_EVENT_PTR(_id) EVENT_PTR(_id, _p) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index ea2a86e..2d0e1f5 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -24,7 +24,7 @@ * user_time and system_time fields in the paca. */ -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #define ACCOUNT_CPU_USER_ENTRY(ra, rb) #define ACCOUNT_CPU_USER_EXIT(ra, rb) #define ACCOUNT_STOLEN_TIME @@ -70,7 +70,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #endif /* CONFIG_PPC_SPLPAR */ -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ /* * Macros for storing registers into and loading registers from diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index d22e73e..e514de5 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -439,6 +439,8 @@ ret_from_fork: ret_from_kernel_thread: REST_NVGPRS(r1) bl schedule_tail + li r3,0 + stw r3,0(r1) mtlr r14 mr r3,r15 PPC440EP_ERR42 diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index b310a05..ac05701 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -94,7 +94,7 @@ system_call_common: addi r9,r1,STACK_FRAME_OVERHEAD ld r11,exception_marker@toc(r2) std r11,-16(r9) /* "regshere" marker */ -#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR) +#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR) BEGIN_FW_FTR_SECTION beq 33f /* if from user, see if there are any DTL entries to process */ @@ -110,7 +110,7 @@ BEGIN_FW_FTR_SECTION addi r9,r1,STACK_FRAME_OVERHEAD 33: END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) -#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */ /* * A syscall should always be called with interrupts enabled @@ -664,6 +664,19 @@ resume_kernel: ld r4,TI_FLAGS(r9) andi. r0,r4,_TIF_NEED_RESCHED bne 1b + + /* + * arch_local_irq_restore() from preempt_schedule_irq above may + * enable hard interrupt but we really should disable interrupts + * when we return from the interrupt, and so that we don't get + * interrupted after loading SRR0/1. + */ +#ifdef CONFIG_PPC_BOOK3E + wrteei 0 +#else + ld r10,PACAKMSR(r13) /* Get kernel MSR without EE */ + mtmsrd r10,1 /* Update machine state */ +#endif /* CONFIG_PPC_BOOK3E */ #endif /* CONFIG_PREEMPT */ .globl fast_exc_return_irq diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index c470a40..a7bc752 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -154,12 +154,12 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs) static int kgdb_singlestep(struct pt_regs *regs) { struct thread_info *thread_info, *exception_thread_info; - struct thread_info *backup_current_thread_info = \ - (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); + struct thread_info *backup_current_thread_info; if (user_mode(regs)) return 0; + backup_current_thread_info = (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); /* * On Book E and perhaps other processors, singlestep is handled on * the critical exception stack. This causes current_thread_info() @@ -185,6 +185,7 @@ static int kgdb_singlestep(struct pt_regs *regs) /* Restore current_thread_info lastly. */ memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info); + kfree(backup_current_thread_info); return 1; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 6f6b1cc..f77fa22 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -143,7 +143,7 @@ EXPORT_SYMBOL_GPL(ppc_proc_freq); unsigned long ppc_tb_freq; EXPORT_SYMBOL_GPL(ppc_tb_freq); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Factors for converting from cputime_t (timebase ticks) to * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds). @@ -347,6 +347,7 @@ void vtime_account_system(struct task_struct *tsk) if (stolen) account_steal_time(stolen); } +EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk) { @@ -377,7 +378,7 @@ void vtime_account_user(struct task_struct *tsk) account_user_time(tsk, utime, utimescaled); } -#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ +#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #define calc_cputime_factors() #endif @@ -494,10 +495,15 @@ void timer_interrupt(struct pt_regs * regs) set_dec(DECREMENTER_MAX); /* Some implementations of hotplug will get timer interrupts while - * offline, just ignore these + * offline, just ignore these and we also need to set + * decrementers_next_tb as MAX to make sure __check_irq_replay + * don't replay timer interrupt when return, otherwise we'll trap + * here infinitely :( */ - if (!cpu_online(smp_processor_id())) + if (!cpu_online(smp_processor_id())) { + *next_tb = ~(u64)0; return; + } /* Conditionally hard-enable interrupts now that the DEC has been * bumped to its maximum value @@ -663,7 +669,7 @@ int update_persistent_clock(struct timespec now) struct rtc_time tm; if (!ppc_md.set_rtc_time) - return 0; + return -ENODEV; to_tm(now.tv_sec + 1 + timezone_offset, &tm); tm.tm_year -= 1900; diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 5658508..7443481 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -115,11 +115,13 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) sldi r29,r5,SID_SHIFT - VPN_SHIFT rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT) or r29,r28,r29 - - /* Calculate hash value for primary slot and store it in r28 */ - rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */ - rldicl r0,r3,64-12,48 /* (ea >> 12) & 0xffff */ - xor r28,r5,r0 + /* + * Calculate hash value for primary slot and store it in r28 + * r3 = va, r5 = vsid + * r0 = (va >> 12) & ((1ul << (28 - 12)) -1) + */ + rldicl r0,r3,64-12,48 + xor r28,r5,r0 /* hash */ b 4f 3: /* Calc vpn and put it in r29 */ @@ -130,11 +132,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* * calculate hash value for primary slot and * store it in r28 for 1T segment + * r3 = va, r5 = vsid */ - rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */ - clrldi r5,r5,40 /* vsid & 0xffffff */ - rldicl r0,r3,64-12,36 /* (ea >> 12) & 0xfffffff */ - xor r28,r28,r5 + sldi r28,r5,25 /* vsid << 25 */ + /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */ + rldicl r0,r3,64-12,36 + xor r28,r28,r5 /* vsid ^ ( vsid << 25) */ xor r28,r28,r0 /* hash */ /* Convert linux PTE bits into HW equivalents */ @@ -407,11 +410,13 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) */ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT) or r29,r28,r29 - - /* Calculate hash value for primary slot and store it in r28 */ - rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */ - rldicl r0,r3,64-12,48 /* (ea >> 12) & 0xffff */ - xor r28,r5,r0 + /* + * Calculate hash value for primary slot and store it in r28 + * r3 = va, r5 = vsid + * r0 = (va >> 12) & ((1ul << (28 - 12)) -1) + */ + rldicl r0,r3,64-12,48 + xor r28,r5,r0 /* hash */ b 4f 3: /* Calc vpn and put it in r29 */ @@ -426,11 +431,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) /* * Calculate hash value for primary slot and * store it in r28 for 1T segment + * r3 = va, r5 = vsid */ - rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */ - clrldi r5,r5,40 /* vsid & 0xffffff */ - rldicl r0,r3,64-12,36 /* (ea >> 12) & 0xfffffff */ - xor r28,r28,r5 + sldi r28,r5,25 /* vsid << 25 */ + /* r0 = (va >> 12) & ((1ul << (40 - 12)) -1) */ + rldicl r0,r3,64-12,36 + xor r28,r28,r5 /* vsid ^ ( vsid << 25) */ xor r28,r28,r0 /* hash */ /* Convert linux PTE bits into HW equivalents */ @@ -752,25 +758,27 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT) or r29,r28,r29 - /* Calculate hash value for primary slot and store it in r28 */ - rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */ - rldicl r0,r3,64-16,52 /* (ea >> 16) & 0xfff */ - xor r28,r5,r0 + /* Calculate hash value for primary slot and store it in r28 + * r3 = va, r5 = vsid + * r0 = (va >> 16) & ((1ul << (28 - 16)) -1) + */ + rldicl r0,r3,64-16,52 + xor r28,r5,r0 /* hash */ b 4f 3: /* Calc vpn and put it in r29 */ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT) or r29,r28,r29 - /* * calculate hash value for primary slot and * store it in r28 for 1T segment + * r3 = va, r5 = vsid */ - rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */ - clrldi r5,r5,40 /* vsid & 0xffffff */ - rldicl r0,r3,64-16,40 /* (ea >> 16) & 0xffffff */ - xor r28,r28,r5 + sldi r28,r5,25 /* vsid << 25 */ + /* r0 = (va >> 16) & ((1ul << (40 - 16)) -1) */ + rldicl r0,r3,64-16,40 + xor r28,r28,r5 /* vsid ^ ( vsid << 25) */ xor r28,r28,r0 /* hash */ /* Convert linux PTE bits into HW equivalents */ diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c index 315f949..f444b94 100644 --- a/arch/powerpc/oprofile/op_model_power4.c +++ b/arch/powerpc/oprofile/op_model_power4.c @@ -52,7 +52,7 @@ static int power7_marked_instr_event(u64 mmcr1) for (pmc = 0; pmc < 4; pmc++) { psel = mmcr1 & (OPROFILE_PM_PMCSEL_MSK << (OPROFILE_MAX_PMC_NUM - pmc) - * OPROFILE_MAX_PMC_NUM); + * OPROFILE_PMSEL_FIELD_WIDTH); psel = (psel >> ((OPROFILE_MAX_PMC_NUM - pmc) * OPROFILE_PMSEL_FIELD_WIDTH)) & ~1ULL; unit = mmcr1 & (OPROFILE_PM_UNIT_MSK diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index aa2465e..fa476d5 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1305,6 +1305,16 @@ static int power_pmu_event_idx(struct perf_event *event) return event->hw.idx; } +ssize_t power_events_sysfs_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct perf_pmu_events_attr *pmu_attr; + + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); + + return sprintf(page, "event=0x%02llx\n", pmu_attr->id); +} + struct pmu power_pmu = { .pmu_enable = power_pmu_enable, .pmu_disable = power_pmu_disable, @@ -1537,6 +1547,8 @@ int __cpuinit register_power_pmu(struct power_pmu *pmu) pr_info("%s performance monitor hardware support registered\n", pmu->name); + power_pmu.attr_groups = ppmu->attr_groups; + #ifdef MSR_HV /* * Use FCHV to ignore kernel events if MSR.HV is set. diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index 2ee01e3..b554879 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -51,6 +51,18 @@ #define MMCR1_PMCSEL_MSK 0xff /* + * Power7 event codes. + */ +#define PME_PM_CYC 0x1e +#define PME_PM_GCT_NOSLOT_CYC 0x100f8 +#define PME_PM_CMPLU_STALL 0x4000a +#define PME_PM_INST_CMPL 0x2 +#define PME_PM_LD_REF_L1 0xc880 +#define PME_PM_LD_MISS_L1 0x400f0 +#define PME_PM_BRU_FIN 0x10068 +#define PME_PM_BRU_MPRED 0x400f6 + +/* * Layout of constraint bits: * 6666555555555544444444443333333333222222222211111111110000000000 * 3210987654321098765432109876543210987654321098765432109876543210 @@ -307,14 +319,14 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[]) } static int power7_generic_events[] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x1e, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */ - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a, /* CMPLU_STALL */ - [PERF_COUNT_HW_INSTRUCTIONS] = 2, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880, /* LD_REF_L1_LSU*/ - [PERF_COUNT_HW_CACHE_MISSES] = 0x400f0, /* LD_MISS_L1 */ - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x10068, /* BRU_FIN */ - [PERF_COUNT_HW_BRANCH_MISSES] = 0x400f6, /* BR_MPRED */ + [PERF_COUNT_HW_CPU_CYCLES] = PME_PM_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PME_PM_GCT_NOSLOT_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PME_PM_CMPLU_STALL, + [PERF_COUNT_HW_INSTRUCTIONS] = PME_PM_INST_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PME_PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PME_PM_LD_MISS_L1, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PME_PM_BRU_FIN, + [PERF_COUNT_HW_BRANCH_MISSES] = PME_PM_BRU_MPRED, }; #define C(x) PERF_COUNT_HW_CACHE_##x @@ -362,6 +374,57 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { }, }; + +GENERIC_EVENT_ATTR(cpu-cycles, CYC); +GENERIC_EVENT_ATTR(stalled-cycles-frontend, GCT_NOSLOT_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-backend, CMPLU_STALL); +GENERIC_EVENT_ATTR(instructions, INST_CMPL); +GENERIC_EVENT_ATTR(cache-references, LD_REF_L1); +GENERIC_EVENT_ATTR(cache-misses, LD_MISS_L1); +GENERIC_EVENT_ATTR(branch-instructions, BRU_FIN); +GENERIC_EVENT_ATTR(branch-misses, BRU_MPRED); + +POWER_EVENT_ATTR(CYC, CYC); +POWER_EVENT_ATTR(GCT_NOSLOT_CYC, GCT_NOSLOT_CYC); +POWER_EVENT_ATTR(CMPLU_STALL, CMPLU_STALL); +POWER_EVENT_ATTR(INST_CMPL, INST_CMPL); +POWER_EVENT_ATTR(LD_REF_L1, LD_REF_L1); +POWER_EVENT_ATTR(LD_MISS_L1, LD_MISS_L1); +POWER_EVENT_ATTR(BRU_FIN, BRU_FIN) +POWER_EVENT_ATTR(BRU_MPRED, BRU_MPRED); + +static struct attribute *power7_events_attr[] = { + GENERIC_EVENT_PTR(CYC), + GENERIC_EVENT_PTR(GCT_NOSLOT_CYC), + GENERIC_EVENT_PTR(CMPLU_STALL), + GENERIC_EVENT_PTR(INST_CMPL), + GENERIC_EVENT_PTR(LD_REF_L1), + GENERIC_EVENT_PTR(LD_MISS_L1), + GENERIC_EVENT_PTR(BRU_FIN), + GENERIC_EVENT_PTR(BRU_MPRED), + + POWER_EVENT_PTR(CYC), + POWER_EVENT_PTR(GCT_NOSLOT_CYC), + POWER_EVENT_PTR(CMPLU_STALL), + POWER_EVENT_PTR(INST_CMPL), + POWER_EVENT_PTR(LD_REF_L1), + POWER_EVENT_PTR(LD_MISS_L1), + POWER_EVENT_PTR(BRU_FIN), + POWER_EVENT_PTR(BRU_MPRED), + NULL +}; + + +static struct attribute_group power7_pmu_events_group = { + .name = "events", + .attrs = power7_events_attr, +}; + +static const struct attribute_group *power7_pmu_attr_groups[] = { + &power7_pmu_events_group, + NULL, +}; + static struct power_pmu power7_pmu = { .name = "POWER7", .n_counter = 6, @@ -373,6 +436,7 @@ static struct power_pmu power7_pmu = { .get_alternatives = power7_get_alternatives, .disable_pmc = power7_disable_pmc, .flags = PPMU_ALT_SIPR, + .attr_groups = power7_pmu_attr_groups, .n_generic = ARRAY_SIZE(power7_generic_events), .generic_events = power7_generic_events, .cache_events = &power7_cache_events, diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 25db92a..4931838 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -24,6 +24,7 @@ #include <linux/errno.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/slab.h> diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c index 95d0017..890f30e 100644 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ b/arch/powerpc/platforms/pasemi/cpufreq.c @@ -236,6 +236,13 @@ out: static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy) { + /* + * We don't support CPU hotplug. Don't unmap after the system + * has already made it to a running state. + */ + if (system_state != SYSTEM_BOOTING) + return 0; + if (sdcasr_mapbase) iounmap(sdcasr_mapbase); if (sdcpwr_mapbase) diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index a764854..0cc0ac0 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -57,7 +57,7 @@ static u8 dtl_event_mask = 0x7; */ static int dtl_buf_entries = N_DISPATCH_LOG; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct dtl_ring { u64 write_index; struct dtl_entry *write_ptr; @@ -142,7 +142,7 @@ static u64 dtl_current_index(struct dtl *dtl) return per_cpu(dtl_rings, dtl->cpu).write_index; } -#else /* CONFIG_VIRT_CPU_ACCOUNTING */ +#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static int dtl_start(struct dtl *dtl) { @@ -188,7 +188,7 @@ static u64 dtl_current_index(struct dtl *dtl) { return lppaca_of(dtl->cpu).dtl_idx; } -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static int dtl_enable(struct dtl *dtl) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index ca55882..527e12c 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -281,7 +281,7 @@ static struct notifier_block pci_dn_reconfig_nb = { struct kmem_cache *dtl_cache; -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Allocate space for the dispatch trace log for all possible cpus * and register the buffers with the hypervisor. This is used for @@ -332,12 +332,12 @@ static int alloc_dispatch_logs(void) return 0; } -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline int alloc_dispatch_logs(void) { return 0; } -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static int alloc_dispatch_log_kmem_cache(void) { diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b5ea38c..c15ba7d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -78,7 +78,6 @@ config S390 select HAVE_KVM if 64BIT select HAVE_ARCH_TRACEHOOK select INIT_ALL_POSSIBLE - select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select ARCH_HAVE_NMI_SAFE_CMPXCHG select HAVE_DEBUG_KMEMLEAK diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index c1d7930..098adbb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1365,6 +1365,18 @@ static inline void pmdp_invalidate(struct vm_area_struct *vma, __pmd_idte(address, pmdp); } +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + if (pmd_write(pmd)) { + __pmd_idte(address, pmdp); + set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd)); + } +} + static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot) { pmd_t __pmd; diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index a5f4f5a..0aa98db 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -120,6 +120,9 @@ static int s390_next_ktime(ktime_t expires, nsecs = ktime_to_ns(ktime_add(timespec_to_ktime(ts), expires)); do_div(nsecs, 125); S390_lowcore.clock_comparator = sched_clock_base_cc + (nsecs << 9); + /* Program the maximum value if we have an overflow (== year 2042) */ + if (unlikely(S390_lowcore.clock_comparator < sched_clock_base_cc)) + S390_lowcore.clock_comparator = -1ULL; set_clock_comparator(S390_lowcore.clock_comparator); return 0; } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index e84b8b6..ce9cc5a 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -127,7 +127,7 @@ void vtime_account_user(struct task_struct *tsk) * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -void vtime_account(struct task_struct *tsk) +void vtime_account_irq_enter(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); u64 timer, system; @@ -145,10 +145,10 @@ void vtime_account(struct task_struct *tsk) virt_timer_forward(system); } -EXPORT_SYMBOL_GPL(vtime_account); +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); void vtime_account_system(struct task_struct *tsk) -__attribute__((alias("vtime_account"))); +__attribute__((alias("vtime_account_irq_enter"))); EXPORT_SYMBOL_GPL(vtime_account_system); void __kprobes vtime_stop_cpu(void) diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index babc2b8..9c833c5 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -11,7 +11,6 @@ config SUPERH select HAVE_ARCH_TRACEHOOK select HAVE_DMA_API_DEBUG select HAVE_DMA_ATTRS - select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select HAVE_DEBUG_BUGVERBOSE select ARCH_HAVE_CUSTOM_GPIO_H @@ -91,9 +90,6 @@ config GENERIC_CSUM config GENERIC_HWEIGHT def_bool y -config IRQ_PER_CPU - def_bool y - config GENERIC_GPIO def_bool n diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 9f2edb5..9bff3db 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -23,7 +23,6 @@ config SPARC select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select RTC_CLASS select RTC_DRV_M48T59 - select HAVE_IRQ_WORK select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG select HAVE_ARCH_JUMP_LABEL @@ -61,6 +60,7 @@ config SPARC64 select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_SYSCALL_WRAPPERS + select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 7870be0..08fcce9 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -71,7 +71,6 @@ #define PMD_PADDR _AC(0xfffffffe,UL) #define PMD_PADDR_SHIFT _AC(11,UL) -#ifdef CONFIG_TRANSPARENT_HUGEPAGE #define PMD_ISHUGE _AC(0x00000001,UL) /* This is the PMD layout when PMD_ISHUGE is set. With 4MB huge @@ -86,7 +85,6 @@ #define PMD_HUGE_ACCESSED _AC(0x00000080,UL) #define PMD_HUGE_EXEC _AC(0x00000040,UL) #define PMD_HUGE_SPLITTING _AC(0x00000020,UL) -#endif /* PGDs point to PMD tables which are 8K aligned. */ #define PGD_PADDR _AC(0xfffffffc,UL) @@ -628,6 +626,12 @@ static inline unsigned long pte_special(pte_t pte) return pte_val(pte) & _PAGE_SPECIAL; } +static inline int pmd_large(pmd_t pmd) +{ + return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) == + (PMD_ISHUGE | PMD_HUGE_PRESENT); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_young(pmd_t pmd) { @@ -646,12 +650,6 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return val >> (PAGE_SHIFT - PMD_PADDR_SHIFT); } -static inline int pmd_large(pmd_t pmd) -{ - return (pmd_val(pmd) & (PMD_ISHUGE | PMD_HUGE_PRESENT)) == - (PMD_ISHUGE | PMD_HUGE_PRESENT); -} - static inline int pmd_trans_splitting(pmd_t pmd) { return (pmd_val(pmd) & (PMD_ISHUGE|PMD_HUGE_SPLITTING)) == diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index 1271b3a..be5bdf9 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -554,10 +554,8 @@ static void __init sbus_iommu_init(struct platform_device *op) regs = pr->phys_addr; iommu = kzalloc(sizeof(*iommu), GFP_ATOMIC); - if (!iommu) - goto fatal_memory_error; strbuf = kzalloc(sizeof(*strbuf), GFP_ATOMIC); - if (!strbuf) + if (!iommu || !strbuf) goto fatal_memory_error; op->dev.archdata.iommu = iommu; @@ -656,6 +654,8 @@ static void __init sbus_iommu_init(struct platform_device *op) return; fatal_memory_error: + kfree(iommu); + kfree(strbuf); prom_printf("sbus_iommu_init: Fatal memory allocation error.\n"); } diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 42c55df..01ee23d 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -66,6 +66,56 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 1; } +static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, + int *nr) +{ + struct page *head, *page, *tail; + u32 mask; + int refs; + + mask = PMD_HUGE_PRESENT; + if (write) + mask |= PMD_HUGE_WRITE; + if ((pmd_val(pmd) & mask) != mask) + return 0; + + refs = 0; + head = pmd_page(pmd); + page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + tail = page; + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + + if (!page_cache_add_speculative(head, refs)) { + *nr -= refs; + return 0; + } + + if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) { + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + /* Any tail page need their mapcount reference taken before we + * return. + */ + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; + } + + return 1; +} + static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -77,9 +127,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) + if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; - if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + if (unlikely(pmd_large(pmd))) { + if (!gup_huge_pmd(pmdp, pmd, addr, next, + write, pages, nr)) + return 0; + } else if (!gup_pte_range(pmd, addr, next, write, + pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 875d008..1bb7ad4 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -140,6 +140,8 @@ config ARCH_DEFCONFIG source "init/Kconfig" +source "kernel/Kconfig.freezer" + menu "Tilera-specific configuration" config NR_CPUS diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h index 2a9b293..3167291 100644 --- a/arch/tile/include/asm/io.h +++ b/arch/tile/include/asm/io.h @@ -250,7 +250,9 @@ static inline void writeq(u64 val, unsigned long addr) #define iowrite32 writel #define iowrite64 writeq -static inline void memset_io(void *dst, int val, size_t len) +#if CHIP_HAS_MMIO() || defined(CONFIG_PCI) + +static inline void memset_io(volatile void *dst, int val, size_t len) { int x; BUG_ON((unsigned long)dst & 0x3); @@ -277,6 +279,8 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, writel(*(u32 *)(src + x), dst + x); } +#endif + /* * The Tile architecture does not support IOPORT, even with PCI. * Unfortunately we can't yet simply not declare these methods, diff --git a/arch/tile/include/asm/irqflags.h b/arch/tile/include/asm/irqflags.h index b4e96fe..241c0bb 100644 --- a/arch/tile/include/asm/irqflags.h +++ b/arch/tile/include/asm/irqflags.h @@ -18,32 +18,20 @@ #include <arch/interrupts.h> #include <arch/chip.h> -#if !defined(__tilegx__) && defined(__ASSEMBLY__) - /* * The set of interrupts we want to allow when interrupts are nominally * disabled. The remainder are effectively "NMI" interrupts from * the point of view of the generic Linux code. Note that synchronous * interrupts (aka "non-queued") are not blocked by the mask in any case. */ -#if CHIP_HAS_AUX_PERF_COUNTERS() -#define LINUX_MASKABLE_INTERRUPTS_HI \ - (~(INT_MASK_HI(INT_PERF_COUNT) | INT_MASK_HI(INT_AUX_PERF_COUNT))) -#else -#define LINUX_MASKABLE_INTERRUPTS_HI \ - (~(INT_MASK_HI(INT_PERF_COUNT))) -#endif - -#else - -#if CHIP_HAS_AUX_PERF_COUNTERS() -#define LINUX_MASKABLE_INTERRUPTS \ - (~(INT_MASK(INT_PERF_COUNT) | INT_MASK(INT_AUX_PERF_COUNT))) -#else #define LINUX_MASKABLE_INTERRUPTS \ - (~(INT_MASK(INT_PERF_COUNT))) -#endif + (~((_AC(1,ULL) << INT_PERF_COUNT) | (_AC(1,ULL) << INT_AUX_PERF_COUNT))) +#if CHIP_HAS_SPLIT_INTR_MASK() +/* The same macro, but for the two 32-bit SPRs separately. */ +#define LINUX_MASKABLE_INTERRUPTS_LO (-1) +#define LINUX_MASKABLE_INTERRUPTS_HI \ + (~((1 << (INT_PERF_COUNT - 32)) | (1 << (INT_AUX_PERF_COUNT - 32)))) #endif #ifndef __ASSEMBLY__ @@ -126,7 +114,7 @@ * to know our current state. */ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask); -#define INITIAL_INTERRUPTS_ENABLED INT_MASK(INT_MEM_ERROR) +#define INITIAL_INTERRUPTS_ENABLED (1ULL << INT_MEM_ERROR) /* Disable interrupts. */ #define arch_local_irq_disable() \ @@ -165,7 +153,7 @@ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask); /* Prevent the given interrupt from being enabled next time we enable irqs. */ #define arch_local_irq_mask(interrupt) \ - (__get_cpu_var(interrupts_enabled_mask) &= ~INT_MASK(interrupt)) + (__get_cpu_var(interrupts_enabled_mask) &= ~(1ULL << (interrupt))) /* Prevent the given interrupt from being enabled immediately. */ #define arch_local_irq_mask_now(interrupt) do { \ @@ -175,7 +163,7 @@ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask); /* Allow the given interrupt to be enabled next time we enable irqs. */ #define arch_local_irq_unmask(interrupt) \ - (__get_cpu_var(interrupts_enabled_mask) |= INT_MASK(interrupt)) + (__get_cpu_var(interrupts_enabled_mask) |= (1ULL << (interrupt))) /* Allow the given interrupt to be enabled immediately, if !irqs_disabled. */ #define arch_local_irq_unmask_now(interrupt) do { \ @@ -250,7 +238,7 @@ DECLARE_PER_CPU(unsigned long long, interrupts_enabled_mask); /* Disable interrupts. */ #define IRQ_DISABLE(tmp0, tmp1) \ { \ - movei tmp0, -1; \ + movei tmp0, LINUX_MASKABLE_INTERRUPTS_LO; \ moveli tmp1, lo16(LINUX_MASKABLE_INTERRUPTS_HI) \ }; \ { \ diff --git a/arch/tile/include/uapi/arch/interrupts_32.h b/arch/tile/include/uapi/arch/interrupts_32.h index 96b5710..2efe3f6 100644 --- a/arch/tile/include/uapi/arch/interrupts_32.h +++ b/arch/tile/include/uapi/arch/interrupts_32.h @@ -15,6 +15,7 @@ #ifndef __ARCH_INTERRUPTS_H__ #define __ARCH_INTERRUPTS_H__ +#ifndef __KERNEL__ /** Mask for an interrupt. */ /* Note: must handle breaking interrupts into high and low words manually. */ #define INT_MASK_LO(intno) (1 << (intno)) @@ -23,6 +24,7 @@ #ifndef __ASSEMBLER__ #define INT_MASK(intno) (1ULL << (intno)) #endif +#endif /** Where a given interrupt executes */ @@ -92,216 +94,216 @@ #ifndef __ASSEMBLER__ #define QUEUED_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_DMATLB_MISS) | \ - INT_MASK(INT_DMATLB_ACCESS) | \ - INT_MASK(INT_SNITLB_MISS) | \ - INT_MASK(INT_SN_NOTIFY) | \ - INT_MASK(INT_SN_FIREWALL) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_DMA_NOTIFY) | \ - INT_MASK(INT_IDN_CA) | \ - INT_MASK(INT_UDN_CA) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DMA_ASID) | \ - INT_MASK(INT_SNI_ASID) | \ - INT_MASK(INT_DMA_CPL) | \ - INT_MASK(INT_SN_CPL) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_DMATLB_MISS) | \ + (1ULL << INT_DMATLB_ACCESS) | \ + (1ULL << INT_SNITLB_MISS) | \ + (1ULL << INT_SN_NOTIFY) | \ + (1ULL << INT_SN_FIREWALL) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_DMA_NOTIFY) | \ + (1ULL << INT_IDN_CA) | \ + (1ULL << INT_UDN_CA) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DMA_ASID) | \ + (1ULL << INT_SNI_ASID) | \ + (1ULL << INT_DMA_CPL) | \ + (1ULL << INT_SN_CPL) | \ + (1ULL << INT_DOUBLE_FAULT) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ 0) #define NONQUEUED_INTERRUPTS ( \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_SN_ACCESS) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_IDN_REFILL) | \ - INT_MASK(INT_UDN_REFILL) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ - INT_MASK(INT_SN_STATIC_ACCESS) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_SN_ACCESS) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_IDN_REFILL) | \ + (1ULL << INT_UDN_REFILL) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ + (1ULL << INT_SN_STATIC_ACCESS) | \ 0) #define CRITICAL_MASKED_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_DMATLB_MISS) | \ - INT_MASK(INT_DMATLB_ACCESS) | \ - INT_MASK(INT_SNITLB_MISS) | \ - INT_MASK(INT_SN_NOTIFY) | \ - INT_MASK(INT_SN_FIREWALL) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_DMA_NOTIFY) | \ - INT_MASK(INT_IDN_CA) | \ - INT_MASK(INT_UDN_CA) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_DMATLB_MISS) | \ + (1ULL << INT_DMATLB_ACCESS) | \ + (1ULL << INT_SNITLB_MISS) | \ + (1ULL << INT_SN_NOTIFY) | \ + (1ULL << INT_SN_FIREWALL) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_DMA_NOTIFY) | \ + (1ULL << INT_IDN_CA) | \ + (1ULL << INT_UDN_CA) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ 0) #define CRITICAL_UNMASKED_INTERRUPTS ( \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_SN_ACCESS) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_IDN_REFILL) | \ - INT_MASK(INT_UDN_REFILL) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DMA_ASID) | \ - INT_MASK(INT_SNI_ASID) | \ - INT_MASK(INT_DMA_CPL) | \ - INT_MASK(INT_SN_CPL) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ - INT_MASK(INT_SN_STATIC_ACCESS) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_SN_ACCESS) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_IDN_REFILL) | \ + (1ULL << INT_UDN_REFILL) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DMA_ASID) | \ + (1ULL << INT_SNI_ASID) | \ + (1ULL << INT_DMA_CPL) | \ + (1ULL << INT_SN_CPL) | \ + (1ULL << INT_DOUBLE_FAULT) | \ + (1ULL << INT_SN_STATIC_ACCESS) | \ 0) #define MASKABLE_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_IDN_REFILL) | \ - INT_MASK(INT_UDN_REFILL) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_DMATLB_MISS) | \ - INT_MASK(INT_DMATLB_ACCESS) | \ - INT_MASK(INT_SNITLB_MISS) | \ - INT_MASK(INT_SN_NOTIFY) | \ - INT_MASK(INT_SN_FIREWALL) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_DMA_NOTIFY) | \ - INT_MASK(INT_IDN_CA) | \ - INT_MASK(INT_UDN_CA) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_IDN_REFILL) | \ + (1ULL << INT_UDN_REFILL) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_DMATLB_MISS) | \ + (1ULL << INT_DMATLB_ACCESS) | \ + (1ULL << INT_SNITLB_MISS) | \ + (1ULL << INT_SN_NOTIFY) | \ + (1ULL << INT_SN_FIREWALL) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_DMA_NOTIFY) | \ + (1ULL << INT_IDN_CA) | \ + (1ULL << INT_UDN_CA) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ 0) #define UNMASKABLE_INTERRUPTS ( \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_SN_ACCESS) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DMA_ASID) | \ - INT_MASK(INT_SNI_ASID) | \ - INT_MASK(INT_DMA_CPL) | \ - INT_MASK(INT_SN_CPL) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ - INT_MASK(INT_SN_STATIC_ACCESS) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_SN_ACCESS) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DMA_ASID) | \ + (1ULL << INT_SNI_ASID) | \ + (1ULL << INT_DMA_CPL) | \ + (1ULL << INT_SN_CPL) | \ + (1ULL << INT_DOUBLE_FAULT) | \ + (1ULL << INT_SN_STATIC_ACCESS) | \ 0) #define SYNC_INTERRUPTS ( \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_SN_ACCESS) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_IDN_REFILL) | \ - INT_MASK(INT_UDN_REFILL) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ - INT_MASK(INT_SN_STATIC_ACCESS) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_SN_ACCESS) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_IDN_REFILL) | \ + (1ULL << INT_UDN_REFILL) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ + (1ULL << INT_SN_STATIC_ACCESS) | \ 0) #define NON_SYNC_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_DMATLB_MISS) | \ - INT_MASK(INT_DMATLB_ACCESS) | \ - INT_MASK(INT_SNITLB_MISS) | \ - INT_MASK(INT_SN_NOTIFY) | \ - INT_MASK(INT_SN_FIREWALL) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_DMA_NOTIFY) | \ - INT_MASK(INT_IDN_CA) | \ - INT_MASK(INT_UDN_CA) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DMA_ASID) | \ - INT_MASK(INT_SNI_ASID) | \ - INT_MASK(INT_DMA_CPL) | \ - INT_MASK(INT_SN_CPL) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_DMATLB_MISS) | \ + (1ULL << INT_DMATLB_ACCESS) | \ + (1ULL << INT_SNITLB_MISS) | \ + (1ULL << INT_SN_NOTIFY) | \ + (1ULL << INT_SN_FIREWALL) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_DMA_NOTIFY) | \ + (1ULL << INT_IDN_CA) | \ + (1ULL << INT_UDN_CA) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DMA_ASID) | \ + (1ULL << INT_SNI_ASID) | \ + (1ULL << INT_DMA_CPL) | \ + (1ULL << INT_SN_CPL) | \ + (1ULL << INT_DOUBLE_FAULT) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ 0) #endif /* !__ASSEMBLER__ */ #endif /* !__ARCH_INTERRUPTS_H__ */ diff --git a/arch/tile/include/uapi/arch/interrupts_64.h b/arch/tile/include/uapi/arch/interrupts_64.h index 5bb58b2..13c9f91 100644 --- a/arch/tile/include/uapi/arch/interrupts_64.h +++ b/arch/tile/include/uapi/arch/interrupts_64.h @@ -15,6 +15,7 @@ #ifndef __ARCH_INTERRUPTS_H__ #define __ARCH_INTERRUPTS_H__ +#ifndef __KERNEL__ /** Mask for an interrupt. */ #ifdef __ASSEMBLER__ /* Note: must handle breaking interrupts into high and low words manually. */ @@ -22,6 +23,7 @@ #else #define INT_MASK(intno) (1ULL << (intno)) #endif +#endif /** Where a given interrupt executes */ @@ -85,192 +87,192 @@ #ifndef __ASSEMBLER__ #define QUEUED_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_AUX_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_IPI_3) | \ - INT_MASK(INT_IPI_2) | \ - INT_MASK(INT_IPI_1) | \ - INT_MASK(INT_IPI_0) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_AUX_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_IPI_3) | \ + (1ULL << INT_IPI_2) | \ + (1ULL << INT_IPI_1) | \ + (1ULL << INT_IPI_0) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DOUBLE_FAULT) | \ 0) #define NONQUEUED_INTERRUPTS ( \ - INT_MASK(INT_SINGLE_STEP_3) | \ - INT_MASK(INT_SINGLE_STEP_2) | \ - INT_MASK(INT_SINGLE_STEP_1) | \ - INT_MASK(INT_SINGLE_STEP_0) | \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_ILL_TRANS) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ + (1ULL << INT_SINGLE_STEP_3) | \ + (1ULL << INT_SINGLE_STEP_2) | \ + (1ULL << INT_SINGLE_STEP_1) | \ + (1ULL << INT_SINGLE_STEP_0) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_ILL_TRANS) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ 0) #define CRITICAL_MASKED_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_SINGLE_STEP_3) | \ - INT_MASK(INT_SINGLE_STEP_2) | \ - INT_MASK(INT_SINGLE_STEP_1) | \ - INT_MASK(INT_SINGLE_STEP_0) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_AUX_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_IPI_3) | \ - INT_MASK(INT_IPI_2) | \ - INT_MASK(INT_IPI_1) | \ - INT_MASK(INT_IPI_0) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_SINGLE_STEP_3) | \ + (1ULL << INT_SINGLE_STEP_2) | \ + (1ULL << INT_SINGLE_STEP_1) | \ + (1ULL << INT_SINGLE_STEP_0) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_AUX_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_IPI_3) | \ + (1ULL << INT_IPI_2) | \ + (1ULL << INT_IPI_1) | \ + (1ULL << INT_IPI_0) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ 0) #define CRITICAL_UNMASKED_INTERRUPTS ( \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_ILL_TRANS) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_ILL_TRANS) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DOUBLE_FAULT) | \ 0) #define MASKABLE_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_SINGLE_STEP_3) | \ - INT_MASK(INT_SINGLE_STEP_2) | \ - INT_MASK(INT_SINGLE_STEP_1) | \ - INT_MASK(INT_SINGLE_STEP_0) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_AUX_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_IPI_3) | \ - INT_MASK(INT_IPI_2) | \ - INT_MASK(INT_IPI_1) | \ - INT_MASK(INT_IPI_0) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_SINGLE_STEP_3) | \ + (1ULL << INT_SINGLE_STEP_2) | \ + (1ULL << INT_SINGLE_STEP_1) | \ + (1ULL << INT_SINGLE_STEP_0) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_AUX_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_IPI_3) | \ + (1ULL << INT_IPI_2) | \ + (1ULL << INT_IPI_1) | \ + (1ULL << INT_IPI_0) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ 0) #define UNMASKABLE_INTERRUPTS ( \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_ILL_TRANS) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_ILL_TRANS) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DOUBLE_FAULT) | \ 0) #define SYNC_INTERRUPTS ( \ - INT_MASK(INT_SINGLE_STEP_3) | \ - INT_MASK(INT_SINGLE_STEP_2) | \ - INT_MASK(INT_SINGLE_STEP_1) | \ - INT_MASK(INT_SINGLE_STEP_0) | \ - INT_MASK(INT_IDN_COMPLETE) | \ - INT_MASK(INT_UDN_COMPLETE) | \ - INT_MASK(INT_ITLB_MISS) | \ - INT_MASK(INT_ILL) | \ - INT_MASK(INT_GPV) | \ - INT_MASK(INT_IDN_ACCESS) | \ - INT_MASK(INT_UDN_ACCESS) | \ - INT_MASK(INT_SWINT_3) | \ - INT_MASK(INT_SWINT_2) | \ - INT_MASK(INT_SWINT_1) | \ - INT_MASK(INT_SWINT_0) | \ - INT_MASK(INT_ILL_TRANS) | \ - INT_MASK(INT_UNALIGN_DATA) | \ - INT_MASK(INT_DTLB_MISS) | \ - INT_MASK(INT_DTLB_ACCESS) | \ + (1ULL << INT_SINGLE_STEP_3) | \ + (1ULL << INT_SINGLE_STEP_2) | \ + (1ULL << INT_SINGLE_STEP_1) | \ + (1ULL << INT_SINGLE_STEP_0) | \ + (1ULL << INT_IDN_COMPLETE) | \ + (1ULL << INT_UDN_COMPLETE) | \ + (1ULL << INT_ITLB_MISS) | \ + (1ULL << INT_ILL) | \ + (1ULL << INT_GPV) | \ + (1ULL << INT_IDN_ACCESS) | \ + (1ULL << INT_UDN_ACCESS) | \ + (1ULL << INT_SWINT_3) | \ + (1ULL << INT_SWINT_2) | \ + (1ULL << INT_SWINT_1) | \ + (1ULL << INT_SWINT_0) | \ + (1ULL << INT_ILL_TRANS) | \ + (1ULL << INT_UNALIGN_DATA) | \ + (1ULL << INT_DTLB_MISS) | \ + (1ULL << INT_DTLB_ACCESS) | \ 0) #define NON_SYNC_INTERRUPTS ( \ - INT_MASK(INT_MEM_ERROR) | \ - INT_MASK(INT_IDN_FIREWALL) | \ - INT_MASK(INT_UDN_FIREWALL) | \ - INT_MASK(INT_TILE_TIMER) | \ - INT_MASK(INT_AUX_TILE_TIMER) | \ - INT_MASK(INT_IDN_TIMER) | \ - INT_MASK(INT_UDN_TIMER) | \ - INT_MASK(INT_IDN_AVAIL) | \ - INT_MASK(INT_UDN_AVAIL) | \ - INT_MASK(INT_IPI_3) | \ - INT_MASK(INT_IPI_2) | \ - INT_MASK(INT_IPI_1) | \ - INT_MASK(INT_IPI_0) | \ - INT_MASK(INT_PERF_COUNT) | \ - INT_MASK(INT_AUX_PERF_COUNT) | \ - INT_MASK(INT_INTCTRL_3) | \ - INT_MASK(INT_INTCTRL_2) | \ - INT_MASK(INT_INTCTRL_1) | \ - INT_MASK(INT_INTCTRL_0) | \ - INT_MASK(INT_BOOT_ACCESS) | \ - INT_MASK(INT_WORLD_ACCESS) | \ - INT_MASK(INT_I_ASID) | \ - INT_MASK(INT_D_ASID) | \ - INT_MASK(INT_DOUBLE_FAULT) | \ + (1ULL << INT_MEM_ERROR) | \ + (1ULL << INT_IDN_FIREWALL) | \ + (1ULL << INT_UDN_FIREWALL) | \ + (1ULL << INT_TILE_TIMER) | \ + (1ULL << INT_AUX_TILE_TIMER) | \ + (1ULL << INT_IDN_TIMER) | \ + (1ULL << INT_UDN_TIMER) | \ + (1ULL << INT_IDN_AVAIL) | \ + (1ULL << INT_UDN_AVAIL) | \ + (1ULL << INT_IPI_3) | \ + (1ULL << INT_IPI_2) | \ + (1ULL << INT_IPI_1) | \ + (1ULL << INT_IPI_0) | \ + (1ULL << INT_PERF_COUNT) | \ + (1ULL << INT_AUX_PERF_COUNT) | \ + (1ULL << INT_INTCTRL_3) | \ + (1ULL << INT_INTCTRL_2) | \ + (1ULL << INT_INTCTRL_1) | \ + (1ULL << INT_INTCTRL_0) | \ + (1ULL << INT_BOOT_ACCESS) | \ + (1ULL << INT_WORLD_ACCESS) | \ + (1ULL << INT_I_ASID) | \ + (1ULL << INT_D_ASID) | \ + (1ULL << INT_DOUBLE_FAULT) | \ 0) #endif /* !__ASSEMBLER__ */ #endif /* !__ARCH_INTERRUPTS_H__ */ diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S index 54bc9a6..4ea0809 100644 --- a/arch/tile/kernel/intvec_64.S +++ b/arch/tile/kernel/intvec_64.S @@ -1035,7 +1035,9 @@ handle_syscall: /* Ensure that the syscall number is within the legal range. */ { moveli r20, hw2(sys_call_table) +#ifdef CONFIG_COMPAT blbs r30, .Lcompat_syscall +#endif } { cmpltu r21, TREG_SYSCALL_NR_NAME, r21 @@ -1093,6 +1095,7 @@ handle_syscall: j .Lresume_userspace /* jump into middle of interrupt_return */ } +#ifdef CONFIG_COMPAT .Lcompat_syscall: /* * Load the base of the compat syscall table in r20, and @@ -1117,6 +1120,7 @@ handle_syscall: { move r15, r4; addxi r4, r4, 0 } { move r16, r5; addxi r5, r5, 0 } j .Lload_syscall_pointer +#endif .Linvalid_syscall: /* Report an invalid syscall back to the user program */ diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 0e5661e..caf93ae 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -159,7 +159,7 @@ static void save_arch_state(struct thread_struct *t); int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p) { - struct pt_regs *childregs = task_pt_regs(p), *regs = current_pt_regs(); + struct pt_regs *childregs = task_pt_regs(p); unsigned long ksp; unsigned long *callee_regs; diff --git a/arch/tile/kernel/reboot.c b/arch/tile/kernel/reboot.c index baa3d90..d1b5c91 100644 --- a/arch/tile/kernel/reboot.c +++ b/arch/tile/kernel/reboot.c @@ -16,6 +16,7 @@ #include <linux/reboot.h> #include <linux/smp.h> #include <linux/pm.h> +#include <linux/export.h> #include <asm/page.h> #include <asm/setup.h> #include <hv/hypervisor.h> @@ -49,3 +50,4 @@ void machine_restart(char *cmd) /* No interesting distinction to be made here. */ void (*pm_power_off)(void) = NULL; +EXPORT_SYMBOL(pm_power_off); diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 6a649a4..d1e15f7 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -31,6 +31,7 @@ #include <linux/timex.h> #include <linux/hugetlb.h> #include <linux/start_kernel.h> +#include <linux/screen_info.h> #include <asm/setup.h> #include <asm/sections.h> #include <asm/cacheflush.h> @@ -49,6 +50,10 @@ static inline int ABS(int x) { return x >= 0 ? x : -x; } /* Chip information */ char chip_model[64] __write_once; +#ifdef CONFIG_VT +struct screen_info screen_info; +#endif + struct pglist_data node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c index b2f44c2..ed258b8 100644 --- a/arch/tile/kernel/stack.c +++ b/arch/tile/kernel/stack.c @@ -112,7 +112,7 @@ static struct pt_regs *valid_fault_handler(struct KBacktraceIterator* kbt) p->pc, p->sp, p->ex1); p = NULL; } - if (!kbt->profile || (INT_MASK(p->faultnum) & QUEUED_INTERRUPTS) == 0) + if (!kbt->profile || ((1ULL << p->faultnum) & QUEUED_INTERRUPTS) == 0) return p; return NULL; } @@ -484,6 +484,7 @@ void save_stack_trace(struct stack_trace *trace) { save_stack_trace_tsk(NULL, trace); } +EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/tile/lib/cacheflush.c b/arch/tile/lib/cacheflush.c index db4fb89..8f8ad81 100644 --- a/arch/tile/lib/cacheflush.c +++ b/arch/tile/lib/cacheflush.c @@ -12,6 +12,7 @@ * more details. */ +#include <linux/export.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <arch/icache.h> @@ -165,3 +166,4 @@ void finv_buffer_remote(void *buffer, size_t size, int hfh) __insn_mtspr(SPR_DSTREAM_PF, old_dstream_pf); #endif } +EXPORT_SYMBOL_GPL(finv_buffer_remote); diff --git a/arch/tile/lib/cpumask.c b/arch/tile/lib/cpumask.c index fdc4036..75947ed 100644 --- a/arch/tile/lib/cpumask.c +++ b/arch/tile/lib/cpumask.c @@ -16,6 +16,7 @@ #include <linux/ctype.h> #include <linux/errno.h> #include <linux/smp.h> +#include <linux/export.h> /* * Allow cropping out bits beyond the end of the array. @@ -50,3 +51,4 @@ int bitmap_parselist_crop(const char *bp, unsigned long *maskp, int nmaskbits) } while (*bp != '\0' && *bp != '\n'); return 0; } +EXPORT_SYMBOL(bitmap_parselist_crop); diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c index dd5f0a3..4385cb6 100644 --- a/arch/tile/lib/exports.c +++ b/arch/tile/lib/exports.c @@ -55,6 +55,8 @@ EXPORT_SYMBOL(hv_dev_poll_cancel); EXPORT_SYMBOL(hv_dev_close); EXPORT_SYMBOL(hv_sysconf); EXPORT_SYMBOL(hv_confstr); +EXPORT_SYMBOL(hv_get_rtc); +EXPORT_SYMBOL(hv_set_rtc); /* libgcc.a */ uint32_t __udivsi3(uint32_t dividend, uint32_t divisor); diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index 5f7868d..1ae9119 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -408,6 +408,7 @@ void homecache_change_page_home(struct page *page, int order, int home) __set_pte(ptep, pte_set_home(pteval, home)); } } +EXPORT_SYMBOL(homecache_change_page_home); struct page *homecache_alloc_pages(gfp_t gfp_mask, unsigned int order, int home) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 79795af..260857a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1,7 +1,7 @@ # Select 32 or 64 bit config 64BIT bool "64-bit kernel" if ARCH = "x86" - default ARCH = "x86_64" + default ARCH != "i386" ---help--- Say yes to build a 64-bit kernel - formerly known as x86_64 Say no to build a 32-bit kernel - formerly known as i386 @@ -28,7 +28,6 @@ config X86 select HAVE_OPROFILE select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS - select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_MEMBLOCK @@ -40,10 +39,12 @@ config X86 select HAVE_DMA_CONTIGUOUS if !SWIOTLB select HAVE_KRETPROBES select HAVE_OPTPROBES + select HAVE_KPROBES_ON_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FENTRY if X86_64 select HAVE_C_RECORDMCOUNT select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_FP_TEST @@ -106,6 +107,7 @@ config X86 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL if X86_64 select KTIME_SCALAR if X86_32 + select ALWAYS_USE_PERSISTENT_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 @@ -114,6 +116,7 @@ config X86 select MODULES_USE_ELF_RELA if X86_64 select CLONE_BACKWARDS if X86_32 select GENERIC_SIGALTSTACK + select ARCH_USE_BUILTIN_BSWAP config INSTRUCTION_DECODER def_bool y @@ -320,6 +323,10 @@ config X86_BIGSMP ---help--- This option is needed for the systems that have more than 8 CPUs +config GOLDFISH + def_bool y + depends on X86_GOLDFISH + if X86_32 config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" @@ -402,6 +409,14 @@ config X86_UV # Following is an alphabetically sorted list of 32 bit extended platforms # Please maintain the alphabetic order if and when there are additions +config X86_GOLDFISH + bool "Goldfish (Virtual Platform)" + depends on X86_32 + ---help--- + Enable support for the Goldfish virtual platform used primarily + for Android development. Unless you are building for the Android + Goldfish emulator say N here. + config X86_INTEL_CE bool "CE4100 TV platform" depends on PCI @@ -2138,6 +2153,7 @@ config OLPC_XO1_RTC config OLPC_XO1_SCI bool "OLPC XO-1 SCI extras" depends on OLPC && OLPC_XO1_PM + depends on INPUT=y select POWER_SUPPLY select GPIO_CS5535 select MFD_CORE @@ -2187,6 +2203,15 @@ config GEOS ---help--- This option enables system support for the Traverse Technologies GEOS. +config TS5500 + bool "Technologic Systems TS-5500 platform support" + depends on MELAN + select CHECK_SIGNATURE + select NEW_LEDS + select LEDS_CLASS + ---help--- + This option enables system support for the Technologic Systems TS-5500. + endif # X86_32 config AMD_NB diff --git a/arch/x86/Makefile b/arch/x86/Makefile index e71fc42..5c47726 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -2,7 +2,11 @@ # select defconfig based on actual architecture ifeq ($(ARCH),x86) + ifeq ($(shell uname -m),x86_64) + KBUILD_DEFCONFIG := x86_64_defconfig + else KBUILD_DEFCONFIG := i386_defconfig + endif else KBUILD_DEFCONFIG := $(ARCH)_defconfig endif diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index ccce0ed..379814b 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -71,7 +71,7 @@ GCOV_PROFILE := n $(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ -cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin > $@ +cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/zoffset.h > $@ $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) @@ -92,7 +92,7 @@ targets += voffset.h $(obj)/voffset.h: vmlinux FORCE $(call if_changed,voffset) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 18e329c..f8fa411 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -256,10 +256,10 @@ static efi_status_t setup_efi_pci(struct boot_params *params) int i; struct setup_data *data; - data = (struct setup_data *)params->hdr.setup_data; + data = (struct setup_data *)(unsigned long)params->hdr.setup_data; while (data && data->next) - data = (struct setup_data *)data->next; + data = (struct setup_data *)(unsigned long)data->next; status = efi_call_phys5(sys_table->boottime->locate_handle, EFI_LOCATE_BY_PROTOCOL, &pci_proto, @@ -295,16 +295,18 @@ static efi_status_t setup_efi_pci(struct boot_params *params) if (!pci) continue; +#ifdef CONFIG_X86_64 status = efi_call_phys4(pci->attributes, pci, EfiPciIoAttributeOperationGet, 0, &attributes); - +#else + status = efi_call_phys5(pci->attributes, pci, + EfiPciIoAttributeOperationGet, 0, 0, + &attributes); +#endif if (status != EFI_SUCCESS) continue; - if (!(attributes & EFI_PCI_IO_ATTRIBUTE_EMBEDDED_ROM)) - continue; - if (!pci->romimage || !pci->romsize) continue; @@ -345,9 +347,9 @@ static efi_status_t setup_efi_pci(struct boot_params *params) memcpy(rom->romdata, pci->romimage, pci->romsize); if (data) - data->next = (uint64_t)rom; + data->next = (unsigned long)rom; else - params->hdr.setup_data = (uint64_t)rom; + params->hdr.setup_data = (unsigned long)rom; data = (struct setup_data *)rom; @@ -432,10 +434,9 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, * Once we've found a GOP supporting ConOut, * don't bother looking any further. */ + first_gop = gop; if (conout_found) break; - - first_gop = gop; } } diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index aa4aaf1..1e3184f 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -35,11 +35,11 @@ ENTRY(startup_32) #ifdef CONFIG_EFI_STUB jmp preferred_addr - .balign 0x10 /* * We don't need the return address, so set up the stack so - * efi_main() can find its arugments. + * efi_main() can find its arguments. */ +ENTRY(efi_pe_entry) add $0x4, %esp call make_boot_params @@ -50,8 +50,10 @@ ENTRY(startup_32) pushl %eax pushl %esi pushl %ecx + sub $0x4, %esp - .org 0x30,0x90 +ENTRY(efi_stub_entry) + add $0x4, %esp call efi_main cmpl $0, %eax movl %eax, %esi diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 2c4b171..f5d1aaa 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -201,12 +201,12 @@ ENTRY(startup_64) */ #ifdef CONFIG_EFI_STUB /* - * The entry point for the PE/COFF executable is 0x210, so only - * legacy boot loaders will execute this jmp. + * The entry point for the PE/COFF executable is efi_pe_entry, so + * only legacy boot loaders will execute this jmp. */ jmp preferred_addr - .org 0x210 +ENTRY(efi_pe_entry) mov %rcx, %rdi mov %rdx, %rsi pushq %rdi @@ -218,7 +218,7 @@ ENTRY(startup_64) popq %rsi popq %rdi - .org 0x230,0x90 +ENTRY(efi_stub_entry) call efi_main movq %rax,%rsi cmpq $0,%rax diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 88f7ff6..7cb56c6 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -325,6 +325,8 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, { real_mode = rmode; + sanitize_boot_params(real_mode); + if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 0e6dc0e..674019d 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -18,6 +18,7 @@ #include <asm/page.h> #include <asm/boot.h> #include <asm/bootparam.h> +#include <asm/bootparam_utils.h> #define BOOT_BOOT_H #include "../ctype.h" diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 8c132a6..944ce59 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -21,6 +21,7 @@ #include <asm/e820.h> #include <asm/page_types.h> #include <asm/setup.h> +#include <asm/bootparam.h> #include "boot.h" #include "voffset.h" #include "zoffset.h" @@ -255,6 +256,9 @@ section_table: # header, from the old boot sector. .section ".header", "a" + .globl sentinel +sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ + .globl hdr hdr: setup_sects: .byte 0 /* Filled in by build.c */ @@ -279,7 +283,7 @@ _start: # Part 2 of the header, from the old setup.S .ascii "HdrS" # header signature - .word 0x020b # header version number (>= 0x0105) + .word 0x020c # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG @@ -297,13 +301,7 @@ type_of_loader: .byte 0 # 0 means ancient bootloader, newer # flags, unused bits must be zero (RFU) bit within loadflags loadflags: -LOADED_HIGH = 1 # If set, the kernel is loaded high -CAN_USE_HEAP = 0x80 # If set, the loader also has set - # heap_end_ptr to tell how much - # space behind setup.S can be used for - # heap purposes. - # Only the loader knows what is free - .byte LOADED_HIGH + .byte LOADED_HIGH # The kernel is to be loaded high setup_move_size: .word 0x8000 # size to move, when setup is not # loaded at 0x90000. We will move setup @@ -369,7 +367,23 @@ relocatable_kernel: .byte 1 relocatable_kernel: .byte 0 #endif min_alignment: .byte MIN_KERNEL_ALIGN_LG2 # minimum alignment -pad3: .word 0 + +xloadflags: +#ifdef CONFIG_X86_64 +# define XLF0 XLF_KERNEL_64 /* 64-bit kernel */ +#else +# define XLF0 0 +#endif +#ifdef CONFIG_EFI_STUB +# ifdef CONFIG_X86_64 +# define XLF23 XLF_EFI_HANDOVER_64 /* 64-bit EFI handover ok */ +# else +# define XLF23 XLF_EFI_HANDOVER_32 /* 32-bit EFI handover ok */ +# endif +#else +# define XLF23 0 +#endif + .word XLF0 | XLF23 cmdline_size: .long COMMAND_LINE_SIZE-1 #length of the command line, #added with boot protocol @@ -397,8 +411,13 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr #define INIT_SIZE VO_INIT_SIZE #endif init_size: .long INIT_SIZE # kernel initialization size -handover_offset: .long 0x30 # offset to the handover +handover_offset: +#ifdef CONFIG_EFI_STUB + .long 0x30 # offset to the handover # protocol entry point +#else + .long 0 +#endif # End of setup header ##################################################### diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 03c0683..96a6c75 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -13,7 +13,7 @@ SECTIONS .bstext : { *(.bstext) } .bsdata : { *(.bsdata) } - . = 497; + . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 4b8e165..94c5446 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -52,6 +52,10 @@ int is_big_kernel; #define PECOFF_RELOC_RESERVE 0x20 +unsigned long efi_stub_entry; +unsigned long efi_pe_entry; +unsigned long startup_64; + /*----------------------------------------------------------------------*/ static const u32 crctab32[] = { @@ -132,7 +136,7 @@ static void die(const char * str, ...) static void usage(void) { - die("Usage: build setup system [> image]"); + die("Usage: build setup system [zoffset.h] [> image]"); } #ifdef CONFIG_EFI_STUB @@ -206,30 +210,54 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) */ put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]); -#ifdef CONFIG_X86_32 /* - * Address of entry point. - * - * The EFI stub entry point is +16 bytes from the start of - * the .text section. + * Address of entry point for PE/COFF executable */ - put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]); -#else - /* - * Address of entry point. startup_32 is at the beginning and - * the 64-bit entry point (startup_64) is always 512 bytes - * after. The EFI stub entry point is 16 bytes after that, as - * the first instruction allows legacy loaders to jump over - * the EFI stub initialisation - */ - put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]); -#endif /* CONFIG_X86_32 */ + put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); update_pecoff_section_header(".text", text_start, text_sz); } #endif /* CONFIG_EFI_STUB */ + +/* + * Parse zoffset.h and find the entry points. We could just #include zoffset.h + * but that would mean tools/build would have to be rebuilt every time. It's + * not as if parsing it is hard... + */ +#define PARSE_ZOFS(p, sym) do { \ + if (!strncmp(p, "#define ZO_" #sym " ", 11+sizeof(#sym))) \ + sym = strtoul(p + 11 + sizeof(#sym), NULL, 16); \ +} while (0) + +static void parse_zoffset(char *fname) +{ + FILE *file; + char *p; + int c; + + file = fopen(fname, "r"); + if (!file) + die("Unable to open `%s': %m", fname); + c = fread(buf, 1, sizeof(buf) - 1, file); + if (ferror(file)) + die("read-error on `zoffset.h'"); + buf[c] = 0; + + p = (char *)buf; + + while (p && *p) { + PARSE_ZOFS(p, efi_stub_entry); + PARSE_ZOFS(p, efi_pe_entry); + PARSE_ZOFS(p, startup_64); + + p = strchr(p, '\n'); + while (p && (*p == '\r' || *p == '\n')) + p++; + } +} + int main(int argc, char ** argv) { unsigned int i, sz, setup_sectors; @@ -241,7 +269,19 @@ int main(int argc, char ** argv) void *kernel; u32 crc = 0xffffffffUL; - if (argc != 3) + /* Defaults for old kernel */ +#ifdef CONFIG_X86_32 + efi_pe_entry = 0x10; + efi_stub_entry = 0x30; +#else + efi_pe_entry = 0x210; + efi_stub_entry = 0x230; + startup_64 = 0x200; +#endif + + if (argc == 4) + parse_zoffset(argv[3]); + else if (argc != 3) usage(); /* Copy the setup code */ @@ -299,6 +339,11 @@ int main(int argc, char ** argv) #ifdef CONFIG_EFI_STUB update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz)); + +#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ + efi_stub_entry -= 0x200; +#endif + put_unaligned_le32(efi_stub_entry, &buf[0x264]); #endif crc = partial_crc32(buf, i, crc); diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 5598547..9444708 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1,3 +1,4 @@ +# CONFIG_64BIT is not set CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 102ff7c..142c4ce 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -207,7 +207,7 @@ sysexit_from_sys_call: testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jnz ia32_ret_from_sys_call TRACE_IRQS_ON - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %eax,%esi /* second arg, syscall return value */ cmpl $-MAX_ERRNO,%eax /* is it an error ? */ jbe 1f @@ -217,7 +217,7 @@ sysexit_from_sys_call: call __audit_syscall_exit movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi - cli + DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jz \exit diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index b3341e9..a54ee1d 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -81,6 +81,23 @@ static inline struct amd_northbridge *node_to_amd_nb(int node) return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL; } +static inline u16 amd_get_node_id(struct pci_dev *pdev) +{ + struct pci_dev *misc; + int i; + + for (i = 0; i != amd_nb_num(); i++) { + misc = node_to_amd_nb(i)->misc; + + if (pci_domain_nr(misc->bus) == pci_domain_nr(pdev->bus) && + PCI_SLOT(misc->devfn) == PCI_SLOT(pdev->devfn)) + return i; + } + + WARN(1, "Unable to find AMD Northbridge id for %s\n", pci_name(pdev)); + return 0; +} + #else #define amd_nb_num(x) 0 diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h new file mode 100644 index 0000000..5b5e9cb --- /dev/null +++ b/arch/x86/include/asm/bootparam_utils.h @@ -0,0 +1,38 @@ +#ifndef _ASM_X86_BOOTPARAM_UTILS_H +#define _ASM_X86_BOOTPARAM_UTILS_H + +#include <asm/bootparam.h> + +/* + * This file is included from multiple environments. Do not + * add completing #includes to make it standalone. + */ + +/* + * Deal with bootloaders which fail to initialize unknown fields in + * boot_params to zero. The list fields in this list are taken from + * analysis of kexec-tools; if other broken bootloaders initialize a + * different set of fields we will need to figure out how to disambiguate. + * + */ +static void sanitize_boot_params(struct boot_params *boot_params) +{ + if (boot_params->sentinel) { + /*fields in boot_params are not valid, clear them */ + memset(&boot_params->olpc_ofw_header, 0, + (char *)&boot_params->alt_mem_k - + (char *)&boot_params->olpc_ofw_header); + memset(&boot_params->kbd_status, 0, + (char *)&boot_params->hdr - + (char *)&boot_params->kbd_status); + memset(&boot_params->_pad7[0], 0, + (char *)&boot_params->edd_mbr_sig_buffer[0] - + (char *)&boot_params->_pad7[0]); + memset(&boot_params->_pad8[0], 0, + (char *)&boot_params->eddbuf[0] - + (char *)&boot_params->_pad8[0]); + memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9)); + } +} + +#endif /* _ASM_X86_BOOTPARAM_UTILS_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 2d9075e..93fe929 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -167,6 +167,7 @@ #define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */ #define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ #define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB (6*32+24) /* NB performance counter extensions */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -309,6 +310,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) +#define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) #define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) #define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 6e8fdf5..28677c5 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -94,6 +94,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; +extern unsigned long x86_efi_facility; extern void efi_set_executable(efi_memory_desc_t *md, bool executable); extern int efi_memblock_x86_reserve_range(void); extern void efi_call_phys_prelog(void); diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 9a25b52..86cb51e 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -44,7 +44,6 @@ #ifdef CONFIG_DYNAMIC_FTRACE #define ARCH_SUPPORTS_FTRACE_OPS 1 -#define ARCH_SUPPORTS_FTRACE_SAVE_REGS #endif #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 434e210..b18df57 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -80,9 +80,9 @@ extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg); extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg); #ifdef CONFIG_PCI_MSI -extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id); +extern int default_setup_hpet_msi(unsigned int irq, unsigned int id); #else -static inline int arch_setup_hpet_msi(unsigned int irq, unsigned int id) +static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id) { return -EINVAL; } @@ -111,6 +111,7 @@ extern void hpet_unregister_irq_handler(rtc_irq_handler handler); static inline int hpet_enable(void) { return 0; } static inline int is_hpet_enabled(void) { return 0; } #define hpet_readl(a) 0 +#define default_setup_hpet_msi NULL #endif #endif /* _ASM_X86_HPET_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index eb92a6e..10a78c3 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -101,6 +101,7 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr, irq_attr->polarity = polarity; } +/* Intel specific interrupt remapping information */ struct irq_2_iommu { struct intel_iommu *iommu; u16 irte_index; @@ -108,6 +109,12 @@ struct irq_2_iommu { u8 irte_mask; }; +/* AMD specific interrupt remapping information */ +struct irq_2_irte { + u16 devid; /* Device ID for IRTE table */ + u16 index; /* Index into IRTE table*/ +}; + /* * This is performance-critical, we want to do it O(1) * @@ -120,7 +127,11 @@ struct irq_cfg { u8 vector; u8 move_in_progress : 1; #ifdef CONFIG_IRQ_REMAP - struct irq_2_iommu irq_2_iommu; + u8 remapped : 1; + union { + struct irq_2_iommu irq_2_iommu; + struct irq_2_irte irq_2_irte; + }; #endif }; diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index b518c75..86095ed 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -25,6 +25,7 @@ extern void init_hypervisor(struct cpuinfo_x86 *c); extern void init_hypervisor_platform(void); +extern bool hypervisor_x2apic_available(void); /* * x86 hypervisor information @@ -41,6 +42,9 @@ struct hypervisor_x86 { /* Platform setup (run once per boot) */ void (*init_platform)(void); + + /* X2APIC detection (run once per boot) */ + bool (*x2apic_available)(void); }; extern const struct hypervisor_x86 *x86_hyper; @@ -51,13 +55,4 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv; extern const struct hypervisor_x86 x86_hyper_xen_hvm; extern const struct hypervisor_x86 x86_hyper_kvm; -static inline bool hypervisor_x2apic_available(void) -{ - if (kvm_para_available()) - return true; - if (xen_x2apic_para_available()) - return true; - return false; -} - #endif diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 73d8c53..459e50a 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -144,11 +144,24 @@ extern int timer_through_8259; (mp_irq_entries && !skip_ioapic_setup && io_apic_irqs) struct io_apic_irq_attr; +struct irq_cfg; extern int io_apic_set_pci_routing(struct device *dev, int irq, struct io_apic_irq_attr *irq_attr); void setup_IO_APIC_irq_extra(u32 gsi); extern void ioapic_insert_resources(void); +extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *, + unsigned int, int, + struct io_apic_irq_attr *); +extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *, + unsigned int, int, + struct io_apic_irq_attr *); +extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg); + +extern void native_compose_msi_msg(struct pci_dev *pdev, + unsigned int irq, unsigned int dest, + struct msi_msg *msg, u8 hpet_id); +extern void native_eoi_ioapic_pin(int apic, int pin, int vector); int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr); extern int save_ioapic_entries(void); @@ -179,6 +192,12 @@ extern void __init native_io_apic_init_mappings(void); extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg); extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val); extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val); +extern void native_disable_io_apic(void); +extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries); +extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries); +extern int native_ioapic_set_affinity(struct irq_data *, + const struct cpumask *, + bool); static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) { @@ -193,6 +212,9 @@ static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned { x86_io_apic_ops.modify(apic, reg, value); } + +extern void io_apic_eoi(unsigned int apic, unsigned int vector); + #else /* !CONFIG_X86_IO_APIC */ #define io_apic_assign_pci_irqs 0 @@ -223,6 +245,12 @@ static inline void disable_ioapic_support(void) { } #define native_io_apic_read NULL #define native_io_apic_write NULL #define native_io_apic_modify NULL +#define native_disable_io_apic NULL +#define native_io_apic_print_entries NULL +#define native_ioapic_set_affinity NULL +#define native_setup_ioapic_entry NULL +#define native_compose_msi_msg NULL +#define native_eoi_ioapic_pin NULL #endif #endif /* _ASM_X86_IO_APIC_H */ diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 5fb9bbb..95fd352 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -26,8 +26,6 @@ #ifdef CONFIG_IRQ_REMAP -extern int irq_remapping_enabled; - extern void setup_irq_remapping_ops(void); extern int irq_remapping_supported(void); extern int irq_remapping_prepare(void); @@ -40,21 +38,19 @@ extern int setup_ioapic_remapped_entry(int irq, unsigned int destination, int vector, struct io_apic_irq_attr *attr); -extern int set_remapped_irq_affinity(struct irq_data *data, - const struct cpumask *mask, - bool force); extern void free_remapped_irq(int irq); extern void compose_remapped_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, struct msi_msg *msg, u8 hpet_id); -extern int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec); -extern int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, - int index, int sub_handle); extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id); +extern void panic_if_irq_remap(const char *msg); +extern bool setup_remapped_irq(int irq, + struct irq_cfg *cfg, + struct irq_chip *chip); -#else /* CONFIG_IRQ_REMAP */ +void irq_remap_modify_chip_defaults(struct irq_chip *chip); -#define irq_remapping_enabled 0 +#else /* CONFIG_IRQ_REMAP */ static inline void setup_irq_remapping_ops(void) { } static inline int irq_remapping_supported(void) { return 0; } @@ -71,30 +67,30 @@ static inline int setup_ioapic_remapped_entry(int irq, { return -ENODEV; } -static inline int set_remapped_irq_affinity(struct irq_data *data, - const struct cpumask *mask, - bool force) -{ - return 0; -} static inline void free_remapped_irq(int irq) { } static inline void compose_remapped_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, struct msi_msg *msg, u8 hpet_id) { } -static inline int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) +static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) { return -ENODEV; } -static inline int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, - int index, int sub_handle) + +static inline void panic_if_irq_remap(const char *msg) +{ +} + +static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip) { - return -ENODEV; } -static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) + +static inline bool setup_remapped_irq(int irq, + struct irq_cfg *cfg, + struct irq_chip *chip) { - return -ENODEV; + return false; } #endif /* CONFIG_IRQ_REMAP */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 1508e51..aac5fa6 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -109,8 +109,8 @@ #define UV_BAU_MESSAGE 0xf5 -/* Xen vector callback to receive events in a HVM domain */ -#define XEN_HVM_EVTCHN_CALLBACK 0xf3 +/* Vector on which hypervisor callbacks will be delivered */ +#define HYPERVISOR_CALLBACK_VECTOR 0xf3 /* * Local APIC timer IRQ vector is on a different priority level, diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 5ed1f161..65231e1 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -85,13 +85,13 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } -static inline int kvm_para_available(void) +static inline bool kvm_para_available(void) { unsigned int eax, ebx, ecx, edx; char signature[13]; if (boot_cpu_data.cpuid_level < 0) - return 0; /* So we don't blow up on old processors */ + return false; /* So we don't blow up on old processors */ if (cpu_has_hypervisor) { cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx); @@ -101,10 +101,10 @@ static inline int kvm_para_available(void) signature[12] = 0; if (strcmp(signature, "KVMKVMKVM") == 0) - return 1; + return true; } - return 0; + return false; } static inline unsigned int kvm_arch_para_features(void) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 4814297..79327e9 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -27,20 +27,20 @@ #define __asmlinkage_protect0(ret) \ __asmlinkage_protect_n(ret) #define __asmlinkage_protect1(ret, arg1) \ - __asmlinkage_protect_n(ret, "g" (arg1)) + __asmlinkage_protect_n(ret, "m" (arg1)) #define __asmlinkage_protect2(ret, arg1, arg2) \ - __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2)) + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2)) #define __asmlinkage_protect3(ret, arg1, arg2, arg3) \ - __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3)) + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3)) #define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \ - __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \ - "g" (arg4)) + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ + "m" (arg4)) #define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \ - __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \ - "g" (arg4), "g" (arg5)) + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ + "m" (arg4), "m" (arg5)) #define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \ - __asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \ - "g" (arg4), "g" (arg5), "g" (arg6)) + __asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \ + "m" (arg4), "m" (arg5), "m" (arg6)) #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index ecdfee6..f4076af 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -3,6 +3,90 @@ #include <uapi/asm/mce.h> +/* + * Machine Check support for x86 + */ + +/* MCG_CAP register defines */ +#define MCG_BANKCNT_MASK 0xff /* Number of Banks */ +#define MCG_CTL_P (1ULL<<8) /* MCG_CTL register available */ +#define MCG_EXT_P (1ULL<<9) /* Extended registers available */ +#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */ +#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */ +#define MCG_EXT_CNT_SHIFT 16 +#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) +#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ + +/* MCG_STATUS register defines */ +#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ +#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */ +#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */ + +/* MCi_STATUS register defines */ +#define MCI_STATUS_VAL (1ULL<<63) /* valid error */ +#define MCI_STATUS_OVER (1ULL<<62) /* previous errors lost */ +#define MCI_STATUS_UC (1ULL<<61) /* uncorrected error */ +#define MCI_STATUS_EN (1ULL<<60) /* error enabled */ +#define MCI_STATUS_MISCV (1ULL<<59) /* misc error reg. valid */ +#define MCI_STATUS_ADDRV (1ULL<<58) /* addr reg. valid */ +#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ +#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ +#define MCI_STATUS_AR (1ULL<<55) /* Action required */ +#define MCACOD 0xffff /* MCA Error Code */ + +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ + +/* MCi_MISC register defines */ +#define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f) +#define MCI_MISC_ADDR_MODE(m) (((m) >> 6) & 7) +#define MCI_MISC_ADDR_SEGOFF 0 /* segment offset */ +#define MCI_MISC_ADDR_LINEAR 1 /* linear address */ +#define MCI_MISC_ADDR_PHYS 2 /* physical address */ +#define MCI_MISC_ADDR_MEM 3 /* memory address */ +#define MCI_MISC_ADDR_GENERIC 7 /* generic */ + +/* CTL2 register defines */ +#define MCI_CTL2_CMCI_EN (1ULL << 30) +#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL + +#define MCJ_CTX_MASK 3 +#define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK) +#define MCJ_CTX_RANDOM 0 /* inject context: random */ +#define MCJ_CTX_PROCESS 0x1 /* inject context: process */ +#define MCJ_CTX_IRQ 0x2 /* inject context: IRQ */ +#define MCJ_NMI_BROADCAST 0x4 /* do NMI broadcasting */ +#define MCJ_EXCEPTION 0x8 /* raise as exception */ +#define MCJ_IRQ_BRAODCAST 0x10 /* do IRQ broadcasting */ + +#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ + +/* Software defined banks */ +#define MCE_EXTENDED_BANK 128 +#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0) +#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) + +#define MCE_LOG_LEN 32 +#define MCE_LOG_SIGNATURE "MACHINECHECK" + +/* + * This structure contains all data related to the MCE log. Also + * carries a signature to make it easier to find from external + * debugging tools. Each entry is only valid when its finished flag + * is set. + */ +struct mce_log { + char signature[12]; /* "MACHINECHECK" */ + unsigned len; /* = MCE_LOG_LEN */ + unsigned next; + unsigned flags; + unsigned recordlen; /* length of struct mce */ + struct mce entry[MCE_LOG_LEN]; +}; struct mca_config { bool dont_log_ce; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 79ce568..c2934be 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -11,4 +11,8 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; +void hyperv_callback_vector(void); +void hyperv_vector_handler(struct pt_regs *regs); +void hv_register_vmbus_handler(int irq, irq_handler_t handler); + #endif diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index dba7805..c28fd02 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -121,9 +121,12 @@ static inline void x86_restore_msi_irqs(struct pci_dev *dev, int irq) #define arch_teardown_msi_irq x86_teardown_msi_irq #define arch_restore_msi_irqs x86_restore_msi_irqs /* implemented in arch/x86/kernel/apic/io_apic. */ +struct msi_desc; int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void native_teardown_msi_irq(unsigned int irq); void native_restore_msi_irqs(struct pci_dev *dev, int irq); +int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, + unsigned int irq_base, unsigned int irq_offset); /* default to the implementation in drivers/lib/msi.c */ #define HAVE_DEFAULT_MSI_TEARDOWN_IRQS #define HAVE_DEFAULT_MSI_RESTORE_IRQS diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 4fabcdf..57cb634 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -29,8 +29,13 @@ #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL -#define AMD_PERFMON_EVENTSEL_GUESTONLY (1ULL << 40) -#define AMD_PERFMON_EVENTSEL_HOSTONLY (1ULL << 41) +#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36) +#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40) +#define AMD64_EVENTSEL_HOSTONLY (1ULL << 41) + +#define AMD64_EVENTSEL_INT_CORE_SEL_SHIFT 37 +#define AMD64_EVENTSEL_INT_CORE_SEL_MASK \ + (0xFULL << AMD64_EVENTSEL_INT_CORE_SEL_SHIFT) #define AMD64_EVENTSEL_EVENT \ (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32)) @@ -46,8 +51,12 @@ #define AMD64_RAW_EVENT_MASK \ (X86_RAW_EVENT_MASK | \ AMD64_EVENTSEL_EVENT) +#define AMD64_RAW_EVENT_MASK_NB \ + (AMD64_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK) #define AMD64_NUM_COUNTERS 4 #define AMD64_NUM_COUNTERS_CORE 6 +#define AMD64_NUM_COUNTERS_NB 4 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5199db2..fc30427 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -142,6 +142,11 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT; } +static inline unsigned long pud_pfn(pud_t pud) +{ + return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT; +} + #define pte_page(pte) pfn_to_page(pte_pfn(pte)) static inline int pmd_large(pmd_t pte) @@ -781,6 +786,18 @@ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) memcpy(dst, src, count * sizeof(pgd_t)); } +/* + * The x86 doesn't have any external MMU info: the kernel page + * tables contain all the necessary information. + */ +static inline void update_mmu_cache(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} +static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd) +{ +} #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 8faa215..9ee3221 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -66,13 +66,6 @@ do { \ __flush_tlb_one((vaddr)); \ } while (0) -/* - * The i386 doesn't have any external MMU info: the kernel page - * tables contain all the necessary information. - */ -#define update_mmu_cache(vma, address, ptep) do { } while (0) -#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) - #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 47356f9..615b0c7 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -142,9 +142,6 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) #define pte_unmap(pte) ((void)(pte))/* NOP */ -#define update_mmu_cache(vma, address, ptep) do { } while (0) -#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) - /* Encode and de-code a swap entry */ #if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 888184b..cf50054 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -943,7 +943,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); -extern int amd_get_nb_id(int cpu); +extern u16 amd_get_nb_id(int cpu); struct aperfmperf { u64 aperf, mperf; diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 6c7fc25..5c6e4fb 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -47,6 +47,12 @@ # define NEED_NOPL 0 #endif +#ifdef CONFIG_MATOM +# define NEED_MOVBE (1<<(X86_FEATURE_MOVBE & 31)) +#else +# define NEED_MOVBE 0 +#endif + #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT /* Paravirtualized systems may not have PSE or PGE available */ @@ -80,7 +86,7 @@ #define REQUIRED_MASK2 0 #define REQUIRED_MASK3 (NEED_NOPL) -#define REQUIRED_MASK4 0 +#define REQUIRED_MASK4 (NEED_MOVBE) #define REQUIRED_MASK5 0 #define REQUIRED_MASK6 0 #define REQUIRED_MASK7 0 diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index b47c2a8..062921e 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -16,7 +16,7 @@ extern void uv_system_init(void); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start, - unsigned end, + unsigned long end, unsigned int cpu); #else /* X86_UV */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 21f7385..2c32df9 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -5,7 +5,7 @@ * * SGI UV architectural definitions * - * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_HUB_H @@ -175,6 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); */ #define UV1_HUB_REVISION_BASE 1 #define UV2_HUB_REVISION_BASE 3 +#define UV3_HUB_REVISION_BASE 5 static inline int is_uv1_hub(void) { @@ -183,6 +184,23 @@ static inline int is_uv1_hub(void) static inline int is_uv2_hub(void) { + return ((uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE) && + (uv_hub_info->hub_revision < UV3_HUB_REVISION_BASE)); +} + +static inline int is_uv3_hub(void) +{ + return uv_hub_info->hub_revision >= UV3_HUB_REVISION_BASE; +} + +static inline int is_uv_hub(void) +{ + return uv_hub_info->hub_revision; +} + +/* code common to uv2 and uv3 only */ +static inline int is_uvx_hub(void) +{ return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE; } @@ -230,14 +248,23 @@ union uvh_apicid { #define UV2_LOCAL_MMR_SIZE (32UL * 1024 * 1024) #define UV2_GLOBAL_MMR32_SIZE (32UL * 1024 * 1024) -#define UV_LOCAL_MMR_BASE (is_uv1_hub() ? UV1_LOCAL_MMR_BASE \ - : UV2_LOCAL_MMR_BASE) -#define UV_GLOBAL_MMR32_BASE (is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE \ - : UV2_GLOBAL_MMR32_BASE) -#define UV_LOCAL_MMR_SIZE (is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \ - UV2_LOCAL_MMR_SIZE) +#define UV3_LOCAL_MMR_BASE 0xfa000000UL +#define UV3_GLOBAL_MMR32_BASE 0xfc000000UL +#define UV3_LOCAL_MMR_SIZE (32UL * 1024 * 1024) +#define UV3_GLOBAL_MMR32_SIZE (32UL * 1024 * 1024) + +#define UV_LOCAL_MMR_BASE (is_uv1_hub() ? UV1_LOCAL_MMR_BASE : \ + (is_uv2_hub() ? UV2_LOCAL_MMR_BASE : \ + UV3_LOCAL_MMR_BASE)) +#define UV_GLOBAL_MMR32_BASE (is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE :\ + (is_uv2_hub() ? UV2_GLOBAL_MMR32_BASE :\ + UV3_GLOBAL_MMR32_BASE)) +#define UV_LOCAL_MMR_SIZE (is_uv1_hub() ? UV1_LOCAL_MMR_SIZE : \ + (is_uv2_hub() ? UV2_LOCAL_MMR_SIZE : \ + UV3_LOCAL_MMR_SIZE)) #define UV_GLOBAL_MMR32_SIZE (is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\ - UV2_GLOBAL_MMR32_SIZE) + (is_uv2_hub() ? UV2_GLOBAL_MMR32_SIZE :\ + UV3_GLOBAL_MMR32_SIZE)) #define UV_GLOBAL_MMR64_BASE (uv_hub_info->global_mmr_base) #define UV_GLOBAL_GRU_MMR_BASE 0x4000000 @@ -599,6 +626,7 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) * 1 - UV1 rev 1.0 initial silicon * 2 - UV1 rev 2.0 production silicon * 3 - UV2 rev 1.0 initial silicon + * 5 - UV3 rev 1.0 initial silicon */ static inline int uv_get_min_hub_revision_id(void) { diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index cf1d736..bd5f80e 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -5,16 +5,25 @@ * * SGI UV MMR definitions * - * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_MMRS_H #define _ASM_X86_UV_UV_MMRS_H /* - * This file contains MMR definitions for both UV1 & UV2 hubs. + * This file contains MMR definitions for all UV hubs types. * - * In general, MMR addresses and structures are identical on both hubs. + * To minimize coding differences between hub types, the symbols are + * grouped by architecture types. + * + * UVH - definitions common to all UV hub types. + * UVXH - definitions common to all UV eXtended hub types (currently 2 & 3). + * UV1H - definitions specific to UV type 1 hub. + * UV2H - definitions specific to UV type 2 hub. + * UV3H - definitions specific to UV type 3 hub. + * + * So in general, MMR addresses and structures are identical on all hubs types. * These MMRs are identified as: * #define UVH_xxx <address> * union uvh_xxx { @@ -23,24 +32,36 @@ * } s; * }; * - * If the MMR exists on both hub type but has different addresses or - * contents, the MMR definition is similar to: - * #define UV1H_xxx <uv1 address> - * #define UV2H_xxx <uv2address> - * #define UVH_xxx (is_uv1_hub() ? UV1H_xxx : UV2H_xxx) + * If the MMR exists on all hub types but have different addresses: + * #define UV1Hxxx a + * #define UV2Hxxx b + * #define UV3Hxxx c + * #define UVHxxx (is_uv1_hub() ? UV1Hxxx : + * (is_uv2_hub() ? UV2Hxxx : + * UV3Hxxx)) + * + * If the MMR exists on all hub types > 1 but have different addresses: + * #define UV2Hxxx b + * #define UV3Hxxx c + * #define UVXHxxx (is_uv2_hub() ? UV2Hxxx : + * UV3Hxxx)) + * * union uvh_xxx { * unsigned long v; - * struct uv1h_int_cmpd_s { (Common fields only) + * struct uvh_xxx_s { # Common fields only * } s; - * struct uv1h_int_cmpd_s { (Full UV1 definition) + * struct uv1h_xxx_s { # Full UV1 definition (*) * } s1; - * struct uv2h_int_cmpd_s { (Full UV2 definition) + * struct uv2h_xxx_s { # Full UV2 definition (*) * } s2; + * struct uv3h_xxx_s { # Full UV3 definition (*) + * } s3; * }; + * (* - if present and different than the common struct) * - * Only essential difference are enumerated. For example, if the address is - * the same for both UV1 & UV2, only a single #define is generated. Likewise, - * if the contents is the same for both hubs, only the "s" structure is + * Only essential differences are enumerated. For example, if the address is + * the same for all UV's, only a single #define is generated. Likewise, + * if the contents is the same for all hubs, only the "s" structure is * generated. * * If the MMR exists on ONLY 1 type of hub, no generic definition is @@ -51,6 +72,8 @@ * struct uvh_int_cmpd_s { * } sn; * }; + * + * (GEN Flags: mflags_opt= undefs=0 UV23=UVXH) */ #define UV_MMR_ENABLE (1UL << 63) @@ -58,15 +81,18 @@ #define UV1_HUB_PART_NUMBER 0x88a5 #define UV2_HUB_PART_NUMBER 0x8eb8 #define UV2_HUB_PART_NUMBER_X 0x1111 +#define UV3_HUB_PART_NUMBER 0x9578 +#define UV3_HUB_PART_NUMBER_X 0x4321 -/* Compat: if this #define is present, UV headers support UV2 */ +/* Compat: Indicate which UV Hubs are supported. */ #define UV2_HUB_IS_SUPPORTED 1 +#define UV3_HUB_IS_SUPPORTED 1 /* ========================================================================= */ /* UVH_BAU_DATA_BROADCAST */ /* ========================================================================= */ -#define UVH_BAU_DATA_BROADCAST 0x61688UL -#define UVH_BAU_DATA_BROADCAST_32 0x440 +#define UVH_BAU_DATA_BROADCAST 0x61688UL +#define UVH_BAU_DATA_BROADCAST_32 0x440 #define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0 #define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL @@ -82,8 +108,8 @@ union uvh_bau_data_broadcast_u { /* ========================================================================= */ /* UVH_BAU_DATA_CONFIG */ /* ========================================================================= */ -#define UVH_BAU_DATA_CONFIG 0x61680UL -#define UVH_BAU_DATA_CONFIG_32 0x438 +#define UVH_BAU_DATA_CONFIG 0x61680UL +#define UVH_BAU_DATA_CONFIG_32 0x438 #define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0 #define UVH_BAU_DATA_CONFIG_DM_SHFT 8 @@ -121,10 +147,14 @@ union uvh_bau_data_config_u { /* ========================================================================= */ /* UVH_EVENT_OCCURRED0 */ /* ========================================================================= */ -#define UVH_EVENT_OCCURRED0 0x70000UL -#define UVH_EVENT_OCCURRED0_32 0x5e8 +#define UVH_EVENT_OCCURRED0 0x70000UL +#define UVH_EVENT_OCCURRED0_32 0x5e8 + +#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0 +#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 +#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL +#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL -#define UV1H_EVENT_OCCURRED0_LB_HCERR_SHFT 0 #define UV1H_EVENT_OCCURRED0_GR0_HCERR_SHFT 1 #define UV1H_EVENT_OCCURRED0_GR1_HCERR_SHFT 2 #define UV1H_EVENT_OCCURRED0_LH_HCERR_SHFT 3 @@ -135,7 +165,6 @@ union uvh_bau_data_config_u { #define UV1H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8 #define UV1H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9 #define UV1H_EVENT_OCCURRED0_LH_AOERR0_SHFT 10 -#define UV1H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 #define UV1H_EVENT_OCCURRED0_XN_AOERR0_SHFT 12 #define UV1H_EVENT_OCCURRED0_SI_AOERR0_SHFT 13 #define UV1H_EVENT_OCCURRED0_LB_AOERR1_SHFT 14 @@ -181,7 +210,6 @@ union uvh_bau_data_config_u { #define UV1H_EVENT_OCCURRED0_RTC3_SHFT 54 #define UV1H_EVENT_OCCURRED0_BAU_DATA_SHFT 55 #define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56 -#define UV1H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL #define UV1H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL #define UV1H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL #define UV1H_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL @@ -192,7 +220,6 @@ union uvh_bau_data_config_u { #define UV1H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL #define UV1H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL #define UV1H_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL -#define UV1H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL #define UV1H_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL #define UV1H_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL #define UV1H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL @@ -239,188 +266,130 @@ union uvh_bau_data_config_u { #define UV1H_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL #define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL -#define UV2H_EVENT_OCCURRED0_LB_HCERR_SHFT 0 -#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT 1 -#define UV2H_EVENT_OCCURRED0_RH_HCERR_SHFT 2 -#define UV2H_EVENT_OCCURRED0_LH0_HCERR_SHFT 3 -#define UV2H_EVENT_OCCURRED0_LH1_HCERR_SHFT 4 -#define UV2H_EVENT_OCCURRED0_GR0_HCERR_SHFT 5 -#define UV2H_EVENT_OCCURRED0_GR1_HCERR_SHFT 6 -#define UV2H_EVENT_OCCURRED0_NI0_HCERR_SHFT 7 -#define UV2H_EVENT_OCCURRED0_NI1_HCERR_SHFT 8 -#define UV2H_EVENT_OCCURRED0_LB_AOERR0_SHFT 9 -#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10 -#define UV2H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 -#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12 -#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13 -#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14 -#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15 -#define UV2H_EVENT_OCCURRED0_XB_AOERR0_SHFT 16 -#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17 -#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18 -#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19 -#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20 -#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21 -#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22 -#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23 -#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24 -#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25 -#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26 -#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27 -#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28 -#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29 -#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30 -#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46 -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47 -#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48 -#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49 -#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50 -#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51 -#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52 -#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT 53 -#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54 -#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55 -#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56 -#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57 -#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58 -#define UV2H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL -#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL -#define UV2H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL -#define UV2H_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL -#define UV2H_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL -#define UV2H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL -#define UV2H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL -#define UV2H_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL -#define UV2H_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL -#define UV2H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL -#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL -#define UV2H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL -#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL -#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL -#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL -#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL -#define UV2H_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL -#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL -#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL -#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL -#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL -#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL -#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL -#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL -#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL -#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL -#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL -#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL -#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL -#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL -#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL -#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL -#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL -#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL -#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL -#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL -#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL -#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL -#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL -#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL -#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL -#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL -#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL -#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL +#define UVXH_EVENT_OCCURRED0_QP_HCERR_SHFT 1 +#define UVXH_EVENT_OCCURRED0_RH_HCERR_SHFT 2 +#define UVXH_EVENT_OCCURRED0_LH0_HCERR_SHFT 3 +#define UVXH_EVENT_OCCURRED0_LH1_HCERR_SHFT 4 +#define UVXH_EVENT_OCCURRED0_GR0_HCERR_SHFT 5 +#define UVXH_EVENT_OCCURRED0_GR1_HCERR_SHFT 6 +#define UVXH_EVENT_OCCURRED0_NI0_HCERR_SHFT 7 +#define UVXH_EVENT_OCCURRED0_NI1_HCERR_SHFT 8 +#define UVXH_EVENT_OCCURRED0_LB_AOERR0_SHFT 9 +#define UVXH_EVENT_OCCURRED0_QP_AOERR0_SHFT 10 +#define UVXH_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12 +#define UVXH_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13 +#define UVXH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14 +#define UVXH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15 +#define UVXH_EVENT_OCCURRED0_XB_AOERR0_SHFT 16 +#define UVXH_EVENT_OCCURRED0_RT_AOERR0_SHFT 17 +#define UVXH_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18 +#define UVXH_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19 +#define UVXH_EVENT_OCCURRED0_LB_AOERR1_SHFT 20 +#define UVXH_EVENT_OCCURRED0_QP_AOERR1_SHFT 21 +#define UVXH_EVENT_OCCURRED0_RH_AOERR1_SHFT 22 +#define UVXH_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23 +#define UVXH_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24 +#define UVXH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25 +#define UVXH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26 +#define UVXH_EVENT_OCCURRED0_XB_AOERR1_SHFT 27 +#define UVXH_EVENT_OCCURRED0_RT_AOERR1_SHFT 28 +#define UVXH_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29 +#define UVXH_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30 +#define UVXH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46 +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47 +#define UVXH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48 +#define UVXH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49 +#define UVXH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50 +#define UVXH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51 +#define UVXH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52 +#define UVXH_EVENT_OCCURRED0_IPI_INT_SHFT 53 +#define UVXH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54 +#define UVXH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55 +#define UVXH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56 +#define UVXH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57 +#define UVXH_EVENT_OCCURRED0_PROFILE_INT_SHFT 58 +#define UVXH_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL +#define UVXH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL +#define UVXH_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL +#define UVXH_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL +#define UVXH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL +#define UVXH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL +#define UVXH_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL +#define UVXH_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL +#define UVXH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL +#define UVXH_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL +#define UVXH_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL +#define UVXH_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL +#define UVXH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL +#define UVXH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL +#define UVXH_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL +#define UVXH_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL +#define UVXH_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL +#define UVXH_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL +#define UVXH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL +#define UVXH_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL +#define UVXH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL +#define UVXH_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL +#define UVXH_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL +#define UVXH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL +#define UVXH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL +#define UVXH_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL +#define UVXH_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL +#define UVXH_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL +#define UVXH_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL +#define UVXH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL +#define UVXH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL +#define UVXH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL +#define UVXH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL +#define UVXH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL +#define UVXH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL +#define UVXH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL +#define UVXH_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL +#define UVXH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL +#define UVXH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL +#define UVXH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL +#define UVXH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL +#define UVXH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL union uvh_event_occurred0_u { unsigned long v; - struct uv1h_event_occurred0_s { + struct uvh_event_occurred0_s { unsigned long lb_hcerr:1; /* RW, W1C */ - unsigned long gr0_hcerr:1; /* RW, W1C */ - unsigned long gr1_hcerr:1; /* RW, W1C */ - unsigned long lh_hcerr:1; /* RW, W1C */ - unsigned long rh_hcerr:1; /* RW, W1C */ - unsigned long xn_hcerr:1; /* RW, W1C */ - unsigned long si_hcerr:1; /* RW, W1C */ - unsigned long lb_aoerr0:1; /* RW, W1C */ - unsigned long gr0_aoerr0:1; /* RW, W1C */ - unsigned long gr1_aoerr0:1; /* RW, W1C */ - unsigned long lh_aoerr0:1; /* RW, W1C */ + unsigned long rsvd_1_10:10; unsigned long rh_aoerr0:1; /* RW, W1C */ - unsigned long xn_aoerr0:1; /* RW, W1C */ - unsigned long si_aoerr0:1; /* RW, W1C */ - unsigned long lb_aoerr1:1; /* RW, W1C */ - unsigned long gr0_aoerr1:1; /* RW, W1C */ - unsigned long gr1_aoerr1:1; /* RW, W1C */ - unsigned long lh_aoerr1:1; /* RW, W1C */ - unsigned long rh_aoerr1:1; /* RW, W1C */ - unsigned long xn_aoerr1:1; /* RW, W1C */ - unsigned long si_aoerr1:1; /* RW, W1C */ - unsigned long rh_vpi_int:1; /* RW, W1C */ - unsigned long system_shutdown_int:1; /* RW, W1C */ - unsigned long lb_irq_int_0:1; /* RW, W1C */ - unsigned long lb_irq_int_1:1; /* RW, W1C */ - unsigned long lb_irq_int_2:1; /* RW, W1C */ - unsigned long lb_irq_int_3:1; /* RW, W1C */ - unsigned long lb_irq_int_4:1; /* RW, W1C */ - unsigned long lb_irq_int_5:1; /* RW, W1C */ - unsigned long lb_irq_int_6:1; /* RW, W1C */ - unsigned long lb_irq_int_7:1; /* RW, W1C */ - unsigned long lb_irq_int_8:1; /* RW, W1C */ - unsigned long lb_irq_int_9:1; /* RW, W1C */ - unsigned long lb_irq_int_10:1; /* RW, W1C */ - unsigned long lb_irq_int_11:1; /* RW, W1C */ - unsigned long lb_irq_int_12:1; /* RW, W1C */ - unsigned long lb_irq_int_13:1; /* RW, W1C */ - unsigned long lb_irq_int_14:1; /* RW, W1C */ - unsigned long lb_irq_int_15:1; /* RW, W1C */ - unsigned long l1_nmi_int:1; /* RW, W1C */ - unsigned long stop_clock:1; /* RW, W1C */ - unsigned long asic_to_l1:1; /* RW, W1C */ - unsigned long l1_to_asic:1; /* RW, W1C */ - unsigned long ltc_int:1; /* RW, W1C */ - unsigned long la_seq_trigger:1; /* RW, W1C */ - unsigned long ipi_int:1; /* RW, W1C */ - unsigned long extio_int0:1; /* RW, W1C */ - unsigned long extio_int1:1; /* RW, W1C */ - unsigned long extio_int2:1; /* RW, W1C */ - unsigned long extio_int3:1; /* RW, W1C */ - unsigned long profile_int:1; /* RW, W1C */ - unsigned long rtc0:1; /* RW, W1C */ - unsigned long rtc1:1; /* RW, W1C */ - unsigned long rtc2:1; /* RW, W1C */ - unsigned long rtc3:1; /* RW, W1C */ - unsigned long bau_data:1; /* RW, W1C */ - unsigned long power_management_req:1; /* RW, W1C */ - unsigned long rsvd_57_63:7; - } s1; - struct uv2h_event_occurred0_s { + unsigned long rsvd_12_63:52; + } s; + struct uvxh_event_occurred0_s { unsigned long lb_hcerr:1; /* RW */ unsigned long qp_hcerr:1; /* RW */ unsigned long rh_hcerr:1; /* RW */ @@ -481,19 +450,20 @@ union uvh_event_occurred0_u { unsigned long extio_int3:1; /* RW */ unsigned long profile_int:1; /* RW */ unsigned long rsvd_59_63:5; - } s2; + } sx; }; /* ========================================================================= */ /* UVH_EVENT_OCCURRED0_ALIAS */ /* ========================================================================= */ -#define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL -#define UVH_EVENT_OCCURRED0_ALIAS_32 0x5f0 +#define UVH_EVENT_OCCURRED0_ALIAS 0x70008UL +#define UVH_EVENT_OCCURRED0_ALIAS_32 0x5f0 + /* ========================================================================= */ /* UVH_GR0_TLB_INT0_CONFIG */ /* ========================================================================= */ -#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL +#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL #define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0 #define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8 @@ -531,7 +501,7 @@ union uvh_gr0_tlb_int0_config_u { /* ========================================================================= */ /* UVH_GR0_TLB_INT1_CONFIG */ /* ========================================================================= */ -#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL +#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL #define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0 #define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8 @@ -571,9 +541,11 @@ union uvh_gr0_tlb_int1_config_u { /* ========================================================================= */ #define UV1H_GR0_TLB_MMR_CONTROL 0x401080UL #define UV2H_GR0_TLB_MMR_CONTROL 0xc01080UL -#define UVH_GR0_TLB_MMR_CONTROL (is_uv1_hub() ? \ - UV1H_GR0_TLB_MMR_CONTROL : \ - UV2H_GR0_TLB_MMR_CONTROL) +#define UV3H_GR0_TLB_MMR_CONTROL 0xc01080UL +#define UVH_GR0_TLB_MMR_CONTROL \ + (is_uv1_hub() ? UV1H_GR0_TLB_MMR_CONTROL : \ + (is_uv2_hub() ? UV2H_GR0_TLB_MMR_CONTROL : \ + UV3H_GR0_TLB_MMR_CONTROL)) #define UVH_GR0_TLB_MMR_CONTROL_INDEX_SHFT 0 #define UVH_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 @@ -611,6 +583,21 @@ union uvh_gr0_tlb_int1_config_u { #define UV1H_GR0_TLB_MMR_CONTROL_MMR_INJ_TLBRREG_MASK 0x0100000000000000UL #define UV1H_GR0_TLB_MMR_CONTROL_MMR_INJ_TLBLRUV_MASK 0x1000000000000000UL +#define UVXH_GR0_TLB_MMR_CONTROL_INDEX_SHFT 0 +#define UVXH_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 +#define UVXH_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT 16 +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT 20 +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_WRITE_SHFT 30 +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_READ_SHFT 31 +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT 32 +#define UVXH_GR0_TLB_MMR_CONTROL_INDEX_MASK 0x0000000000000fffUL +#define UVXH_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK 0x0000000000003000UL +#define UVXH_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK 0x0000000000010000UL +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK 0x0000000000100000UL +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_WRITE_MASK 0x0000000040000000UL +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_READ_MASK 0x0000000080000000UL +#define UVXH_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_MASK 0x0000000100000000UL + #define UV2H_GR0_TLB_MMR_CONTROL_INDEX_SHFT 0 #define UV2H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 #define UV2H_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT 16 @@ -630,6 +617,23 @@ union uvh_gr0_tlb_int1_config_u { #define UV2H_GR0_TLB_MMR_CONTROL_MMR_INJ_CON_MASK 0x0001000000000000UL #define UV2H_GR0_TLB_MMR_CONTROL_MMR_INJ_TLBRAM_MASK 0x0010000000000000UL +#define UV3H_GR0_TLB_MMR_CONTROL_INDEX_SHFT 0 +#define UV3H_GR0_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 +#define UV3H_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT 16 +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT 20 +#define UV3H_GR0_TLB_MMR_CONTROL_ECC_SEL_SHFT 21 +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_WRITE_SHFT 30 +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_READ_SHFT 31 +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT 32 +#define UV3H_GR0_TLB_MMR_CONTROL_INDEX_MASK 0x0000000000000fffUL +#define UV3H_GR0_TLB_MMR_CONTROL_MEM_SEL_MASK 0x0000000000003000UL +#define UV3H_GR0_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK 0x0000000000010000UL +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK 0x0000000000100000UL +#define UV3H_GR0_TLB_MMR_CONTROL_ECC_SEL_MASK 0x0000000000200000UL +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_WRITE_MASK 0x0000000040000000UL +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_READ_MASK 0x0000000080000000UL +#define UV3H_GR0_TLB_MMR_CONTROL_MMR_OP_DONE_MASK 0x0000000100000000UL + union uvh_gr0_tlb_mmr_control_u { unsigned long v; struct uvh_gr0_tlb_mmr_control_s { @@ -642,7 +646,9 @@ union uvh_gr0_tlb_mmr_control_u { unsigned long rsvd_21_29:9; unsigned long mmr_write:1; /* WP */ unsigned long mmr_read:1; /* WP */ - unsigned long rsvd_32_63:32; + unsigned long rsvd_32_48:17; + unsigned long rsvd_49_51:3; + unsigned long rsvd_52_63:12; } s; struct uv1h_gr0_tlb_mmr_control_s { unsigned long index:12; /* RW */ @@ -666,6 +672,23 @@ union uvh_gr0_tlb_mmr_control_u { unsigned long mmr_inj_tlblruv:1; /* RW */ unsigned long rsvd_61_63:3; } s1; + struct uvxh_gr0_tlb_mmr_control_s { + unsigned long index:12; /* RW */ + unsigned long mem_sel:2; /* RW */ + unsigned long rsvd_14_15:2; + unsigned long auto_valid_en:1; /* RW */ + unsigned long rsvd_17_19:3; + unsigned long mmr_hash_index_en:1; /* RW */ + unsigned long rsvd_21_29:9; + unsigned long mmr_write:1; /* WP */ + unsigned long mmr_read:1; /* WP */ + unsigned long mmr_op_done:1; /* RW */ + unsigned long rsvd_33_47:15; + unsigned long rsvd_48:1; + unsigned long rsvd_49_51:3; + unsigned long rsvd_52:1; + unsigned long rsvd_53_63:11; + } sx; struct uv2h_gr0_tlb_mmr_control_s { unsigned long index:12; /* RW */ unsigned long mem_sel:2; /* RW */ @@ -683,6 +706,24 @@ union uvh_gr0_tlb_mmr_control_u { unsigned long mmr_inj_tlbram:1; /* RW */ unsigned long rsvd_53_63:11; } s2; + struct uv3h_gr0_tlb_mmr_control_s { + unsigned long index:12; /* RW */ + unsigned long mem_sel:2; /* RW */ + unsigned long rsvd_14_15:2; + unsigned long auto_valid_en:1; /* RW */ + unsigned long rsvd_17_19:3; + unsigned long mmr_hash_index_en:1; /* RW */ + unsigned long ecc_sel:1; /* RW */ + unsigned long rsvd_22_29:8; + unsigned long mmr_write:1; /* WP */ + unsigned long mmr_read:1; /* WP */ + unsigned long mmr_op_done:1; /* RW */ + unsigned long rsvd_33_47:15; + unsigned long undef_48:1; /* Undefined */ + unsigned long rsvd_49_51:3; + unsigned long undef_52:1; /* Undefined */ + unsigned long rsvd_53_63:11; + } s3; }; /* ========================================================================= */ @@ -690,9 +731,11 @@ union uvh_gr0_tlb_mmr_control_u { /* ========================================================================= */ #define UV1H_GR0_TLB_MMR_READ_DATA_HI 0x4010a0UL #define UV2H_GR0_TLB_MMR_READ_DATA_HI 0xc010a0UL -#define UVH_GR0_TLB_MMR_READ_DATA_HI (is_uv1_hub() ? \ - UV1H_GR0_TLB_MMR_READ_DATA_HI : \ - UV2H_GR0_TLB_MMR_READ_DATA_HI) +#define UV3H_GR0_TLB_MMR_READ_DATA_HI 0xc010a0UL +#define UVH_GR0_TLB_MMR_READ_DATA_HI \ + (is_uv1_hub() ? UV1H_GR0_TLB_MMR_READ_DATA_HI : \ + (is_uv2_hub() ? UV2H_GR0_TLB_MMR_READ_DATA_HI : \ + UV3H_GR0_TLB_MMR_READ_DATA_HI)) #define UVH_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 #define UVH_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 @@ -703,6 +746,46 @@ union uvh_gr0_tlb_mmr_control_u { #define UVH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL #define UVH_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UV1H_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL + +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UVXH_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL + +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UV2H_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL + +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_AA_EXT_SHFT 45 +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_WAY_ECC_SHFT 55 +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_AA_EXT_MASK 0x0000200000000000UL +#define UV3H_GR0_TLB_MMR_READ_DATA_HI_WAY_ECC_MASK 0xff80000000000000UL + union uvh_gr0_tlb_mmr_read_data_hi_u { unsigned long v; struct uvh_gr0_tlb_mmr_read_data_hi_s { @@ -712,6 +795,36 @@ union uvh_gr0_tlb_mmr_read_data_hi_u { unsigned long larger:1; /* RO */ unsigned long rsvd_45_63:19; } s; + struct uv1h_gr0_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long rsvd_45_63:19; + } s1; + struct uvxh_gr0_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long rsvd_45_63:19; + } sx; + struct uv2h_gr0_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long rsvd_45_63:19; + } s2; + struct uv3h_gr0_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long aa_ext:1; /* RO */ + unsigned long undef_46_54:9; /* Undefined */ + unsigned long way_ecc:9; /* RO */ + } s3; }; /* ========================================================================= */ @@ -719,9 +832,11 @@ union uvh_gr0_tlb_mmr_read_data_hi_u { /* ========================================================================= */ #define UV1H_GR0_TLB_MMR_READ_DATA_LO 0x4010a8UL #define UV2H_GR0_TLB_MMR_READ_DATA_LO 0xc010a8UL -#define UVH_GR0_TLB_MMR_READ_DATA_LO (is_uv1_hub() ? \ - UV1H_GR0_TLB_MMR_READ_DATA_LO : \ - UV2H_GR0_TLB_MMR_READ_DATA_LO) +#define UV3H_GR0_TLB_MMR_READ_DATA_LO 0xc010a8UL +#define UVH_GR0_TLB_MMR_READ_DATA_LO \ + (is_uv1_hub() ? UV1H_GR0_TLB_MMR_READ_DATA_LO : \ + (is_uv2_hub() ? UV2H_GR0_TLB_MMR_READ_DATA_LO : \ + UV3H_GR0_TLB_MMR_READ_DATA_LO)) #define UVH_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 #define UVH_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 @@ -730,6 +845,34 @@ union uvh_gr0_tlb_mmr_read_data_hi_u { #define UVH_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL #define UVH_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL +#define UV1H_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UV1H_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UV1H_GR0_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UV1H_GR0_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UV1H_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UV1H_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + +#define UVXH_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UVXH_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UVXH_GR0_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UVXH_GR0_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UVXH_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UVXH_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + +#define UV2H_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UV2H_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UV2H_GR0_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UV2H_GR0_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UV2H_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UV2H_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + +#define UV3H_GR0_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UV3H_GR0_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UV3H_GR0_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UV3H_GR0_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UV3H_GR0_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UV3H_GR0_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + union uvh_gr0_tlb_mmr_read_data_lo_u { unsigned long v; struct uvh_gr0_tlb_mmr_read_data_lo_s { @@ -737,12 +880,32 @@ union uvh_gr0_tlb_mmr_read_data_lo_u { unsigned long asid:24; /* RO */ unsigned long valid:1; /* RO */ } s; + struct uv1h_gr0_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } s1; + struct uvxh_gr0_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } sx; + struct uv2h_gr0_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } s2; + struct uv3h_gr0_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } s3; }; /* ========================================================================= */ /* UVH_GR1_TLB_INT0_CONFIG */ /* ========================================================================= */ -#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL +#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL #define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0 #define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8 @@ -780,7 +943,7 @@ union uvh_gr1_tlb_int0_config_u { /* ========================================================================= */ /* UVH_GR1_TLB_INT1_CONFIG */ /* ========================================================================= */ -#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL +#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL #define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0 #define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8 @@ -820,9 +983,11 @@ union uvh_gr1_tlb_int1_config_u { /* ========================================================================= */ #define UV1H_GR1_TLB_MMR_CONTROL 0x801080UL #define UV2H_GR1_TLB_MMR_CONTROL 0x1001080UL -#define UVH_GR1_TLB_MMR_CONTROL (is_uv1_hub() ? \ - UV1H_GR1_TLB_MMR_CONTROL : \ - UV2H_GR1_TLB_MMR_CONTROL) +#define UV3H_GR1_TLB_MMR_CONTROL 0x1001080UL +#define UVH_GR1_TLB_MMR_CONTROL \ + (is_uv1_hub() ? UV1H_GR1_TLB_MMR_CONTROL : \ + (is_uv2_hub() ? UV2H_GR1_TLB_MMR_CONTROL : \ + UV3H_GR1_TLB_MMR_CONTROL)) #define UVH_GR1_TLB_MMR_CONTROL_INDEX_SHFT 0 #define UVH_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 @@ -860,6 +1025,21 @@ union uvh_gr1_tlb_int1_config_u { #define UV1H_GR1_TLB_MMR_CONTROL_MMR_INJ_TLBRREG_MASK 0x0100000000000000UL #define UV1H_GR1_TLB_MMR_CONTROL_MMR_INJ_TLBLRUV_MASK 0x1000000000000000UL +#define UVXH_GR1_TLB_MMR_CONTROL_INDEX_SHFT 0 +#define UVXH_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 +#define UVXH_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT 16 +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT 20 +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_WRITE_SHFT 30 +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_READ_SHFT 31 +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT 32 +#define UVXH_GR1_TLB_MMR_CONTROL_INDEX_MASK 0x0000000000000fffUL +#define UVXH_GR1_TLB_MMR_CONTROL_MEM_SEL_MASK 0x0000000000003000UL +#define UVXH_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK 0x0000000000010000UL +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK 0x0000000000100000UL +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_WRITE_MASK 0x0000000040000000UL +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_READ_MASK 0x0000000080000000UL +#define UVXH_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_MASK 0x0000000100000000UL + #define UV2H_GR1_TLB_MMR_CONTROL_INDEX_SHFT 0 #define UV2H_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 #define UV2H_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT 16 @@ -879,6 +1059,23 @@ union uvh_gr1_tlb_int1_config_u { #define UV2H_GR1_TLB_MMR_CONTROL_MMR_INJ_CON_MASK 0x0001000000000000UL #define UV2H_GR1_TLB_MMR_CONTROL_MMR_INJ_TLBRAM_MASK 0x0010000000000000UL +#define UV3H_GR1_TLB_MMR_CONTROL_INDEX_SHFT 0 +#define UV3H_GR1_TLB_MMR_CONTROL_MEM_SEL_SHFT 12 +#define UV3H_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_SHFT 16 +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_SHFT 20 +#define UV3H_GR1_TLB_MMR_CONTROL_ECC_SEL_SHFT 21 +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_WRITE_SHFT 30 +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_READ_SHFT 31 +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_SHFT 32 +#define UV3H_GR1_TLB_MMR_CONTROL_INDEX_MASK 0x0000000000000fffUL +#define UV3H_GR1_TLB_MMR_CONTROL_MEM_SEL_MASK 0x0000000000003000UL +#define UV3H_GR1_TLB_MMR_CONTROL_AUTO_VALID_EN_MASK 0x0000000000010000UL +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_HASH_INDEX_EN_MASK 0x0000000000100000UL +#define UV3H_GR1_TLB_MMR_CONTROL_ECC_SEL_MASK 0x0000000000200000UL +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_WRITE_MASK 0x0000000040000000UL +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_READ_MASK 0x0000000080000000UL +#define UV3H_GR1_TLB_MMR_CONTROL_MMR_OP_DONE_MASK 0x0000000100000000UL + union uvh_gr1_tlb_mmr_control_u { unsigned long v; struct uvh_gr1_tlb_mmr_control_s { @@ -891,7 +1088,9 @@ union uvh_gr1_tlb_mmr_control_u { unsigned long rsvd_21_29:9; unsigned long mmr_write:1; /* WP */ unsigned long mmr_read:1; /* WP */ - unsigned long rsvd_32_63:32; + unsigned long rsvd_32_48:17; + unsigned long rsvd_49_51:3; + unsigned long rsvd_52_63:12; } s; struct uv1h_gr1_tlb_mmr_control_s { unsigned long index:12; /* RW */ @@ -915,6 +1114,23 @@ union uvh_gr1_tlb_mmr_control_u { unsigned long mmr_inj_tlblruv:1; /* RW */ unsigned long rsvd_61_63:3; } s1; + struct uvxh_gr1_tlb_mmr_control_s { + unsigned long index:12; /* RW */ + unsigned long mem_sel:2; /* RW */ + unsigned long rsvd_14_15:2; + unsigned long auto_valid_en:1; /* RW */ + unsigned long rsvd_17_19:3; + unsigned long mmr_hash_index_en:1; /* RW */ + unsigned long rsvd_21_29:9; + unsigned long mmr_write:1; /* WP */ + unsigned long mmr_read:1; /* WP */ + unsigned long mmr_op_done:1; /* RW */ + unsigned long rsvd_33_47:15; + unsigned long rsvd_48:1; + unsigned long rsvd_49_51:3; + unsigned long rsvd_52:1; + unsigned long rsvd_53_63:11; + } sx; struct uv2h_gr1_tlb_mmr_control_s { unsigned long index:12; /* RW */ unsigned long mem_sel:2; /* RW */ @@ -932,6 +1148,24 @@ union uvh_gr1_tlb_mmr_control_u { unsigned long mmr_inj_tlbram:1; /* RW */ unsigned long rsvd_53_63:11; } s2; + struct uv3h_gr1_tlb_mmr_control_s { + unsigned long index:12; /* RW */ + unsigned long mem_sel:2; /* RW */ + unsigned long rsvd_14_15:2; + unsigned long auto_valid_en:1; /* RW */ + unsigned long rsvd_17_19:3; + unsigned long mmr_hash_index_en:1; /* RW */ + unsigned long ecc_sel:1; /* RW */ + unsigned long rsvd_22_29:8; + unsigned long mmr_write:1; /* WP */ + unsigned long mmr_read:1; /* WP */ + unsigned long mmr_op_done:1; /* RW */ + unsigned long rsvd_33_47:15; + unsigned long undef_48:1; /* Undefined */ + unsigned long rsvd_49_51:3; + unsigned long undef_52:1; /* Undefined */ + unsigned long rsvd_53_63:11; + } s3; }; /* ========================================================================= */ @@ -939,9 +1173,11 @@ union uvh_gr1_tlb_mmr_control_u { /* ========================================================================= */ #define UV1H_GR1_TLB_MMR_READ_DATA_HI 0x8010a0UL #define UV2H_GR1_TLB_MMR_READ_DATA_HI 0x10010a0UL -#define UVH_GR1_TLB_MMR_READ_DATA_HI (is_uv1_hub() ? \ - UV1H_GR1_TLB_MMR_READ_DATA_HI : \ - UV2H_GR1_TLB_MMR_READ_DATA_HI) +#define UV3H_GR1_TLB_MMR_READ_DATA_HI 0x10010a0UL +#define UVH_GR1_TLB_MMR_READ_DATA_HI \ + (is_uv1_hub() ? UV1H_GR1_TLB_MMR_READ_DATA_HI : \ + (is_uv2_hub() ? UV2H_GR1_TLB_MMR_READ_DATA_HI : \ + UV3H_GR1_TLB_MMR_READ_DATA_HI)) #define UVH_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 #define UVH_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 @@ -952,6 +1188,46 @@ union uvh_gr1_tlb_mmr_control_u { #define UVH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL #define UVH_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UV1H_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL + +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UVXH_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL + +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UV2H_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL + +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_PFN_SHFT 0 +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_GAA_SHFT 41 +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_SHFT 43 +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_LARGER_SHFT 44 +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_AA_EXT_SHFT 45 +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_WAY_ECC_SHFT 55 +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_PFN_MASK 0x000001ffffffffffUL +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_GAA_MASK 0x0000060000000000UL +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_DIRTY_MASK 0x0000080000000000UL +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_LARGER_MASK 0x0000100000000000UL +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_AA_EXT_MASK 0x0000200000000000UL +#define UV3H_GR1_TLB_MMR_READ_DATA_HI_WAY_ECC_MASK 0xff80000000000000UL + union uvh_gr1_tlb_mmr_read_data_hi_u { unsigned long v; struct uvh_gr1_tlb_mmr_read_data_hi_s { @@ -961,6 +1237,36 @@ union uvh_gr1_tlb_mmr_read_data_hi_u { unsigned long larger:1; /* RO */ unsigned long rsvd_45_63:19; } s; + struct uv1h_gr1_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long rsvd_45_63:19; + } s1; + struct uvxh_gr1_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long rsvd_45_63:19; + } sx; + struct uv2h_gr1_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long rsvd_45_63:19; + } s2; + struct uv3h_gr1_tlb_mmr_read_data_hi_s { + unsigned long pfn:41; /* RO */ + unsigned long gaa:2; /* RO */ + unsigned long dirty:1; /* RO */ + unsigned long larger:1; /* RO */ + unsigned long aa_ext:1; /* RO */ + unsigned long undef_46_54:9; /* Undefined */ + unsigned long way_ecc:9; /* RO */ + } s3; }; /* ========================================================================= */ @@ -968,9 +1274,11 @@ union uvh_gr1_tlb_mmr_read_data_hi_u { /* ========================================================================= */ #define UV1H_GR1_TLB_MMR_READ_DATA_LO 0x8010a8UL #define UV2H_GR1_TLB_MMR_READ_DATA_LO 0x10010a8UL -#define UVH_GR1_TLB_MMR_READ_DATA_LO (is_uv1_hub() ? \ - UV1H_GR1_TLB_MMR_READ_DATA_LO : \ - UV2H_GR1_TLB_MMR_READ_DATA_LO) +#define UV3H_GR1_TLB_MMR_READ_DATA_LO 0x10010a8UL +#define UVH_GR1_TLB_MMR_READ_DATA_LO \ + (is_uv1_hub() ? UV1H_GR1_TLB_MMR_READ_DATA_LO : \ + (is_uv2_hub() ? UV2H_GR1_TLB_MMR_READ_DATA_LO : \ + UV3H_GR1_TLB_MMR_READ_DATA_LO)) #define UVH_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 #define UVH_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 @@ -979,6 +1287,34 @@ union uvh_gr1_tlb_mmr_read_data_hi_u { #define UVH_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL #define UVH_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL +#define UV1H_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UV1H_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UV1H_GR1_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UV1H_GR1_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UV1H_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UV1H_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + +#define UVXH_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UVXH_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UVXH_GR1_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UVXH_GR1_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UVXH_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UVXH_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + +#define UV2H_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UV2H_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UV2H_GR1_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UV2H_GR1_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UV2H_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UV2H_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + +#define UV3H_GR1_TLB_MMR_READ_DATA_LO_VPN_SHFT 0 +#define UV3H_GR1_TLB_MMR_READ_DATA_LO_ASID_SHFT 39 +#define UV3H_GR1_TLB_MMR_READ_DATA_LO_VALID_SHFT 63 +#define UV3H_GR1_TLB_MMR_READ_DATA_LO_VPN_MASK 0x0000007fffffffffUL +#define UV3H_GR1_TLB_MMR_READ_DATA_LO_ASID_MASK 0x7fffff8000000000UL +#define UV3H_GR1_TLB_MMR_READ_DATA_LO_VALID_MASK 0x8000000000000000UL + union uvh_gr1_tlb_mmr_read_data_lo_u { unsigned long v; struct uvh_gr1_tlb_mmr_read_data_lo_s { @@ -986,12 +1322,32 @@ union uvh_gr1_tlb_mmr_read_data_lo_u { unsigned long asid:24; /* RO */ unsigned long valid:1; /* RO */ } s; + struct uv1h_gr1_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } s1; + struct uvxh_gr1_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } sx; + struct uv2h_gr1_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } s2; + struct uv3h_gr1_tlb_mmr_read_data_lo_s { + unsigned long vpn:39; /* RO */ + unsigned long asid:24; /* RO */ + unsigned long valid:1; /* RO */ + } s3; }; /* ========================================================================= */ /* UVH_INT_CMPB */ /* ========================================================================= */ -#define UVH_INT_CMPB 0x22080UL +#define UVH_INT_CMPB 0x22080UL #define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT 0 #define UVH_INT_CMPB_REAL_TIME_CMPB_MASK 0x00ffffffffffffffUL @@ -1007,10 +1363,13 @@ union uvh_int_cmpb_u { /* ========================================================================= */ /* UVH_INT_CMPC */ /* ========================================================================= */ -#define UVH_INT_CMPC 0x22100UL +#define UVH_INT_CMPC 0x22100UL + +#define UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT 0 +#define UV1H_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL -#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0 -#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0xffffffffffffffUL +#define UVXH_INT_CMPC_REAL_TIME_CMP_2_SHFT 0 +#define UVXH_INT_CMPC_REAL_TIME_CMP_2_MASK 0x00ffffffffffffffUL union uvh_int_cmpc_u { unsigned long v; @@ -1023,10 +1382,13 @@ union uvh_int_cmpc_u { /* ========================================================================= */ /* UVH_INT_CMPD */ /* ========================================================================= */ -#define UVH_INT_CMPD 0x22180UL +#define UVH_INT_CMPD 0x22180UL -#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0 -#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0xffffffffffffffUL +#define UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT 0 +#define UV1H_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL + +#define UVXH_INT_CMPD_REAL_TIME_CMP_3_SHFT 0 +#define UVXH_INT_CMPD_REAL_TIME_CMP_3_MASK 0x00ffffffffffffffUL union uvh_int_cmpd_u { unsigned long v; @@ -1039,8 +1401,8 @@ union uvh_int_cmpd_u { /* ========================================================================= */ /* UVH_IPI_INT */ /* ========================================================================= */ -#define UVH_IPI_INT 0x60500UL -#define UVH_IPI_INT_32 0x348 +#define UVH_IPI_INT 0x60500UL +#define UVH_IPI_INT_32 0x348 #define UVH_IPI_INT_VECTOR_SHFT 0 #define UVH_IPI_INT_DELIVERY_MODE_SHFT 8 @@ -1069,8 +1431,8 @@ union uvh_ipi_int_u { /* ========================================================================= */ /* UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST */ /* ========================================================================= */ -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0 +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49 @@ -1091,8 +1453,8 @@ union uvh_lb_bau_intd_payload_queue_first_u { /* ========================================================================= */ /* UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST */ /* ========================================================================= */ -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8 +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL @@ -1109,8 +1471,8 @@ union uvh_lb_bau_intd_payload_queue_last_u { /* ========================================================================= */ /* UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL */ /* ========================================================================= */ -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL -#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0 +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL +#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL @@ -1127,8 +1489,8 @@ union uvh_lb_bau_intd_payload_queue_tail_u { /* ========================================================================= */ /* UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE */ /* ========================================================================= */ -#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL -#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68 +#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL +#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1 @@ -1189,14 +1551,21 @@ union uvh_lb_bau_intd_software_acknowledge_u { /* ========================================================================= */ /* UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS */ /* ========================================================================= */ -#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL -#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70 +#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x320088UL +#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70 + /* ========================================================================= */ /* UVH_LB_BAU_MISC_CONTROL */ /* ========================================================================= */ -#define UVH_LB_BAU_MISC_CONTROL 0x320170UL -#define UVH_LB_BAU_MISC_CONTROL_32 0xa10 +#define UVH_LB_BAU_MISC_CONTROL 0x320170UL +#define UV1H_LB_BAU_MISC_CONTROL 0x320170UL +#define UV2H_LB_BAU_MISC_CONTROL 0x320170UL +#define UV3H_LB_BAU_MISC_CONTROL 0x320170UL +#define UVH_LB_BAU_MISC_CONTROL_32 0xa10 +#define UV1H_LB_BAU_MISC_CONTROL_32 0x320170UL +#define UV2H_LB_BAU_MISC_CONTROL_32 0x320170UL +#define UV3H_LB_BAU_MISC_CONTROL_32 0x320170UL #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 #define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 @@ -1213,6 +1582,7 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UVH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24 #define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 +#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL #define UVH_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL #define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL @@ -1228,6 +1598,7 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UVH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL #define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL +#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL #define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 #define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 @@ -1262,6 +1633,53 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL #define UV1H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL +#define UVXH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 +#define UVXH_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 +#define UVXH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9 +#define UVXH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10 +#define UVXH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11 +#define UVXH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14 +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15 +#define UVXH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16 +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20 +#define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21 +#define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22 +#define UVXH_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23 +#define UVXH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24 +#define UVXH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27 +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29 +#define UVXH_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT 30 +#define UVXH_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31 +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32 +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33 +#define UVXH_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34 +#define UVXH_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35 +#define UVXH_LB_BAU_MISC_CONTROL_FUN_SHFT 48 +#define UVXH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL +#define UVXH_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL +#define UVXH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL +#define UVXH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL +#define UVXH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL +#define UVXH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL +#define UVXH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL +#define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL +#define UVXH_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL +#define UVXH_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL +#define UVXH_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL +#define UVXH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL +#define UVXH_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK 0x0000000040000000UL +#define UVXH_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL +#define UVXH_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL +#define UVXH_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL +#define UVXH_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL +#define UVXH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL + #define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 #define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 #define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9 @@ -1309,6 +1727,59 @@ union uvh_lb_bau_intd_software_acknowledge_u { #define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL #define UV2H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL +#define UV3H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0 +#define UV3H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8 +#define UV3H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9 +#define UV3H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10 +#define UV3H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11 +#define UV3H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15 +#define UV3H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20 +#define UV3H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21 +#define UV3H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22 +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23 +#define UV3H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24 +#define UV3H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29 +#define UV3H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT 30 +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33 +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34 +#define UV3H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35 +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_QUIESCE_MSGS_TO_QPI_SHFT 36 +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_PREFETCH_HINT_SHFT 37 +#define UV3H_LB_BAU_MISC_CONTROL_THREAD_KILL_TIMEBASE_SHFT 38 +#define UV3H_LB_BAU_MISC_CONTROL_FUN_SHFT 48 +#define UV3H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL +#define UV3H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL +#define UV3H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL +#define UV3H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL +#define UV3H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL +#define UV3H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL +#define UV3H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL +#define UV3H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL +#define UV3H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL +#define UV3H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL +#define UV3H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL +#define UV3H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK 0x0000000040000000UL +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL +#define UV3H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL +#define UV3H_LB_BAU_MISC_CONTROL_SUPPRESS_QUIESCE_MSGS_TO_QPI_MASK 0x0000001000000000UL +#define UV3H_LB_BAU_MISC_CONTROL_ENABLE_INTD_PREFETCH_HINT_MASK 0x0000002000000000UL +#define UV3H_LB_BAU_MISC_CONTROL_THREAD_KILL_TIMEBASE_MASK 0x00003fc000000000UL +#define UV3H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL + union uvh_lb_bau_misc_control_u { unsigned long v; struct uvh_lb_bau_misc_control_s { @@ -1327,7 +1798,8 @@ union uvh_lb_bau_misc_control_u { unsigned long programmed_initial_priority:3; /* RW */ unsigned long use_incoming_priority:1; /* RW */ unsigned long enable_programmed_initial_priority:1;/* RW */ - unsigned long rsvd_29_63:35; + unsigned long rsvd_29_47:19; + unsigned long fun:16; /* RW */ } s; struct uv1h_lb_bau_misc_control_s { unsigned long rejection_delay:8; /* RW */ @@ -1348,6 +1820,32 @@ union uvh_lb_bau_misc_control_u { unsigned long rsvd_29_47:19; unsigned long fun:16; /* RW */ } s1; + struct uvxh_lb_bau_misc_control_s { + unsigned long rejection_delay:8; /* RW */ + unsigned long apic_mode:1; /* RW */ + unsigned long force_broadcast:1; /* RW */ + unsigned long force_lock_nop:1; /* RW */ + unsigned long qpi_agent_presence_vector:3; /* RW */ + unsigned long descriptor_fetch_mode:1; /* RW */ + unsigned long enable_intd_soft_ack_mode:1; /* RW */ + unsigned long intd_soft_ack_timeout_period:4; /* RW */ + unsigned long enable_dual_mapping_mode:1; /* RW */ + unsigned long vga_io_port_decode_enable:1; /* RW */ + unsigned long vga_io_port_16_bit_decode:1; /* RW */ + unsigned long suppress_dest_registration:1; /* RW */ + unsigned long programmed_initial_priority:3; /* RW */ + unsigned long use_incoming_priority:1; /* RW */ + unsigned long enable_programmed_initial_priority:1;/* RW */ + unsigned long enable_automatic_apic_mode_selection:1;/* RW */ + unsigned long apic_mode_status:1; /* RO */ + unsigned long suppress_interrupts_to_self:1; /* RW */ + unsigned long enable_lock_based_system_flush:1;/* RW */ + unsigned long enable_extended_sb_status:1; /* RW */ + unsigned long suppress_int_prio_udt_to_self:1;/* RW */ + unsigned long use_legacy_descriptor_formats:1;/* RW */ + unsigned long rsvd_36_47:12; + unsigned long fun:16; /* RW */ + } sx; struct uv2h_lb_bau_misc_control_s { unsigned long rejection_delay:8; /* RW */ unsigned long apic_mode:1; /* RW */ @@ -1374,13 +1872,42 @@ union uvh_lb_bau_misc_control_u { unsigned long rsvd_36_47:12; unsigned long fun:16; /* RW */ } s2; + struct uv3h_lb_bau_misc_control_s { + unsigned long rejection_delay:8; /* RW */ + unsigned long apic_mode:1; /* RW */ + unsigned long force_broadcast:1; /* RW */ + unsigned long force_lock_nop:1; /* RW */ + unsigned long qpi_agent_presence_vector:3; /* RW */ + unsigned long descriptor_fetch_mode:1; /* RW */ + unsigned long enable_intd_soft_ack_mode:1; /* RW */ + unsigned long intd_soft_ack_timeout_period:4; /* RW */ + unsigned long enable_dual_mapping_mode:1; /* RW */ + unsigned long vga_io_port_decode_enable:1; /* RW */ + unsigned long vga_io_port_16_bit_decode:1; /* RW */ + unsigned long suppress_dest_registration:1; /* RW */ + unsigned long programmed_initial_priority:3; /* RW */ + unsigned long use_incoming_priority:1; /* RW */ + unsigned long enable_programmed_initial_priority:1;/* RW */ + unsigned long enable_automatic_apic_mode_selection:1;/* RW */ + unsigned long apic_mode_status:1; /* RO */ + unsigned long suppress_interrupts_to_self:1; /* RW */ + unsigned long enable_lock_based_system_flush:1;/* RW */ + unsigned long enable_extended_sb_status:1; /* RW */ + unsigned long suppress_int_prio_udt_to_self:1;/* RW */ + unsigned long use_legacy_descriptor_formats:1;/* RW */ + unsigned long suppress_quiesce_msgs_to_qpi:1; /* RW */ + unsigned long enable_intd_prefetch_hint:1; /* RW */ + unsigned long thread_kill_timebase:8; /* RW */ + unsigned long rsvd_46_47:2; + unsigned long fun:16; /* RW */ + } s3; }; /* ========================================================================= */ /* UVH_LB_BAU_SB_ACTIVATION_CONTROL */ /* ========================================================================= */ -#define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL -#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8 +#define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL +#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT 62 @@ -1402,8 +1929,8 @@ union uvh_lb_bau_sb_activation_control_u { /* ========================================================================= */ /* UVH_LB_BAU_SB_ACTIVATION_STATUS_0 */ /* ========================================================================= */ -#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL -#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0 +#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL +#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL @@ -1418,8 +1945,8 @@ union uvh_lb_bau_sb_activation_status_0_u { /* ========================================================================= */ /* UVH_LB_BAU_SB_ACTIVATION_STATUS_1 */ /* ========================================================================= */ -#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL -#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8 +#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL +#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL @@ -1434,8 +1961,8 @@ union uvh_lb_bau_sb_activation_status_1_u { /* ========================================================================= */ /* UVH_LB_BAU_SB_DESCRIPTOR_BASE */ /* ========================================================================= */ -#define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL -#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0 +#define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL +#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49 @@ -1456,7 +1983,10 @@ union uvh_lb_bau_sb_descriptor_base_u { /* ========================================================================= */ /* UVH_NODE_ID */ /* ========================================================================= */ -#define UVH_NODE_ID 0x0UL +#define UVH_NODE_ID 0x0UL +#define UV1H_NODE_ID 0x0UL +#define UV2H_NODE_ID 0x0UL +#define UV3H_NODE_ID 0x0UL #define UVH_NODE_ID_FORCE1_SHFT 0 #define UVH_NODE_ID_MANUFACTURER_SHFT 1 @@ -1484,6 +2014,21 @@ union uvh_lb_bau_sb_descriptor_base_u { #define UV1H_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL #define UV1H_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL +#define UVXH_NODE_ID_FORCE1_SHFT 0 +#define UVXH_NODE_ID_MANUFACTURER_SHFT 1 +#define UVXH_NODE_ID_PART_NUMBER_SHFT 12 +#define UVXH_NODE_ID_REVISION_SHFT 28 +#define UVXH_NODE_ID_NODE_ID_SHFT 32 +#define UVXH_NODE_ID_NODES_PER_BIT_SHFT 50 +#define UVXH_NODE_ID_NI_PORT_SHFT 57 +#define UVXH_NODE_ID_FORCE1_MASK 0x0000000000000001UL +#define UVXH_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL +#define UVXH_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL +#define UVXH_NODE_ID_REVISION_MASK 0x00000000f0000000UL +#define UVXH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL +#define UVXH_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL +#define UVXH_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL + #define UV2H_NODE_ID_FORCE1_SHFT 0 #define UV2H_NODE_ID_MANUFACTURER_SHFT 1 #define UV2H_NODE_ID_PART_NUMBER_SHFT 12 @@ -1499,6 +2044,25 @@ union uvh_lb_bau_sb_descriptor_base_u { #define UV2H_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL #define UV2H_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL +#define UV3H_NODE_ID_FORCE1_SHFT 0 +#define UV3H_NODE_ID_MANUFACTURER_SHFT 1 +#define UV3H_NODE_ID_PART_NUMBER_SHFT 12 +#define UV3H_NODE_ID_REVISION_SHFT 28 +#define UV3H_NODE_ID_NODE_ID_SHFT 32 +#define UV3H_NODE_ID_ROUTER_SELECT_SHFT 48 +#define UV3H_NODE_ID_RESERVED_2_SHFT 49 +#define UV3H_NODE_ID_NODES_PER_BIT_SHFT 50 +#define UV3H_NODE_ID_NI_PORT_SHFT 57 +#define UV3H_NODE_ID_FORCE1_MASK 0x0000000000000001UL +#define UV3H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL +#define UV3H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL +#define UV3H_NODE_ID_REVISION_MASK 0x00000000f0000000UL +#define UV3H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL +#define UV3H_NODE_ID_ROUTER_SELECT_MASK 0x0001000000000000UL +#define UV3H_NODE_ID_RESERVED_2_MASK 0x0002000000000000UL +#define UV3H_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL +#define UV3H_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL + union uvh_node_id_u { unsigned long v; struct uvh_node_id_s { @@ -1521,6 +2085,17 @@ union uvh_node_id_u { unsigned long ni_port:4; /* RO */ unsigned long rsvd_60_63:4; } s1; + struct uvxh_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:15; /* RW */ + unsigned long rsvd_47_49:3; + unsigned long nodes_per_bit:7; /* RO */ + unsigned long ni_port:5; /* RO */ + unsigned long rsvd_62_63:2; + } sx; struct uv2h_node_id_s { unsigned long force1:1; /* RO */ unsigned long manufacturer:11; /* RO */ @@ -1532,13 +2107,26 @@ union uvh_node_id_u { unsigned long ni_port:5; /* RO */ unsigned long rsvd_62_63:2; } s2; + struct uv3h_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:15; /* RW */ + unsigned long rsvd_47:1; + unsigned long router_select:1; /* RO */ + unsigned long rsvd_49:1; + unsigned long nodes_per_bit:7; /* RO */ + unsigned long ni_port:5; /* RO */ + unsigned long rsvd_62_63:2; + } s3; }; /* ========================================================================= */ /* UVH_NODE_PRESENT_TABLE */ /* ========================================================================= */ -#define UVH_NODE_PRESENT_TABLE 0x1400UL -#define UVH_NODE_PRESENT_TABLE_DEPTH 16 +#define UVH_NODE_PRESENT_TABLE 0x1400UL +#define UVH_NODE_PRESENT_TABLE_DEPTH 16 #define UVH_NODE_PRESENT_TABLE_NODES_SHFT 0 #define UVH_NODE_PRESENT_TABLE_NODES_MASK 0xffffffffffffffffUL @@ -1553,7 +2141,7 @@ union uvh_node_present_table_u { /* ========================================================================= */ /* UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL +#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48 @@ -1577,7 +2165,7 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL +#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48 @@ -1601,7 +2189,7 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL +#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48 @@ -1625,7 +2213,7 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL +#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL @@ -1642,7 +2230,7 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL +#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL @@ -1659,7 +2247,7 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL +#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL @@ -1676,7 +2264,10 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_CONFIG_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_CONFIG_MMR 0x1600000UL +#define UVH_RH_GAM_CONFIG_MMR 0x1600000UL +#define UV1H_RH_GAM_CONFIG_MMR 0x1600000UL +#define UV2H_RH_GAM_CONFIG_MMR 0x1600000UL +#define UV3H_RH_GAM_CONFIG_MMR 0x1600000UL #define UVH_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 @@ -1690,11 +2281,21 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u { #define UV1H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL #define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL +#define UVXH_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0 +#define UVXH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 +#define UVXH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL +#define UVXH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL + #define UV2H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0 #define UV2H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 #define UV2H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL #define UV2H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL +#define UV3H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0 +#define UV3H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6 +#define UV3H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL +#define UV3H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL + union uvh_rh_gam_config_mmr_u { unsigned long v; struct uvh_rh_gam_config_mmr_s { @@ -1709,20 +2310,37 @@ union uvh_rh_gam_config_mmr_u { unsigned long mmiol_cfg:1; /* RW */ unsigned long rsvd_13_63:51; } s1; + struct uvxh_rh_gam_config_mmr_s { + unsigned long m_skt:6; /* RW */ + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } sx; struct uv2h_rh_gam_config_mmr_s { unsigned long m_skt:6; /* RW */ unsigned long n_skt:4; /* RW */ unsigned long rsvd_10_63:54; } s2; + struct uv3h_rh_gam_config_mmr_s { + unsigned long m_skt:6; /* RW */ + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } s3; }; /* ========================================================================= */ /* UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL +#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48 @@ -1733,6 +2351,13 @@ union uvh_rh_gam_config_mmr_u { #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL #define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + #define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 #define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 #define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 @@ -1740,12 +2365,23 @@ union uvh_rh_gam_config_mmr_u { #define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL #define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28 +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52 +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_MODE_SHFT 62 +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_MODE_MASK 0x4000000000000000UL +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + union uvh_rh_gam_gru_overlay_config_mmr_u { unsigned long v; struct uvh_rh_gam_gru_overlay_config_mmr_s { unsigned long rsvd_0_27:28; unsigned long base:18; /* RW */ - unsigned long rsvd_46_62:17; + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; unsigned long enable:1; /* RW */ } s; struct uv1h_rh_gam_gru_overlay_config_mmr_s { @@ -1758,6 +2394,14 @@ union uvh_rh_gam_gru_overlay_config_mmr_u { unsigned long rsvd_56_62:7; unsigned long enable:1; /* RW */ } s1; + struct uvxh_rh_gam_gru_overlay_config_mmr_s { + unsigned long rsvd_0_27:28; + unsigned long base:18; /* RW */ + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } sx; struct uv2h_rh_gam_gru_overlay_config_mmr_s { unsigned long rsvd_0_27:28; unsigned long base:18; /* RW */ @@ -1766,12 +2410,22 @@ union uvh_rh_gam_gru_overlay_config_mmr_u { unsigned long rsvd_56_62:7; unsigned long enable:1; /* RW */ } s2; + struct uv3h_rh_gam_gru_overlay_config_mmr_s { + unsigned long rsvd_0_27:28; + unsigned long base:18; /* RW */ + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_61:6; + unsigned long mode:1; /* RW */ + unsigned long enable:1; /* RW */ + } s3; }; /* ========================================================================= */ /* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL +#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46 @@ -1814,10 +2468,15 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u { /* ========================================================================= */ /* UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR */ /* ========================================================================= */ -#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL +#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL +#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL +#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL +#define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 +#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL +#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46 @@ -1826,11 +2485,21 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u { #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + #define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 #define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 #define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL #define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL +#define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26 +#define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63 +#define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL +#define UV3H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL + union uvh_rh_gam_mmr_overlay_config_mmr_u { unsigned long v; struct uvh_rh_gam_mmr_overlay_config_mmr_s { @@ -1846,18 +2515,30 @@ union uvh_rh_gam_mmr_overlay_config_mmr_u { unsigned long rsvd_47_62:16; unsigned long enable:1; /* RW */ } s1; + struct uvxh_rh_gam_mmr_overlay_config_mmr_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } sx; struct uv2h_rh_gam_mmr_overlay_config_mmr_s { unsigned long rsvd_0_25:26; unsigned long base:20; /* RW */ unsigned long rsvd_46_62:17; unsigned long enable:1; /* RW */ } s2; + struct uv3h_rh_gam_mmr_overlay_config_mmr_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } s3; }; /* ========================================================================= */ /* UVH_RTC */ /* ========================================================================= */ -#define UVH_RTC 0x340000UL +#define UVH_RTC 0x340000UL #define UVH_RTC_REAL_TIME_CLOCK_SHFT 0 #define UVH_RTC_REAL_TIME_CLOCK_MASK 0x00ffffffffffffffUL @@ -1873,7 +2554,7 @@ union uvh_rtc_u { /* ========================================================================= */ /* UVH_RTC1_INT_CONFIG */ /* ========================================================================= */ -#define UVH_RTC1_INT_CONFIG 0x615c0UL +#define UVH_RTC1_INT_CONFIG 0x615c0UL #define UVH_RTC1_INT_CONFIG_VECTOR_SHFT 0 #define UVH_RTC1_INT_CONFIG_DM_SHFT 8 @@ -1911,8 +2592,8 @@ union uvh_rtc1_int_config_u { /* ========================================================================= */ /* UVH_SCRATCH5 */ /* ========================================================================= */ -#define UVH_SCRATCH5 0x2d0200UL -#define UVH_SCRATCH5_32 0x778 +#define UVH_SCRATCH5 0x2d0200UL +#define UVH_SCRATCH5_32 0x778 #define UVH_SCRATCH5_SCRATCH5_SHFT 0 #define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL @@ -1925,79 +2606,79 @@ union uvh_scratch5_u { }; /* ========================================================================= */ -/* UV2H_EVENT_OCCURRED2 */ -/* ========================================================================= */ -#define UV2H_EVENT_OCCURRED2 0x70100UL -#define UV2H_EVENT_OCCURRED2_32 0xb68 - -#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT 0 -#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT 1 -#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT 2 -#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT 3 -#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT 4 -#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT 5 -#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT 6 -#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT 7 -#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT 8 -#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT 9 -#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT 10 -#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT 11 -#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT 12 -#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT 13 -#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT 14 -#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT 15 -#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT 16 -#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT 17 -#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT 18 -#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT 19 -#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT 20 -#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT 21 -#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT 22 -#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT 23 -#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT 24 -#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT 25 -#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT 26 -#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT 27 -#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT 28 -#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT 29 -#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT 30 -#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT 31 -#define UV2H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL -#define UV2H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL -#define UV2H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL -#define UV2H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL -#define UV2H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL -#define UV2H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL -#define UV2H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL -#define UV2H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL -#define UV2H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL -#define UV2H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL -#define UV2H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL -#define UV2H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL -#define UV2H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL -#define UV2H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL -#define UV2H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL -#define UV2H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL -#define UV2H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL -#define UV2H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL -#define UV2H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL -#define UV2H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL -#define UV2H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL -#define UV2H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL -#define UV2H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL -#define UV2H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL -#define UV2H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL -#define UV2H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL -#define UV2H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL -#define UV2H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL -#define UV2H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL -#define UV2H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL -#define UV2H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL -#define UV2H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL - -union uv2h_event_occurred2_u { +/* UVXH_EVENT_OCCURRED2 */ +/* ========================================================================= */ +#define UVXH_EVENT_OCCURRED2 0x70100UL +#define UVXH_EVENT_OCCURRED2_32 0xb68 + +#define UVXH_EVENT_OCCURRED2_RTC_0_SHFT 0 +#define UVXH_EVENT_OCCURRED2_RTC_1_SHFT 1 +#define UVXH_EVENT_OCCURRED2_RTC_2_SHFT 2 +#define UVXH_EVENT_OCCURRED2_RTC_3_SHFT 3 +#define UVXH_EVENT_OCCURRED2_RTC_4_SHFT 4 +#define UVXH_EVENT_OCCURRED2_RTC_5_SHFT 5 +#define UVXH_EVENT_OCCURRED2_RTC_6_SHFT 6 +#define UVXH_EVENT_OCCURRED2_RTC_7_SHFT 7 +#define UVXH_EVENT_OCCURRED2_RTC_8_SHFT 8 +#define UVXH_EVENT_OCCURRED2_RTC_9_SHFT 9 +#define UVXH_EVENT_OCCURRED2_RTC_10_SHFT 10 +#define UVXH_EVENT_OCCURRED2_RTC_11_SHFT 11 +#define UVXH_EVENT_OCCURRED2_RTC_12_SHFT 12 +#define UVXH_EVENT_OCCURRED2_RTC_13_SHFT 13 +#define UVXH_EVENT_OCCURRED2_RTC_14_SHFT 14 +#define UVXH_EVENT_OCCURRED2_RTC_15_SHFT 15 +#define UVXH_EVENT_OCCURRED2_RTC_16_SHFT 16 +#define UVXH_EVENT_OCCURRED2_RTC_17_SHFT 17 +#define UVXH_EVENT_OCCURRED2_RTC_18_SHFT 18 +#define UVXH_EVENT_OCCURRED2_RTC_19_SHFT 19 +#define UVXH_EVENT_OCCURRED2_RTC_20_SHFT 20 +#define UVXH_EVENT_OCCURRED2_RTC_21_SHFT 21 +#define UVXH_EVENT_OCCURRED2_RTC_22_SHFT 22 +#define UVXH_EVENT_OCCURRED2_RTC_23_SHFT 23 +#define UVXH_EVENT_OCCURRED2_RTC_24_SHFT 24 +#define UVXH_EVENT_OCCURRED2_RTC_25_SHFT 25 +#define UVXH_EVENT_OCCURRED2_RTC_26_SHFT 26 +#define UVXH_EVENT_OCCURRED2_RTC_27_SHFT 27 +#define UVXH_EVENT_OCCURRED2_RTC_28_SHFT 28 +#define UVXH_EVENT_OCCURRED2_RTC_29_SHFT 29 +#define UVXH_EVENT_OCCURRED2_RTC_30_SHFT 30 +#define UVXH_EVENT_OCCURRED2_RTC_31_SHFT 31 +#define UVXH_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL +#define UVXH_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL +#define UVXH_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL +#define UVXH_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL +#define UVXH_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL +#define UVXH_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL +#define UVXH_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL +#define UVXH_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL +#define UVXH_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL +#define UVXH_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL +#define UVXH_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL +#define UVXH_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL +#define UVXH_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL +#define UVXH_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL +#define UVXH_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL +#define UVXH_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL +#define UVXH_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL +#define UVXH_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL +#define UVXH_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL +#define UVXH_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL +#define UVXH_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL +#define UVXH_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL +#define UVXH_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL +#define UVXH_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL +#define UVXH_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL +#define UVXH_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL +#define UVXH_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL +#define UVXH_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL +#define UVXH_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL +#define UVXH_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL +#define UVXH_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL +#define UVXH_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL + +union uvxh_event_occurred2_u { unsigned long v; - struct uv2h_event_occurred2_s { + struct uvxh_event_occurred2_s { unsigned long rtc_0:1; /* RW */ unsigned long rtc_1:1; /* RW */ unsigned long rtc_2:1; /* RW */ @@ -2031,29 +2712,46 @@ union uv2h_event_occurred2_u { unsigned long rtc_30:1; /* RW */ unsigned long rtc_31:1; /* RW */ unsigned long rsvd_32_63:32; - } s1; + } sx; }; /* ========================================================================= */ -/* UV2H_EVENT_OCCURRED2_ALIAS */ +/* UVXH_EVENT_OCCURRED2_ALIAS */ /* ========================================================================= */ -#define UV2H_EVENT_OCCURRED2_ALIAS 0x70108UL -#define UV2H_EVENT_OCCURRED2_ALIAS_32 0xb70 +#define UVXH_EVENT_OCCURRED2_ALIAS 0x70108UL +#define UVXH_EVENT_OCCURRED2_ALIAS_32 0xb70 + /* ========================================================================= */ -/* UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 */ +/* UVXH_LB_BAU_SB_ACTIVATION_STATUS_2 */ /* ========================================================================= */ -#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL -#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0 +#define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL +#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL +#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL +#define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0 +#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x320130UL +#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x320130UL + +#define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0 +#define UVXH_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL #define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0 #define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL -union uv2h_lb_bau_sb_activation_status_2_u { +#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0 +#define UV3H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL + +union uvxh_lb_bau_sb_activation_status_2_u { unsigned long v; + struct uvxh_lb_bau_sb_activation_status_2_s { + unsigned long aux_error:64; /* RW */ + } sx; struct uv2h_lb_bau_sb_activation_status_2_s { unsigned long aux_error:64; /* RW */ - } s1; + } s2; + struct uv3h_lb_bau_sb_activation_status_2_s { + unsigned long aux_error:64; /* RW */ + } s3; }; /* ========================================================================= */ @@ -2073,5 +2771,87 @@ union uv1h_lb_target_physical_apic_id_mask_u { } s1; }; +/* ========================================================================= */ +/* UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR */ +/* ========================================================================= */ +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL + +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT 26 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 46 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x00003ffffc000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x000fc00000000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL + +union uv3h_rh_gam_mmioh_overlay_config0_mmr_u { + unsigned long v; + struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s3; +}; + +/* ========================================================================= */ +/* UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR */ +/* ========================================================================= */ +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1604000UL + +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT 26 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 46 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x00003ffffc000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x000fc00000000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL + +union uv3h_rh_gam_mmioh_overlay_config1_mmr_u { + unsigned long v; + struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s3; +}; + +/* ========================================================================= */ +/* UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR */ +/* ========================================================================= */ +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x1603800UL +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128 + +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0 +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL + +union uv3h_rh_gam_mmioh_redirect_config0_mmr_u { + unsigned long v; + struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s3; +}; + +/* ========================================================================= */ +/* UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR */ +/* ========================================================================= */ +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x1604800UL +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128 + +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0 +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL + +union uv3h_rh_gam_mmioh_redirect_config1_mmr_u { + unsigned long v; + struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s3; +}; + #endif /* _ASM_X86_UV_UV_MMRS_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 5769349..7669941 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -181,19 +181,38 @@ struct x86_platform_ops { }; struct pci_dev; +struct msi_msg; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); + void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq, + unsigned int dest, struct msi_msg *msg, + u8 hpet_id); void (*teardown_msi_irq)(unsigned int irq); void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev, int irq); + int (*setup_hpet_msi)(unsigned int irq, unsigned int id); }; +struct IO_APIC_route_entry; +struct io_apic_irq_attr; +struct irq_data; +struct cpumask; + struct x86_io_apic_ops { - void (*init) (void); - unsigned int (*read) (unsigned int apic, unsigned int reg); - void (*write) (unsigned int apic, unsigned int reg, unsigned int value); - void (*modify)(unsigned int apic, unsigned int reg, unsigned int value); + void (*init) (void); + unsigned int (*read) (unsigned int apic, unsigned int reg); + void (*write) (unsigned int apic, unsigned int reg, unsigned int value); + void (*modify) (unsigned int apic, unsigned int reg, unsigned int value); + void (*disable)(void); + void (*print_entries)(unsigned int apic, unsigned int nr_entries); + int (*set_affinity)(struct irq_data *data, + const struct cpumask *mask, + bool force); + int (*setup_entry)(int irq, struct IO_APIC_route_entry *entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr); + void (*eoi_ioapic_pin)(int apic, int pin, int vector); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h index f8fde90..d882975 100644 --- a/arch/x86/include/asm/xor.h +++ b/arch/x86/include/asm/xor.h @@ -1,10 +1,499 @@ #ifdef CONFIG_KMEMCHECK /* kmemcheck doesn't handle MMX/SSE/SSE2 instructions */ # include <asm-generic/xor.h> +#elif !defined(_ASM_X86_XOR_H) +#define _ASM_X86_XOR_H + +/* + * Optimized RAID-5 checksumming functions for SSE. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * You should have received a copy of the GNU General Public License + * (for example /usr/src/linux/COPYING); if not, write to the Free + * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +/* + * Cache avoiding checksumming functions utilizing KNI instructions + * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) + */ + +/* + * Based on + * High-speed RAID5 checksumming functions utilizing SSE instructions. + * Copyright (C) 1998 Ingo Molnar. + */ + +/* + * x86-64 changes / gcc fixes from Andi Kleen. + * Copyright 2002 Andi Kleen, SuSE Labs. + * + * This hasn't been optimized for the hammer yet, but there are likely + * no advantages to be gotten from x86-64 here anyways. + */ + +#include <asm/i387.h> + +#ifdef CONFIG_X86_32 +/* reduce register pressure */ +# define XOR_CONSTANT_CONSTRAINT "i" #else +# define XOR_CONSTANT_CONSTRAINT "re" +#endif + +#define OFFS(x) "16*("#x")" +#define PF_OFFS(x) "256+16*("#x")" +#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n" +#define LD(x, y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n" +#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n" +#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n" +#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n" +#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n" +#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n" +#define XO1(x, y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n" +#define XO2(x, y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n" +#define XO3(x, y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n" +#define XO4(x, y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n" +#define NOP(x) + +#define BLK64(pf, op, i) \ + pf(i) \ + op(i, 0) \ + op(i + 1, 1) \ + op(i + 2, 2) \ + op(i + 3, 3) + +static void +xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + LD(i, 0) \ + LD(i + 1, 1) \ + PF1(i) \ + PF1(i + 2) \ + LD(i + 2, 2) \ + LD(i + 3, 3) \ + PF0(i + 4) \ + PF0(i + 6) \ + XO1(i, 0) \ + XO1(i + 1, 1) \ + XO1(i + 2, 2) \ + XO1(i + 3, 3) \ + ST(i, 0) \ + ST(i + 1, 1) \ + ST(i + 2, 2) \ + ST(i + 3, 3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), + [p1] "+r" (p1), [p2] "+r" (p2) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_2_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + BLK64(PF0, LD, i) \ + BLK64(PF1, XO1, i) \ + BLK64(NOP, ST, i) \ + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), + [p1] "+r" (p1), [p2] "+r" (p2) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + PF1(i) \ + PF1(i + 2) \ + LD(i, 0) \ + LD(i + 1, 1) \ + LD(i + 2, 2) \ + LD(i + 3, 3) \ + PF2(i) \ + PF2(i + 2) \ + PF0(i + 4) \ + PF0(i + 6) \ + XO1(i, 0) \ + XO1(i + 1, 1) \ + XO1(i + 2, 2) \ + XO1(i + 3, 3) \ + XO2(i, 0) \ + XO2(i + 1, 1) \ + XO2(i + 2, 2) \ + XO2(i + 3, 3) \ + ST(i, 0) \ + ST(i + 1, 1) \ + ST(i + 2, 2) \ + ST(i + 3, 3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " add %[inc], %[p3] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), + [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_3_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + BLK64(PF0, LD, i) \ + BLK64(PF1, XO1, i) \ + BLK64(PF2, XO2, i) \ + BLK64(NOP, ST, i) \ + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " add %[inc], %[p3] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), + [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + PF1(i) \ + PF1(i + 2) \ + LD(i, 0) \ + LD(i + 1, 1) \ + LD(i + 2, 2) \ + LD(i + 3, 3) \ + PF2(i) \ + PF2(i + 2) \ + XO1(i, 0) \ + XO1(i + 1, 1) \ + XO1(i + 2, 2) \ + XO1(i + 3, 3) \ + PF3(i) \ + PF3(i + 2) \ + PF0(i + 4) \ + PF0(i + 6) \ + XO2(i, 0) \ + XO2(i + 1, 1) \ + XO2(i + 2, 2) \ + XO2(i + 3, 3) \ + XO3(i, 0) \ + XO3(i + 1, 1) \ + XO3(i + 2, 2) \ + XO3(i + 3, 3) \ + ST(i, 0) \ + ST(i + 1, 1) \ + ST(i + 2, 2) \ + ST(i + 3, 3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " add %[inc], %[p3] ;\n" + " add %[inc], %[p4] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), [p1] "+r" (p1), + [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_4_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + BLK64(PF0, LD, i) \ + BLK64(PF1, XO1, i) \ + BLK64(PF2, XO2, i) \ + BLK64(PF3, XO3, i) \ + BLK64(NOP, ST, i) \ + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " add %[inc], %[p3] ;\n" + " add %[inc], %[p4] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), [p1] "+r" (p1), + [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + PF1(i) \ + PF1(i + 2) \ + LD(i, 0) \ + LD(i + 1, 1) \ + LD(i + 2, 2) \ + LD(i + 3, 3) \ + PF2(i) \ + PF2(i + 2) \ + XO1(i, 0) \ + XO1(i + 1, 1) \ + XO1(i + 2, 2) \ + XO1(i + 3, 3) \ + PF3(i) \ + PF3(i + 2) \ + XO2(i, 0) \ + XO2(i + 1, 1) \ + XO2(i + 2, 2) \ + XO2(i + 3, 3) \ + PF4(i) \ + PF4(i + 2) \ + PF0(i + 4) \ + PF0(i + 6) \ + XO3(i, 0) \ + XO3(i + 1, 1) \ + XO3(i + 2, 2) \ + XO3(i + 3, 3) \ + XO4(i, 0) \ + XO4(i + 1, 1) \ + XO4(i + 2, 2) \ + XO4(i + 3, 3) \ + ST(i, 0) \ + ST(i + 1, 1) \ + ST(i + 2, 2) \ + ST(i + 3, 3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " add %[inc], %[p3] ;\n" + " add %[inc], %[p4] ;\n" + " add %[inc], %[p5] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), + [p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static void +xor_sse_5_pf64(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + unsigned long lines = bytes >> 8; + + kernel_fpu_begin(); + + asm volatile( +#undef BLOCK +#define BLOCK(i) \ + BLK64(PF0, LD, i) \ + BLK64(PF1, XO1, i) \ + BLK64(PF2, XO2, i) \ + BLK64(PF3, XO3, i) \ + BLK64(PF4, XO4, i) \ + BLK64(NOP, ST, i) \ + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " add %[inc], %[p1] ;\n" + " add %[inc], %[p2] ;\n" + " add %[inc], %[p3] ;\n" + " add %[inc], %[p4] ;\n" + " add %[inc], %[p5] ;\n" + " dec %[cnt] ;\n" + " jnz 1b ;\n" + : [cnt] "+r" (lines), [p1] "+r" (p1), [p2] "+r" (p2), + [p3] "+r" (p3), [p4] "+r" (p4), [p5] "+r" (p5) + : [inc] XOR_CONSTANT_CONSTRAINT (256UL) + : "memory"); + + kernel_fpu_end(); +} + +static struct xor_block_template xor_block_sse_pf64 = { + .name = "prefetch64-sse", + .do_2 = xor_sse_2_pf64, + .do_3 = xor_sse_3_pf64, + .do_4 = xor_sse_4_pf64, + .do_5 = xor_sse_5_pf64, +}; + +#undef LD +#undef XO1 +#undef XO2 +#undef XO3 +#undef XO4 +#undef ST +#undef NOP +#undef BLK64 +#undef BLOCK + +#undef XOR_CONSTANT_CONSTRAINT + #ifdef CONFIG_X86_32 # include <asm/xor_32.h> #else # include <asm/xor_64.h> #endif -#endif + +#define XOR_SELECT_TEMPLATE(FASTEST) \ + AVX_SELECT(FASTEST) + +#endif /* _ASM_X86_XOR_H */ diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index f79cb7e..ce05722 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -2,7 +2,7 @@ #define _ASM_X86_XOR_32_H /* - * Optimized RAID-5 checksumming functions for MMX and SSE. + * Optimized RAID-5 checksumming functions for MMX. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -529,290 +529,6 @@ static struct xor_block_template xor_block_p5_mmx = { .do_5 = xor_p5_mmx_5, }; -/* - * Cache avoiding checksumming functions utilizing KNI instructions - * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) - */ - -#define OFFS(x) "16*("#x")" -#define PF_OFFS(x) "256+16*("#x")" -#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n" -#define LD(x, y) " movaps "OFFS(x)"(%1), %%xmm"#y" ;\n" -#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%1) ;\n" -#define PF1(x) " prefetchnta "PF_OFFS(x)"(%2) ;\n" -#define PF2(x) " prefetchnta "PF_OFFS(x)"(%3) ;\n" -#define PF3(x) " prefetchnta "PF_OFFS(x)"(%4) ;\n" -#define PF4(x) " prefetchnta "PF_OFFS(x)"(%5) ;\n" -#define PF5(x) " prefetchnta "PF_OFFS(x)"(%6) ;\n" -#define XO1(x, y) " xorps "OFFS(x)"(%2), %%xmm"#y" ;\n" -#define XO2(x, y) " xorps "OFFS(x)"(%3), %%xmm"#y" ;\n" -#define XO3(x, y) " xorps "OFFS(x)"(%4), %%xmm"#y" ;\n" -#define XO4(x, y) " xorps "OFFS(x)"(%5), %%xmm"#y" ;\n" -#define XO5(x, y) " xorps "OFFS(x)"(%6), %%xmm"#y" ;\n" - - -static void -xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) -{ - unsigned long lines = bytes >> 8; - - kernel_fpu_begin(); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - LD(i, 0) \ - LD(i + 1, 1) \ - PF1(i) \ - PF1(i + 2) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO1(i, 0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - ST(i, 0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addl $256, %1 ;\n" - " addl $256, %2 ;\n" - " decl %0 ;\n" - " jnz 1b ;\n" - : "+r" (lines), - "+r" (p1), "+r" (p2) - : - : "memory"); - - kernel_fpu_end(); -} - -static void -xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) -{ - unsigned long lines = bytes >> 8; - - kernel_fpu_begin(); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i + 2) \ - LD(i,0) \ - LD(i + 1, 1) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF2(i) \ - PF2(i + 2) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO1(i,0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - XO2(i,0) \ - XO2(i + 1, 1) \ - XO2(i + 2, 2) \ - XO2(i + 3, 3) \ - ST(i,0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addl $256, %1 ;\n" - " addl $256, %2 ;\n" - " addl $256, %3 ;\n" - " decl %0 ;\n" - " jnz 1b ;\n" - : "+r" (lines), - "+r" (p1), "+r"(p2), "+r"(p3) - : - : "memory" ); - - kernel_fpu_end(); -} - -static void -xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) -{ - unsigned long lines = bytes >> 8; - - kernel_fpu_begin(); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i + 2) \ - LD(i,0) \ - LD(i + 1, 1) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF2(i) \ - PF2(i + 2) \ - XO1(i,0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - PF3(i) \ - PF3(i + 2) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO2(i,0) \ - XO2(i + 1, 1) \ - XO2(i + 2, 2) \ - XO2(i + 3, 3) \ - XO3(i,0) \ - XO3(i + 1, 1) \ - XO3(i + 2, 2) \ - XO3(i + 3, 3) \ - ST(i,0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addl $256, %1 ;\n" - " addl $256, %2 ;\n" - " addl $256, %3 ;\n" - " addl $256, %4 ;\n" - " decl %0 ;\n" - " jnz 1b ;\n" - : "+r" (lines), - "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4) - : - : "memory" ); - - kernel_fpu_end(); -} - -static void -xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) -{ - unsigned long lines = bytes >> 8; - - kernel_fpu_begin(); - - /* Make sure GCC forgets anything it knows about p4 or p5, - such that it won't pass to the asm volatile below a - register that is shared with any other variable. That's - because we modify p4 and p5 there, but we can't mark them - as read/write, otherwise we'd overflow the 10-asm-operands - limit of GCC < 3.1. */ - asm("" : "+r" (p4), "+r" (p5)); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i + 2) \ - LD(i,0) \ - LD(i + 1, 1) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF2(i) \ - PF2(i + 2) \ - XO1(i,0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - PF3(i) \ - PF3(i + 2) \ - XO2(i,0) \ - XO2(i + 1, 1) \ - XO2(i + 2, 2) \ - XO2(i + 3, 3) \ - PF4(i) \ - PF4(i + 2) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO3(i,0) \ - XO3(i + 1, 1) \ - XO3(i + 2, 2) \ - XO3(i + 3, 3) \ - XO4(i,0) \ - XO4(i + 1, 1) \ - XO4(i + 2, 2) \ - XO4(i + 3, 3) \ - ST(i,0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addl $256, %1 ;\n" - " addl $256, %2 ;\n" - " addl $256, %3 ;\n" - " addl $256, %4 ;\n" - " addl $256, %5 ;\n" - " decl %0 ;\n" - " jnz 1b ;\n" - : "+r" (lines), - "+r" (p1), "+r" (p2), "+r" (p3) - : "r" (p4), "r" (p5) - : "memory"); - - /* p4 and p5 were modified, and now the variables are dead. - Clobber them just to be sure nobody does something stupid - like assuming they have some legal value. */ - asm("" : "=r" (p4), "=r" (p5)); - - kernel_fpu_end(); -} - static struct xor_block_template xor_block_pIII_sse = { .name = "pIII_sse", .do_2 = xor_sse_2, @@ -827,26 +543,25 @@ static struct xor_block_template xor_block_pIII_sse = { /* Also try the generic routines. */ #include <asm-generic/xor.h> +/* We force the use of the SSE xor block because it can write around L2. + We may also be able to load into the L1 only depending on how the cpu + deals with a load to a line that is being prefetched. */ #undef XOR_TRY_TEMPLATES #define XOR_TRY_TEMPLATES \ do { \ - xor_speed(&xor_block_8regs); \ - xor_speed(&xor_block_8regs_p); \ - xor_speed(&xor_block_32regs); \ - xor_speed(&xor_block_32regs_p); \ AVX_XOR_SPEED; \ - if (cpu_has_xmm) \ + if (cpu_has_xmm) { \ xor_speed(&xor_block_pIII_sse); \ - if (cpu_has_mmx) { \ + xor_speed(&xor_block_sse_pf64); \ + } else if (cpu_has_mmx) { \ xor_speed(&xor_block_pII_mmx); \ xor_speed(&xor_block_p5_mmx); \ + } else { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_8regs_p); \ + xor_speed(&xor_block_32regs); \ + xor_speed(&xor_block_32regs_p); \ } \ } while (0) -/* We force the use of the SSE xor block because it can write around L2. - We may also be able to load into the L1 only depending on how the cpu - deals with a load to a line that is being prefetched. */ -#define XOR_SELECT_TEMPLATE(FASTEST) \ - AVX_SELECT(cpu_has_xmm ? &xor_block_pIII_sse : FASTEST) - #endif /* _ASM_X86_XOR_32_H */ diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h index 87ac522..546f1e3 100644 --- a/arch/x86/include/asm/xor_64.h +++ b/arch/x86/include/asm/xor_64.h @@ -1,301 +1,6 @@ #ifndef _ASM_X86_XOR_64_H #define _ASM_X86_XOR_64_H -/* - * Optimized RAID-5 checksumming functions for MMX and SSE. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * You should have received a copy of the GNU General Public License - * (for example /usr/src/linux/COPYING); if not, write to the Free - * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - - -/* - * Cache avoiding checksumming functions utilizing KNI instructions - * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo) - */ - -/* - * Based on - * High-speed RAID5 checksumming functions utilizing SSE instructions. - * Copyright (C) 1998 Ingo Molnar. - */ - -/* - * x86-64 changes / gcc fixes from Andi Kleen. - * Copyright 2002 Andi Kleen, SuSE Labs. - * - * This hasn't been optimized for the hammer yet, but there are likely - * no advantages to be gotten from x86-64 here anyways. - */ - -#include <asm/i387.h> - -#define OFFS(x) "16*("#x")" -#define PF_OFFS(x) "256+16*("#x")" -#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n" -#define LD(x, y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n" -#define ST(x, y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n" -#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n" -#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n" -#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n" -#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n" -#define PF5(x) " prefetchnta "PF_OFFS(x)"(%[p6]) ;\n" -#define XO1(x, y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n" -#define XO2(x, y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n" -#define XO3(x, y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n" -#define XO4(x, y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n" -#define XO5(x, y) " xorps "OFFS(x)"(%[p6]), %%xmm"#y" ;\n" - - -static void -xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) -{ - unsigned int lines = bytes >> 8; - - kernel_fpu_begin(); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - LD(i, 0) \ - LD(i + 1, 1) \ - PF1(i) \ - PF1(i + 2) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO1(i, 0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - ST(i, 0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " decl %[cnt] ; jnz 1b" - : [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines) - : [inc] "r" (256UL) - : "memory"); - - kernel_fpu_end(); -} - -static void -xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) -{ - unsigned int lines = bytes >> 8; - - kernel_fpu_begin(); - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i + 2) \ - LD(i, 0) \ - LD(i + 1, 1) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF2(i) \ - PF2(i + 2) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO1(i, 0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - XO2(i, 0) \ - XO2(i + 1, 1) \ - XO2(i + 2, 2) \ - XO2(i + 3, 3) \ - ST(i, 0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " addq %[inc], %[p3] ;\n" - " decl %[cnt] ; jnz 1b" - : [cnt] "+r" (lines), - [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) - : [inc] "r" (256UL) - : "memory"); - kernel_fpu_end(); -} - -static void -xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) -{ - unsigned int lines = bytes >> 8; - - kernel_fpu_begin(); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i + 2) \ - LD(i, 0) \ - LD(i + 1, 1) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF2(i) \ - PF2(i + 2) \ - XO1(i, 0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - PF3(i) \ - PF3(i + 2) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO2(i, 0) \ - XO2(i + 1, 1) \ - XO2(i + 2, 2) \ - XO2(i + 3, 3) \ - XO3(i, 0) \ - XO3(i + 1, 1) \ - XO3(i + 2, 2) \ - XO3(i + 3, 3) \ - ST(i, 0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " addq %[inc], %[p3] ;\n" - " addq %[inc], %[p4] ;\n" - " decl %[cnt] ; jnz 1b" - : [cnt] "+c" (lines), - [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) - : [inc] "r" (256UL) - : "memory" ); - - kernel_fpu_end(); -} - -static void -xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) -{ - unsigned int lines = bytes >> 8; - - kernel_fpu_begin(); - - asm volatile( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i + 2) \ - LD(i, 0) \ - LD(i + 1, 1) \ - LD(i + 2, 2) \ - LD(i + 3, 3) \ - PF2(i) \ - PF2(i + 2) \ - XO1(i, 0) \ - XO1(i + 1, 1) \ - XO1(i + 2, 2) \ - XO1(i + 3, 3) \ - PF3(i) \ - PF3(i + 2) \ - XO2(i, 0) \ - XO2(i + 1, 1) \ - XO2(i + 2, 2) \ - XO2(i + 3, 3) \ - PF4(i) \ - PF4(i + 2) \ - PF0(i + 4) \ - PF0(i + 6) \ - XO3(i, 0) \ - XO3(i + 1, 1) \ - XO3(i + 2, 2) \ - XO3(i + 3, 3) \ - XO4(i, 0) \ - XO4(i + 1, 1) \ - XO4(i + 2, 2) \ - XO4(i + 3, 3) \ - ST(i, 0) \ - ST(i + 1, 1) \ - ST(i + 2, 2) \ - ST(i + 3, 3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " addq %[inc], %[p3] ;\n" - " addq %[inc], %[p4] ;\n" - " addq %[inc], %[p5] ;\n" - " decl %[cnt] ; jnz 1b" - : [cnt] "+c" (lines), - [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4), - [p5] "+r" (p5) - : [inc] "r" (256UL) - : "memory"); - - kernel_fpu_end(); -} - static struct xor_block_template xor_block_sse = { .name = "generic_sse", .do_2 = xor_sse_2, @@ -308,17 +13,15 @@ static struct xor_block_template xor_block_sse = { /* Also try the AVX routines */ #include <asm/xor_avx.h> +/* We force the use of the SSE xor block because it can write around L2. + We may also be able to load into the L1 only depending on how the cpu + deals with a load to a line that is being prefetched. */ #undef XOR_TRY_TEMPLATES #define XOR_TRY_TEMPLATES \ do { \ AVX_XOR_SPEED; \ + xor_speed(&xor_block_sse_pf64); \ xor_speed(&xor_block_sse); \ } while (0) -/* We force the use of the SSE xor block because it can write around L2. - We may also be able to load into the L1 only depending on how the cpu - deals with a load to a line that is being prefetched. */ -#define XOR_SELECT_TEMPLATE(FASTEST) \ - AVX_SELECT(&xor_block_sse) - #endif /* _ASM_X86_XOR_64_H */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 92862cd..c15ddaf 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -1,6 +1,31 @@ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H +/* setup_data types */ +#define SETUP_NONE 0 +#define SETUP_E820_EXT 1 +#define SETUP_DTB 2 +#define SETUP_PCI 3 + +/* ram_size flags */ +#define RAMDISK_IMAGE_START_MASK 0x07FF +#define RAMDISK_PROMPT_FLAG 0x8000 +#define RAMDISK_LOAD_FLAG 0x4000 + +/* loadflags */ +#define LOADED_HIGH (1<<0) +#define QUIET_FLAG (1<<5) +#define KEEP_SEGMENTS (1<<6) +#define CAN_USE_HEAP (1<<7) + +/* xloadflags */ +#define XLF_KERNEL_64 (1<<0) +#define XLF_CAN_BE_LOADED_ABOVE_4G (1<<1) +#define XLF_EFI_HANDOVER_32 (1<<2) +#define XLF_EFI_HANDOVER_64 (1<<3) + +#ifndef __ASSEMBLY__ + #include <linux/types.h> #include <linux/screen_info.h> #include <linux/apm_bios.h> @@ -9,12 +34,6 @@ #include <asm/ist.h> #include <video/edid.h> -/* setup data types */ -#define SETUP_NONE 0 -#define SETUP_E820_EXT 1 -#define SETUP_DTB 2 -#define SETUP_PCI 3 - /* extensible setup data list node */ struct setup_data { __u64 next; @@ -28,9 +47,6 @@ struct setup_header { __u16 root_flags; __u32 syssize; __u16 ram_size; -#define RAMDISK_IMAGE_START_MASK 0x07FF -#define RAMDISK_PROMPT_FLAG 0x8000 -#define RAMDISK_LOAD_FLAG 0x4000 __u16 vid_mode; __u16 root_dev; __u16 boot_flag; @@ -42,10 +58,6 @@ struct setup_header { __u16 kernel_version; __u8 type_of_loader; __u8 loadflags; -#define LOADED_HIGH (1<<0) -#define QUIET_FLAG (1<<5) -#define KEEP_SEGMENTS (1<<6) -#define CAN_USE_HEAP (1<<7) __u16 setup_move_size; __u32 code32_start; __u32 ramdisk_image; @@ -58,7 +70,8 @@ struct setup_header { __u32 initrd_addr_max; __u32 kernel_alignment; __u8 relocatable_kernel; - __u8 _pad2[3]; + __u8 min_alignment; + __u16 xloadflags; __u32 cmdline_size; __u32 hardware_subarch; __u64 hardware_subarch_data; @@ -106,7 +119,10 @@ struct boot_params { __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ struct sys_desc_table sys_desc_table; /* 0x0a0 */ struct olpc_ofw_header olpc_ofw_header; /* 0x0b0 */ - __u8 _pad4[128]; /* 0x0c0 */ + __u32 ext_ramdisk_image; /* 0x0c0 */ + __u32 ext_ramdisk_size; /* 0x0c4 */ + __u32 ext_cmd_line_ptr; /* 0x0c8 */ + __u8 _pad4[116]; /* 0x0cc */ struct edid_info edid_info; /* 0x140 */ struct efi_info efi_info; /* 0x1c0 */ __u32 alt_mem_k; /* 0x1e0 */ @@ -115,7 +131,20 @@ struct boot_params { __u8 eddbuf_entries; /* 0x1e9 */ __u8 edd_mbr_sig_buf_entries; /* 0x1ea */ __u8 kbd_status; /* 0x1eb */ - __u8 _pad6[5]; /* 0x1ec */ + __u8 _pad5[3]; /* 0x1ec */ + /* + * The sentinel is set to a nonzero value (0xff) in header.S. + * + * A bootloader is supposed to only take setup_header and put + * it into a clean boot_params buffer. If it turns out that + * it is clumsy or too generous with the buffer, it most + * probably will pick up the sentinel variable too. The fact + * that this variable then is still 0xff will let kernel + * know that some variables in boot_params are invalid and + * kernel should zero out certain portions of boot_params. + */ + __u8 sentinel; /* 0x1ef */ + __u8 _pad6[1]; /* 0x1f0 */ struct setup_header hdr; /* setup header */ /* 0x1f1 */ __u8 _pad7[0x290-0x1f1-sizeof(struct setup_header)]; __u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX]; /* 0x290 */ @@ -134,6 +163,6 @@ enum { X86_NR_SUBARCHS, }; - +#endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_BOOTPARAM_H */ diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 58c8298..a0eab85 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -4,66 +4,6 @@ #include <linux/types.h> #include <asm/ioctls.h> -/* - * Machine Check support for x86 - */ - -/* MCG_CAP register defines */ -#define MCG_BANKCNT_MASK 0xff /* Number of Banks */ -#define MCG_CTL_P (1ULL<<8) /* MCG_CTL register available */ -#define MCG_EXT_P (1ULL<<9) /* Extended registers available */ -#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */ -#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */ -#define MCG_EXT_CNT_SHIFT 16 -#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) -#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ - -/* MCG_STATUS register defines */ -#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ -#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */ -#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */ - -/* MCi_STATUS register defines */ -#define MCI_STATUS_VAL (1ULL<<63) /* valid error */ -#define MCI_STATUS_OVER (1ULL<<62) /* previous errors lost */ -#define MCI_STATUS_UC (1ULL<<61) /* uncorrected error */ -#define MCI_STATUS_EN (1ULL<<60) /* error enabled */ -#define MCI_STATUS_MISCV (1ULL<<59) /* misc error reg. valid */ -#define MCI_STATUS_ADDRV (1ULL<<58) /* addr reg. valid */ -#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ -#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ -#define MCI_STATUS_AR (1ULL<<55) /* Action required */ -#define MCACOD 0xffff /* MCA Error Code */ - -/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ -#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 -#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ -#define MCACOD_DATA 0x0134 /* Data Load */ -#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ - -/* MCi_MISC register defines */ -#define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f) -#define MCI_MISC_ADDR_MODE(m) (((m) >> 6) & 7) -#define MCI_MISC_ADDR_SEGOFF 0 /* segment offset */ -#define MCI_MISC_ADDR_LINEAR 1 /* linear address */ -#define MCI_MISC_ADDR_PHYS 2 /* physical address */ -#define MCI_MISC_ADDR_MEM 3 /* memory address */ -#define MCI_MISC_ADDR_GENERIC 7 /* generic */ - -/* CTL2 register defines */ -#define MCI_CTL2_CMCI_EN (1ULL << 30) -#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL - -#define MCJ_CTX_MASK 3 -#define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK) -#define MCJ_CTX_RANDOM 0 /* inject context: random */ -#define MCJ_CTX_PROCESS 0x1 /* inject context: process */ -#define MCJ_CTX_IRQ 0x2 /* inject context: IRQ */ -#define MCJ_NMI_BROADCAST 0x4 /* do NMI broadcasting */ -#define MCJ_EXCEPTION 0x8 /* raise as exception */ -#define MCJ_IRQ_BRAODCAST 0x10 /* do IRQ broadcasting */ - /* Fields are zero when not available */ struct mce { __u64 status; @@ -87,35 +27,8 @@ struct mce { __u64 mcgcap; /* MCGCAP MSR: machine check capabilities of CPU */ }; -/* - * This structure contains all data related to the MCE log. Also - * carries a signature to make it easier to find from external - * debugging tools. Each entry is only valid when its finished flag - * is set. - */ - -#define MCE_LOG_LEN 32 - -struct mce_log { - char signature[12]; /* "MACHINECHECK" */ - unsigned len; /* = MCE_LOG_LEN */ - unsigned next; - unsigned flags; - unsigned recordlen; /* length of struct mce */ - struct mce entry[MCE_LOG_LEN]; -}; - -#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ - -#define MCE_LOG_SIGNATURE "MACHINECHECK" - #define MCE_GET_RECORD_LEN _IOR('M', 1, int) #define MCE_GET_LOG_LEN _IOR('M', 2, int) #define MCE_GETCLEAR_FLAGS _IOR('M', 3, int) -/* Software defined banks */ -#define MCE_EXTENDED_BANK 128 -#define MCE_THERMAL_BANK MCE_EXTENDED_BANK + 0 -#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) - #endif /* _UAPI_ASM_X86_MCE_H */ diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 433a59f..075a402 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -194,6 +194,8 @@ /* Fam 15h MSRs */ #define MSR_F15H_PERF_CTL 0xc0010200 #define MSR_F15H_PERF_CTR 0xc0010201 +#define MSR_F15H_NB_PERF_CTL 0xc0010240 +#define MSR_F15H_NB_PERF_CTR 0xc0010241 /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 34e923a..ac3b3d0 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -65,8 +65,7 @@ obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o -obj-$(CONFIG_KPROBES) += kprobes.o -obj-$(CONFIG_OPTPROBES) += kprobes-opt.o +obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index afdc3f75..c9876ef 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -240,7 +240,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n, dw_apb_clockevent_pause(adev->timer); if (system_state == SYSTEM_RUNNING) { pr_debug("skipping APBT CPU %lu offline\n", cpu); - } else if (adev) { + } else { pr_debug("APBT clockevent for cpu %lu offline\n", cpu); dw_apb_clockevent_stop(adev->timer); } @@ -311,7 +311,6 @@ void __init apbt_time_init(void) #ifdef CONFIG_SMP int i; struct sfi_timer_table_entry *p_mtmr; - unsigned int percpu_timer; struct apbt_dev *adev; #endif @@ -346,13 +345,10 @@ void __init apbt_time_init(void) return; } pr_debug("%s: %d CPUs online\n", __func__, num_online_cpus()); - if (num_possible_cpus() <= sfi_mtimer_num) { - percpu_timer = 1; + if (num_possible_cpus() <= sfi_mtimer_num) apbt_num_timers_used = num_possible_cpus(); - } else { - percpu_timer = 0; + else apbt_num_timers_used = 1; - } pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used); /* here we set up per CPU timer data structure */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index b994cc8..a5b4dce 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1477,8 +1477,7 @@ void __init bsp_end_local_APIC_setup(void) * Now that local APIC setup is completed for BP, configure the fault * handling for interrupt remapping. */ - if (irq_remapping_enabled) - irq_remap_enable_fault_handling(); + irq_remap_enable_fault_handling(); } @@ -2251,8 +2250,7 @@ static int lapic_suspend(void) local_irq_save(flags); disable_local_APIC(); - if (irq_remapping_enabled) - irq_remapping_disable(); + irq_remapping_disable(); local_irq_restore(flags); return 0; @@ -2268,16 +2266,15 @@ static void lapic_resume(void) return; local_irq_save(flags); - if (irq_remapping_enabled) { - /* - * IO-APIC and PIC have their own resume routines. - * We just mask them here to make sure the interrupt - * subsystem is completely quiet while we enable x2apic - * and interrupt-remapping. - */ - mask_ioapic_entries(); - legacy_pic->mask_all(); - } + + /* + * IO-APIC and PIC have their own resume routines. + * We just mask them here to make sure the interrupt + * subsystem is completely quiet while we enable x2apic + * and interrupt-remapping. + */ + mask_ioapic_entries(); + legacy_pic->mask_all(); if (x2apic_mode) enable_x2apic(); @@ -2320,8 +2317,7 @@ static void lapic_resume(void) apic_write(APIC_ESR, 0); apic_read(APIC_ESR); - if (irq_remapping_enabled) - irq_remapping_reenable(x2apic_mode); + irq_remapping_reenable(x2apic_mode); local_irq_restore(flags); } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index b739d39..9ed796c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -68,22 +68,6 @@ #define for_each_irq_pin(entry, head) \ for (entry = head; entry; entry = entry->next) -#ifdef CONFIG_IRQ_REMAP -static void irq_remap_modify_chip_defaults(struct irq_chip *chip); -static inline bool irq_remapped(struct irq_cfg *cfg) -{ - return cfg->irq_2_iommu.iommu != NULL; -} -#else -static inline bool irq_remapped(struct irq_cfg *cfg) -{ - return false; -} -static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip) -{ -} -#endif - /* * Is the SiS APIC rmw bug present ? * -1 = don't know, 0 = no, 1 = yes @@ -300,9 +284,9 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) return cfg; } -static int alloc_irq_from(unsigned int from, int node) +static int alloc_irqs_from(unsigned int from, unsigned int count, int node) { - return irq_alloc_desc_from(from, node); + return irq_alloc_descs_from(from, count, node); } static void free_irq_at(unsigned int at, struct irq_cfg *cfg) @@ -326,7 +310,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mpc_ioapic_addr(idx) & ~PAGE_MASK); } -static inline void io_apic_eoi(unsigned int apic, unsigned int vector) +void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(vector, &io_apic->eoi); @@ -573,19 +557,10 @@ static void unmask_ioapic_irq(struct irq_data *data) * Otherwise, we simulate the EOI message manually by changing the trigger * mode to edge and then back to level, with RTE being masked during this. */ -static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) +void native_eoi_ioapic_pin(int apic, int pin, int vector) { if (mpc_ioapic_ver(apic) >= 0x20) { - /* - * Intr-remapping uses pin number as the virtual vector - * in the RTE. Actual vector is programmed in - * intr-remapping table entry. Hence for the io-apic - * EOI we use the pin number. - */ - if (cfg && irq_remapped(cfg)) - io_apic_eoi(apic, pin); - else - io_apic_eoi(apic, vector); + io_apic_eoi(apic, vector); } else { struct IO_APIC_route_entry entry, entry1; @@ -606,14 +581,15 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) } } -static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) { struct irq_pin_list *entry; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); for_each_irq_pin(entry, cfg->irq_2_pin) - __eoi_ioapic_pin(entry->apic, entry->pin, cfg->vector, cfg); + x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin, + cfg->vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -650,7 +626,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) } raw_spin_lock_irqsave(&ioapic_lock, flags); - __eoi_ioapic_pin(apic, pin, entry.vector, NULL); + x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -1304,25 +1280,18 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, fasteoi = false; } - if (irq_remapped(cfg)) { - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - irq_remap_modify_chip_defaults(chip); + if (setup_remapped_irq(irq, cfg, chip)) fasteoi = trigger != 0; - } hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; irq_set_chip_and_handler_name(irq, chip, hdl, fasteoi ? "fasteoi" : "edge"); } -static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr) +int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr) { - if (irq_remapping_enabled) - return setup_ioapic_remapped_entry(irq, entry, destination, - vector, attr); - memset(entry, 0, sizeof(*entry)); entry->delivery_mode = apic->irq_delivery_mode; @@ -1370,8 +1339,8 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, cfg->vector, irq, attr->trigger, attr->polarity, dest); - if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", + if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { + pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); __clear_irq_vector(irq, cfg); @@ -1479,9 +1448,6 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, struct IO_APIC_route_entry entry; unsigned int dest; - if (irq_remapping_enabled) - return; - memset(&entry, 0, sizeof(entry)); /* @@ -1513,9 +1479,63 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, ioapic_write_entry(ioapic_idx, pin, entry); } -__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries) { int i; + + pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n"); + + for (i = 0; i <= nr_entries; i++) { + struct IO_APIC_route_entry entry; + + entry = ioapic_read_entry(apic, i); + + pr_debug(" %02x %02X ", i, entry.dest); + pr_cont("%1d %1d %1d %1d %1d " + "%1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector); + } +} + +void intel_ir_io_apic_print_entries(unsigned int apic, + unsigned int nr_entries) +{ + int i; + + pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n"); + + for (i = 0; i <= nr_entries; i++) { + struct IR_IO_APIC_route_entry *ir_entry; + struct IO_APIC_route_entry entry; + + entry = ioapic_read_entry(apic, i); + + ir_entry = (struct IR_IO_APIC_route_entry *)&entry; + + pr_debug(" %02x %04X ", i, ir_entry->index); + pr_cont("%1d %1d %1d %1d %1d " + "%1d %1d %X %02X\n", + ir_entry->format, + ir_entry->mask, + ir_entry->trigger, + ir_entry->irr, + ir_entry->polarity, + ir_entry->delivery_status, + ir_entry->index2, + ir_entry->zero, + ir_entry->vector); + } +} + +__apicdebuginit(void) print_IO_APIC(int ioapic_idx) +{ union IO_APIC_reg_00 reg_00; union IO_APIC_reg_01 reg_01; union IO_APIC_reg_02 reg_02; @@ -1568,58 +1588,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) printk(KERN_DEBUG ".... IRQ redirection table:\n"); - if (irq_remapping_enabled) { - printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR" - " Pol Stat Indx2 Zero Vect:\n"); - } else { - printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol" - " Stat Dmod Deli Vect:\n"); - } - - for (i = 0; i <= reg_01.bits.entries; i++) { - if (irq_remapping_enabled) { - struct IO_APIC_route_entry entry; - struct IR_IO_APIC_route_entry *ir_entry; - - entry = ioapic_read_entry(ioapic_idx, i); - ir_entry = (struct IR_IO_APIC_route_entry *) &entry; - printk(KERN_DEBUG " %02x %04X ", - i, - ir_entry->index - ); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %X %02X\n", - ir_entry->format, - ir_entry->mask, - ir_entry->trigger, - ir_entry->irr, - ir_entry->polarity, - ir_entry->delivery_status, - ir_entry->index2, - ir_entry->zero, - ir_entry->vector - ); - } else { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(ioapic_idx, i); - printk(KERN_DEBUG " %02x %02X ", - i, - entry.dest - ); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); - } - } + x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); } __apicdebuginit(void) print_IO_APICs(void) @@ -1921,30 +1890,14 @@ void __init enable_IO_APIC(void) clear_IO_APIC(); } -/* - * Not an __init, needed by the reboot code - */ -void disable_IO_APIC(void) +void native_disable_io_apic(void) { /* - * Clear the IO-APIC before rebooting: - */ - clear_IO_APIC(); - - if (!legacy_pic->nr_legacy_irqs) - return; - - /* * If the i8259 is routed through an IOAPIC * Put that IOAPIC in virtual wire mode * so legacy interrupts can be delivered. - * - * With interrupt-remapping, for now we will use virtual wire A mode, - * as virtual wire B is little complex (need to configure both - * IOAPIC RTE as well as interrupt-remapping table entry). - * As this gets called during crash dump, keep this simple for now. */ - if (ioapic_i8259.pin != -1 && !irq_remapping_enabled) { + if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); @@ -1964,12 +1917,25 @@ void disable_IO_APIC(void) ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } + if (cpu_has_apic || apic_from_smp_config()) + disconnect_bsp_APIC(ioapic_i8259.pin != -1); + +} + +/* + * Not an __init, needed by the reboot code + */ +void disable_IO_APIC(void) +{ /* - * Use virtual wire A mode when interrupt remapping is enabled. + * Clear the IO-APIC before rebooting: */ - if (cpu_has_apic || apic_from_smp_config()) - disconnect_bsp_APIC(!irq_remapping_enabled && - ioapic_i8259.pin != -1); + clear_IO_APIC(); + + if (!legacy_pic->nr_legacy_irqs) + return; + + x86_io_apic_ops.disable(); } #ifdef CONFIG_X86_32 @@ -2322,12 +2288,8 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq apic = entry->apic; pin = entry->pin; - /* - * With interrupt-remapping, destination information comes - * from interrupt-remapping table entry. - */ - if (!irq_remapped(cfg)) - io_apic_write(apic, 0x11 + pin*2, dest); + + io_apic_write(apic, 0x11 + pin*2, dest); reg = io_apic_read(apic, 0x10 + pin*2); reg &= ~IO_APIC_REDIR_VECTOR_MASK; reg |= vector; @@ -2369,9 +2331,10 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, return 0; } -static int -ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) + +int native_ioapic_set_affinity(struct irq_data *data, + const struct cpumask *mask, + bool force) { unsigned int dest, irq = data->irq; unsigned long flags; @@ -2548,33 +2511,6 @@ static void ack_apic_level(struct irq_data *data) ioapic_irqd_unmask(data, cfg, masked); } -#ifdef CONFIG_IRQ_REMAP -static void ir_ack_apic_edge(struct irq_data *data) -{ - ack_APIC_irq(); -} - -static void ir_ack_apic_level(struct irq_data *data) -{ - ack_APIC_irq(); - eoi_ioapic_irq(data->irq, data->chip_data); -} - -static void ir_print_prefix(struct irq_data *data, struct seq_file *p) -{ - seq_printf(p, " IR-%s", data->chip->name); -} - -static void irq_remap_modify_chip_defaults(struct irq_chip *chip) -{ - chip->irq_print_chip = ir_print_prefix; - chip->irq_ack = ir_ack_apic_edge; - chip->irq_eoi = ir_ack_apic_level; - - chip->irq_set_affinity = set_remapped_irq_affinity; -} -#endif /* CONFIG_IRQ_REMAP */ - static struct irq_chip ioapic_chip __read_mostly = { .name = "IO-APIC", .irq_startup = startup_ioapic_irq, @@ -2582,7 +2518,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_unmask = unmask_ioapic_irq, .irq_ack = ack_apic_edge, .irq_eoi = ack_apic_level, - .irq_set_affinity = ioapic_set_affinity, + .irq_set_affinity = native_ioapic_set_affinity, .irq_retrigger = ioapic_retrigger_irq, }; @@ -2781,8 +2717,7 @@ static inline void __init check_timer(void) * 8259A. */ if (pin1 == -1) { - if (irq_remapping_enabled) - panic("BIOS bug: timer not connected to IO-APIC"); + panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC"); pin1 = pin2; apic1 = apic2; no_pin1 = 1; @@ -2814,8 +2749,7 @@ static inline void __init check_timer(void) clear_IO_APIC_pin(0, pin1); goto out; } - if (irq_remapping_enabled) - panic("timer doesn't work through Interrupt-remapped IO-APIC"); + panic_if_irq_remap("timer doesn't work through Interrupt-remapped IO-APIC"); local_irq_disable(); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) @@ -2982,37 +2916,58 @@ device_initcall(ioapic_init_ops); /* * Dynamic irq allocate and deallocation */ -unsigned int create_irq_nr(unsigned int from, int node) +unsigned int __create_irqs(unsigned int from, unsigned int count, int node) { - struct irq_cfg *cfg; + struct irq_cfg **cfg; unsigned long flags; - unsigned int ret = 0; - int irq; + int irq, i; if (from < nr_irqs_gsi) from = nr_irqs_gsi; - irq = alloc_irq_from(from, node); - if (irq < 0) - return 0; - cfg = alloc_irq_cfg(irq, node); - if (!cfg) { - free_irq_at(irq, NULL); + cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node); + if (!cfg) return 0; + + irq = alloc_irqs_from(from, count, node); + if (irq < 0) + goto out_cfgs; + + for (i = 0; i < count; i++) { + cfg[i] = alloc_irq_cfg(irq + i, node); + if (!cfg[i]) + goto out_irqs; } raw_spin_lock_irqsave(&vector_lock, flags); - if (!__assign_irq_vector(irq, cfg, apic->target_cpus())) - ret = irq; + for (i = 0; i < count; i++) + if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus())) + goto out_vecs; raw_spin_unlock_irqrestore(&vector_lock, flags); - if (ret) { - irq_set_chip_data(irq, cfg); - irq_clear_status_flags(irq, IRQ_NOREQUEST); - } else { - free_irq_at(irq, cfg); + for (i = 0; i < count; i++) { + irq_set_chip_data(irq + i, cfg[i]); + irq_clear_status_flags(irq + i, IRQ_NOREQUEST); } - return ret; + + kfree(cfg); + return irq; + +out_vecs: + for (i--; i >= 0; i--) + __clear_irq_vector(irq + i, cfg[i]); + raw_spin_unlock_irqrestore(&vector_lock, flags); +out_irqs: + for (i = 0; i < count; i++) + free_irq_at(irq + i, cfg[i]); +out_cfgs: + kfree(cfg); + return 0; +} + +unsigned int create_irq_nr(unsigned int from, int node) +{ + return __create_irqs(from, 1, node); } int create_irq(void) @@ -3037,48 +2992,35 @@ void destroy_irq(unsigned int irq) irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); - if (irq_remapped(cfg)) - free_remapped_irq(irq); + free_remapped_irq(irq); + raw_spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); raw_spin_unlock_irqrestore(&vector_lock, flags); free_irq_at(irq, cfg); } +void destroy_irqs(unsigned int irq, unsigned int count) +{ + unsigned int i; + + for (i = 0; i < count; i++) + destroy_irq(irq + i); +} + /* * MSI message composition */ -#ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg, u8 hpet_id) +void native_compose_msi_msg(struct pci_dev *pdev, + unsigned int irq, unsigned int dest, + struct msi_msg *msg, u8 hpet_id) { - struct irq_cfg *cfg; - int err; - unsigned dest; - - if (disable_apic) - return -ENXIO; - - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + struct irq_cfg *cfg = irq_cfg(irq); - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; - - if (irq_remapped(cfg)) { - compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id); - return err; - } + msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) - msg->address_hi = MSI_ADDR_BASE_HI | - MSI_ADDR_EXT_DEST_ID(dest); - else - msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); msg->address_lo = MSI_ADDR_BASE_LO | @@ -3097,8 +3039,32 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, MSI_DATA_DELIVERY_FIXED: MSI_DATA_DELIVERY_LOWPRI) | MSI_DATA_VECTOR(cfg->vector); +} - return err; +#ifdef CONFIG_PCI_MSI +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) +{ + struct irq_cfg *cfg; + int err; + unsigned dest; + + if (disable_apic) + return -ENXIO; + + cfg = irq_cfg(irq); + err = assign_irq_vector(irq, cfg, apic->target_cpus()); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; + + x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); + + return 0; } static int @@ -3136,23 +3102,28 @@ static struct irq_chip msi_chip = { .irq_retrigger = ioapic_retrigger_irq, }; -static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) +int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, + unsigned int irq_base, unsigned int irq_offset) { struct irq_chip *chip = &msi_chip; struct msi_msg msg; + unsigned int irq = irq_base + irq_offset; int ret; ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; - irq_set_msi_desc(irq, msidesc); - write_msi_msg(irq, &msg); + irq_set_msi_desc_off(irq_base, irq_offset, msidesc); - if (irq_remapped(irq_get_chip_data(irq))) { - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - irq_remap_modify_chip_defaults(chip); - } + /* + * MSI-X message is written per-IRQ, the offset is always 0. + * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. + */ + if (!irq_offset) + write_msi_msg(irq, &msg); + + setup_remapped_irq(irq, irq_get_chip_data(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); @@ -3163,46 +3134,26 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - int node, ret, sub_handle, index = 0; unsigned int irq, irq_want; struct msi_desc *msidesc; + int node, ret; - /* x86 doesn't support multiple MSI yet */ + /* Multiple MSI vectors only supported with interrupt remapping */ if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; node = dev_to_node(&dev->dev); irq_want = nr_irqs_gsi; - sub_handle = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { irq = create_irq_nr(irq_want, node); if (irq == 0) - return -1; + return -ENOSPC; + irq_want = irq + 1; - if (!irq_remapping_enabled) - goto no_ir; - if (!sub_handle) { - /* - * allocate the consecutive block of IRTE's - * for 'nvec' - */ - index = msi_alloc_remapped_irq(dev, irq, nvec); - if (index < 0) { - ret = index; - goto error; - } - } else { - ret = msi_setup_remapped_irq(dev, irq, index, - sub_handle); - if (ret < 0) - goto error; - } -no_ir: - ret = setup_msi_irq(dev, msidesc, irq); + ret = setup_msi_irq(dev, msidesc, irq, 0); if (ret < 0) goto error; - sub_handle++; } return 0; @@ -3298,26 +3249,19 @@ static struct irq_chip hpet_msi_type = { .irq_retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq, unsigned int id) +int default_setup_hpet_msi(unsigned int irq, unsigned int id) { struct irq_chip *chip = &hpet_msi_type; struct msi_msg msg; int ret; - if (irq_remapping_enabled) { - ret = setup_hpet_msi_remapped(irq, id); - if (ret) - return ret; - } - ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; hpet_msi_write(irq_get_handler_data(irq), &msg); irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - if (irq_remapped(irq_get_chip_data(irq))) - irq_remap_modify_chip_defaults(chip); + setup_remapped_irq(irq, irq_get_chip_data(irq), chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); return 0; @@ -3683,10 +3627,7 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); - if (irq_remapping_enabled) - set_remapped_irq_affinity(idata, mask, false); - else - ioapic_set_affinity(idata, mask, false); + x86_io_apic_ops.set_affinity(idata, mask, false); } } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index cce91bf..7434d85 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -106,7 +106,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) unsigned long mask = cpumask_bits(cpumask)[0]; unsigned long flags; - if (WARN_ONCE(!mask, "empty IPI mask")) + if (!mask) return; local_irq_save(flags); diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index e03a1e1..562a76d 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -20,18 +20,19 @@ static int set_x2apic_phys_mode(char *arg) } early_param("x2apic_phys", set_x2apic_phys_mode); -static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static bool x2apic_fadt_phys(void) { - if (x2apic_phys) - return x2apic_enabled(); - else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && - (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) && - x2apic_enabled()) { + if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && + (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { printk(KERN_DEBUG "System requires x2apic physical mode\n"); - return 1; + return true; } - else - return 0; + return false; +} + +static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } static void @@ -82,7 +83,7 @@ static void init_x2apic_ldr(void) static int x2apic_phys_probe(void) { - if (x2apic_mode && x2apic_phys) + if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys())) return 1; return apic == &apic_x2apic_phys; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 8cfade9..794f6eb 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -5,7 +5,7 @@ * * SGI UV APIC functions (note: not an Intel compatible APIC) * - * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. */ #include <linux/cpumask.h> #include <linux/hardirq.h> @@ -91,10 +91,16 @@ static int __init early_get_pnodeid(void) m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR); uv_min_hub_revision_id = node_id.s.revision; - if (node_id.s.part_number == UV2_HUB_PART_NUMBER) - uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; - if (node_id.s.part_number == UV2_HUB_PART_NUMBER_X) + switch (node_id.s.part_number) { + case UV2_HUB_PART_NUMBER: + case UV2_HUB_PART_NUMBER_X: uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1; + break; + case UV3_HUB_PART_NUMBER: + case UV3_HUB_PART_NUMBER_X: + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + break; + } uv_hub_info->hub_revision = uv_min_hub_revision_id; pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1); @@ -130,13 +136,16 @@ static void __init uv_set_apicid_hibit(void) static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int pnodeid, is_uv1, is_uv2; + int pnodeid, is_uv1, is_uv2, is_uv3; is_uv1 = !strcmp(oem_id, "SGI"); is_uv2 = !strcmp(oem_id, "SGI2"); - if (is_uv1 || is_uv2) { + is_uv3 = !strncmp(oem_id, "SGI3", 4); /* there are varieties of UV3 */ + if (is_uv1 || is_uv2 || is_uv3) { uv_hub_info->hub_revision = - is_uv1 ? UV1_HUB_REVISION_BASE : UV2_HUB_REVISION_BASE; + (is_uv1 ? UV1_HUB_REVISION_BASE : + (is_uv2 ? UV2_HUB_REVISION_BASE : + UV3_HUB_REVISION_BASE)); pnodeid = early_get_pnodeid(); early_get_apic_pnode_shift(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; @@ -450,14 +459,17 @@ static __init void map_high(char *id, unsigned long base, int pshift, paddr = base << pshift; bytes = (1UL << bshift) * (max_pnode + 1); - printk(KERN_INFO "UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, - paddr + bytes); + if (!paddr) { + pr_info("UV: Map %s_HI base address NULL\n", id); + return; + } + pr_info("UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); if (map_type == map_uc) init_extra_mapping_uc(paddr, bytes); else init_extra_mapping_wb(paddr, bytes); - } + static __init void map_gru_high(int max_pnode) { union uvh_rh_gam_gru_overlay_config_mmr_u gru; @@ -468,7 +480,8 @@ static __init void map_gru_high(int max_pnode) map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); gru_start_paddr = ((u64)gru.s.base << shift); gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); - + } else { + pr_info("UV: GRU disabled\n"); } } @@ -480,23 +493,146 @@ static __init void map_mmr_high(int max_pnode) mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); if (mmr.s.enable) map_high("MMR", mmr.s.base, shift, shift, max_pnode, map_uc); + else + pr_info("UV: MMR disabled\n"); +} + +/* + * This commonality works because both 0 & 1 versions of the MMIOH OVERLAY + * and REDIRECT MMR regs are exactly the same on UV3. + */ +struct mmioh_config { + unsigned long overlay; + unsigned long redirect; + char *id; +}; + +static __initdata struct mmioh_config mmiohs[] = { + { + UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR, + UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR, + "MMIOH0" + }, + { + UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR, + UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR, + "MMIOH1" + }, +}; + +static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) +{ + union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay; + unsigned long mmr; + unsigned long base; + int i, n, shift, m_io, max_io; + int nasid, lnasid, fi, li; + char *id; + + id = mmiohs[index].id; + overlay.v = uv_read_local_mmr(mmiohs[index].overlay); + pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", + id, overlay.v, overlay.s3.base, overlay.s3.m_io); + if (!overlay.s3.enable) { + pr_info("UV: %s disabled\n", id); + return; + } + + shift = UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT; + base = (unsigned long)overlay.s3.base; + m_io = overlay.s3.m_io; + mmr = mmiohs[index].redirect; + n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH; + min_pnode *= 2; /* convert to NASID */ + max_pnode *= 2; + max_io = lnasid = fi = li = -1; + + for (i = 0; i < n; i++) { + union uv3h_rh_gam_mmioh_redirect_config0_mmr_u redirect; + + redirect.v = uv_read_local_mmr(mmr + i * 8); + nasid = redirect.s3.nasid; + if (nasid < min_pnode || max_pnode < nasid) + nasid = -1; /* invalid NASID */ + + if (nasid == lnasid) { + li = i; + if (i != n-1) /* last entry check */ + continue; + } + + /* check if we have a cached (or last) redirect to print */ + if (lnasid != -1 || (i == n-1 && nasid != -1)) { + unsigned long addr1, addr2; + int f, l; + + if (lnasid == -1) { + f = l = i; + lnasid = nasid; + } else { + f = fi; + l = li; + } + addr1 = (base << shift) + + f * (unsigned long)(1 << m_io); + addr2 = (base << shift) + + (l + 1) * (unsigned long)(1 << m_io); + pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", + id, fi, li, lnasid, addr1, addr2); + if (max_io < l) + max_io = l; + } + fi = li = i; + lnasid = nasid; + } + + pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", + id, base, shift, m_io, max_io); + + if (max_io >= 0) + map_high(id, base, shift, m_io, max_io, map_uc); } -static __init void map_mmioh_high(int max_pnode) +static __init void map_mmioh_high(int min_pnode, int max_pnode) { union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; - int shift; + unsigned long mmr, base; + int shift, enable, m_io, n_io; - mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); - if (is_uv1_hub() && mmioh.s1.enable) { - shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - map_high("MMIOH", mmioh.s1.base, shift, mmioh.s1.m_io, - max_pnode, map_uc); + if (is_uv3_hub()) { + /* Map both MMIOH Regions */ + map_mmioh_high_uv3(0, min_pnode, max_pnode); + map_mmioh_high_uv3(1, min_pnode, max_pnode); + return; } - if (is_uv2_hub() && mmioh.s2.enable) { + + if (is_uv1_hub()) { + mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; + shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s1.enable; + base = mmioh.s1.base; + m_io = mmioh.s1.m_io; + n_io = mmioh.s1.n_io; + } else if (is_uv2_hub()) { + mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - map_high("MMIOH", mmioh.s2.base, shift, mmioh.s2.m_io, - max_pnode, map_uc); + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s2.enable; + base = mmioh.s2.base; + m_io = mmioh.s2.m_io; + n_io = mmioh.s2.n_io; + } else + return; + + if (enable) { + max_pnode &= (1 << n_io) - 1; + pr_info( + "UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", + base, shift, m_io, n_io, max_pnode); + map_high("MMIOH", base, shift, m_io, max_pnode, map_uc); + } else { + pr_info("UV: MMIOH disabled\n"); } } @@ -724,42 +860,41 @@ void uv_nmi_init(void) void __init uv_system_init(void) { union uvh_rh_gam_config_mmr_u m_n_config; - union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; union uvh_node_id_u node_id; unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; - int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io; - int gnode_extra, max_pnode = 0; + int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; + int gnode_extra, min_pnode = 999999, max_pnode = -1; unsigned long mmr_base, present, paddr; - unsigned short pnode_mask, pnode_io_mask; + unsigned short pnode_mask; + char *hub = (is_uv1_hub() ? "UV1" : + (is_uv2_hub() ? "UV2" : + "UV3")); - printk(KERN_INFO "UV: Found %s hub\n", is_uv1_hub() ? "UV1" : "UV2"); + pr_info("UV: Found %s hub\n", hub); map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; - mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR); - n_io = is_uv1_hub() ? mmioh.s1.n_io : mmioh.s2.n_io; + pnode_mask = (1 << n_val) - 1; mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; - pnode_mask = (1 << n_val) - 1; - pnode_io_mask = (1 << n_io) - 1; node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1; gnode_upper = ((unsigned long)gnode_extra << m_val); - printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n", - n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask); + pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x\n", + n_val, m_val, pnode_mask, gnode_upper, gnode_extra); - printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base); + pr_info("UV: global MMR base 0x%lx\n", mmr_base); for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) uv_possible_blades += hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8)); /* uv_num_possible_blades() is really the hub count */ - printk(KERN_INFO "UV: Found %d blades, %d hubs\n", + pr_info("UV: Found %d blades, %d hubs\n", is_uv1_hub() ? uv_num_possible_blades() : (uv_num_possible_blades() + 1) / 2, uv_num_possible_blades()); @@ -794,6 +929,7 @@ void __init uv_system_init(void) uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; spin_lock_init(&uv_blade_info[blade].nmi_lock); + min_pnode = min(pnode, min_pnode); max_pnode = max(pnode, max_pnode); blade++; } @@ -856,7 +992,7 @@ void __init uv_system_init(void) map_gru_high(max_pnode); map_mmr_high(max_pnode); - map_mmioh_high(max_pnode & pnode_io_mask); + map_mmioh_high(min_pnode, max_pnode); uv_cpu_init(); uv_scir_register_cpu_notifier(); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index d65464e..8d7012b 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -899,6 +899,7 @@ static void apm_cpu_idle(void) static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ static unsigned int last_stime; /* = 0 */ + cputime_t stime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -906,23 +907,23 @@ static void apm_cpu_idle(void) WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012"); recalc: + task_cputime(current, NULL, &stime); if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; - last_jiffies = jiffies; - last_stime = current->stime; } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = current->stime - last_stime; + idle_percentage = stime - last_stime; idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); if (apm_info.forbid_idle) use_apm_idle = 0; - last_jiffies = jiffies; - last_stime = current->stime; } + last_jiffies = jiffies; + last_stime = stime; + bucket = IDLE_LEAKY_MAX; while (!need_resched()) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 15239ff..782c456 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -364,9 +364,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) #endif } -int amd_get_nb_id(int cpu) +u16 amd_get_nb_id(int cpu) { - int id = 0; + u16 id = 0; #ifdef CONFIG_SMP id = per_cpu(cpu_llc_id, cpu); #endif diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index a8f8fa9..1e7e84a 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -79,3 +79,10 @@ void __init init_hypervisor_platform(void) if (x86_hyper->init_platform) x86_hyper->init_platform(); } + +bool __init hypervisor_x2apic_available(void) +{ + return x86_hyper && + x86_hyper->x2apic_available && + x86_hyper->x2apic_available(); +} diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index fe9edec..7c6f7d5 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -298,8 +298,7 @@ struct _cache_attr { unsigned int); }; -#ifdef CONFIG_AMD_NB - +#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS) /* * L3 cache descriptors */ @@ -524,9 +523,9 @@ store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, static struct _cache_attr subcaches = __ATTR(subcaches, 0644, show_subcaches, store_subcaches); -#else /* CONFIG_AMD_NB */ +#else #define amd_init_l3_cache(x, y) -#endif /* CONFIG_AMD_NB */ +#endif /* CONFIG_AMD_NB && CONFIG_SYSFS */ static int __cpuinit cpuid4_cache_lookup_regs(int index, @@ -1227,7 +1226,7 @@ static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = { .notifier_call = cacheinfo_cpu_callback, }; -static int __cpuinit cache_sysfs_init(void) +static int __init cache_sysfs_init(void) { int i; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 80dbda8..fc7608a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -512,11 +512,8 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { - if (!mce_ring_empty()) { - struct work_struct *work = &__get_cpu_var(mce_work); - if (!work_pending(work)) - schedule_work(work); - } + if (!mce_ring_empty()) + schedule_work(&__get_cpu_var(mce_work)); } DEFINE_PER_CPU(struct irq_work, mce_irq_work); @@ -1351,12 +1348,7 @@ int mce_notify_irq(void) /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); - /* - * There is no risk of missing notifications because - * work_pending is always cleared before the function is - * executed. - */ - if (mce_helper[0] && !work_pending(&mce_trigger_work)) + if (mce_helper[0]) schedule_work(&mce_trigger_work); if (__ratelimit(&ratelimit)) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 0a630dd..a7d26d8 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -14,10 +14,15 @@ #include <linux/time.h> #include <linux/clocksource.h> #include <linux/module.h> +#include <linux/hardirq.h> +#include <linux/interrupt.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> #include <asm/mshyperv.h> +#include <asm/desc.h> +#include <asm/idle.h> +#include <asm/irq_regs.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); @@ -30,6 +35,13 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; + /* + * Xen emulates Hyper-V to support enlightened Windows. + * Check to see first if we are on a Xen Hypervisor. + */ + if (xen_cpuid_base()) + return false; + cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -68,7 +80,14 @@ static void __init ms_hyperv_init_platform(void) printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); - clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); + if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) + clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); +#if IS_ENABLED(CONFIG_HYPERV) + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); +#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -77,3 +96,36 @@ const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .init_platform = ms_hyperv_init_platform, }; EXPORT_SYMBOL(x86_hyper_ms_hyperv); + +#if IS_ENABLED(CONFIG_HYPERV) +static int vmbus_irq = -1; +static irq_handler_t vmbus_isr; + +void hv_register_vmbus_handler(int irq, irq_handler_t handler) +{ + vmbus_irq = irq; + vmbus_isr = handler; +} + +void hyperv_vector_handler(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + struct irq_desc *desc; + + irq_enter(); + exit_idle(); + + desc = irq_to_desc(vmbus_irq); + + if (desc) + generic_handle_irq_desc(vmbus_irq, desc); + + irq_exit(); + set_irq_regs(old_regs); +} +#else +void hv_register_vmbus_handler(int irq, irq_handler_t handler) +{ +} +#endif +EXPORT_SYMBOL_GPL(hv_register_vmbus_handler); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 6774c17..bf0f01a 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -829,7 +829,7 @@ static inline void x86_assign_hw_event(struct perf_event *event, } else { hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); - hwc->event_base_rdpmc = hwc->idx; + hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx); } } @@ -1310,11 +1310,6 @@ static struct attribute_group x86_pmu_format_group = { .attrs = NULL, }; -struct perf_pmu_events_attr { - struct device_attribute attr; - u64 id; -}; - /* * Remove all undefined events (x86_pmu.event_map(id) == 0) * out of events_attr attributes. @@ -1348,11 +1343,9 @@ static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *at #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr -#define EVENT_ATTR(_name, _id) \ -static struct perf_pmu_events_attr EVENT_VAR(_id) = { \ - .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ - .id = PERF_COUNT_HW_##_id, \ -}; +#define EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id, \ + events_sysfs_show) EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 115c1ea..7f5c75c 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -325,6 +325,8 @@ struct x86_pmu { int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; unsigned perfctr; + int (*addr_offset)(int index, bool eventsel); + int (*rdpmc_index)(int index); u64 (*event_map)(int); int max_events; int num_counters; @@ -446,28 +448,21 @@ extern u64 __read_mostly hw_cache_extra_regs u64 x86_perf_event_update(struct perf_event *event); -static inline int x86_pmu_addr_offset(int index) +static inline unsigned int x86_pmu_config_addr(int index) { - int offset; - - /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ - alternative_io(ASM_NOP2, - "shll $1, %%eax", - X86_FEATURE_PERFCTR_CORE, - "=a" (offset), - "a" (index)); - - return offset; + return x86_pmu.eventsel + (x86_pmu.addr_offset ? + x86_pmu.addr_offset(index, true) : index); } -static inline unsigned int x86_pmu_config_addr(int index) +static inline unsigned int x86_pmu_event_addr(int index) { - return x86_pmu.eventsel + x86_pmu_addr_offset(index); + return x86_pmu.perfctr + (x86_pmu.addr_offset ? + x86_pmu.addr_offset(index, false) : index); } -static inline unsigned int x86_pmu_event_addr(int index) +static inline int x86_pmu_rdpmc_index(int index) { - return x86_pmu.perfctr + x86_pmu_addr_offset(index); + return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index; } int x86_setup_perfctr(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index c93bc4e..dfdab42 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -132,21 +132,102 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } -static int amd_pmu_hw_config(struct perf_event *event) +static struct event_constraint *amd_nb_event_constraint; + +/* + * Previously calculated offsets + */ +static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly; +static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly; +static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly; + +/* + * Legacy CPUs: + * 4 counters starting at 0xc0010000 each offset by 1 + * + * CPUs with core performance counter extensions: + * 6 counters starting at 0xc0010200 each offset by 2 + * + * CPUs with north bridge performance counter extensions: + * 4 additional counters starting at 0xc0010240 each offset by 2 + * (indexed right above either one of the above core counters) + */ +static inline int amd_pmu_addr_offset(int index, bool eventsel) { - int ret; + int offset, first, base; - /* pass precise event sampling to ibs: */ - if (event->attr.precise_ip && get_ibs_caps()) - return -ENOENT; + if (!index) + return index; + + if (eventsel) + offset = event_offsets[index]; + else + offset = count_offsets[index]; + + if (offset) + return offset; + + if (amd_nb_event_constraint && + test_bit(index, amd_nb_event_constraint->idxmsk)) { + /* + * calculate the offset of NB counters with respect to + * base eventsel or perfctr + */ + + first = find_first_bit(amd_nb_event_constraint->idxmsk, + X86_PMC_IDX_MAX); + + if (eventsel) + base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel; + else + base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr; + + offset = base + ((index - first) << 1); + } else if (!cpu_has_perfctr_core) + offset = index; + else + offset = index << 1; + + if (eventsel) + event_offsets[index] = offset; + else + count_offsets[index] = offset; + + return offset; +} + +static inline int amd_pmu_rdpmc_index(int index) +{ + int ret, first; + + if (!index) + return index; + + ret = rdpmc_indexes[index]; - ret = x86_pmu_hw_config(event); if (ret) return ret; - if (has_branch_stack(event)) - return -EOPNOTSUPP; + if (amd_nb_event_constraint && + test_bit(index, amd_nb_event_constraint->idxmsk)) { + /* + * according to the mnual, ECX value of the NB counters is + * the index of the NB counter (0, 1, 2 or 3) plus 6 + */ + + first = find_first_bit(amd_nb_event_constraint->idxmsk, + X86_PMC_IDX_MAX); + ret = index - first + 6; + } else + ret = index; + + rdpmc_indexes[index] = ret; + + return ret; +} +static int amd_core_hw_config(struct perf_event *event) +{ if (event->attr.exclude_host && event->attr.exclude_guest) /* * When HO == GO == 1 the hardware treats that as GO == HO == 0 @@ -156,14 +237,37 @@ static int amd_pmu_hw_config(struct perf_event *event) event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | ARCH_PERFMON_EVENTSEL_OS); else if (event->attr.exclude_host) - event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY; + event->hw.config |= AMD64_EVENTSEL_GUESTONLY; else if (event->attr.exclude_guest) - event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY; + event->hw.config |= AMD64_EVENTSEL_HOSTONLY; + + return 0; +} + +/* + * NB counters do not support the following event select bits: + * Host/Guest only + * Counter mask + * Invert counter mask + * Edge detect + * OS/User mode + */ +static int amd_nb_hw_config(struct perf_event *event) +{ + /* for NB, we only allow system wide counting mode */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_host || event->attr.exclude_guest) + return -EINVAL; - if (event->attr.type != PERF_TYPE_RAW) - return 0; + event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | + ARCH_PERFMON_EVENTSEL_OS); - event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; + if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB | + ARCH_PERFMON_EVENTSEL_INT)) + return -EINVAL; return 0; } @@ -181,6 +285,11 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc) return (hwc->config & 0xe0) == 0xe0; } +static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc) +{ + return amd_nb_event_constraint && amd_is_nb_event(hwc); +} + static inline int amd_has_nb(struct cpu_hw_events *cpuc) { struct amd_nb *nb = cpuc->amd_nb; @@ -188,20 +297,37 @@ static inline int amd_has_nb(struct cpu_hw_events *cpuc) return nb && nb->nb_id != -1; } -static void amd_put_event_constraints(struct cpu_hw_events *cpuc, - struct perf_event *event) +static int amd_pmu_hw_config(struct perf_event *event) +{ + int ret; + + /* pass precise event sampling to ibs: */ + if (event->attr.precise_ip && get_ibs_caps()) + return -ENOENT; + + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + ret = x86_pmu_hw_config(event); + if (ret) + return ret; + + if (event->attr.type == PERF_TYPE_RAW) + event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; + + if (amd_is_perfctr_nb_event(&event->hw)) + return amd_nb_hw_config(event); + + return amd_core_hw_config(event); +} + +static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; int i; /* - * only care about NB events - */ - if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc))) - return; - - /* * need to scan whole list because event may not have * been assigned during scheduling * @@ -215,6 +341,19 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc, } } +static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc) +{ + int core_id = cpu_data(smp_processor_id()).cpu_core_id; + + /* deliver interrupts only to this core */ + if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) { + hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE; + hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK; + hwc->config |= (u64)(core_id) << + AMD64_EVENTSEL_INT_CORE_SEL_SHIFT; + } +} + /* * AMD64 NorthBridge events need special treatment because * counter access needs to be synchronized across all cores @@ -247,24 +386,24 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc, * * Given that resources are allocated (cmpxchg), they must be * eventually freed for others to use. This is accomplished by - * calling amd_put_event_constraints(). + * calling __amd_put_nb_event_constraints() * * Non NB events are not impacted by this restriction. */ static struct event_constraint * -amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +__amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, + struct event_constraint *c) { struct hw_perf_event *hwc = &event->hw; struct amd_nb *nb = cpuc->amd_nb; - struct perf_event *old = NULL; - int max = x86_pmu.num_counters; - int i, j, k = -1; + struct perf_event *old; + int idx, new = -1; - /* - * if not NB event or no NB, then no constraints - */ - if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc))) - return &unconstrained; + if (!c) + c = &unconstrained; + + if (cpuc->is_fake) + return c; /* * detect if already present, if so reuse @@ -276,48 +415,36 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) * because of successive calls to x86_schedule_events() from * hw_perf_group_sched_in() without hw_perf_enable() */ - for (i = 0; i < max; i++) { - /* - * keep track of first free slot - */ - if (k == -1 && !nb->owners[i]) - k = i; + for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) { + if (new == -1 || hwc->idx == idx) + /* assign free slot, prefer hwc->idx */ + old = cmpxchg(nb->owners + idx, NULL, event); + else if (nb->owners[idx] == event) + /* event already present */ + old = event; + else + continue; + + if (old && old != event) + continue; + + /* reassign to this slot */ + if (new != -1) + cmpxchg(nb->owners + new, event, NULL); + new = idx; /* already present, reuse */ - if (nb->owners[i] == event) - goto done; - } - /* - * not present, so grab a new slot - * starting either at: - */ - if (hwc->idx != -1) { - /* previous assignment */ - i = hwc->idx; - } else if (k != -1) { - /* start from free slot found */ - i = k; - } else { - /* - * event not found, no slot found in - * first pass, try again from the - * beginning - */ - i = 0; - } - j = i; - do { - old = cmpxchg(nb->owners+i, NULL, event); - if (!old) + if (old == event) break; - if (++i == max) - i = 0; - } while (i != j); -done: - if (!old) - return &nb->event_constraints[i]; - - return &emptyconstraint; + } + + if (new == -1) + return &emptyconstraint; + + if (amd_is_perfctr_nb_event(hwc)) + amd_nb_interrupt_hw_config(hwc); + + return &nb->event_constraints[new]; } static struct amd_nb *amd_alloc_nb(int cpu) @@ -364,7 +491,7 @@ static void amd_pmu_cpu_starting(int cpu) struct amd_nb *nb; int i, nb_id; - cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; if (boot_cpu_data.x86_max_cores < 2) return; @@ -407,6 +534,26 @@ static void amd_pmu_cpu_dead(int cpu) } } +static struct event_constraint * +amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + /* + * if not NB event or no NB, then no constraints + */ + if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))) + return &unconstrained; + + return __amd_get_nb_event_constraints(cpuc, event, + amd_nb_event_constraint); +} + +static void amd_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + if (amd_has_nb(cpuc) && amd_is_nb_event(&event->hw)) + __amd_put_nb_event_constraints(cpuc, event); +} + PMU_FORMAT_ATTR(event, "config:0-7,32-35"); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -496,6 +643,9 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09, static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); +static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0); +static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0); + static struct event_constraint * amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -561,8 +711,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev return &amd_f15_PMC20; } case AMD_EVENT_NB: - /* not yet implemented */ - return &emptyconstraint; + return __amd_get_nb_event_constraints(cpuc, event, + amd_nb_event_constraint); default: return &emptyconstraint; } @@ -587,6 +737,8 @@ static __initconst const struct x86_pmu amd_pmu = { .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, + .addr_offset = amd_pmu_addr_offset, + .rdpmc_index = amd_pmu_rdpmc_index, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), .num_counters = AMD64_NUM_COUNTERS, @@ -608,7 +760,7 @@ static __initconst const struct x86_pmu amd_pmu = { static int setup_event_constraints(void) { - if (boot_cpu_data.x86 >= 0x15) + if (boot_cpu_data.x86 == 0x15) x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; return 0; } @@ -638,6 +790,23 @@ static int setup_perfctr_core(void) return 0; } +static int setup_perfctr_nb(void) +{ + if (!cpu_has_perfctr_nb) + return -ENODEV; + + x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB; + + if (cpu_has_perfctr_core) + amd_nb_event_constraint = &amd_NBPMC96; + else + amd_nb_event_constraint = &amd_NBPMC74; + + printk(KERN_INFO "perf: AMD northbridge performance counters detected\n"); + + return 0; +} + __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -648,6 +817,7 @@ __init int amd_pmu_init(void) setup_event_constraints(); setup_perfctr_core(); + setup_perfctr_nb(); /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, @@ -678,7 +848,7 @@ void amd_pmu_disable_virt(void) * SVM is disabled the Guest-only bits still gets set and the counter * will not count anything. */ - cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; + cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; /* Reload all events */ x86_pmu_disable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 93b9e11..4914e94 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2019,7 +2019,10 @@ __init int intel_pmu_init(void) break; case 28: /* Atom */ - case 54: /* Cedariew */ + case 38: /* Lincroft */ + case 39: /* Penwell */ + case 53: /* Cloverview */ + case 54: /* Cedarview */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2084,6 +2087,7 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; case 58: /* IvyBridge */ + case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index f2af39f..4820c23 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -19,7 +19,7 @@ static const u64 p6_perfmon_event_map[] = }; -static __initconst u64 p6_hw_cache_event_ids +static u64 p6_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index d22d0c4..03a3632 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -33,6 +33,9 @@ #define VMWARE_PORT_CMD_GETVERSION 10 #define VMWARE_PORT_CMD_GETHZ 45 +#define VMWARE_PORT_CMD_GETVCPU_INFO 68 +#define VMWARE_PORT_CMD_LEGACY_X2APIC 3 +#define VMWARE_PORT_CMD_VCPU_RESERVED 31 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ __asm__("inl (%%dx)" : \ @@ -125,10 +128,20 @@ static void __cpuinit vmware_set_cpu_features(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); } +/* Checks if hypervisor supports x2apic without VT-D interrupt remapping. */ +static bool __init vmware_legacy_x2apic_available(void) +{ + uint32_t eax, ebx, ecx, edx; + VMWARE_PORT(GETVCPU_INFO, eax, ebx, ecx, edx); + return (eax & (1 << VMWARE_PORT_CMD_VCPU_RESERVED)) == 0 && + (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0; +} + const __refconst struct hypervisor_x86 x86_hyper_vmware = { .name = "VMware", .detect = vmware_platform, .set_cpu_features = vmware_set_cpu_features, .init_platform = vmware_platform_setup, + .x2apic_available = vmware_legacy_x2apic_available, }; EXPORT_SYMBOL(x86_hyper_vmware); diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 6ed91d9..8831176 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1091,11 +1091,18 @@ ENTRY(xen_failsafe_callback) _ASM_EXTABLE(4b,9b) ENDPROC(xen_failsafe_callback) -BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK, +BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, xen_evtchn_do_upcall) #endif /* CONFIG_XEN */ +#if IS_ENABLED(CONFIG_HYPERV) + +BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + hyperv_vector_handler) + +#endif /* CONFIG_HYPERV */ + #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 07a7a04..048f224 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1454,11 +1454,16 @@ ENTRY(xen_failsafe_callback) CFI_ENDPROC END(xen_failsafe_callback) -apicinterrupt XEN_HVM_EVTCHN_CALLBACK \ +apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ xen_hvm_callback_vector xen_evtchn_do_upcall #endif /* CONFIG_XEN */ +#if IS_ENABLED(CONFIG_HYPERV) +apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ + hyperv_callback_vector hyperv_vector_handler +#endif /* CONFIG_HYPERV */ + /* * Some functions should be protected against kprobes */ @@ -1781,6 +1786,7 @@ first_nmi: * Leave room for the "copied" frame */ subq $(5*8), %rsp + CFI_ADJUST_CFA_OFFSET 5*8 /* Copy the stack frame to the Saved frame */ .rept 5 @@ -1863,10 +1869,8 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - RESTORE_ALL 8 - - /* Pop the extra iret frame */ - addq $(5*8), %rsp + /* Pop the extra iret frame at once */ + RESTORE_ALL 6*8 /* Clear the NMI executing stack variable */ movq $0, 5*8(%rsp) diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index c18f59d..6773c91 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -18,6 +18,7 @@ #include <asm/io_apic.h> #include <asm/bios_ebda.h> #include <asm/tlbflush.h> +#include <asm/bootparam_utils.h> static void __init i386_default_early_setup(void) { @@ -30,6 +31,8 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { + sanitize_boot_params(&boot_params); + memblock_reserve(__pa_symbol(&_text), __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 037df57..849fc9e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -25,6 +25,7 @@ #include <asm/kdebug.h> #include <asm/e820.h> #include <asm/bios_ebda.h> +#include <asm/bootparam_utils.h> static void __init zap_identity_mappings(void) { @@ -46,6 +47,7 @@ static void __init copy_bootdata(char *real_mode_data) char * command_line; memcpy(&boot_params, real_mode_data, sizeof boot_params); + sanitize_boot_params(&boot_params); if (boot_params.hdr.cmd_line_ptr) { command_line = __va(boot_params.hdr.cmd_line_ptr); memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 8e7f655..3c3f58a 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -300,37 +300,52 @@ ENTRY(startup_32_smp) leal -__PAGE_OFFSET(%ecx),%esp default_entry: +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) + movl $(CR0_STATE & ~X86_CR0_PG),%eax + movl %eax,%cr0 + +/* + * We want to start out with EFLAGS unambiguously cleared. Some BIOSes leave + * bits like NT set. This would confuse the debugger if this code is traced. So + * initialize them properly now before switching to protected mode. That means + * DF in particular (even though we have cleared it earlier after copying the + * command line) because GCC expects it. + */ + pushl $0 + popfl + /* - * New page tables may be in 4Mbyte page mode and may - * be using the global pages. + * New page tables may be in 4Mbyte page mode and may be using the global pages. * - * NOTE! If we are on a 486 we may have no cr4 at all! - * Specifically, cr4 exists if and only if CPUID exists - * and has flags other than the FPU flag set. + * NOTE! If we are on a 486 we may have no cr4 at all! Specifically, cr4 exists + * if and only if CPUID exists and has flags other than the FPU flag set. */ + movl $-1,pa(X86_CPUID) # preset CPUID level movl $X86_EFLAGS_ID,%ecx pushl %ecx - popfl + popfl # set EFLAGS=ID pushfl - popl %eax - pushl $0 - popfl - pushfl - popl %edx - xorl %edx,%eax - testl %ecx,%eax - jz 6f # No ID flag = no CPUID = no CR4 + popl %eax # get EFLAGS + testl $X86_EFLAGS_ID,%eax # did EFLAGS.ID remained set? + jz enable_paging # hw disallowed setting of ID bit + # which means no CPUID and no CR4 + + xorl %eax,%eax + cpuid + movl %eax,pa(X86_CPUID) # save largest std CPUID function movl $1,%eax cpuid - andl $~1,%edx # Ignore CPUID.FPU - jz 6f # No flags or only CPUID.FPU = no CR4 + andl $~1,%edx # Ignore CPUID.FPU + jz enable_paging # No flags or only CPUID.FPU = no CR4 movl pa(mmu_cr4_features),%eax movl %eax,%cr4 testb $X86_CR4_PAE, %al # check if PAE is enabled - jz 6f + jz enable_paging /* Check if extended functions are implemented */ movl $0x80000000, %eax @@ -338,7 +353,7 @@ default_entry: /* Value must be in the range 0x80000001 to 0x8000ffff */ subl $0x80000001, %eax cmpl $(0x8000ffff-0x80000001), %eax - ja 6f + ja enable_paging /* Clear bogus XD_DISABLE bits */ call verify_cpu @@ -347,7 +362,7 @@ default_entry: cpuid /* Execute Disable bit supported? */ btl $(X86_FEATURE_NX & 31), %edx - jnc 6f + jnc enable_paging /* Setup EFER (Extended Feature Enable Register) */ movl $MSR_EFER, %ecx @@ -357,15 +372,14 @@ default_entry: /* Make changes effective */ wrmsr -6: +enable_paging: /* * Enable paging */ movl $pa(initial_page_table), %eax movl %eax,%cr3 /* set the page table pointer.. */ - movl %cr0,%eax - orl $X86_CR0_PG,%eax + movl $CR0_STATE,%eax movl %eax,%cr0 /* ..and set paging (PG) bit */ ljmp $__BOOT_CS,$1f /* Clear prefetch and normalize %eip */ 1: @@ -373,14 +387,6 @@ default_entry: addl $__PAGE_OFFSET, %esp /* - * Initialize eflags. Some BIOS's leave bits like NT set. This would - * confuse the debugger if this code is traced. - * XXX - best to initialize before switching to protected mode. - */ - pushl $0 - popfl - -/* * start system 32-bit setup. We need to re-do some of the things done * in 16-bit mode for the "real" operations. */ @@ -389,31 +395,11 @@ default_entry: jz 1f # Did we do this already? call *%eax 1: - -/* check if it is 486 or 386. */ + /* - * XXX - this does a lot of unnecessary setup. Alignment checks don't - * apply at our cpl of 0 and the stack ought to be aligned already, and - * we don't need to preserve eflags. + * Check if it is 486 */ - movl $-1,X86_CPUID # -1 for no CPUID initially - movb $3,X86 # at least 386 - pushfl # push EFLAGS - popl %eax # get EFLAGS - movl %eax,%ecx # save original EFLAGS - xorl $0x240000,%eax # flip AC and ID bits in EFLAGS - pushl %eax # copy to EFLAGS - popfl # set EFLAGS - pushfl # get new EFLAGS - popl %eax # put it in eax - xorl %ecx,%eax # change in flags - pushl %ecx # restore original EFLAGS - popfl - testl $0x40000,%eax # check if AC bit changed - je is386 - - movb $4,X86 # at least 486 - testl $0x200000,%eax # check if ID bit changed + cmpl $-1,X86_CPUID je is486 /* get vendor info */ @@ -439,11 +425,10 @@ default_entry: movb %cl,X86_MASK movl %edx,X86_CAPABILITY -is486: movl $0x50022,%ecx # set AM, WP, NE and MP - jmp 2f - -is386: movl $2,%ecx # set MP -2: movl %cr0,%eax +is486: + movb $4,X86 + movl $0x50022,%ecx # set AM, WP, NE and MP + movl %cr0,%eax andl $0x80000011,%eax # Save PG,PE,ET orl %ecx,%eax movl %eax,%cr0 @@ -468,7 +453,6 @@ is386: movl $2,%ecx # set MP xorl %eax,%eax # Clear LDT lldt %ax - cld # gcc2 wants the direction flag cleared at all times pushl $0 # fake return address for unwinder jmp *(initial_code) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index e28670f..da85a8e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -478,7 +478,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { - if (arch_setup_hpet_msi(irq, hpet_blockid)) { + if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { destroy_irq(irq); return -EINVAL; } diff --git a/arch/x86/kernel/kprobes/Makefile b/arch/x86/kernel/kprobes/Makefile new file mode 100644 index 0000000..0d33169 --- /dev/null +++ b/arch/x86/kernel/kprobes/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for kernel probes +# + +obj-$(CONFIG_KPROBES) += core.o +obj-$(CONFIG_OPTPROBES) += opt.o +obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o diff --git a/arch/x86/kernel/kprobes-common.h b/arch/x86/kernel/kprobes/common.h index 3230b68..2e9d4b5 100644 --- a/arch/x86/kernel/kprobes-common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -99,4 +99,15 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig return addr; } #endif + +#ifdef CONFIG_KPROBES_ON_FTRACE +extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb); +#else +static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + return 0; +} +#endif #endif diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes/core.c index 57916c0..e124554 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes/core.c @@ -58,7 +58,7 @@ #include <asm/insn.h> #include <asm/debugreg.h> -#include "kprobes-common.h" +#include "common.h" void jprobe_return_end(void); @@ -78,7 +78,7 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); * Groups, and some special opcodes can not boost. * This is non-const and volatile to keep gcc from statically * optimizing it out, as variable_test_bit makes gcc think only - * *(unsigned long*) is used. + * *(unsigned long*) is used. */ static volatile u32 twobyte_is_boostable[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ @@ -117,7 +117,7 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) struct __arch_relative_insn { u8 op; s32 raddr; - } __attribute__((packed)) *insn; + } __packed *insn; insn = (struct __arch_relative_insn *)from; insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); @@ -541,23 +541,6 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } -#ifdef KPROBES_CAN_USE_FTRACE -static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) -{ - /* - * Emulate singlestep (and also recover regs->ip) - * as if there is a 5byte nop - */ - regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; - if (unlikely(p->post_handler)) { - kcb->kprobe_status = KPROBE_HIT_SSDONE; - p->post_handler(p, regs, 0); - } - __this_cpu_write(current_kprobe, NULL); -} -#endif - /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. @@ -616,13 +599,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) } else if (kprobe_running()) { p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { -#ifdef KPROBES_CAN_USE_FTRACE - if (kprobe_ftrace(p)) { - skip_singlestep(p, regs, kcb); - return 1; - } -#endif - setup_singlestep(p, regs, kcb, 0); + if (!skip_singlestep(p, regs, kcb)) + setup_singlestep(p, regs, kcb, 0); return 1; } } /* else: not a kprobe fault; let the kernel handle it */ @@ -1075,50 +1053,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } -#ifdef KPROBES_CAN_USE_FTRACE -/* Ftrace callback handler for kprobes */ -void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs) -{ - struct kprobe *p; - struct kprobe_ctlblk *kcb; - unsigned long flags; - - /* Disable irq for emulating a breakpoint and avoiding preempt */ - local_irq_save(flags); - - p = get_kprobe((kprobe_opcode_t *)ip); - if (unlikely(!p) || kprobe_disabled(p)) - goto end; - - kcb = get_kprobe_ctlblk(); - if (kprobe_running()) { - kprobes_inc_nmissed_count(p); - } else { - /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ - regs->ip = ip + sizeof(kprobe_opcode_t); - - __this_cpu_write(current_kprobe, p); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) - skip_singlestep(p, regs, kcb); - /* - * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe. - */ - } -end: - local_irq_restore(flags); -} - -int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) -{ - p->ainsn.insn = NULL; - p->ainsn.boostable = -1; - return 0; -} -#endif - int __init arch_init_kprobes(void) { return arch_init_optprobes(); diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c new file mode 100644 index 0000000..23ef5c5 --- /dev/null +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -0,0 +1,93 @@ +/* + * Dynamic Ftrace based Kprobes Optimization + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) Hitachi Ltd., 2012 + */ +#include <linux/kprobes.h> +#include <linux/ptrace.h> +#include <linux/hardirq.h> +#include <linux/preempt.h> +#include <linux/ftrace.h> + +#include "common.h" + +static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + __this_cpu_write(current_kprobe, NULL); + return 1; +} + +int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + if (kprobe_ftrace(p)) + return __skip_singlestep(p, regs, kcb); + else + return 0; +} + +/* Ftrace callback handler for kprobes */ +void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + unsigned long flags; + + /* Disable irq for emulating a breakpoint and avoiding preempt */ + local_irq_save(flags); + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto end; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) + __skip_singlestep(p, regs, kcb); + /* + * If pre_handler returns !0, it sets regs->ip and + * resets current kprobe. + */ + } +end: + local_irq_restore(flags); +} + +int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = -1; + return 0; +} diff --git a/arch/x86/kernel/kprobes-opt.c b/arch/x86/kernel/kprobes/opt.c index c5e410e..76dc6f0 100644 --- a/arch/x86/kernel/kprobes-opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -37,7 +37,7 @@ #include <asm/insn.h> #include <asm/debugreg.h> -#include "kprobes-common.h" +#include "common.h" unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 9c2bd8b..2b44ea5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -505,6 +505,7 @@ static bool __init kvm_detect(void) const struct hypervisor_x86 x86_hyper_kvm __refconst = { .name = "KVM", .detect = kvm_detect, + .x2apic_available = kvm_para_available, }; EXPORT_SYMBOL_GPL(x86_hyper_kvm); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index a7c5661..4929502 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -174,6 +174,9 @@ static int msr_open(struct inode *inode, struct file *file) unsigned int cpu; struct cpuinfo_x86 *c; + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + cpu = iminor(file->f_path.dentry->d_inode); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 0f5dec5..872079a 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -56,7 +56,7 @@ struct device x86_dma_fallback_dev = { EXPORT_SYMBOL(x86_dma_fallback_dev); /* Number of entries preallocated for DMA-API debugging */ -#define PREALLOC_DMA_DEBUG_ENTRIES 32768 +#define PREALLOC_DMA_DEBUG_ENTRIES 65536 int dma_set_mask(struct device *dev, u64 mask) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index b629bbe..29a8120 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -22,7 +22,7 @@ #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/rcupdate.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/context_tracking.h> #include <asm/uaccess.h> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 4e8ba39..76fa1e9 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -584,7 +584,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_EFI: - if (efi_enabled) + if (efi_enabled(EFI_RUNTIME_SERVICES)) efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD, diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 801602b..2e8f3d3 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -149,7 +149,6 @@ unsigned long mach_get_cmos_time(void) if (century) { century = bcd2bin(century); year += century * 100; - printk(KERN_INFO "Extended CMOS year: %d\n", century * 100); } else year += CMOS_YEARS_OFFS; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 00f6c14..8b24289 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -807,15 +807,15 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - efi_enabled = 1; - efi_64bit = false; + set_bit(EFI_BOOT, &x86_efi_facility); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - efi_enabled = 1; - efi_64bit = true; + set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_64BIT, &x86_efi_facility); } - if (efi_enabled && efi_memblock_x86_reserve_range()) - efi_enabled = 0; + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); #endif x86_init.oem.arch_setup(); @@ -888,7 +888,7 @@ void __init setup_arch(char **cmdline_p) finish_e820_parsing(); - if (efi_enabled) + if (efi_enabled(EFI_BOOT)) efi_init(); dmi_scan_machine(); @@ -971,7 +971,7 @@ void __init setup_arch(char **cmdline_p) * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. */ - if (efi_enabled) + if (efi_enabled(EFI_MEMMAP)) efi_reserve_boot_services(); /* preallocate 4k for mptable mpc */ @@ -1114,7 +1114,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) + if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) conswitchp = &vga_con; #elif defined(CONFIG_DUMMY_CONSOLE) conswitchp = &dummy_con; @@ -1131,14 +1131,14 @@ void __init setup_arch(char **cmdline_p) register_refined_jiffies(CLOCK_TICK_RATE); #ifdef CONFIG_EFI - /* Once setup is done above, disable efi_enabled on mismatched - * firmware/kernel archtectures since there is no support for - * runtime services. + /* Once setup is done above, unmap the EFI memory map on + * mismatched firmware/kernel archtectures since there is no + * support for runtime services. */ - if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) { + if (efi_enabled(EFI_BOOT) && + IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) { pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); efi_unmap_memmap(); - efi_enabled = 0; } #endif } diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 97ef74b..dbded5a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -157,7 +157,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (flags & MAP_FIXED) return addr; - /* for MAP_32BIT mappings we force the legact mmap base */ + /* for MAP_32BIT mappings we force the legacy mmap base */ if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) goto bottomup; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 06ccb50..4b9ea10 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -623,7 +623,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) ns_now = __cycles_2_ns(tsc_now); if (cpu_khz) { - *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; + *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) + + cpu_khz / 2) / cpu_khz; *offset = ns_now - mult_frac(tsc_now, *scale, (1UL << CYC2NS_SCALE_FACTOR)); } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index c71025b..0ba4cfb 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -680,8 +680,10 @@ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (auprobe->insn[i] == 0x66) continue; - if (auprobe->insn[i] == 0x90) + if (auprobe->insn[i] == 0x90) { + regs->ip += i + 1; return true; + } break; } diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 7a3d075..d065d67 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -19,6 +19,7 @@ #include <asm/time.h> #include <asm/irq.h> #include <asm/io_apic.h> +#include <asm/hpet.h> #include <asm/pat.h> #include <asm/tsc.h> #include <asm/iommu.h> @@ -111,15 +112,22 @@ struct x86_platform_ops x86_platform = { EXPORT_SYMBOL_GPL(x86_platform); struct x86_msi_ops x86_msi = { - .setup_msi_irqs = native_setup_msi_irqs, - .teardown_msi_irq = native_teardown_msi_irq, - .teardown_msi_irqs = default_teardown_msi_irqs, - .restore_msi_irqs = default_restore_msi_irqs, + .setup_msi_irqs = native_setup_msi_irqs, + .compose_msi_msg = native_compose_msi_msg, + .teardown_msi_irq = native_teardown_msi_irq, + .teardown_msi_irqs = default_teardown_msi_irqs, + .restore_msi_irqs = default_restore_msi_irqs, + .setup_hpet_msi = default_setup_hpet_msi, }; struct x86_io_apic_ops x86_io_apic_ops = { - .init = native_io_apic_init_mappings, - .read = native_io_apic_read, - .write = native_io_apic_write, - .modify = native_io_apic_modify, + .init = native_io_apic_init_mappings, + .read = native_io_apic_read, + .write = native_io_apic_write, + .modify = native_io_apic_modify, + .disable = native_disable_io_apic, + .print_entries = native_io_apic_print_entries, + .set_affinity = native_ioapic_set_affinity, + .setup_entry = native_setup_ioapic_entry, + .eoi_ioapic_pin = native_eoi_ioapic_pin, }; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 027088f..fb674fd 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -748,13 +748,15 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, return; } #endif + /* Kernel addresses are always protection faults: */ + if (address >= TASK_SIZE) + error_code |= PF_PROT; - if (unlikely(show_unhandled_signals)) + if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); - /* Kernel addresses are always protection faults: */ tsk->thread.cr2 = address; - tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_PF; force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 2ead3c8..d6eeead 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -605,7 +605,7 @@ kernel_physical_mapping_init(unsigned long start, } if (pgd_changed) - sync_global_pgds(addr, end); + sync_global_pgds(addr, end - 1); __flush_tlb_all(); @@ -831,6 +831,9 @@ int kern_addr_valid(unsigned long addr) if (pud_none(*pud)) return 0; + if (pud_large(*pud)) + return pfn_valid(pud_pfn(*pud)); + pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return 0; @@ -981,7 +984,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) } } - sync_global_pgds((unsigned long)start_page, end); + sync_global_pgds((unsigned long)start_page, end - 1); return 0; } diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index c80b9fb..8dabbed 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -9,6 +9,7 @@ #include <linux/memblock.h> static u64 patterns[] __initdata = { + /* The first entry has to be 0 to leave memtest with zeroed memory */ 0, 0xffffffffffffffffULL, 0x5555555555555555ULL, @@ -110,15 +111,8 @@ void __init early_memtest(unsigned long start, unsigned long end) return; printk(KERN_INFO "early_memtest: # of tests: %d\n", memtest_pattern); - for (i = 0; i < memtest_pattern; i++) { + for (i = memtest_pattern-1; i < UINT_MAX; --i) { idx = i % ARRAY_SIZE(patterns); do_one_pass(patterns[idx], start, end); } - - if (idx > 0) { - printk(KERN_INFO "early_memtest: wipe out " - "test pattern from memory\n"); - /* additional test with pattern 0 will do this */ - do_one_pass(0, start, end); - } } diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 4ddf497..cdd0da9 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -149,39 +149,40 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) int node, pxm; if (srat_disabled()) - return -1; - if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) { - bad_srat(); - return -1; - } + goto out_err; + if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) + goto out_err_bad_srat; if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - return -1; - + goto out_err; if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) - return -1; + goto out_err; + start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; if (acpi_srat_revision <= 1) pxm &= 0xff; + node = setup_node(pxm); if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); - bad_srat(); - return -1; + goto out_err_bad_srat; } - if (numa_add_memblk(node, start, end) < 0) { - bad_srat(); - return -1; - } + if (numa_add_memblk(node, start, end) < 0) + goto out_err_bad_srat; node_set(node, numa_nodes_parsed); printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1); + return 0; +out_err_bad_srat: + bad_srat(); +out_err: + return -1; } void __init acpi_numa_arch_fixup(void) {} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 13a6b29..282375f 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -335,7 +335,7 @@ static const struct file_operations fops_tlbflush = { .llseek = default_llseek, }; -static int __cpuinit create_tlb_flushall_shift(void) +static int __init create_tlb_flushall_shift(void) { debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR, arch_debugfs_dir, NULL, &fops_tlbflush); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index fb29968..082e881 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -548,8 +548,7 @@ static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg, if (cfg->address < 0xFFFFFFFF) return 0; - if (!strcmp(mcfg->header.oem_id, "SGI") || - !strcmp(mcfg->header.oem_id, "SGI2")) + if (!strncmp(mcfg->header.oem_id, "SGI", 3)) return 0; if (mcfg->header.revision >= 1) { diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index 8d87439..01e0231 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -2,10 +2,12 @@ obj-y += ce4100/ obj-y += efi/ obj-y += geode/ +obj-y += goldfish/ obj-y += iris/ obj-y += mrst/ obj-y += olpc/ obj-y += scx200/ obj-y += sfi/ +obj-y += ts5500/ obj-y += visws/ obj-y += uv/ diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index d9c1b95..7145ec6 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -11,20 +11,21 @@ * published by the Free Software Foundation. */ #include <linux/kernel.h> +#include <linux/init.h> #include <linux/acpi.h> #include <linux/efi.h> #include <linux/efi-bgrt.h> struct acpi_table_bgrt *bgrt_tab; -void *bgrt_image; -size_t bgrt_image_size; +void *__initdata bgrt_image; +size_t __initdata bgrt_image_size; struct bmp_header { u16 id; u32 size; } __packed; -void efi_bgrt_init(void) +void __init efi_bgrt_init(void) { acpi_status status; void __iomem *image; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index ad44391..928bf83 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -51,9 +51,6 @@ #define EFI_DEBUG 1 -int efi_enabled; -EXPORT_SYMBOL(efi_enabled); - struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, .acpi = EFI_INVALID_TABLE_ADDR, @@ -69,19 +66,28 @@ EXPORT_SYMBOL(efi); struct efi_memory_map memmap; -bool efi_64bit; - static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; static inline bool efi_is_native(void) { - return IS_ENABLED(CONFIG_X86_64) == efi_64bit; + return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT); +} + +unsigned long x86_efi_facility; + +/* + * Returns 1 if 'facility' is enabled, 0 otherwise. + */ +int efi_enabled(int facility) +{ + return test_bit(facility, &x86_efi_facility) != 0; } +EXPORT_SYMBOL(efi_enabled); static int __init setup_noefi(char *arg) { - efi_enabled = 0; + clear_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); return 0; } early_param("noefi", setup_noefi); @@ -426,6 +432,7 @@ void __init efi_reserve_boot_services(void) void __init efi_unmap_memmap(void) { + clear_bit(EFI_MEMMAP, &x86_efi_facility); if (memmap.map) { early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; @@ -460,7 +467,7 @@ void __init efi_free_boot_services(void) static int __init efi_systab_init(void *phys) { - if (efi_64bit) { + if (efi_enabled(EFI_64BIT)) { efi_system_table_64_t *systab64; u64 tmp = 0; @@ -552,7 +559,7 @@ static int __init efi_config_init(u64 tables, int nr_tables) void *config_tables, *tablep; int i, sz; - if (efi_64bit) + if (efi_enabled(EFI_64BIT)) sz = sizeof(efi_config_table_64_t); else sz = sizeof(efi_config_table_32_t); @@ -572,7 +579,7 @@ static int __init efi_config_init(u64 tables, int nr_tables) efi_guid_t guid; unsigned long table; - if (efi_64bit) { + if (efi_enabled(EFI_64BIT)) { u64 table64; guid = ((efi_config_table_64_t *)tablep)->guid; table64 = ((efi_config_table_64_t *)tablep)->table; @@ -684,7 +691,6 @@ void __init efi_init(void) if (boot_params.efi_info.efi_systab_hi || boot_params.efi_info.efi_memmap_hi) { pr_info("Table located above 4GB, disabling EFI.\n"); - efi_enabled = 0; return; } efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab; @@ -694,10 +700,10 @@ void __init efi_init(void) ((__u64)boot_params.efi_info.efi_systab_hi<<32)); #endif - if (efi_systab_init(efi_phys.systab)) { - efi_enabled = 0; + if (efi_systab_init(efi_phys.systab)) return; - } + + set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* * Show what we know for posterity @@ -715,10 +721,10 @@ void __init efi_init(void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); - if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) { - efi_enabled = 0; + if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) return; - } + + set_bit(EFI_CONFIG_TABLES, &x86_efi_facility); /* * Note: We currently don't support runtime services on an EFI @@ -727,15 +733,17 @@ void __init efi_init(void) if (!efi_is_native()) pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); - else if (efi_runtime_init()) { - efi_enabled = 0; - return; + else { + if (efi_runtime_init()) + return; + set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); } - if (efi_memmap_init()) { - efi_enabled = 0; + if (efi_memmap_init()) return; - } + + set_bit(EFI_MEMMAP, &x86_efi_facility); + #ifdef CONFIG_X86_32 if (efi_is_native()) { x86_platform.get_wallclock = efi_get_time; @@ -941,7 +949,7 @@ void __init efi_enter_virtual_mode(void) * * Call EFI services through wrapper functions. */ - efi.runtime_version = efi_systab.fw_revision; + efi.runtime_version = efi_systab.hdr.revision; efi.get_time = virt_efi_get_time; efi.set_time = virt_efi_set_time; efi.get_wakeup_time = virt_efi_get_wakeup_time; @@ -969,6 +977,9 @@ u32 efi_mem_type(unsigned long phys_addr) efi_memory_desc_t *md; void *p; + if (!efi_enabled(EFI_MEMMAP)) + return 0; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; if ((md->phys_addr <= phys_addr) && diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 95fd505..2b20038 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -38,7 +38,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> -static pgd_t save_pgd __initdata; +static pgd_t *save_pgd __initdata; static unsigned long efi_flags __initdata; static void __init early_code_mapping_set_exec(int executable) @@ -61,12 +61,20 @@ static void __init early_code_mapping_set_exec(int executable) void __init efi_call_phys_prelog(void) { unsigned long vaddress; + int pgd; + int n_pgds; early_code_mapping_set_exec(1); local_irq_save(efi_flags); - vaddress = (unsigned long)__va(0x0UL); - save_pgd = *pgd_offset_k(0x0UL); - set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress)); + + n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); + save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL); + + for (pgd = 0; pgd < n_pgds; pgd++) { + save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE); + vaddress = (unsigned long)__va(pgd * PGDIR_SIZE); + set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress)); + } __flush_tlb_all(); } @@ -75,7 +83,11 @@ void __init efi_call_phys_epilog(void) /* * After the lock is released, the original page table is restored. */ - set_pgd(pgd_offset_k(0x0UL), save_pgd); + int pgd; + int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + for (pgd = 0; pgd < n_pgds; pgd++) + set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]); + kfree(save_pgd); __flush_tlb_all(); local_irq_restore(efi_flags); early_code_mapping_set_exec(0); diff --git a/arch/x86/platform/goldfish/Makefile b/arch/x86/platform/goldfish/Makefile new file mode 100644 index 0000000..f030b53 --- /dev/null +++ b/arch/x86/platform/goldfish/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_GOLDFISH) += goldfish.o diff --git a/arch/x86/platform/goldfish/goldfish.c b/arch/x86/platform/goldfish/goldfish.c new file mode 100644 index 0000000..1693107 --- /dev/null +++ b/arch/x86/platform/goldfish/goldfish.c @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2007 Google, Inc. + * Copyright (C) 2011 Intel, Inc. + * Copyright (C) 2013 Intel, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/irq.h> +#include <linux/platform_device.h> + +/* + * Where in virtual device memory the IO devices (timers, system controllers + * and so on) + */ + +#define GOLDFISH_PDEV_BUS_BASE (0xff001000) +#define GOLDFISH_PDEV_BUS_END (0xff7fffff) +#define GOLDFISH_PDEV_BUS_IRQ (4) + +#define GOLDFISH_TTY_BASE (0x2000) + +static struct resource goldfish_pdev_bus_resources[] = { + { + .start = GOLDFISH_PDEV_BUS_BASE, + .end = GOLDFISH_PDEV_BUS_END, + .flags = IORESOURCE_MEM, + }, + { + .start = GOLDFISH_PDEV_BUS_IRQ, + .end = GOLDFISH_PDEV_BUS_IRQ, + .flags = IORESOURCE_IRQ, + } +}; + +static int __init goldfish_init(void) +{ + platform_device_register_simple("goldfish_pdev_bus", -1, + goldfish_pdev_bus_resources, 2); + return 0; +} +device_initcall(goldfish_init); diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c index 7785b72..bcd1a70 100644 --- a/arch/x86/platform/sfi/sfi.c +++ b/arch/x86/platform/sfi/sfi.c @@ -35,7 +35,7 @@ static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; /* All CPUs enumerated by SFI must be present and enabled */ -static void __cpuinit mp_sfi_register_lapic(u8 id) +static void __init mp_sfi_register_lapic(u8 id) { if (MAX_LOCAL_APIC - id <= 0) { pr_warning("Processor #%d invalid (max %d)\n", diff --git a/arch/x86/platform/ts5500/Makefile b/arch/x86/platform/ts5500/Makefile new file mode 100644 index 0000000..c54e348 --- /dev/null +++ b/arch/x86/platform/ts5500/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_TS5500) += ts5500.o diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c new file mode 100644 index 0000000..39febb2 --- /dev/null +++ b/arch/x86/platform/ts5500/ts5500.c @@ -0,0 +1,339 @@ +/* + * Technologic Systems TS-5500 Single Board Computer support + * + * Copyright (C) 2013 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License as published by the Free Software + * Foundation; either version 2 of the License, or (at your option) any later + * version. + * + * + * This driver registers the Technologic Systems TS-5500 Single Board Computer + * (SBC) and its devices, and exposes information to userspace such as jumpers' + * state or available options. For further information about sysfs entries, see + * Documentation/ABI/testing/sysfs-platform-ts5500. + * + * This code actually supports the TS-5500 platform, but it may be extended to + * support similar Technologic Systems x86-based platforms, such as the TS-5600. + */ + +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/leds.h> +#include <linux/module.h> +#include <linux/platform_data/gpio-ts5500.h> +#include <linux/platform_data/max197.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +/* Product code register */ +#define TS5500_PRODUCT_CODE_ADDR 0x74 +#define TS5500_PRODUCT_CODE 0x60 /* TS-5500 product code */ + +/* SRAM/RS-485/ADC options, and RS-485 RTS/Automatic RS-485 flags register */ +#define TS5500_SRAM_RS485_ADC_ADDR 0x75 +#define TS5500_SRAM BIT(0) /* SRAM option */ +#define TS5500_RS485 BIT(1) /* RS-485 option */ +#define TS5500_ADC BIT(2) /* A/D converter option */ +#define TS5500_RS485_RTS BIT(6) /* RTS for RS-485 */ +#define TS5500_RS485_AUTO BIT(7) /* Automatic RS-485 */ + +/* External Reset/Industrial Temperature Range options register */ +#define TS5500_ERESET_ITR_ADDR 0x76 +#define TS5500_ERESET BIT(0) /* External Reset option */ +#define TS5500_ITR BIT(1) /* Indust. Temp. Range option */ + +/* LED/Jumpers register */ +#define TS5500_LED_JP_ADDR 0x77 +#define TS5500_LED BIT(0) /* LED flag */ +#define TS5500_JP1 BIT(1) /* Automatic CMOS */ +#define TS5500_JP2 BIT(2) /* Enable Serial Console */ +#define TS5500_JP3 BIT(3) /* Write Enable Drive A */ +#define TS5500_JP4 BIT(4) /* Fast Console (115K baud) */ +#define TS5500_JP5 BIT(5) /* User Jumper */ +#define TS5500_JP6 BIT(6) /* Console on COM1 (req. JP2) */ +#define TS5500_JP7 BIT(7) /* Undocumented (Unused) */ + +/* A/D Converter registers */ +#define TS5500_ADC_CONV_BUSY_ADDR 0x195 /* Conversion state register */ +#define TS5500_ADC_CONV_BUSY BIT(0) +#define TS5500_ADC_CONV_INIT_LSB_ADDR 0x196 /* Start conv. / LSB register */ +#define TS5500_ADC_CONV_MSB_ADDR 0x197 /* MSB register */ +#define TS5500_ADC_CONV_DELAY 12 /* usec */ + +/** + * struct ts5500_sbc - TS-5500 board description + * @id: Board product ID. + * @sram: Flag for SRAM option. + * @rs485: Flag for RS-485 option. + * @adc: Flag for Analog/Digital converter option. + * @ereset: Flag for External Reset option. + * @itr: Flag for Industrial Temperature Range option. + * @jumpers: Bitfield for jumpers' state. + */ +struct ts5500_sbc { + int id; + bool sram; + bool rs485; + bool adc; + bool ereset; + bool itr; + u8 jumpers; +}; + +/* Board signatures in BIOS shadow RAM */ +static const struct { + const char * const string; + const ssize_t offset; +} ts5500_signatures[] __initdata = { + { "TS-5x00 AMD Elan", 0xb14 }, +}; + +static int __init ts5500_check_signature(void) +{ + void __iomem *bios; + int i, ret = -ENODEV; + + bios = ioremap(0xf0000, 0x10000); + if (!bios) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(ts5500_signatures); i++) { + if (check_signature(bios + ts5500_signatures[i].offset, + ts5500_signatures[i].string, + strlen(ts5500_signatures[i].string))) { + ret = 0; + break; + } + } + + iounmap(bios); + return ret; +} + +static int __init ts5500_detect_config(struct ts5500_sbc *sbc) +{ + u8 tmp; + int ret = 0; + + if (!request_region(TS5500_PRODUCT_CODE_ADDR, 4, "ts5500")) + return -EBUSY; + + tmp = inb(TS5500_PRODUCT_CODE_ADDR); + if (tmp != TS5500_PRODUCT_CODE) { + pr_err("This platform is not a TS-5500 (found ID 0x%x)\n", tmp); + ret = -ENODEV; + goto cleanup; + } + sbc->id = tmp; + + tmp = inb(TS5500_SRAM_RS485_ADC_ADDR); + sbc->sram = tmp & TS5500_SRAM; + sbc->rs485 = tmp & TS5500_RS485; + sbc->adc = tmp & TS5500_ADC; + + tmp = inb(TS5500_ERESET_ITR_ADDR); + sbc->ereset = tmp & TS5500_ERESET; + sbc->itr = tmp & TS5500_ITR; + + tmp = inb(TS5500_LED_JP_ADDR); + sbc->jumpers = tmp & ~TS5500_LED; + +cleanup: + release_region(TS5500_PRODUCT_CODE_ADDR, 4); + return ret; +} + +static ssize_t ts5500_show_id(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ts5500_sbc *sbc = dev_get_drvdata(dev); + + return sprintf(buf, "0x%.2x\n", sbc->id); +} + +static ssize_t ts5500_show_jumpers(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct ts5500_sbc *sbc = dev_get_drvdata(dev); + + return sprintf(buf, "0x%.2x\n", sbc->jumpers >> 1); +} + +#define TS5500_SHOW(field) \ + static ssize_t ts5500_show_##field(struct device *dev, \ + struct device_attribute *attr, \ + char *buf) \ + { \ + struct ts5500_sbc *sbc = dev_get_drvdata(dev); \ + return sprintf(buf, "%d\n", sbc->field); \ + } + +TS5500_SHOW(sram) +TS5500_SHOW(rs485) +TS5500_SHOW(adc) +TS5500_SHOW(ereset) +TS5500_SHOW(itr) + +static DEVICE_ATTR(id, S_IRUGO, ts5500_show_id, NULL); +static DEVICE_ATTR(jumpers, S_IRUGO, ts5500_show_jumpers, NULL); +static DEVICE_ATTR(sram, S_IRUGO, ts5500_show_sram, NULL); +static DEVICE_ATTR(rs485, S_IRUGO, ts5500_show_rs485, NULL); +static DEVICE_ATTR(adc, S_IRUGO, ts5500_show_adc, NULL); +static DEVICE_ATTR(ereset, S_IRUGO, ts5500_show_ereset, NULL); +static DEVICE_ATTR(itr, S_IRUGO, ts5500_show_itr, NULL); + +static struct attribute *ts5500_attributes[] = { + &dev_attr_id.attr, + &dev_attr_jumpers.attr, + &dev_attr_sram.attr, + &dev_attr_rs485.attr, + &dev_attr_adc.attr, + &dev_attr_ereset.attr, + &dev_attr_itr.attr, + NULL +}; + +static const struct attribute_group ts5500_attr_group = { + .attrs = ts5500_attributes, +}; + +static struct resource ts5500_dio1_resource[] = { + DEFINE_RES_IRQ_NAMED(7, "DIO1 interrupt"), +}; + +static struct platform_device ts5500_dio1_pdev = { + .name = "ts5500-dio1", + .id = -1, + .resource = ts5500_dio1_resource, + .num_resources = 1, +}; + +static struct resource ts5500_dio2_resource[] = { + DEFINE_RES_IRQ_NAMED(6, "DIO2 interrupt"), +}; + +static struct platform_device ts5500_dio2_pdev = { + .name = "ts5500-dio2", + .id = -1, + .resource = ts5500_dio2_resource, + .num_resources = 1, +}; + +static void ts5500_led_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + outb(!!brightness, TS5500_LED_JP_ADDR); +} + +static enum led_brightness ts5500_led_get(struct led_classdev *led_cdev) +{ + return (inb(TS5500_LED_JP_ADDR) & TS5500_LED) ? LED_FULL : LED_OFF; +} + +static struct led_classdev ts5500_led_cdev = { + .name = "ts5500:green:", + .brightness_set = ts5500_led_set, + .brightness_get = ts5500_led_get, +}; + +static int ts5500_adc_convert(u8 ctrl) +{ + u8 lsb, msb; + + /* Start conversion (ensure the 3 MSB are set to 0) */ + outb(ctrl & 0x1f, TS5500_ADC_CONV_INIT_LSB_ADDR); + + /* + * The platform has CPLD logic driving the A/D converter. + * The conversion must complete within 11 microseconds, + * otherwise we have to re-initiate a conversion. + */ + udelay(TS5500_ADC_CONV_DELAY); + if (inb(TS5500_ADC_CONV_BUSY_ADDR) & TS5500_ADC_CONV_BUSY) + return -EBUSY; + + /* Read the raw data */ + lsb = inb(TS5500_ADC_CONV_INIT_LSB_ADDR); + msb = inb(TS5500_ADC_CONV_MSB_ADDR); + + return (msb << 8) | lsb; +} + +static struct max197_platform_data ts5500_adc_pdata = { + .convert = ts5500_adc_convert, +}; + +static struct platform_device ts5500_adc_pdev = { + .name = "max197", + .id = -1, + .dev = { + .platform_data = &ts5500_adc_pdata, + }, +}; + +static int __init ts5500_init(void) +{ + struct platform_device *pdev; + struct ts5500_sbc *sbc; + int err; + + /* + * There is no DMI available or PCI bridge subvendor info, + * only the BIOS provides a 16-bit identification call. + * It is safer to find a signature in the BIOS shadow RAM. + */ + err = ts5500_check_signature(); + if (err) + return err; + + pdev = platform_device_register_simple("ts5500", -1, NULL, 0); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + sbc = devm_kzalloc(&pdev->dev, sizeof(struct ts5500_sbc), GFP_KERNEL); + if (!sbc) { + err = -ENOMEM; + goto error; + } + + err = ts5500_detect_config(sbc); + if (err) + goto error; + + platform_set_drvdata(pdev, sbc); + + err = sysfs_create_group(&pdev->dev.kobj, &ts5500_attr_group); + if (err) + goto error; + + ts5500_dio1_pdev.dev.parent = &pdev->dev; + if (platform_device_register(&ts5500_dio1_pdev)) + dev_warn(&pdev->dev, "DIO1 block registration failed\n"); + ts5500_dio2_pdev.dev.parent = &pdev->dev; + if (platform_device_register(&ts5500_dio2_pdev)) + dev_warn(&pdev->dev, "DIO2 block registration failed\n"); + + if (led_classdev_register(&pdev->dev, &ts5500_led_cdev)) + dev_warn(&pdev->dev, "LED registration failed\n"); + + if (sbc->adc) { + ts5500_adc_pdev.dev.parent = &pdev->dev; + if (platform_device_register(&ts5500_adc_pdev)) + dev_warn(&pdev->dev, "ADC registration failed\n"); + } + + return 0; +error: + platform_device_unregister(pdev); + return err; +} +device_initcall(ts5500_init); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Savoir-faire Linux Inc. <kernel@savoirfairelinux.com>"); +MODULE_DESCRIPTION("Technologic Systems TS-5500 platform driver"); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index b8b3a37..0f92173 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1034,7 +1034,8 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, * globally purge translation cache of a virtual address or all TLB's * @cpumask: mask of all cpu's in which the address is to be removed * @mm: mm_struct containing virtual address range - * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu) + * @start: start virtual address to be removed from TLB + * @end: end virtual address to be remove from TLB * @cpu: the current cpu * * This is the entry point for initiating any UV global TLB shootdown. @@ -1056,7 +1057,7 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, */ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long start, - unsigned end, unsigned int cpu) + unsigned long end, unsigned int cpu) { int locals = 0; int remotes = 0; @@ -1113,7 +1114,10 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, record_send_statistics(stat, locals, hubs, remotes, bau_desc); - bau_desc->payload.address = start; + if (!end || (end - start) <= PAGE_SIZE) + bau_desc->payload.address = start; + else + bau_desc->payload.address = TLB_FLUSH_ALL; bau_desc->payload.sending_cpu = cpu; /* * uv_flush_send_and_wait returns 0 if all cpu's were messaged, @@ -1463,7 +1467,7 @@ static ssize_t ptc_proc_write(struct file *file, const char __user *user, } if (input_arg == 0) { - elements = sizeof(stat_description)/sizeof(*stat_description); + elements = ARRAY_SIZE(stat_description); printk(KERN_DEBUG "# cpu: cpu number\n"); printk(KERN_DEBUG "Sender statistics:\n"); for (i = 0; i < elements; i++) @@ -1504,7 +1508,7 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr, char *q; int cnt = 0; int val; - int e = sizeof(tunables) / sizeof(*tunables); + int e = ARRAY_SIZE(tunables); p = instr + strspn(instr, WHITESPACE); q = p; diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 5032e0d..98718f6 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -15,7 +15,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * - * Copyright (c) 2009 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2009-2013 Silicon Graphics, Inc. All Rights Reserved. * Copyright (c) Dimitri Sivanich */ #include <linux/clockchips.h> @@ -102,9 +102,10 @@ static int uv_intr_pending(int pnode) if (is_uv1_hub()) return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) & UV1H_EVENT_OCCURRED0_RTC1_MASK; - else - return uv_read_global_mmr64(pnode, UV2H_EVENT_OCCURRED2) & - UV2H_EVENT_OCCURRED2_RTC_1_MASK; + else if (is_uvx_hub()) + return uv_read_global_mmr64(pnode, UVXH_EVENT_OCCURRED2) & + UVXH_EVENT_OCCURRED2_RTC_1_MASK; + return 0; } /* Setup interrupt and return non-zero if early expiration occurred. */ @@ -122,8 +123,8 @@ static int uv_setup_intr(int cpu, u64 expires) uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, UV1H_EVENT_OCCURRED0_RTC1_MASK); else - uv_write_global_mmr64(pnode, UV2H_EVENT_OCCURRED2_ALIAS, - UV2H_EVENT_OCCURRED2_RTC_1_MASK); + uv_write_global_mmr64(pnode, UVXH_EVENT_OCCURRED2_ALIAS, + UVXH_EVENT_OCCURRED2_RTC_1_MASK); val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | ((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c index cc2f8c1..872eb60 100644 --- a/arch/x86/tools/insn_sanity.c +++ b/arch/x86/tools/insn_sanity.c @@ -55,7 +55,7 @@ static FILE *input_file; /* Input file name */ static void usage(const char *err) { if (err) - fprintf(stderr, "Error: %s\n\n", err); + fprintf(stderr, "%s: Error: %s\n\n", prog, err); fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog); fprintf(stderr, "\t-y 64bit mode\n"); fprintf(stderr, "\t-n 32bit mode\n"); @@ -269,7 +269,13 @@ int main(int argc, char **argv) insns++; } - fprintf(stdout, "%s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", (errors) ? "Failure" : "Success", insns, (input_file) ? "given" : "random", errors, seed); + fprintf(stdout, "%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", + prog, + (errors) ? "Failure" : "Success", + insns, + (input_file) ? "given" : "random", + errors, + seed); return errors ? 1 : 0; } diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 5a1847d..79d67bd 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -814,12 +814,14 @@ int main(int argc, char **argv) read_relocs(fp); if (show_absolute_syms) { print_absolute_symbols(); - return 0; + goto out; } if (show_absolute_relocs) { print_absolute_relocs(); - return 0; + goto out; } emit_relocs(as_text, use_real_mode); +out: + fclose(fp); return 0; } diff --git a/arch/x86/um/fault.c b/arch/x86/um/fault.c index 8784ab3..84ac7f7 100644 --- a/arch/x86/um/fault.c +++ b/arch/x86/um/fault.c @@ -20,7 +20,7 @@ int arch_fixup(unsigned long address, struct uml_pt_regs *regs) const struct exception_table_entry *fixup; fixup = search_exception_tables(address); - if (fixup != 0) { + if (fixup) { UPT_IP(regs) = fixup->fixup; return 1; } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 205ad32..c74436e 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -60,7 +60,7 @@ notrace static cycle_t vread_tsc(void) static notrace cycle_t vread_hpet(void) { - return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); + return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + HPET_COUNTER); } #ifdef CONFIG_PARAVIRT_CLOCK diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 138e566..39928d1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1517,72 +1517,51 @@ asmlinkage void __init xen_start_kernel(void) #endif } -#ifdef CONFIG_XEN_PVHVM -#define HVM_SHARED_INFO_ADDR 0xFE700000UL -static struct shared_info *xen_hvm_shared_info; -static unsigned long xen_hvm_sip_phys; -static int xen_major, xen_minor; - -static void xen_hvm_connect_shared_info(unsigned long pfn) +void __ref xen_hvm_init_shared_info(void) { + int cpu; struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = pfn; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); -} -static void __init xen_hvm_set_shared_info(struct shared_info *sip) -{ - int cpu; - - HYPERVISOR_shared_info = sip; + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info * page, we use it in the event channel upcall and in some pvclock * related functions. We don't need the vcpu_info placement * optimizations because we don't use any pv_mmu or pv_irq op on - * HVM. */ - for_each_online_cpu(cpu) + * HVM. + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and + * in that case multiple vcpus might be online. */ + for_each_online_cpu(cpu) { per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; -} - -/* Reconnect the shared_info pfn to a (new) mfn */ -void xen_hvm_resume_shared_info(void) -{ - xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT); -} - -/* Xen tools prior to Xen 4 do not provide a E820_Reserved area for guest usage. - * On these old tools the shared info page will be placed in E820_Ram. - * Xen 4 provides a E820_Reserved area at 0xFC000000, and this code expects - * that nothing is mapped up to HVM_SHARED_INFO_ADDR. - * Xen 4.3+ provides an explicit 1MB area at HVM_SHARED_INFO_ADDR which is used - * here for the shared info page. */ -static void __init xen_hvm_init_shared_info(void) -{ - if (xen_major < 4) { - xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); - xen_hvm_sip_phys = __pa(xen_hvm_shared_info); - } else { - xen_hvm_sip_phys = HVM_SHARED_INFO_ADDR; - set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_hvm_sip_phys); - xen_hvm_shared_info = - (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); } - xen_hvm_connect_shared_info(xen_hvm_sip_phys >> PAGE_SHIFT); - xen_hvm_set_shared_info(xen_hvm_shared_info); } +#ifdef CONFIG_XEN_PVHVM static void __init init_hvm_pv_info(void) { - uint32_t ecx, edx, pages, msr, base; + int major, minor; + uint32_t eax, ebx, ecx, edx, pages, msr, base; u64 pfn; base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + + major = eax >> 16; + minor = eax & 0xffff; + printk(KERN_INFO "Xen version %d.%d.\n", major, minor); + cpuid(base + 2, &pages, &msr, &ecx, &edx); pfn = __pa(hypercall_page); @@ -1633,22 +1612,12 @@ static void __init xen_hvm_guest_init(void) static bool __init xen_hvm_platform(void) { - uint32_t eax, ebx, ecx, edx, base; - if (xen_pv_domain()) return false; - base = xen_cpuid_base(); - if (!base) + if (!xen_cpuid_base()) return false; - cpuid(base + 1, &eax, &ebx, &ecx, &edx); - - xen_major = eax >> 16; - xen_minor = eax & 0xffff; - - printk(KERN_INFO "Xen version %d.%d.\n", xen_major, xen_minor); - return true; } @@ -1668,6 +1637,7 @@ const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = { .name = "Xen HVM", .detect = xen_hvm_platform, .init_platform = xen_hvm_guest_init, + .x2apic_available = xen_x2apic_para_available, }; EXPORT_SYMBOL(x86_hyper_xen_hvm); #endif diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index ae8a00c..45329c8 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_resume_shared_info(); + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index f9643fc..33ca6e4 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -89,11 +89,11 @@ ENTRY(xen_iret) */ #ifdef CONFIG_SMP GET_THREAD_INFO(%eax) - movl TI_cpu(%eax), %eax - movl __per_cpu_offset(,%eax,4), %eax - mov xen_vcpu(%eax), %eax + movl %ss:TI_cpu(%eax), %eax + movl %ss:__per_cpu_offset(,%eax,4), %eax + mov %ss:xen_vcpu(%eax), %eax #else - movl xen_vcpu, %eax + movl %ss:xen_vcpu, %eax #endif /* check IF state we're restoring */ @@ -106,11 +106,11 @@ ENTRY(xen_iret) * resuming the code, so we don't have to be worried about * being preempted to another CPU. */ - setz XEN_vcpu_info_mask(%eax) + setz %ss:XEN_vcpu_info_mask(%eax) xen_iret_start_crit: /* check for unmasked and pending */ - cmpw $0x0001, XEN_vcpu_info_pending(%eax) + cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax) /* * If there's something pending, mask events again so we can @@ -118,7 +118,7 @@ xen_iret_start_crit: * touch XEN_vcpu_info_mask. */ jne 1f - movb $1, XEN_vcpu_info_mask(%eax) + movb $1, %ss:XEN_vcpu_info_mask(%eax) 1: popl %eax diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index d2e73d1..a95b417 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -40,7 +40,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_resume_shared_info(void); +void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h index 4acb5fe..172a02a 100644 --- a/arch/xtensa/include/asm/dma-mapping.h +++ b/arch/xtensa/include/asm/dma-mapping.h @@ -170,4 +170,19 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, consistent_sync(vaddr, size, direction); } +/* Not supported for now */ +static inline int dma_mmap_coherent(struct device *dev, + struct vm_area_struct *vma, void *cpu_addr, + dma_addr_t dma_addr, size_t size) +{ + return -EINVAL; +} + +static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size) +{ + return -EINVAL; +} + #endif /* _XTENSA_DMA_MAPPING_H */ diff --git a/block/blk-exec.c b/block/blk-exec.c index 74638ec..c88202f 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/sched/sysctl.h> #include "blk.h" diff --git a/block/elevator.c b/block/elevator.c index 9edba1b..603b2c1 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -100,14 +100,14 @@ static void elevator_put(struct elevator_type *e) module_put(e->elevator_owner); } -static struct elevator_type *elevator_get(const char *name) +static struct elevator_type *elevator_get(const char *name, bool try_loading) { struct elevator_type *e; spin_lock(&elv_list_lock); e = elevator_find(name); - if (!e) { + if (!e && try_loading) { spin_unlock(&elv_list_lock); request_module("%s-iosched", name); spin_lock(&elv_list_lock); @@ -136,6 +136,22 @@ static int __init elevator_setup(char *str) __setup("elevator=", elevator_setup); +/* called during boot to load the elevator chosen by the elevator param */ +void __init load_default_elevator_module(void) +{ + struct elevator_type *e; + + if (!chosen_elevator[0]) + return; + + spin_lock(&elv_list_lock); + e = elevator_find(chosen_elevator); + spin_unlock(&elv_list_lock); + + if (!e) + request_module("%s-iosched", chosen_elevator); +} + static struct kobj_type elv_ktype; static struct elevator_queue *elevator_alloc(struct request_queue *q, @@ -191,25 +207,30 @@ int elevator_init(struct request_queue *q, char *name) q->boundary_rq = NULL; if (name) { - e = elevator_get(name); + e = elevator_get(name, true); if (!e) return -EINVAL; } + /* + * Use the default elevator specified by config boot param or + * config option. Don't try to load modules as we could be running + * off async and request_module() isn't allowed from async. + */ if (!e && *chosen_elevator) { - e = elevator_get(chosen_elevator); + e = elevator_get(chosen_elevator, false); if (!e) printk(KERN_ERR "I/O scheduler %s not found\n", chosen_elevator); } if (!e) { - e = elevator_get(CONFIG_DEFAULT_IOSCHED); + e = elevator_get(CONFIG_DEFAULT_IOSCHED, false); if (!e) { printk(KERN_ERR "Default I/O scheduler not found. " \ "Using noop.\n"); - e = elevator_get("noop"); + e = elevator_get("noop", false); } } @@ -951,7 +972,7 @@ int elevator_change(struct request_queue *q, const char *name) return -ENXIO; strlcpy(elevator_name, name, sizeof(elevator_name)); - e = elevator_get(strstrip(elevator_name)); + e = elevator_get(strstrip(elevator_name), true); if (!e) { printk(KERN_ERR "elevator: type %s not found\n", elevator_name); return -EINVAL; diff --git a/block/genhd.c b/block/genhd.c index 9a289d7..3993ebf 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -35,6 +35,8 @@ static DEFINE_IDR(ext_devt_idr); static struct device_type disk_type; +static void disk_check_events(struct disk_events *ev, + unsigned int *clearing_ptr); static void disk_alloc_events(struct gendisk *disk); static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); @@ -1549,6 +1551,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) const struct block_device_operations *bdops = disk->fops; struct disk_events *ev = disk->ev; unsigned int pending; + unsigned int clearing = mask; if (!ev) { /* for drivers still using the old ->media_changed method */ @@ -1558,34 +1561,53 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) return 0; } - /* tell the workfn about the events being cleared */ + disk_block_events(disk); + + /* + * store the union of mask and ev->clearing on the stack so that the + * race with disk_flush_events does not cause ambiguity (ev->clearing + * can still be modified even if events are blocked). + */ spin_lock_irq(&ev->lock); - ev->clearing |= mask; + clearing |= ev->clearing; + ev->clearing = 0; spin_unlock_irq(&ev->lock); - /* uncondtionally schedule event check and wait for it to finish */ - disk_block_events(disk); - queue_delayed_work(system_freezable_wq, &ev->dwork, 0); - flush_delayed_work(&ev->dwork); - __disk_unblock_events(disk, false); + disk_check_events(ev, &clearing); + /* + * if ev->clearing is not 0, the disk_flush_events got called in the + * middle of this function, so we want to run the workfn without delay. + */ + __disk_unblock_events(disk, ev->clearing ? true : false); /* then, fetch and clear pending events */ spin_lock_irq(&ev->lock); - WARN_ON_ONCE(ev->clearing & mask); /* cleared by workfn */ pending = ev->pending & mask; ev->pending &= ~mask; spin_unlock_irq(&ev->lock); + WARN_ON_ONCE(clearing & mask); return pending; } +/* + * Separate this part out so that a different pointer for clearing_ptr can be + * passed in for disk_clear_events. + */ static void disk_events_workfn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct disk_events *ev = container_of(dwork, struct disk_events, dwork); + + disk_check_events(ev, &ev->clearing); +} + +static void disk_check_events(struct disk_events *ev, + unsigned int *clearing_ptr) +{ struct gendisk *disk = ev->disk; char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; - unsigned int clearing = ev->clearing; + unsigned int clearing = *clearing_ptr; unsigned int events; unsigned long intv; int nr_events = 0, i; @@ -1598,7 +1620,7 @@ static void disk_events_workfn(struct work_struct *work) events &= ~ev->pending; ev->pending |= events; - ev->clearing &= ~clearing; + *clearing_ptr &= ~clearing; intv = disk_events_poll_jiffies(disk); if (!ev->block && intv) diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c index e6defd8..1e5d8a4 100644 --- a/drivers/acpi/apei/cper.c +++ b/drivers/acpi/apei/cper.c @@ -29,6 +29,7 @@ #include <linux/time.h> #include <linux/cper.h> #include <linux/acpi.h> +#include <linux/pci.h> #include <linux/aer.h> /* @@ -249,6 +250,10 @@ static const char *cper_pcie_port_type_strs[] = { static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, const struct acpi_hest_generic_data *gdata) { +#ifdef CONFIG_ACPI_APEI_PCIEAER + struct pci_dev *dev; +#endif + if (pcie->validation_bits & CPER_PCIE_VALID_PORT_TYPE) printk("%s""port_type: %d, %s\n", pfx, pcie->port_type, pcie->port_type < ARRAY_SIZE(cper_pcie_port_type_strs) ? @@ -281,10 +286,18 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, "%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n", pfx, pcie->bridge.secondary_status, pcie->bridge.control); #ifdef CONFIG_ACPI_APEI_PCIEAER - if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) { - struct aer_capability_regs *aer_regs = (void *)pcie->aer_info; - cper_print_aer(pfx, gdata->error_severity, aer_regs); + dev = pci_get_domain_bus_and_slot(pcie->device_id.segment, + pcie->device_id.bus, pcie->device_id.function); + if (!dev) { + pr_err("PCI AER Cannot get PCI device %04x:%02x:%02x.%d\n", + pcie->device_id.segment, pcie->device_id.bus, + pcie->device_id.slot, pcie->device_id.function); + return; } + if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) + cper_print_aer(pfx, dev, gdata->error_severity, + (struct aer_capability_regs *) pcie->aer_info); + pci_dev_put(dev); #endif } diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 3ff2678..bd22f86 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -250,7 +250,7 @@ acpi_physical_address __init acpi_os_get_root_pointer(void) return acpi_rsdp; #endif - if (efi_enabled) { + if (efi_enabled(EFI_CONFIG_TABLES)) { if (efi.acpi20 != EFI_INVALID_TABLE_ADDR) return efi.acpi20; else if (efi.acpi != EFI_INVALID_TABLE_ADDR) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 4979127..495aeed 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1061,6 +1061,86 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host) {} #endif +int ahci_init_interrupts(struct pci_dev *pdev, struct ahci_host_priv *hpriv) +{ + int rc; + unsigned int maxvec; + + if (!(hpriv->flags & AHCI_HFLAG_NO_MSI)) { + rc = pci_enable_msi_block_auto(pdev, &maxvec); + if (rc > 0) { + if ((rc == maxvec) || (rc == 1)) + return rc; + /* + * Assume that advantage of multipe MSIs is negated, + * so fallback to single MSI mode to save resources + */ + pci_disable_msi(pdev); + if (!pci_enable_msi(pdev)) + return 1; + } + } + + pci_intx(pdev, 1); + return 0; +} + +/** + * ahci_host_activate - start AHCI host, request IRQs and register it + * @host: target ATA host + * @irq: base IRQ number to request + * @n_msis: number of MSIs allocated for this host + * @irq_handler: irq_handler used when requesting IRQs + * @irq_flags: irq_flags used when requesting IRQs + * + * Similar to ata_host_activate, but requests IRQs according to AHCI-1.1 + * when multiple MSIs were allocated. That is one MSI per port, starting + * from @irq. + * + * LOCKING: + * Inherited from calling layer (may sleep). + * + * RETURNS: + * 0 on success, -errno otherwise. + */ +int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis) +{ + int i, rc; + + /* Sharing Last Message among several ports is not supported */ + if (n_msis < host->n_ports) + return -EINVAL; + + rc = ata_host_start(host); + if (rc) + return rc; + + for (i = 0; i < host->n_ports; i++) { + rc = devm_request_threaded_irq(host->dev, + irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED, + dev_driver_string(host->dev), host->ports[i]); + if (rc) + goto out_free_irqs; + } + + for (i = 0; i < host->n_ports; i++) + ata_port_desc(host->ports[i], "irq %d", irq + i); + + rc = ata_host_register(host, &ahci_sht); + if (rc) + goto out_free_all_irqs; + + return 0; + +out_free_all_irqs: + i = host->n_ports; +out_free_irqs: + for (i--; i >= 0; i--) + devm_free_irq(host->dev, irq + i, host->ports[i]); + + return rc; +} + static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned int board_id = ent->driver_data; @@ -1069,7 +1149,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) struct device *dev = &pdev->dev; struct ahci_host_priv *hpriv; struct ata_host *host; - int n_ports, i, rc; + int n_ports, n_msis, i, rc; int ahci_pci_bar = AHCI_PCI_BAR_STANDARD; VPRINTK("ENTER\n"); @@ -1156,11 +1236,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (ahci_sb600_enable_64bit(pdev)) hpriv->flags &= ~AHCI_HFLAG_32BIT_ONLY; - if ((hpriv->flags & AHCI_HFLAG_NO_MSI) || pci_enable_msi(pdev)) - pci_intx(pdev, 1); - hpriv->mmio = pcim_iomap_table(pdev)[ahci_pci_bar]; + n_msis = ahci_init_interrupts(pdev, hpriv); + if (n_msis > 1) + hpriv->flags |= AHCI_HFLAG_MULTI_MSI; + /* save initial config */ ahci_pci_save_initial_config(pdev, hpriv); @@ -1256,6 +1337,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) ahci_pci_print_info(host); pci_set_master(pdev); + + if (hpriv->flags & AHCI_HFLAG_MULTI_MSI) + return ahci_host_activate(host, pdev->irq, n_msis); + return ata_host_activate(host, pdev->irq, ahci_interrupt, IRQF_SHARED, &ahci_sht); } diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 9be4712..b830e6c 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -231,6 +231,7 @@ enum { AHCI_HFLAG_DELAY_ENGINE = (1 << 15), /* do not start engine on port start (wait until error-handling stage) */ + AHCI_HFLAG_MULTI_MSI = (1 << 16), /* multiple PCI MSIs */ /* ap->flags bits */ @@ -297,6 +298,8 @@ struct ahci_port_priv { unsigned int ncq_saw_d2h:1; unsigned int ncq_saw_dmas:1; unsigned int ncq_saw_sdb:1; + u32 intr_status; /* interrupts to handle */ + spinlock_t lock; /* protects parent ata_port */ u32 intr_mask; /* interrupts to enable */ bool fbs_supported; /* set iff FBS is supported */ bool fbs_enabled; /* set iff FBS is enabled */ @@ -359,7 +362,10 @@ void ahci_set_em_messages(struct ahci_host_priv *hpriv, struct ata_port_info *pi); int ahci_reset_em(struct ata_host *host); irqreturn_t ahci_interrupt(int irq, void *dev_instance); +irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance); +irqreturn_t ahci_thread_fn(int irq, void *dev_instance); void ahci_print_info(struct ata_host *host, const char *scc_s); +int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis); static inline void __iomem *__ahci_port_base(struct ata_host *host, unsigned int port_no) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 6cd7805..34c8216 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1655,19 +1655,16 @@ static void ahci_error_intr(struct ata_port *ap, u32 irq_stat) ata_port_abort(ap); } -static void ahci_port_intr(struct ata_port *ap) +static void ahci_handle_port_interrupt(struct ata_port *ap, + void __iomem *port_mmio, u32 status) { - void __iomem *port_mmio = ahci_port_base(ap); struct ata_eh_info *ehi = &ap->link.eh_info; struct ahci_port_priv *pp = ap->private_data; struct ahci_host_priv *hpriv = ap->host->private_data; int resetting = !!(ap->pflags & ATA_PFLAG_RESETTING); - u32 status, qc_active = 0; + u32 qc_active = 0; int rc; - status = readl(port_mmio + PORT_IRQ_STAT); - writel(status, port_mmio + PORT_IRQ_STAT); - /* ignore BAD_PMP while resetting */ if (unlikely(resetting)) status &= ~PORT_IRQ_BAD_PMP; @@ -1743,6 +1740,107 @@ static void ahci_port_intr(struct ata_port *ap) } } +void ahci_port_intr(struct ata_port *ap) +{ + void __iomem *port_mmio = ahci_port_base(ap); + u32 status; + + status = readl(port_mmio + PORT_IRQ_STAT); + writel(status, port_mmio + PORT_IRQ_STAT); + + ahci_handle_port_interrupt(ap, port_mmio, status); +} + +irqreturn_t ahci_thread_fn(int irq, void *dev_instance) +{ + struct ata_port *ap = dev_instance; + struct ahci_port_priv *pp = ap->private_data; + void __iomem *port_mmio = ahci_port_base(ap); + unsigned long flags; + u32 status; + + spin_lock_irqsave(&ap->host->lock, flags); + status = pp->intr_status; + if (status) + pp->intr_status = 0; + spin_unlock_irqrestore(&ap->host->lock, flags); + + spin_lock_bh(ap->lock); + ahci_handle_port_interrupt(ap, port_mmio, status); + spin_unlock_bh(ap->lock); + + return IRQ_HANDLED; +} +EXPORT_SYMBOL_GPL(ahci_thread_fn); + +void ahci_hw_port_interrupt(struct ata_port *ap) +{ + void __iomem *port_mmio = ahci_port_base(ap); + struct ahci_port_priv *pp = ap->private_data; + u32 status; + + status = readl(port_mmio + PORT_IRQ_STAT); + writel(status, port_mmio + PORT_IRQ_STAT); + + pp->intr_status |= status; +} + +irqreturn_t ahci_hw_interrupt(int irq, void *dev_instance) +{ + struct ata_port *ap_this = dev_instance; + struct ahci_port_priv *pp = ap_this->private_data; + struct ata_host *host = ap_this->host; + struct ahci_host_priv *hpriv = host->private_data; + void __iomem *mmio = hpriv->mmio; + unsigned int i; + u32 irq_stat, irq_masked; + + VPRINTK("ENTER\n"); + + spin_lock(&host->lock); + + irq_stat = readl(mmio + HOST_IRQ_STAT); + + if (!irq_stat) { + u32 status = pp->intr_status; + + spin_unlock(&host->lock); + + VPRINTK("EXIT\n"); + + return status ? IRQ_WAKE_THREAD : IRQ_NONE; + } + + irq_masked = irq_stat & hpriv->port_map; + + for (i = 0; i < host->n_ports; i++) { + struct ata_port *ap; + + if (!(irq_masked & (1 << i))) + continue; + + ap = host->ports[i]; + if (ap) { + ahci_hw_port_interrupt(ap); + VPRINTK("port %u\n", i); + } else { + VPRINTK("port %u (no irq)\n", i); + if (ata_ratelimit()) + dev_warn(host->dev, + "interrupt on disabled port %u\n", i); + } + } + + writel(irq_stat, mmio + HOST_IRQ_STAT); + + spin_unlock(&host->lock); + + VPRINTK("EXIT\n"); + + return IRQ_WAKE_THREAD; +} +EXPORT_SYMBOL_GPL(ahci_hw_interrupt); + irqreturn_t ahci_interrupt(int irq, void *dev_instance) { struct ata_host *host = dev_instance; @@ -2196,6 +2294,14 @@ static int ahci_port_start(struct ata_port *ap) */ pp->intr_mask = DEF_PORT_IRQ; + /* + * Switch to per-port locking in case each port has its own MSI vector. + */ + if ((hpriv->flags & AHCI_HFLAG_MULTI_MSI)) { + spin_lock_init(&pp->lock); + ap->lock = &pp->lock; + } + ap->private_data = pp; /* engage engines, captain */ diff --git a/drivers/atm/iphase.h b/drivers/atm/iphase.h index 6a0955e..53ecac5 100644 --- a/drivers/atm/iphase.h +++ b/drivers/atm/iphase.h @@ -636,82 +636,82 @@ struct rx_buf_desc { #define SEG_BASE IPHASE5575_FRAG_CONTROL_REG_BASE #define REASS_BASE IPHASE5575_REASS_CONTROL_REG_BASE -typedef volatile u_int freg_t; +typedef volatile u_int ffreg_t; typedef u_int rreg_t; typedef struct _ffredn_t { - freg_t idlehead_high; /* Idle cell header (high) */ - freg_t idlehead_low; /* Idle cell header (low) */ - freg_t maxrate; /* Maximum rate */ - freg_t stparms; /* Traffic Management Parameters */ - freg_t abrubr_abr; /* ABRUBR Priority Byte 1, TCR Byte 0 */ - freg_t rm_type; /* */ - u_int filler5[0x17 - 0x06]; - freg_t cmd_reg; /* Command register */ - u_int filler18[0x20 - 0x18]; - freg_t cbr_base; /* CBR Pointer Base */ - freg_t vbr_base; /* VBR Pointer Base */ - freg_t abr_base; /* ABR Pointer Base */ - freg_t ubr_base; /* UBR Pointer Base */ - u_int filler24; - freg_t vbrwq_base; /* VBR Wait Queue Base */ - freg_t abrwq_base; /* ABR Wait Queue Base */ - freg_t ubrwq_base; /* UBR Wait Queue Base */ - freg_t vct_base; /* Main VC Table Base */ - freg_t vcte_base; /* Extended Main VC Table Base */ - u_int filler2a[0x2C - 0x2A]; - freg_t cbr_tab_beg; /* CBR Table Begin */ - freg_t cbr_tab_end; /* CBR Table End */ - freg_t cbr_pointer; /* CBR Pointer */ - u_int filler2f[0x30 - 0x2F]; - freg_t prq_st_adr; /* Packet Ready Queue Start Address */ - freg_t prq_ed_adr; /* Packet Ready Queue End Address */ - freg_t prq_rd_ptr; /* Packet Ready Queue read pointer */ - freg_t prq_wr_ptr; /* Packet Ready Queue write pointer */ - freg_t tcq_st_adr; /* Transmit Complete Queue Start Address*/ - freg_t tcq_ed_adr; /* Transmit Complete Queue End Address */ - freg_t tcq_rd_ptr; /* Transmit Complete Queue read pointer */ - freg_t tcq_wr_ptr; /* Transmit Complete Queue write pointer*/ - u_int filler38[0x40 - 0x38]; - freg_t queue_base; /* Base address for PRQ and TCQ */ - freg_t desc_base; /* Base address of descriptor table */ - u_int filler42[0x45 - 0x42]; - freg_t mode_reg_0; /* Mode register 0 */ - freg_t mode_reg_1; /* Mode register 1 */ - freg_t intr_status_reg;/* Interrupt Status register */ - freg_t mask_reg; /* Mask Register */ - freg_t cell_ctr_high1; /* Total cell transfer count (high) */ - freg_t cell_ctr_lo1; /* Total cell transfer count (low) */ - freg_t state_reg; /* Status register */ - u_int filler4c[0x58 - 0x4c]; - freg_t curr_desc_num; /* Contains the current descriptor num */ - freg_t next_desc; /* Next descriptor */ - freg_t next_vc; /* Next VC */ - u_int filler5b[0x5d - 0x5b]; - freg_t present_slot_cnt;/* Present slot count */ - u_int filler5e[0x6a - 0x5e]; - freg_t new_desc_num; /* New descriptor number */ - freg_t new_vc; /* New VC */ - freg_t sched_tbl_ptr; /* Schedule table pointer */ - freg_t vbrwq_wptr; /* VBR wait queue write pointer */ - freg_t vbrwq_rptr; /* VBR wait queue read pointer */ - freg_t abrwq_wptr; /* ABR wait queue write pointer */ - freg_t abrwq_rptr; /* ABR wait queue read pointer */ - freg_t ubrwq_wptr; /* UBR wait queue write pointer */ - freg_t ubrwq_rptr; /* UBR wait queue read pointer */ - freg_t cbr_vc; /* CBR VC */ - freg_t vbr_sb_vc; /* VBR SB VC */ - freg_t abr_sb_vc; /* ABR SB VC */ - freg_t ubr_sb_vc; /* UBR SB VC */ - freg_t vbr_next_link; /* VBR next link */ - freg_t abr_next_link; /* ABR next link */ - freg_t ubr_next_link; /* UBR next link */ - u_int filler7a[0x7c-0x7a]; - freg_t out_rate_head; /* Out of rate head */ - u_int filler7d[0xca-0x7d]; /* pad out to full address space */ - freg_t cell_ctr_high1_nc;/* Total cell transfer count (high) */ - freg_t cell_ctr_lo1_nc;/* Total cell transfer count (low) */ - u_int fillercc[0x100-0xcc]; /* pad out to full address space */ + ffreg_t idlehead_high; /* Idle cell header (high) */ + ffreg_t idlehead_low; /* Idle cell header (low) */ + ffreg_t maxrate; /* Maximum rate */ + ffreg_t stparms; /* Traffic Management Parameters */ + ffreg_t abrubr_abr; /* ABRUBR Priority Byte 1, TCR Byte 0 */ + ffreg_t rm_type; /* */ + u_int filler5[0x17 - 0x06]; + ffreg_t cmd_reg; /* Command register */ + u_int filler18[0x20 - 0x18]; + ffreg_t cbr_base; /* CBR Pointer Base */ + ffreg_t vbr_base; /* VBR Pointer Base */ + ffreg_t abr_base; /* ABR Pointer Base */ + ffreg_t ubr_base; /* UBR Pointer Base */ + u_int filler24; + ffreg_t vbrwq_base; /* VBR Wait Queue Base */ + ffreg_t abrwq_base; /* ABR Wait Queue Base */ + ffreg_t ubrwq_base; /* UBR Wait Queue Base */ + ffreg_t vct_base; /* Main VC Table Base */ + ffreg_t vcte_base; /* Extended Main VC Table Base */ + u_int filler2a[0x2C - 0x2A]; + ffreg_t cbr_tab_beg; /* CBR Table Begin */ + ffreg_t cbr_tab_end; /* CBR Table End */ + ffreg_t cbr_pointer; /* CBR Pointer */ + u_int filler2f[0x30 - 0x2F]; + ffreg_t prq_st_adr; /* Packet Ready Queue Start Address */ + ffreg_t prq_ed_adr; /* Packet Ready Queue End Address */ + ffreg_t prq_rd_ptr; /* Packet Ready Queue read pointer */ + ffreg_t prq_wr_ptr; /* Packet Ready Queue write pointer */ + ffreg_t tcq_st_adr; /* Transmit Complete Queue Start Address*/ + ffreg_t tcq_ed_adr; /* Transmit Complete Queue End Address */ + ffreg_t tcq_rd_ptr; /* Transmit Complete Queue read pointer */ + ffreg_t tcq_wr_ptr; /* Transmit Complete Queue write pointer*/ + u_int filler38[0x40 - 0x38]; + ffreg_t queue_base; /* Base address for PRQ and TCQ */ + ffreg_t desc_base; /* Base address of descriptor table */ + u_int filler42[0x45 - 0x42]; + ffreg_t mode_reg_0; /* Mode register 0 */ + ffreg_t mode_reg_1; /* Mode register 1 */ + ffreg_t intr_status_reg;/* Interrupt Status register */ + ffreg_t mask_reg; /* Mask Register */ + ffreg_t cell_ctr_high1; /* Total cell transfer count (high) */ + ffreg_t cell_ctr_lo1; /* Total cell transfer count (low) */ + ffreg_t state_reg; /* Status register */ + u_int filler4c[0x58 - 0x4c]; + ffreg_t curr_desc_num; /* Contains the current descriptor num */ + ffreg_t next_desc; /* Next descriptor */ + ffreg_t next_vc; /* Next VC */ + u_int filler5b[0x5d - 0x5b]; + ffreg_t present_slot_cnt;/* Present slot count */ + u_int filler5e[0x6a - 0x5e]; + ffreg_t new_desc_num; /* New descriptor number */ + ffreg_t new_vc; /* New VC */ + ffreg_t sched_tbl_ptr; /* Schedule table pointer */ + ffreg_t vbrwq_wptr; /* VBR wait queue write pointer */ + ffreg_t vbrwq_rptr; /* VBR wait queue read pointer */ + ffreg_t abrwq_wptr; /* ABR wait queue write pointer */ + ffreg_t abrwq_rptr; /* ABR wait queue read pointer */ + ffreg_t ubrwq_wptr; /* UBR wait queue write pointer */ + ffreg_t ubrwq_rptr; /* UBR wait queue read pointer */ + ffreg_t cbr_vc; /* CBR VC */ + ffreg_t vbr_sb_vc; /* VBR SB VC */ + ffreg_t abr_sb_vc; /* ABR SB VC */ + ffreg_t ubr_sb_vc; /* UBR SB VC */ + ffreg_t vbr_next_link; /* VBR next link */ + ffreg_t abr_next_link; /* ABR next link */ + ffreg_t ubr_next_link; /* UBR next link */ + u_int filler7a[0x7c-0x7a]; + ffreg_t out_rate_head; /* Out of rate head */ + u_int filler7d[0xca-0x7d]; /* pad out to full address space */ + ffreg_t cell_ctr_high1_nc;/* Total cell transfer count (high) */ + ffreg_t cell_ctr_lo1_nc;/* Total cell transfer count (low) */ + u_int fillercc[0x100-0xcc]; /* pad out to full address space */ } ffredn_t; typedef struct _rfredn_t { diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 5aa2d70..4e22ce3 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -21,6 +21,7 @@ endif obj-$(CONFIG_SYS_HYPERVISOR) += hypervisor.o obj-$(CONFIG_REGMAP) += regmap/ obj-$(CONFIG_SOC_BUS) += soc.o +obj-$(CONFIG_PINCTRL) += pinctrl.o ccflags-$(CONFIG_DEBUG_DRIVER) := -DDEBUG diff --git a/drivers/base/dd.c b/drivers/base/dd.c index e3bbed8..65631015 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -24,6 +24,7 @@ #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> +#include <linux/pinctrl/devinfo.h> #include "base.h" #include "power/power.h" @@ -269,6 +270,12 @@ static int really_probe(struct device *dev, struct device_driver *drv) WARN_ON(!list_empty(&dev->devres_head)); dev->driver = drv; + + /* If using pinctrl, bind pins now before probing */ + ret = pinctrl_bind_pins(dev); + if (ret) + goto probe_failed; + if (driver_sysfs_add(dev)) { printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n", __func__, dev_name(dev)); diff --git a/drivers/base/pinctrl.c b/drivers/base/pinctrl.c new file mode 100644 index 0000000..67a274e --- /dev/null +++ b/drivers/base/pinctrl.c @@ -0,0 +1,69 @@ +/* + * Driver core interface to the pinctrl subsystem. + * + * Copyright (C) 2012 ST-Ericsson SA + * Written on behalf of Linaro for ST-Ericsson + * Based on bits of regulator core, gpio core and clk core + * + * Author: Linus Walleij <linus.walleij@linaro.org> + * + * License terms: GNU General Public License (GPL) version 2 + */ + +#include <linux/device.h> +#include <linux/pinctrl/devinfo.h> +#include <linux/pinctrl/consumer.h> +#include <linux/slab.h> + +/** + * pinctrl_bind_pins() - called by the device core before probe + * @dev: the device that is just about to probe + */ +int pinctrl_bind_pins(struct device *dev) +{ + int ret; + + dev->pins = devm_kzalloc(dev, sizeof(*(dev->pins)), GFP_KERNEL); + if (!dev->pins) + return -ENOMEM; + + dev->pins->p = devm_pinctrl_get(dev); + if (IS_ERR(dev->pins->p)) { + dev_dbg(dev, "no pinctrl handle\n"); + ret = PTR_ERR(dev->pins->p); + goto cleanup_alloc; + } + + dev->pins->default_state = pinctrl_lookup_state(dev->pins->p, + PINCTRL_STATE_DEFAULT); + if (IS_ERR(dev->pins->default_state)) { + dev_dbg(dev, "no default pinctrl state\n"); + ret = 0; + goto cleanup_get; + } + + ret = pinctrl_select_state(dev->pins->p, dev->pins->default_state); + if (ret) { + dev_dbg(dev, "failed to activate default pinctrl state\n"); + goto cleanup_get; + } + + return 0; + + /* + * If no pinctrl handle or default state was found for this device, + * let's explicitly free the pin container in the device, there is + * no point in keeping it around. + */ +cleanup_get: + devm_pinctrl_put(dev->pins->p); +cleanup_alloc: + devm_kfree(dev, dev->pins); + dev->pins = NULL; + + /* Only return deferrals */ + if (ret != -EPROBE_DEFER) + ret = 0; + + return ret; +} diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile index 5e75d1b..cf12998 100644 --- a/drivers/base/regmap/Makefile +++ b/drivers/base/regmap/Makefile @@ -1,5 +1,5 @@ obj-$(CONFIG_REGMAP) += regmap.o regcache.o -obj-$(CONFIG_REGMAP) += regcache-rbtree.o regcache-lzo.o +obj-$(CONFIG_REGMAP) += regcache-rbtree.o regcache-lzo.o regcache-flat.o obj-$(CONFIG_DEBUG_FS) += regmap-debugfs.o obj-$(CONFIG_REGMAP_I2C) += regmap-i2c.o obj-$(CONFIG_REGMAP_SPI) += regmap-spi.o diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 401d191..5a22bd3 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -16,6 +16,7 @@ #include <linux/regmap.h> #include <linux/fs.h> #include <linux/list.h> +#include <linux/wait.h> struct regmap; struct regcache_ops; @@ -25,6 +26,7 @@ struct regmap_debugfs_off_cache { off_t min; off_t max; unsigned int base_reg; + unsigned int max_reg; }; struct regmap_format { @@ -39,6 +41,13 @@ struct regmap_format { unsigned int (*parse_val)(void *buf); }; +struct regmap_async { + struct list_head list; + struct work_struct cleanup; + struct regmap *map; + void *work_buf; +}; + struct regmap { struct mutex mutex; spinlock_t spinlock; @@ -53,6 +62,11 @@ struct regmap { void *bus_context; const char *name; + spinlock_t async_lock; + wait_queue_head_t async_waitq; + struct list_head async_list; + int async_ret; + #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; const char *debugfs_name; @@ -74,6 +88,11 @@ struct regmap { const struct regmap_access_table *volatile_table; const struct regmap_access_table *precious_table; + int (*reg_read)(void *context, unsigned int reg, unsigned int *val); + int (*reg_write)(void *context, unsigned int reg, unsigned int val); + + bool defer_caching; + u8 read_flag_mask; u8 write_flag_mask; @@ -175,7 +194,10 @@ bool regcache_set_val(void *base, unsigned int idx, unsigned int val, unsigned int word_size); int regcache_lookup_reg(struct regmap *map, unsigned int reg); +void regmap_async_complete_cb(struct regmap_async *async, int ret); + extern struct regcache_ops regcache_rbtree_ops; extern struct regcache_ops regcache_lzo_ops; +extern struct regcache_ops regcache_flat_ops; #endif diff --git a/drivers/base/regmap/regcache-flat.c b/drivers/base/regmap/regcache-flat.c new file mode 100644 index 0000000..d9762e4 --- /dev/null +++ b/drivers/base/regmap/regcache-flat.c @@ -0,0 +1,72 @@ +/* + * Register cache access API - flat caching support + * + * Copyright 2012 Wolfson Microelectronics plc + * + * Author: Mark Brown <broonie@opensource.wolfsonmicro.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/seq_file.h> + +#include "internal.h" + +static int regcache_flat_init(struct regmap *map) +{ + int i; + unsigned int *cache; + + map->cache = kzalloc(sizeof(unsigned int) * (map->max_register + 1), + GFP_KERNEL); + if (!map->cache) + return -ENOMEM; + + cache = map->cache; + + for (i = 0; i < map->num_reg_defaults; i++) + cache[map->reg_defaults[i].reg] = map->reg_defaults[i].def; + + return 0; +} + +static int regcache_flat_exit(struct regmap *map) +{ + kfree(map->cache); + map->cache = NULL; + + return 0; +} + +static int regcache_flat_read(struct regmap *map, + unsigned int reg, unsigned int *value) +{ + unsigned int *cache = map->cache; + + *value = cache[reg]; + + return 0; +} + +static int regcache_flat_write(struct regmap *map, unsigned int reg, + unsigned int value) +{ + unsigned int *cache = map->cache; + + cache[reg] = value; + + return 0; +} + +struct regcache_ops regcache_flat_ops = { + .type = REGCACHE_FLAT, + .name = "flat", + .init = regcache_flat_init, + .exit = regcache_flat_exit, + .read = regcache_flat_read, + .write = regcache_flat_write, +}; diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index 835883b..e69ff3e 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -22,6 +22,7 @@ static const struct regcache_ops *cache_types[] = { ®cache_rbtree_ops, ®cache_lzo_ops, + ®cache_flat_ops, }; static int regcache_hw_init(struct regmap *map) diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index d9a6c94..78d5f20 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -81,6 +81,8 @@ static unsigned int regmap_debugfs_get_dump_start(struct regmap *map, struct regmap_debugfs_off_cache *c = NULL; loff_t p = 0; unsigned int i, ret; + unsigned int fpos_offset; + unsigned int reg_offset; /* * If we don't have a cache build one so we don't have to do a @@ -93,6 +95,9 @@ static unsigned int regmap_debugfs_get_dump_start(struct regmap *map, regmap_precious(map, i)) { if (c) { c->max = p - 1; + fpos_offset = c->max - c->min; + reg_offset = fpos_offset / map->debugfs_tot_len; + c->max_reg = c->base_reg + reg_offset; list_add_tail(&c->list, &map->debugfs_off_cache); c = NULL; @@ -119,6 +124,9 @@ static unsigned int regmap_debugfs_get_dump_start(struct regmap *map, /* Close the last entry off if we didn't scan beyond it */ if (c) { c->max = p - 1; + fpos_offset = c->max - c->min; + reg_offset = fpos_offset / map->debugfs_tot_len; + c->max_reg = c->base_reg + reg_offset; list_add_tail(&c->list, &map->debugfs_off_cache); } @@ -128,25 +136,38 @@ static unsigned int regmap_debugfs_get_dump_start(struct regmap *map, * allocate and we should never be in this code if there are * no registers at all. */ - if (list_empty(&map->debugfs_off_cache)) { - WARN_ON(list_empty(&map->debugfs_off_cache)); - return base; - } + WARN_ON(list_empty(&map->debugfs_off_cache)); + ret = base; - /* Find the relevant block */ + /* Find the relevant block:offset */ list_for_each_entry(c, &map->debugfs_off_cache, list) { if (from >= c->min && from <= c->max) { - *pos = c->min; - return c->base_reg; + fpos_offset = from - c->min; + reg_offset = fpos_offset / map->debugfs_tot_len; + *pos = c->min + (reg_offset * map->debugfs_tot_len); + return c->base_reg + reg_offset; } - *pos = c->min; - ret = c->base_reg; + *pos = c->max; + ret = c->max_reg; } return ret; } +static inline void regmap_calc_tot_len(struct regmap *map, + void *buf, size_t count) +{ + /* Calculate the length of a fixed format */ + if (!map->debugfs_tot_len) { + map->debugfs_reg_len = regmap_calc_reg_len(map->max_register, + buf, count); + map->debugfs_val_len = 2 * map->format.val_bytes; + map->debugfs_tot_len = map->debugfs_reg_len + + map->debugfs_val_len + 3; /* : \n */ + } +} + static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from, unsigned int to, char __user *user_buf, size_t count, loff_t *ppos) @@ -165,14 +186,7 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from, if (!buf) return -ENOMEM; - /* Calculate the length of a fixed format */ - if (!map->debugfs_tot_len) { - map->debugfs_reg_len = regmap_calc_reg_len(map->max_register, - buf, count); - map->debugfs_val_len = 2 * map->format.val_bytes; - map->debugfs_tot_len = map->debugfs_reg_len + - map->debugfs_val_len + 3; /* : \n */ - } + regmap_calc_tot_len(map, buf, count); /* Work out which register we're starting at */ start_reg = regmap_debugfs_get_dump_start(map, from, *ppos, &p); @@ -187,7 +201,7 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from, /* If we're in the region the user is trying to read */ if (p >= *ppos) { /* ...but not beyond it */ - if (buf_pos + 1 + map->debugfs_tot_len >= count) + if (buf_pos + map->debugfs_tot_len > count) break; /* Format the register */ diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 5972ad9..4706c63 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -34,6 +34,7 @@ struct regmap_irq_chip_data { int irq; int wake_count; + void *status_reg_buf; unsigned int *status_buf; unsigned int *mask_buf; unsigned int *mask_buf_def; @@ -87,6 +88,23 @@ static void regmap_irq_sync_unlock(struct irq_data *data) if (ret != 0) dev_err(d->map->dev, "Failed to sync masks in %x\n", reg); + + reg = d->chip->wake_base + + (i * map->reg_stride * d->irq_reg_stride); + if (d->wake_buf) { + if (d->chip->wake_invert) + ret = regmap_update_bits(d->map, reg, + d->mask_buf_def[i], + ~d->wake_buf[i]); + else + ret = regmap_update_bits(d->map, reg, + d->mask_buf_def[i], + d->wake_buf[i]); + if (ret != 0) + dev_err(d->map->dev, + "Failed to sync wakes in %x: %d\n", + reg, ret); + } } if (d->chip->runtime_pm) @@ -129,16 +147,15 @@ static int regmap_irq_set_wake(struct irq_data *data, unsigned int on) struct regmap *map = d->map; const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq); - if (!d->chip->wake_base) - return -EINVAL; - if (on) { - d->wake_buf[irq_data->reg_offset / map->reg_stride] - &= ~irq_data->mask; + if (d->wake_buf) + d->wake_buf[irq_data->reg_offset / map->reg_stride] + &= ~irq_data->mask; d->wake_count++; } else { - d->wake_buf[irq_data->reg_offset / map->reg_stride] - |= irq_data->mask; + if (d->wake_buf) + d->wake_buf[irq_data->reg_offset / map->reg_stride] + |= irq_data->mask; d->wake_count--; } @@ -172,25 +189,69 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) } /* - * Ignore masked IRQs and ack if we need to; we ack early so - * there is no race between handling and acknowleding the - * interrupt. We assume that typically few of the interrupts - * will fire simultaneously so don't worry about overhead from - * doing a write per register. + * Read in the statuses, using a single bulk read if possible + * in order to reduce the I/O overheads. */ - for (i = 0; i < data->chip->num_regs; i++) { - ret = regmap_read(map, chip->status_base + (i * map->reg_stride - * data->irq_reg_stride), - &data->status_buf[i]); + if (!map->use_single_rw && map->reg_stride == 1 && + data->irq_reg_stride == 1) { + u8 *buf8 = data->status_reg_buf; + u16 *buf16 = data->status_reg_buf; + u32 *buf32 = data->status_reg_buf; + BUG_ON(!data->status_reg_buf); + + ret = regmap_bulk_read(map, chip->status_base, + data->status_reg_buf, + chip->num_regs); if (ret != 0) { dev_err(map->dev, "Failed to read IRQ status: %d\n", - ret); - if (chip->runtime_pm) - pm_runtime_put(map->dev); + ret); return IRQ_NONE; } + for (i = 0; i < data->chip->num_regs; i++) { + switch (map->format.val_bytes) { + case 1: + data->status_buf[i] = buf8[i]; + break; + case 2: + data->status_buf[i] = buf16[i]; + break; + case 4: + data->status_buf[i] = buf32[i]; + break; + default: + BUG(); + return IRQ_NONE; + } + } + + } else { + for (i = 0; i < data->chip->num_regs; i++) { + ret = regmap_read(map, chip->status_base + + (i * map->reg_stride + * data->irq_reg_stride), + &data->status_buf[i]); + + if (ret != 0) { + dev_err(map->dev, + "Failed to read IRQ status: %d\n", + ret); + if (chip->runtime_pm) + pm_runtime_put(map->dev); + return IRQ_NONE; + } + } + } + + /* + * Ignore masked IRQs and ack if we need to; we ack early so + * there is no race between handling and acknowleding the + * interrupt. We assume that typically few of the interrupts + * will fire simultaneously so don't worry about overhead from + * doing a write per register. + */ + for (i = 0; i < data->chip->num_regs; i++) { data->status_buf[i] &= ~data->mask_buf[i]; if (data->status_buf[i] && chip->ack_base) { @@ -316,11 +377,6 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, d->irq_chip = regmap_irq_chip; d->irq_chip.name = chip->name; - if (!chip->wake_base) { - d->irq_chip.irq_set_wake = NULL; - d->irq_chip.flags |= IRQCHIP_MASK_ON_SUSPEND | - IRQCHIP_SKIP_SET_WAKE; - } d->irq = irq; d->map = map; d->chip = chip; @@ -331,6 +387,14 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, else d->irq_reg_stride = 1; + if (!map->use_single_rw && map->reg_stride == 1 && + d->irq_reg_stride == 1) { + d->status_reg_buf = kmalloc(map->format.val_bytes * + chip->num_regs, GFP_KERNEL); + if (!d->status_reg_buf) + goto err_alloc; + } + mutex_init(&d->lock); for (i = 0; i < chip->num_irqs; i++) @@ -361,8 +425,15 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, d->wake_buf[i] = d->mask_buf_def[i]; reg = chip->wake_base + (i * map->reg_stride * d->irq_reg_stride); - ret = regmap_update_bits(map, reg, d->wake_buf[i], - d->wake_buf[i]); + + if (chip->wake_invert) + ret = regmap_update_bits(map, reg, + d->mask_buf_def[i], + 0); + else + ret = regmap_update_bits(map, reg, + d->mask_buf_def[i], + d->wake_buf[i]); if (ret != 0) { dev_err(map->dev, "Failed to set masks in 0x%x: %d\n", reg, ret); @@ -401,6 +472,7 @@ err_alloc: kfree(d->mask_buf_def); kfree(d->mask_buf); kfree(d->status_buf); + kfree(d->status_reg_buf); kfree(d); return ret; } @@ -422,6 +494,7 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d) kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); + kfree(d->status_reg_buf); kfree(d->status_buf); kfree(d); } diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c index f05fc74..98745dd 100644 --- a/drivers/base/regmap/regmap-mmio.c +++ b/drivers/base/regmap/regmap-mmio.c @@ -16,6 +16,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/clk.h> #include <linux/err.h> #include <linux/init.h> #include <linux/io.h> @@ -26,6 +27,7 @@ struct regmap_mmio_context { void __iomem *regs; unsigned val_bytes; + struct clk *clk; }; static int regmap_mmio_gather_write(void *context, @@ -34,9 +36,16 @@ static int regmap_mmio_gather_write(void *context, { struct regmap_mmio_context *ctx = context; u32 offset; + int ret; BUG_ON(reg_size != 4); + if (ctx->clk) { + ret = clk_enable(ctx->clk); + if (ret < 0) + return ret; + } + offset = *(u32 *)reg; while (val_size) { @@ -64,6 +73,9 @@ static int regmap_mmio_gather_write(void *context, offset += ctx->val_bytes; } + if (ctx->clk) + clk_disable(ctx->clk); + return 0; } @@ -80,9 +92,16 @@ static int regmap_mmio_read(void *context, { struct regmap_mmio_context *ctx = context; u32 offset; + int ret; BUG_ON(reg_size != 4); + if (ctx->clk) { + ret = clk_enable(ctx->clk); + if (ret < 0) + return ret; + } + offset = *(u32 *)reg; while (val_size) { @@ -110,11 +129,20 @@ static int regmap_mmio_read(void *context, offset += ctx->val_bytes; } + if (ctx->clk) + clk_disable(ctx->clk); + return 0; } static void regmap_mmio_free_context(void *context) { + struct regmap_mmio_context *ctx = context; + + if (ctx->clk) { + clk_unprepare(ctx->clk); + clk_put(ctx->clk); + } kfree(context); } @@ -128,11 +156,14 @@ static struct regmap_bus regmap_mmio = { .val_format_endian_default = REGMAP_ENDIAN_NATIVE, }; -static struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, +static struct regmap_mmio_context *regmap_mmio_gen_context(struct device *dev, + const char *clk_id, + void __iomem *regs, const struct regmap_config *config) { struct regmap_mmio_context *ctx; int min_stride; + int ret; if (config->reg_bits != 32) return ERR_PTR(-EINVAL); @@ -179,37 +210,59 @@ static struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, ctx->regs = regs; ctx->val_bytes = config->val_bits / 8; + if (clk_id == NULL) + return ctx; + + ctx->clk = clk_get(dev, clk_id); + if (IS_ERR(ctx->clk)) { + ret = PTR_ERR(ctx->clk); + goto err_free; + } + + ret = clk_prepare(ctx->clk); + if (ret < 0) { + clk_put(ctx->clk); + goto err_free; + } + return ctx; + +err_free: + kfree(ctx); + + return ERR_PTR(ret); } /** - * regmap_init_mmio(): Initialise register map + * regmap_init_mmio_clk(): Initialise register map with register clock * * @dev: Device that will be interacted with + * @clk_id: register clock consumer ID * @regs: Pointer to memory-mapped IO region * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer to * a struct regmap. */ -struct regmap *regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config) +struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id, + void __iomem *regs, + const struct regmap_config *config) { struct regmap_mmio_context *ctx; - ctx = regmap_mmio_gen_context(regs, config); + ctx = regmap_mmio_gen_context(dev, clk_id, regs, config); if (IS_ERR(ctx)) return ERR_CAST(ctx); return regmap_init(dev, ®map_mmio, ctx, config); } -EXPORT_SYMBOL_GPL(regmap_init_mmio); +EXPORT_SYMBOL_GPL(regmap_init_mmio_clk); /** - * devm_regmap_init_mmio(): Initialise managed register map + * devm_regmap_init_mmio_clk(): Initialise managed register map with clock * * @dev: Device that will be interacted with + * @clk_id: register clock consumer ID * @regs: Pointer to memory-mapped IO region * @config: Configuration for register map * @@ -217,18 +270,18 @@ EXPORT_SYMBOL_GPL(regmap_init_mmio); * to a struct regmap. The regmap will be automatically freed by the * device management code. */ -struct regmap *devm_regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config) +struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id, + void __iomem *regs, + const struct regmap_config *config) { struct regmap_mmio_context *ctx; - ctx = regmap_mmio_gen_context(regs, config); + ctx = regmap_mmio_gen_context(dev, clk_id, regs, config); if (IS_ERR(ctx)) return ERR_CAST(ctx); return devm_regmap_init(dev, ®map_mmio, ctx, config); } -EXPORT_SYMBOL_GPL(devm_regmap_init_mmio); +EXPORT_SYMBOL_GPL(devm_regmap_init_mmio_clk); MODULE_LICENSE("GPL v2"); diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c index ffa46a9..4c506bd 100644 --- a/drivers/base/regmap/regmap-spi.c +++ b/drivers/base/regmap/regmap-spi.c @@ -15,6 +15,21 @@ #include <linux/init.h> #include <linux/module.h> +#include "internal.h" + +struct regmap_async_spi { + struct regmap_async core; + struct spi_message m; + struct spi_transfer t[2]; +}; + +static void regmap_spi_complete(void *data) +{ + struct regmap_async_spi *async = data; + + regmap_async_complete_cb(&async->core, async->m.status); +} + static int regmap_spi_write(void *context, const void *data, size_t count) { struct device *dev = context; @@ -40,6 +55,43 @@ static int regmap_spi_gather_write(void *context, return spi_sync(spi, &m); } +static int regmap_spi_async_write(void *context, + const void *reg, size_t reg_len, + const void *val, size_t val_len, + struct regmap_async *a) +{ + struct regmap_async_spi *async = container_of(a, + struct regmap_async_spi, + core); + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + + async->t[0].tx_buf = reg; + async->t[0].len = reg_len; + async->t[1].tx_buf = val; + async->t[1].len = val_len; + + spi_message_init(&async->m); + spi_message_add_tail(&async->t[0], &async->m); + spi_message_add_tail(&async->t[1], &async->m); + + async->m.complete = regmap_spi_complete; + async->m.context = async; + + return spi_async(spi, &async->m); +} + +static struct regmap_async *regmap_spi_async_alloc(void) +{ + struct regmap_async_spi *async_spi; + + async_spi = kzalloc(sizeof(*async_spi), GFP_KERNEL); + if (!async_spi) + return NULL; + + return &async_spi->core; +} + static int regmap_spi_read(void *context, const void *reg, size_t reg_size, void *val, size_t val_size) @@ -53,6 +105,8 @@ static int regmap_spi_read(void *context, static struct regmap_bus regmap_spi = { .write = regmap_spi_write, .gather_write = regmap_spi_gather_write, + .async_write = regmap_spi_async_write, + .async_alloc = regmap_spi_async_alloc, .read = regmap_spi_read, .read_flag_mask = 0x80, }; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index f00b059..3d23675 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -16,6 +16,7 @@ #include <linux/mutex.h> #include <linux/err.h> #include <linux/rbtree.h> +#include <linux/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/regmap.h> @@ -34,6 +35,22 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change); +static int _regmap_bus_read(void *context, unsigned int reg, + unsigned int *val); +static int _regmap_bus_formatted_write(void *context, unsigned int reg, + unsigned int val); +static int _regmap_bus_raw_write(void *context, unsigned int reg, + unsigned int val); + +static void async_cleanup(struct work_struct *work) +{ + struct regmap_async *async = container_of(work, struct regmap_async, + cleanup); + + kfree(async->work_buf); + kfree(async); +} + bool regmap_reg_in_ranges(unsigned int reg, const struct regmap_range *ranges, unsigned int nranges) @@ -372,7 +389,7 @@ struct regmap *regmap_init(struct device *dev, enum regmap_endian reg_endian, val_endian; int i, j; - if (!bus || !config) + if (!config) goto err; map = kzalloc(sizeof(*map), GFP_KERNEL); @@ -386,7 +403,8 @@ struct regmap *regmap_init(struct device *dev, map->unlock = config->unlock; map->lock_arg = config->lock_arg; } else { - if (bus->fast_io) { + if ((bus && bus->fast_io) || + config->fast_io) { spin_lock_init(&map->spinlock); map->lock = regmap_lock_spinlock; map->unlock = regmap_unlock_spinlock; @@ -423,13 +441,27 @@ struct regmap *regmap_init(struct device *dev, map->cache_type = config->cache_type; map->name = config->name; + spin_lock_init(&map->async_lock); + INIT_LIST_HEAD(&map->async_list); + init_waitqueue_head(&map->async_waitq); + if (config->read_flag_mask || config->write_flag_mask) { map->read_flag_mask = config->read_flag_mask; map->write_flag_mask = config->write_flag_mask; - } else { + } else if (bus) { map->read_flag_mask = bus->read_flag_mask; } + if (!bus) { + map->reg_read = config->reg_read; + map->reg_write = config->reg_write; + + map->defer_caching = false; + goto skip_format_initialization; + } else { + map->reg_read = _regmap_bus_read; + } + reg_endian = config->reg_format_endian; if (reg_endian == REGMAP_ENDIAN_DEFAULT) reg_endian = bus->reg_format_endian_default; @@ -500,6 +532,12 @@ struct regmap *regmap_init(struct device *dev, } break; + case 24: + if (reg_endian != REGMAP_ENDIAN_BIG) + goto err_map; + map->format.format_reg = regmap_format_24; + break; + case 32: switch (reg_endian) { case REGMAP_ENDIAN_BIG: @@ -575,6 +613,16 @@ struct regmap *regmap_init(struct device *dev, goto err_map; } + if (map->format.format_write) { + map->defer_caching = false; + map->reg_write = _regmap_bus_formatted_write; + } else if (map->format.format_val) { + map->defer_caching = true; + map->reg_write = _regmap_bus_raw_write; + } + +skip_format_initialization: + map->range_tree = RB_ROOT; for (i = 0; i < config->num_ranges; i++) { const struct regmap_range_cfg *range_cfg = &config->ranges[i]; @@ -776,7 +824,7 @@ void regmap_exit(struct regmap *map) regcache_exit(map); regmap_debugfs_exit(map); regmap_range_exit(map); - if (map->bus->free_context) + if (map->bus && map->bus->free_context) map->bus->free_context(map->bus_context); kfree(map->work_buf); kfree(map); @@ -870,15 +918,20 @@ static int _regmap_select_page(struct regmap *map, unsigned int *reg, } static int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool async) { struct regmap_range_node *range; + unsigned long flags; u8 *u8 = map->work_buf; + void *work_val = map->work_buf + map->format.reg_bytes + + map->format.pad_bytes; void *buf; int ret = -ENOTSUPP; size_t len; int i; + BUG_ON(!map->bus); + /* Check for unwritable registers before we start */ if (map->writeable_reg) for (i = 0; i < val_len / map->format.val_bytes; i++) @@ -918,7 +971,7 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, dev_dbg(map->dev, "Writing window %d/%zu\n", win_residue, val_len / map->format.val_bytes); ret = _regmap_raw_write(map, reg, val, win_residue * - map->format.val_bytes); + map->format.val_bytes, async); if (ret != 0) return ret; @@ -941,6 +994,50 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, u8[0] |= map->write_flag_mask; + if (async && map->bus->async_write) { + struct regmap_async *async = map->bus->async_alloc(); + if (!async) + return -ENOMEM; + + async->work_buf = kzalloc(map->format.buf_size, + GFP_KERNEL | GFP_DMA); + if (!async->work_buf) { + kfree(async); + return -ENOMEM; + } + + INIT_WORK(&async->cleanup, async_cleanup); + async->map = map; + + /* If the caller supplied the value we can use it safely. */ + memcpy(async->work_buf, map->work_buf, map->format.pad_bytes + + map->format.reg_bytes + map->format.val_bytes); + if (val == work_val) + val = async->work_buf + map->format.pad_bytes + + map->format.reg_bytes; + + spin_lock_irqsave(&map->async_lock, flags); + list_add_tail(&async->list, &map->async_list); + spin_unlock_irqrestore(&map->async_lock, flags); + + ret = map->bus->async_write(map->bus_context, async->work_buf, + map->format.reg_bytes + + map->format.pad_bytes, + val, val_len, async); + + if (ret != 0) { + dev_err(map->dev, "Failed to schedule write: %d\n", + ret); + + spin_lock_irqsave(&map->async_lock, flags); + list_del(&async->list); + spin_unlock_irqrestore(&map->async_lock, flags); + + kfree(async->work_buf); + kfree(async); + } + } + trace_regmap_hw_write_start(map->dev, reg, val_len / map->format.val_bytes); @@ -948,8 +1045,7 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, * send the work_buf directly, otherwise try to do a gather * write. */ - if (val == (map->work_buf + map->format.pad_bytes + - map->format.reg_bytes)) + if (val == work_val) ret = map->bus->write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes + @@ -981,14 +1077,62 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, return ret; } +static int _regmap_bus_formatted_write(void *context, unsigned int reg, + unsigned int val) +{ + int ret; + struct regmap_range_node *range; + struct regmap *map = context; + + BUG_ON(!map->bus || !map->format.format_write); + + range = _regmap_range_lookup(map, reg); + if (range) { + ret = _regmap_select_page(map, ®, range, 1); + if (ret != 0) + return ret; + } + + map->format.format_write(map, reg, val); + + trace_regmap_hw_write_start(map->dev, reg, 1); + + ret = map->bus->write(map->bus_context, map->work_buf, + map->format.buf_size); + + trace_regmap_hw_write_done(map->dev, reg, 1); + + return ret; +} + +static int _regmap_bus_raw_write(void *context, unsigned int reg, + unsigned int val) +{ + struct regmap *map = context; + + BUG_ON(!map->bus || !map->format.format_val); + + map->format.format_val(map->work_buf + map->format.reg_bytes + + map->format.pad_bytes, val, 0); + return _regmap_raw_write(map, reg, + map->work_buf + + map->format.reg_bytes + + map->format.pad_bytes, + map->format.val_bytes, false); +} + +static inline void *_regmap_map_get_context(struct regmap *map) +{ + return (map->bus) ? map : map->bus_context; +} + int _regmap_write(struct regmap *map, unsigned int reg, unsigned int val) { - struct regmap_range_node *range; int ret; - BUG_ON(!map->format.format_write && !map->format.format_val); + void *context = _regmap_map_get_context(map); - if (!map->cache_bypass && map->format.format_write) { + if (!map->cache_bypass && !map->defer_caching) { ret = regcache_write(map, reg, val); if (ret != 0) return ret; @@ -1005,33 +1149,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, trace_regmap_reg_write(map->dev, reg, val); - if (map->format.format_write) { - range = _regmap_range_lookup(map, reg); - if (range) { - ret = _regmap_select_page(map, ®, range, 1); - if (ret != 0) - return ret; - } - - map->format.format_write(map, reg, val); - - trace_regmap_hw_write_start(map->dev, reg, 1); - - ret = map->bus->write(map->bus_context, map->work_buf, - map->format.buf_size); - - trace_regmap_hw_write_done(map->dev, reg, 1); - - return ret; - } else { - map->format.format_val(map->work_buf + map->format.reg_bytes - + map->format.pad_bytes, val, 0); - return _regmap_raw_write(map, reg, - map->work_buf + - map->format.reg_bytes + - map->format.pad_bytes, - map->format.val_bytes); - } + return map->reg_write(context, reg, val); } /** @@ -1082,6 +1200,8 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, { int ret; + if (!map->bus) + return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; if (reg % map->reg_stride) @@ -1089,7 +1209,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, map->lock(map->lock_arg); - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->unlock(map->lock_arg); @@ -1118,6 +1238,8 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_bytes = map->format.val_bytes; void *wval; + if (!map->bus) + return -EINVAL; if (!map->format.parse_val) return -EINVAL; if (reg % map->reg_stride) @@ -1145,14 +1267,15 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, if (map->use_single_rw) { for (i = 0; i < val_count; i++) { ret = regmap_raw_write(map, - reg + (i * map->reg_stride), - val + (i * val_bytes), - val_bytes); + reg + (i * map->reg_stride), + val + (i * val_bytes), + val_bytes); if (ret != 0) return ret; } } else { - ret = _regmap_raw_write(map, reg, wval, val_bytes * val_count); + ret = _regmap_raw_write(map, reg, wval, val_bytes * val_count, + false); } if (val_bytes != 1) @@ -1164,6 +1287,48 @@ out: } EXPORT_SYMBOL_GPL(regmap_bulk_write); +/** + * regmap_raw_write_async(): Write raw values to one or more registers + * asynchronously + * + * @map: Register map to write to + * @reg: Initial register to write to + * @val: Block of data to be written, laid out for direct transmission to the + * device. Must be valid until regmap_async_complete() is called. + * @val_len: Length of data pointed to by val. + * + * This function is intended to be used for things like firmware + * download where a large block of data needs to be transferred to the + * device. No formatting will be done on the data provided. + * + * If supported by the underlying bus the write will be scheduled + * asynchronously, helping maximise I/O speed on higher speed buses + * like SPI. regmap_async_complete() can be called to ensure that all + * asynchrnous writes have been completed. + * + * A value of zero will be returned on success, a negative errno will + * be returned in error cases. + */ +int regmap_raw_write_async(struct regmap *map, unsigned int reg, + const void *val, size_t val_len) +{ + int ret; + + if (val_len % map->format.val_bytes) + return -EINVAL; + if (reg % map->reg_stride) + return -EINVAL; + + map->lock(map->lock_arg); + + ret = _regmap_raw_write(map, reg, val, val_len, true); + + map->unlock(map->lock_arg); + + return ret; +} +EXPORT_SYMBOL_GPL(regmap_raw_write_async); + static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int val_len) { @@ -1171,6 +1336,8 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, u8 *u8 = map->work_buf; int ret; + BUG_ON(!map->bus); + range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, @@ -1202,10 +1369,29 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, return ret; } +static int _regmap_bus_read(void *context, unsigned int reg, + unsigned int *val) +{ + int ret; + struct regmap *map = context; + + if (!map->format.parse_val) + return -EINVAL; + + ret = _regmap_raw_read(map, reg, map->work_buf, map->format.val_bytes); + if (ret == 0) + *val = map->format.parse_val(map->work_buf); + + return ret; +} + static int _regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) { int ret; + void *context = _regmap_map_get_context(map); + + BUG_ON(!map->reg_read); if (!map->cache_bypass) { ret = regcache_read(map, reg, val); @@ -1213,26 +1399,21 @@ static int _regmap_read(struct regmap *map, unsigned int reg, return 0; } - if (!map->format.parse_val) - return -EINVAL; - if (map->cache_only) return -EBUSY; - ret = _regmap_raw_read(map, reg, map->work_buf, map->format.val_bytes); + ret = map->reg_read(context, reg, val); if (ret == 0) { - *val = map->format.parse_val(map->work_buf); - #ifdef LOG_DEVICE if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) dev_info(map->dev, "%x => %x\n", reg, *val); #endif trace_regmap_reg_read(map->dev, reg, *val); - } - if (ret == 0 && !map->cache_bypass) - regcache_write(map, reg, *val); + if (!map->cache_bypass) + regcache_write(map, reg, *val); + } return ret; } @@ -1283,6 +1464,8 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int v; int ret, i; + if (!map->bus) + return -EINVAL; if (val_len % map->format.val_bytes) return -EINVAL; if (reg % map->reg_stride) @@ -1334,6 +1517,8 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_bytes = map->format.val_bytes; bool vol = regmap_volatile_range(map, reg, val_count); + if (!map->bus) + return -EINVAL; if (!map->format.parse_val) return -EINVAL; if (reg % map->reg_stride) @@ -1450,6 +1635,68 @@ int regmap_update_bits_check(struct regmap *map, unsigned int reg, } EXPORT_SYMBOL_GPL(regmap_update_bits_check); +void regmap_async_complete_cb(struct regmap_async *async, int ret) +{ + struct regmap *map = async->map; + bool wake; + + spin_lock(&map->async_lock); + + list_del(&async->list); + wake = list_empty(&map->async_list); + + if (ret != 0) + map->async_ret = ret; + + spin_unlock(&map->async_lock); + + schedule_work(&async->cleanup); + + if (wake) + wake_up(&map->async_waitq); +} +EXPORT_SYMBOL_GPL(regmap_async_complete_cb); + +static int regmap_async_is_done(struct regmap *map) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&map->async_lock, flags); + ret = list_empty(&map->async_list); + spin_unlock_irqrestore(&map->async_lock, flags); + + return ret; +} + +/** + * regmap_async_complete: Ensure all asynchronous I/O has completed. + * + * @map: Map to operate on. + * + * Blocks until any pending asynchronous I/O has completed. Returns + * an error code for any failed I/O operations. + */ +int regmap_async_complete(struct regmap *map) +{ + unsigned long flags; + int ret; + + /* Nothing to do with no async support */ + if (!map->bus->async_write) + return 0; + + wait_event(map->async_waitq, regmap_async_is_done(map)); + + spin_lock_irqsave(&map->async_lock, flags); + ret = map->async_ret; + map->async_ret = 0; + spin_unlock_irqrestore(&map->async_lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(regmap_async_complete); + /** * regmap_register_patch: Register and apply register updates to be applied * on device initialistion diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index 19e3fbf..cb0c454 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -94,11 +94,16 @@ void bcma_core_pci_hostmode_init(struct bcma_drv_pci *pc); #ifdef CONFIG_BCMA_DRIVER_GPIO /* driver_gpio.c */ int bcma_gpio_init(struct bcma_drv_cc *cc); +int bcma_gpio_unregister(struct bcma_drv_cc *cc); #else static inline int bcma_gpio_init(struct bcma_drv_cc *cc) { return -ENOTSUPP; } +static inline int bcma_gpio_unregister(struct bcma_drv_cc *cc) +{ + return 0; +} #endif /* CONFIG_BCMA_DRIVER_GPIO */ #endif diff --git a/drivers/bcma/driver_chipcommon_nflash.c b/drivers/bcma/driver_chipcommon_nflash.c index dbda91e..1f0b83e 100644 --- a/drivers/bcma/driver_chipcommon_nflash.c +++ b/drivers/bcma/driver_chipcommon_nflash.c @@ -21,7 +21,7 @@ int bcma_nflash_init(struct bcma_drv_cc *cc) struct bcma_bus *bus = cc->core->bus; if (bus->chipinfo.id != BCMA_CHIP_ID_BCM4706 && - cc->core->id.rev != 0x38) { + cc->core->id.rev != 38) { bcma_err(bus, "NAND flash on unsupported board!\n"); return -ENOTSUPP; } diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c index 9a6f585..71f755c 100644 --- a/drivers/bcma/driver_gpio.c +++ b/drivers/bcma/driver_gpio.c @@ -96,3 +96,8 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) return gpiochip_add(chip); } + +int bcma_gpio_unregister(struct bcma_drv_cc *cc) +{ + return gpiochip_remove(&cc->gpio); +} diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index 4a92f64..324f9de 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -268,6 +268,13 @@ int bcma_bus_register(struct bcma_bus *bus) void bcma_bus_unregister(struct bcma_bus *bus) { struct bcma_device *cores[3]; + int err; + + err = bcma_gpio_unregister(&bus->drv_cc); + if (err == -EBUSY) + bcma_err(bus, "Some GPIOs are still in use.\n"); + else if (err) + bcma_err(bus, "Can not unregister GPIO driver: %i\n", err); cores[0] = bcma_find_core(bus, BCMA_CORE_MIPS_74K); cores[1] = bcma_find_core(bus, BCMA_CORE_PCIE); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index f58a4a4..2b8303a 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -168,7 +168,7 @@ static void wake_all_senders(struct drbd_tconn *tconn) { } /* must hold resource->req_lock */ -static void start_new_tl_epoch(struct drbd_tconn *tconn) +void start_new_tl_epoch(struct drbd_tconn *tconn) { /* no point closing an epoch, if it is empty, anyways. */ if (tconn->current_tle_writes == 0) diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h index 016de6b..c08d229 100644 --- a/drivers/block/drbd/drbd_req.h +++ b/drivers/block/drbd/drbd_req.h @@ -267,6 +267,7 @@ struct bio_and_error { int error; }; +extern void start_new_tl_epoch(struct drbd_tconn *tconn); extern void drbd_req_destroy(struct kref *kref); extern void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m); diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 53bf618..0fe220c 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -931,6 +931,7 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns, enum drbd_state_rv rv = SS_SUCCESS; enum sanitize_state_warnings ssw; struct after_state_chg_work *ascw; + bool did_remote, should_do_remote; os = drbd_read_state(mdev); @@ -981,11 +982,17 @@ __drbd_set_state(struct drbd_conf *mdev, union drbd_state ns, (os.disk != D_DISKLESS && ns.disk == D_DISKLESS)) atomic_inc(&mdev->local_cnt); + did_remote = drbd_should_do_remote(mdev->state); mdev->state.i = ns.i; + should_do_remote = drbd_should_do_remote(mdev->state); mdev->tconn->susp = ns.susp; mdev->tconn->susp_nod = ns.susp_nod; mdev->tconn->susp_fen = ns.susp_fen; + /* put replicated vs not-replicated requests in seperate epochs */ + if (did_remote != should_do_remote) + start_new_tl_epoch(mdev->tconn); + if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING) drbd_print_uuids(mdev, "attached to UUIDs"); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 9694dd9..3fd1009 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -626,12 +626,13 @@ static void mtip_timeout_function(unsigned long int data) } } - if (cmdto_cnt && !test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) { + if (cmdto_cnt) { print_tags(port->dd, "timed out", tagaccum, cmdto_cnt); - - mtip_restart_port(port); + if (!test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) { + mtip_restart_port(port); + wake_up_interruptible(&port->svc_wait); + } clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags); - wake_up_interruptible(&port->svc_wait); } if (port->ic_pause_timer) { @@ -3887,7 +3888,12 @@ static int mtip_block_remove(struct driver_data *dd) * Delete our gendisk structure. This also removes the device * from /dev */ - del_gendisk(dd->disk); + if (dd->disk) { + if (dd->disk->queue) + del_gendisk(dd->disk); + else + put_disk(dd->disk); + } spin_lock(&rssd_index_lock); ida_remove(&rssd_index_ida, dd->index); @@ -3921,7 +3927,13 @@ static int mtip_block_shutdown(struct driver_data *dd) "Shutting down %s ...\n", dd->disk->disk_name); /* Delete our gendisk structure, and cleanup the blk queue. */ - del_gendisk(dd->disk); + if (dd->disk) { + if (dd->disk->queue) + del_gendisk(dd->disk); + else + put_disk(dd->disk); + } + spin_lock(&rssd_index_lock); ida_remove(&rssd_index_ida, dd->index); diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 564156a..5814deb 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -461,7 +461,7 @@ static int generic_request(struct vdc_port *port, u8 op, void *buf, int len) int op_len, err; void *req_buf; - if (!(((u64)1 << ((u64)op - 1)) & port->operations)) + if (!(((u64)1 << (u64)op) & port->operations)) return -EOPNOTSUPP; switch (op) { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 74374fb..5ac841f 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -161,10 +161,12 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, static void make_response(struct xen_blkif *blkif, u64 id, unsigned short op, int st); -#define foreach_grant(pos, rbtree, node) \ - for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node); \ +#define foreach_grant_safe(pos, n, rbtree, node) \ + for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node), \ + (n) = rb_next(&(pos)->node); \ &(pos)->node != NULL; \ - (pos) = container_of(rb_next(&(pos)->node), typeof(*(pos)), node)) + (pos) = container_of(n, typeof(*(pos)), node), \ + (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL) static void add_persistent_gnt(struct rb_root *root, @@ -217,10 +219,11 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num) struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct persistent_gnt *persistent_gnt; + struct rb_node *n; int ret = 0; int segs_to_unmap = 0; - foreach_grant(persistent_gnt, root, node) { + foreach_grant_safe(persistent_gnt, n, root, node) { BUG_ON(persistent_gnt->handle == BLKBACK_INVALID_HANDLE); gnttab_set_unmap_op(&unmap[segs_to_unmap], @@ -230,9 +233,6 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num) persistent_gnt->handle); pages[segs_to_unmap] = persistent_gnt->page; - rb_erase(&persistent_gnt->node, root); - kfree(persistent_gnt); - num--; if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST || !rb_next(&persistent_gnt->node)) { @@ -241,6 +241,10 @@ static void free_persistent_gnts(struct rb_root *root, unsigned int num) BUG_ON(ret); segs_to_unmap = 0; } + + rb_erase(&persistent_gnt->node, root); + kfree(persistent_gnt); + num--; } BUG_ON(num != 0); } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 96e9b00..11043c1 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -792,6 +792,7 @@ static void blkif_free(struct blkfront_info *info, int suspend) { struct llist_node *all_gnts; struct grant *persistent_gnt; + struct llist_node *n; /* Prevent new requests being issued until we fix things up. */ spin_lock_irq(&info->io_lock); @@ -804,7 +805,7 @@ static void blkif_free(struct blkfront_info *info, int suspend) /* Remove all persistent grants */ if (info->persistent_gnts_c) { all_gnts = llist_del_all(&info->persistent_gnts); - llist_for_each_entry(persistent_gnt, all_gnts, node) { + llist_for_each_entry_safe(persistent_gnt, n, all_gnts, node) { gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL); __free_page(pfn_to_page(persistent_gnt->pfn)); kfree(persistent_gnt); @@ -835,7 +836,7 @@ static void blkif_free(struct blkfront_info *info, int suspend) static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info, struct blkif_response *bret) { - int i; + int i = 0; struct bio_vec *bvec; struct req_iterator iter; unsigned long flags; @@ -852,7 +853,8 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info, */ rq_for_each_segment(bvec, s->request, iter) { BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE); - i = offset >> PAGE_SHIFT; + if (bvec->bv_offset < offset) + i++; BUG_ON(i >= s->req.u.rw.nr_segments); shared_data = kmap_atomic( pfn_to_page(s->grants_used[i]->pfn)); @@ -861,7 +863,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info, bvec->bv_len); bvec_kunmap_irq(bvec_data, &flags); kunmap_atomic(shared_data); - offset += bvec->bv_len; + offset = bvec->bv_offset + bvec->bv_len; } } /* Add the persistent grant into the list of free grants */ diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index b00000e..33c9a44 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -77,10 +77,15 @@ static struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0CF3, 0x311D) }, { USB_DEVICE(0x13d3, 0x3375) }, { USB_DEVICE(0x04CA, 0x3005) }, + { USB_DEVICE(0x04CA, 0x3006) }, + { USB_DEVICE(0x04CA, 0x3008) }, { USB_DEVICE(0x13d3, 0x3362) }, { USB_DEVICE(0x0CF3, 0xE004) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0489, 0xe057) }, + { USB_DEVICE(0x13d3, 0x3393) }, + { USB_DEVICE(0x0489, 0xe04e) }, + { USB_DEVICE(0x0489, 0xe056) }, /* Atheros AR5BBU12 with sflash firmware */ { USB_DEVICE(0x0489, 0xE02C) }, @@ -104,10 +109,15 @@ static struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU22 with sflash firmware */ { USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a1d4ede..7e351e3 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -135,10 +135,15 @@ static struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU12 with sflash firmware */ { USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE }, diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 684b0d5..ee4dbea 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2062,7 +2062,8 @@ static void virtcons_remove(struct virtio_device *vdev) /* Disable interrupts for vqs */ vdev->config->reset(vdev); /* Finish up work that's lined up */ - cancel_work_sync(&portdev->control_work); + if (use_multiport(portdev)) + cancel_work_sync(&portdev->control_work); list_for_each_entry_safe(port, port2, &portdev->ports, list) unplug_port(port); diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ad8bf2a..2d3f882 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -31,7 +31,7 @@ static struct ecc_settings **ecc_stngs; * *FIXME: Produce a better mapping/linearisation. */ -struct scrubrate { +static const struct scrubrate { u32 scrubval; /* bit pattern for scrub rate */ u32 bandwidth; /* bandwidth consumed (bytes/sec) */ } scrubrates[] = { @@ -239,7 +239,7 @@ static int amd64_get_scrub_rate(struct mem_ctl_info *mci) * DRAM base/limit associated with node_id */ static bool amd64_base_limit_match(struct amd64_pvt *pvt, u64 sys_addr, - unsigned nid) + u8 nid) { u64 addr; @@ -265,7 +265,7 @@ static struct mem_ctl_info *find_mc_by_sys_addr(struct mem_ctl_info *mci, u64 sys_addr) { struct amd64_pvt *pvt; - unsigned node_id; + u8 node_id; u32 intlv_en, bits; /* @@ -939,7 +939,8 @@ static u64 get_error_address(struct mce *m) struct amd64_pvt *pvt; u64 cc6_base, tmp_addr; u32 tmp; - u8 mce_nid, intlv_en; + u16 mce_nid; + u8 intlv_en; if ((addr & GENMASK(24, 47)) >> 24 != 0x00fdf7) return addr; @@ -979,10 +980,29 @@ static u64 get_error_address(struct mce *m) return addr; } +static struct pci_dev *pci_get_related_function(unsigned int vendor, + unsigned int device, + struct pci_dev *related) +{ + struct pci_dev *dev = NULL; + + while ((dev = pci_get_device(vendor, device, dev))) { + if (pci_domain_nr(dev->bus) == pci_domain_nr(related->bus) && + (dev->bus->number == related->bus->number) && + (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn))) + break; + } + + return dev; +} + static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) { + struct amd_northbridge *nb; + struct pci_dev *misc, *f1 = NULL; struct cpuinfo_x86 *c = &boot_cpu_data; int off = range << 3; + u32 llim; amd64_read_pci_cfg(pvt->F1, DRAM_BASE_LO + off, &pvt->ranges[range].base.lo); amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_LO + off, &pvt->ranges[range].lim.lo); @@ -996,30 +1016,32 @@ static void read_dram_base_limit_regs(struct amd64_pvt *pvt, unsigned range) amd64_read_pci_cfg(pvt->F1, DRAM_BASE_HI + off, &pvt->ranges[range].base.hi); amd64_read_pci_cfg(pvt->F1, DRAM_LIMIT_HI + off, &pvt->ranges[range].lim.hi); - /* Factor in CC6 save area by reading dst node's limit reg */ - if (c->x86 == 0x15) { - struct pci_dev *f1 = NULL; - u8 nid = dram_dst_node(pvt, range); - u32 llim; + /* F15h: factor in CC6 save area by reading dst node's limit reg */ + if (c->x86 != 0x15) + return; - f1 = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0x18 + nid, 1)); - if (WARN_ON(!f1)) - return; + nb = node_to_amd_nb(dram_dst_node(pvt, range)); + if (WARN_ON(!nb)) + return; - amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); + misc = nb->misc; + f1 = pci_get_related_function(misc->vendor, PCI_DEVICE_ID_AMD_15H_NB_F1, misc); + if (WARN_ON(!f1)) + return; - pvt->ranges[range].lim.lo &= GENMASK(0, 15); + amd64_read_pci_cfg(f1, DRAM_LOCAL_NODE_LIM, &llim); - /* {[39:27],111b} */ - pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16; + pvt->ranges[range].lim.lo &= GENMASK(0, 15); - pvt->ranges[range].lim.hi &= GENMASK(0, 7); + /* {[39:27],111b} */ + pvt->ranges[range].lim.lo |= ((llim & 0x1fff) << 3 | 0x7) << 16; - /* [47:40] */ - pvt->ranges[range].lim.hi |= llim >> 13; + pvt->ranges[range].lim.hi &= GENMASK(0, 7); - pci_dev_put(f1); - } + /* [47:40] */ + pvt->ranges[range].lim.hi |= llim >> 13; + + pci_dev_put(f1); } static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr, @@ -1305,7 +1327,7 @@ static u8 f1x_determine_channel(struct amd64_pvt *pvt, u64 sys_addr, } /* Convert the sys_addr to the normalized DCT address */ -static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, unsigned range, +static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range, u64 sys_addr, bool hi_rng, u32 dct_sel_base_addr) { @@ -1381,7 +1403,7 @@ static int f10_process_possible_spare(struct amd64_pvt *pvt, u8 dct, int csrow) * -EINVAL: NOT FOUND * 0..csrow = Chip-Select Row */ -static int f1x_lookup_addr_in_dct(u64 in_addr, u32 nid, u8 dct) +static int f1x_lookup_addr_in_dct(u64 in_addr, u8 nid, u8 dct) { struct mem_ctl_info *mci; struct amd64_pvt *pvt; @@ -1672,23 +1694,6 @@ static struct amd64_family_type amd64_family_types[] = { }, }; -static struct pci_dev *pci_get_related_function(unsigned int vendor, - unsigned int device, - struct pci_dev *related) -{ - struct pci_dev *dev = NULL; - - dev = pci_get_device(vendor, device, dev); - while (dev) { - if ((dev->bus->number == related->bus->number) && - (PCI_SLOT(dev->devfn) == PCI_SLOT(related->devfn))) - break; - dev = pci_get_device(vendor, device, dev); - } - - return dev; -} - /* * These are tables of eigenvectors (one per line) which can be used for the * construction of the syndrome tables. The modified syndrome search algorithm @@ -1696,7 +1701,7 @@ static struct pci_dev *pci_get_related_function(unsigned int vendor, * * Algorithm courtesy of Ross LaFetra from AMD. */ -static u16 x4_vectors[] = { +static const u16 x4_vectors[] = { 0x2f57, 0x1afe, 0x66cc, 0xdd88, 0x11eb, 0x3396, 0x7f4c, 0xeac8, 0x0001, 0x0002, 0x0004, 0x0008, @@ -1735,7 +1740,7 @@ static u16 x4_vectors[] = { 0x19a9, 0x2efe, 0xb5cc, 0x6f88, }; -static u16 x8_vectors[] = { +static const u16 x8_vectors[] = { 0x0145, 0x028a, 0x2374, 0x43c8, 0xa1f0, 0x0520, 0x0a40, 0x1480, 0x0211, 0x0422, 0x0844, 0x1088, 0x01b0, 0x44e0, 0x23c0, 0xed80, 0x1011, 0x0116, 0x022c, 0x0458, 0x08b0, 0x8c60, 0x2740, 0x4e80, @@ -1757,7 +1762,7 @@ static u16 x8_vectors[] = { 0x0100, 0x0200, 0x0400, 0x0800, 0x1000, 0x2000, 0x4000, 0x8000, }; -static int decode_syndrome(u16 syndrome, u16 *vectors, unsigned num_vecs, +static int decode_syndrome(u16 syndrome, const u16 *vectors, unsigned num_vecs, unsigned v_dim) { unsigned int i, err_sym; @@ -2181,7 +2186,7 @@ static int init_csrows(struct mem_ctl_info *mci) } /* get all cores on this DCT */ -static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, unsigned nid) +static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid) { int cpu; @@ -2191,7 +2196,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, unsigned nid) } /* check MCG_CTL on all the cpus on this node */ -static bool amd64_nb_mce_bank_enabled_on_node(unsigned nid) +static bool amd64_nb_mce_bank_enabled_on_node(u16 nid) { cpumask_var_t mask; int cpu, nbe; @@ -2224,7 +2229,7 @@ out: return ret; } -static int toggle_ecc_err_reporting(struct ecc_settings *s, u8 nid, bool on) +static int toggle_ecc_err_reporting(struct ecc_settings *s, u16 nid, bool on) { cpumask_var_t cmask; int cpu; @@ -2262,7 +2267,7 @@ static int toggle_ecc_err_reporting(struct ecc_settings *s, u8 nid, bool on) return 0; } -static bool enable_ecc_error_reporting(struct ecc_settings *s, u8 nid, +static bool enable_ecc_error_reporting(struct ecc_settings *s, u16 nid, struct pci_dev *F3) { bool ret = true; @@ -2314,7 +2319,7 @@ static bool enable_ecc_error_reporting(struct ecc_settings *s, u8 nid, return ret; } -static void restore_ecc_error_reporting(struct ecc_settings *s, u8 nid, +static void restore_ecc_error_reporting(struct ecc_settings *s, u16 nid, struct pci_dev *F3) { u32 value, mask = 0x3; /* UECC/CECC enable */ @@ -2353,7 +2358,7 @@ static const char *ecc_msg = "'ecc_enable_override'.\n" " (Note that use of the override may cause unknown side effects.)\n"; -static bool ecc_enabled(struct pci_dev *F3, u8 nid) +static bool ecc_enabled(struct pci_dev *F3, u16 nid) { u32 value; u8 ecc_en = 0; @@ -2474,7 +2479,7 @@ static int amd64_init_one_instance(struct pci_dev *F2) struct mem_ctl_info *mci = NULL; struct edac_mc_layer layers[2]; int err = 0, ret; - u8 nid = get_node_id(F2); + u16 nid = amd_get_node_id(F2); ret = -ENOMEM; pvt = kzalloc(sizeof(struct amd64_pvt), GFP_KERNEL); @@ -2566,7 +2571,7 @@ err_ret: static int amd64_probe_one_instance(struct pci_dev *pdev, const struct pci_device_id *mc_type) { - u8 nid = get_node_id(pdev); + u16 nid = amd_get_node_id(pdev); struct pci_dev *F3 = node_to_amd_nb(nid)->misc; struct ecc_settings *s; int ret = 0; @@ -2616,7 +2621,7 @@ static void amd64_remove_one_instance(struct pci_dev *pdev) { struct mem_ctl_info *mci; struct amd64_pvt *pvt; - u8 nid = get_node_id(pdev); + u16 nid = amd_get_node_id(pdev); struct pci_dev *F3 = node_to_amd_nb(nid)->misc; struct ecc_settings *s = ecc_stngs[nid]; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index e864f40..35637d8 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -292,12 +292,6 @@ /* MSRs */ #define MSR_MCGCTL_NBE BIT(4) -/* AMD sets the first MC device at device ID 0x18. */ -static inline u8 get_node_id(struct pci_dev *pdev) -{ - return PCI_SLOT(pdev->devfn) - 0x18; -} - enum amd_families { K8_CPUS = 0, F10_CPUS, @@ -340,7 +334,7 @@ struct amd64_pvt { /* pci_device handles which we utilize */ struct pci_dev *F1, *F2, *F3; - unsigned mc_node_id; /* MC index of this MC node */ + u16 mc_node_id; /* MC index of this MC node */ int ext_model; /* extended model value of this node */ int channel_count; @@ -393,7 +387,7 @@ struct err_info { u32 offset; }; -static inline u64 get_dram_base(struct amd64_pvt *pvt, unsigned i) +static inline u64 get_dram_base(struct amd64_pvt *pvt, u8 i) { u64 addr = ((u64)pvt->ranges[i].base.lo & 0xffff0000) << 8; @@ -403,7 +397,7 @@ static inline u64 get_dram_base(struct amd64_pvt *pvt, unsigned i) return (((u64)pvt->ranges[i].base.hi & 0x000000ff) << 40) | addr; } -static inline u64 get_dram_limit(struct amd64_pvt *pvt, unsigned i) +static inline u64 get_dram_limit(struct amd64_pvt *pvt, u8 i) { u64 lim = (((u64)pvt->ranges[i].lim.lo & 0xffff0000) << 8) | 0x00ffffff; diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 281f566..d1e9eb1 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -340,7 +340,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, /* * Alocate and fill the csrow/channels structs */ - mci->csrows = kcalloc(sizeof(*mci->csrows), tot_csrows, GFP_KERNEL); + mci->csrows = kcalloc(tot_csrows, sizeof(*mci->csrows), GFP_KERNEL); if (!mci->csrows) goto error; for (row = 0; row < tot_csrows; row++) { @@ -351,7 +351,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, csr->csrow_idx = row; csr->mci = mci; csr->nr_channels = tot_channels; - csr->channels = kcalloc(sizeof(*csr->channels), tot_channels, + csr->channels = kcalloc(tot_channels, sizeof(*csr->channels), GFP_KERNEL); if (!csr->channels) goto error; @@ -369,7 +369,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, /* * Allocate and fill the dimm structs */ - mci->dimms = kcalloc(sizeof(*mci->dimms), tot_dimms, GFP_KERNEL); + mci->dimms = kcalloc(tot_dimms, sizeof(*mci->dimms), GFP_KERNEL); if (!mci->dimms) goto error; diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index dc6e905..0056c4d 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -256,7 +256,7 @@ static ssize_t edac_pci_dev_store(struct kobject *kobj, struct edac_pci_dev_attribute *edac_pci_dev; edac_pci_dev = (struct edac_pci_dev_attribute *)attr; - if (edac_pci_dev->show) + if (edac_pci_dev->store) return edac_pci_dev->store(edac_pci_dev->value, buffer, count); return -EIO; } diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index fd3ae62..982f1f5 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -471,7 +471,7 @@ void __init dmi_scan_machine(void) char __iomem *p, *q; int rc; - if (efi_enabled) { + if (efi_enabled(EFI_CONFIG_TABLES)) { if (efi.smbios == EFI_INVALID_TABLE_ADDR) goto error; diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 7b1c374..f5596db 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -674,7 +674,7 @@ static int efi_status_to_err(efi_status_t status) err = -EACCES; break; case EFI_NOT_FOUND: - err = -ENOENT; + err = -EIO; break; default: err = -EINVAL; @@ -793,6 +793,7 @@ static ssize_t efivarfs_file_write(struct file *file, spin_unlock(&efivars->lock); efivar_unregister(var); drop_nlink(inode); + d_delete(file->f_dentry); dput(file->f_dentry); } else { @@ -994,7 +995,7 @@ static int efivarfs_unlink(struct inode *dir, struct dentry *dentry) list_del(&var->list); spin_unlock(&efivars->lock); efivar_unregister(var); - drop_nlink(dir); + drop_nlink(dentry->d_inode); dput(dentry); return 0; } @@ -1782,7 +1783,7 @@ efivars_init(void) printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION, EFIVARS_DATE); - if (!efi_enabled) + if (!efi_enabled(EFI_RUNTIME_SERVICES)) return 0; /* For now we'll register the efi directory at /sys/firmware/efi */ @@ -1822,7 +1823,7 @@ err_put: static void __exit efivars_exit(void) { - if (efi_enabled) { + if (efi_enabled(EFI_RUNTIME_SERVICES)) { unregister_efivars(&__efivars); kobject_put(efi_kobj); } diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c index 4da4eb9..2224f1d 100644 --- a/drivers/firmware/iscsi_ibft_find.c +++ b/drivers/firmware/iscsi_ibft_find.c @@ -99,7 +99,7 @@ unsigned long __init find_ibft_region(unsigned long *sizep) /* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will * only use ACPI for this */ - if (!efi_enabled) + if (!efi_enabled(EFI_BOOT)) find_ibft_in_mem(); if (ibft_addr) { diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 682de75..e5116fa 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -657,12 +657,6 @@ config GPIO_JANZ_TTL This driver provides support for driving the pins in output mode only. Input mode is not supported. -config GPIO_AB8500 - bool "ST-Ericsson AB8500 Mixed Signal Circuit gpio functions" - depends on AB8500_CORE && BROKEN - help - Select this to enable the AB8500 IC GPIO driver - config GPIO_TPS6586X bool "TPS6586X GPIO" depends on MFD_TPS6586X diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index c5aebd0..45a388c 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_GPIO_ACPI) += gpiolib-acpi.o obj-$(CONFIG_GPIO_GENERIC) += gpio-generic.o obj-$(CONFIG_GPIO_74X164) += gpio-74x164.o -obj-$(CONFIG_GPIO_AB8500) += gpio-ab8500.o obj-$(CONFIG_GPIO_ADNP) += gpio-adnp.o obj-$(CONFIG_GPIO_ADP5520) += gpio-adp5520.o obj-$(CONFIG_GPIO_ADP5588) += gpio-adp5588.o diff --git a/drivers/gpio/gpio-ab8500.c b/drivers/gpio/gpio-ab8500.c deleted file mode 100644 index 983ad42..0000000 --- a/drivers/gpio/gpio-ab8500.c +++ /dev/null @@ -1,520 +0,0 @@ -/* - * Copyright (C) ST-Ericsson SA 2011 - * - * Author: BIBEK BASU <bibek.basu@stericsson.com> - * License terms: GNU General Public License (GPL) version 2 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/err.h> -#include <linux/platform_device.h> -#include <linux/gpio.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/mfd/ab8500.h> -#include <linux/mfd/abx500.h> -#include <linux/mfd/ab8500/gpio.h> - -/* - * GPIO registers offset - * Bank: 0x10 - */ -#define AB8500_GPIO_SEL1_REG 0x00 -#define AB8500_GPIO_SEL2_REG 0x01 -#define AB8500_GPIO_SEL3_REG 0x02 -#define AB8500_GPIO_SEL4_REG 0x03 -#define AB8500_GPIO_SEL5_REG 0x04 -#define AB8500_GPIO_SEL6_REG 0x05 - -#define AB8500_GPIO_DIR1_REG 0x10 -#define AB8500_GPIO_DIR2_REG 0x11 -#define AB8500_GPIO_DIR3_REG 0x12 -#define AB8500_GPIO_DIR4_REG 0x13 -#define AB8500_GPIO_DIR5_REG 0x14 -#define AB8500_GPIO_DIR6_REG 0x15 - -#define AB8500_GPIO_OUT1_REG 0x20 -#define AB8500_GPIO_OUT2_REG 0x21 -#define AB8500_GPIO_OUT3_REG 0x22 -#define AB8500_GPIO_OUT4_REG 0x23 -#define AB8500_GPIO_OUT5_REG 0x24 -#define AB8500_GPIO_OUT6_REG 0x25 - -#define AB8500_GPIO_PUD1_REG 0x30 -#define AB8500_GPIO_PUD2_REG 0x31 -#define AB8500_GPIO_PUD3_REG 0x32 -#define AB8500_GPIO_PUD4_REG 0x33 -#define AB8500_GPIO_PUD5_REG 0x34 -#define AB8500_GPIO_PUD6_REG 0x35 - -#define AB8500_GPIO_IN1_REG 0x40 -#define AB8500_GPIO_IN2_REG 0x41 -#define AB8500_GPIO_IN3_REG 0x42 -#define AB8500_GPIO_IN4_REG 0x43 -#define AB8500_GPIO_IN5_REG 0x44 -#define AB8500_GPIO_IN6_REG 0x45 -#define AB8500_GPIO_ALTFUN_REG 0x45 -#define ALTFUN_REG_INDEX 6 -#define AB8500_NUM_GPIO 42 -#define AB8500_NUM_VIR_GPIO_IRQ 16 - -enum ab8500_gpio_action { - NONE, - STARTUP, - SHUTDOWN, - MASK, - UNMASK -}; - -struct ab8500_gpio { - struct gpio_chip chip; - struct ab8500 *parent; - struct device *dev; - struct mutex lock; - u32 irq_base; - enum ab8500_gpio_action irq_action; - u16 rising; - u16 falling; -}; -/** - * to_ab8500_gpio() - get the pointer to ab8500_gpio - * @chip: Member of the structure ab8500_gpio - */ -static inline struct ab8500_gpio *to_ab8500_gpio(struct gpio_chip *chip) -{ - return container_of(chip, struct ab8500_gpio, chip); -} - -static int ab8500_gpio_set_bits(struct gpio_chip *chip, u8 reg, - unsigned offset, int val) -{ - struct ab8500_gpio *ab8500_gpio = to_ab8500_gpio(chip); - u8 pos = offset % 8; - int ret; - - reg = reg + (offset / 8); - ret = abx500_mask_and_set_register_interruptible(ab8500_gpio->dev, - AB8500_MISC, reg, 1 << pos, val << pos); - if (ret < 0) - dev_err(ab8500_gpio->dev, "%s write failed\n", __func__); - return ret; -} -/** - * ab8500_gpio_get() - Get the particular GPIO value - * @chip: Gpio device - * @offset: GPIO number to read - */ -static int ab8500_gpio_get(struct gpio_chip *chip, unsigned offset) -{ - struct ab8500_gpio *ab8500_gpio = to_ab8500_gpio(chip); - u8 mask = 1 << (offset % 8); - u8 reg = AB8500_GPIO_OUT1_REG + (offset / 8); - int ret; - u8 data; - ret = abx500_get_register_interruptible(ab8500_gpio->dev, AB8500_MISC, - reg, &data); - if (ret < 0) { - dev_err(ab8500_gpio->dev, "%s read failed\n", __func__); - return ret; - } - return (data & mask) >> (offset % 8); -} - -static void ab8500_gpio_set(struct gpio_chip *chip, unsigned offset, int val) -{ - struct ab8500_gpio *ab8500_gpio = to_ab8500_gpio(chip); - int ret; - /* Write the data */ - ret = ab8500_gpio_set_bits(chip, AB8500_GPIO_OUT1_REG, offset, 1); - if (ret < 0) - dev_err(ab8500_gpio->dev, "%s write failed\n", __func__); -} - -static int ab8500_gpio_direction_output(struct gpio_chip *chip, unsigned offset, - int val) -{ - int ret; - /* set direction as output */ - ret = ab8500_gpio_set_bits(chip, AB8500_GPIO_DIR1_REG, offset, 1); - if (ret < 0) - return ret; - /* disable pull down */ - ret = ab8500_gpio_set_bits(chip, AB8500_GPIO_PUD1_REG, offset, 1); - if (ret < 0) - return ret; - /* set the output as 1 or 0 */ - return ab8500_gpio_set_bits(chip, AB8500_GPIO_OUT1_REG, offset, val); - -} - -static int ab8500_gpio_direction_input(struct gpio_chip *chip, unsigned offset) -{ - /* set the register as input */ - return ab8500_gpio_set_bits(chip, AB8500_GPIO_DIR1_REG, offset, 0); -} - -static int ab8500_gpio_to_irq(struct gpio_chip *chip, unsigned offset) -{ - /* - * Only some GPIOs are interrupt capable, and they are - * organized in discontiguous clusters: - * - * GPIO6 to GPIO13 - * GPIO24 and GPIO25 - * GPIO36 to GPIO41 - */ - static struct ab8500_gpio_irq_cluster { - int start; - int end; - } clusters[] = { - {.start = 6, .end = 13}, - {.start = 24, .end = 25}, - {.start = 36, .end = 41}, - }; - struct ab8500_gpio *ab8500_gpio = to_ab8500_gpio(chip); - int base = ab8500_gpio->irq_base; - int i; - - for (i = 0; i < ARRAY_SIZE(clusters); i++) { - struct ab8500_gpio_irq_cluster *cluster = &clusters[i]; - - if (offset >= cluster->start && offset <= cluster->end) - return base + offset - cluster->start; - - /* Advance by the number of gpios in this cluster */ - base += cluster->end - cluster->start + 1; - } - - return -EINVAL; -} - -static struct gpio_chip ab8500gpio_chip = { - .label = "ab8500_gpio", - .owner = THIS_MODULE, - .direction_input = ab8500_gpio_direction_input, - .get = ab8500_gpio_get, - .direction_output = ab8500_gpio_direction_output, - .set = ab8500_gpio_set, - .to_irq = ab8500_gpio_to_irq, -}; - -static unsigned int irq_to_rising(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - int offset = irq - ab8500_gpio->irq_base; - int new_irq = offset + AB8500_INT_GPIO6R - + ab8500_gpio->parent->irq_base; - return new_irq; -} - -static unsigned int irq_to_falling(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - int offset = irq - ab8500_gpio->irq_base; - int new_irq = offset + AB8500_INT_GPIO6F - + ab8500_gpio->parent->irq_base; - return new_irq; - -} - -static unsigned int rising_to_irq(unsigned int irq, void *dev) -{ - struct ab8500_gpio *ab8500_gpio = dev; - int offset = irq - AB8500_INT_GPIO6R - - ab8500_gpio->parent->irq_base ; - int new_irq = offset + ab8500_gpio->irq_base; - return new_irq; -} - -static unsigned int falling_to_irq(unsigned int irq, void *dev) -{ - struct ab8500_gpio *ab8500_gpio = dev; - int offset = irq - AB8500_INT_GPIO6F - - ab8500_gpio->parent->irq_base ; - int new_irq = offset + ab8500_gpio->irq_base; - return new_irq; - -} - -/* - * IRQ handler - */ - -static irqreturn_t handle_rising(int irq, void *dev) -{ - - handle_nested_irq(rising_to_irq(irq , dev)); - return IRQ_HANDLED; -} - -static irqreturn_t handle_falling(int irq, void *dev) -{ - - handle_nested_irq(falling_to_irq(irq, dev)); - return IRQ_HANDLED; -} - -static void ab8500_gpio_irq_lock(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - mutex_lock(&ab8500_gpio->lock); -} - -static void ab8500_gpio_irq_sync_unlock(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - int offset = irq - ab8500_gpio->irq_base; - bool rising = ab8500_gpio->rising & BIT(offset); - bool falling = ab8500_gpio->falling & BIT(offset); - int ret; - - switch (ab8500_gpio->irq_action) { - case STARTUP: - if (rising) - ret = request_threaded_irq(irq_to_rising(irq), - NULL, handle_rising, - IRQF_TRIGGER_RISING, - "ab8500-gpio-r", ab8500_gpio); - if (falling) - ret = request_threaded_irq(irq_to_falling(irq), - NULL, handle_falling, - IRQF_TRIGGER_FALLING, - "ab8500-gpio-f", ab8500_gpio); - break; - case SHUTDOWN: - if (rising) - free_irq(irq_to_rising(irq), ab8500_gpio); - if (falling) - free_irq(irq_to_falling(irq), ab8500_gpio); - break; - case MASK: - if (rising) - disable_irq(irq_to_rising(irq)); - if (falling) - disable_irq(irq_to_falling(irq)); - break; - case UNMASK: - if (rising) - enable_irq(irq_to_rising(irq)); - if (falling) - enable_irq(irq_to_falling(irq)); - break; - case NONE: - break; - } - ab8500_gpio->irq_action = NONE; - ab8500_gpio->rising &= ~(BIT(offset)); - ab8500_gpio->falling &= ~(BIT(offset)); - mutex_unlock(&ab8500_gpio->lock); -} - - -static void ab8500_gpio_irq_mask(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - ab8500_gpio->irq_action = MASK; -} - -static void ab8500_gpio_irq_unmask(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - ab8500_gpio->irq_action = UNMASK; -} - -static int ab8500_gpio_irq_set_type(unsigned int irq, unsigned int type) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - int offset = irq - ab8500_gpio->irq_base; - - if (type == IRQ_TYPE_EDGE_BOTH) { - ab8500_gpio->rising = BIT(offset); - ab8500_gpio->falling = BIT(offset); - } else if (type == IRQ_TYPE_EDGE_RISING) { - ab8500_gpio->rising = BIT(offset); - } else { - ab8500_gpio->falling = BIT(offset); - } - return 0; -} - -unsigned int ab8500_gpio_irq_startup(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - ab8500_gpio->irq_action = STARTUP; - return 0; -} - -void ab8500_gpio_irq_shutdown(unsigned int irq) -{ - struct ab8500_gpio *ab8500_gpio = get_irq_chip_data(irq); - ab8500_gpio->irq_action = SHUTDOWN; -} - -static struct irq_chip ab8500_gpio_irq_chip = { - .name = "ab8500-gpio", - .startup = ab8500_gpio_irq_startup, - .shutdown = ab8500_gpio_irq_shutdown, - .bus_lock = ab8500_gpio_irq_lock, - .bus_sync_unlock = ab8500_gpio_irq_sync_unlock, - .mask = ab8500_gpio_irq_mask, - .unmask = ab8500_gpio_irq_unmask, - .set_type = ab8500_gpio_irq_set_type, -}; - -static int ab8500_gpio_irq_init(struct ab8500_gpio *ab8500_gpio) -{ - u32 base = ab8500_gpio->irq_base; - int irq; - - for (irq = base; irq < base + AB8500_NUM_VIR_GPIO_IRQ ; irq++) { - set_irq_chip_data(irq, ab8500_gpio); - set_irq_chip_and_handler(irq, &ab8500_gpio_irq_chip, - handle_simple_irq); - set_irq_nested_thread(irq, 1); -#ifdef CONFIG_ARM - set_irq_flags(irq, IRQF_VALID); -#else - set_irq_noprobe(irq); -#endif - } - - return 0; -} - -static void ab8500_gpio_irq_remove(struct ab8500_gpio *ab8500_gpio) -{ - int base = ab8500_gpio->irq_base; - int irq; - - for (irq = base; irq < base + AB8500_NUM_VIR_GPIO_IRQ; irq++) { -#ifdef CONFIG_ARM - set_irq_flags(irq, 0); -#endif - set_irq_chip_and_handler(irq, NULL, NULL); - set_irq_chip_data(irq, NULL); - } -} - -static int ab8500_gpio_probe(struct platform_device *pdev) -{ - struct ab8500_platform_data *ab8500_pdata = - dev_get_platdata(pdev->dev.parent); - struct ab8500_gpio_platform_data *pdata; - struct ab8500_gpio *ab8500_gpio; - int ret; - int i; - - pdata = ab8500_pdata->gpio; - if (!pdata) { - dev_err(&pdev->dev, "gpio platform data missing\n"); - return -ENODEV; - } - - ab8500_gpio = kzalloc(sizeof(struct ab8500_gpio), GFP_KERNEL); - if (ab8500_gpio == NULL) { - dev_err(&pdev->dev, "failed to allocate memory\n"); - return -ENOMEM; - } - ab8500_gpio->dev = &pdev->dev; - ab8500_gpio->parent = dev_get_drvdata(pdev->dev.parent); - ab8500_gpio->chip = ab8500gpio_chip; - ab8500_gpio->chip.ngpio = AB8500_NUM_GPIO; - ab8500_gpio->chip.dev = &pdev->dev; - ab8500_gpio->chip.base = pdata->gpio_base; - ab8500_gpio->irq_base = pdata->irq_base; - /* initialize the lock */ - mutex_init(&ab8500_gpio->lock); - /* - * AB8500 core will handle and clear the IRQ - * configre GPIO based on config-reg value. - * These values are for selecting the PINs as - * GPIO or alternate function - */ - for (i = AB8500_GPIO_SEL1_REG; i <= AB8500_GPIO_SEL6_REG; i++) { - ret = abx500_set_register_interruptible(ab8500_gpio->dev, - AB8500_MISC, i, - pdata->config_reg[i]); - if (ret < 0) - goto out_free; - } - ret = abx500_set_register_interruptible(ab8500_gpio->dev, AB8500_MISC, - AB8500_GPIO_ALTFUN_REG, - pdata->config_reg[ALTFUN_REG_INDEX]); - if (ret < 0) - goto out_free; - - ret = ab8500_gpio_irq_init(ab8500_gpio); - if (ret) - goto out_free; - ret = gpiochip_add(&ab8500_gpio->chip); - if (ret) { - dev_err(&pdev->dev, "unable to add gpiochip: %d\n", - ret); - goto out_rem_irq; - } - platform_set_drvdata(pdev, ab8500_gpio); - return 0; - -out_rem_irq: - ab8500_gpio_irq_remove(ab8500_gpio); -out_free: - mutex_destroy(&ab8500_gpio->lock); - kfree(ab8500_gpio); - return ret; -} - -/* - * ab8500_gpio_remove() - remove Ab8500-gpio driver - * @pdev : Platform device registered - */ -static int ab8500_gpio_remove(struct platform_device *pdev) -{ - struct ab8500_gpio *ab8500_gpio = platform_get_drvdata(pdev); - int ret; - - ret = gpiochip_remove(&ab8500_gpio->chip); - if (ret < 0) { - dev_err(ab8500_gpio->dev, "unable to remove gpiochip: %d\n", - ret); - return ret; - } - - platform_set_drvdata(pdev, NULL); - mutex_destroy(&ab8500_gpio->lock); - kfree(ab8500_gpio); - - return 0; -} - -static struct platform_driver ab8500_gpio_driver = { - .driver = { - .name = "ab8500-gpio", - .owner = THIS_MODULE, - }, - .probe = ab8500_gpio_probe, - .remove = ab8500_gpio_remove, -}; - -static int __init ab8500_gpio_init(void) -{ - return platform_driver_register(&ab8500_gpio_driver); -} -arch_initcall(ab8500_gpio_init); - -static void __exit ab8500_gpio_exit(void) -{ - platform_driver_unregister(&ab8500_gpio_driver); -} -module_exit(ab8500_gpio_exit); - -MODULE_AUTHOR("BIBEK BASU <bibek.basu@stericsson.com>"); -MODULE_DESCRIPTION("Driver allows to use AB8500 unused pins to be used as GPIO"); -MODULE_ALIAS("platform:ab8500-gpio"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index d542a14..25b1dbe 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -250,7 +250,7 @@ static void of_gpiochip_add_pin_range(struct gpio_chip *chip) * on the same GPIO chip. */ ret = gpiochip_add_pin_range(chip, - pinctrl_dev_get_name(pctldev), + pinctrl_dev_get_devname(pctldev), 0, /* offset in gpiochip */ pinspec.args[0], pinspec.args[1]); diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 1d1f1e5..046bcda 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -24,7 +24,7 @@ config DRM_EXYNOS_DMABUF config DRM_EXYNOS_FIMD bool "Exynos DRM FIMD" - depends on DRM_EXYNOS && !FB_S3C + depends on DRM_EXYNOS && !FB_S3C && !ARCH_MULTIPLATFORM help Choose this option if you want to use Exynos FIMD for DRM. @@ -48,7 +48,7 @@ config DRM_EXYNOS_G2D config DRM_EXYNOS_IPP bool "Exynos DRM IPP" - depends on DRM_EXYNOS + depends on DRM_EXYNOS && !ARCH_MULTIPLATFORM help Choose this option if you want to use IPP feature for DRM. diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c index ab37437..4c5b685 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_connector.c +++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c @@ -18,7 +18,6 @@ #include "exynos_drm_drv.h" #include "exynos_drm_encoder.h" -#define MAX_EDID 256 #define to_exynos_connector(x) container_of(x, struct exynos_drm_connector,\ drm_connector) @@ -96,7 +95,9 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector) to_exynos_connector(connector); struct exynos_drm_manager *manager = exynos_connector->manager; struct exynos_drm_display_ops *display_ops = manager->display_ops; - unsigned int count; + struct edid *edid = NULL; + unsigned int count = 0; + int ret; DRM_DEBUG_KMS("%s\n", __FILE__); @@ -114,27 +115,21 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector) * because lcd panel has only one mode. */ if (display_ops->get_edid) { - int ret; - void *edid; - - edid = kzalloc(MAX_EDID, GFP_KERNEL); - if (!edid) { - DRM_ERROR("failed to allocate edid\n"); - return 0; + edid = display_ops->get_edid(manager->dev, connector); + if (IS_ERR_OR_NULL(edid)) { + ret = PTR_ERR(edid); + edid = NULL; + DRM_ERROR("Panel operation get_edid failed %d\n", ret); + goto out; } - ret = display_ops->get_edid(manager->dev, connector, - edid, MAX_EDID); - if (ret < 0) { - DRM_ERROR("failed to get edid data.\n"); - kfree(edid); - edid = NULL; - return 0; + count = drm_add_edid_modes(connector, edid); + if (count < 0) { + DRM_ERROR("Add edid modes failed %d\n", count); + goto out; } drm_mode_connector_update_edid_property(connector, edid); - count = drm_add_edid_modes(connector, edid); - kfree(edid); } else { struct exynos_drm_panel_info *panel; struct drm_display_mode *mode = drm_mode_create(connector->dev); @@ -161,6 +156,8 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector) count = 1; } +out: + kfree(edid); return count; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c index 9df9771..ba0a3aa 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c @@ -19,6 +19,7 @@ struct exynos_drm_dmabuf_attachment { struct sg_table sgt; enum dma_data_direction dir; + bool is_mapped; }; static int exynos_gem_attach_dma_buf(struct dma_buf *dmabuf, @@ -72,17 +73,10 @@ static struct sg_table * DRM_DEBUG_PRIME("%s\n", __FILE__); - if (WARN_ON(dir == DMA_NONE)) - return ERR_PTR(-EINVAL); - /* just return current sgt if already requested. */ - if (exynos_attach->dir == dir) + if (exynos_attach->dir == dir && exynos_attach->is_mapped) return &exynos_attach->sgt; - /* reattaching is not allowed. */ - if (WARN_ON(exynos_attach->dir != DMA_NONE)) - return ERR_PTR(-EBUSY); - buf = gem_obj->buffer; if (!buf) { DRM_ERROR("buffer is null.\n"); @@ -107,13 +101,17 @@ static struct sg_table * wr = sg_next(wr); } - nents = dma_map_sg(attach->dev, sgt->sgl, sgt->orig_nents, dir); - if (!nents) { - DRM_ERROR("failed to map sgl with iommu.\n"); - sgt = ERR_PTR(-EIO); - goto err_unlock; + if (dir != DMA_NONE) { + nents = dma_map_sg(attach->dev, sgt->sgl, sgt->orig_nents, dir); + if (!nents) { + DRM_ERROR("failed to map sgl with iommu.\n"); + sg_free_table(sgt); + sgt = ERR_PTR(-EIO); + goto err_unlock; + } } + exynos_attach->is_mapped = true; exynos_attach->dir = dir; attach->priv = exynos_attach; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index b9e51bc..4606fac 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -148,8 +148,8 @@ struct exynos_drm_overlay { struct exynos_drm_display_ops { enum exynos_drm_output_type type; bool (*is_connected)(struct device *dev); - int (*get_edid)(struct device *dev, struct drm_connector *connector, - u8 *edid, int len); + struct edid *(*get_edid)(struct device *dev, + struct drm_connector *connector); void *(*get_panel)(struct device *dev); int (*check_timing)(struct device *dev, void *timing); int (*power_on)(struct device *dev, int mode); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 36c3905..9a4c08e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -324,7 +324,7 @@ out: g2d_userptr = NULL; } -dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev, +static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev, unsigned long userptr, unsigned long size, struct drm_file *filp, diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c index 850e995..2864453 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.c @@ -108,18 +108,17 @@ static bool drm_hdmi_is_connected(struct device *dev) return false; } -static int drm_hdmi_get_edid(struct device *dev, - struct drm_connector *connector, u8 *edid, int len) +static struct edid *drm_hdmi_get_edid(struct device *dev, + struct drm_connector *connector) { struct drm_hdmi_context *ctx = to_context(dev); DRM_DEBUG_KMS("%s\n", __FILE__); if (hdmi_ops && hdmi_ops->get_edid) - return hdmi_ops->get_edid(ctx->hdmi_ctx->ctx, connector, edid, - len); + return hdmi_ops->get_edid(ctx->hdmi_ctx->ctx, connector); - return 0; + return NULL; } static int drm_hdmi_check_timing(struct device *dev, void *timing) diff --git a/drivers/gpu/drm/exynos/exynos_drm_hdmi.h b/drivers/gpu/drm/exynos/exynos_drm_hdmi.h index 784a7e9..d80516f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_hdmi.h +++ b/drivers/gpu/drm/exynos/exynos_drm_hdmi.h @@ -30,8 +30,8 @@ struct exynos_drm_hdmi_context { struct exynos_hdmi_ops { /* display */ bool (*is_connected)(void *ctx); - int (*get_edid)(void *ctx, struct drm_connector *connector, - u8 *edid, int len); + struct edid *(*get_edid)(void *ctx, + struct drm_connector *connector); int (*check_timing)(void *ctx, void *timing); int (*power_on)(void *ctx, int mode); diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index 0bda964..1a55635 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -869,7 +869,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node, } } -void ipp_handle_cmd_work(struct device *dev, +static void ipp_handle_cmd_work(struct device *dev, struct exynos_drm_ippdrv *ippdrv, struct drm_exynos_ipp_cmd_work *cmd_work, struct drm_exynos_ipp_cmd_node *c_node) diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index e9e83ef..f976e29 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -734,7 +734,7 @@ static int rotator_remove(struct platform_device *pdev) return 0; } -struct rot_limit_table rot_limit_tbl = { +static struct rot_limit_table rot_limit_tbl = { .ycbcr420_2p = { .min_w = 32, .min_h = 32, @@ -751,7 +751,7 @@ struct rot_limit_table rot_limit_tbl = { }, }; -struct platform_device_id rotator_driver_ids[] = { +static struct platform_device_id rotator_driver_ids[] = { { .name = "exynos-rot", .driver_data = (unsigned long)&rot_limit_tbl, diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index d0ca3c4..13ccbd4 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -98,10 +98,12 @@ static bool vidi_display_is_connected(struct device *dev) return ctx->connected ? true : false; } -static int vidi_get_edid(struct device *dev, struct drm_connector *connector, - u8 *edid, int len) +static struct edid *vidi_get_edid(struct device *dev, + struct drm_connector *connector) { struct vidi_context *ctx = get_vidi_context(dev); + struct edid *edid; + int edid_len; DRM_DEBUG_KMS("%s\n", __FILE__); @@ -111,13 +113,18 @@ static int vidi_get_edid(struct device *dev, struct drm_connector *connector, */ if (!ctx->raw_edid) { DRM_DEBUG_KMS("raw_edid is null.\n"); - return -EFAULT; + return ERR_PTR(-EFAULT); } - memcpy(edid, ctx->raw_edid, min((1 + ctx->raw_edid->extensions) - * EDID_LENGTH, len)); + edid_len = (1 + ctx->raw_edid->extensions) * EDID_LENGTH; + edid = kzalloc(edid_len, GFP_KERNEL); + if (!edid) { + DRM_DEBUG_KMS("failed to allocate edid\n"); + return ERR_PTR(-ENOMEM); + } - return 0; + memcpy(edid, ctx->raw_edid, edid_len); + return edid; } static void *vidi_get_panel(struct device *dev) @@ -514,7 +521,6 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data, struct exynos_drm_manager *manager; struct exynos_drm_display_ops *display_ops; struct drm_exynos_vidi_connection *vidi = data; - struct edid *raw_edid; int edid_len; DRM_DEBUG_KMS("%s\n", __FILE__); @@ -551,11 +557,11 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data, } if (vidi->connection) { - if (!vidi->edid) { - DRM_DEBUG_KMS("edid data is null.\n"); + struct edid *raw_edid = (struct edid *)(uint32_t)vidi->edid; + if (!drm_edid_is_valid(raw_edid)) { + DRM_DEBUG_KMS("edid data is invalid.\n"); return -EINVAL; } - raw_edid = (struct edid *)(uint32_t)vidi->edid; edid_len = (1 + raw_edid->extensions) * EDID_LENGTH; ctx->raw_edid = kzalloc(edid_len, GFP_KERNEL); if (!ctx->raw_edid) { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 41ff79d..fbab3c4 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -34,7 +34,6 @@ #include <linux/regulator/consumer.h> #include <linux/io.h> #include <linux/of_gpio.h> -#include <plat/gpio-cfg.h> #include <drm/exynos_drm.h> @@ -98,8 +97,7 @@ struct hdmi_context { void __iomem *regs; void *parent_ctx; - int external_irq; - int internal_irq; + int irq; struct i2c_client *ddc_port; struct i2c_client *hdmiphy_port; @@ -1391,8 +1389,7 @@ static bool hdmi_is_connected(void *ctx) return hdata->hpd; } -static int hdmi_get_edid(void *ctx, struct drm_connector *connector, - u8 *edid, int len) +static struct edid *hdmi_get_edid(void *ctx, struct drm_connector *connector) { struct edid *raw_edid; struct hdmi_context *hdata = ctx; @@ -1400,22 +1397,18 @@ static int hdmi_get_edid(void *ctx, struct drm_connector *connector, DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__); if (!hdata->ddc_port) - return -ENODEV; + return ERR_PTR(-ENODEV); raw_edid = drm_get_edid(connector, hdata->ddc_port->adapter); - if (raw_edid) { - hdata->dvi_mode = !drm_detect_hdmi_monitor(raw_edid); - memcpy(edid, raw_edid, min((1 + raw_edid->extensions) - * EDID_LENGTH, len)); - DRM_DEBUG_KMS("%s : width[%d] x height[%d]\n", - (hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"), - raw_edid->width_cm, raw_edid->height_cm); - kfree(raw_edid); - } else { - return -ENODEV; - } + if (!raw_edid) + return ERR_PTR(-ENODEV); - return 0; + hdata->dvi_mode = !drm_detect_hdmi_monitor(raw_edid); + DRM_DEBUG_KMS("%s : width[%d] x height[%d]\n", + (hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"), + raw_edid->width_cm, raw_edid->height_cm); + + return raw_edid; } static int hdmi_v13_check_timing(struct fb_videomode *check_timing) @@ -1652,16 +1645,16 @@ static void hdmi_conf_reset(struct hdmi_context *hdata) /* resetting HDMI core */ hdmi_reg_writemask(hdata, reg, 0, HDMI_CORE_SW_RSTOUT); - mdelay(10); + usleep_range(10000, 12000); hdmi_reg_writemask(hdata, reg, ~0, HDMI_CORE_SW_RSTOUT); - mdelay(10); + usleep_range(10000, 12000); } static void hdmi_conf_init(struct hdmi_context *hdata) { struct hdmi_infoframe infoframe; - /* disable HPD interrupts */ + /* disable HPD interrupts from HDMI IP block, use GPIO instead */ hdmi_reg_writemask(hdata, HDMI_INTC_CON, 0, HDMI_INTC_EN_GLOBAL | HDMI_INTC_EN_HPD_PLUG | HDMI_INTC_EN_HPD_UNPLUG); @@ -1779,7 +1772,7 @@ static void hdmi_v13_timing_apply(struct hdmi_context *hdata) u32 val = hdmi_reg_read(hdata, HDMI_V13_PHY_STATUS); if (val & HDMI_PHY_STATUS_READY) break; - mdelay(1); + usleep_range(1000, 2000); } /* steady state not achieved */ if (tries == 0) { @@ -1946,7 +1939,7 @@ static void hdmi_v14_timing_apply(struct hdmi_context *hdata) u32 val = hdmi_reg_read(hdata, HDMI_PHY_STATUS_0); if (val & HDMI_PHY_STATUS_READY) break; - mdelay(1); + usleep_range(1000, 2000); } /* steady state not achieved */ if (tries == 0) { @@ -1998,9 +1991,9 @@ static void hdmiphy_conf_reset(struct hdmi_context *hdata) /* reset hdmiphy */ hdmi_reg_writemask(hdata, reg, ~0, HDMI_PHY_SW_RSTOUT); - mdelay(10); + usleep_range(10000, 12000); hdmi_reg_writemask(hdata, reg, 0, HDMI_PHY_SW_RSTOUT); - mdelay(10); + usleep_range(10000, 12000); } static void hdmiphy_poweron(struct hdmi_context *hdata) @@ -2048,7 +2041,7 @@ static void hdmiphy_conf_apply(struct hdmi_context *hdata) return; } - mdelay(10); + usleep_range(10000, 12000); /* operation mode */ operation[0] = 0x1f; @@ -2170,6 +2163,13 @@ static void hdmi_commit(void *ctx) DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__); + mutex_lock(&hdata->hdmi_mutex); + if (!hdata->powered) { + mutex_unlock(&hdata->hdmi_mutex); + return; + } + mutex_unlock(&hdata->hdmi_mutex); + hdmi_conf_apply(hdata); } @@ -2265,7 +2265,7 @@ static struct exynos_hdmi_ops hdmi_ops = { .dpms = hdmi_dpms, }; -static irqreturn_t hdmi_external_irq_thread(int irq, void *arg) +static irqreturn_t hdmi_irq_thread(int irq, void *arg) { struct exynos_drm_hdmi_context *ctx = arg; struct hdmi_context *hdata = ctx->ctx; @@ -2280,31 +2280,6 @@ static irqreturn_t hdmi_external_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -static irqreturn_t hdmi_internal_irq_thread(int irq, void *arg) -{ - struct exynos_drm_hdmi_context *ctx = arg; - struct hdmi_context *hdata = ctx->ctx; - u32 intc_flag; - - intc_flag = hdmi_reg_read(hdata, HDMI_INTC_FLAG); - /* clearing flags for HPD plug/unplug */ - if (intc_flag & HDMI_INTC_FLAG_HPD_UNPLUG) { - DRM_DEBUG_KMS("unplugged\n"); - hdmi_reg_writemask(hdata, HDMI_INTC_FLAG, ~0, - HDMI_INTC_FLAG_HPD_UNPLUG); - } - if (intc_flag & HDMI_INTC_FLAG_HPD_PLUG) { - DRM_DEBUG_KMS("plugged\n"); - hdmi_reg_writemask(hdata, HDMI_INTC_FLAG, ~0, - HDMI_INTC_FLAG_HPD_PLUG); - } - - if (ctx->drm_dev) - drm_helper_hpd_irq_event(ctx->drm_dev); - - return IRQ_HANDLED; -} - static int hdmi_resources_init(struct hdmi_context *hdata) { struct device *dev = hdata->dev; @@ -2555,39 +2530,24 @@ static int hdmi_probe(struct platform_device *pdev) hdata->hdmiphy_port = hdmi_hdmiphy; - hdata->external_irq = gpio_to_irq(hdata->hpd_gpio); - if (hdata->external_irq < 0) { - DRM_ERROR("failed to get GPIO external irq\n"); - ret = hdata->external_irq; - goto err_hdmiphy; - } - - hdata->internal_irq = platform_get_irq(pdev, 0); - if (hdata->internal_irq < 0) { - DRM_ERROR("failed to get platform internal irq\n"); - ret = hdata->internal_irq; + hdata->irq = gpio_to_irq(hdata->hpd_gpio); + if (hdata->irq < 0) { + DRM_ERROR("failed to get GPIO irq\n"); + ret = hdata->irq; goto err_hdmiphy; } hdata->hpd = gpio_get_value(hdata->hpd_gpio); - ret = request_threaded_irq(hdata->external_irq, NULL, - hdmi_external_irq_thread, IRQF_TRIGGER_RISING | + ret = request_threaded_irq(hdata->irq, NULL, + hdmi_irq_thread, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - "hdmi_external", drm_hdmi_ctx); + "hdmi", drm_hdmi_ctx); if (ret) { - DRM_ERROR("failed to register hdmi external interrupt\n"); + DRM_ERROR("failed to register hdmi interrupt\n"); goto err_hdmiphy; } - ret = request_threaded_irq(hdata->internal_irq, NULL, - hdmi_internal_irq_thread, IRQF_ONESHOT, - "hdmi_internal", drm_hdmi_ctx); - if (ret) { - DRM_ERROR("failed to register hdmi internal interrupt\n"); - goto err_free_irq; - } - /* Attach HDMI Driver to common hdmi. */ exynos_hdmi_drv_attach(drm_hdmi_ctx); @@ -2598,8 +2558,6 @@ static int hdmi_probe(struct platform_device *pdev) return 0; -err_free_irq: - free_irq(hdata->external_irq, drm_hdmi_ctx); err_hdmiphy: i2c_del_driver(&hdmiphy_driver); err_ddc: @@ -2617,8 +2575,7 @@ static int hdmi_remove(struct platform_device *pdev) pm_runtime_disable(dev); - free_irq(hdata->internal_irq, hdata); - free_irq(hdata->external_irq, hdata); + free_irq(hdata->irq, hdata); /* hdmiphy i2c driver */ @@ -2637,8 +2594,7 @@ static int hdmi_suspend(struct device *dev) DRM_DEBUG_KMS("[%d] %s\n", __LINE__, __func__); - disable_irq(hdata->internal_irq); - disable_irq(hdata->external_irq); + disable_irq(hdata->irq); hdata->hpd = false; if (ctx->drm_dev) @@ -2663,8 +2619,7 @@ static int hdmi_resume(struct device *dev) hdata->hpd = gpio_get_value(hdata->hpd_gpio); - enable_irq(hdata->external_irq); - enable_irq(hdata->internal_irq); + enable_irq(hdata->irq); if (!pm_runtime_suspended(dev)) { DRM_DEBUG_KMS("%s : Already resumed\n", __func__); diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index c187ea3..c414584 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -600,7 +600,7 @@ static void vp_win_reset(struct mixer_context *ctx) /* waiting until VP_SRESET_PROCESSING is 0 */ if (~vp_reg_read(res, VP_SRESET) & VP_SRESET_PROCESSING) break; - mdelay(10); + usleep_range(10000, 12000); } WARN(tries == 0, "failed to reset Video Processor\n"); } @@ -776,6 +776,13 @@ static void mixer_win_commit(void *ctx, int win) DRM_DEBUG_KMS("[%d] %s, win: %d\n", __LINE__, __func__, win); + mutex_lock(&mixer_ctx->mixer_mutex); + if (!mixer_ctx->powered) { + mutex_unlock(&mixer_ctx->mixer_mutex); + return; + } + mutex_unlock(&mixer_ctx->mixer_mutex); + if (win > 1 && mixer_ctx->vp_enabled) vp_video_buffer(mixer_ctx, win); else diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 7944d3015..9d4a2c2 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -30,6 +30,7 @@ #include <linux/debugfs.h> #include <linux/slab.h> #include <linux/export.h> +#include <generated/utsrelease.h> #include <drm/drmP.h> #include "intel_drv.h" #include "intel_ringbuffer.h" @@ -690,6 +691,7 @@ static int i915_error_state(struct seq_file *m, void *unused) seq_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec, error->time.tv_usec); + seq_printf(m, "Kernel: " UTS_RELEASE); seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device); seq_printf(m, "EIR: 0x%08x\n", error->eir); seq_printf(m, "IER: 0x%08x\n", error->ier); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b401788..59afb7e 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -533,6 +533,7 @@ #define MI_MODE 0x0209c # define VS_TIMER_DISPATCH (1 << 6) # define MI_FLUSH_ENABLE (1 << 12) +# define ASYNC_FLIP_PERF_DISABLE (1 << 14) #define GEN6_GT_MODE 0x20d0 #define GEN6_GT_MODE_HI (1 << 9) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index ae253e0..42ff97d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -505,13 +505,25 @@ static int init_render_ring(struct intel_ring_buffer *ring) struct drm_i915_private *dev_priv = dev->dev_private; int ret = init_ring_common(ring); - if (INTEL_INFO(dev)->gen > 3) { + if (INTEL_INFO(dev)->gen > 3) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH)); - if (IS_GEN7(dev)) - I915_WRITE(GFX_MODE_GEN7, - _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) | - _MASKED_BIT_ENABLE(GFX_REPLAY_MODE)); - } + + /* We need to disable the AsyncFlip performance optimisations in order + * to use MI_WAIT_FOR_EVENT within the CS. It should already be + * programmed to '1' on all products. + */ + if (INTEL_INFO(dev)->gen >= 6) + I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE)); + + /* Required for the hardware to program scanline values for waiting */ + if (INTEL_INFO(dev)->gen == 6) + I915_WRITE(GFX_MODE, + _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_ALWAYS)); + + if (IS_GEN7(dev)) + I915_WRITE(GFX_MODE_GEN7, + _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) | + _MASKED_BIT_ENABLE(GFX_REPLAY_MODE)); if (INTEL_INFO(dev)->gen >= 5) { ret = init_pipe_control(ring); diff --git a/drivers/gpu/drm/nouveau/core/core/falcon.c b/drivers/gpu/drm/nouveau/core/core/falcon.c index 6b0843c..e05c157 100644 --- a/drivers/gpu/drm/nouveau/core/core/falcon.c +++ b/drivers/gpu/drm/nouveau/core/core/falcon.c @@ -73,8 +73,11 @@ _nouveau_falcon_init(struct nouveau_object *object) nv_debug(falcon, "data limit: %d\n", falcon->data.limit); /* wait for 'uc halted' to be signalled before continuing */ - if (falcon->secret) { - nv_wait(falcon, 0x008, 0x00000010, 0x00000010); + if (falcon->secret && falcon->version < 4) { + if (!falcon->version) + nv_wait(falcon, 0x008, 0x00000010, 0x00000010); + else + nv_wait(falcon, 0x180, 0x80000000, 0); nv_wo32(falcon, 0x004, 0x00000010); } diff --git a/drivers/gpu/drm/nouveau/core/core/subdev.c b/drivers/gpu/drm/nouveau/core/core/subdev.c index f74c30a..48f0637 100644 --- a/drivers/gpu/drm/nouveau/core/core/subdev.c +++ b/drivers/gpu/drm/nouveau/core/core/subdev.c @@ -99,7 +99,7 @@ nouveau_subdev_create_(struct nouveau_object *parent, if (ret) return ret; - mutex_init(&subdev->mutex); + __mutex_init(&subdev->mutex, subname, &oclass->lock_class_key); subdev->name = subname; if (parent) { diff --git a/drivers/gpu/drm/nouveau/core/include/core/object.h b/drivers/gpu/drm/nouveau/core/include/core/object.h index 5982935..106bb19 100644 --- a/drivers/gpu/drm/nouveau/core/include/core/object.h +++ b/drivers/gpu/drm/nouveau/core/include/core/object.h @@ -50,10 +50,13 @@ int nouveau_object_fini(struct nouveau_object *, bool suspend); extern struct nouveau_ofuncs nouveau_object_ofuncs; +/* Don't allocate dynamically, because lockdep needs lock_class_keys to be in + * ".data". */ struct nouveau_oclass { u32 handle; - struct nouveau_ofuncs *ofuncs; - struct nouveau_omthds *omthds; + struct nouveau_ofuncs * const ofuncs; + struct nouveau_omthds * const omthds; + struct lock_class_key lock_class_key; }; #define nv_oclass(o) nv_object(o)->oclass diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/base.c b/drivers/gpu/drm/nouveau/core/subdev/fb/base.c index d6d1600..d62045f 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/fb/base.c +++ b/drivers/gpu/drm/nouveau/core/subdev/fb/base.c @@ -86,8 +86,8 @@ nouveau_fb_preinit(struct nouveau_fb *pfb) return ret; } - if (!nouveau_mm_initialised(&pfb->tags) && tags) { - ret = nouveau_mm_init(&pfb->tags, 0, ++tags, 1); + if (!nouveau_mm_initialised(&pfb->tags)) { + ret = nouveau_mm_init(&pfb->tags, 0, tags ? ++tags : 0, 1); if (ret) return ret; } diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c index 487cb8c..eac236e 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c +++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c @@ -99,7 +99,7 @@ nv50_fb_vram_init(struct nouveau_fb *pfb) struct nouveau_bios *bios = nouveau_bios(device); const u32 rsvd_head = ( 256 * 1024) >> 12; /* vga memory */ const u32 rsvd_tail = (1024 * 1024) >> 12; /* vbios etc */ - u32 size; + u32 size, tags = 0; int ret; pfb->ram.size = nv_rd32(pfb, 0x10020c); @@ -140,10 +140,11 @@ nv50_fb_vram_init(struct nouveau_fb *pfb) return ret; pfb->ram.ranks = (nv_rd32(pfb, 0x100200) & 0x4) ? 2 : 1; + tags = nv_rd32(pfb, 0x100320); break; } - return nv_rd32(pfb, 0x100320); + return tags; } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 69d7b1d..1699a90 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -28,6 +28,7 @@ */ #include <core/engine.h> +#include <linux/swiotlb.h> #include <subdev/fb.h> #include <subdev/vm.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 8b090f1..5e7aef2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -245,6 +245,8 @@ static int nouveau_drm_probe(struct pci_dev *pdev, return 0; } +static struct lock_class_key drm_client_lock_class_key; + static int nouveau_drm_load(struct drm_device *dev, unsigned long flags) { @@ -256,6 +258,7 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) ret = nouveau_cli_create(pdev, "DRM", sizeof(*drm), (void**)&drm); if (ret) return ret; + lockdep_set_class(&drm->client.mutex, &drm_client_lock_class_key); dev->dev_private = drm; drm->dev = dev; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 4d0e60a..a2d478e 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -1313,14 +1313,18 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav if (!(tmp & EVERGREEN_CRTC_BLANK_DATA_EN)) { radeon_wait_for_vblank(rdev, i); tmp |= EVERGREEN_CRTC_BLANK_DATA_EN; + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } } else { tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); if (!(tmp & EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE)) { radeon_wait_for_vblank(rdev, i); tmp |= EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE; + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } } /* wait for the next frame */ @@ -1345,6 +1349,8 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav blackout &= ~BLACKOUT_MODE_MASK; WREG32(MC_SHARED_BLACKOUT_CNTL, blackout | 1); } + /* wait for the MC to settle */ + udelay(100); } void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save) @@ -1378,11 +1384,15 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s if (ASIC_IS_DCE6(rdev)) { tmp = RREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i]); tmp |= EVERGREEN_CRTC_BLANK_DATA_EN; + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } else { tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); tmp &= ~EVERGREEN_CRTC_DISP_READ_REQUEST_DISABLE; + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); WREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i], tmp); + WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0); } /* wait for the next frame */ frame_count = radeon_get_vblank_counter(rdev, i); @@ -2036,9 +2046,20 @@ static void evergreen_gpu_init(struct radeon_device *rdev) WREG32(HDP_ADDR_CONFIG, gb_addr_config); WREG32(DMA_TILING_CONFIG, gb_addr_config); - tmp = gb_addr_config & NUM_PIPES_MASK; - tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends, - EVERGREEN_MAX_BACKENDS, disabled_rb_mask); + if ((rdev->config.evergreen.max_backends == 1) && + (rdev->flags & RADEON_IS_IGP)) { + if ((disabled_rb_mask & 3) == 1) { + /* RB0 disabled, RB1 enabled */ + tmp = 0x11111111; + } else { + /* RB1 disabled, RB0 enabled */ + tmp = 0x00000000; + } + } else { + tmp = gb_addr_config & NUM_PIPES_MASK; + tmp = r6xx_remap_render_backend(rdev, tmp, rdev->config.evergreen.max_backends, + EVERGREEN_MAX_BACKENDS, disabled_rb_mask); + } WREG32(GB_BACKEND_MAP, tmp); WREG32(CGTS_SYS_TCC_DISABLE, 0); diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 7a44566..ee4cff5 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -2909,14 +2909,14 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) return -EINVAL; } if (tiled) { - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8); p->idx += count + 7; } else { - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff; @@ -2954,12 +2954,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n"); return -EINVAL; } - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; - dst2_offset = ib[idx+2]; + dst2_offset = radeon_get_ib_value(p, idx+2); dst2_offset <<= 8; - src_offset = ib[idx+8]; - src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+8); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n", src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); @@ -3014,12 +3014,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; - dst2_offset = ib[idx+2]; + dst2_offset = radeon_get_ib_value(p, idx+2); dst2_offset <<= 8; - src_offset = ib[idx+8]; - src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+8); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n", src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); @@ -3046,22 +3046,22 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) /* detile bit */ if (idx_value & (1 << 31)) { /* tiled src, linear dst */ - src_offset = ib[idx+1]; + src_offset = radeon_get_ib_value(p, idx+1); src_offset <<= 8; ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8); - dst_offset = ib[idx+7]; - dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+7); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32; ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff; } else { /* linear src, tiled dst */ - src_offset = ib[idx+7]; - src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+7); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32; ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff; - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8); } @@ -3098,12 +3098,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; - dst2_offset = ib[idx+2]; + dst2_offset = radeon_get_ib_value(p, idx+2); dst2_offset <<= 8; - src_offset = ib[idx+8]; - src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+8); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n", src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); @@ -3135,22 +3135,22 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) /* detile bit */ if (idx_value & (1 << 31)) { /* tiled src, linear dst */ - src_offset = ib[idx+1]; + src_offset = radeon_get_ib_value(p, idx+1); src_offset <<= 8; ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8); - dst_offset = ib[idx+7]; - dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+7); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32; ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff; } else { /* linear src, tiled dst */ - src_offset = ib[idx+7]; - src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+7); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32; ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff; - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8); } @@ -3176,10 +3176,10 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) switch (misc) { case 0: /* L2L, byte */ - src_offset = ib[idx+2]; - src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32; - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+2); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32; if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) { dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n", src_offset + count, radeon_bo_size(src_reloc->robj)); @@ -3216,12 +3216,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n"); return -EINVAL; } - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+4] & 0xff)) << 32; - dst2_offset = ib[idx+2]; - dst2_offset |= ((u64)(ib[idx+5] & 0xff)) << 32; - src_offset = ib[idx+3]; - src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; + dst2_offset = radeon_get_ib_value(p, idx+2); + dst2_offset |= ((u64)(radeon_get_ib_value(p, idx+5) & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+3); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n", src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); @@ -3251,10 +3251,10 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) } } else { /* L2L, dw */ - src_offset = ib[idx+2]; - src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32; - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+2); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32; if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) { dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n", src_offset + (count * 4), radeon_bo_size(src_reloc->robj)); @@ -3279,8 +3279,8 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("bad DMA_PACKET_CONSTANT_FILL\n"); return -EINVAL; } - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+3] & 0x00ff0000)) << 16; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16; if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n", dst_offset, radeon_bo_size(dst_reloc->robj)); diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 59acabb..835992d 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1216,7 +1216,7 @@ void cayman_dma_stop(struct radeon_device *rdev) int cayman_dma_resume(struct radeon_device *rdev) { struct radeon_ring *ring; - u32 rb_cntl, dma_cntl; + u32 rb_cntl, dma_cntl, ib_cntl; u32 rb_bufsz; u32 reg_offset, wb_offset; int i, r; @@ -1265,7 +1265,11 @@ int cayman_dma_resume(struct radeon_device *rdev) WREG32(DMA_RB_BASE + reg_offset, ring->gpu_addr >> 8); /* enable DMA IBs */ - WREG32(DMA_IB_CNTL + reg_offset, DMA_IB_ENABLE | CMD_VMID_FORCE); + ib_cntl = DMA_IB_ENABLE | CMD_VMID_FORCE; +#ifdef __BIG_ENDIAN + ib_cntl |= DMA_IB_SWAP_ENABLE; +#endif + WREG32(DMA_IB_CNTL + reg_offset, ib_cntl); dma_cntl = RREG32(DMA_CNTL + reg_offset); dma_cntl &= ~CTXEMPTY_INT_ENABLE; diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 3cb9d60..becb03e 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -1462,12 +1462,15 @@ u32 r6xx_remap_render_backend(struct radeon_device *rdev, u32 disabled_rb_mask) { u32 rendering_pipe_num, rb_num_width, req_rb_num; - u32 pipe_rb_ratio, pipe_rb_remain; + u32 pipe_rb_ratio, pipe_rb_remain, tmp; u32 data = 0, mask = 1 << (max_rb_num - 1); unsigned i, j; /* mask out the RBs that don't exist on that asic */ - disabled_rb_mask |= (0xff << max_rb_num) & 0xff; + tmp = disabled_rb_mask | ((0xff << max_rb_num) & 0xff); + /* make sure at least one RB is available */ + if ((tmp & 0xff) != 0xff) + disabled_rb_mask = tmp; rendering_pipe_num = 1 << tiling_pipe_num; req_rb_num = total_max_rb_num - r600_count_pipe_bits(disabled_rb_mask); @@ -2313,7 +2316,7 @@ void r600_dma_stop(struct radeon_device *rdev) int r600_dma_resume(struct radeon_device *rdev) { struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_DMA_INDEX]; - u32 rb_cntl, dma_cntl; + u32 rb_cntl, dma_cntl, ib_cntl; u32 rb_bufsz; int r; @@ -2353,7 +2356,11 @@ int r600_dma_resume(struct radeon_device *rdev) WREG32(DMA_RB_BASE, ring->gpu_addr >> 8); /* enable DMA IBs */ - WREG32(DMA_IB_CNTL, DMA_IB_ENABLE); + ib_cntl = DMA_IB_ENABLE; +#ifdef __BIG_ENDIAN + ib_cntl |= DMA_IB_SWAP_ENABLE; +#endif + WREG32(DMA_IB_CNTL, ib_cntl); dma_cntl = RREG32(DMA_CNTL); dma_cntl &= ~CTXEMPTY_INT_ENABLE; diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 69ec24a..9b2512b 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -2623,14 +2623,14 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) return -EINVAL; } if (tiled) { - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8); p->idx += count + 5; } else { - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff; @@ -2658,32 +2658,32 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) /* detile bit */ if (idx_value & (1 << 31)) { /* tiled src, linear dst */ - src_offset = ib[idx+1]; + src_offset = radeon_get_ib_value(p, idx+1); src_offset <<= 8; ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8); - dst_offset = ib[idx+5]; - dst_offset |= ((u64)(ib[idx+6] & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+5); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32; ib[idx+5] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+6] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff; } else { /* linear src, tiled dst */ - src_offset = ib[idx+5]; - src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+5); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32; ib[idx+5] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff; - dst_offset = ib[idx+1]; + dst_offset = radeon_get_ib_value(p, idx+1); dst_offset <<= 8; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8); } p->idx += 7; } else { if (p->family >= CHIP_RV770) { - src_offset = ib[idx+2]; - src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32; - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32; + src_offset = radeon_get_ib_value(p, idx+2); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc); @@ -2691,10 +2691,10 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff; p->idx += 5; } else { - src_offset = ib[idx+2]; - src_offset |= ((u64)(ib[idx+3] & 0xff)) << 32; - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+3] & 0xff0000)) << 16; + src_offset = radeon_get_ib_value(p, idx+2); + src_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff0000)) << 16; ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc); ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc); @@ -2724,8 +2724,8 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("bad DMA_PACKET_WRITE\n"); return -EINVAL; } - dst_offset = ib[idx+1]; - dst_offset |= ((u64)(ib[idx+3] & 0x00ff0000)) << 16; + dst_offset = radeon_get_ib_value(p, idx+1); + dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16; if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) { dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n", dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj)); diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 9056faf..0b202c0 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -1445,7 +1445,7 @@ static struct radeon_asic cayman_asic = { .vm = { .init = &cayman_vm_init, .fini = &cayman_vm_fini, - .pt_ring_index = R600_RING_TYPE_DMA_INDEX, + .pt_ring_index = RADEON_RING_TYPE_GFX_INDEX, .set_page = &cayman_vm_set_page, }, .ring = { @@ -1572,7 +1572,7 @@ static struct radeon_asic trinity_asic = { .vm = { .init = &cayman_vm_init, .fini = &cayman_vm_fini, - .pt_ring_index = R600_RING_TYPE_DMA_INDEX, + .pt_ring_index = RADEON_RING_TYPE_GFX_INDEX, .set_page = &cayman_vm_set_page, }, .ring = { @@ -1699,7 +1699,7 @@ static struct radeon_asic si_asic = { .vm = { .init = &si_vm_init, .fini = &si_vm_fini, - .pt_ring_index = R600_RING_TYPE_DMA_INDEX, + .pt_ring_index = RADEON_RING_TYPE_GFX_INDEX, .set_page = &si_vm_set_page, }, .ring = { diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 33a56a0..3e403bd 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -2470,6 +2470,14 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev) 1), ATOM_DEVICE_CRT1_SUPPORT); } + /* RV100 board with external TDMS bit mis-set. + * Actually uses internal TMDS, clear the bit. + */ + if (dev->pdev->device == 0x5159 && + dev->pdev->subsystem_vendor == 0x1014 && + dev->pdev->subsystem_device == 0x029A) { + tmp &= ~(1 << 4); + } if ((tmp >> 4) & 0x1) { devices |= ATOM_DEVICE_DFP2_SUPPORT; radeon_add_legacy_encoder(dev, diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 469661f..5407459 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -286,6 +286,8 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) p->chunks[p->chunk_ib_idx].kpage[1] == NULL) { kfree(p->chunks[p->chunk_ib_idx].kpage[0]); kfree(p->chunks[p->chunk_ib_idx].kpage[1]); + p->chunks[p->chunk_ib_idx].kpage[0] = NULL; + p->chunks[p->chunk_ib_idx].kpage[1] = NULL; return -ENOMEM; } } diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c index ad6df62..0d67674 100644 --- a/drivers/gpu/drm/radeon/radeon_cursor.c +++ b/drivers/gpu/drm/radeon/radeon_cursor.c @@ -241,7 +241,8 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc, y = 0; } - if (ASIC_IS_AVIVO(rdev)) { + /* fixed on DCE6 and newer */ + if (ASIC_IS_AVIVO(rdev) && !ASIC_IS_DCE6(rdev)) { int i = 0; struct drm_crtc *crtc_p; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index edfc54e..0d6562b 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -429,7 +429,8 @@ bool radeon_card_posted(struct radeon_device *rdev) { uint32_t reg; - if (efi_enabled && rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) + if (efi_enabled(EFI_BOOT) && + rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) return false; /* first check CRTCs */ diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 1da2386..05c96fa 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1115,14 +1115,16 @@ radeon_user_framebuffer_create(struct drm_device *dev, } radeon_fb = kzalloc(sizeof(*radeon_fb), GFP_KERNEL); - if (radeon_fb == NULL) + if (radeon_fb == NULL) { + drm_gem_object_unreference_unlocked(obj); return ERR_PTR(-ENOMEM); + } ret = radeon_framebuffer_init(dev, radeon_fb, mode_cmd, obj); if (ret) { kfree(radeon_fb); drm_gem_object_unreference_unlocked(obj); - return NULL; + return ERR_PTR(ret); } return &radeon_fb->base; diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 2430d80..cd72062 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -377,6 +377,9 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi { int r; + /* make sure we aren't trying to allocate more space than there is on the ring */ + if (ndw > (ring->ring_size / 4)) + return -ENOMEM; /* Align requested size with padding so unlock_commit can * pad safely */ ndw = (ndw + ring->align_mask) & ~ring->align_mask; diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 1d8ff2f..93f760e 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -38,6 +38,7 @@ #include <drm/radeon_drm.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/swiotlb.h> #include "radeon_reg.h" #include "radeon.h" diff --git a/drivers/gpu/drm/radeon/reg_srcs/cayman b/drivers/gpu/drm/radeon/reg_srcs/cayman index 0f656b1..a072fa8 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/cayman +++ b/drivers/gpu/drm/radeon/reg_srcs/cayman @@ -1,5 +1,6 @@ cayman 0x9400 0x0000802C GRBM_GFX_INDEX +0x00008040 WAIT_UNTIL 0x000084FC CP_STRMOUT_CNTL 0x000085F0 CP_COHER_CNTL 0x000085F4 CP_COHER_SIZE diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 2bb6d0e..435ed35 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -336,6 +336,8 @@ void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save) WREG32(R600_CITF_CNTL, blackout); } } + /* wait for the MC to settle */ + udelay(100); } void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 44420fc..8be35c8 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -429,7 +429,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, struct ttm_bo_device *bdev = bo->bdev; struct ttm_bo_driver *driver = bdev->driver; - fbo = kzalloc(sizeof(*fbo), GFP_KERNEL); + fbo = kmalloc(sizeof(*fbo), GFP_KERNEL); if (!fbo) return -ENOMEM; @@ -448,7 +448,12 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, fbo->vm_node = NULL; atomic_set(&fbo->cpu_writers, 0); - fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj); + spin_lock(&bdev->fence_lock); + if (bo->sync_obj) + fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj); + else + fbo->sync_obj = NULL; + spin_unlock(&bdev->fence_lock); kref_init(&fbo->list_kref); kref_init(&fbo->kref); fbo->destroy = &ttm_transfered_destroy; @@ -661,13 +666,11 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, */ set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags); - - /* ttm_buffer_object_transfer accesses bo->sync_obj */ - ret = ttm_buffer_object_transfer(bo, &ghost_obj); spin_unlock(&bdev->fence_lock); if (tmp_obj) driver->sync_obj_unref(&tmp_obj); + ret = ttm_buffer_object_transfer(bo, &ghost_obj); if (ret) return ret; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 4dfa605..34e2547 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -306,6 +306,9 @@ #define USB_VENDOR_ID_EZKEY 0x0518 #define USB_DEVICE_ID_BTC_8193 0x0002 +#define USB_VENDOR_ID_FORMOSA 0x147a +#define USB_DEVICE_ID_FORMOSA_IR_RECEIVER 0xe03e + #define USB_VENDOR_ID_FREESCALE 0x15A2 #define USB_DEVICE_ID_FREESCALE_MX28 0x004F diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 12e4fdc..e766b56 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -540,13 +540,24 @@ static int i2c_hid_output_raw_report(struct hid_device *hid, __u8 *buf, { struct i2c_client *client = hid->driver_data; int report_id = buf[0]; + int ret; if (report_type == HID_INPUT_REPORT) return -EINVAL; - return i2c_hid_set_report(client, + if (report_id) { + buf++; + count--; + } + + ret = i2c_hid_set_report(client, report_type == HID_FEATURE_REPORT ? 0x03 : 0x02, report_id, buf, count); + + if (report_id && ret >= 0) + ret++; /* add report_id to the number of transfered bytes */ + + return ret; } static int i2c_hid_parse(struct hid_device *hid) diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index ac9e352..e0e6abf 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -70,6 +70,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, { USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET }, { USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index b38ef6d..64630f1 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -2,7 +2,7 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" - depends on X86 && ACPI && PCI + depends on X86 && ACPI && PCI && X86_LOCAL_APIC help Select this option to run Linux as a Hyper-V client operating system. diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 4850d03..3527509 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -263,20 +263,15 @@ static void remove_qp(struct qib_ibdev *dev, struct qib_qp *qp) struct qib_qp __rcu **qpp; qpp = &dev->qp_table[n]; - q = rcu_dereference_protected(*qpp, - lockdep_is_held(&dev->qpt_lock)); - for (; q; qpp = &q->next) { + for (; (q = rcu_dereference_protected(*qpp, + lockdep_is_held(&dev->qpt_lock))) != NULL; + qpp = &q->next) if (q == qp) { atomic_dec(&qp->refcount); *qpp = qp->next; rcu_assign_pointer(qp->next, NULL); - q = rcu_dereference_protected(*qpp, - lockdep_is_held(&dev->qpt_lock)); break; } - q = rcu_dereference_protected(*qpp, - lockdep_is_held(&dev->qpt_lock)); - } } spin_unlock_irqrestore(&dev->qpt_lock, flags); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 03103d2..67b0c1d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -741,6 +741,9 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ tx_req->mapping = addr; + skb_orphan(skb); + skb_dst_drop(skb); + rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), addr, skb->len); if (unlikely(rc)) { @@ -752,9 +755,6 @@ void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_ dev->trans_start = jiffies; ++tx->tx_head; - skb_orphan(skb); - skb_dst_drop(skb); - if (++priv->tx_outstanding == ipoib_sendq_size) { ipoib_dbg(priv, "TX ring 0x%x full, stopping kernel net queue\n", tx->qp->qp_num); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index a1bca70..2cfa76f 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -600,6 +600,9 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, netif_stop_queue(dev); } + skb_orphan(skb); + skb_dst_drop(skb); + rc = post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), address->ah, qpn, tx_req, phead, hlen); if (unlikely(rc)) { @@ -615,9 +618,6 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, address->last_send = priv->tx_head; ++priv->tx_head; - - skb_orphan(skb); - skb_dst_drop(skb); } if (unlikely(priv->tx_outstanding > MAX_SEND_CQE)) diff --git a/drivers/input/input.c b/drivers/input/input.c index ce01332f..c044699 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1785,12 +1785,13 @@ static void devm_input_device_release(struct device *dev, void *res) * its driver (or binding fails). Once managed input device is allocated, * it is ready to be set up and registered in the same fashion as regular * input device. There are no special devm_input_device_[un]register() - * variants, regular ones work with both managed and unmanaged devices. + * variants, regular ones work with both managed and unmanaged devices, + * should you need them. In most cases however, managed input device need + * not be explicitly unregistered or freed. * * NOTE: the owner device is set up as parent of input device and users * should not override it. */ - struct input_dev *devm_input_allocate_device(struct device *dev) { struct input_dev *input; @@ -2004,6 +2005,17 @@ static void devm_input_device_unregister(struct device *dev, void *res) * Once device has been successfully registered it can be unregistered * with input_unregister_device(); input_free_device() should not be * called in this case. + * + * Note that this function is also used to register managed input devices + * (ones allocated with devm_input_allocate_device()). Such managed input + * devices need not be explicitly unregistered or freed, their tear down + * is controlled by the devres infrastructure. It is also worth noting + * that tear down of managed input devices is internally a 2-step process: + * registered managed input device is first unregistered, but stays in + * memory and can still handle input_event() calls (although events will + * not be delivered anywhere). The freeing of managed input device will + * happen later, when devres stack is unwound to the point where device + * allocation was made. */ int input_register_device(struct input_dev *dev) { diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c index 358cd7e..7cd74e2 100644 --- a/drivers/input/joystick/analog.c +++ b/drivers/input/joystick/analog.c @@ -162,7 +162,7 @@ static unsigned int get_time_pit(void) #define GET_TIME(x) do { x = get_cycles(); } while (0) #define DELTA(x,y) ((y)-(x)) #define TIME_NAME "PCC" -#elif defined(CONFIG_MN10300) +#elif defined(CONFIG_MN10300) || defined(CONFIG_TILE) #define GET_TIME(x) do { x = get_cycles(); } while (0) #define DELTA(x, y) ((x) - (y)) #define TIME_NAME "TSC" diff --git a/drivers/input/keyboard/lm8323.c b/drivers/input/keyboard/lm8323.c index 93c8126..0de23f4 100644 --- a/drivers/input/keyboard/lm8323.c +++ b/drivers/input/keyboard/lm8323.c @@ -398,7 +398,7 @@ static irqreturn_t lm8323_irq(int irq, void *_lm) lm8323_configure(lm); } for (i = 0; i < LM8323_NUM_PWMS; i++) { - if (ints & (1 << (INT_PWM1 + i))) { + if (ints & (INT_PWM1 << i)) { dev_vdbg(&lm->client->dev, "pwm%d engine completed\n", i); pwm_done(&lm->pwm[i]); diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c index f92d34f..aaf23ae 100644 --- a/drivers/input/tablet/wacom_sys.c +++ b/drivers/input/tablet/wacom_sys.c @@ -553,10 +553,10 @@ static int wacom_set_device_mode(struct usb_interface *intf, int report_id, int if (!rep_data) return error; - rep_data[0] = report_id; - rep_data[1] = mode; - do { + rep_data[0] = report_id; + rep_data[1] = mode; + error = wacom_set_report(intf, WAC_HID_FEATURE_REPORT, report_id, rep_data, length, 1); if (error >= 0) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index c1c74e0..d33eaaf 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -4017,10 +4017,10 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count) index -= count - 1; + cfg->remapped = 1; irte_info = &cfg->irq_2_iommu; irte_info->sub_handle = devid; irte_info->irte_index = index; - irte_info->iommu = (void *)cfg; goto out; } @@ -4127,9 +4127,9 @@ static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, index = attr->ioapic_pin; /* Setup IRQ remapping info */ + cfg->remapped = 1; irte_info->sub_handle = devid; irte_info->irte_index = index; - irte_info->iommu = (void *)cfg; /* Setup IRTE for IOMMU */ irte.val = 0; @@ -4288,9 +4288,9 @@ static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq, devid = get_device_id(&pdev->dev); irte_info = &cfg->irq_2_iommu; + cfg->remapped = 1; irte_info->sub_handle = devid; irte_info->irte_index = index + offset; - irte_info->iommu = (void *)cfg; return 0; } @@ -4314,9 +4314,9 @@ static int setup_hpet_msi(unsigned int irq, unsigned int id) if (index < 0) return index; + cfg->remapped = 1; irte_info->sub_handle = devid; irte_info->irte_index = index; - irte_info->iommu = (void *)cfg; return 0; } diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 81837b0..faf10ba 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -975,6 +975,38 @@ static void __init free_iommu_all(void) } /* + * Family15h Model 10h-1fh erratum 746 (IOMMU Logging May Stall Translations) + * Workaround: + * BIOS should disable L2B micellaneous clock gating by setting + * L2_L2B_CK_GATE_CONTROL[CKGateL2BMiscDisable](D0F2xF4_x90[2]) = 1b + */ +static void __init amd_iommu_erratum_746_workaround(struct amd_iommu *iommu) +{ + u32 value; + + if ((boot_cpu_data.x86 != 0x15) || + (boot_cpu_data.x86_model < 0x10) || + (boot_cpu_data.x86_model > 0x1f)) + return; + + pci_write_config_dword(iommu->dev, 0xf0, 0x90); + pci_read_config_dword(iommu->dev, 0xf4, &value); + + if (value & BIT(2)) + return; + + /* Select NB indirect register 0x90 and enable writing */ + pci_write_config_dword(iommu->dev, 0xf0, 0x90 | (1 << 8)); + + pci_write_config_dword(iommu->dev, 0xf4, value | 0x4); + pr_info("AMD-Vi: Applying erratum 746 workaround for IOMMU at %s\n", + dev_name(&iommu->dev->dev)); + + /* Clear the enable writing bit */ + pci_write_config_dword(iommu->dev, 0xf0, 0x90); +} + +/* * This function clues the initialization function for one IOMMU * together and also allocates the command buffer and programs the * hardware. It does NOT enable the IOMMU. This is done afterwards. @@ -1172,6 +1204,8 @@ static int iommu_init_pci(struct amd_iommu *iommu) iommu->stored_l2[i] = iommu_read_l2(iommu, i); } + amd_iommu_erratum_746_workaround(iommu); + return pci_enable_device(iommu->dev); } diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 86e2f4a..174bb65 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -41,6 +41,8 @@ #include <asm/irq_remapping.h> #include <asm/iommu_table.h> +#include "irq_remapping.h" + /* No locks are needed as DMA remapping hardware unit * list is constructed at boot time and hotplug of * these units are not supported by the architecture. diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b9d0911..43d5c8b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -46,6 +46,8 @@ #include <asm/cacheflush.h> #include <asm/iommu.h> +#include "irq_remapping.h" + #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE @@ -4234,6 +4236,21 @@ static struct iommu_ops intel_iommu_ops = { .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; +static void quirk_iommu_g4x_gfx(struct pci_dev *dev) +{ + /* G4x/GM45 integrated gfx dmar support is totally busted. */ + printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n"); + dmar_map_gfx = 0; +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx); + static void quirk_iommu_rwbf(struct pci_dev *dev) { /* @@ -4242,12 +4259,6 @@ static void quirk_iommu_rwbf(struct pci_dev *dev) */ printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n"); rwbf_quirk = 1; - - /* https://bugzilla.redhat.com/show_bug.cgi?id=538163 */ - if (dev->revision == 0x07) { - printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n"); - dmar_map_gfx = 0; - } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf); diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index af8904d..f3b8f23 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -68,6 +68,7 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) { struct ir_table *table = iommu->ir_table; struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); u16 index, start_index; unsigned int mask = 0; unsigned long flags; @@ -115,6 +116,7 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count) for (i = index; i < index + count; i++) table->base[i].present = 1; + cfg->remapped = 1; irq_iommu->iommu = iommu; irq_iommu->irte_index = index; irq_iommu->sub_handle = 0; @@ -155,6 +157,7 @@ static int map_irq_to_irte_handle(int irq, u16 *sub_handle) static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle) { struct irq_2_iommu *irq_iommu = irq_2_iommu(irq); + struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; if (!irq_iommu) @@ -162,6 +165,7 @@ static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subha raw_spin_lock_irqsave(&irq_2_ir_lock, flags); + cfg->remapped = 1; irq_iommu->iommu = iommu; irq_iommu->irte_index = index; irq_iommu->sub_handle = subhandle; @@ -425,11 +429,22 @@ static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode) /* Enable interrupt-remapping */ iommu->gcmd |= DMA_GCMD_IRE; + iommu->gcmd &= ~DMA_GCMD_CFI; /* Block compatibility-format MSIs */ writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_IRES), sts); + /* + * With CFI clear in the Global Command register, we should be + * protected from dangerous (i.e. compatibility) interrupts + * regardless of x2apic status. Check just to be sure. + */ + if (sts & DMA_GSTS_CFIS) + WARN(1, KERN_WARNING + "Compatibility-format IRQs enabled despite intr remapping;\n" + "you are vulnerable to IRQ injection.\n"); + raw_spin_unlock_irqrestore(&iommu->register_lock, flags); } @@ -526,20 +541,24 @@ static int __init intel_irq_remapping_supported(void) static int __init intel_enable_irq_remapping(void) { struct dmar_drhd_unit *drhd; + bool x2apic_present; int setup = 0; int eim = 0; + x2apic_present = x2apic_supported(); + if (parse_ioapics_under_ir() != 1) { printk(KERN_INFO "Not enable interrupt remapping\n"); - return -1; + goto error; } - if (x2apic_supported()) { + if (x2apic_present) { eim = !dmar_x2apic_optout(); - WARN(!eim, KERN_WARNING - "Your BIOS is broken and requested that x2apic be disabled\n" - "This will leave your machine vulnerable to irq-injection attacks\n" - "Use 'intremap=no_x2apic_optout' to override BIOS request\n"); + if (!eim) + printk(KERN_WARNING + "Your BIOS is broken and requested that x2apic be disabled.\n" + "This will slightly decrease performance.\n" + "Use 'intremap=no_x2apic_optout' to override BIOS request.\n"); } for_each_drhd_unit(drhd) { @@ -578,7 +597,7 @@ static int __init intel_enable_irq_remapping(void) if (eim && !ecap_eim_support(iommu->ecap)) { printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, " " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap); - return -1; + goto error; } } @@ -594,7 +613,7 @@ static int __init intel_enable_irq_remapping(void) printk(KERN_ERR "DRHD %Lx: failed to enable queued, " " invalidation, ecap %Lx, ret %d\n", drhd->reg_base_addr, iommu->ecap, ret); - return -1; + goto error; } } @@ -617,6 +636,14 @@ static int __init intel_enable_irq_remapping(void) goto error; irq_remapping_enabled = 1; + + /* + * VT-d has a different layout for IO-APIC entries when + * interrupt remapping is enabled. So it needs a special routine + * to print IO-APIC entries for debugging purposes too. + */ + x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries; + pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic"); return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE; @@ -625,6 +652,11 @@ error: /* * handle error condition gracefully here! */ + + if (x2apic_present) + WARN(1, KERN_WARNING + "Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n"); + return -1; } diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index faf85d6..d56f8c1 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -1,11 +1,18 @@ +#include <linux/seq_file.h> +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/cpumask.h> #include <linux/errno.h> #include <linux/msi.h> +#include <linux/irq.h> +#include <linux/pci.h> #include <asm/hw_irq.h> #include <asm/irq_remapping.h> +#include <asm/processor.h> +#include <asm/x86_init.h> +#include <asm/apic.h> #include "irq_remapping.h" @@ -17,6 +24,152 @@ int no_x2apic_optout; static struct irq_remap_ops *remap_ops; +static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec); +static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, + int index, int sub_handle); +static int set_remapped_irq_affinity(struct irq_data *data, + const struct cpumask *mask, + bool force); + +static bool irq_remapped(struct irq_cfg *cfg) +{ + return (cfg->remapped == 1); +} + +static void irq_remapping_disable_io_apic(void) +{ + /* + * With interrupt-remapping, for now we will use virtual wire A + * mode, as virtual wire B is little complex (need to configure + * both IOAPIC RTE as well as interrupt-remapping table entry). + * As this gets called during crash dump, keep this simple for + * now. + */ + if (cpu_has_apic || apic_from_smp_config()) + disconnect_bsp_APIC(0); +} + +static int do_setup_msi_irqs(struct pci_dev *dev, int nvec) +{ + int node, ret, sub_handle, index = 0; + unsigned int irq; + struct msi_desc *msidesc; + + nvec = __roundup_pow_of_two(nvec); + + WARN_ON(!list_is_singular(&dev->msi_list)); + msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + WARN_ON(msidesc->irq); + WARN_ON(msidesc->msi_attrib.multiple); + + node = dev_to_node(&dev->dev); + irq = __create_irqs(get_nr_irqs_gsi(), nvec, node); + if (irq == 0) + return -ENOSPC; + + msidesc->msi_attrib.multiple = ilog2(nvec); + for (sub_handle = 0; sub_handle < nvec; sub_handle++) { + if (!sub_handle) { + index = msi_alloc_remapped_irq(dev, irq, nvec); + if (index < 0) { + ret = index; + goto error; + } + } else { + ret = msi_setup_remapped_irq(dev, irq + sub_handle, + index, sub_handle); + if (ret < 0) + goto error; + } + ret = setup_msi_irq(dev, msidesc, irq, sub_handle); + if (ret < 0) + goto error; + } + return 0; + +error: + destroy_irqs(irq, nvec); + + /* + * Restore altered MSI descriptor fields and prevent just destroyed + * IRQs from tearing down again in default_teardown_msi_irqs() + */ + msidesc->irq = 0; + msidesc->msi_attrib.multiple = 0; + + return ret; +} + +static int do_setup_msix_irqs(struct pci_dev *dev, int nvec) +{ + int node, ret, sub_handle, index = 0; + struct msi_desc *msidesc; + unsigned int irq; + + node = dev_to_node(&dev->dev); + irq = get_nr_irqs_gsi(); + sub_handle = 0; + + list_for_each_entry(msidesc, &dev->msi_list, list) { + + irq = create_irq_nr(irq, node); + if (irq == 0) + return -1; + + if (sub_handle == 0) + ret = index = msi_alloc_remapped_irq(dev, irq, nvec); + else + ret = msi_setup_remapped_irq(dev, irq, index, sub_handle); + + if (ret < 0) + goto error; + + ret = setup_msi_irq(dev, msidesc, irq, 0); + if (ret < 0) + goto error; + + sub_handle += 1; + irq += 1; + } + + return 0; + +error: + destroy_irq(irq); + return ret; +} + +static int irq_remapping_setup_msi_irqs(struct pci_dev *dev, + int nvec, int type) +{ + if (type == PCI_CAP_ID_MSI) + return do_setup_msi_irqs(dev, nvec); + else + return do_setup_msix_irqs(dev, nvec); +} + +void eoi_ioapic_pin_remapped(int apic, int pin, int vector) +{ + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + io_apic_eoi(apic, pin); +} + +static void __init irq_remapping_modify_x86_ops(void) +{ + x86_io_apic_ops.disable = irq_remapping_disable_io_apic; + x86_io_apic_ops.set_affinity = set_remapped_irq_affinity; + x86_io_apic_ops.setup_entry = setup_ioapic_remapped_entry; + x86_io_apic_ops.eoi_ioapic_pin = eoi_ioapic_pin_remapped; + x86_msi.setup_msi_irqs = irq_remapping_setup_msi_irqs; + x86_msi.setup_hpet_msi = setup_hpet_msi_remapped; + x86_msi.compose_msi_msg = compose_remapped_msi_msg; +} + static __init int setup_nointremap(char *str) { disable_irq_remap = 1; @@ -79,15 +232,24 @@ int __init irq_remapping_prepare(void) int __init irq_remapping_enable(void) { + int ret; + if (!remap_ops || !remap_ops->enable) return -ENODEV; - return remap_ops->enable(); + ret = remap_ops->enable(); + + if (irq_remapping_enabled) + irq_remapping_modify_x86_ops(); + + return ret; } void irq_remapping_disable(void) { - if (!remap_ops || !remap_ops->disable) + if (!irq_remapping_enabled || + !remap_ops || + !remap_ops->disable) return; remap_ops->disable(); @@ -95,7 +257,9 @@ void irq_remapping_disable(void) int irq_remapping_reenable(int mode) { - if (!remap_ops || !remap_ops->reenable) + if (!irq_remapping_enabled || + !remap_ops || + !remap_ops->reenable) return 0; return remap_ops->reenable(mode); @@ -103,6 +267,9 @@ int irq_remapping_reenable(int mode) int __init irq_remap_enable_fault_handling(void) { + if (!irq_remapping_enabled) + return 0; + if (!remap_ops || !remap_ops->enable_faulting) return -ENODEV; @@ -133,23 +300,28 @@ int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, void free_remapped_irq(int irq) { + struct irq_cfg *cfg = irq_get_chip_data(irq); + if (!remap_ops || !remap_ops->free_irq) return; - remap_ops->free_irq(irq); + if (irq_remapped(cfg)) + remap_ops->free_irq(irq); } void compose_remapped_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, struct msi_msg *msg, u8 hpet_id) { - if (!remap_ops || !remap_ops->compose_msi_msg) - return; + struct irq_cfg *cfg = irq_get_chip_data(irq); - remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id); + if (!irq_remapped(cfg)) + native_compose_msi_msg(pdev, irq, dest, msg, hpet_id); + else if (remap_ops && remap_ops->compose_msi_msg) + remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id); } -int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) +static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) { if (!remap_ops || !remap_ops->msi_alloc_irq) return -ENODEV; @@ -157,8 +329,8 @@ int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec) return remap_ops->msi_alloc_irq(pdev, irq, nvec); } -int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, - int index, int sub_handle) +static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq, + int index, int sub_handle) { if (!remap_ops || !remap_ops->msi_setup_irq) return -ENODEV; @@ -173,3 +345,42 @@ int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) return remap_ops->setup_hpet_msi(irq, id); } + +void panic_if_irq_remap(const char *msg) +{ + if (irq_remapping_enabled) + panic(msg); +} + +static void ir_ack_apic_edge(struct irq_data *data) +{ + ack_APIC_irq(); +} + +static void ir_ack_apic_level(struct irq_data *data) +{ + ack_APIC_irq(); + eoi_ioapic_irq(data->irq, data->chip_data); +} + +static void ir_print_prefix(struct irq_data *data, struct seq_file *p) +{ + seq_printf(p, " IR-%s", data->chip->name); +} + +void irq_remap_modify_chip_defaults(struct irq_chip *chip) +{ + chip->irq_print_chip = ir_print_prefix; + chip->irq_ack = ir_ack_apic_edge; + chip->irq_eoi = ir_ack_apic_level; + chip->irq_set_affinity = x86_io_apic_ops.set_affinity; +} + +bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip) +{ + if (!irq_remapped(cfg)) + return false; + irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); + irq_remap_modify_chip_defaults(chip); + return true; +} diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index 95363ac..ecb6376 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -34,6 +34,7 @@ struct msi_msg; extern int disable_irq_remap; extern int disable_sourceid_checking; extern int no_x2apic_optout; +extern int irq_remapping_enabled; struct irq_remap_ops { /* Check whether Interrupt Remapping is supported */ diff --git a/drivers/isdn/gigaset/capi.c b/drivers/isdn/gigaset/capi.c index 68452b7..03a0a01 100644 --- a/drivers/isdn/gigaset/capi.c +++ b/drivers/isdn/gigaset/capi.c @@ -248,6 +248,8 @@ static inline void dump_rawmsg(enum debuglevel level, const char *tag, CAPIMSG_APPID(data), CAPIMSG_MSGID(data), l, CAPIMSG_CONTROL(data)); l -= 12; + if (l <= 0) + return; dbgline = kmalloc(3 * l, GFP_ATOMIC); if (!dbgline) return; diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index 5f21f62..deda591 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/mISDNif.h> #include <linux/kthread.h> +#include <linux/sched.h> #include "core.h" static u_int *debug; @@ -202,6 +203,9 @@ static int mISDNStackd(void *data) { struct mISDNstack *st = data; +#ifdef MISDN_MSG_STATS + cputime_t utime, stime; +#endif int err = 0; sigfillset(¤t->blocked); @@ -303,9 +307,10 @@ mISDNStackd(void *data) "msg %d sleep %d stopped\n", dev_name(&st->dev->dev), st->msg_cnt, st->sleep_cnt, st->stopped_cnt); + task_cputime(st->thread, &utime, &stime); printk(KERN_DEBUG "mISDNStackd daemon for %s utime(%ld) stime(%ld)\n", - dev_name(&st->dev->dev), st->thread->utime, st->thread->stime); + dev_name(&st->dev->dev), utime, stime); printk(KERN_DEBUG "mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n", dev_name(&st->dev->dev), st->thread->nvcsw, st->thread->nivcsw); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 3d8984e..9e58dbd 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -340,24 +340,22 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) } /* - * validate_rebuild_devices + * validate_raid_redundancy * @rs * - * Determine if the devices specified for rebuild can result in a valid - * usable array that is capable of rebuilding the given devices. + * Determine if there are enough devices in the array that haven't + * failed (or are being rebuilt) to form a usable array. * * Returns: 0 on success, -EINVAL on failure. */ -static int validate_rebuild_devices(struct raid_set *rs) +static int validate_raid_redundancy(struct raid_set *rs) { unsigned i, rebuild_cnt = 0; unsigned rebuilds_per_group, copies, d; - if (!(rs->print_flags & DMPF_REBUILD)) - return 0; - for (i = 0; i < rs->md.raid_disks; i++) - if (!test_bit(In_sync, &rs->dev[i].rdev.flags)) + if (!test_bit(In_sync, &rs->dev[i].rdev.flags) || + !rs->dev[i].rdev.sb_page) rebuild_cnt++; switch (rs->raid_type->level) { @@ -393,27 +391,24 @@ static int validate_rebuild_devices(struct raid_set *rs) * A A B B C * C D D E E */ - rebuilds_per_group = 0; for (i = 0; i < rs->md.raid_disks * copies; i++) { + if (!(i % copies)) + rebuilds_per_group = 0; d = i % rs->md.raid_disks; - if (!test_bit(In_sync, &rs->dev[d].rdev.flags) && + if ((!rs->dev[d].rdev.sb_page || + !test_bit(In_sync, &rs->dev[d].rdev.flags)) && (++rebuilds_per_group >= copies)) goto too_many; - if (!((i + 1) % copies)) - rebuilds_per_group = 0; } break; default: - DMERR("The rebuild parameter is not supported for %s", - rs->raid_type->name); - rs->ti->error = "Rebuild not supported for this RAID type"; - return -EINVAL; + if (rebuild_cnt) + return -EINVAL; } return 0; too_many: - rs->ti->error = "Too many rebuild devices specified"; return -EINVAL; } @@ -664,9 +659,6 @@ static int parse_raid_params(struct raid_set *rs, char **argv, } rs->md.dev_sectors = sectors_per_dev; - if (validate_rebuild_devices(rs)) - return -EINVAL; - /* Assume there are no metadata devices until the drives are parsed */ rs->md.persistent = 0; rs->md.external = 1; @@ -995,28 +987,10 @@ static int super_validate(struct mddev *mddev, struct md_rdev *rdev) static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) { int ret; - unsigned redundancy = 0; struct raid_dev *dev; struct md_rdev *rdev, *tmp, *freshest; struct mddev *mddev = &rs->md; - switch (rs->raid_type->level) { - case 1: - redundancy = rs->md.raid_disks - 1; - break; - case 4: - case 5: - case 6: - redundancy = rs->raid_type->parity_devs; - break; - case 10: - redundancy = raid10_md_layout_to_copies(mddev->layout) - 1; - break; - default: - ti->error = "Unknown RAID type"; - return -EINVAL; - } - freshest = NULL; rdev_for_each_safe(rdev, tmp, mddev) { /* @@ -1045,44 +1019,43 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) break; default: dev = container_of(rdev, struct raid_dev, rdev); - if (redundancy--) { - if (dev->meta_dev) - dm_put_device(ti, dev->meta_dev); - - dev->meta_dev = NULL; - rdev->meta_bdev = NULL; + if (dev->meta_dev) + dm_put_device(ti, dev->meta_dev); - if (rdev->sb_page) - put_page(rdev->sb_page); + dev->meta_dev = NULL; + rdev->meta_bdev = NULL; - rdev->sb_page = NULL; + if (rdev->sb_page) + put_page(rdev->sb_page); - rdev->sb_loaded = 0; + rdev->sb_page = NULL; - /* - * We might be able to salvage the data device - * even though the meta device has failed. For - * now, we behave as though '- -' had been - * set for this device in the table. - */ - if (dev->data_dev) - dm_put_device(ti, dev->data_dev); + rdev->sb_loaded = 0; - dev->data_dev = NULL; - rdev->bdev = NULL; + /* + * We might be able to salvage the data device + * even though the meta device has failed. For + * now, we behave as though '- -' had been + * set for this device in the table. + */ + if (dev->data_dev) + dm_put_device(ti, dev->data_dev); - list_del(&rdev->same_set); + dev->data_dev = NULL; + rdev->bdev = NULL; - continue; - } - ti->error = "Failed to load superblock"; - return ret; + list_del(&rdev->same_set); } } if (!freshest) return 0; + if (validate_raid_redundancy(rs)) { + rs->ti->error = "Insufficient redundancy to activate array"; + return -EINVAL; + } + /* * Validation of the freshest device provides the source of * validation for the remaining devices. @@ -1432,7 +1405,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 4, 0}, + .version = {1, 4, 1}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 675ae52..5409607 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2746,19 +2746,9 @@ static int thin_iterate_devices(struct dm_target *ti, return 0; } -/* - * A thin device always inherits its queue limits from its pool. - */ -static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) -{ - struct thin_c *tc = ti->private; - - *limits = bdev_get_queue(tc->pool_dev->bdev)->limits; -} - static struct target_type thin_target = { .name = "thin", - .version = {1, 6, 0}, + .version = {1, 7, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, @@ -2767,7 +2757,6 @@ static struct target_type thin_target = { .postsuspend = thin_postsuspend, .status = thin_status, .iterate_devices = thin_iterate_devices, - .io_hints = thin_io_hints, }; /*----------------------------------------------------------------*/ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c72e4d5..314a0e2 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1188,6 +1188,7 @@ static int __clone_and_map_changing_extent_only(struct clone_info *ci, { struct dm_target *ti; sector_t len; + unsigned num_requests; do { ti = dm_table_find_target(ci->map, ci->sector); @@ -1200,7 +1201,8 @@ static int __clone_and_map_changing_extent_only(struct clone_info *ci, * reconfiguration might also have changed that since the * check was performed. */ - if (!get_num_requests || !get_num_requests(ti)) + num_requests = get_num_requests ? get_num_requests(ti) : 0; + if (!num_requests) return -EOPNOTSUPP; if (is_split_required && !is_split_required(ti)) @@ -1208,7 +1210,7 @@ static int __clone_and_map_changing_extent_only(struct clone_info *ci, else len = min(ci->sector_count, max_io_len(ci->sector, ti)); - __issue_target_requests(ci, ti, ti->num_discard_requests, len); + __issue_target_requests(ci, ti, num_requests, len); ci->sector += len; } while (ci->sector_count -= len); diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 49d9504..0223ad2 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -1820,7 +1820,7 @@ static int dvb_frontend_ioctl(struct file *file, struct dvb_frontend *fe = dvbdev->priv; struct dtv_frontend_properties *c = &fe->dtv_property_cache; struct dvb_frontend_private *fepriv = fe->frontend_priv; - int err = -ENOTTY; + int err = -EOPNOTSUPP; dev_dbg(fe->dvb->device, "%s: (%d)\n", __func__, _IOC_NR(cmd)); if (fepriv->exit != DVB_FE_NO_EXIT) @@ -1938,7 +1938,7 @@ static int dvb_frontend_ioctl_properties(struct file *file, } } else - err = -ENOTTY; + err = -EOPNOTSUPP; out: kfree(tvp); @@ -2071,7 +2071,7 @@ static int dvb_frontend_ioctl_legacy(struct file *file, struct dvb_frontend *fe = dvbdev->priv; struct dvb_frontend_private *fepriv = fe->frontend_priv; struct dtv_frontend_properties *c = &fe->dtv_property_cache; - int err = -ENOTTY; + int err = -EOPNOTSUPP; switch (cmd) { case FE_GET_INFO: { diff --git a/drivers/media/radio/radio-keene.c b/drivers/media/radio/radio-keene.c index e10e525..296941a 100644 --- a/drivers/media/radio/radio-keene.c +++ b/drivers/media/radio/radio-keene.c @@ -374,6 +374,7 @@ static int usb_keene_probe(struct usb_interface *intf, radio->vdev.ioctl_ops = &usb_keene_ioctl_ops; radio->vdev.lock = &radio->lock; radio->vdev.release = video_device_release_empty; + radio->vdev.vfl_dir = VFL_DIR_TX; radio->usbdev = interface_to_usbdev(intf); radio->intf = intf; diff --git a/drivers/media/radio/radio-si4713.c b/drivers/media/radio/radio-si4713.c index a082e40..1507c9d 100644 --- a/drivers/media/radio/radio-si4713.c +++ b/drivers/media/radio/radio-si4713.c @@ -250,6 +250,7 @@ static struct video_device radio_si4713_vdev_template = { .name = "radio-si4713", .release = video_device_release, .ioctl_ops = &radio_si4713_ioctl_ops, + .vfl_dir = VFL_DIR_TX, }; /* Platform driver interface */ diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c index c48be19..cabbe3a 100644 --- a/drivers/media/radio/radio-wl1273.c +++ b/drivers/media/radio/radio-wl1273.c @@ -1971,6 +1971,7 @@ static struct video_device wl1273_viddev_template = { .ioctl_ops = &wl1273_ioctl_ops, .name = WL1273_FM_DRIVER_NAME, .release = wl1273_vdev_release, + .vfl_dir = VFL_DIR_TX, }; static int wl1273_fm_radio_remove(struct platform_device *pdev) diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c index 048de45..0a8ee8f 100644 --- a/drivers/media/radio/wl128x/fmdrv_v4l2.c +++ b/drivers/media/radio/wl128x/fmdrv_v4l2.c @@ -518,6 +518,16 @@ static struct video_device fm_viddev_template = { .ioctl_ops = &fm_drv_ioctl_ops, .name = FM_DRV_NAME, .release = video_device_release, + /* + * To ensure both the tuner and modulator ioctls are accessible we + * set the vfl_dir to M2M to indicate this. + * + * It is not really a mem2mem device of course, but it can both receive + * and transmit using the same radio device. It's the only radio driver + * that does this and it should really be split in two radio devices, + * but that would affect applications using this driver. + */ + .vfl_dir = VFL_DIR_M2M, }; int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr) diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 47ad4e2..ff553ba 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -237,6 +237,7 @@ config MFD_TPS65910 depends on I2C=y && GPIOLIB select MFD_CORE select REGMAP_I2C + select REGMAP_IRQ select IRQ_DOMAIN help if you say yes here you get support for the TPS65910 series of diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index e1650ba..4778bb1 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -19,6 +19,7 @@ #include <linux/mfd/core.h> #include <linux/mfd/abx500.h> #include <linux/mfd/abx500/ab8500.h> +#include <linux/mfd/abx500/ab8500-bm.h> #include <linux/mfd/dbx500-prcmu.h> #include <linux/regulator/ab8500.h> #include <linux/of.h> diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index bc8a3ed..222c03a 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -239,7 +239,12 @@ static int arizona_runtime_resume(struct device *dev) return ret; } - regcache_sync(arizona->regmap); + ret = regcache_sync(arizona->regmap); + if (ret != 0) { + dev_err(arizona->dev, "Failed to restore register cache\n"); + regulator_disable(arizona->dcvdd); + return ret; + } return 0; } diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c index 74713bf..2bec5f0 100644 --- a/drivers/mfd/arizona-irq.c +++ b/drivers/mfd/arizona-irq.c @@ -176,14 +176,7 @@ int arizona_irq_init(struct arizona *arizona) aod = &wm5102_aod; irq = &wm5102_irq; - switch (arizona->rev) { - case 0: - case 1: - ctrlif_error = false; - break; - default: - break; - } + ctrlif_error = false; break; #endif #ifdef CONFIG_MFD_WM5110 @@ -191,14 +184,7 @@ int arizona_irq_init(struct arizona *arizona) aod = &wm5110_aod; irq = &wm5110_irq; - switch (arizona->rev) { - case 0: - case 1: - ctrlif_error = false; - break; - default: - break; - } + ctrlif_error = false; break; #endif default: diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c index ac74a4d..885e567 100644 --- a/drivers/mfd/da9052-i2c.c +++ b/drivers/mfd/da9052-i2c.c @@ -27,6 +27,66 @@ #include <linux/of_device.h> #endif +/* I2C safe register check */ +static inline bool i2c_safe_reg(unsigned char reg) +{ + switch (reg) { + case DA9052_STATUS_A_REG: + case DA9052_STATUS_B_REG: + case DA9052_STATUS_C_REG: + case DA9052_STATUS_D_REG: + case DA9052_ADC_RES_L_REG: + case DA9052_ADC_RES_H_REG: + case DA9052_VDD_RES_REG: + case DA9052_ICHG_AV_REG: + case DA9052_TBAT_RES_REG: + case DA9052_ADCIN4_RES_REG: + case DA9052_ADCIN5_RES_REG: + case DA9052_ADCIN6_RES_REG: + case DA9052_TJUNC_RES_REG: + case DA9052_TSI_X_MSB_REG: + case DA9052_TSI_Y_MSB_REG: + case DA9052_TSI_LSB_REG: + case DA9052_TSI_Z_MSB_REG: + return true; + default: + return false; + } +} + +/* + * There is an issue with DA9052 and DA9053_AA/BA/BB PMIC where the PMIC + * gets lockup up or fails to respond following a system reset. + * This fix is to follow any read or write with a dummy read to a safe + * register. + */ +int da9052_i2c_fix(struct da9052 *da9052, unsigned char reg) +{ + int val; + + switch (da9052->chip_id) { + case DA9052: + case DA9053_AA: + case DA9053_BA: + case DA9053_BB: + /* A dummy read to a safe register address. */ + if (!i2c_safe_reg(reg)) + return regmap_read(da9052->regmap, + DA9052_PARK_REGISTER, + &val); + break; + default: + /* + * For other chips parking of I2C register + * to a safe place is not required. + */ + break; + } + + return 0; +} +EXPORT_SYMBOL(da9052_i2c_fix); + static int da9052_i2c_enable_multiwrite(struct da9052 *da9052) { int reg_val, ret; @@ -83,6 +143,7 @@ static int da9052_i2c_probe(struct i2c_client *client, da9052->dev = &client->dev; da9052->chip_irq = client->irq; + da9052->fix_io = da9052_i2c_fix; i2c_set_clientdata(client, da9052); diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index dc8826d..268f45d 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -2524,7 +2524,7 @@ static bool read_mailbox_0(void) for (n = 0; n < NUM_PRCMU_WAKEUPS; n++) { if (ev & prcmu_irq_bit[n]) - generic_handle_irq(IRQ_PRCMU_BASE + n); + generic_handle_irq(irq_find_mapping(db8500_irq_domain, n)); } r = true; break; @@ -2737,13 +2737,14 @@ static int db8500_irq_map(struct irq_domain *d, unsigned int virq, } static struct irq_domain_ops db8500_irq_ops = { - .map = db8500_irq_map, - .xlate = irq_domain_xlate_twocell, + .map = db8500_irq_map, + .xlate = irq_domain_xlate_twocell, }; static int db8500_irq_init(struct device_node *np) { - int irq_base = -1; + int irq_base = 0; + int i; /* In the device tree case, just take some IRQs */ if (!np) @@ -2758,6 +2759,10 @@ static int db8500_irq_init(struct device_node *np) return -ENOSYS; } + /* All wakeups will be used, so create mappings for all */ + for (i = 0; i < NUM_PRCMU_WAKEUPS; i++) + irq_create_mapping(db8500_irq_domain, i); + return 0; } diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c index f6878f8..4d73963 100644 --- a/drivers/mfd/max77686.c +++ b/drivers/mfd/max77686.c @@ -93,15 +93,6 @@ static int max77686_i2c_probe(struct i2c_client *i2c, if (max77686 == NULL) return -ENOMEM; - max77686->regmap = regmap_init_i2c(i2c, &max77686_regmap_config); - if (IS_ERR(max77686->regmap)) { - ret = PTR_ERR(max77686->regmap); - dev_err(max77686->dev, "Failed to allocate register map: %d\n", - ret); - kfree(max77686); - return ret; - } - i2c_set_clientdata(i2c, max77686); max77686->dev = &i2c->dev; max77686->i2c = i2c; @@ -111,6 +102,15 @@ static int max77686_i2c_probe(struct i2c_client *i2c, max77686->irq_gpio = pdata->irq_gpio; max77686->irq = i2c->irq; + max77686->regmap = regmap_init_i2c(i2c, &max77686_regmap_config); + if (IS_ERR(max77686->regmap)) { + ret = PTR_ERR(max77686->regmap); + dev_err(max77686->dev, "Failed to allocate register map: %d\n", + ret); + kfree(max77686); + return ret; + } + if (regmap_read(max77686->regmap, MAX77686_REG_DEVICE_ID, &data) < 0) { dev_err(max77686->dev, diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c index cc5155e..9e60fed 100644 --- a/drivers/mfd/max77693.c +++ b/drivers/mfd/max77693.c @@ -114,35 +114,37 @@ static int max77693_i2c_probe(struct i2c_client *i2c, u8 reg_data; int ret = 0; + if (!pdata) { + dev_err(&i2c->dev, "No platform data found.\n"); + return -EINVAL; + } + max77693 = devm_kzalloc(&i2c->dev, sizeof(struct max77693_dev), GFP_KERNEL); if (max77693 == NULL) return -ENOMEM; - max77693->regmap = devm_regmap_init_i2c(i2c, &max77693_regmap_config); - if (IS_ERR(max77693->regmap)) { - ret = PTR_ERR(max77693->regmap); - dev_err(max77693->dev,"failed to allocate register map: %d\n", - ret); - goto err_regmap; - } - i2c_set_clientdata(i2c, max77693); max77693->dev = &i2c->dev; max77693->i2c = i2c; max77693->irq = i2c->irq; max77693->type = id->driver_data; - if (!pdata) - goto err_regmap; + max77693->regmap = devm_regmap_init_i2c(i2c, &max77693_regmap_config); + if (IS_ERR(max77693->regmap)) { + ret = PTR_ERR(max77693->regmap); + dev_err(max77693->dev, "failed to allocate register map: %d\n", + ret); + return ret; + } max77693->wakeup = pdata->wakeup; - if (max77693_read_reg(max77693->regmap, - MAX77693_PMIC_REG_PMIC_ID2, ®_data) < 0) { + ret = max77693_read_reg(max77693->regmap, MAX77693_PMIC_REG_PMIC_ID2, + ®_data); + if (ret < 0) { dev_err(max77693->dev, "device not found on this channel\n"); - ret = -ENODEV; - goto err_regmap; + return ret; } else dev_info(max77693->dev, "device ID: 0x%x\n", reg_data); @@ -163,7 +165,7 @@ static int max77693_i2c_probe(struct i2c_client *i2c, ret = PTR_ERR(max77693->regmap_muic); dev_err(max77693->dev, "failed to allocate register map: %d\n", ret); - goto err_regmap; + goto err_regmap_muic; } ret = max77693_irq_init(max77693); @@ -184,9 +186,9 @@ static int max77693_i2c_probe(struct i2c_client *i2c, err_mfd: max77693_irq_exit(max77693); err_irq: +err_regmap_muic: i2c_unregister_device(max77693->muic); i2c_unregister_device(max77693->haptic); -err_regmap: return ret; } diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c index 64803f1..d115673 100644 --- a/drivers/mfd/pcf50633-core.c +++ b/drivers/mfd/pcf50633-core.c @@ -208,6 +208,8 @@ static int pcf50633_probe(struct i2c_client *client, if (!pcf) return -ENOMEM; + i2c_set_clientdata(client, pcf); + pcf->dev = &client->dev; pcf->pdata = pdata; mutex_init(&pcf->lock); @@ -219,9 +221,6 @@ static int pcf50633_probe(struct i2c_client *client, return ret; } - i2c_set_clientdata(client, pcf); - pcf->dev = &client->dev; - version = pcf50633_reg_read(pcf, 0); variant = pcf50633_reg_read(pcf, 1); if (version < 0 || variant < 0) { diff --git a/drivers/mfd/rtl8411.c b/drivers/mfd/rtl8411.c index 89f046c..3d3b4ad 100644 --- a/drivers/mfd/rtl8411.c +++ b/drivers/mfd/rtl8411.c @@ -112,6 +112,21 @@ static int rtl8411_card_power_off(struct rtsx_pcr *pcr, int card) BPP_LDO_POWB, BPP_LDO_SUSPEND); } +static int rtl8411_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage) +{ + u8 mask, val; + + mask = (BPP_REG_TUNED18 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_MASK; + if (voltage == OUTPUT_3V3) + val = (BPP_ASIC_3V3 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_3V3; + else if (voltage == OUTPUT_1V8) + val = (BPP_ASIC_1V8 << BPP_TUNED18_SHIFT_8411) | BPP_PAD_1V8; + else + return -EINVAL; + + return rtsx_pci_write_register(pcr, LDO_CTL, mask, val); +} + static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr) { unsigned int card_exist; @@ -163,6 +178,18 @@ static unsigned int rtl8411_cd_deglitch(struct rtsx_pcr *pcr) return card_exist; } +static int rtl8411_conv_clk_and_div_n(int input, int dir) +{ + int output; + + if (dir == CLK_TO_DIV_N) + output = input * 4 / 5 - 2; + else + output = (input + 2) * 5 / 4; + + return output; +} + static const struct pcr_ops rtl8411_pcr_ops = { .extra_init_hw = rtl8411_extra_init_hw, .optimize_phy = NULL, @@ -172,7 +199,9 @@ static const struct pcr_ops rtl8411_pcr_ops = { .disable_auto_blink = rtl8411_disable_auto_blink, .card_power_on = rtl8411_card_power_on, .card_power_off = rtl8411_card_power_off, + .switch_output_voltage = rtl8411_switch_output_voltage, .cd_deglitch = rtl8411_cd_deglitch, + .conv_clk_and_div_n = rtl8411_conv_clk_and_div_n, }; /* SD Pull Control Enable: diff --git a/drivers/mfd/rts5209.c b/drivers/mfd/rts5209.c index 283a4f1..98fe0f3 100644 --- a/drivers/mfd/rts5209.c +++ b/drivers/mfd/rts5209.c @@ -144,6 +144,25 @@ static int rts5209_card_power_off(struct rtsx_pcr *pcr, int card) return rtsx_pci_send_cmd(pcr, 100); } +static int rts5209_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage) +{ + int err; + + if (voltage == OUTPUT_3V3) { + err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24); + if (err < 0) + return err; + } else if (voltage == OUTPUT_1V8) { + err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24); + if (err < 0) + return err; + } else { + return -EINVAL; + } + + return 0; +} + static const struct pcr_ops rts5209_pcr_ops = { .extra_init_hw = rts5209_extra_init_hw, .optimize_phy = rts5209_optimize_phy, @@ -153,7 +172,9 @@ static const struct pcr_ops rts5209_pcr_ops = { .disable_auto_blink = rts5209_disable_auto_blink, .card_power_on = rts5209_card_power_on, .card_power_off = rts5209_card_power_off, + .switch_output_voltage = rts5209_switch_output_voltage, .cd_deglitch = NULL, + .conv_clk_and_div_n = NULL, }; /* SD Pull Control Enable: diff --git a/drivers/mfd/rts5229.c b/drivers/mfd/rts5229.c index b9dbab2..29d889c 100644 --- a/drivers/mfd/rts5229.c +++ b/drivers/mfd/rts5229.c @@ -114,6 +114,25 @@ static int rts5229_card_power_off(struct rtsx_pcr *pcr, int card) return rtsx_pci_send_cmd(pcr, 100); } +static int rts5229_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage) +{ + int err; + + if (voltage == OUTPUT_3V3) { + err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24); + if (err < 0) + return err; + } else if (voltage == OUTPUT_1V8) { + err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24); + if (err < 0) + return err; + } else { + return -EINVAL; + } + + return 0; +} + static const struct pcr_ops rts5229_pcr_ops = { .extra_init_hw = rts5229_extra_init_hw, .optimize_phy = rts5229_optimize_phy, @@ -123,7 +142,9 @@ static const struct pcr_ops rts5229_pcr_ops = { .disable_auto_blink = rts5229_disable_auto_blink, .card_power_on = rts5229_card_power_on, .card_power_off = rts5229_card_power_off, + .switch_output_voltage = rts5229_switch_output_voltage, .cd_deglitch = NULL, + .conv_clk_and_div_n = NULL, }; /* SD Pull Control Enable: diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c index 7a7b0bd..9fc5700 100644 --- a/drivers/mfd/rtsx_pcr.c +++ b/drivers/mfd/rtsx_pcr.c @@ -630,7 +630,10 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, if (clk == pcr->cur_clock) return 0; - N = (u8)(clk - 2); + if (pcr->ops->conv_clk_and_div_n) + N = (u8)pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N); + else + N = (u8)(clk - 2); if ((clk <= 2) || (N > max_N)) return -EINVAL; @@ -641,7 +644,14 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, /* Make sure that the SSC clock div_n is equal or greater than min_N */ div = CLK_DIV_1; while ((N < min_N) && (div < max_div)) { - N = (N + 2) * 2 - 2; + if (pcr->ops->conv_clk_and_div_n) { + int dbl_clk = pcr->ops->conv_clk_and_div_n(N, + DIV_N_TO_CLK) * 2; + N = (u8)pcr->ops->conv_clk_and_div_n(dbl_clk, + CLK_TO_DIV_N); + } else { + N = (N + 2) * 2 - 2; + } div++; } dev_dbg(&(pcr->pci->dev), "N = %d, div = %d\n", N, div); @@ -703,6 +713,15 @@ int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card) } EXPORT_SYMBOL_GPL(rtsx_pci_card_power_off); +int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage) +{ + if (pcr->ops->switch_output_voltage) + return pcr->ops->switch_output_voltage(pcr, voltage); + + return 0; +} +EXPORT_SYMBOL_GPL(rtsx_pci_switch_output_voltage); + unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr) { unsigned int val; @@ -767,10 +786,10 @@ static void rtsx_pci_card_detect(struct work_struct *work) spin_unlock_irqrestore(&pcr->lock, flags); - if (card_detect & SD_EXIST) + if ((card_detect & SD_EXIST) && pcr->slots[RTSX_SD_CARD].card_event) pcr->slots[RTSX_SD_CARD].card_event( pcr->slots[RTSX_SD_CARD].p_dev); - if (card_detect & MS_EXIST) + if ((card_detect & MS_EXIST) && pcr->slots[RTSX_MS_CARD].card_event) pcr->slots[RTSX_MS_CARD].card_event( pcr->slots[RTSX_MS_CARD].p_dev); } diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index 49d361a..77ee26ef 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -17,6 +17,7 @@ #include <linux/err.h> #include <linux/slab.h> #include <linux/i2c.h> +#include <linux/of_irq.h> #include <linux/interrupt.h> #include <linux/pm_runtime.h> #include <linux/mutex.h> @@ -60,6 +61,15 @@ static struct mfd_cell s2mps11_devs[] = { }, }; +#ifdef CONFIG_OF +static struct of_device_id sec_dt_match[] = { + { .compatible = "samsung,s5m8767-pmic", + .data = (void *)S5M8767X, + }, + {}, +}; +#endif + int sec_reg_read(struct sec_pmic_dev *sec_pmic, u8 reg, void *dest) { return regmap_read(sec_pmic->regmap, reg, dest); @@ -95,6 +105,57 @@ static struct regmap_config sec_regmap_config = { .val_bits = 8, }; + +#ifdef CONFIG_OF +/* + * Only the common platform data elements for s5m8767 are parsed here from the + * device tree. Other sub-modules of s5m8767 such as pmic, rtc , charger and + * others have to parse their own platform data elements from device tree. + * + * The s5m8767 platform data structure is instantiated here and the drivers for + * the sub-modules need not instantiate another instance while parsing their + * platform data. + */ +static struct sec_platform_data *sec_pmic_i2c_parse_dt_pdata( + struct device *dev) +{ + struct sec_platform_data *pd; + + pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL); + if (!pd) { + dev_err(dev, "could not allocate memory for pdata\n"); + return ERR_PTR(-ENOMEM); + } + + /* + * ToDo: the 'wakeup' member in the platform data is more of a linux + * specfic information. Hence, there is no binding for that yet and + * not parsed here. + */ + + return pd; +} +#else +static struct sec_platform_data *sec_pmic_i2c_parse_dt_pdata( + struct device *dev) +{ + return 0; +} +#endif + +static inline int sec_i2c_get_driver_data(struct i2c_client *i2c, + const struct i2c_device_id *id) +{ +#ifdef CONFIG_OF + if (i2c->dev.of_node) { + const struct of_device_id *match; + match = of_match_node(sec_dt_match, i2c->dev.of_node); + return (int)match->data; + } +#endif + return (int)id->driver_data; +} + static int sec_pmic_probe(struct i2c_client *i2c, const struct i2c_device_id *id) { @@ -111,13 +172,22 @@ static int sec_pmic_probe(struct i2c_client *i2c, sec_pmic->dev = &i2c->dev; sec_pmic->i2c = i2c; sec_pmic->irq = i2c->irq; - sec_pmic->type = id->driver_data; - + sec_pmic->type = sec_i2c_get_driver_data(i2c, id); + + if (sec_pmic->dev->of_node) { + pdata = sec_pmic_i2c_parse_dt_pdata(sec_pmic->dev); + if (IS_ERR(pdata)) { + ret = PTR_ERR(pdata); + return ret; + } + pdata->device_type = sec_pmic->type; + } if (pdata) { sec_pmic->device_type = pdata->device_type; sec_pmic->ono = pdata->ono; sec_pmic->irq_base = pdata->irq_base; sec_pmic->wakeup = pdata->wakeup; + sec_pmic->pdata = pdata; } sec_pmic->regmap = devm_regmap_init_i2c(i2c, &sec_regmap_config); @@ -192,6 +262,7 @@ static struct i2c_driver sec_pmic_driver = { .driver = { .name = "sec_pmic", .owner = THIS_MODULE, + .of_match_table = of_match_ptr(sec_dt_match), }, .probe = sec_pmic_probe, .remove = sec_pmic_remove, diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c index a06d66b..ecc092c 100644 --- a/drivers/mfd/tc3589x.c +++ b/drivers/mfd/tc3589x.c @@ -219,25 +219,18 @@ static void tc3589x_irq_unmap(struct irq_domain *d, unsigned int virq) } static struct irq_domain_ops tc3589x_irq_ops = { - .map = tc3589x_irq_map, + .map = tc3589x_irq_map, .unmap = tc3589x_irq_unmap, - .xlate = irq_domain_xlate_twocell, + .xlate = irq_domain_xlate_twocell, }; static int tc3589x_irq_init(struct tc3589x *tc3589x, struct device_node *np) { int base = tc3589x->irq_base; - if (base) { - tc3589x->domain = irq_domain_add_legacy( - NULL, TC3589x_NR_INTERNAL_IRQS, base, - 0, &tc3589x_irq_ops, tc3589x); - } - else { - tc3589x->domain = irq_domain_add_linear( - np, TC3589x_NR_INTERNAL_IRQS, - &tc3589x_irq_ops, tc3589x); - } + tc3589x->domain = irq_domain_add_simple( + np, TC3589x_NR_INTERNAL_IRQS, base, + &tc3589x_irq_ops, tc3589x); if (!tc3589x->domain) { dev_err(tc3589x->dev, "Failed to create irqdomain\n"); diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c index 4dae241..dd362c1 100644 --- a/drivers/mfd/twl4030-power.c +++ b/drivers/mfd/twl4030-power.c @@ -159,7 +159,7 @@ out: static int twl4030_write_script(u8 address, struct twl4030_ins *script, int len) { - int err; + int err = -EINVAL; for (; len; len--, address++, script++) { if (len == 1) { diff --git a/drivers/mfd/vexpress-config.c b/drivers/mfd/vexpress-config.c index fae15d8..3c1723aa 100644 --- a/drivers/mfd/vexpress-config.c +++ b/drivers/mfd/vexpress-config.c @@ -67,6 +67,7 @@ struct vexpress_config_bridge *vexpress_config_bridge_register( return bridge; } +EXPORT_SYMBOL(vexpress_config_bridge_register); void vexpress_config_bridge_unregister(struct vexpress_config_bridge *bridge) { @@ -83,6 +84,7 @@ void vexpress_config_bridge_unregister(struct vexpress_config_bridge *bridge) while (!list_empty(&__bridge.transactions)) cpu_relax(); } +EXPORT_SYMBOL(vexpress_config_bridge_unregister); struct vexpress_config_func { @@ -142,6 +144,7 @@ struct vexpress_config_func *__vexpress_config_func_get(struct device *dev, return func; } +EXPORT_SYMBOL(__vexpress_config_func_get); void vexpress_config_func_put(struct vexpress_config_func *func) { @@ -149,7 +152,7 @@ void vexpress_config_func_put(struct vexpress_config_func *func) of_node_put(func->bridge->node); kfree(func); } - +EXPORT_SYMBOL(vexpress_config_func_put); struct vexpress_config_trans { struct vexpress_config_func *func; @@ -229,6 +232,7 @@ void vexpress_config_complete(struct vexpress_config_bridge *bridge, complete(&trans->completion); } +EXPORT_SYMBOL(vexpress_config_complete); int vexpress_config_wait(struct vexpress_config_trans *trans) { @@ -236,7 +240,7 @@ int vexpress_config_wait(struct vexpress_config_trans *trans) return trans->status; } - +EXPORT_SYMBOL(vexpress_config_wait); int vexpress_config_read(struct vexpress_config_func *func, int offset, u32 *data) diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c index 088872a..f6fcb87 100644 --- a/drivers/mfd/wm5102-tables.c +++ b/drivers/mfd/wm5102-tables.c @@ -96,6 +96,7 @@ const struct regmap_irq_chip wm5102_aod = { .mask_base = ARIZONA_AOD_IRQ_MASK_IRQ1, .ack_base = ARIZONA_AOD_IRQ1, .wake_base = ARIZONA_WAKE_CONTROL, + .wake_invert = 1, .num_regs = 1, .irqs = wm5102_aod_irqs, .num_irqs = ARRAY_SIZE(wm5102_aod_irqs), @@ -1882,7 +1883,7 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg) } } -#define WM5102_MAX_REGISTER 0x1a8fff +#define WM5102_MAX_REGISTER 0x1a9800 const struct regmap_config wm5102_spi_regmap = { .reg_bits = 32, diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c index adda6b1..c415998 100644 --- a/drivers/mfd/wm5110-tables.c +++ b/drivers/mfd/wm5110-tables.c @@ -255,6 +255,7 @@ const struct regmap_irq_chip wm5110_aod = { .mask_base = ARIZONA_AOD_IRQ_MASK_IRQ1, .ack_base = ARIZONA_AOD_IRQ1, .wake_base = ARIZONA_WAKE_CONTROL, + .wake_invert = 1, .num_regs = 1, .irqs = wm5110_aod_irqs, .num_irqs = ARRAY_SIZE(wm5110_aod_irqs), diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index 492c8ca..44d273c 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -517,7 +517,7 @@ static int __init gru_init(void) { int ret; - if (!is_uv_system()) + if (!is_uv_system() || (is_uvx_hub() && !is_uv2_hub())) return 0; #if defined CONFIG_IA64 diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c index 571915d..f74b5ad 100644 --- a/drivers/mmc/host/rtsx_pci_sdmmc.c +++ b/drivers/mmc/host/rtsx_pci_sdmmc.c @@ -1060,26 +1060,6 @@ static int sd_wait_voltage_stable_2(struct realtek_pci_sdmmc *host) return 0; } -static int sd_change_bank_voltage(struct realtek_pci_sdmmc *host, u8 voltage) -{ - struct rtsx_pcr *pcr = host->pcr; - int err; - - if (voltage == SD_IO_3V3) { - err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4FC0 | 0x24); - if (err < 0) - return err; - } else if (voltage == SD_IO_1V8) { - err = rtsx_pci_write_phy_register(pcr, 0x08, 0x4C40 | 0x24); - if (err < 0) - return err; - } else { - return -EINVAL; - } - - return 0; -} - static int sdmmc_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios) { struct realtek_pci_sdmmc *host = mmc_priv(mmc); @@ -1098,11 +1078,11 @@ static int sdmmc_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios) rtsx_pci_start_run(pcr); if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) - voltage = SD_IO_3V3; + voltage = OUTPUT_3V3; else - voltage = SD_IO_1V8; + voltage = OUTPUT_1V8; - if (voltage == SD_IO_1V8) { + if (voltage == OUTPUT_1V8) { err = rtsx_pci_write_register(pcr, SD30_DRIVE_SEL, 0x07, DRIVER_TYPE_B); if (err < 0) @@ -1113,11 +1093,11 @@ static int sdmmc_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios) goto out; } - err = sd_change_bank_voltage(host, voltage); + err = rtsx_pci_switch_output_voltage(pcr, voltage); if (err < 0) goto out; - if (voltage == SD_IO_1V8) { + if (voltage == OUTPUT_1V8) { err = sd_wait_voltage_stable_2(host); if (err < 0) goto out; diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 27f80cd..46dcb54 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -272,6 +272,7 @@ config MTD_DOCG3 tristate "M-Systems Disk-On-Chip G3" select BCH select BCH_CONST_PARAMS + select BITREVERSE ---help--- This provides an MTD device driver for the M-Systems DiskOnChip G3 devices. diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c index 67cc73c..7901d72 100644 --- a/drivers/mtd/maps/physmap_of.c +++ b/drivers/mtd/maps/physmap_of.c @@ -170,7 +170,7 @@ static int of_flash_probe(struct platform_device *dev) resource_size_t res_size; struct mtd_part_parser_data ppdata; bool map_indirect; - const char *mtd_name; + const char *mtd_name = NULL; match = of_match_device(of_flash_match, &dev->dev); if (!match) diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c index 86c9a79..595de40 100644 --- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c +++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c @@ -17,8 +17,8 @@ #include "bcm47xxnflash.h" /* Broadcom uses 1'000'000 but it seems to be too many. Tests on WNDR4500 has - * shown 164 retries as maxiumum. */ -#define NFLASH_READY_RETRIES 1000 + * shown ~1000 retries as maxiumum. */ +#define NFLASH_READY_RETRIES 10000 #define NFLASH_SECTOR_SIZE 512 diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c index 3502606..feae55c 100644 --- a/drivers/mtd/nand/davinci_nand.c +++ b/drivers/mtd/nand/davinci_nand.c @@ -523,7 +523,7 @@ static struct nand_ecclayout hwecc4_2048 __initconst = { static const struct of_device_id davinci_nand_of_match[] = { {.compatible = "ti,davinci-nand", }, {}, -} +}; MODULE_DEVICE_TABLE(of, davinci_nand_of_match); static struct davinci_nand_pdata diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 8323ac9..3766682 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -2857,8 +2857,11 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip, int i; int val; - /* ONFI need to be probed in 8 bits mode */ - WARN_ON(chip->options & NAND_BUSWIDTH_16); + /* ONFI need to be probed in 8 bits mode, and 16 bits should be selected with NAND_BUSWIDTH_AUTO */ + if (chip->options & NAND_BUSWIDTH_16) { + pr_err("Trying ONFI probe in 16 bits mode, aborting !\n"); + return 0; + } /* Try ONFI for unknown chip or LP */ chip->cmdfunc(mtd, NAND_CMD_READID, 0x20, -1); if (chip->read_byte(mtd) != 'O' || chip->read_byte(mtd) != 'N' || diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 1877ed7..1c9e09f 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1053,6 +1053,7 @@ static ssize_t bonding_store_primary(struct device *d, pr_info("%s: Setting primary slave to None.\n", bond->dev->name); bond->primary_slave = NULL; + memset(bond->params.primary, 0, sizeof(bond->params.primary)); bond_select_active_slave(bond); goto out; } diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 5233b8f..2282b1a 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -488,8 +488,12 @@ static void c_can_setup_receive_object(struct net_device *dev, int iface, priv->write_reg(priv, C_CAN_IFACE(MASK1_REG, iface), IFX_WRITE_LOW_16BIT(mask)); + + /* According to C_CAN documentation, the reserved bit + * in IFx_MASK2 register is fixed 1 + */ priv->write_reg(priv, C_CAN_IFACE(MASK2_REG, iface), - IFX_WRITE_HIGH_16BIT(mask)); + IFX_WRITE_HIGH_16BIT(mask) | BIT(13)); priv->write_reg(priv, C_CAN_IFACE(ARB1_REG, iface), IFX_WRITE_LOW_16BIT(id)); @@ -960,7 +964,7 @@ static int c_can_handle_bus_err(struct net_device *dev, break; case LEC_ACK_ERROR: netdev_dbg(dev, "ack error\n"); - cf->data[2] |= (CAN_ERR_PROT_LOC_ACK | + cf->data[3] |= (CAN_ERR_PROT_LOC_ACK | CAN_ERR_PROT_LOC_ACK_DEL); break; case LEC_BIT1_ERROR: @@ -973,7 +977,7 @@ static int c_can_handle_bus_err(struct net_device *dev, break; case LEC_CRC_ERROR: netdev_dbg(dev, "CRC error\n"); - cf->data[2] |= (CAN_ERR_PROT_LOC_CRC_SEQ | + cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ | CAN_ERR_PROT_LOC_CRC_DEL); break; default: diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c index 7d17485..5c314a9 100644 --- a/drivers/net/can/pch_can.c +++ b/drivers/net/can/pch_can.c @@ -560,7 +560,7 @@ static void pch_can_error(struct net_device *ndev, u32 status) stats->rx_errors++; break; case PCH_CRC_ERR: - cf->data[2] |= CAN_ERR_PROT_LOC_CRC_SEQ | + cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ | CAN_ERR_PROT_LOC_CRC_DEL; priv->can.can_stats.bus_error++; stats->rx_errors++; diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index d84888f..600ac72 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -339,8 +339,7 @@ static void peak_pciec_set_leds(struct peak_pciec_card *card, u8 led_mask, u8 s) */ static void peak_pciec_start_led_work(struct peak_pciec_card *card) { - if (!delayed_work_pending(&card->led_work)) - schedule_delayed_work(&card->led_work, HZ); + schedule_delayed_work(&card->led_work, HZ); } /* diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index f898c63..300581b 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -746,12 +746,12 @@ static int ti_hecc_error(struct net_device *ndev, int int_status, } if (err_status & HECC_CANES_CRCE) { hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE); - cf->data[2] |= CAN_ERR_PROT_LOC_CRC_SEQ | + cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ | CAN_ERR_PROT_LOC_CRC_DEL; } if (err_status & HECC_CANES_ACKE) { hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE); - cf->data[2] |= CAN_ERR_PROT_LOC_ACK | + cf->data[3] |= CAN_ERR_PROT_LOC_ACK | CAN_ERR_PROT_LOC_ACK_DEL; } } diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index 66df936..ffd8de2 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -432,7 +432,7 @@ static int tc574_config(struct pcmcia_device *link) netdev_info(dev, "%s at io %#3lx, irq %d, hw_addr %pM\n", cardname, dev->base_addr, dev->irq, dev->dev_addr); netdev_info(dev, " %dK FIFO split %s Rx:Tx, %sMII interface.\n", - 8 << config & Ram_size, + 8 << (config & Ram_size), ram_split[(config & Ram_split) >> Ram_split_shift], config & Autoselect ? "autoselect " : ""); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 56d3f69..0035c01 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -21,7 +21,7 @@ #include "atl1c.h" -#define ATL1C_DRV_VERSION "1.0.1.0-NAPI" +#define ATL1C_DRV_VERSION "1.0.1.1-NAPI" char atl1c_driver_name[] = "atl1c"; char atl1c_driver_version[] = ATL1C_DRV_VERSION; @@ -1652,6 +1652,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter) u16 num_alloc = 0; u16 rfd_next_to_use, next_next; struct atl1c_rx_free_desc *rfd_desc; + dma_addr_t mapping; next_next = rfd_next_to_use = rfd_ring->next_to_use; if (++next_next == rfd_ring->count) @@ -1678,9 +1679,18 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter) ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); buffer_info->skb = skb; buffer_info->length = adapter->rx_buffer_len; - buffer_info->dma = pci_map_single(pdev, vir_addr, + mapping = pci_map_single(pdev, vir_addr, buffer_info->length, PCI_DMA_FROMDEVICE); + if (unlikely(pci_dma_mapping_error(pdev, mapping))) { + dev_kfree_skb(skb); + buffer_info->skb = NULL; + buffer_info->length = 0; + ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE); + netif_warn(adapter, rx_err, adapter->netdev, "RX pci_map_single failed"); + break; + } + buffer_info->dma = mapping; ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE, ATL1C_PCIMAP_FROMDEVICE); rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma); @@ -2015,7 +2025,29 @@ check_sum: return 0; } -static void atl1c_tx_map(struct atl1c_adapter *adapter, +static void atl1c_tx_rollback(struct atl1c_adapter *adpt, + struct atl1c_tpd_desc *first_tpd, + enum atl1c_trans_queue type) +{ + struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[type]; + struct atl1c_buffer *buffer_info; + struct atl1c_tpd_desc *tpd; + u16 first_index, index; + + first_index = first_tpd - (struct atl1c_tpd_desc *)tpd_ring->desc; + index = first_index; + while (index != tpd_ring->next_to_use) { + tpd = ATL1C_TPD_DESC(tpd_ring, index); + buffer_info = &tpd_ring->buffer_info[index]; + atl1c_clean_buffer(adpt->pdev, buffer_info, 0); + memset(tpd, 0, sizeof(struct atl1c_tpd_desc)); + if (++index == tpd_ring->count) + index = 0; + } + tpd_ring->next_to_use = first_index; +} + +static int atl1c_tx_map(struct atl1c_adapter *adapter, struct sk_buff *skb, struct atl1c_tpd_desc *tpd, enum atl1c_trans_queue type) { @@ -2040,7 +2072,10 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter, buffer_info->length = map_len; buffer_info->dma = pci_map_single(adapter->pdev, skb->data, hdr_len, PCI_DMA_TODEVICE); - ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); + if (unlikely(pci_dma_mapping_error(adapter->pdev, + buffer_info->dma))) + goto err_dma; + ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE, ATL1C_PCIMAP_TODEVICE); mapped_len += map_len; @@ -2062,6 +2097,10 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter, buffer_info->dma = pci_map_single(adapter->pdev, skb->data + mapped_len, buffer_info->length, PCI_DMA_TODEVICE); + if (unlikely(pci_dma_mapping_error(adapter->pdev, + buffer_info->dma))) + goto err_dma; + ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE, ATL1C_PCIMAP_TODEVICE); @@ -2083,6 +2122,9 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter, frag, 0, buffer_info->length, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma)) + goto err_dma; + ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY); ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_PAGE, ATL1C_PCIMAP_TODEVICE); @@ -2095,6 +2137,13 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter, /* The last buffer info contain the skb address, so it will be free after unmap */ buffer_info->skb = skb; + + return 0; + +err_dma: + buffer_info->dma = 0; + buffer_info->length = 0; + return -1; } static void atl1c_tx_queue(struct atl1c_adapter *adapter, struct sk_buff *skb, @@ -2157,10 +2206,18 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb, if (skb_network_offset(skb) != ETH_HLEN) tpd->word1 |= 1 << TPD_ETH_TYPE_SHIFT; /* Ethernet frame */ - atl1c_tx_map(adapter, skb, tpd, type); - atl1c_tx_queue(adapter, skb, tpd, type); + if (atl1c_tx_map(adapter, skb, tpd, type) < 0) { + netif_info(adapter, tx_done, adapter->netdev, + "tx-skb droppted due to dma error\n"); + /* roll back tpd/buffer */ + atl1c_tx_rollback(adapter, tpd, type); + spin_unlock_irqrestore(&adapter->tx_lock, flags); + dev_kfree_skb(skb); + } else { + atl1c_tx_queue(adapter, skb, tpd, type); + spin_unlock_irqrestore(&adapter->tx_lock, flags); + } - spin_unlock_irqrestore(&adapter->tx_lock, flags); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index f771ddf..a5edac8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -504,13 +504,11 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp, skb_shinfo(skb)->gso_size = bnx2x_set_lro_mss(bp, tpa_info->parsing_flags, len_on_bd); - /* set for GRO */ - if (fp->mode == TPA_MODE_GRO) - skb_shinfo(skb)->gso_type = - (GET_FLAG(tpa_info->parsing_flags, - PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) == - PRS_FLAG_OVERETH_IPV6) ? - SKB_GSO_TCPV6 : SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_type = + (GET_FLAG(tpa_info->parsing_flags, + PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) == + PRS_FLAG_OVERETH_IPV6) ? + SKB_GSO_TCPV6 : SKB_GSO_TCPV4; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 78ea90c..bdb0869 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -1283,14 +1283,26 @@ static int tg3_phy_auxctl_write(struct tg3 *tp, int reg, u32 set) return tg3_writephy(tp, MII_TG3_AUX_CTRL, set | reg); } -#define TG3_PHY_AUXCTL_SMDSP_ENABLE(tp) \ - tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, \ - MII_TG3_AUXCTL_ACTL_SMDSP_ENA | \ - MII_TG3_AUXCTL_ACTL_TX_6DB) +static int tg3_phy_toggle_auxctl_smdsp(struct tg3 *tp, bool enable) +{ + u32 val; + int err; -#define TG3_PHY_AUXCTL_SMDSP_DISABLE(tp) \ - tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, \ - MII_TG3_AUXCTL_ACTL_TX_6DB); + err = tg3_phy_auxctl_read(tp, MII_TG3_AUXCTL_SHDWSEL_AUXCTL, &val); + + if (err) + return err; + if (enable) + + val |= MII_TG3_AUXCTL_ACTL_SMDSP_ENA; + else + val &= ~MII_TG3_AUXCTL_ACTL_SMDSP_ENA; + + err = tg3_phy_auxctl_write((tp), MII_TG3_AUXCTL_SHDWSEL_AUXCTL, + val | MII_TG3_AUXCTL_ACTL_TX_6DB); + + return err; +} static int tg3_bmcr_reset(struct tg3 *tp) { @@ -2223,7 +2235,7 @@ static void tg3_phy_apply_otp(struct tg3 *tp) otp = tp->phy_otp; - if (TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) + if (tg3_phy_toggle_auxctl_smdsp(tp, true)) return; phy = ((otp & TG3_OTP_AGCTGT_MASK) >> TG3_OTP_AGCTGT_SHIFT); @@ -2248,7 +2260,7 @@ static void tg3_phy_apply_otp(struct tg3 *tp) ((otp & TG3_OTP_RCOFF_MASK) >> TG3_OTP_RCOFF_SHIFT); tg3_phydsp_write(tp, MII_TG3_DSP_EXP97, phy); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) @@ -2284,9 +2296,9 @@ static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) if (!tp->setlpicnt) { if (current_link_up == 1 && - !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + !tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, 0x0000); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } val = tr32(TG3_CPMU_EEE_MODE); @@ -2302,11 +2314,11 @@ static void tg3_phy_eee_enable(struct tg3 *tp) (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || tg3_flag(tp, 57765_CLASS)) && - !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + !tg3_phy_toggle_auxctl_smdsp(tp, true)) { val = MII_TG3_DSP_TAP26_ALNOKO | MII_TG3_DSP_TAP26_RMRXSTO; tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } val = tr32(TG3_CPMU_EEE_MODE); @@ -2450,7 +2462,7 @@ static int tg3_phy_reset_5703_4_5(struct tg3 *tp) tg3_writephy(tp, MII_CTRL1000, CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER); - err = TG3_PHY_AUXCTL_SMDSP_ENABLE(tp); + err = tg3_phy_toggle_auxctl_smdsp(tp, true); if (err) return err; @@ -2471,7 +2483,7 @@ static int tg3_phy_reset_5703_4_5(struct tg3 *tp) tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x8200); tg3_writephy(tp, MII_TG3_DSP_CONTROL, 0x0000); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); tg3_writephy(tp, MII_CTRL1000, phy9_orig); @@ -2572,10 +2584,10 @@ static int tg3_phy_reset(struct tg3 *tp) out: if ((tp->phy_flags & TG3_PHYFLG_ADC_BUG) && - !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + !tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_phydsp_write(tp, 0x201f, 0x2aaa); tg3_phydsp_write(tp, 0x000a, 0x0323); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } if (tp->phy_flags & TG3_PHYFLG_5704_A0_BUG) { @@ -2584,14 +2596,14 @@ out: } if (tp->phy_flags & TG3_PHYFLG_BER_BUG) { - if (!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + if (!tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_phydsp_write(tp, 0x000a, 0x310b); tg3_phydsp_write(tp, 0x201f, 0x9506); tg3_phydsp_write(tp, 0x401f, 0x14e2); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } } else if (tp->phy_flags & TG3_PHYFLG_JITTER_BUG) { - if (!TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) { + if (!tg3_phy_toggle_auxctl_smdsp(tp, true)) { tg3_writephy(tp, MII_TG3_DSP_ADDRESS, 0x000a); if (tp->phy_flags & TG3_PHYFLG_ADJUST_TRIM) { tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x110b); @@ -2600,7 +2612,7 @@ out: } else tg3_writephy(tp, MII_TG3_DSP_RW_PORT, 0x010b); - TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + tg3_phy_toggle_auxctl_smdsp(tp, false); } } @@ -4009,7 +4021,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl) tw32(TG3_CPMU_EEE_MODE, tr32(TG3_CPMU_EEE_MODE) & ~TG3_CPMU_EEEMD_LPI_ENABLE); - err = TG3_PHY_AUXCTL_SMDSP_ENABLE(tp); + err = tg3_phy_toggle_auxctl_smdsp(tp, true); if (!err) { u32 err2; @@ -4042,7 +4054,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl) MII_TG3_DSP_CH34TP2_HIBW01); } - err2 = TG3_PHY_AUXCTL_SMDSP_DISABLE(tp); + err2 = tg3_phy_toggle_auxctl_smdsp(tp, false); if (!err) err = err2; } @@ -6950,6 +6962,9 @@ static void tg3_poll_controller(struct net_device *dev) int i; struct tg3 *tp = netdev_priv(dev); + if (tg3_irq_sync(tp)) + return; + for (i = 0; i < tp->irq_cnt; i++) tg3_interrupt(tp->napi[i].irq_vec, &tp->napi[i]); } @@ -16367,6 +16382,7 @@ static int tg3_init_one(struct pci_dev *pdev, tp->pm_cap = pm_cap; tp->rx_mode = TG3_DEF_RX_MODE; tp->tx_mode = TG3_DEF_TX_MODE; + tp->irq_sync = 1; if (tg3_debug > 0) tp->msg_enable = tg3_debug; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index a9b0830..b9d4bb9 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -693,6 +693,11 @@ static int macb_poll(struct napi_struct *napi, int budget) * get notified when new packets arrive. */ macb_writel(bp, IER, MACB_RX_INT_FLAGS); + + /* Packets received while interrupts were disabled */ + status = macb_readl(bp, RSR); + if (unlikely(status)) + napi_reschedule(napi); } /* TODO: Handle errors */ diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index b407043..f7f0290 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -548,6 +548,10 @@ static int desc_get_rx_status(struct xgmac_priv *priv, struct xgmac_dma_desc *p) return -1; } + /* All frames should fit into a single buffer */ + if (!(status & RXDESC_FIRST_SEG) || !(status & RXDESC_LAST_SEG)) + return -1; + /* Check if packet has checksum already */ if ((status & RXDESC_FRAME_TYPE) && (status & RXDESC_EXT_STATUS) && !(ext_status & RXDESC_IP_PAYLOAD_MASK)) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index f0718e1..c306df7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1994,9 +1994,20 @@ static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) { const struct port_info *pi = netdev_priv(dev); struct adapter *adap = pi->adapter; - - return set_rxq_intr_params(adap, &adap->sge.ethrxq[pi->first_qset].rspq, - c->rx_coalesce_usecs, c->rx_max_coalesced_frames); + struct sge_rspq *q; + int i; + int r = 0; + + for (i = pi->first_qset; i < pi->first_qset + pi->nqsets; i++) { + q = &adap->sge.ethrxq[i].rspq; + r = set_rxq_intr_params(adap, q, c->rx_coalesce_usecs, + c->rx_max_coalesced_frames); + if (r) { + dev_err(&dev->dev, "failed to set coalesce %d\n", r); + break; + } + } + return r; } static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 4eba17b..f1b3df1 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -36,13 +36,13 @@ #define DRV_VER "4.4.161.0u" #define DRV_NAME "be2net" -#define BE_NAME "ServerEngines BladeEngine2 10Gbps NIC" -#define BE3_NAME "ServerEngines BladeEngine3 10Gbps NIC" -#define OC_NAME "Emulex OneConnect 10Gbps NIC" +#define BE_NAME "Emulex BladeEngine2" +#define BE3_NAME "Emulex BladeEngine3" +#define OC_NAME "Emulex OneConnect" #define OC_NAME_BE OC_NAME "(be3)" #define OC_NAME_LANCER OC_NAME "(Lancer)" #define OC_NAME_SH OC_NAME "(Skyhawk)" -#define DRV_DESC "ServerEngines BladeEngine 10Gbps NIC Driver" +#define DRV_DESC "Emulex OneConnect 10Gbps NIC Driver" #define BE_VENDOR_ID 0x19a2 #define EMULEX_VENDOR_ID 0x10df diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 5c99570..4d6f3c5 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -25,7 +25,7 @@ MODULE_VERSION(DRV_VER); MODULE_DEVICE_TABLE(pci, be_dev_ids); MODULE_DESCRIPTION(DRV_DESC " " DRV_VER); -MODULE_AUTHOR("ServerEngines Corporation"); +MODULE_AUTHOR("Emulex Corporation"); MODULE_LICENSE("GPL"); static unsigned int num_vfs; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 02a12b6..4dab6fc 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -232,6 +232,7 @@ #define E1000_CTRL_FRCDPX 0x00001000 /* Force Duplex */ #define E1000_CTRL_LANPHYPC_OVERRIDE 0x00010000 /* SW control of LANPHYPC */ #define E1000_CTRL_LANPHYPC_VALUE 0x00020000 /* SW value of LANPHYPC */ +#define E1000_CTRL_MEHE 0x00080000 /* Memory Error Handling Enable */ #define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */ #define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */ #define E1000_CTRL_SWDPIO0 0x00400000 /* SWDPIN 0 Input or output */ @@ -389,6 +390,12 @@ #define E1000_PBS_16K E1000_PBA_16K +/* Uncorrectable/correctable ECC Error counts and enable bits */ +#define E1000_PBECCSTS_CORR_ERR_CNT_MASK 0x000000FF +#define E1000_PBECCSTS_UNCORR_ERR_CNT_MASK 0x0000FF00 +#define E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT 8 +#define E1000_PBECCSTS_ECC_ENABLE 0x00010000 + #define IFS_MAX 80 #define IFS_MIN 40 #define IFS_RATIO 4 @@ -408,6 +415,7 @@ #define E1000_ICR_RXSEQ 0x00000008 /* Rx sequence error */ #define E1000_ICR_RXDMT0 0x00000010 /* Rx desc min. threshold (0) */ #define E1000_ICR_RXT0 0x00000080 /* Rx timer intr (ring 0) */ +#define E1000_ICR_ECCER 0x00400000 /* Uncorrectable ECC Error */ #define E1000_ICR_INT_ASSERTED 0x80000000 /* If this bit asserted, the driver should claim the interrupt */ #define E1000_ICR_RXQ0 0x00100000 /* Rx Queue 0 Interrupt */ #define E1000_ICR_RXQ1 0x00200000 /* Rx Queue 1 Interrupt */ @@ -443,6 +451,7 @@ #define E1000_IMS_RXSEQ E1000_ICR_RXSEQ /* Rx sequence error */ #define E1000_IMS_RXDMT0 E1000_ICR_RXDMT0 /* Rx desc min. threshold */ #define E1000_IMS_RXT0 E1000_ICR_RXT0 /* Rx timer intr */ +#define E1000_IMS_ECCER E1000_ICR_ECCER /* Uncorrectable ECC Error */ #define E1000_IMS_RXQ0 E1000_ICR_RXQ0 /* Rx Queue 0 Interrupt */ #define E1000_IMS_RXQ1 E1000_ICR_RXQ1 /* Rx Queue 1 Interrupt */ #define E1000_IMS_TXQ0 E1000_ICR_TXQ0 /* Tx Queue 0 Interrupt */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 6782a2e..7e95f22 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -309,6 +309,8 @@ struct e1000_adapter { struct napi_struct napi; + unsigned int uncorr_errors; /* uncorrectable ECC errors */ + unsigned int corr_errors; /* correctable ECC errors */ unsigned int restart_queue; u32 txd_cmd; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index f95bc6e..fd4772a 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -108,6 +108,8 @@ static const struct e1000_stats e1000_gstrings_stats[] = { E1000_STAT("dropped_smbus", stats.mgpdc), E1000_STAT("rx_dma_failed", rx_dma_failed), E1000_STAT("tx_dma_failed", tx_dma_failed), + E1000_STAT("uncorr_ecc_errors", uncorr_errors), + E1000_STAT("corr_ecc_errors", corr_errors), }; #define E1000_GLOBAL_STATS_LEN ARRAY_SIZE(e1000_gstrings_stats) diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index cf21777..b88676f 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -77,6 +77,7 @@ enum e1e_registers { #define E1000_POEMB E1000_PHY_CTRL /* PHY OEM Bits */ E1000_PBA = 0x01000, /* Packet Buffer Allocation - RW */ E1000_PBS = 0x01008, /* Packet Buffer Size */ + E1000_PBECCSTS = 0x0100C, /* Packet Buffer ECC Status - RW */ E1000_EEMNGCTL = 0x01010, /* MNG EEprom Control */ E1000_EEWR = 0x0102C, /* EEPROM Write Register - RW */ E1000_FLOP = 0x0103C, /* FLASH Opcode Register */ diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 9763365..24d9f61 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -3624,6 +3624,17 @@ static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw) if (hw->mac.type == e1000_ich8lan) reg |= (E1000_RFCTL_IPV6_EX_DIS | E1000_RFCTL_NEW_IPV6_EXT_DIS); ew32(RFCTL, reg); + + /* Enable ECC on Lynxpoint */ + if (hw->mac.type == e1000_pch_lpt) { + reg = er32(PBECCSTS); + reg |= E1000_PBECCSTS_ECC_ENABLE; + ew32(PBECCSTS, reg); + + reg = er32(CTRL); + reg |= E1000_CTRL_MEHE; + ew32(CTRL, reg); + } } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fbf75fd..643c883 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1678,6 +1678,23 @@ static irqreturn_t e1000_intr_msi(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } + /* Reset on uncorrectable ECC error */ + if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) { + u32 pbeccsts = er32(PBECCSTS); + + adapter->corr_errors += + pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; + adapter->uncorr_errors += + (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >> + E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT; + + /* Do the reset outside of interrupt context */ + schedule_work(&adapter->reset_task); + + /* return immediately since reset is imminent */ + return IRQ_HANDLED; + } + if (napi_schedule_prep(&adapter->napi)) { adapter->total_tx_bytes = 0; adapter->total_tx_packets = 0; @@ -1741,6 +1758,23 @@ static irqreturn_t e1000_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } + /* Reset on uncorrectable ECC error */ + if ((icr & E1000_ICR_ECCER) && (hw->mac.type == e1000_pch_lpt)) { + u32 pbeccsts = er32(PBECCSTS); + + adapter->corr_errors += + pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; + adapter->uncorr_errors += + (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >> + E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT; + + /* Do the reset outside of interrupt context */ + schedule_work(&adapter->reset_task); + + /* return immediately since reset is imminent */ + return IRQ_HANDLED; + } + if (napi_schedule_prep(&adapter->napi)) { adapter->total_tx_bytes = 0; adapter->total_tx_packets = 0; @@ -2104,6 +2138,8 @@ static void e1000_irq_enable(struct e1000_adapter *adapter) if (adapter->msix_entries) { ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574); ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | E1000_IMS_LSC); + } else if (hw->mac.type == e1000_pch_lpt) { + ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER); } else { ew32(IMS, IMS_ENABLE_MASK); } @@ -4251,6 +4287,16 @@ static void e1000e_update_stats(struct e1000_adapter *adapter) adapter->stats.mgptc += er32(MGTPTC); adapter->stats.mgprc += er32(MGTPRC); adapter->stats.mgpdc += er32(MGTPDC); + + /* Correctable ECC Errors */ + if (hw->mac.type == e1000_pch_lpt) { + u32 pbeccsts = er32(PBECCSTS); + adapter->corr_errors += + pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK; + adapter->uncorr_errors += + (pbeccsts & E1000_PBECCSTS_UNCORR_ERR_CNT_MASK) >> + E1000_PBECCSTS_UNCORR_ERR_CNT_SHIFT; + } } /** diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index f3a632b..687c83d 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -32,7 +32,7 @@ obj-$(CONFIG_IXGBE) += ixgbe.o -ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o ixgbe_debugfs.o\ +ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o ixgbe_ptp.o @@ -40,4 +40,5 @@ ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o +ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index 50aa546..3504686 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -24,9 +24,6 @@ Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 *******************************************************************************/ - -#ifdef CONFIG_DEBUG_FS - #include <linux/debugfs.h> #include <linux/module.h> @@ -277,5 +274,3 @@ void ixgbe_dbg_exit(void) { debugfs_remove_recursive(ixgbe_dbg_root); } - -#endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 20a5af6..b3e3294 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1401,6 +1401,7 @@ static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring, /* set gso_size to avoid messing up TCP MSS */ skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len), IXGBE_CB(skb)->append_cnt); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; } static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 1a751c9..bb9256a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -660,11 +660,11 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, break; case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; - tsync_rx_mtrl = IXGBE_RXMTRL_V1_SYNC_MSG; + tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG; break; case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; - tsync_rx_mtrl = IXGBE_RXMTRL_V1_DELAY_REQ_MSG; + tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG; break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 2b799f4..6771b69 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -630,10 +630,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->tx_csum++; } - /* Copy dst mac address to wqe */ - ethh = (struct ethhdr *)skb->data; - tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest); - tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2)); + if (mlx4_is_mfunc(mdev->dev) || priv->validate_loopback) { + /* Copy dst mac address to wqe. This allows loopback in eSwitch, + * so that VFs and PF can communicate with each other + */ + ethh = (struct ethhdr *)skb->data; + tx_desc->ctrl.srcrb_flags16[0] = get_unaligned((__be16 *)ethh->h_dest); + tx_desc->ctrl.imm = get_unaligned((__be32 *)(ethh->h_dest + 2)); + } + /* Handle LSO (TSO) packets */ if (lso_header_size) { /* Mark opcode as LSO */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index e1bafff..5163af3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -380,7 +380,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) } } - if ((dev_cap->flags & + if ((dev->caps.flags & (MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) && mlx4_is_master(dev)) dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE; @@ -1790,15 +1790,8 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) int i; if (msi_x) { - /* In multifunction mode each function gets 2 msi-X vectors - * one for data path completions anf the other for asynch events - * or command completions */ - if (mlx4_is_mfunc(dev)) { - nreq = 2; - } else { - nreq = min_t(int, dev->caps.num_eqs - - dev->caps.reserved_eqs, nreq); - } + nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, + nreq); entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); if (!entries) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c index bc165f4..695667d 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c @@ -144,7 +144,7 @@ void netxen_release_tx_buffers(struct netxen_adapter *adapter) buffrag->length, PCI_DMA_TODEVICE); buffrag->dma = 0ULL; } - for (j = 0; j < cmd_buf->frag_count; j++) { + for (j = 1; j < cmd_buf->frag_count; j++) { buffrag++; if (buffrag->dma) { pci_unmap_page(adapter->pdev, buffrag->dma, diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 6098fd4a..69e321a 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1963,10 +1963,12 @@ unwind: while (--i >= 0) { nf = &pbuf->frag_array[i+1]; pci_unmap_page(pdev, nf->dma, nf->length, PCI_DMA_TODEVICE); + nf->dma = 0ULL; } nf = &pbuf->frag_array[0]; pci_unmap_single(pdev, nf->dma, skb_headlen(skb), PCI_DMA_TODEVICE); + nf->dma = 0ULL; out_err: return -ENOMEM; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 6f82812..09aa310 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -986,8 +986,13 @@ qlcnic_process_lro(struct qlcnic_adapter *adapter, th->seq = htonl(seq_number); length = skb->len; - if (adapter->flags & QLCNIC_FW_LRO_MSS_CAP) + if (adapter->flags & QLCNIC_FW_LRO_MSS_CAP) { skb_shinfo(skb)->gso_size = qlcnic_get_lro_sts_mss(sts_data1); + if (skb->protocol == htons(ETH_P_IPV6)) + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + else + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + } if (vid != 0xffff) __vlan_hwaccel_put_tag(skb, vid); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index ed96f30..998974f 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -450,7 +450,6 @@ enum rtl8168_registers { #define PWM_EN (1 << 22) #define RXDV_GATED_EN (1 << 19) #define EARLY_TALLY_EN (1 << 16) -#define FORCE_CLK (1 << 15) /* force clock request */ }; enum rtl_register_content { @@ -514,7 +513,6 @@ enum rtl_register_content { PMEnable = (1 << 0), /* Power Management Enable */ /* Config2 register p. 25 */ - ClkReqEn = (1 << 7), /* Clock Request Enable */ MSIEnable = (1 << 5), /* 8169 only. Reserved in the 8168. */ PCI_Clock_66MHz = 0x01, PCI_Clock_33MHz = 0x00, @@ -535,7 +533,6 @@ enum rtl_register_content { Spi_en = (1 << 3), LanWake = (1 << 1), /* LanWake enable/disable */ PMEStatus = (1 << 0), /* PME status can be reset by PCI RST# */ - ASPM_en = (1 << 0), /* ASPM enable */ /* TBICSR p.28 */ TBIReset = 0x80000000, @@ -684,7 +681,6 @@ enum features { RTL_FEATURE_WOL = (1 << 0), RTL_FEATURE_MSI = (1 << 1), RTL_FEATURE_GMII = (1 << 2), - RTL_FEATURE_FW_LOADED = (1 << 3), }; struct rtl8169_counters { @@ -1826,8 +1822,6 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb) if (opts2 & RxVlanTag) __vlan_hwaccel_put_tag(skb, swab16(opts2 & 0xffff)); - - desc->opts2 = 0; } static int rtl8169_gset_tbi(struct net_device *dev, struct ethtool_cmd *cmd) @@ -2391,10 +2385,8 @@ static void rtl_apply_firmware(struct rtl8169_private *tp) struct rtl_fw *rtl_fw = tp->rtl_fw; /* TODO: release firmware once rtl_phy_write_fw signals failures. */ - if (!IS_ERR_OR_NULL(rtl_fw)) { + if (!IS_ERR_OR_NULL(rtl_fw)) rtl_phy_write_fw(tp, rtl_fw); - tp->features |= RTL_FEATURE_FW_LOADED; - } } static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val) @@ -2405,31 +2397,6 @@ static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val) rtl_apply_firmware(tp); } -static void r810x_aldps_disable(struct rtl8169_private *tp) -{ - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, 0x18, 0x0310); - msleep(100); -} - -static void r810x_aldps_enable(struct rtl8169_private *tp) -{ - if (!(tp->features & RTL_FEATURE_FW_LOADED)) - return; - - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, 0x18, 0x8310); -} - -static void r8168_aldps_enable_1(struct rtl8169_private *tp) -{ - if (!(tp->features & RTL_FEATURE_FW_LOADED)) - return; - - rtl_writephy(tp, 0x1f, 0x0000); - rtl_w1w0_phy(tp, 0x15, 0x1000, 0x0000); -} - static void rtl8169s_hw_phy_config(struct rtl8169_private *tp) { static const struct phy_reg phy_reg_init[] = { @@ -3220,8 +3187,6 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp) rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0400); rtl_writephy(tp, 0x1f, 0x0000); - r8168_aldps_enable_1(tp); - /* Broken BIOS workaround: feed GigaMAC registers with MAC address. */ rtl_rar_exgmac_set(tp, tp->dev->dev_addr); } @@ -3296,8 +3261,6 @@ static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x05, 0x8b85); rtl_w1w0_phy(tp, 0x06, 0x4000, 0x0000); rtl_writephy(tp, 0x1f, 0x0000); - - r8168_aldps_enable_1(tp); } static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp) @@ -3305,8 +3268,6 @@ static void rtl8168f_2_hw_phy_config(struct rtl8169_private *tp) rtl_apply_firmware(tp); rtl8168f_hw_phy_config(tp); - - r8168_aldps_enable_1(tp); } static void rtl8411_hw_phy_config(struct rtl8169_private *tp) @@ -3404,8 +3365,6 @@ static void rtl8411_hw_phy_config(struct rtl8169_private *tp) rtl_w1w0_phy(tp, 0x19, 0x0000, 0x0001); rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0400); rtl_writephy(tp, 0x1f, 0x0000); - - r8168_aldps_enable_1(tp); } static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp) @@ -3491,19 +3450,21 @@ static void rtl8105e_hw_phy_config(struct rtl8169_private *tp) }; /* Disable ALDPS before ram code */ - r810x_aldps_disable(tp); + rtl_writephy(tp, 0x1f, 0x0000); + rtl_writephy(tp, 0x18, 0x0310); + msleep(100); rtl_apply_firmware(tp); rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init)); - - r810x_aldps_enable(tp); } static void rtl8402_hw_phy_config(struct rtl8169_private *tp) { /* Disable ALDPS before setting firmware */ - r810x_aldps_disable(tp); + rtl_writephy(tp, 0x1f, 0x0000); + rtl_writephy(tp, 0x18, 0x0310); + msleep(20); rtl_apply_firmware(tp); @@ -3513,8 +3474,6 @@ static void rtl8402_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x10, 0x401f); rtl_writephy(tp, 0x19, 0x7030); rtl_writephy(tp, 0x1f, 0x0000); - - r810x_aldps_enable(tp); } static void rtl8106e_hw_phy_config(struct rtl8169_private *tp) @@ -3527,7 +3486,9 @@ static void rtl8106e_hw_phy_config(struct rtl8169_private *tp) }; /* Disable ALDPS before ram code */ - r810x_aldps_disable(tp); + rtl_writephy(tp, 0x1f, 0x0000); + rtl_writephy(tp, 0x18, 0x0310); + msleep(100); rtl_apply_firmware(tp); @@ -3535,8 +3496,6 @@ static void rtl8106e_hw_phy_config(struct rtl8169_private *tp) rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init)); rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); - - r810x_aldps_enable(tp); } static void rtl_hw_phy_config(struct net_device *dev) @@ -5053,6 +5012,8 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) RTL_W8(MaxTxPacketSize, EarlySize); + rtl_disable_clock_request(pdev); + RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); @@ -5061,8 +5022,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN); RTL_W32(MISC, RTL_R32(MISC) | PWM_EN); - RTL_W8(Config5, (RTL_R8(Config5) & ~Spi_en) | ASPM_en); - RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn); + RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en); } static void rtl_hw_start_8168f(struct rtl8169_private *tp) @@ -5087,12 +5047,13 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) RTL_W8(MaxTxPacketSize, EarlySize); + rtl_disable_clock_request(pdev); + RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN); - RTL_W32(MISC, RTL_R32(MISC) | PWM_EN | FORCE_CLK); - RTL_W8(Config5, (RTL_R8(Config5) & ~Spi_en) | ASPM_en); - RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn); + RTL_W32(MISC, RTL_R32(MISC) | PWM_EN); + RTL_W8(Config5, RTL_R8(Config5) & ~Spi_en); } static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) @@ -5149,10 +5110,8 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) rtl_w1w0_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC); RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); - RTL_W32(MISC, (RTL_R32(MISC) | FORCE_CLK) & ~RXDV_GATED_EN); + RTL_W32(MISC, RTL_R32(MISC) & ~RXDV_GATED_EN); RTL_W8(MaxTxPacketSize, EarlySize); - RTL_W8(Config5, RTL_R8(Config5) | ASPM_en); - RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn); rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); @@ -5368,9 +5327,6 @@ static void rtl_hw_start_8105e_1(struct rtl8169_private *tp) RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET); RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN); - RTL_W8(Config5, RTL_R8(Config5) | ASPM_en); - RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn); - RTL_W32(MISC, RTL_R32(MISC) | FORCE_CLK); rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1)); } @@ -5396,9 +5352,6 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) RTL_W32(TxConfig, RTL_R32(TxConfig) | TXCFG_AUTO_FIFO); RTL_W8(MCU, RTL_R8(MCU) & ~NOW_IS_OOB); - RTL_W8(Config5, RTL_R8(Config5) | ASPM_en); - RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn); - RTL_W32(MISC, RTL_R32(MISC) | FORCE_CLK); rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402)); @@ -5420,10 +5373,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(FuncEvent, RTL_R32(FuncEvent) | 0x002800); - RTL_W32(MISC, - (RTL_R32(MISC) | DISABLE_LAN_EN | FORCE_CLK) & ~EARLY_TALLY_EN); - RTL_W8(Config5, RTL_R8(Config5) | ASPM_en); - RTL_W8(Config2, RTL_R8(Config2) | ClkReqEn); + RTL_W32(MISC, (RTL_R32(MISC) | DISABLE_LAN_EN) & ~EARLY_TALLY_EN); RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET); RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN); } @@ -6064,8 +6014,6 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget !(status & (RxRWT | RxFOVF)) && (dev->features & NETIF_F_RXALL)) goto process_pkt; - - rtl8169_mark_to_asic(desc, rx_buf_sz); } else { struct sk_buff *skb; dma_addr_t addr; @@ -6086,16 +6034,14 @@ process_pkt: if (unlikely(rtl8169_fragmented_frame(status))) { dev->stats.rx_dropped++; dev->stats.rx_length_errors++; - rtl8169_mark_to_asic(desc, rx_buf_sz); - continue; + goto release_descriptor; } skb = rtl8169_try_rx_copy(tp->Rx_databuff[entry], tp, pkt_size, addr); - rtl8169_mark_to_asic(desc, rx_buf_sz); if (!skb) { dev->stats.rx_dropped++; - continue; + goto release_descriptor; } rtl8169_rx_csum(skb, status); @@ -6111,13 +6057,10 @@ process_pkt: tp->rx_stats.bytes += pkt_size; u64_stats_update_end(&tp->rx_stats.syncp); } - - /* Work around for AMD plateform. */ - if ((desc->opts2 & cpu_to_le32(0xfffe000)) && - (tp->mac_version == RTL_GIGA_MAC_VER_05)) { - desc->opts2 = 0; - cur_rx++; - } +release_descriptor: + desc->opts2 = 0; + wmb(); + rtl8169_mark_to_asic(desc, rx_buf_sz); } count = cur_rx - tp->cur_rx; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f07c061..b75f4b2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -69,7 +69,7 @@ #undef STMMAC_XMIT_DEBUG /*#define STMMAC_XMIT_DEBUG*/ -#ifdef STMMAC_TX_DEBUG +#ifdef STMMAC_XMIT_DEBUG #define TX_DBG(fmt, args...) printk(fmt, ## args) #else #define TX_DBG(fmt, args...) do { } while (0) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 0376a5e..0b9829f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -188,8 +188,6 @@ int stmmac_mdio_register(struct net_device *ndev) goto bus_register_fail; } - priv->mii = new_bus; - found = 0; for (addr = 0; addr < PHY_MAX_ADDR; addr++) { struct phy_device *phydev = new_bus->phy_map[addr]; @@ -237,8 +235,14 @@ int stmmac_mdio_register(struct net_device *ndev) } } - if (!found) + if (!found) { pr_warning("%s: No PHY found\n", ndev->name); + mdiobus_unregister(new_bus); + mdiobus_free(new_bus); + return -ENODEV; + } + + priv->mii = new_bus; return 0; diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 7992b3e..78ace59 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1801,7 +1801,7 @@ static void rhine_tx(struct net_device *dev) rp->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); } - dev_kfree_skb_irq(rp->tx_skbuff[entry]); + dev_kfree_skb(rp->tx_skbuff[entry]); rp->tx_skbuff[entry] = NULL; entry = (++rp->dirty_tx) % TX_RING_SIZE; } @@ -2010,11 +2010,7 @@ static void rhine_slow_event_task(struct work_struct *work) if (intr_status & IntrPCIErr) netif_warn(rp, hw, dev, "PCI error\n"); - napi_disable(&rp->napi); - rhine_irq_disable(rp); - /* Slow and safe. Consider __napi_schedule as a replacement ? */ - napi_enable(&rp->napi); - napi_schedule(&rp->napi); + iowrite16(RHINE_EVENT & 0xffff, rp->base + IntrEnable); out_unlock: mutex_unlock(&rp->task_lock); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 5fd6f46..e6fe0d8 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -84,7 +84,7 @@ struct hv_netvsc_packet { }; struct netvsc_device_info { - unsigned char mac_adr[6]; + unsigned char mac_adr[ETH_ALEN]; bool link_state; /* 0 - link up, 1 - link down */ int ring_size; }; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f825a62..8264f0e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -349,7 +349,7 @@ static int netvsc_set_mac_addr(struct net_device *ndev, void *p) struct net_device_context *ndevctx = netdev_priv(ndev); struct hv_device *hdev = ndevctx->device_ctx; struct sockaddr *addr = p; - char save_adr[14]; + char save_adr[ETH_ALEN]; unsigned char save_aatype; int err; diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 81f8f9e..fcbf680 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -77,6 +77,11 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb_orphan(skb); + /* Before queueing this packet to netif_rx(), + * make sure dst is refcounted. + */ + skb_dst_force(skb); + skb->protocol = eth_type_trans(skb, dev); /* it's OK to use per_cpu_ptr() because BHs are off */ diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 68a43fe..d3fb97d 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -822,7 +822,10 @@ static int macvlan_changelink(struct net_device *dev, static size_t macvlan_get_size(const struct net_device *dev) { - return nla_total_size(4); + return (0 + + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + ); } static int macvlan_fill_info(struct sk_buff *skb, diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index d5199cb..b5ddd50 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -36,8 +36,9 @@ MODULE_LICENSE("GPL"); /* IP101A/G - IP1001 */ #define IP10XX_SPEC_CTRL_STATUS 16 /* Spec. Control Register */ +#define IP1001_RXPHASE_SEL (1<<0) /* Add delay on RX_CLK */ +#define IP1001_TXPHASE_SEL (1<<1) /* Add delay on TX_CLK */ #define IP1001_SPEC_CTRL_STATUS_2 20 /* IP1001 Spec. Control Reg 2 */ -#define IP1001_PHASE_SEL_MASK 3 /* IP1001 RX/TXPHASE_SEL */ #define IP1001_APS_ON 11 /* IP1001 APS Mode bit */ #define IP101A_G_APS_ON 2 /* IP101A/G APS Mode bit */ #define IP101A_G_IRQ_CONF_STATUS 0x11 /* Conf Info IRQ & Status Reg */ @@ -138,19 +139,24 @@ static int ip1001_config_init(struct phy_device *phydev) if (c < 0) return c; - /* INTR pin used: speed/link/duplex will cause an interrupt */ - c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT); - if (c < 0) - return c; + if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) || + (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) || + (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) || + (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) { - if (phydev->interface == PHY_INTERFACE_MODE_RGMII) { - /* Additional delay (2ns) used to adjust RX clock phase - * at RGMII interface */ c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS); if (c < 0) return c; - c |= IP1001_PHASE_SEL_MASK; + c &= ~(IP1001_RXPHASE_SEL | IP1001_TXPHASE_SEL); + + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) + c |= (IP1001_RXPHASE_SEL | IP1001_TXPHASE_SEL); + else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + c |= IP1001_RXPHASE_SEL; + else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + c |= IP1001_TXPHASE_SEL; + c = phy_write(phydev, IP10XX_SPEC_CTRL_STATUS, c); if (c < 0) return c; @@ -167,6 +173,11 @@ static int ip101a_g_config_init(struct phy_device *phydev) if (c < 0) return c; + /* INTR pin used: speed/link/duplex will cause an interrupt */ + c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT); + if (c < 0) + return c; + /* Enable Auto Power Saving mode */ c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS); c |= IP101A_G_APS_ON; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 5d2a3f2..22dec9c 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -353,15 +353,6 @@ static int m88e1111_config_init(struct phy_device *phydev) int err; int temp; - /* Enable Fiber/Copper auto selection */ - temp = phy_read(phydev, MII_M1111_PHY_EXT_SR); - temp &= ~MII_M1111_HWCFG_FIBER_COPPER_AUTO; - phy_write(phydev, MII_M1111_PHY_EXT_SR, temp); - - temp = phy_read(phydev, MII_BMCR); - temp |= BMCR_RESET; - phy_write(phydev, MII_BMCR, temp); - if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) || (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) || (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) || diff --git a/drivers/net/tun.c b/drivers/net/tun.c index af372d0..2917a86 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -109,11 +109,11 @@ struct tap_filter { unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; }; -/* 1024 is probably a high enough limit: modern hypervisors seem to support on - * the order of 100-200 CPUs so this leaves us some breathing space if we want - * to match a queue per guest CPU. - */ -#define MAX_TAP_QUEUES 1024 +/* DEFAULT_MAX_NUM_RSS_QUEUES were choosed to let the rx/tx queues allocated for + * the netdevice to be fit in one page. So we can make sure the success of + * memory allocation. TODO: increase the limit. */ +#define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES +#define MAX_TAP_FLOWS 4096 #define TUN_FLOW_EXPIRE (3 * HZ) @@ -185,6 +185,8 @@ struct tun_struct { unsigned long ageing_time; unsigned int numdisabled; struct list_head disabled; + void *security; + u32 flow_count; }; static inline u32 tun_hashfn(u32 rxhash) @@ -218,6 +220,7 @@ static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, e->queue_index = queue_index; e->tun = tun; hlist_add_head_rcu(&e->hash_link, head); + ++tun->flow_count; } return e; } @@ -228,6 +231,7 @@ static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) e->rxhash, e->queue_index); hlist_del_rcu(&e->hash_link); kfree_rcu(e, rcu); + --tun->flow_count; } static void tun_flow_flush(struct tun_struct *tun) @@ -294,11 +298,12 @@ static void tun_flow_cleanup(unsigned long data) } static void tun_flow_update(struct tun_struct *tun, u32 rxhash, - u16 queue_index) + struct tun_file *tfile) { struct hlist_head *head; struct tun_flow_entry *e; unsigned long delay = tun->ageing_time; + u16 queue_index = tfile->queue_index; if (!rxhash) return; @@ -307,7 +312,9 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, rcu_read_lock(); - if (tun->numqueues == 1) + /* We may get a very small possibility of OOO during switching, not + * worth to optimize.*/ + if (tun->numqueues == 1 || tfile->detached) goto unlock; e = tun_flow_find(head, rxhash); @@ -317,7 +324,8 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, e->updated = jiffies; } else { spin_lock_bh(&tun->lock); - if (!tun_flow_find(head, rxhash)) + if (!tun_flow_find(head, rxhash) && + tun->flow_count < MAX_TAP_FLOWS) tun_flow_create(tun, head, rxhash, queue_index); if (!timer_pending(&tun->flow_gc_timer)) @@ -406,21 +414,21 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun = rtnl_dereference(tfile->tun); - if (tun) { + if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); dev = tun->dev; rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); - rcu_assign_pointer(tfile->tun, NULL); ntfile = rtnl_dereference(tun->tfiles[index]); ntfile->queue_index = index; --tun->numqueues; - if (clean) + if (clean) { + rcu_assign_pointer(tfile->tun, NULL); sock_put(&tfile->sk); - else + } else tun_disable_queue(tun, tfile); synchronize_net(); @@ -434,10 +442,13 @@ static void __tun_detach(struct tun_file *tfile, bool clean) } if (clean) { - if (tun && tun->numqueues == 0 && tun->numdisabled == 0 && - !(tun->flags & TUN_PERSIST)) - if (tun->dev->reg_state == NETREG_REGISTERED) + if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { + netif_carrier_off(tun->dev); + + if (!(tun->flags & TUN_PERSIST) && + tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); + } BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags)); @@ -465,6 +476,10 @@ static void tun_detach_all(struct net_device *dev) rcu_assign_pointer(tfile->tun, NULL); --tun->numqueues; } + list_for_each_entry(tfile, &tun->disabled, next) { + wake_up_all(&tfile->wq.wait); + rcu_assign_pointer(tfile->tun, NULL); + } BUG_ON(tun->numqueues != 0); synchronize_net(); @@ -490,8 +505,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file) struct tun_file *tfile = file->private_data; int err; + err = security_tun_dev_attach(tfile->socket.sk, tun->security); + if (err < 0) + goto out; + err = -EINVAL; - if (rtnl_dereference(tfile->tun)) + if (rtnl_dereference(tfile->tun) && !tfile->detached) goto out; err = -EBUSY; @@ -1190,7 +1209,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, tun->dev->stats.rx_packets++; tun->dev->stats.rx_bytes += len; - tun_flow_update(tun, rxhash, tfile->queue_index); + tun_flow_update(tun, rxhash, tfile); return total_len; } @@ -1373,6 +1392,7 @@ static void tun_free_netdev(struct net_device *dev) BUG_ON(!(list_empty(&tun->disabled))); tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); free_netdev(dev); } @@ -1562,7 +1582,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (tun_not_capable(tun)) return -EPERM; - err = security_tun_dev_attach(tfile->socket.sk); + err = security_tun_dev_open(tun->security); if (err < 0) return err; @@ -1577,6 +1597,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) else { char *name; unsigned long flags = 0; + int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? + MAX_TAP_QUEUES : 1; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1600,8 +1622,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) name = ifr->ifr_name; dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, - tun_setup, - MAX_TAP_QUEUES, MAX_TAP_QUEUES); + tun_setup, queues, queues); + if (!dev) return -ENOMEM; @@ -1619,7 +1641,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) spin_lock_init(&tun->lock); - security_tun_dev_post_create(&tfile->sk); + err = security_tun_dev_alloc_security(&tun->security); + if (err < 0) + goto err_free_dev; tun_net_init(dev); @@ -1644,10 +1668,10 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) device_create_file(&tun->dev->dev, &dev_attr_owner) || device_create_file(&tun->dev->dev, &dev_attr_group)) pr_err("Failed to create tun sysfs files\n"); - - netif_carrier_on(tun->dev); } + netif_carrier_on(tun->dev); + tun_debug(KERN_INFO, tun, "tun_set_iff\n"); if (ifr->ifr_flags & IFF_NO_PI) @@ -1789,19 +1813,24 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { tun = tfile->detached; - if (!tun) + if (!tun) { ret = -EINVAL; - else - ret = tun_attach(tun, file); + goto unlock; + } + ret = security_tun_dev_attach_queue(tun->security); + if (ret < 0) + goto unlock; + ret = tun_attach(tun, file); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); - if (!tun || !(tun->flags & TUN_TAP_MQ)) + if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached) ret = -EINVAL; else __tun_detach(tfile, false); } else ret = -EINVAL; +unlock: rtnl_unlock(); return ret; } diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 42f51c7..248d2dc 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -374,6 +374,21 @@ static const struct driver_info cdc_mbim_info = { .tx_fixup = cdc_mbim_tx_fixup, }; +/* MBIM and NCM devices should not need a ZLP after NTBs with + * dwNtbOutMaxSize length. This driver_info is for the exceptional + * devices requiring it anyway, allowing them to be supported without + * forcing the performance penalty on all the sane devices. + */ +static const struct driver_info cdc_mbim_info_zlp = { + .description = "CDC MBIM", + .flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN | FLAG_SEND_ZLP, + .bind = cdc_mbim_bind, + .unbind = cdc_mbim_unbind, + .manage_power = cdc_mbim_manage_power, + .rx_fixup = cdc_mbim_rx_fixup, + .tx_fixup = cdc_mbim_tx_fixup, +}; + static const struct usb_device_id mbim_devs[] = { /* This duplicate NCM entry is intentional. MBIM devices can * be disguised as NCM by default, and this is necessary to @@ -385,6 +400,10 @@ static const struct usb_device_id mbim_devs[] = { { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info, }, + /* Sierra Wireless MC7710 need ZLPs */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68a2, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&cdc_mbim_info_zlp, + }, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&cdc_mbim_info, }, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 71b6e92..00d3b2d 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -435,6 +435,13 @@ advance: len -= temp; } + /* some buggy devices have an IAD but no CDC Union */ + if (!ctx->union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) { + ctx->control = intf; + ctx->data = usb_ifnum_to_if(dev->udev, intf->cur_altsetting->desc.bInterfaceNumber + 1); + dev_dbg(&intf->dev, "CDC Union missing - got slave from IAD\n"); + } + /* check if we got everything */ if ((ctx->control == NULL) || (ctx->data == NULL) || ((!ctx->mbim_desc) && ((ctx->ether_desc == NULL) || (ctx->control != intf)))) @@ -497,7 +504,8 @@ advance: error2: usb_set_intfdata(ctx->control, NULL); usb_set_intfdata(ctx->data, NULL); - usb_driver_release_interface(driver, ctx->data); + if (ctx->data != ctx->control) + usb_driver_release_interface(driver, ctx->data); error: cdc_ncm_free((struct cdc_ncm_ctx *)dev->data[0]); dev->data[0] = 0; @@ -1155,6 +1163,20 @@ static const struct driver_info wwan_info = { .tx_fixup = cdc_ncm_tx_fixup, }; +/* Same as wwan_info, but with FLAG_NOARP */ +static const struct driver_info wwan_noarp_info = { + .description = "Mobile Broadband Network Device (NO ARP)", + .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET + | FLAG_WWAN | FLAG_NOARP, + .bind = cdc_ncm_bind, + .unbind = cdc_ncm_unbind, + .check_connect = cdc_ncm_check_connect, + .manage_power = usbnet_manage_power, + .status = cdc_ncm_status, + .rx_fixup = cdc_ncm_rx_fixup, + .tx_fixup = cdc_ncm_tx_fixup, +}; + static const struct usb_device_id cdc_devs[] = { /* Ericsson MBM devices like F5521gw */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO @@ -1193,6 +1215,16 @@ static const struct usb_device_id cdc_devs[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x46), .driver_info = (unsigned long)&wwan_info, }, + { USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x76), + .driver_info = (unsigned long)&wwan_info, + }, + + /* Infineon(now Intel) HSPA Modem platform */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1519, 0x0443, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, /* Generic CDC-NCM devices */ { USB_INTERFACE_INFO(USB_CLASS_COMM, diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 3f554c1..d7e9944 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -45,6 +45,12 @@ #define DM_MCAST_ADDR 0x16 /* 8 bytes */ #define DM_GPR_CTRL 0x1e #define DM_GPR_DATA 0x1f +#define DM_CHIP_ID 0x2c +#define DM_MODE_CTRL 0x91 /* only on dm9620 */ + +/* chip id values */ +#define ID_DM9601 0 +#define ID_DM9620 1 #define DM_MAX_MCAST 64 #define DM_MCAST_SIZE 8 @@ -53,7 +59,6 @@ #define DM_RX_OVERHEAD 7 /* 3 byte header + 4 byte crc tail */ #define DM_TIMEOUT 1000 - static int dm_read(struct usbnet *dev, u8 reg, u16 length, void *data) { int err; @@ -84,32 +89,23 @@ static int dm_write(struct usbnet *dev, u8 reg, u16 length, void *data) static int dm_write_reg(struct usbnet *dev, u8 reg, u8 value) { - return usbnet_write_cmd(dev, DM_WRITE_REGS, + return usbnet_write_cmd(dev, DM_WRITE_REG, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, reg, NULL, 0); } -static void dm_write_async_helper(struct usbnet *dev, u8 reg, u8 value, - u16 length, void *data) +static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) { usbnet_write_cmd_async(dev, DM_WRITE_REGS, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, - value, reg, data, length); -} - -static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) -{ - netdev_dbg(dev->net, "dm_write_async() reg=0x%02x length=%d\n", reg, length); - - dm_write_async_helper(dev, reg, 0, length, data); + 0, reg, data, length); } static void dm_write_reg_async(struct usbnet *dev, u8 reg, u8 value) { - netdev_dbg(dev->net, "dm_write_reg_async() reg=0x%02x value=0x%02x\n", - reg, value); - - dm_write_async_helper(dev, reg, value, 0, NULL); + usbnet_write_cmd_async(dev, DM_WRITE_REG, + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, + value, reg, NULL, 0); } static int dm_read_shared_word(struct usbnet *dev, int phy, u8 reg, __le16 *value) @@ -358,7 +354,7 @@ static const struct net_device_ops dm9601_netdev_ops = { static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf) { int ret; - u8 mac[ETH_ALEN]; + u8 mac[ETH_ALEN], id; ret = usbnet_get_endpoints(dev, intf); if (ret) @@ -399,6 +395,24 @@ static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf) __dm9601_set_mac_address(dev); } + if (dm_read_reg(dev, DM_CHIP_ID, &id) < 0) { + netdev_err(dev->net, "Error reading chip ID\n"); + ret = -ENODEV; + goto out; + } + + /* put dm9620 devices in dm9601 mode */ + if (id == ID_DM9620) { + u8 mode; + + if (dm_read_reg(dev, DM_MODE_CTRL, &mode) < 0) { + netdev_err(dev->net, "Error reading MODE_CTRL\n"); + ret = -ENODEV; + goto out; + } + dm_write_reg(dev, DM_MODE_CTRL, mode & 0x7f); + } + /* power up phy */ dm_write_reg(dev, DM_GPR_CTRL, 1); dm_write_reg(dev, DM_GPR_DATA, 0); @@ -581,6 +595,10 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0a46, 0x9000), /* DM9000E */ .driver_info = (unsigned long)&dm9601_info, }, + { + USB_DEVICE(0x0a46, 0x9620), /* DM9620 USB to Fast Ethernet Adapter */ + .driver_info = (unsigned long)&dm9601_info, + }, {}, // END }; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6a1ca50..19d9035 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -351,6 +351,10 @@ static const struct usb_device_id products[] = { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 1, 57), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* HUAWEI_INTERFACE_NDIS_CONTROL_QUALCOMM */ + USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x69), + .driver_info = (unsigned long)&qmi_wwan_info, + }, /* 2. Combined interface devices matching on class+protocol */ { /* Huawei E367 and possibly others in "Windows mode" */ @@ -361,6 +365,14 @@ static const struct usb_device_id products[] = { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 1, 17), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* HUAWEI_NDIS_SINGLE_INTERFACE_VDF */ + USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x37), + .driver_info = (unsigned long)&qmi_wwan_info, + }, + { /* HUAWEI_INTERFACE_NDIS_HW_QUALCOMM */ + USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, USB_CLASS_VENDOR_SPEC, 0x01, 0x67), + .driver_info = (unsigned long)&qmi_wwan_info, + }, { /* Pantech UML290, P4200 and more */ USB_VENDOR_AND_INTERFACE_INFO(0x106c, USB_CLASS_VENDOR_SPEC, 0xf0, 0xff), .driver_info = (unsigned long)&qmi_wwan_info, @@ -399,6 +411,7 @@ static const struct usb_device_id products[] = { }, /* 3. Combined interface devices matching on interface number */ + {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ {QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */ {QMI_FIXED_INTF(0x19d2, 0x0002, 1)}, {QMI_FIXED_INTF(0x19d2, 0x0012, 1)}, @@ -433,6 +446,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x0199, 1)}, /* ZTE MF820S */ {QMI_FIXED_INTF(0x19d2, 0x0200, 1)}, {QMI_FIXED_INTF(0x19d2, 0x0257, 3)}, /* ZTE MF821 */ + {QMI_FIXED_INTF(0x19d2, 0x0265, 4)}, /* ONDA MT8205 4G LTE */ {QMI_FIXED_INTF(0x19d2, 0x0284, 4)}, /* ZTE MF880 */ {QMI_FIXED_INTF(0x19d2, 0x0326, 4)}, /* ZTE MF821D */ {QMI_FIXED_INTF(0x19d2, 0x1008, 4)}, /* ZTE (Vodafone) K3570-Z */ @@ -459,6 +473,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */ {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ + {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ + {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 3d4bf01..5e33606 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -380,6 +380,12 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) unsigned long lockflags; size_t size = dev->rx_urb_size; + /* prevent rx skb allocation when error ratio is high */ + if (test_bit(EVENT_RX_KILL, &dev->flags)) { + usb_free_urb(urb); + return -ENOLINK; + } + skb = __netdev_alloc_skb_ip_align(dev->net, size, flags); if (!skb) { netif_dbg(dev, rx_err, dev->net, "no rx skb\n"); @@ -539,6 +545,17 @@ block: break; } + /* stop rx if packet error rate is high */ + if (++dev->pkt_cnt > 30) { + dev->pkt_cnt = 0; + dev->pkt_err = 0; + } else { + if (state == rx_cleanup) + dev->pkt_err++; + if (dev->pkt_err > 20) + set_bit(EVENT_RX_KILL, &dev->flags); + } + state = defer_bh(dev, skb, &dev->rxq, state); if (urb) { @@ -791,6 +808,11 @@ int usbnet_open (struct net_device *net) (dev->driver_info->flags & FLAG_FRAMING_AX) ? "ASIX" : "simple"); + /* reset rx error state */ + dev->pkt_cnt = 0; + dev->pkt_err = 0; + clear_bit(EVENT_RX_KILL, &dev->flags); + // delay posting reads until we're fully open tasklet_schedule (&dev->bh); if (info->manage_power) { @@ -1103,13 +1125,11 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, if (info->tx_fixup) { skb = info->tx_fixup (dev, skb, GFP_ATOMIC); if (!skb) { - if (netif_msg_tx_err(dev)) { - netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); - goto drop; - } else { - /* cdc_ncm collected packet; waits for more */ + /* packet collected; minidriver waiting for more */ + if (info->flags & FLAG_MULTI_PACKET) goto not_drop; - } + netif_dbg(dev, tx_err, dev->net, "can't tx_fixup skb\n"); + goto drop; } } length = skb->len; @@ -1254,6 +1274,9 @@ static void usbnet_bh (unsigned long param) } } + /* restart RX again after disabling due to high error rate */ + clear_bit(EVENT_RX_KILL, &dev->flags); + // waiting for all pending urbs to complete? if (dev->wait) { if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) { @@ -1448,6 +1471,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_WWAN) != 0) strcpy(net->name, "wwan%d"); + /* devices that cannot do ARP */ + if ((dev->driver_info->flags & FLAG_NOARP) != 0) + net->flags |= IFF_NOARP; + /* maybe the remote can't receive an Ethernet MTU */ if (net->mtu > (dev->hard_mtu - net->hard_header_len)) net->mtu = dev->hard_mtu - net->hard_header_len; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a6fcf15..35c00c5 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -26,6 +26,7 @@ #include <linux/scatterlist.h> #include <linux/if_vlan.h> #include <linux/slab.h> +#include <linux/cpu.h> static int napi_weight = 128; module_param(napi_weight, int, 0444); @@ -123,6 +124,12 @@ struct virtnet_info { /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; + + /* Per-cpu variable to show the mapping from CPU to virtqueue */ + int __percpu *vq_index; + + /* CPU hot plug notifier */ + struct notifier_block nb; }; struct skb_vnet_hdr { @@ -1013,32 +1020,75 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid) return 0; } -static void virtnet_set_affinity(struct virtnet_info *vi, bool set) +static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu) { int i; + int cpu; + + if (vi->affinity_hint_set) { + for (i = 0; i < vi->max_queue_pairs; i++) { + virtqueue_set_affinity(vi->rq[i].vq, -1); + virtqueue_set_affinity(vi->sq[i].vq, -1); + } + + vi->affinity_hint_set = false; + } + + i = 0; + for_each_online_cpu(cpu) { + if (cpu == hcpu) { + *per_cpu_ptr(vi->vq_index, cpu) = -1; + } else { + *per_cpu_ptr(vi->vq_index, cpu) = + ++i % vi->curr_queue_pairs; + } + } +} + +static void virtnet_set_affinity(struct virtnet_info *vi) +{ + int i; + int cpu; /* In multiqueue mode, when the number of cpu is equal to the number of * queue pairs, we let the queue pairs to be private to one cpu by * setting the affinity hint to eliminate the contention. */ - if ((vi->curr_queue_pairs == 1 || - vi->max_queue_pairs != num_online_cpus()) && set) { - if (vi->affinity_hint_set) - set = false; - else - return; + if (vi->curr_queue_pairs == 1 || + vi->max_queue_pairs != num_online_cpus()) { + virtnet_clean_affinity(vi, -1); + return; } - for (i = 0; i < vi->max_queue_pairs; i++) { - int cpu = set ? i : -1; + i = 0; + for_each_online_cpu(cpu) { virtqueue_set_affinity(vi->rq[i].vq, cpu); virtqueue_set_affinity(vi->sq[i].vq, cpu); + *per_cpu_ptr(vi->vq_index, cpu) = i; + i++; } - if (set) - vi->affinity_hint_set = true; - else - vi->affinity_hint_set = false; + vi->affinity_hint_set = true; +} + +static int virtnet_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + struct virtnet_info *vi = container_of(nfb, struct virtnet_info, nb); + + switch(action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + case CPU_DEAD: + virtnet_set_affinity(vi); + break; + case CPU_DOWN_PREPARE: + virtnet_clean_affinity(vi, (long)hcpu); + break; + default: + break; + } + return NOTIFY_OK; } static void virtnet_get_ringparam(struct net_device *dev, @@ -1082,13 +1132,15 @@ static int virtnet_set_channels(struct net_device *dev, if (queue_pairs > vi->max_queue_pairs) return -EINVAL; + get_online_cpus(); err = virtnet_set_queues(vi, queue_pairs); if (!err) { netif_set_real_num_tx_queues(dev, queue_pairs); netif_set_real_num_rx_queues(dev, queue_pairs); - virtnet_set_affinity(vi, true); + virtnet_set_affinity(vi); } + put_online_cpus(); return err; } @@ -1127,12 +1179,19 @@ static int virtnet_change_mtu(struct net_device *dev, int new_mtu) /* To avoid contending a lock hold by a vcpu who would exit to host, select the * txq based on the processor id. - * TODO: handle cpu hotplug. */ static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb) { - int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : - smp_processor_id(); + int txq; + struct virtnet_info *vi = netdev_priv(dev); + + if (skb_rx_queue_recorded(skb)) { + txq = skb_get_rx_queue(skb); + } else { + txq = *__this_cpu_ptr(vi->vq_index); + if (txq == -1) + txq = 0; + } while (unlikely(txq >= dev->real_num_tx_queues)) txq -= dev->real_num_tx_queues; @@ -1248,7 +1307,7 @@ static void virtnet_del_vqs(struct virtnet_info *vi) { struct virtio_device *vdev = vi->vdev; - virtnet_set_affinity(vi, false); + virtnet_clean_affinity(vi, -1); vdev->config->del_vqs(vdev); @@ -1371,7 +1430,10 @@ static int init_vqs(struct virtnet_info *vi) if (ret) goto err_free; - virtnet_set_affinity(vi, true); + get_online_cpus(); + virtnet_set_affinity(vi); + put_online_cpus(); + return 0; err_free: @@ -1453,6 +1515,10 @@ static int virtnet_probe(struct virtio_device *vdev) if (vi->stats == NULL) goto free; + vi->vq_index = alloc_percpu(int); + if (vi->vq_index == NULL) + goto free_stats; + mutex_init(&vi->config_lock); vi->config_enable = true; INIT_WORK(&vi->config_work, virtnet_config_changed_work); @@ -1476,7 +1542,7 @@ static int virtnet_probe(struct virtio_device *vdev) /* Allocate/initialize the rx/tx queues, and invoke find_vqs */ err = init_vqs(vi); if (err) - goto free_stats; + goto free_index; netif_set_real_num_tx_queues(dev, 1); netif_set_real_num_rx_queues(dev, 1); @@ -1499,6 +1565,13 @@ static int virtnet_probe(struct virtio_device *vdev) } } + vi->nb.notifier_call = &virtnet_cpu_callback; + err = register_hotcpu_notifier(&vi->nb); + if (err) { + pr_debug("virtio_net: registering cpu notifier failed\n"); + goto free_recv_bufs; + } + /* Assume link up if device can't report link status, otherwise get link status from config. */ if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { @@ -1520,6 +1593,8 @@ free_recv_bufs: free_vqs: cancel_delayed_work_sync(&vi->refill); virtnet_del_vqs(vi); +free_index: + free_percpu(vi->vq_index); free_stats: free_percpu(vi->stats); free: @@ -1543,6 +1618,8 @@ static void virtnet_remove(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; + unregister_hotcpu_notifier(&vi->nb); + /* Prevent config work handler from accessing the device. */ mutex_lock(&vi->config_lock); vi->config_enable = false; @@ -1554,6 +1631,7 @@ static void virtnet_remove(struct virtio_device *vdev) flush_work(&vi->config_work); + free_percpu(vi->vq_index); free_percpu(vi->stats); free_netdev(vi->dev); } diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index dc8913c..12c6440 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -154,8 +154,7 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue) if (ret & 1) { /* Link is up. */ printk(KERN_INFO "%s: NIC Link is Up %d Mbps\n", adapter->netdev->name, adapter->link_speed); - if (!netif_carrier_ok(adapter->netdev)) - netif_carrier_on(adapter->netdev); + netif_carrier_on(adapter->netdev); if (affectTxQueue) { for (i = 0; i < adapter->num_tx_queues; i++) @@ -165,8 +164,7 @@ vmxnet3_check_link(struct vmxnet3_adapter *adapter, bool affectTxQueue) } else { printk(KERN_INFO "%s: NIC Link is Down\n", adapter->netdev->name); - if (netif_carrier_ok(adapter->netdev)) - netif_carrier_off(adapter->netdev); + netif_carrier_off(adapter->netdev); if (affectTxQueue) { for (i = 0; i < adapter->num_tx_queues; i++) @@ -3061,6 +3059,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); netif_set_real_num_rx_queues(adapter->netdev, adapter->num_rx_queues); + netif_carrier_off(netdev); err = register_netdev(netdev); if (err) { diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c index 1d76ae8..530581c 100644 --- a/drivers/net/wimax/i2400m/netdev.c +++ b/drivers/net/wimax/i2400m/netdev.c @@ -156,7 +156,7 @@ void i2400m_wake_tx_work(struct work_struct *ws) struct i2400m *i2400m = container_of(ws, struct i2400m, wake_tx_ws); struct net_device *net_dev = i2400m->wimax_dev.net_dev; struct device *dev = i2400m_dev(i2400m); - struct sk_buff *skb = i2400m->wake_tx_skb; + struct sk_buff *skb; unsigned long flags; spin_lock_irqsave(&i2400m->tx_lock, flags); @@ -236,23 +236,26 @@ void i2400m_tx_prep_header(struct sk_buff *skb) void i2400m_net_wake_stop(struct i2400m *i2400m) { struct device *dev = i2400m_dev(i2400m); + struct sk_buff *wake_tx_skb; + unsigned long flags; d_fnstart(3, dev, "(i2400m %p)\n", i2400m); - /* See i2400m_hard_start_xmit(), references are taken there - * and here we release them if the work was still - * pending. Note we can't differentiate work not pending vs - * never scheduled, so the NULL check does that. */ - if (cancel_work_sync(&i2400m->wake_tx_ws) == 0 - && i2400m->wake_tx_skb != NULL) { - unsigned long flags; - struct sk_buff *wake_tx_skb; - spin_lock_irqsave(&i2400m->tx_lock, flags); - wake_tx_skb = i2400m->wake_tx_skb; /* compat help */ - i2400m->wake_tx_skb = NULL; /* compat help */ - spin_unlock_irqrestore(&i2400m->tx_lock, flags); + /* + * See i2400m_hard_start_xmit(), references are taken there and + * here we release them if the packet was still pending. + */ + cancel_work_sync(&i2400m->wake_tx_ws); + + spin_lock_irqsave(&i2400m->tx_lock, flags); + wake_tx_skb = i2400m->wake_tx_skb; + i2400m->wake_tx_skb = NULL; + spin_unlock_irqrestore(&i2400m->tx_lock, flags); + + if (wake_tx_skb) { i2400m_put(i2400m); kfree_skb(wake_tx_skb); } + d_fnend(3, dev, "(i2400m %p) = void\n", i2400m); } @@ -288,7 +291,7 @@ int i2400m_net_wake_tx(struct i2400m *i2400m, struct net_device *net_dev, * and if pending, release those resources. */ result = 0; spin_lock_irqsave(&i2400m->tx_lock, flags); - if (!work_pending(&i2400m->wake_tx_ws)) { + if (!i2400m->wake_tx_skb) { netif_stop_queue(net_dev); i2400m_get(i2400m); i2400m->wake_tx_skb = skb_get(skb); /* transfer ref count */ diff --git a/drivers/net/wireless/ath/ath9k/ar9003_calib.c b/drivers/net/wireless/ath/ath9k/ar9003_calib.c index 8b0d8dc..56317b0 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_calib.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_calib.c @@ -976,6 +976,8 @@ static bool ar9003_hw_init_cal(struct ath_hw *ah, AR_PHY_CL_TAB_1, AR_PHY_CL_TAB_2 }; + ar9003_hw_set_chain_masks(ah, ah->caps.rx_chainmask, ah->caps.tx_chainmask); + if (rtt) { if (!ar9003_hw_rtt_restore(ah, chan)) run_rtt_cal = true; diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c index ce19c09..3afc24b 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c @@ -586,32 +586,19 @@ static void ar9003_hw_init_bb(struct ath_hw *ah, ath9k_hw_synth_delay(ah, chan, synthDelay); } -static void ar9003_hw_set_chain_masks(struct ath_hw *ah, u8 rx, u8 tx) +void ar9003_hw_set_chain_masks(struct ath_hw *ah, u8 rx, u8 tx) { - switch (rx) { - case 0x5: + if (ah->caps.tx_chainmask == 5 || ah->caps.rx_chainmask == 5) REG_SET_BIT(ah, AR_PHY_ANALOG_SWAP, AR_PHY_SWAP_ALT_CHAIN); - case 0x3: - case 0x1: - case 0x2: - case 0x7: - REG_WRITE(ah, AR_PHY_RX_CHAINMASK, rx); - REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, rx); - break; - default: - break; - } + + REG_WRITE(ah, AR_PHY_RX_CHAINMASK, rx); + REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, rx); if ((ah->caps.hw_caps & ATH9K_HW_CAP_APM) && (tx == 0x7)) - REG_WRITE(ah, AR_SELFGEN_MASK, 0x3); - else - REG_WRITE(ah, AR_SELFGEN_MASK, tx); + tx = 3; - if (tx == 0x5) { - REG_SET_BIT(ah, AR_PHY_ANALOG_SWAP, - AR_PHY_SWAP_ALT_CHAIN); - } + REG_WRITE(ah, AR_SELFGEN_MASK, tx); } /* diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index 86e26a1..42794c5 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -317,7 +317,6 @@ struct ath_rx { u32 *rxlink; u32 num_pkts; unsigned int rxfilter; - spinlock_t rxbuflock; struct list_head rxbuf; struct ath_descdma rxdma; struct ath_buf *rx_bufptr; @@ -328,7 +327,6 @@ struct ath_rx { int ath_startrecv(struct ath_softc *sc); bool ath_stoprecv(struct ath_softc *sc); -void ath_flushrecv(struct ath_softc *sc); u32 ath_calcrxfilter(struct ath_softc *sc); int ath_rx_init(struct ath_softc *sc, int nbufs); void ath_rx_cleanup(struct ath_softc *sc); @@ -646,7 +644,6 @@ void ath_ant_comb_update(struct ath_softc *sc); enum sc_op_flags { SC_OP_INVALID, SC_OP_BEACONS, - SC_OP_RXFLUSH, SC_OP_ANI_RUN, SC_OP_PRIM_STA_VIF, SC_OP_HW_RESET, diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index 531fffd..2ca355e 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -147,6 +147,7 @@ static struct ath_buf *ath9k_beacon_generate(struct ieee80211_hw *hw, skb->len, DMA_TO_DEVICE); dev_kfree_skb_any(skb); bf->bf_buf_addr = 0; + bf->bf_mpdu = NULL; } skb = ieee80211_beacon_get(hw, vif); @@ -359,7 +360,6 @@ void ath9k_beacon_tasklet(unsigned long data) return; bf = ath9k_beacon_generate(sc->hw, vif); - WARN_ON(!bf); if (sc->beacon.bmisscnt != 0) { ath_dbg(common, BSTUCK, "resume beacon xmit after %u misses\n", diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 13ff9ed..e585fc8 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -861,7 +861,6 @@ static ssize_t read_file_recv(struct file *file, char __user *user_buf, RXS_ERR("RX-LENGTH-ERR", rx_len_err); RXS_ERR("RX-OOM-ERR", rx_oom_err); RXS_ERR("RX-RATE-ERR", rx_rate_err); - RXS_ERR("RX-DROP-RXFLUSH", rx_drop_rxflush); RXS_ERR("RX-TOO-MANY-FRAGS", rx_too_many_frags_err); PHY_ERR("UNDERRUN ERR", ATH9K_PHYERR_UNDERRUN); diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h index 375c3b4..6df2ab6 100644 --- a/drivers/net/wireless/ath/ath9k/debug.h +++ b/drivers/net/wireless/ath/ath9k/debug.h @@ -216,7 +216,6 @@ struct ath_tx_stats { * @rx_oom_err: No. of frames dropped due to OOM issues. * @rx_rate_err: No. of frames dropped due to rate errors. * @rx_too_many_frags_err: Frames dropped due to too-many-frags received. - * @rx_drop_rxflush: No. of frames dropped due to RX-FLUSH. * @rx_beacons: No. of beacons received. * @rx_frags: No. of rx-fragements received. */ @@ -235,7 +234,6 @@ struct ath_rx_stats { u32 rx_oom_err; u32 rx_rate_err; u32 rx_too_many_frags_err; - u32 rx_drop_rxflush; u32 rx_beacons; u32 rx_frags; }; diff --git a/drivers/net/wireless/ath/ath9k/htc_hst.c b/drivers/net/wireless/ath/ath9k/htc_hst.c index 4a9570d..aac4a40 100644 --- a/drivers/net/wireless/ath/ath9k/htc_hst.c +++ b/drivers/net/wireless/ath/ath9k/htc_hst.c @@ -344,6 +344,8 @@ void ath9k_htc_txcompletion_cb(struct htc_target *htc_handle, endpoint->ep_callbacks.tx(endpoint->ep_callbacks.priv, skb, htc_hdr->endpoint_id, txok); + } else { + kfree_skb(skb); } } diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index 7f1a8e9..9d26fc5 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -1066,6 +1066,7 @@ void ar9003_paprd_setup_gain_table(struct ath_hw *ah, int chain); int ar9003_paprd_init_table(struct ath_hw *ah); bool ar9003_paprd_is_done(struct ath_hw *ah); bool ar9003_is_paprd_enabled(struct ath_hw *ah); +void ar9003_hw_set_chain_masks(struct ath_hw *ah, u8 rx, u8 tx); /* Hardware family op attach helpers */ void ar5008_hw_attach_phy_ops(struct ath_hw *ah); diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index be30a9a..dd91f8f 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -182,7 +182,7 @@ static void ath_restart_work(struct ath_softc *sc) ath_start_ani(sc); } -static bool ath_prepare_reset(struct ath_softc *sc, bool retry_tx, bool flush) +static bool ath_prepare_reset(struct ath_softc *sc, bool retry_tx) { struct ath_hw *ah = sc->sc_ah; bool ret = true; @@ -202,14 +202,6 @@ static bool ath_prepare_reset(struct ath_softc *sc, bool retry_tx, bool flush) if (!ath_drain_all_txq(sc, retry_tx)) ret = false; - if (!flush) { - if (ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) - ath_rx_tasklet(sc, 1, true); - ath_rx_tasklet(sc, 1, false); - } else { - ath_flushrecv(sc); - } - return ret; } @@ -262,11 +254,11 @@ static int ath_reset_internal(struct ath_softc *sc, struct ath9k_channel *hchan, struct ath_common *common = ath9k_hw_common(ah); struct ath9k_hw_cal_data *caldata = NULL; bool fastcc = true; - bool flush = false; int r; __ath_cancel_work(sc); + tasklet_disable(&sc->intr_tq); spin_lock_bh(&sc->sc_pcu_lock); if (!(sc->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)) { @@ -276,11 +268,10 @@ static int ath_reset_internal(struct ath_softc *sc, struct ath9k_channel *hchan, if (!hchan) { fastcc = false; - flush = true; hchan = ah->curchan; } - if (!ath_prepare_reset(sc, retry_tx, flush)) + if (!ath_prepare_reset(sc, retry_tx)) fastcc = false; ath_dbg(common, CONFIG, "Reset to %u MHz, HT40: %d fastcc: %d\n", @@ -302,6 +293,8 @@ static int ath_reset_internal(struct ath_softc *sc, struct ath9k_channel *hchan, out: spin_unlock_bh(&sc->sc_pcu_lock); + tasklet_enable(&sc->intr_tq); + return r; } @@ -804,7 +797,7 @@ static void ath9k_stop(struct ieee80211_hw *hw) ath9k_hw_cfg_gpio_input(ah, ah->led_pin); } - ath_prepare_reset(sc, false, true); + ath_prepare_reset(sc, false); if (sc->rx.frag) { dev_kfree_skb_any(sc->rx.frag); @@ -1833,6 +1826,9 @@ static u32 fill_chainmask(u32 cap, u32 new) static bool validate_antenna_mask(struct ath_hw *ah, u32 val) { + if (AR_SREV_9300_20_OR_LATER(ah)) + return true; + switch (val & 0x7) { case 0x1: case 0x3: diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index d4df98a..90752f2 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -254,8 +254,6 @@ rx_init_fail: static void ath_edma_start_recv(struct ath_softc *sc) { - spin_lock_bh(&sc->rx.rxbuflock); - ath9k_hw_rxena(sc->sc_ah); ath_rx_addbuffer_edma(sc, ATH9K_RX_QUEUE_HP, @@ -267,8 +265,6 @@ static void ath_edma_start_recv(struct ath_softc *sc) ath_opmode_init(sc); ath9k_hw_startpcureceive(sc->sc_ah, !!(sc->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)); - - spin_unlock_bh(&sc->rx.rxbuflock); } static void ath_edma_stop_recv(struct ath_softc *sc) @@ -285,8 +281,6 @@ int ath_rx_init(struct ath_softc *sc, int nbufs) int error = 0; spin_lock_init(&sc->sc_pcu_lock); - spin_lock_init(&sc->rx.rxbuflock); - clear_bit(SC_OP_RXFLUSH, &sc->sc_flags); common->rx_bufsize = IEEE80211_MAX_MPDU_LEN / 2 + sc->sc_ah->caps.rx_status_len; @@ -447,7 +441,6 @@ int ath_startrecv(struct ath_softc *sc) return 0; } - spin_lock_bh(&sc->rx.rxbuflock); if (list_empty(&sc->rx.rxbuf)) goto start_recv; @@ -468,26 +461,31 @@ start_recv: ath_opmode_init(sc); ath9k_hw_startpcureceive(ah, !!(sc->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)); - spin_unlock_bh(&sc->rx.rxbuflock); - return 0; } +static void ath_flushrecv(struct ath_softc *sc) +{ + if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) + ath_rx_tasklet(sc, 1, true); + ath_rx_tasklet(sc, 1, false); +} + bool ath_stoprecv(struct ath_softc *sc) { struct ath_hw *ah = sc->sc_ah; bool stopped, reset = false; - spin_lock_bh(&sc->rx.rxbuflock); ath9k_hw_abortpcurecv(ah); ath9k_hw_setrxfilter(ah, 0); stopped = ath9k_hw_stopdmarecv(ah, &reset); + ath_flushrecv(sc); + if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) ath_edma_stop_recv(sc); else sc->rx.rxlink = NULL; - spin_unlock_bh(&sc->rx.rxbuflock); if (!(ah->ah_flags & AH_UNPLUGGED) && unlikely(!stopped)) { @@ -499,15 +497,6 @@ bool ath_stoprecv(struct ath_softc *sc) return stopped && !reset; } -void ath_flushrecv(struct ath_softc *sc) -{ - set_bit(SC_OP_RXFLUSH, &sc->sc_flags); - if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) - ath_rx_tasklet(sc, 1, true); - ath_rx_tasklet(sc, 1, false); - clear_bit(SC_OP_RXFLUSH, &sc->sc_flags); -} - static bool ath_beacon_dtim_pending_cab(struct sk_buff *skb) { /* Check whether the Beacon frame has DTIM indicating buffered bc/mc */ @@ -744,6 +733,7 @@ static struct ath_buf *ath_get_next_rx_buf(struct ath_softc *sc, return NULL; } + list_del(&bf->list); if (!bf->bf_mpdu) return bf; @@ -1059,16 +1049,12 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) dma_type = DMA_FROM_DEVICE; qtype = hp ? ATH9K_RX_QUEUE_HP : ATH9K_RX_QUEUE_LP; - spin_lock_bh(&sc->rx.rxbuflock); tsf = ath9k_hw_gettsf64(ah); tsf_lower = tsf & 0xffffffff; do { bool decrypt_error = false; - /* If handling rx interrupt and flush is in progress => exit */ - if (test_bit(SC_OP_RXFLUSH, &sc->sc_flags) && (flush == 0)) - break; memset(&rs, 0, sizeof(rs)); if (edma) @@ -1111,15 +1097,6 @@ int ath_rx_tasklet(struct ath_softc *sc, int flush, bool hp) ath_debug_stat_rx(sc, &rs); - /* - * If we're asked to flush receive queue, directly - * chain it back at the queue without processing it. - */ - if (test_bit(SC_OP_RXFLUSH, &sc->sc_flags)) { - RX_STAT_INC(rx_drop_rxflush); - goto requeue_drop_frag; - } - memset(rxs, 0, sizeof(struct ieee80211_rx_status)); rxs->mactime = (tsf & ~0xffffffffULL) | rs.rs_tstamp; @@ -1254,19 +1231,18 @@ requeue_drop_frag: sc->rx.frag = NULL; } requeue: + list_add_tail(&bf->list, &sc->rx.rxbuf); + if (flush) + continue; + if (edma) { - list_add_tail(&bf->list, &sc->rx.rxbuf); ath_rx_edma_buf_link(sc, qtype); } else { - list_move_tail(&bf->list, &sc->rx.rxbuf); ath_rx_buf_link(sc, bf); - if (!flush) - ath9k_hw_rxena(ah); + ath9k_hw_rxena(ah); } } while (1); - spin_unlock_bh(&sc->rx.rxbuflock); - if (!(ah->imask & ATH9K_INT_RXEOL)) { ah->imask |= (ATH9K_INT_RXEOL | ATH9K_INT_RXORN); ath9k_hw_set_interrupts(ah); diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c index 1fbd8ec..e5fd209 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c @@ -36,6 +36,7 @@ #include "debug.h" #define N_TX_QUEUES 4 /* #tx queues on mac80211<->driver interface */ +#define BRCMS_FLUSH_TIMEOUT 500 /* msec */ /* Flags we support */ #define MAC_FILTERS (FIF_PROMISC_IN_BSS | \ @@ -708,16 +709,29 @@ static void brcms_ops_rfkill_poll(struct ieee80211_hw *hw) wiphy_rfkill_set_hw_state(wl->pub->ieee_hw->wiphy, blocked); } +static bool brcms_tx_flush_completed(struct brcms_info *wl) +{ + bool result; + + spin_lock_bh(&wl->lock); + result = brcms_c_tx_flush_completed(wl->wlc); + spin_unlock_bh(&wl->lock); + return result; +} + static void brcms_ops_flush(struct ieee80211_hw *hw, bool drop) { struct brcms_info *wl = hw->priv; + int ret; no_printk("%s: drop = %s\n", __func__, drop ? "true" : "false"); - /* wait for packet queue and dma fifos to run empty */ - spin_lock_bh(&wl->lock); - brcms_c_wait_for_tx_completion(wl->wlc, drop); - spin_unlock_bh(&wl->lock); + ret = wait_event_timeout(wl->tx_flush_wq, + brcms_tx_flush_completed(wl), + msecs_to_jiffies(BRCMS_FLUSH_TIMEOUT)); + + brcms_dbg_mac80211(wl->wlc->hw->d11core, + "ret=%d\n", jiffies_to_msecs(ret)); } static const struct ieee80211_ops brcms_ops = { @@ -772,6 +786,7 @@ void brcms_dpc(unsigned long data) done: spin_unlock_bh(&wl->lock); + wake_up(&wl->tx_flush_wq); } /* @@ -1020,6 +1035,8 @@ static struct brcms_info *brcms_attach(struct bcma_device *pdev) atomic_set(&wl->callbacks, 0); + init_waitqueue_head(&wl->tx_flush_wq); + /* setup the bottom half handler */ tasklet_init(&wl->tasklet, brcms_dpc, (unsigned long) wl); @@ -1407,9 +1424,10 @@ void brcms_add_timer(struct brcms_timer *t, uint ms, int periodic) #endif t->ms = ms; t->periodic = (bool) periodic; - t->set = true; - - atomic_inc(&t->wl->callbacks); + if (!t->set) { + t->set = true; + atomic_inc(&t->wl->callbacks); + } ieee80211_queue_delayed_work(hw, &t->dly_wrk, msecs_to_jiffies(ms)); } @@ -1608,13 +1626,3 @@ bool brcms_rfkill_set_hw_state(struct brcms_info *wl) spin_lock_bh(&wl->lock); return blocked; } - -/* - * precondition: perimeter lock has been acquired - */ -void brcms_msleep(struct brcms_info *wl, uint ms) -{ - spin_unlock_bh(&wl->lock); - msleep(ms); - spin_lock_bh(&wl->lock); -} diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h index 9358bd5..947ccac 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.h @@ -68,6 +68,8 @@ struct brcms_info { spinlock_t lock; /* per-device perimeter lock */ spinlock_t isr_lock; /* per-device ISR synchronization lock */ + /* tx flush */ + wait_queue_head_t tx_flush_wq; /* timer related fields */ atomic_t callbacks; /* # outstanding callback functions */ @@ -100,7 +102,6 @@ extern struct brcms_timer *brcms_init_timer(struct brcms_info *wl, extern void brcms_free_timer(struct brcms_timer *timer); extern void brcms_add_timer(struct brcms_timer *timer, uint ms, int periodic); extern bool brcms_del_timer(struct brcms_timer *timer); -extern void brcms_msleep(struct brcms_info *wl, uint ms); extern void brcms_dpc(unsigned long data); extern void brcms_timer(struct brcms_timer *t); extern void brcms_fatal_error(struct brcms_info *wl); diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c index 17594de..8b58390 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/main.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c @@ -1027,7 +1027,6 @@ brcms_c_dotxstatus(struct brcms_c_info *wlc, struct tx_status *txs) static bool brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal) { - bool morepending = false; struct bcma_device *core; struct tx_status txstatus, *txs; u32 s1, s2; @@ -1041,23 +1040,20 @@ brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal) txs = &txstatus; core = wlc_hw->d11core; *fatal = false; - s1 = bcma_read32(core, D11REGOFFS(frmtxstatus)); - while (!(*fatal) - && (s1 & TXS_V)) { - /* !give others some time to run! */ - if (n >= max_tx_num) { - morepending = true; - break; - } + while (n < max_tx_num) { + s1 = bcma_read32(core, D11REGOFFS(frmtxstatus)); if (s1 == 0xffffffff) { brcms_err(core, "wl%d: %s: dead chip\n", wlc_hw->unit, __func__); *fatal = true; return false; } - s2 = bcma_read32(core, D11REGOFFS(frmtxstatus2)); + /* only process when valid */ + if (!(s1 & TXS_V)) + break; + s2 = bcma_read32(core, D11REGOFFS(frmtxstatus2)); txs->status = s1 & TXS_STATUS_MASK; txs->frameid = (s1 & TXS_FID_MASK) >> TXS_FID_SHIFT; txs->sequence = s2 & TXS_SEQ_MASK; @@ -1065,15 +1061,12 @@ brcms_b_txstatus(struct brcms_hardware *wlc_hw, bool bound, bool *fatal) txs->lasttxtime = 0; *fatal = brcms_c_dotxstatus(wlc_hw->wlc, txs); - - s1 = bcma_read32(core, D11REGOFFS(frmtxstatus)); + if (*fatal == true) + return false; n++; } - if (*fatal) - return false; - - return morepending; + return n >= max_tx_num; } static void brcms_c_tbtt(struct brcms_c_info *wlc) @@ -7518,25 +7511,16 @@ int brcms_c_get_curband(struct brcms_c_info *wlc) return wlc->band->bandunit; } -void brcms_c_wait_for_tx_completion(struct brcms_c_info *wlc, bool drop) +bool brcms_c_tx_flush_completed(struct brcms_c_info *wlc) { - int timeout = 20; int i; /* Kick DMA to send any pending AMPDU */ for (i = 0; i < ARRAY_SIZE(wlc->hw->di); i++) if (wlc->hw->di[i]) - dma_txflush(wlc->hw->di[i]); - - /* wait for queue and DMA fifos to run dry */ - while (brcms_txpktpendtot(wlc) > 0) { - brcms_msleep(wlc->wl, 1); - - if (--timeout == 0) - break; - } + dma_kick_tx(wlc->hw->di[i]); - WARN_ON_ONCE(timeout == 0); + return !brcms_txpktpendtot(wlc); } void brcms_c_set_beacon_listen_interval(struct brcms_c_info *wlc, u8 interval) diff --git a/drivers/net/wireless/brcm80211/brcmsmac/pub.h b/drivers/net/wireless/brcm80211/brcmsmac/pub.h index 4fb2834..b0f14b7 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/pub.h +++ b/drivers/net/wireless/brcm80211/brcmsmac/pub.h @@ -314,8 +314,6 @@ extern void brcms_c_associate_upd(struct brcms_c_info *wlc, bool state); extern void brcms_c_scan_start(struct brcms_c_info *wlc); extern void brcms_c_scan_stop(struct brcms_c_info *wlc); extern int brcms_c_get_curband(struct brcms_c_info *wlc); -extern void brcms_c_wait_for_tx_completion(struct brcms_c_info *wlc, - bool drop); extern int brcms_c_set_channel(struct brcms_c_info *wlc, u16 channel); extern int brcms_c_set_rate_limit(struct brcms_c_info *wlc, u16 srl, u16 lrl); extern void brcms_c_get_current_rateset(struct brcms_c_info *wlc, @@ -332,5 +330,6 @@ extern int brcms_c_set_tx_power(struct brcms_c_info *wlc, int txpwr); extern int brcms_c_get_tx_power(struct brcms_c_info *wlc); extern bool brcms_c_check_radio_disabled(struct brcms_c_info *wlc); extern void brcms_c_mute(struct brcms_c_info *wlc, bool on); +extern bool brcms_c_tx_flush_completed(struct brcms_c_info *wlc); #endif /* _BRCM_PUB_H_ */ diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index d92b21a..b3ab7b7 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -2181,9 +2181,10 @@ static void isr_indicate_rf_kill(struct ipw2100_priv *priv, u32 status) mod_delayed_work(system_wq, &priv->rf_kill, round_jiffies_relative(HZ)); } -static void send_scan_event(void *data) +static void ipw2100_scan_event(struct work_struct *work) { - struct ipw2100_priv *priv = data; + struct ipw2100_priv *priv = container_of(work, struct ipw2100_priv, + scan_event.work); union iwreq_data wrqu; wrqu.data.length = 0; @@ -2191,18 +2192,6 @@ static void send_scan_event(void *data) wireless_send_event(priv->net_dev, SIOCGIWSCAN, &wrqu, NULL); } -static void ipw2100_scan_event_later(struct work_struct *work) -{ - send_scan_event(container_of(work, struct ipw2100_priv, - scan_event_later.work)); -} - -static void ipw2100_scan_event_now(struct work_struct *work) -{ - send_scan_event(container_of(work, struct ipw2100_priv, - scan_event_now)); -} - static void isr_scan_complete(struct ipw2100_priv *priv, u32 status) { IPW_DEBUG_SCAN("scan complete\n"); @@ -2212,13 +2201,11 @@ static void isr_scan_complete(struct ipw2100_priv *priv, u32 status) /* Only userspace-requested scan completion events go out immediately */ if (!priv->user_requested_scan) { - if (!delayed_work_pending(&priv->scan_event_later)) - schedule_delayed_work(&priv->scan_event_later, - round_jiffies_relative(msecs_to_jiffies(4000))); + schedule_delayed_work(&priv->scan_event, + round_jiffies_relative(msecs_to_jiffies(4000))); } else { priv->user_requested_scan = 0; - cancel_delayed_work(&priv->scan_event_later); - schedule_work(&priv->scan_event_now); + mod_delayed_work(system_wq, &priv->scan_event, 0); } } @@ -4459,8 +4446,7 @@ static void ipw2100_kill_works(struct ipw2100_priv *priv) cancel_delayed_work_sync(&priv->wx_event_work); cancel_delayed_work_sync(&priv->hang_check); cancel_delayed_work_sync(&priv->rf_kill); - cancel_work_sync(&priv->scan_event_now); - cancel_delayed_work_sync(&priv->scan_event_later); + cancel_delayed_work_sync(&priv->scan_event); } static int ipw2100_tx_allocate(struct ipw2100_priv *priv) @@ -6195,8 +6181,7 @@ static struct net_device *ipw2100_alloc_device(struct pci_dev *pci_dev, INIT_DELAYED_WORK(&priv->wx_event_work, ipw2100_wx_event_work); INIT_DELAYED_WORK(&priv->hang_check, ipw2100_hang_check); INIT_DELAYED_WORK(&priv->rf_kill, ipw2100_rf_kill); - INIT_WORK(&priv->scan_event_now, ipw2100_scan_event_now); - INIT_DELAYED_WORK(&priv->scan_event_later, ipw2100_scan_event_later); + INIT_DELAYED_WORK(&priv->scan_event, ipw2100_scan_event); tasklet_init(&priv->irq_tasklet, (void (*)(unsigned long)) ipw2100_irq_tasklet, (unsigned long)priv); diff --git a/drivers/net/wireless/ipw2x00/ipw2100.h b/drivers/net/wireless/ipw2x00/ipw2100.h index 5fe17cb..c6d7879 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.h +++ b/drivers/net/wireless/ipw2x00/ipw2100.h @@ -577,8 +577,7 @@ struct ipw2100_priv { struct delayed_work wx_event_work; struct delayed_work hang_check; struct delayed_work rf_kill; - struct work_struct scan_event_now; - struct delayed_work scan_event_later; + struct delayed_work scan_event; int user_requested_scan; diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c index 844f201..2c2d6db 100644 --- a/drivers/net/wireless/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/ipw2x00/ipw2200.c @@ -4480,18 +4480,11 @@ static void handle_scan_event(struct ipw_priv *priv) { /* Only userspace-requested scan completion events go out immediately */ if (!priv->user_requested_scan) { - if (!delayed_work_pending(&priv->scan_event)) - schedule_delayed_work(&priv->scan_event, - round_jiffies_relative(msecs_to_jiffies(4000))); + schedule_delayed_work(&priv->scan_event, + round_jiffies_relative(msecs_to_jiffies(4000))); } else { - union iwreq_data wrqu; - priv->user_requested_scan = 0; - cancel_delayed_work(&priv->scan_event); - - wrqu.data.length = 0; - wrqu.data.flags = 0; - wireless_send_event(priv->net_dev, SIOCGIWSCAN, &wrqu, NULL); + mod_delayed_work(system_wq, &priv->scan_event, 0); } } diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c index 7e16d10..90b8970 100644 --- a/drivers/net/wireless/iwlegacy/common.c +++ b/drivers/net/wireless/iwlegacy/common.c @@ -3958,17 +3958,21 @@ il_connection_init_rx_config(struct il_priv *il) memset(&il->staging, 0, sizeof(il->staging)); - if (!il->vif) { + switch (il->iw_mode) { + case NL80211_IFTYPE_UNSPECIFIED: il->staging.dev_type = RXON_DEV_TYPE_ESS; - } else if (il->vif->type == NL80211_IFTYPE_STATION) { + break; + case NL80211_IFTYPE_STATION: il->staging.dev_type = RXON_DEV_TYPE_ESS; il->staging.filter_flags = RXON_FILTER_ACCEPT_GRP_MSK; - } else if (il->vif->type == NL80211_IFTYPE_ADHOC) { + break; + case NL80211_IFTYPE_ADHOC: il->staging.dev_type = RXON_DEV_TYPE_IBSS; il->staging.flags = RXON_FLG_SHORT_PREAMBLE_MSK; il->staging.filter_flags = RXON_FILTER_BCON_AWARE_MSK | RXON_FILTER_ACCEPT_GRP_MSK; - } else { + break; + default: IL_ERR("Unsupported interface type %d\n", il->vif->type); return; } @@ -4550,8 +4554,7 @@ out: EXPORT_SYMBOL(il_mac_add_interface); static void -il_teardown_interface(struct il_priv *il, struct ieee80211_vif *vif, - bool mode_change) +il_teardown_interface(struct il_priv *il, struct ieee80211_vif *vif) { lockdep_assert_held(&il->mutex); @@ -4560,9 +4563,7 @@ il_teardown_interface(struct il_priv *il, struct ieee80211_vif *vif, il_force_scan_end(il); } - if (!mode_change) - il_set_mode(il); - + il_set_mode(il); } void @@ -4575,8 +4576,8 @@ il_mac_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) WARN_ON(il->vif != vif); il->vif = NULL; - - il_teardown_interface(il, vif, false); + il->iw_mode = NL80211_IFTYPE_UNSPECIFIED; + il_teardown_interface(il, vif); memset(il->bssid, 0, ETH_ALEN); D_MAC80211("leave\n"); @@ -4685,18 +4686,10 @@ il_mac_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif, } /* success */ - il_teardown_interface(il, vif, true); vif->type = newtype; vif->p2p = false; - err = il_set_mode(il); - WARN_ON(err); - /* - * We've switched internally, but submitting to the - * device may have failed for some reason. Mask this - * error, because otherwise mac80211 will not switch - * (and set the interface type back) and we'll be - * out of sync with it. - */ + il->iw_mode = newtype; + il_teardown_interface(il, vif); err = 0; out: diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c index a790599..2797964 100644 --- a/drivers/net/wireless/iwlwifi/dvm/tx.c +++ b/drivers/net/wireless/iwlwifi/dvm/tx.c @@ -1079,6 +1079,8 @@ static void iwlagn_set_tx_status(struct iwl_priv *priv, { u16 status = le16_to_cpu(tx_resp->status.status); + info->flags &= ~IEEE80211_TX_CTL_AMPDU; + info->status.rates[0].count = tx_resp->failure_frame + 1; info->flags |= iwl_tx_status_to_mac80211(status); iwlagn_hwrate_to_tx_control(priv, le32_to_cpu(tx_resp->rate_n_flags), @@ -1151,6 +1153,13 @@ int iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb, next_reclaimed = ssn; } + if (tid != IWL_TID_NON_QOS) { + priv->tid_data[sta_id][tid].next_reclaimed = + next_reclaimed; + IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n", + next_reclaimed); + } + iwl_trans_reclaim(priv->trans, txq_id, ssn, &skbs); iwlagn_check_ratid_empty(priv, sta_id, tid); @@ -1201,28 +1210,11 @@ int iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb, if (!is_agg) iwlagn_non_agg_tx_status(priv, ctx, hdr->addr1); - /* - * W/A for FW bug - the seq_ctl isn't updated when the - * queues are flushed. Fetch it from the packet itself - */ - if (!is_agg && status == TX_STATUS_FAIL_FIFO_FLUSHED) { - next_reclaimed = le16_to_cpu(hdr->seq_ctrl); - next_reclaimed = - SEQ_TO_SN(next_reclaimed + 0x10); - } - is_offchannel_skb = (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN); freed++; } - if (tid != IWL_TID_NON_QOS) { - priv->tid_data[sta_id][tid].next_reclaimed = - next_reclaimed; - IWL_DEBUG_TX_REPLY(priv, "Next reclaimed packet:%d\n", - next_reclaimed); - } - WARN_ON(!is_agg && freed != 1); /* diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index efe525b..cdb11b3 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -1459,7 +1459,7 @@ mwifiex_cfg80211_assoc(struct mwifiex_private *priv, size_t ssid_len, u8 *ssid, struct cfg80211_ssid req_ssid; int ret, auth_type = 0; struct cfg80211_bss *bss = NULL; - u8 is_scanning_required = 0, config_bands = 0; + u8 is_scanning_required = 0; memset(&req_ssid, 0, sizeof(struct cfg80211_ssid)); @@ -1478,19 +1478,6 @@ mwifiex_cfg80211_assoc(struct mwifiex_private *priv, size_t ssid_len, u8 *ssid, /* disconnect before try to associate */ mwifiex_deauthenticate(priv, NULL); - if (channel) { - if (mode == NL80211_IFTYPE_STATION) { - if (channel->band == IEEE80211_BAND_2GHZ) - config_bands = BAND_B | BAND_G | BAND_GN; - else - config_bands = BAND_A | BAND_AN; - - if (!((config_bands | priv->adapter->fw_bands) & - ~priv->adapter->fw_bands)) - priv->adapter->config_bands = config_bands; - } - } - /* As this is new association, clear locally stored * keys and security related flags */ priv->sec_info.wpa_enabled = false; @@ -1707,7 +1694,7 @@ static int mwifiex_set_ibss_params(struct mwifiex_private *priv, if (cfg80211_get_chandef_type(¶ms->chandef) != NL80211_CHAN_NO_HT) - config_bands |= BAND_GN; + config_bands |= BAND_G | BAND_GN; } else { if (cfg80211_get_chandef_type(¶ms->chandef) == NL80211_CHAN_NO_HT) diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c index 13fbc4e..b879e13 100644 --- a/drivers/net/wireless/mwifiex/pcie.c +++ b/drivers/net/wireless/mwifiex/pcie.c @@ -161,7 +161,7 @@ static int mwifiex_pcie_suspend(struct pci_dev *pdev, pm_message_t state) if (pdev) { card = (struct pcie_service_card *) pci_get_drvdata(pdev); - if (!card || card->adapter) { + if (!card || !card->adapter) { pr_err("Card or adapter structure is not valid\n"); return 0; } diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c index 9189a32..973a9d9 100644 --- a/drivers/net/wireless/mwifiex/scan.c +++ b/drivers/net/wireless/mwifiex/scan.c @@ -1563,7 +1563,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, dev_err(adapter->dev, "SCAN_RESP: too many AP returned (%d)\n", scan_rsp->number_of_sets); ret = -1; - goto done; + goto check_next_scan; } bytes_left = le16_to_cpu(scan_rsp->bss_descript_size); @@ -1634,7 +1634,8 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, if (!beacon_size || beacon_size > bytes_left) { bss_info += bytes_left; bytes_left = 0; - return -1; + ret = -1; + goto check_next_scan; } /* Initialize the current working beacon pointer for this BSS @@ -1690,7 +1691,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, dev_err(priv->adapter->dev, "%s: bytes left < IE length\n", __func__); - goto done; + goto check_next_scan; } if (element_id == WLAN_EID_DS_PARAMS) { channel = *(current_ptr + sizeof(struct ieee_types_header)); @@ -1753,6 +1754,7 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, } } +check_next_scan: spin_lock_irqsave(&adapter->scan_pending_q_lock, flags); if (list_empty(&adapter->scan_pending_q)) { spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags); @@ -1813,7 +1815,6 @@ int mwifiex_ret_802_11_scan(struct mwifiex_private *priv, } } -done: return ret; } diff --git a/drivers/net/wireless/mwifiex/sdio.c b/drivers/net/wireless/mwifiex/sdio.c index 5a1c1d0..f2874c3 100644 --- a/drivers/net/wireless/mwifiex/sdio.c +++ b/drivers/net/wireless/mwifiex/sdio.c @@ -1752,6 +1752,8 @@ mwifiex_update_mp_end_port(struct mwifiex_adapter *adapter, u16 port) static struct mmc_host *reset_host; static void sdio_card_reset_worker(struct work_struct *work) { + struct mmc_host *target = reset_host; + /* The actual reset operation must be run outside of driver thread. * This is because mmc_remove_host() will cause the device to be * instantly destroyed, and the driver then needs to end its thread, @@ -1761,10 +1763,10 @@ static void sdio_card_reset_worker(struct work_struct *work) */ pr_err("Resetting card...\n"); - mmc_remove_host(reset_host); + mmc_remove_host(target); /* 20ms delay is based on experiment with sdhci controller */ mdelay(20); - mmc_add_host(reset_host); + mmc_add_host(target); } static DECLARE_WORK(card_reset_work, sdio_card_reset_worker); @@ -1773,9 +1775,6 @@ static void mwifiex_sdio_card_reset(struct mwifiex_adapter *adapter) { struct sdio_mmc_card *card = adapter->card; - if (work_pending(&card_reset_work)) - return; - reset_host = card->func->card->host; schedule_work(&card_reset_work); } diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c index 60e88b5..f542bb8 100644 --- a/drivers/net/wireless/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/mwifiex/sta_ioctl.c @@ -283,6 +283,20 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss, if (ret) goto done; + if (bss_desc) { + u8 config_bands = 0; + + if (mwifiex_band_to_radio_type((u8) bss_desc->bss_band) + == HostCmd_SCAN_RADIO_TYPE_BG) + config_bands = BAND_B | BAND_G | BAND_GN; + else + config_bands = BAND_A | BAND_AN; + + if (!((config_bands | adapter->fw_bands) & + ~adapter->fw_bands)) + adapter->config_bands = config_bands; + } + ret = mwifiex_check_network_compatibility(priv, bss_desc); if (ret) goto done; diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 83564d3..a00a03e 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -318,20 +318,20 @@ struct mwl8k_sta { #define MWL8K_STA(_sta) ((struct mwl8k_sta *)&((_sta)->drv_priv)) static const struct ieee80211_channel mwl8k_channels_24[] = { - { .center_freq = 2412, .hw_value = 1, }, - { .center_freq = 2417, .hw_value = 2, }, - { .center_freq = 2422, .hw_value = 3, }, - { .center_freq = 2427, .hw_value = 4, }, - { .center_freq = 2432, .hw_value = 5, }, - { .center_freq = 2437, .hw_value = 6, }, - { .center_freq = 2442, .hw_value = 7, }, - { .center_freq = 2447, .hw_value = 8, }, - { .center_freq = 2452, .hw_value = 9, }, - { .center_freq = 2457, .hw_value = 10, }, - { .center_freq = 2462, .hw_value = 11, }, - { .center_freq = 2467, .hw_value = 12, }, - { .center_freq = 2472, .hw_value = 13, }, - { .center_freq = 2484, .hw_value = 14, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2412, .hw_value = 1, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2417, .hw_value = 2, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2422, .hw_value = 3, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2427, .hw_value = 4, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2432, .hw_value = 5, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2437, .hw_value = 6, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2442, .hw_value = 7, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2447, .hw_value = 8, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2452, .hw_value = 9, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2457, .hw_value = 10, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2462, .hw_value = 11, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2467, .hw_value = 12, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2472, .hw_value = 13, }, + { .band = IEEE80211_BAND_2GHZ, .center_freq = 2484, .hw_value = 14, }, }; static const struct ieee80211_rate mwl8k_rates_24[] = { @@ -352,10 +352,10 @@ static const struct ieee80211_rate mwl8k_rates_24[] = { }; static const struct ieee80211_channel mwl8k_channels_50[] = { - { .center_freq = 5180, .hw_value = 36, }, - { .center_freq = 5200, .hw_value = 40, }, - { .center_freq = 5220, .hw_value = 44, }, - { .center_freq = 5240, .hw_value = 48, }, + { .band = IEEE80211_BAND_5GHZ, .center_freq = 5180, .hw_value = 36, }, + { .band = IEEE80211_BAND_5GHZ, .center_freq = 5200, .hw_value = 40, }, + { .band = IEEE80211_BAND_5GHZ, .center_freq = 5220, .hw_value = 44, }, + { .band = IEEE80211_BAND_5GHZ, .center_freq = 5240, .hw_value = 48, }, }; static const struct ieee80211_rate mwl8k_rates_50[] = { diff --git a/drivers/net/wireless/rtlwifi/Kconfig b/drivers/net/wireless/rtlwifi/Kconfig index 21b1bbb..b80bc46 100644 --- a/drivers/net/wireless/rtlwifi/Kconfig +++ b/drivers/net/wireless/rtlwifi/Kconfig @@ -57,12 +57,12 @@ config RTL8192CU config RTLWIFI tristate - depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE + depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE || RTL8723AE default m config RTLWIFI_DEBUG bool "Additional debugging output" - depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE + depends on RTL8192CE || RTL8192CU || RTL8192SE || RTL8192DE || RTL8723AE default y config RTL8192C_COMMON diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c index 4494d13..0f8b051 100644 --- a/drivers/net/wireless/rtlwifi/base.c +++ b/drivers/net/wireless/rtlwifi/base.c @@ -1004,7 +1004,8 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx) is_tx ? "Tx" : "Rx"); if (is_tx) { - rtl_lps_leave(hw); + schedule_work(&rtlpriv-> + works.lps_leave_work); ppsc->last_delaylps_stamp_jiffies = jiffies; } @@ -1014,7 +1015,7 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx) } } else if (ETH_P_ARP == ether_type) { if (is_tx) { - rtl_lps_leave(hw); + schedule_work(&rtlpriv->works.lps_leave_work); ppsc->last_delaylps_stamp_jiffies = jiffies; } @@ -1024,7 +1025,7 @@ u8 rtl_is_special_data(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx) "802.1X %s EAPOL pkt!!\n", is_tx ? "Tx" : "Rx"); if (is_tx) { - rtl_lps_leave(hw); + schedule_work(&rtlpriv->works.lps_leave_work); ppsc->last_delaylps_stamp_jiffies = jiffies; } diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c index f2ecdeb..1535efd 100644 --- a/drivers/net/wireless/rtlwifi/usb.c +++ b/drivers/net/wireless/rtlwifi/usb.c @@ -542,8 +542,8 @@ static void _rtl_rx_pre_process(struct ieee80211_hw *hw, struct sk_buff *skb) WARN_ON(skb_queue_empty(&rx_queue)); while (!skb_queue_empty(&rx_queue)) { _skb = skb_dequeue(&rx_queue); - _rtl_usb_rx_process_agg(hw, skb); - ieee80211_rx_irqsafe(hw, skb); + _rtl_usb_rx_process_agg(hw, _skb); + ieee80211_rx_irqsafe(hw, _skb); } } diff --git a/drivers/net/wireless/ti/wl1251/ps.c b/drivers/net/wireless/ti/wl1251/ps.c index db719f7..b9e27b9 100644 --- a/drivers/net/wireless/ti/wl1251/ps.c +++ b/drivers/net/wireless/ti/wl1251/ps.c @@ -68,8 +68,7 @@ int wl1251_ps_elp_wakeup(struct wl1251 *wl) unsigned long timeout, start; u32 elp_reg; - if (delayed_work_pending(&wl->elp_work)) - cancel_delayed_work(&wl->elp_work); + cancel_delayed_work(&wl->elp_work); if (!wl->elp) return 0; diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 94b79c3..9d7f172 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -151,6 +151,9 @@ void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb); /* Notify xenvif that ring now has space to send an skb to the frontend */ void xenvif_notify_tx_completion(struct xenvif *vif); +/* Prevent the device from generating any further traffic. */ +void xenvif_carrier_off(struct xenvif *vif); + /* Returns number of ring slots required to send an skb to the frontend */ unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index b7d41f8..b8c5193 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -343,17 +343,22 @@ err: return err; } -void xenvif_disconnect(struct xenvif *vif) +void xenvif_carrier_off(struct xenvif *vif) { struct net_device *dev = vif->dev; - if (netif_carrier_ok(dev)) { - rtnl_lock(); - netif_carrier_off(dev); /* discard queued packets */ - if (netif_running(dev)) - xenvif_down(vif); - rtnl_unlock(); - xenvif_put(vif); - } + + rtnl_lock(); + netif_carrier_off(dev); /* discard queued packets */ + if (netif_running(dev)) + xenvif_down(vif); + rtnl_unlock(); + xenvif_put(vif); +} + +void xenvif_disconnect(struct xenvif *vif) +{ + if (netif_carrier_ok(vif->dev)) + xenvif_carrier_off(vif); atomic_dec(&vif->refcnt); wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index f2d6b78..2b9520c 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -147,7 +147,8 @@ void xen_netbk_remove_xenvif(struct xenvif *vif) atomic_dec(&netbk->netfront_count); } -static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx); +static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx, + u8 status); static void make_tx_response(struct xenvif *vif, struct xen_netif_tx_request *txp, s8 st); @@ -879,7 +880,7 @@ static void netbk_tx_err(struct xenvif *vif, do { make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - if (cons >= end) + if (cons == end) break; txp = RING_GET_REQUEST(&vif->tx, cons++); } while (1); @@ -888,6 +889,13 @@ static void netbk_tx_err(struct xenvif *vif, xenvif_put(vif); } +static void netbk_fatal_tx_err(struct xenvif *vif) +{ + netdev_err(vif->dev, "fatal error; disabling device\n"); + xenvif_carrier_off(vif); + xenvif_put(vif); +} + static int netbk_count_requests(struct xenvif *vif, struct xen_netif_tx_request *first, struct xen_netif_tx_request *txp, @@ -901,19 +909,22 @@ static int netbk_count_requests(struct xenvif *vif, do { if (frags >= work_to_do) { - netdev_dbg(vif->dev, "Need more frags\n"); + netdev_err(vif->dev, "Need more frags\n"); + netbk_fatal_tx_err(vif); return -frags; } if (unlikely(frags >= MAX_SKB_FRAGS)) { - netdev_dbg(vif->dev, "Too many frags\n"); + netdev_err(vif->dev, "Too many frags\n"); + netbk_fatal_tx_err(vif); return -frags; } memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags), sizeof(*txp)); if (txp->size > first->size) { - netdev_dbg(vif->dev, "Frags galore\n"); + netdev_err(vif->dev, "Frag is bigger than frame.\n"); + netbk_fatal_tx_err(vif); return -frags; } @@ -921,8 +932,9 @@ static int netbk_count_requests(struct xenvif *vif, frags++; if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) { - netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n", + netdev_err(vif->dev, "txp->offset: %x, size: %u\n", txp->offset, txp->size); + netbk_fatal_tx_err(vif); return -frags; } } while ((txp++)->flags & XEN_NETTXF_more_data); @@ -966,7 +978,7 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk, pending_idx = netbk->pending_ring[index]; page = xen_netbk_alloc_page(netbk, skb, pending_idx); if (!page) - return NULL; + goto err; gop->source.u.ref = txp->gref; gop->source.domid = vif->domid; @@ -988,6 +1000,17 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk, } return gop; +err: + /* Unwind, freeing all pages and sending error responses. */ + while (i-- > start) { + xen_netbk_idx_release(netbk, frag_get_pending_idx(&frags[i]), + XEN_NETIF_RSP_ERROR); + } + /* The head too, if necessary. */ + if (start) + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR); + + return NULL; } static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, @@ -996,30 +1019,20 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, { struct gnttab_copy *gop = *gopp; u16 pending_idx = *((u16 *)skb->data); - struct pending_tx_info *pending_tx_info = netbk->pending_tx_info; - struct xenvif *vif = pending_tx_info[pending_idx].vif; - struct xen_netif_tx_request *txp; struct skb_shared_info *shinfo = skb_shinfo(skb); int nr_frags = shinfo->nr_frags; int i, err, start; /* Check status of header. */ err = gop->status; - if (unlikely(err)) { - pending_ring_idx_t index; - index = pending_index(netbk->pending_prod++); - txp = &pending_tx_info[pending_idx].req; - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - netbk->pending_ring[index] = pending_idx; - xenvif_put(vif); - } + if (unlikely(err)) + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR); /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); for (i = start; i < nr_frags; i++) { int j, newerr; - pending_ring_idx_t index; pending_idx = frag_get_pending_idx(&shinfo->frags[i]); @@ -1028,16 +1041,12 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, if (likely(!newerr)) { /* Had a previous error? Invalidate this fragment. */ if (unlikely(err)) - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); continue; } /* Error on this fragment: respond to client with an error. */ - txp = &netbk->pending_tx_info[pending_idx].req; - make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); - index = pending_index(netbk->pending_prod++); - netbk->pending_ring[index] = pending_idx; - xenvif_put(vif); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR); /* Not the first error? Preceding frags already invalidated. */ if (err) @@ -1045,10 +1054,10 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, /* First error: invalidate header and preceding fragments. */ pending_idx = *((u16 *)skb->data); - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); for (j = start; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); } /* Remember the error: invalidate all subsequent fragments. */ @@ -1082,7 +1091,7 @@ static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb) /* Take an extra reference to offset xen_netbk_idx_release */ get_page(netbk->mmap_pages[pending_idx]); - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); } } @@ -1095,7 +1104,8 @@ static int xen_netbk_get_extras(struct xenvif *vif, do { if (unlikely(work_to_do-- <= 0)) { - netdev_dbg(vif->dev, "Missing extra info\n"); + netdev_err(vif->dev, "Missing extra info\n"); + netbk_fatal_tx_err(vif); return -EBADR; } @@ -1104,8 +1114,9 @@ static int xen_netbk_get_extras(struct xenvif *vif, if (unlikely(!extra.type || extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { vif->tx.req_cons = ++cons; - netdev_dbg(vif->dev, + netdev_err(vif->dev, "Invalid extra type: %d\n", extra.type); + netbk_fatal_tx_err(vif); return -EINVAL; } @@ -1121,13 +1132,15 @@ static int netbk_set_skb_gso(struct xenvif *vif, struct xen_netif_extra_info *gso) { if (!gso->u.gso.size) { - netdev_dbg(vif->dev, "GSO size must not be zero.\n"); + netdev_err(vif->dev, "GSO size must not be zero.\n"); + netbk_fatal_tx_err(vif); return -EINVAL; } /* Currently only TCPv4 S.O. is supported. */ if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) { - netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); + netbk_fatal_tx_err(vif); return -EINVAL; } @@ -1264,9 +1277,25 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) /* Get a netif from the list with work to do. */ vif = poll_net_schedule_list(netbk); + /* This can sometimes happen because the test of + * list_empty(net_schedule_list) at the top of the + * loop is unlocked. Just go back and have another + * look. + */ if (!vif) continue; + if (vif->tx.sring->req_prod - vif->tx.req_cons > + XEN_NETIF_TX_RING_SIZE) { + netdev_err(vif->dev, + "Impossible number of requests. " + "req_prod %d, req_cons %d, size %ld\n", + vif->tx.sring->req_prod, vif->tx.req_cons, + XEN_NETIF_TX_RING_SIZE); + netbk_fatal_tx_err(vif); + continue; + } + RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do); if (!work_to_do) { xenvif_put(vif); @@ -1294,17 +1323,14 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) work_to_do = xen_netbk_get_extras(vif, extras, work_to_do); idx = vif->tx.req_cons; - if (unlikely(work_to_do < 0)) { - netbk_tx_err(vif, &txreq, idx); + if (unlikely(work_to_do < 0)) continue; - } } ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do); - if (unlikely(ret < 0)) { - netbk_tx_err(vif, &txreq, idx - ret); + if (unlikely(ret < 0)) continue; - } + idx += ret; if (unlikely(txreq.size < ETH_HLEN)) { @@ -1316,11 +1342,11 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) /* No crossing a page as the payload mustn't fragment. */ if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) { - netdev_dbg(vif->dev, + netdev_err(vif->dev, "txreq.offset: %x, size: %u, end: %lu\n", txreq.offset, txreq.size, (txreq.offset&~PAGE_MASK) + txreq.size); - netbk_tx_err(vif, &txreq, idx); + netbk_fatal_tx_err(vif); continue; } @@ -1348,8 +1374,8 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk) gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; if (netbk_set_skb_gso(vif, skb, gso)) { + /* Failure in netbk_set_skb_gso is fatal. */ kfree_skb(skb); - netbk_tx_err(vif, &txreq, idx); continue; } } @@ -1448,7 +1474,7 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk) txp->size -= data_len; } else { /* Schedule a response immediately. */ - xen_netbk_idx_release(netbk, pending_idx); + xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY); } if (txp->flags & XEN_NETTXF_csum_blank) @@ -1500,7 +1526,8 @@ static void xen_netbk_tx_action(struct xen_netbk *netbk) xen_netbk_tx_submit(netbk); } -static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx) +static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx, + u8 status) { struct xenvif *vif; struct pending_tx_info *pending_tx_info; @@ -1514,7 +1541,7 @@ static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx) vif = pending_tx_info->vif; - make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY); + make_tx_response(vif, &pending_tx_info->req, status); index = pending_index(netbk->pending_prod++); netbk->pending_ring[index] = pending_idx; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 5099636..00cc78c7 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -845,6 +845,32 @@ int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec) } EXPORT_SYMBOL(pci_enable_msi_block); +int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec) +{ + int ret, pos, nvec; + u16 msgctl; + + pos = pci_find_capability(dev, PCI_CAP_ID_MSI); + if (!pos) + return -EINVAL; + + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); + ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + + if (maxvec) + *maxvec = ret; + + do { + nvec = ret; + ret = pci_enable_msi_block(dev, nvec); + } while (ret > 0); + + if (ret < 0) + return ret; + return nvec; +} +EXPORT_SYMBOL(pci_enable_msi_block_auto); + void pci_msi_shutdown(struct pci_dev *dev) { struct msi_desc *desc; diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c index 3ea5173..5ab1425 100644 --- a/drivers/pci/pcie/aer/aerdrv_errprint.c +++ b/drivers/pci/pcie/aer/aerdrv_errprint.c @@ -23,6 +23,9 @@ #include "aerdrv.h" +#define CREATE_TRACE_POINTS +#include <trace/events/ras.h> + #define AER_AGENT_RECEIVER 0 #define AER_AGENT_REQUESTER 1 #define AER_AGENT_COMPLETER 2 @@ -121,12 +124,11 @@ static const char *aer_agent_string[] = { "Transmitter ID" }; -static void __aer_print_error(const char *prefix, +static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { int i, status; const char *errmsg = NULL; - status = (info->status & ~info->mask); for (i = 0; i < 32; i++) { @@ -141,26 +143,22 @@ static void __aer_print_error(const char *prefix, aer_uncorrectable_error_string[i] : NULL; if (errmsg) - printk("%s"" [%2d] %-22s%s\n", prefix, i, errmsg, + dev_err(&dev->dev, " [%2d] %-22s%s\n", i, errmsg, info->first_error == i ? " (First)" : ""); else - printk("%s"" [%2d] Unknown Error Bit%s\n", prefix, i, - info->first_error == i ? " (First)" : ""); + dev_err(&dev->dev, " [%2d] Unknown Error Bit%s\n", + i, info->first_error == i ? " (First)" : ""); } } void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { int id = ((dev->bus->number << 8) | dev->devfn); - char prefix[44]; - - snprintf(prefix, sizeof(prefix), "%s%s %s: ", - (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR, - dev_driver_string(&dev->dev), dev_name(&dev->dev)); if (info->status == 0) { - printk("%s""PCIe Bus Error: severity=%s, type=Unaccessible, " - "id=%04x(Unregistered Agent ID)\n", prefix, + dev_err(&dev->dev, + "PCIe Bus Error: severity=%s, type=Unaccessible, " + "id=%04x(Unregistered Agent ID)\n", aer_error_severity_string[info->severity], id); } else { int layer, agent; @@ -168,22 +166,24 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); - printk("%s""PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n", - prefix, aer_error_severity_string[info->severity], + dev_err(&dev->dev, + "PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n", + aer_error_severity_string[info->severity], aer_error_layer[layer], id, aer_agent_string[agent]); - printk("%s"" device [%04x:%04x] error status/mask=%08x/%08x\n", - prefix, dev->vendor, dev->device, + dev_err(&dev->dev, + " device [%04x:%04x] error status/mask=%08x/%08x\n", + dev->vendor, dev->device, info->status, info->mask); - __aer_print_error(prefix, info); + __aer_print_error(dev, info); if (info->tlp_header_valid) { unsigned char *tlp = (unsigned char *) &info->tlp; - printk("%s"" TLP Header:" + dev_err(&dev->dev, " TLP Header:" " %02x%02x%02x%02x %02x%02x%02x%02x" " %02x%02x%02x%02x %02x%02x%02x%02x\n", - prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, + *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), *(tlp + 11), *(tlp + 10), *(tlp + 9), *(tlp + 8), *(tlp + 15), *(tlp + 14), @@ -192,8 +192,11 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) } if (info->id && info->error_dev_num > 1 && info->id == id) - printk("%s"" Error of this Agent(%04x) is reported first\n", - prefix, id); + dev_err(&dev->dev, + " Error of this Agent(%04x) is reported first\n", + id); + trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask), + info->severity); } void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) @@ -217,7 +220,7 @@ int cper_severity_to_aer(int cper_severity) } EXPORT_SYMBOL_GPL(cper_severity_to_aer); -void cper_print_aer(const char *prefix, int cper_severity, +void cper_print_aer(const char *prefix, struct pci_dev *dev, int cper_severity, struct aer_capability_regs *aer) { int aer_severity, layer, agent, status_strs_size, tlp_header_valid = 0; @@ -239,25 +242,27 @@ void cper_print_aer(const char *prefix, int cper_severity, } layer = AER_GET_LAYER_ERROR(aer_severity, status); agent = AER_GET_AGENT(aer_severity, status); - printk("%s""aer_status: 0x%08x, aer_mask: 0x%08x\n", - prefix, status, mask); + dev_err(&dev->dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", + status, mask); cper_print_bits(prefix, status, status_strs, status_strs_size); - printk("%s""aer_layer=%s, aer_agent=%s\n", prefix, + dev_err(&dev->dev, "aer_layer=%s, aer_agent=%s\n", aer_error_layer[layer], aer_agent_string[agent]); if (aer_severity != AER_CORRECTABLE) - printk("%s""aer_uncor_severity: 0x%08x\n", - prefix, aer->uncor_severity); + dev_err(&dev->dev, "aer_uncor_severity: 0x%08x\n", + aer->uncor_severity); if (tlp_header_valid) { const unsigned char *tlp; tlp = (const unsigned char *)&aer->header_log; - printk("%s""aer_tlp_header:" + dev_err(&dev->dev, "aer_tlp_header:" " %02x%02x%02x%02x %02x%02x%02x%02x" " %02x%02x%02x%02x %02x%02x%02x%02x\n", - prefix, *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, + *(tlp + 3), *(tlp + 2), *(tlp + 1), *tlp, *(tlp + 7), *(tlp + 6), *(tlp + 5), *(tlp + 4), *(tlp + 11), *(tlp + 10), *(tlp + 9), *(tlp + 8), *(tlp + 15), *(tlp + 14), *(tlp + 13), *(tlp + 12)); } + trace_aer_event(dev_name(&dev->dev), (status & ~mask), + aer_severity); } #endif diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 7c0fd92..84954a7 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -19,6 +19,8 @@ static void pci_free_resources(struct pci_dev *dev) static void pci_stop_dev(struct pci_dev *dev) { + pci_pme_active(dev, false); + if (dev->is_added) { pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index c31aeb0..393b0ec 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -26,6 +26,29 @@ config DEBUG_PINCTRL help Say Y here to add some extra checks and diagnostics to PINCTRL calls. +config PINCTRL_ABX500 + bool "ST-Ericsson ABx500 family Mixed Signal Circuit gpio functions" + depends on AB8500_CORE + select GENERIC_PINCONF + help + Select this to enable the ABx500 family IC GPIO driver + +config PINCTRL_AB8500 + bool "AB8500 pin controller driver" + depends on PINCTRL_ABX500 && ARCH_U8500 + +config PINCTRL_AB8540 + bool "AB8540 pin controller driver" + depends on PINCTRL_ABX500 && ARCH_U8500 + +config PINCTRL_AB9540 + bool "AB9540 pin controller driver" + depends on PINCTRL_ABX500 && ARCH_U8500 + +config PINCTRL_AB8505 + bool "AB8505 pin controller driver" + depends on PINCTRL_ABX500 && ARCH_U8500 + config PINCTRL_AT91 bool "AT91 pinctrl driver" depends on OF @@ -151,6 +174,11 @@ config PINCTRL_SIRF depends on ARCH_SIRF select PINMUX +config PINCTRL_SUNXI + bool + select PINMUX + select GENERIC_PINCONF + config PINCTRL_TEGRA bool select PINMUX @@ -164,6 +192,10 @@ config PINCTRL_TEGRA30 bool select PINCTRL_TEGRA +config PINCTRL_TEGRA114 + bool + select PINCTRL_TEGRA + config PINCTRL_U300 bool "U300 pin controller driver" depends on ARCH_U300 @@ -181,12 +213,11 @@ config PINCTRL_COH901 config PINCTRL_SAMSUNG bool - depends on OF && GPIOLIB select PINMUX select PINCONF -config PINCTRL_EXYNOS4 - bool "Pinctrl driver data for Exynos4 SoC" +config PINCTRL_EXYNOS + bool "Pinctrl driver data for Samsung EXYNOS SoCs" depends on OF && GPIOLIB select PINCTRL_SAMSUNG diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index fc4606f..0fd5f57 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -9,6 +9,11 @@ ifeq ($(CONFIG_OF),y) obj-$(CONFIG_PINCTRL) += devicetree.o endif obj-$(CONFIG_GENERIC_PINCONF) += pinconf-generic.o +obj-$(CONFIG_PINCTRL_ABX500) += pinctrl-abx500.o +obj-$(CONFIG_PINCTRL_AB8500) += pinctrl-ab8500.o +obj-$(CONFIG_PINCTRL_AB8540) += pinctrl-ab8540.o +obj-$(CONFIG_PINCTRL_AB9540) += pinctrl-ab9540.o +obj-$(CONFIG_PINCTRL_AB8505) += pinctrl-ab8505.o obj-$(CONFIG_PINCTRL_AT91) += pinctrl-at91.o obj-$(CONFIG_PINCTRL_BCM2835) += pinctrl-bcm2835.o obj-$(CONFIG_PINCTRL_IMX) += pinctrl-imx.o @@ -30,13 +35,15 @@ obj-$(CONFIG_PINCTRL_PXA168) += pinctrl-pxa168.o obj-$(CONFIG_PINCTRL_PXA910) += pinctrl-pxa910.o obj-$(CONFIG_PINCTRL_SINGLE) += pinctrl-single.o obj-$(CONFIG_PINCTRL_SIRF) += pinctrl-sirf.o +obj-$(CONFIG_PINCTRL_SUNXI) += pinctrl-sunxi.o obj-$(CONFIG_PINCTRL_TEGRA) += pinctrl-tegra.o obj-$(CONFIG_PINCTRL_TEGRA20) += pinctrl-tegra20.o obj-$(CONFIG_PINCTRL_TEGRA30) += pinctrl-tegra30.o +obj-$(CONFIG_PINCTRL_TEGRA114) += pinctrl-tegra114.o obj-$(CONFIG_PINCTRL_U300) += pinctrl-u300.o obj-$(CONFIG_PINCTRL_COH901) += pinctrl-coh901.o obj-$(CONFIG_PINCTRL_SAMSUNG) += pinctrl-samsung.o -obj-$(CONFIG_PINCTRL_EXYNOS4) += pinctrl-exynos.o +obj-$(CONFIG_PINCTRL_EXYNOS) += pinctrl-exynos.o obj-$(CONFIG_PINCTRL_EXYNOS5440) += pinctrl-exynos5440.o obj-$(CONFIG_PINCTRL_XWAY) += pinctrl-xway.o obj-$(CONFIG_PINCTRL_LANTIQ) += pinctrl-lantiq.o diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 59f5a96..b0de6e7 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -14,6 +14,7 @@ #define pr_fmt(fmt) "pinctrl core: " fmt #include <linux/kernel.h> +#include <linux/kref.h> #include <linux/export.h> #include <linux/init.h> #include <linux/device.h> @@ -31,17 +32,6 @@ #include "pinmux.h" #include "pinconf.h" -/** - * struct pinctrl_maps - a list item containing part of the mapping table - * @node: mapping table list node - * @maps: array of mapping table entries - * @num_maps: the number of entries in @maps - */ -struct pinctrl_maps { - struct list_head node; - struct pinctrl_map const *maps; - unsigned num_maps; -}; static bool pinctrl_dummy_state; @@ -55,13 +45,8 @@ LIST_HEAD(pinctrldev_list); static LIST_HEAD(pinctrl_list); /* List of pinctrl maps (struct pinctrl_maps) */ -static LIST_HEAD(pinctrl_maps); +LIST_HEAD(pinctrl_maps); -#define for_each_maps(_maps_node_, _i_, _map_) \ - list_for_each_entry(_maps_node_, &pinctrl_maps, node) \ - for (_i_ = 0, _map_ = &_maps_node_->maps[_i_]; \ - _i_ < _maps_node_->num_maps; \ - _i_++, _map_ = &_maps_node_->maps[_i_]) /** * pinctrl_provide_dummies() - indicate if pinctrl provides dummy state support @@ -83,6 +68,12 @@ const char *pinctrl_dev_get_name(struct pinctrl_dev *pctldev) } EXPORT_SYMBOL_GPL(pinctrl_dev_get_name); +const char *pinctrl_dev_get_devname(struct pinctrl_dev *pctldev) +{ + return dev_name(pctldev->dev); +} +EXPORT_SYMBOL_GPL(pinctrl_dev_get_devname); + void *pinctrl_dev_get_drvdata(struct pinctrl_dev *pctldev) { return pctldev->driver_data; @@ -609,13 +600,16 @@ static int add_setting(struct pinctrl *p, struct pinctrl_map const *map) setting->pctldev = get_pinctrl_dev_from_devname(map->ctrl_dev_name); if (setting->pctldev == NULL) { - dev_info(p->dev, "unknown pinctrl device %s in map entry, deferring probe", - map->ctrl_dev_name); kfree(setting); + /* Do not defer probing of hogs (circular loop) */ + if (!strcmp(map->ctrl_dev_name, map->dev_name)) + return -ENODEV; /* * OK let us guess that the driver is not there yet, and * let's defer obtaining this pinctrl handle to later... */ + dev_info(p->dev, "unknown pinctrl device %s in map entry, deferring probe", + map->ctrl_dev_name); return -EPROBE_DEFER; } @@ -694,11 +688,31 @@ static struct pinctrl *create_pinctrl(struct device *dev) continue; ret = add_setting(p, map); - if (ret < 0) { + /* + * At this point the adding of a setting may: + * + * - Defer, if the pinctrl device is not yet available + * - Fail, if the pinctrl device is not yet available, + * AND the setting is a hog. We cannot defer that, since + * the hog will kick in immediately after the device + * is registered. + * + * If the error returned was not -EPROBE_DEFER then we + * accumulate the errors to see if we end up with + * an -EPROBE_DEFER later, as that is the worst case. + */ + if (ret == -EPROBE_DEFER) { pinctrl_put_locked(p, false); return ERR_PTR(ret); } } + if (ret < 0) { + /* If some other error than deferral occured, return here */ + pinctrl_put_locked(p, false); + return ERR_PTR(ret); + } + + kref_init(&p->users); /* Add the pinctrl handle to the global list */ list_add_tail(&p->node, &pinctrl_list); @@ -713,9 +727,17 @@ static struct pinctrl *pinctrl_get_locked(struct device *dev) if (WARN_ON(!dev)) return ERR_PTR(-EINVAL); + /* + * See if somebody else (such as the device core) has already + * obtained a handle to the pinctrl for this device. In that case, + * return another pointer to it. + */ p = find_pinctrl(dev); - if (p != NULL) - return ERR_PTR(-EBUSY); + if (p != NULL) { + dev_dbg(dev, "obtain a copy of previously claimed pinctrl\n"); + kref_get(&p->users); + return p; + } return create_pinctrl(dev); } @@ -771,13 +793,24 @@ static void pinctrl_put_locked(struct pinctrl *p, bool inlist) } /** - * pinctrl_put() - release a previously claimed pinctrl handle + * pinctrl_release() - release the pinctrl handle + * @kref: the kref in the pinctrl being released + */ +static void pinctrl_release(struct kref *kref) +{ + struct pinctrl *p = container_of(kref, struct pinctrl, users); + + pinctrl_put_locked(p, true); +} + +/** + * pinctrl_put() - decrease use count on a previously claimed pinctrl handle * @p: the pinctrl handle to release */ void pinctrl_put(struct pinctrl *p) { mutex_lock(&pinctrl_mutex); - pinctrl_put_locked(p, true); + kref_put(&p->users, pinctrl_release); mutex_unlock(&pinctrl_mutex); } EXPORT_SYMBOL_GPL(pinctrl_put); @@ -1055,6 +1088,30 @@ void pinctrl_unregister_map(struct pinctrl_map const *map) } } +/** + * pinctrl_force_sleep() - turn a given controller device into sleep state + * @pctldev: pin controller device + */ +int pinctrl_force_sleep(struct pinctrl_dev *pctldev) +{ + if (!IS_ERR(pctldev->p) && !IS_ERR(pctldev->hog_sleep)) + return pinctrl_select_state(pctldev->p, pctldev->hog_sleep); + return 0; +} +EXPORT_SYMBOL_GPL(pinctrl_force_sleep); + +/** + * pinctrl_force_default() - turn a given controller device into default state + * @pctldev: pin controller device + */ +int pinctrl_force_default(struct pinctrl_dev *pctldev) +{ + if (!IS_ERR(pctldev->p) && !IS_ERR(pctldev->hog_default)) + return pinctrl_select_state(pctldev->p, pctldev->hog_default); + return 0; +} +EXPORT_SYMBOL_GPL(pinctrl_force_default); + #ifdef CONFIG_DEBUG_FS static int pinctrl_pins_show(struct seq_file *s, void *what) @@ -1500,16 +1557,23 @@ struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, pctldev->p = pinctrl_get_locked(pctldev->dev); if (!IS_ERR(pctldev->p)) { - struct pinctrl_state *s = + pctldev->hog_default = pinctrl_lookup_state_locked(pctldev->p, PINCTRL_STATE_DEFAULT); - if (IS_ERR(s)) { + if (IS_ERR(pctldev->hog_default)) { dev_dbg(dev, "failed to lookup the default state\n"); } else { - if (pinctrl_select_state_locked(pctldev->p, s)) + if (pinctrl_select_state_locked(pctldev->p, + pctldev->hog_default)) dev_err(dev, "failed to select default state\n"); } + + pctldev->hog_sleep = + pinctrl_lookup_state_locked(pctldev->p, + PINCTRL_STATE_SLEEP); + if (IS_ERR(pctldev->hog_sleep)) + dev_dbg(dev, "failed to lookup the sleep state\n"); } mutex_unlock(&pinctrl_mutex); diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h index 12f5694..ee72f1f 100644 --- a/drivers/pinctrl/core.h +++ b/drivers/pinctrl/core.h @@ -9,6 +9,7 @@ * License terms: GNU General Public License (GPL) version 2 */ +#include <linux/kref.h> #include <linux/mutex.h> #include <linux/radix-tree.h> #include <linux/pinctrl/pinconf.h> @@ -30,6 +31,8 @@ struct pinctrl_gpio_range; * @driver_data: driver data for drivers registering to the pin controller * subsystem * @p: result of pinctrl_get() for this device + * @hog_default: default state for pins hogged by this device + * @hog_sleep: sleep state for pins hogged by this device * @device_root: debugfs root for this device */ struct pinctrl_dev { @@ -41,6 +44,8 @@ struct pinctrl_dev { struct module *owner; void *driver_data; struct pinctrl *p; + struct pinctrl_state *hog_default; + struct pinctrl_state *hog_sleep; #ifdef CONFIG_DEBUG_FS struct dentry *device_root; #endif @@ -54,6 +59,7 @@ struct pinctrl_dev { * @state: the current state * @dt_maps: the mapping table chunks dynamically parsed from device tree for * this device, if any + * @users: reference count */ struct pinctrl { struct list_head node; @@ -61,6 +67,7 @@ struct pinctrl { struct list_head states; struct pinctrl_state *state; struct list_head dt_maps; + struct kref users; }; /** @@ -148,6 +155,18 @@ struct pin_desc { #endif }; +/** + * struct pinctrl_maps - a list item containing part of the mapping table + * @node: mapping table list node + * @maps: array of mapping table entries + * @num_maps: the number of entries in @maps + */ +struct pinctrl_maps { + struct list_head node; + struct pinctrl_map const *maps; + unsigned num_maps; +}; + struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name); int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name); const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin); @@ -164,5 +183,15 @@ int pinctrl_register_map(struct pinctrl_map const *maps, unsigned num_maps, bool dup, bool locked); void pinctrl_unregister_map(struct pinctrl_map const *map); +extern int pinctrl_force_sleep(struct pinctrl_dev *pctldev); +extern int pinctrl_force_default(struct pinctrl_dev *pctldev); + extern struct mutex pinctrl_mutex; extern struct list_head pinctrldev_list; +extern struct list_head pinctrl_maps; + +#define for_each_maps(_maps_node_, _i_, _map_) \ + list_for_each_entry(_maps_node_, &pinctrl_maps, node) \ + for (_i_ = 0, _map_ = &_maps_node_->maps[_i_]; \ + _i_ < _maps_node_->num_maps; \ + _i_++, _map_ = &_maps_node_->maps[_i_]) diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index fe2d1af..fd40a11 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -141,6 +141,11 @@ static int dt_to_map_one_config(struct pinctrl *p, const char *statename, pctldev = find_pinctrl_by_of_node(np_pctldev); if (pctldev) break; + /* Do not defer probing of hogs (circular loop) */ + if (np_pctldev == p->dev->of_node) { + of_node_put(np_pctldev); + return -ENODEV; + } } of_node_put(np_pctldev); diff --git a/drivers/pinctrl/mvebu/pinctrl-dove.c b/drivers/pinctrl/mvebu/pinctrl-dove.c index 69aba36..428ea96 100644 --- a/drivers/pinctrl/mvebu/pinctrl-dove.c +++ b/drivers/pinctrl/mvebu/pinctrl-dove.c @@ -588,7 +588,7 @@ static int dove_pinctrl_probe(struct platform_device *pdev) { const struct of_device_id *match = of_match_device(dove_pinctrl_of_match, &pdev->dev); - pdev->dev.platform_data = match->data; + pdev->dev.platform_data = (void *)match->data; /* * General MPP Configuration Register is part of pdma registers. diff --git a/drivers/pinctrl/mvebu/pinctrl-kirkwood.c b/drivers/pinctrl/mvebu/pinctrl-kirkwood.c index f12084e..cdd483d 100644 --- a/drivers/pinctrl/mvebu/pinctrl-kirkwood.c +++ b/drivers/pinctrl/mvebu/pinctrl-kirkwood.c @@ -66,9 +66,9 @@ static struct mvebu_mpp_mode mv88f6xxx_mpp_modes[] = { MPP_VAR_FUNCTION(0x5, "sata0", "act", V(0, 1, 1, 1, 1, 0)), MPP_VAR_FUNCTION(0xb, "lcd", "vsync", V(0, 0, 0, 0, 1, 0))), MPP_MODE(6, - MPP_VAR_FUNCTION(0x0, "sysrst", "out", V(1, 1, 1, 1, 1, 1)), - MPP_VAR_FUNCTION(0x1, "spi", "mosi", V(1, 1, 1, 1, 1, 1)), - MPP_VAR_FUNCTION(0x2, "ptp", "trig", V(1, 1, 1, 1, 0, 0))), + MPP_VAR_FUNCTION(0x1, "sysrst", "out", V(1, 1, 1, 1, 1, 1)), + MPP_VAR_FUNCTION(0x2, "spi", "mosi", V(1, 1, 1, 1, 1, 1)), + MPP_VAR_FUNCTION(0x3, "ptp", "trig", V(1, 1, 1, 1, 0, 0))), MPP_MODE(7, MPP_VAR_FUNCTION(0x0, "gpo", NULL, V(1, 1, 1, 1, 1, 1)), MPP_VAR_FUNCTION(0x1, "pex", "rsto", V(1, 1, 1, 1, 0, 1)), @@ -458,7 +458,7 @@ static int kirkwood_pinctrl_probe(struct platform_device *pdev) { const struct of_device_id *match = of_match_device(kirkwood_pinctrl_of_match, &pdev->dev); - pdev->dev.platform_data = match->data; + pdev->dev.platform_data = (void *)match->data; return mvebu_pinctrl_probe(pdev); } diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 833a364..06c304a 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -41,11 +41,13 @@ struct pin_config_item conf_items[] = { PCONFDUMP(PIN_CONFIG_DRIVE_PUSH_PULL, "output drive push pull", NULL), PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_DRAIN, "output drive open drain", NULL), PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_SOURCE, "output drive open source", NULL), - PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT_DISABLE, "input schmitt disabled", NULL), + PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT_ENABLE, "input schmitt enabled", NULL), PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT, "input schmitt trigger", NULL), PCONFDUMP(PIN_CONFIG_INPUT_DEBOUNCE, "input debounce", "time units"), PCONFDUMP(PIN_CONFIG_POWER_SOURCE, "pin power source", "selector"), + PCONFDUMP(PIN_CONFIG_SLEW_RATE, "slew rate", NULL), PCONFDUMP(PIN_CONFIG_LOW_POWER_MODE, "pin low power", "mode"), + PCONFDUMP(PIN_CONFIG_OUTPUT, "pin output", "level"), }; void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev, diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c index baee2cc..ac8d382 100644 --- a/drivers/pinctrl/pinconf.c +++ b/drivers/pinctrl/pinconf.c @@ -574,6 +574,207 @@ static const struct file_operations pinconf_groups_ops = { .release = single_release, }; +/* 32bit read/write ressources */ +#define MAX_NAME_LEN 16 +char dbg_pinname[MAX_NAME_LEN]; /* shared: name of the state of the pin*/ +char dbg_state_name[MAX_NAME_LEN]; /* shared: state of the pin*/ +static u32 dbg_config; /* shared: config to be read/set for the pin & state*/ + +static int pinconf_dbg_pinname_print(struct seq_file *s, void *d) +{ + if (strlen(dbg_pinname)) + seq_printf(s, "%s\n", dbg_pinname); + else + seq_printf(s, "No pin name set\n"); + return 0; +} + +static int pinconf_dbg_pinname_open(struct inode *inode, struct file *file) +{ + return single_open(file, pinconf_dbg_pinname_print, inode->i_private); +} + +static int pinconf_dbg_pinname_write(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + int err; + + if (count > MAX_NAME_LEN) + return -EINVAL; + + err = sscanf(user_buf, "%15s", dbg_pinname); + + if (err != 1) + return -EINVAL; + + return count; +} + +static const struct file_operations pinconf_dbg_pinname_fops = { + .open = pinconf_dbg_pinname_open, + .write = pinconf_dbg_pinname_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .owner = THIS_MODULE, +}; + +static int pinconf_dbg_state_print(struct seq_file *s, void *d) +{ + if (strlen(dbg_state_name)) + seq_printf(s, "%s\n", dbg_pinname); + else + seq_printf(s, "No pin state set\n"); + return 0; +} + +static int pinconf_dbg_state_open(struct inode *inode, struct file *file) +{ + return single_open(file, pinconf_dbg_state_print, inode->i_private); +} + +static int pinconf_dbg_state_write(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + int err; + + if (count > MAX_NAME_LEN) + return -EINVAL; + + err = sscanf(user_buf, "%15s", dbg_state_name); + + if (err != 1) + return -EINVAL; + + return count; +} + +static const struct file_operations pinconf_dbg_pinstate_fops = { + .open = pinconf_dbg_state_open, + .write = pinconf_dbg_state_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .owner = THIS_MODULE, +}; + +/** + * pinconf_dbg_config_print() - display the pinctrl config from the pinctrl + * map, of a pin/state pair based on pinname and state that have been + * selected with the debugfs entries pinconf-name and pinconf-state + * @s: contains the 32bits config to be written + * @d: not used + */ +static int pinconf_dbg_config_print(struct seq_file *s, void *d) +{ + struct pinctrl_maps *maps_node; + struct pinctrl_map const *map; + struct pinctrl_dev *pctldev = NULL; + struct pinconf_ops *confops = NULL; + int i, j; + bool found = false; + + mutex_lock(&pinctrl_mutex); + + /* Parse the pinctrl map and look for the elected pin/state */ + for_each_maps(maps_node, i, map) { + if (map->type != PIN_MAP_TYPE_CONFIGS_PIN) + continue; + + if (strncmp(map->name, dbg_state_name, MAX_NAME_LEN) > 0) + continue; + + for (j = 0; j < map->data.configs.num_configs; j++) { + if (0 == strncmp(map->data.configs.group_or_pin, + dbg_pinname, MAX_NAME_LEN)) { + /* We found the right pin / state, read the + * config and store the pctldev */ + dbg_config = map->data.configs.configs[j]; + pctldev = get_pinctrl_dev_from_devname + (map->ctrl_dev_name); + found = true; + break; + } + } + } + + mutex_unlock(&pinctrl_mutex); + + if (found) { + seq_printf(s, "Config of %s in state %s: 0x%08X\n", dbg_pinname, + dbg_state_name, dbg_config); + + if (pctldev) + confops = pctldev->desc->confops; + + if (confops && confops->pin_config_config_dbg_show) + confops->pin_config_config_dbg_show(pctldev, + s, dbg_config); + } else { + seq_printf(s, "No pin found for defined name/state\n"); + } + + return 0; +} + +static int pinconf_dbg_config_open(struct inode *inode, struct file *file) +{ + return single_open(file, pinconf_dbg_config_print, inode->i_private); +} + +/** + * pinconf_dbg_config_write() - overwrite the pinctrl config in thepinctrl + * map, of a pin/state pair based on pinname and state that have been + * selected with the debugfs entries pinconf-name and pinconf-state + */ +static int pinconf_dbg_config_write(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + int err; + unsigned long config; + struct pinctrl_maps *maps_node; + struct pinctrl_map const *map; + int i, j; + + err = kstrtoul_from_user(user_buf, count, 0, &config); + + if (err) + return err; + + dbg_config = config; + + mutex_lock(&pinctrl_mutex); + + /* Parse the pinctrl map and look for the selected pin/state */ + for_each_maps(maps_node, i, map) { + if (map->type != PIN_MAP_TYPE_CONFIGS_PIN) + continue; + + if (strncmp(map->name, dbg_state_name, MAX_NAME_LEN) > 0) + continue; + + /* we found the right pin / state, so overwrite config */ + for (j = 0; j < map->data.configs.num_configs; j++) { + if (strncmp(map->data.configs.group_or_pin, dbg_pinname, + MAX_NAME_LEN) == 0) + map->data.configs.configs[j] = dbg_config; + } + } + + mutex_unlock(&pinctrl_mutex); + + return count; +} + +static const struct file_operations pinconf_dbg_pinconfig_fops = { + .open = pinconf_dbg_config_open, + .write = pinconf_dbg_config_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .owner = THIS_MODULE, +}; + void pinconf_init_device_debugfs(struct dentry *devroot, struct pinctrl_dev *pctldev) { @@ -581,6 +782,12 @@ void pinconf_init_device_debugfs(struct dentry *devroot, devroot, pctldev, &pinconf_pins_ops); debugfs_create_file("pinconf-groups", S_IFREG | S_IRUGO, devroot, pctldev, &pinconf_groups_ops); + debugfs_create_file("pinconf-name", (S_IRUGO | S_IWUSR | S_IWGRP), + devroot, pctldev, &pinconf_dbg_pinname_fops); + debugfs_create_file("pinconf-state", (S_IRUGO | S_IWUSR | S_IWGRP), + devroot, pctldev, &pinconf_dbg_pinstate_fops); + debugfs_create_file("pinconf-config", (S_IRUGO | S_IWUSR | S_IWGRP), + devroot, pctldev, &pinconf_dbg_pinconfig_fops); } #endif diff --git a/drivers/pinctrl/pinctrl-ab8500.c b/drivers/pinctrl/pinctrl-ab8500.c new file mode 100644 index 0000000..3b471d8 --- /dev/null +++ b/drivers/pinctrl/pinctrl-ab8500.c @@ -0,0 +1,484 @@ +/* + * Copyright (C) ST-Ericsson SA 2012 + * + * Author: Patrice Chotard <patrice.chotard@stericsson.com> for ST-Ericsson. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/mfd/abx500/ab8500.h> +#include "pinctrl-abx500.h" + +/* All the pins that can be used for GPIO and some other functions */ +#define ABX500_GPIO(offset) (offset) + +#define AB8500_PIN_T10 ABX500_GPIO(1) +#define AB8500_PIN_T9 ABX500_GPIO(2) +#define AB8500_PIN_U9 ABX500_GPIO(3) +#define AB8500_PIN_W2 ABX500_GPIO(4) +/* hole */ +#define AB8500_PIN_Y18 ABX500_GPIO(6) +#define AB8500_PIN_AA20 ABX500_GPIO(7) +#define AB8500_PIN_W18 ABX500_GPIO(8) +#define AB8500_PIN_AA19 ABX500_GPIO(9) +#define AB8500_PIN_U17 ABX500_GPIO(10) +#define AB8500_PIN_AA18 ABX500_GPIO(11) +#define AB8500_PIN_U16 ABX500_GPIO(12) +#define AB8500_PIN_W17 ABX500_GPIO(13) +#define AB8500_PIN_F14 ABX500_GPIO(14) +#define AB8500_PIN_B17 ABX500_GPIO(15) +#define AB8500_PIN_F15 ABX500_GPIO(16) +#define AB8500_PIN_P5 ABX500_GPIO(17) +#define AB8500_PIN_R5 ABX500_GPIO(18) +#define AB8500_PIN_U5 ABX500_GPIO(19) +#define AB8500_PIN_T5 ABX500_GPIO(20) +#define AB8500_PIN_H19 ABX500_GPIO(21) +#define AB8500_PIN_G20 ABX500_GPIO(22) +#define AB8500_PIN_G19 ABX500_GPIO(23) +#define AB8500_PIN_T14 ABX500_GPIO(24) +#define AB8500_PIN_R16 ABX500_GPIO(25) +#define AB8500_PIN_M16 ABX500_GPIO(26) +#define AB8500_PIN_J6 ABX500_GPIO(27) +#define AB8500_PIN_K6 ABX500_GPIO(28) +#define AB8500_PIN_G6 ABX500_GPIO(29) +#define AB8500_PIN_H6 ABX500_GPIO(30) +#define AB8500_PIN_F5 ABX500_GPIO(31) +#define AB8500_PIN_G5 ABX500_GPIO(32) +/* hole */ +#define AB8500_PIN_R17 ABX500_GPIO(34) +#define AB8500_PIN_W15 ABX500_GPIO(35) +#define AB8500_PIN_A17 ABX500_GPIO(36) +#define AB8500_PIN_E15 ABX500_GPIO(37) +#define AB8500_PIN_C17 ABX500_GPIO(38) +#define AB8500_PIN_E16 ABX500_GPIO(39) +#define AB8500_PIN_T19 ABX500_GPIO(40) +#define AB8500_PIN_U19 ABX500_GPIO(41) +#define AB8500_PIN_U2 ABX500_GPIO(42) + +/* indicates the highest GPIO number */ +#define AB8500_GPIO_MAX_NUMBER 42 + +/* + * The names of the pins are denoted by GPIO number and ball name, even + * though they can be used for other things than GPIO, this is the first + * column in the table of the data sheet and often used on schematics and + * such. + */ +static const struct pinctrl_pin_desc ab8500_pins[] = { + PINCTRL_PIN(AB8500_PIN_T10, "GPIO1_T10"), + PINCTRL_PIN(AB8500_PIN_T9, "GPIO2_T9"), + PINCTRL_PIN(AB8500_PIN_U9, "GPIO3_U9"), + PINCTRL_PIN(AB8500_PIN_W2, "GPIO4_W2"), + /* hole */ + PINCTRL_PIN(AB8500_PIN_Y18, "GPIO6_Y18"), + PINCTRL_PIN(AB8500_PIN_AA20, "GPIO7_AA20"), + PINCTRL_PIN(AB8500_PIN_W18, "GPIO8_W18"), + PINCTRL_PIN(AB8500_PIN_AA19, "GPIO9_AA19"), + PINCTRL_PIN(AB8500_PIN_U17, "GPIO10_U17"), + PINCTRL_PIN(AB8500_PIN_AA18, "GPIO11_AA18"), + PINCTRL_PIN(AB8500_PIN_U16, "GPIO12_U16"), + PINCTRL_PIN(AB8500_PIN_W17, "GPIO13_W17"), + PINCTRL_PIN(AB8500_PIN_F14, "GPIO14_F14"), + PINCTRL_PIN(AB8500_PIN_B17, "GPIO15_B17"), + PINCTRL_PIN(AB8500_PIN_F15, "GPIO16_F15"), + PINCTRL_PIN(AB8500_PIN_P5, "GPIO17_P5"), + PINCTRL_PIN(AB8500_PIN_R5, "GPIO18_R5"), + PINCTRL_PIN(AB8500_PIN_U5, "GPIO19_U5"), + PINCTRL_PIN(AB8500_PIN_T5, "GPIO20_T5"), + PINCTRL_PIN(AB8500_PIN_H19, "GPIO21_H19"), + PINCTRL_PIN(AB8500_PIN_G20, "GPIO22_G20"), + PINCTRL_PIN(AB8500_PIN_G19, "GPIO23_G19"), + PINCTRL_PIN(AB8500_PIN_T14, "GPIO24_T14"), + PINCTRL_PIN(AB8500_PIN_R16, "GPIO25_R16"), + PINCTRL_PIN(AB8500_PIN_M16, "GPIO26_M16"), + PINCTRL_PIN(AB8500_PIN_J6, "GPIO27_J6"), + PINCTRL_PIN(AB8500_PIN_K6, "GPIO28_K6"), + PINCTRL_PIN(AB8500_PIN_G6, "GPIO29_G6"), + PINCTRL_PIN(AB8500_PIN_H6, "GPIO30_H6"), + PINCTRL_PIN(AB8500_PIN_F5, "GPIO31_F5"), + PINCTRL_PIN(AB8500_PIN_G5, "GPIO32_G5"), + /* hole */ + PINCTRL_PIN(AB8500_PIN_R17, "GPIO34_R17"), + PINCTRL_PIN(AB8500_PIN_W15, "GPIO35_W15"), + PINCTRL_PIN(AB8500_PIN_A17, "GPIO36_A17"), + PINCTRL_PIN(AB8500_PIN_E15, "GPIO37_E15"), + PINCTRL_PIN(AB8500_PIN_C17, "GPIO38_C17"), + PINCTRL_PIN(AB8500_PIN_E16, "GPIO39_E16"), + PINCTRL_PIN(AB8500_PIN_T19, "GPIO40_T19"), + PINCTRL_PIN(AB8500_PIN_U19, "GPIO41_U19"), + PINCTRL_PIN(AB8500_PIN_U2, "GPIO42_U2"), +}; + +/* + * Maps local GPIO offsets to local pin numbers + */ +static const struct abx500_pinrange ab8500_pinranges[] = { + ABX500_PINRANGE(1, 4, ABX500_ALT_A), + ABX500_PINRANGE(6, 4, ABX500_ALT_A), + ABX500_PINRANGE(10, 4, ABX500_DEFAULT), + ABX500_PINRANGE(14, 12, ABX500_ALT_A), + ABX500_PINRANGE(26, 1, ABX500_DEFAULT), + ABX500_PINRANGE(27, 6, ABX500_ALT_A), + ABX500_PINRANGE(34, 1, ABX500_ALT_A), + ABX500_PINRANGE(35, 1, ABX500_DEFAULT), + ABX500_PINRANGE(36, 7, ABX500_ALT_A), +}; + +/* + * Read the pin group names like this: + * sysclkreq2_d_1 = first groups of pins for sysclkreq2 on default function + * + * The groups are arranged as sets per altfunction column, so we can + * mux in one group at a time by selecting the same altfunction for them + * all. When functions require pins on different altfunctions, you need + * to combine several groups. + */ + +/* default column */ +static const unsigned sysclkreq2_d_1_pins[] = { AB8500_PIN_T10 }; +static const unsigned sysclkreq3_d_1_pins[] = { AB8500_PIN_T9 }; +static const unsigned sysclkreq4_d_1_pins[] = { AB8500_PIN_U9 }; +static const unsigned sysclkreq6_d_1_pins[] = { AB8500_PIN_W2 }; +static const unsigned ycbcr0123_d_1_pins[] = { AB8500_PIN_Y18, AB8500_PIN_AA20, + AB8500_PIN_W18, AB8500_PIN_AA19}; +static const unsigned gpio10_d_1_pins[] = { AB8500_PIN_U17 }; +static const unsigned gpio11_d_1_pins[] = { AB8500_PIN_AA18 }; +static const unsigned gpio12_d_1_pins[] = { AB8500_PIN_U16 }; +static const unsigned gpio13_d_1_pins[] = { AB8500_PIN_W17 }; +static const unsigned pwmout1_d_1_pins[] = { AB8500_PIN_F14 }; +static const unsigned pwmout2_d_1_pins[] = { AB8500_PIN_B17 }; +static const unsigned pwmout3_d_1_pins[] = { AB8500_PIN_F15 }; + +/* audio data interface 1*/ +static const unsigned adi1_d_1_pins[] = { AB8500_PIN_P5, AB8500_PIN_R5, + AB8500_PIN_U5, AB8500_PIN_T5 }; +/* USBUICC */ +static const unsigned usbuicc_d_1_pins[] = { AB8500_PIN_H19, AB8500_PIN_G20, + AB8500_PIN_G19 }; +static const unsigned sysclkreq7_d_1_pins[] = { AB8500_PIN_T14 }; +static const unsigned sysclkreq8_d_1_pins[] = { AB8500_PIN_R16 }; +static const unsigned gpio26_d_1_pins[] = { AB8500_PIN_M16 }; +/* Digital microphone 1 and 2 */ +static const unsigned dmic12_d_1_pins[] = { AB8500_PIN_J6, AB8500_PIN_K6 }; +/* Digital microphone 3 and 4 */ +static const unsigned dmic34_d_1_pins[] = { AB8500_PIN_G6, AB8500_PIN_H6 }; +/* Digital microphone 5 and 6 */ +static const unsigned dmic56_d_1_pins[] = { AB8500_PIN_F5, AB8500_PIN_G5 }; +static const unsigned extcpena_d_1_pins[] = { AB8500_PIN_R17 }; +static const unsigned gpio35_d_1_pins[] = { AB8500_PIN_W15 }; +/* APE SPI */ +static const unsigned apespi_d_1_pins[] = { AB8500_PIN_A17, AB8500_PIN_E15, + AB8500_PIN_C17, AB8500_PIN_E16}; +/* modem SDA/SCL */ +static const unsigned modsclsda_d_1_pins[] = { AB8500_PIN_T19, AB8500_PIN_U19 }; +static const unsigned sysclkreq5_d_1_pins[] = { AB8500_PIN_U2 }; + +/* Altfunction A column */ +static const unsigned gpio1_a_1_pins[] = { AB8500_PIN_T10 }; +static const unsigned gpio2_a_1_pins[] = { AB8500_PIN_T9 }; +static const unsigned gpio3_a_1_pins[] = { AB8500_PIN_U9 }; +static const unsigned gpio4_a_1_pins[] = { AB8500_PIN_W2 }; +static const unsigned gpio6_a_1_pins[] = { AB8500_PIN_Y18 }; +static const unsigned gpio7_a_1_pins[] = { AB8500_PIN_AA20 }; +static const unsigned gpio8_a_1_pins[] = { AB8500_PIN_W18 }; +static const unsigned gpio9_a_1_pins[] = { AB8500_PIN_AA19 }; +/* YCbCr4 YCbCr5 YCbCr6 YCbCr7*/ +static const unsigned ycbcr4567_a_1_pins[] = { AB8500_PIN_U17, AB8500_PIN_AA18, + AB8500_PIN_U16, AB8500_PIN_W17}; +static const unsigned gpio14_a_1_pins[] = { AB8500_PIN_F14 }; +static const unsigned gpio15_a_1_pins[] = { AB8500_PIN_B17 }; +static const unsigned gpio16_a_1_pins[] = { AB8500_PIN_F15 }; +static const unsigned gpio17_a_1_pins[] = { AB8500_PIN_P5 }; +static const unsigned gpio18_a_1_pins[] = { AB8500_PIN_R5 }; +static const unsigned gpio19_a_1_pins[] = { AB8500_PIN_U5 }; +static const unsigned gpio20_a_1_pins[] = { AB8500_PIN_T5 }; +static const unsigned gpio21_a_1_pins[] = { AB8500_PIN_H19 }; +static const unsigned gpio22_a_1_pins[] = { AB8500_PIN_G20 }; +static const unsigned gpio23_a_1_pins[] = { AB8500_PIN_G19 }; +static const unsigned gpio24_a_1_pins[] = { AB8500_PIN_T14 }; +static const unsigned gpio25_a_1_pins[] = { AB8500_PIN_R16 }; +static const unsigned gpio27_a_1_pins[] = { AB8500_PIN_J6 }; +static const unsigned gpio28_a_1_pins[] = { AB8500_PIN_K6 }; +static const unsigned gpio29_a_1_pins[] = { AB8500_PIN_G6 }; +static const unsigned gpio30_a_1_pins[] = { AB8500_PIN_H6 }; +static const unsigned gpio31_a_1_pins[] = { AB8500_PIN_F5 }; +static const unsigned gpio32_a_1_pins[] = { AB8500_PIN_G5 }; +static const unsigned gpio34_a_1_pins[] = { AB8500_PIN_R17 }; +static const unsigned gpio36_a_1_pins[] = { AB8500_PIN_A17 }; +static const unsigned gpio37_a_1_pins[] = { AB8500_PIN_E15 }; +static const unsigned gpio38_a_1_pins[] = { AB8500_PIN_C17 }; +static const unsigned gpio39_a_1_pins[] = { AB8500_PIN_E16 }; +static const unsigned gpio40_a_1_pins[] = { AB8500_PIN_T19 }; +static const unsigned gpio41_a_1_pins[] = { AB8500_PIN_U19 }; +static const unsigned gpio42_a_1_pins[] = { AB8500_PIN_U2 }; + +/* Altfunction B colum */ +static const unsigned hiqclkena_b_1_pins[] = { AB8500_PIN_U17 }; +static const unsigned usbuiccpd_b_1_pins[] = { AB8500_PIN_AA18 }; +static const unsigned i2ctrig1_b_1_pins[] = { AB8500_PIN_U16 }; +static const unsigned i2ctrig2_b_1_pins[] = { AB8500_PIN_W17 }; + +/* Altfunction C column */ +static const unsigned usbvdat_c_1_pins[] = { AB8500_PIN_W17 }; + + +#define AB8500_PIN_GROUP(a, b) { .name = #a, .pins = a##_pins, \ + .npins = ARRAY_SIZE(a##_pins), .altsetting = b } + +static const struct abx500_pingroup ab8500_groups[] = { + /* default column */ + AB8500_PIN_GROUP(sysclkreq2_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(sysclkreq3_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(sysclkreq4_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(sysclkreq6_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(ycbcr0123_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(gpio10_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(gpio11_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(gpio12_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(gpio13_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(pwmout1_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(pwmout2_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(pwmout3_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(adi1_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(usbuicc_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(sysclkreq7_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(sysclkreq8_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(gpio26_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(dmic12_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(dmic34_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(dmic56_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(extcpena_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(gpio35_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(apespi_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(modsclsda_d_1, ABX500_DEFAULT), + AB8500_PIN_GROUP(sysclkreq5_d_1, ABX500_DEFAULT), + /* Altfunction A column */ + AB8500_PIN_GROUP(gpio1_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio2_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio3_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio4_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio6_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio7_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio8_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio9_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(ycbcr4567_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio14_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio15_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio16_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio17_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio18_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio19_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio20_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio21_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio22_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio23_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio24_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio25_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio27_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio28_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio29_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio30_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio31_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio32_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio34_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio36_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio37_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio38_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio39_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio40_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio41_a_1, ABX500_ALT_A), + AB8500_PIN_GROUP(gpio42_a_1, ABX500_ALT_A), + /* Altfunction B column */ + AB8500_PIN_GROUP(hiqclkena_b_1, ABX500_ALT_B), + AB8500_PIN_GROUP(usbuiccpd_b_1, ABX500_ALT_B), + AB8500_PIN_GROUP(i2ctrig1_b_1, ABX500_ALT_B), + AB8500_PIN_GROUP(i2ctrig2_b_1, ABX500_ALT_B), + /* Altfunction C column */ + AB8500_PIN_GROUP(usbvdat_c_1, ABX500_ALT_C), +}; + +/* We use this macro to define the groups applicable to a function */ +#define AB8500_FUNC_GROUPS(a, b...) \ +static const char * const a##_groups[] = { b }; + +AB8500_FUNC_GROUPS(sysclkreq, "sysclkreq2_d_1", "sysclkreq3_d_1", + "sysclkreq4_d_1", "sysclkreq5_d_1", "sysclkreq6_d_1", + "sysclkreq7_d_1", "sysclkreq8_d_1"); +AB8500_FUNC_GROUPS(ycbcr, "ycbcr0123_d_1", "ycbcr4567_a_1"); +AB8500_FUNC_GROUPS(gpio, "gpio1_a_1", "gpio2_a_1", "gpio3_a_1", "gpio4_a_1", + "gpio6_a_1", "gpio7_a_1", "gpio8_a_1", "gpio9_a_1", + "gpio10_d_1", "gpio11_d_1", "gpio12_d_1", "gpio13_d_1", + "gpio14_a_1", "gpio15_a_1", "gpio16_a_1", "gpio17_a_1", + "gpio18_a_1", "gpio19_a_1", "gpio20_a_1", "gpio21_a_1", + "gpio22_a_1", "gpio23_a_1", "gpio24_a_1", "gpio25_a_1", + "gpio26_d_1", "gpio27_a_1", "gpio28_a_1", "gpio29_a_1", + "gpio30_a_1", "gpio31_a_1", "gpio32_a_1", "gpio34_a_1", + "gpio35_d_1", "gpio36_a_1", "gpio37_a_1", "gpio38_a_1", + "gpio39_a_1", "gpio40_a_1", "gpio41_a_1", "gpio42_a_1"); +AB8500_FUNC_GROUPS(pwmout, "pwmout1_d_1", "pwmout2_d_1", "pwmout3_d_1"); +AB8500_FUNC_GROUPS(adi1, "adi1_d_1"); +AB8500_FUNC_GROUPS(usbuicc, "usbuicc_d_1", "usbuiccpd_b_1"); +AB8500_FUNC_GROUPS(dmic, "dmic12_d_1", "dmic34_d_1", "dmic56_d_1"); +AB8500_FUNC_GROUPS(extcpena, "extcpena_d_1"); +AB8500_FUNC_GROUPS(apespi, "apespi_d_1"); +AB8500_FUNC_GROUPS(modsclsda, "modsclsda_d_1"); +AB8500_FUNC_GROUPS(hiqclkena, "hiqclkena_b_1"); +AB8500_FUNC_GROUPS(i2ctrig, "i2ctrig1_b_1", "i2ctrig2_b_1"); +AB8500_FUNC_GROUPS(usbvdat, "usbvdat_c_1"); + +#define FUNCTION(fname) \ + { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +static const struct abx500_function ab8500_functions[] = { + FUNCTION(sysclkreq), + FUNCTION(ycbcr), + FUNCTION(gpio), + FUNCTION(pwmout), + FUNCTION(adi1), + FUNCTION(usbuicc), + FUNCTION(dmic), + FUNCTION(extcpena), + FUNCTION(apespi), + FUNCTION(modsclsda), + FUNCTION(hiqclkena), + FUNCTION(i2ctrig), + FUNCTION(usbvdat), +}; + +/* + * this table translates what's is in the AB8500 specification regarding the + * balls alternate functions (as for DB, default, ALT_A, ALT_B and ALT_C). + * ALTERNATE_FUNCTIONS(GPIO_NUMBER, GPIOSEL bit, ALTERNATFUNC bit1, + * ALTERNATEFUNC bit2, ALTA val, ALTB val, ALTC val), + * + * example : + * + * ALTERNATE_FUNCTIONS(13, 4, 3, 4, 0, 1 ,2), + * means that pin AB8500_PIN_W17 (pin 13) supports 4 mux (default/ALT_A, + * ALT_B and ALT_C), so GPIOSEL and ALTERNATFUNC registers are used to + * select the mux. ALTA, ALTB and ALTC val indicates values to write in + * ALTERNATFUNC register. We need to specifies these values as SOC + * designers didn't apply the same logic on how to select mux in the + * ABx500 family. + * + * As this pins supports at least ALT_B mux, default mux is + * selected by writing 1 in GPIOSEL bit : + * + * | GPIOSEL bit=4 | alternatfunc bit2=4 | alternatfunc bit1=3 + * default | 1 | 0 | 0 + * alt_A | 0 | 0 | 0 + * alt_B | 0 | 0 | 1 + * alt_C | 0 | 1 | 0 + * + * ALTERNATE_FUNCTIONS(8, 7, UNUSED, UNUSED), + * means that pin AB8500_PIN_W18 (pin 8) supports 2 mux, so only GPIOSEL + * register is used to select the mux. As this pins doesn't support at + * least ALT_B mux, default mux is by writing 0 in GPIOSEL bit : + * + * | GPIOSEL bit=7 | alternatfunc bit2= | alternatfunc bit1= + * default | 0 | 0 | 0 + * alt_A | 1 | 0 | 0 + */ + +struct alternate_functions ab8500_alternate_functions[AB8500_GPIO_MAX_NUMBER + 1] = { + ALTERNATE_FUNCTIONS(0, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO0 */ + ALTERNATE_FUNCTIONS(1, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO1, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(2, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO2, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(3, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO3, altA controlled by bit 2*/ + ALTERNATE_FUNCTIONS(4, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO4, altA controlled by bit 3*/ + /* bit 4 reserved */ + ALTERNATE_FUNCTIONS(5, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO5 */ + ALTERNATE_FUNCTIONS(6, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO6, altA controlled by bit 5*/ + ALTERNATE_FUNCTIONS(7, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO7, altA controlled by bit 6*/ + ALTERNATE_FUNCTIONS(8, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO8, altA controlled by bit 7*/ + + ALTERNATE_FUNCTIONS(9, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO9, altA controlled by bit 0*/ + ALTERNATE_FUNCTIONS(10, 1, 0, UNUSED, 0, 1, 0), /* GPIO10, altA and altB controlled by bit 0 */ + ALTERNATE_FUNCTIONS(11, 2, 1, UNUSED, 0, 1, 0), /* GPIO11, altA and altB controlled by bit 1 */ + ALTERNATE_FUNCTIONS(12, 3, 2, UNUSED, 0, 1, 0), /* GPIO12, altA and altB controlled by bit 2 */ + ALTERNATE_FUNCTIONS(13, 4, 3, 4, 0, 1, 2), /* GPIO13, altA altB and altC controlled by bit 3 and 4 */ + ALTERNATE_FUNCTIONS(14, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO14, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(15, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO15, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(16, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO16, altA controlled by bit 7 */ + /* + * pins 17 to 20 are special case, only bit 0 is used to select + * alternate function for these 4 pins. + * bits 1 to 3 are reserved + */ + ALTERNATE_FUNCTIONS(17, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO17, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(18, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO18, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(19, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO19, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(20, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO20, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(21, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO21, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(22, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO22, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(23, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO23, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(24, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO24, altA controlled by bit 7 */ + + ALTERNATE_FUNCTIONS(25, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO25, altA controlled by bit 0 */ + /* pin 26 special case, no alternate function, bit 1 reserved */ + ALTERNATE_FUNCTIONS(26, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* GPIO26 */ + ALTERNATE_FUNCTIONS(27, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO27, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(28, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO28, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(29, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO29, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(30, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO30, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(31, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO31, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(32, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO32, altA controlled by bit 7 */ + + ALTERNATE_FUNCTIONS(33, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO33 */ + ALTERNATE_FUNCTIONS(34, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO34, altA controlled by bit 1 */ + /* pin 35 special case, no alternate function, bit 2 reserved */ + ALTERNATE_FUNCTIONS(35, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* GPIO35 */ + ALTERNATE_FUNCTIONS(36, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO36, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(37, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO37, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(38, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO38, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(39, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO39, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(40, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO40, altA controlled by bit 7 */ + + ALTERNATE_FUNCTIONS(41, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO41, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(42, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO42, altA controlled by bit 1 */ +}; + +/* + * Only some GPIOs are interrupt capable, and they are + * organized in discontiguous clusters: + * + * GPIO6 to GPIO13 + * GPIO24 and GPIO25 + * GPIO36 to GPIO41 + */ +struct abx500_gpio_irq_cluster ab8500_gpio_irq_cluster[] = { + GPIO_IRQ_CLUSTER(6, 13, AB8500_INT_GPIO6R), + GPIO_IRQ_CLUSTER(24, 25, AB8500_INT_GPIO24R), + GPIO_IRQ_CLUSTER(36, 41, AB8500_INT_GPIO36R), +}; + +static struct abx500_pinctrl_soc_data ab8500_soc = { + .gpio_ranges = ab8500_pinranges, + .gpio_num_ranges = ARRAY_SIZE(ab8500_pinranges), + .pins = ab8500_pins, + .npins = ARRAY_SIZE(ab8500_pins), + .functions = ab8500_functions, + .nfunctions = ARRAY_SIZE(ab8500_functions), + .groups = ab8500_groups, + .ngroups = ARRAY_SIZE(ab8500_groups), + .alternate_functions = ab8500_alternate_functions, + .gpio_irq_cluster = ab8500_gpio_irq_cluster, + .ngpio_irq_cluster = ARRAY_SIZE(ab8500_gpio_irq_cluster), + .irq_gpio_rising_offset = AB8500_INT_GPIO6R, + .irq_gpio_falling_offset = AB8500_INT_GPIO6F, + .irq_gpio_factor = 1, +}; + +void abx500_pinctrl_ab8500_init(struct abx500_pinctrl_soc_data **soc) +{ + *soc = &ab8500_soc; +} diff --git a/drivers/pinctrl/pinctrl-ab8505.c b/drivers/pinctrl/pinctrl-ab8505.c new file mode 100644 index 0000000..3a4238e --- /dev/null +++ b/drivers/pinctrl/pinctrl-ab8505.c @@ -0,0 +1,380 @@ +/* + * Copyright (C) ST-Ericsson SA 2012 + * + * Author: Patrice Chotard <patrice.chotard@stericsson.com> for ST-Ericsson. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/mfd/abx500/ab8500.h> +#include "pinctrl-abx500.h" + +/* All the pins that can be used for GPIO and some other functions */ +#define ABX500_GPIO(offset) (offset) + +#define AB8505_PIN_N4 ABX500_GPIO(1) +#define AB8505_PIN_R5 ABX500_GPIO(2) +#define AB8505_PIN_P5 ABX500_GPIO(3) +/* hole */ +#define AB8505_PIN_B16 ABX500_GPIO(10) +#define AB8505_PIN_B17 ABX500_GPIO(11) +/* hole */ +#define AB8505_PIN_D17 ABX500_GPIO(13) +#define AB8505_PIN_C16 ABX500_GPIO(14) +/* hole */ +#define AB8505_PIN_P2 ABX500_GPIO(17) +#define AB8505_PIN_N3 ABX500_GPIO(18) +#define AB8505_PIN_T1 ABX500_GPIO(19) +#define AB8505_PIN_P3 ABX500_GPIO(20) +/* hole */ +#define AB8505_PIN_H14 ABX500_GPIO(34) +/* hole */ +#define AB8505_PIN_J15 ABX500_GPIO(40) +#define AB8505_PIN_J14 ABX500_GPIO(41) +/* hole */ +#define AB8505_PIN_L4 ABX500_GPIO(50) +/* hole */ +#define AB8505_PIN_D16 ABX500_GPIO(52) +#define AB8505_PIN_D15 ABX500_GPIO(53) + +/* indicates the higher GPIO number */ +#define AB8505_GPIO_MAX_NUMBER 53 + +/* + * The names of the pins are denoted by GPIO number and ball name, even + * though they can be used for other things than GPIO, this is the first + * column in the table of the data sheet and often used on schematics and + * such. + */ +static const struct pinctrl_pin_desc ab8505_pins[] = { + PINCTRL_PIN(AB8505_PIN_N4, "GPIO1_N4"), + PINCTRL_PIN(AB8505_PIN_R5, "GPIO2_R5"), + PINCTRL_PIN(AB8505_PIN_P5, "GPIO3_P5"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_B16, "GPIO10_B16"), + PINCTRL_PIN(AB8505_PIN_B17, "GPIO11_B17"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_D17, "GPIO13_D17"), + PINCTRL_PIN(AB8505_PIN_C16, "GPIO14_C16"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_P2, "GPIO17_P2"), + PINCTRL_PIN(AB8505_PIN_N3, "GPIO18_N3"), + PINCTRL_PIN(AB8505_PIN_T1, "GPIO19_T1"), + PINCTRL_PIN(AB8505_PIN_P3, "GPIO20_P3"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_H14, "GPIO34_H14"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_J15, "GPIO40_J15"), + PINCTRL_PIN(AB8505_PIN_J14, "GPIO41_J14"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_L4, "GPIO50_L4"), +/* hole */ + PINCTRL_PIN(AB8505_PIN_D16, "GPIO52_D16"), + PINCTRL_PIN(AB8505_PIN_D15, "GPIO53_D15"), +}; + +/* + * Maps local GPIO offsets to local pin numbers + */ +static const struct abx500_pinrange ab8505_pinranges[] = { + ABX500_PINRANGE(1, 3, ABX500_ALT_A), + ABX500_PINRANGE(10, 2, ABX500_DEFAULT), + ABX500_PINRANGE(13, 1, ABX500_DEFAULT), + ABX500_PINRANGE(14, 1, ABX500_ALT_A), + ABX500_PINRANGE(17, 4, ABX500_ALT_A), + ABX500_PINRANGE(34, 1, ABX500_ALT_A), + ABX500_PINRANGE(40, 2, ABX500_ALT_A), + ABX500_PINRANGE(50, 1, ABX500_DEFAULT), + ABX500_PINRANGE(52, 2, ABX500_ALT_A), +}; + +/* + * Read the pin group names like this: + * sysclkreq2_d_1 = first groups of pins for sysclkreq2 on default function + * + * The groups are arranged as sets per altfunction column, so we can + * mux in one group at a time by selecting the same altfunction for them + * all. When functions require pins on different altfunctions, you need + * to combine several groups. + */ + +/* default column */ +static const unsigned sysclkreq2_d_1_pins[] = { AB8505_PIN_N4 }; +static const unsigned sysclkreq3_d_1_pins[] = { AB8505_PIN_R5 }; +static const unsigned sysclkreq4_d_1_pins[] = { AB8505_PIN_P5 }; +static const unsigned gpio10_d_1_pins[] = { AB8505_PIN_B16 }; +static const unsigned gpio11_d_1_pins[] = { AB8505_PIN_B17 }; +static const unsigned gpio13_d_1_pins[] = { AB8505_PIN_D17 }; +static const unsigned pwmout1_d_1_pins[] = { AB8505_PIN_C16 }; +/* audio data interface 2*/ +static const unsigned adi2_d_1_pins[] = { AB8505_PIN_P2, AB8505_PIN_N3, + AB8505_PIN_T1, AB8505_PIN_P3 }; +static const unsigned extcpena_d_1_pins[] = { AB8505_PIN_H14 }; +/* modem SDA/SCL */ +static const unsigned modsclsda_d_1_pins[] = { AB8505_PIN_J15, AB8505_PIN_J14 }; +static const unsigned gpio50_d_1_pins[] = { AB8505_PIN_L4 }; +static const unsigned resethw_d_1_pins[] = { AB8505_PIN_D16 }; +static const unsigned service_d_1_pins[] = { AB8505_PIN_D15 }; + +/* Altfunction A column */ +static const unsigned gpio1_a_1_pins[] = { AB8505_PIN_N4 }; +static const unsigned gpio2_a_1_pins[] = { AB8505_PIN_R5 }; +static const unsigned gpio3_a_1_pins[] = { AB8505_PIN_P5 }; +static const unsigned hiqclkena_a_1_pins[] = { AB8505_PIN_B16 }; +static const unsigned pdmclk_a_1_pins[] = { AB8505_PIN_B17 }; +static const unsigned uarttxdata_a_1_pins[] = { AB8505_PIN_D17 }; +static const unsigned gpio14_a_1_pins[] = { AB8505_PIN_C16 }; +static const unsigned gpio17_a_1_pins[] = { AB8505_PIN_P2 }; +static const unsigned gpio18_a_1_pins[] = { AB8505_PIN_N3 }; +static const unsigned gpio19_a_1_pins[] = { AB8505_PIN_T1 }; +static const unsigned gpio20_a_1_pins[] = { AB8505_PIN_P3 }; +static const unsigned gpio34_a_1_pins[] = { AB8505_PIN_H14 }; +static const unsigned gpio40_a_1_pins[] = { AB8505_PIN_J15 }; +static const unsigned gpio41_a_1_pins[] = { AB8505_PIN_J14 }; +static const unsigned uartrxdata_a_1_pins[] = { AB8505_PIN_J14 }; +static const unsigned gpio50_a_1_pins[] = { AB8505_PIN_L4 }; +static const unsigned gpio52_a_1_pins[] = { AB8505_PIN_D16 }; +static const unsigned gpio53_a_1_pins[] = { AB8505_PIN_D15 }; + +/* Altfunction B colum */ +static const unsigned pdmdata_b_1_pins[] = { AB8505_PIN_B16 }; +static const unsigned extvibrapwm1_b_1_pins[] = { AB8505_PIN_D17 }; +static const unsigned extvibrapwm2_b_1_pins[] = { AB8505_PIN_L4 }; + +/* Altfunction C column */ +static const unsigned usbvdat_c_1_pins[] = { AB8505_PIN_D17 }; + +#define AB8505_PIN_GROUP(a, b) { .name = #a, .pins = a##_pins, \ + .npins = ARRAY_SIZE(a##_pins), .altsetting = b } + +static const struct abx500_pingroup ab8505_groups[] = { + AB8505_PIN_GROUP(sysclkreq2_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(sysclkreq3_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(sysclkreq4_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(gpio10_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(gpio11_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(gpio13_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(pwmout1_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(adi2_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(extcpena_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(modsclsda_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(gpio50_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(resethw_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(service_d_1, ABX500_DEFAULT), + AB8505_PIN_GROUP(gpio1_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio2_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio3_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(hiqclkena_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(pdmclk_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(uarttxdata_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio14_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio17_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio18_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio19_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio20_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio34_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio40_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio41_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(uartrxdata_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio52_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(gpio53_a_1, ABX500_ALT_A), + AB8505_PIN_GROUP(pdmdata_b_1, ABX500_ALT_B), + AB8505_PIN_GROUP(extvibrapwm1_b_1, ABX500_ALT_B), + AB8505_PIN_GROUP(extvibrapwm2_b_1, ABX500_ALT_B), + AB8505_PIN_GROUP(usbvdat_c_1, ABX500_ALT_C), +}; + +/* We use this macro to define the groups applicable to a function */ +#define AB8505_FUNC_GROUPS(a, b...) \ +static const char * const a##_groups[] = { b }; + +AB8505_FUNC_GROUPS(sysclkreq, "sysclkreq2_d_1", "sysclkreq3_d_1", + "sysclkreq4_d_1"); +AB8505_FUNC_GROUPS(gpio, "gpio1_a_1", "gpio2_a_1", "gpio3_a_1", + "gpio10_d_1", "gpio11_d_1", "gpio13_d_1", "gpio14_a_1", + "gpio17_a_1", "gpio18_a_1", "gpio19_a_1", "gpio20_a_1", + "gpio34_a_1", "gpio40_a_1", "gpio41_a_1", "gpio50_d_1", + "gpio52_a_1", "gpio53_a_1"); +AB8505_FUNC_GROUPS(pwmout, "pwmout1_d_1"); +AB8505_FUNC_GROUPS(adi2, "adi2_d_1"); +AB8505_FUNC_GROUPS(extcpena, "extcpena_d_1"); +AB8505_FUNC_GROUPS(modsclsda, "modsclsda_d_1"); +AB8505_FUNC_GROUPS(resethw, "resethw_d_1"); +AB8505_FUNC_GROUPS(service, "service_d_1"); +AB8505_FUNC_GROUPS(hiqclkena, "hiqclkena_a_1"); +AB8505_FUNC_GROUPS(pdm, "pdmclk_a_1", "pdmdata_b_1"); +AB8505_FUNC_GROUPS(uartdata, "uarttxdata_a_1", "uartrxdata_a_1"); +AB8505_FUNC_GROUPS(extvibra, "extvibrapwm1_b_1", "extvibrapwm2_b_1"); +AB8505_FUNC_GROUPS(usbvdat, "usbvdat_c_1"); + +#define FUNCTION(fname) \ + { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +static const struct abx500_function ab8505_functions[] = { + FUNCTION(sysclkreq), + FUNCTION(gpio), + FUNCTION(pwmout), + FUNCTION(adi2), + FUNCTION(extcpena), + FUNCTION(modsclsda), + FUNCTION(resethw), + FUNCTION(service), + FUNCTION(hiqclkena), + FUNCTION(pdm), + FUNCTION(uartdata), + FUNCTION(extvibra), + FUNCTION(extvibra), + FUNCTION(usbvdat), +}; + +/* + * this table translates what's is in the AB8505 specification regarding the + * balls alternate functions (as for DB, default, ALT_A, ALT_B and ALT_C). + * ALTERNATE_FUNCTIONS(GPIO_NUMBER, GPIOSEL bit, ALTERNATFUNC bit1, + * ALTERNATEFUNC bit2, ALTA val, ALTB val, ALTC val), + * + * example : + * + * ALTERNATE_FUNCTIONS(13, 4, 3, 4, 1, 0, 2), + * means that pin AB8505_PIN_D18 (pin 13) supports 4 mux (default/ALT_A, + * ALT_B and ALT_C), so GPIOSEL and ALTERNATFUNC registers are used to + * select the mux. ALTA, ALTB and ALTC val indicates values to write in + * ALTERNATFUNC register. We need to specifies these values as SOC + * designers didn't apply the same logic on how to select mux in the + * ABx500 family. + * + * As this pins supports at least ALT_B mux, default mux is + * selected by writing 1 in GPIOSEL bit : + * + * | GPIOSEL bit=4 | alternatfunc bit2=4 | alternatfunc bit1=3 + * default | 1 | 0 | 0 + * alt_A | 0 | 0 | 1 + * alt_B | 0 | 0 | 0 + * alt_C | 0 | 1 | 0 + * + * ALTERNATE_FUNCTIONS(1, 0, UNUSED, UNUSED), + * means that pin AB9540_PIN_R4 (pin 1) supports 2 mux, so only GPIOSEL + * register is used to select the mux. As this pins doesn't support at + * least ALT_B mux, default mux is by writing 0 in GPIOSEL bit : + * + * | GPIOSEL bit=0 | alternatfunc bit2= | alternatfunc bit1= + * default | 0 | 0 | 0 + * alt_A | 1 | 0 | 0 + */ + +struct alternate_functions ab8505_alternate_functions[AB8505_GPIO_MAX_NUMBER + 1] = { + ALTERNATE_FUNCTIONS(0, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO0 */ + ALTERNATE_FUNCTIONS(1, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO1, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(2, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO2, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(3, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO3, altA controlled by bit 2*/ + ALTERNATE_FUNCTIONS(4, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO4, bit 3 reserved */ + ALTERNATE_FUNCTIONS(5, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO5, bit 4 reserved */ + ALTERNATE_FUNCTIONS(6, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO6, bit 5 reserved */ + ALTERNATE_FUNCTIONS(7, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO7, bit 6 reserved */ + ALTERNATE_FUNCTIONS(8, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO8, bit 7 reserved */ + + ALTERNATE_FUNCTIONS(9, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO9, bit 0 reserved */ + ALTERNATE_FUNCTIONS(10, 1, 0, UNUSED, 1, 0, 0), /* GPIO10, altA and altB controlled by bit 0 */ + ALTERNATE_FUNCTIONS(11, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO11, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(12, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO12, bit3 reseved */ + ALTERNATE_FUNCTIONS(13, 4, 3, 4, 1, 0, 2), /* GPIO13, altA altB and altC controlled by bit 3 and 4 */ + ALTERNATE_FUNCTIONS(14, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO14, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(15, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO15, bit 6 reserved */ + ALTERNATE_FUNCTIONS(16, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO15, bit 7 reserved */ + /* + * pins 17 to 20 are special case, only bit 0 is used to select + * alternate function for these 4 pins. + * bits 1 to 3 are reserved + */ + ALTERNATE_FUNCTIONS(17, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO17, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(18, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO18, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(19, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO19, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(20, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO20, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(21, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO21, bit 4 reserved */ + ALTERNATE_FUNCTIONS(22, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO22, bit 5 reserved */ + ALTERNATE_FUNCTIONS(23, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO23, bit 6 reserved */ + ALTERNATE_FUNCTIONS(24, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO24, bit 7 reserved */ + + ALTERNATE_FUNCTIONS(25, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO25, bit 0 reserved */ + ALTERNATE_FUNCTIONS(26, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO26, bit 1 reserved */ + ALTERNATE_FUNCTIONS(27, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO27, bit 2 reserved */ + ALTERNATE_FUNCTIONS(28, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO28, bit 3 reserved */ + ALTERNATE_FUNCTIONS(29, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO29, bit 4 reserved */ + ALTERNATE_FUNCTIONS(30, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO30, bit 5 reserved */ + ALTERNATE_FUNCTIONS(31, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO31, bit 6 reserved */ + ALTERNATE_FUNCTIONS(32, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO32, bit 7 reserved */ + + ALTERNATE_FUNCTIONS(33, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO33, bit 0 reserved */ + ALTERNATE_FUNCTIONS(34, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO34, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(35, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO35, bit 2 reserved */ + ALTERNATE_FUNCTIONS(36, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO36, bit 2 reserved */ + ALTERNATE_FUNCTIONS(37, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO37, bit 2 reserved */ + ALTERNATE_FUNCTIONS(38, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO38, bit 2 reserved */ + ALTERNATE_FUNCTIONS(39, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO39, bit 2 reserved */ + ALTERNATE_FUNCTIONS(40, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO40, altA controlled by bit 7*/ + + ALTERNATE_FUNCTIONS(41, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO41, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(42, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO42, bit 1 reserved */ + ALTERNATE_FUNCTIONS(43, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO43, bit 2 reserved */ + ALTERNATE_FUNCTIONS(44, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO44, bit 3 reserved */ + ALTERNATE_FUNCTIONS(45, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO45, bit 4 reserved */ + ALTERNATE_FUNCTIONS(46, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO46, bit 5 reserved */ + ALTERNATE_FUNCTIONS(47, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO47, bit 6 reserved */ + ALTERNATE_FUNCTIONS(48, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO48, bit 7 reserved */ + + ALTERNATE_FUNCTIONS(49, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO49, bit 0 reserved */ + ALTERNATE_FUNCTIONS(50, 1, 2, UNUSED, 1, 0, 0), /* GPIO50, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(51, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO49, bit 0 reserved */ + ALTERNATE_FUNCTIONS(52, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO52, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(53, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO53, altA controlled by bit 4 */ +}; + +/* + * For AB8505 Only some GPIOs are interrupt capable, and they are + * organized in discontiguous clusters: + * + * GPIO10 to GPIO11 + * GPIO13 + * GPIO40 and GPIO41 + * GPIO50 + * GPIO52 to GPIO53 + */ +struct abx500_gpio_irq_cluster ab8505_gpio_irq_cluster[] = { + GPIO_IRQ_CLUSTER(10, 11, AB8500_INT_GPIO10R), + GPIO_IRQ_CLUSTER(13, 13, AB8500_INT_GPIO13R), + GPIO_IRQ_CLUSTER(40, 41, AB8500_INT_GPIO40R), + GPIO_IRQ_CLUSTER(50, 50, AB9540_INT_GPIO50R), + GPIO_IRQ_CLUSTER(52, 53, AB9540_INT_GPIO52R), +}; + +static struct abx500_pinctrl_soc_data ab8505_soc = { + .gpio_ranges = ab8505_pinranges, + .gpio_num_ranges = ARRAY_SIZE(ab8505_pinranges), + .pins = ab8505_pins, + .npins = ARRAY_SIZE(ab8505_pins), + .functions = ab8505_functions, + .nfunctions = ARRAY_SIZE(ab8505_functions), + .groups = ab8505_groups, + .ngroups = ARRAY_SIZE(ab8505_groups), + .alternate_functions = ab8505_alternate_functions, + .gpio_irq_cluster = ab8505_gpio_irq_cluster, + .ngpio_irq_cluster = ARRAY_SIZE(ab8505_gpio_irq_cluster), + .irq_gpio_rising_offset = AB8500_INT_GPIO6R, + .irq_gpio_falling_offset = AB8500_INT_GPIO6F, + .irq_gpio_factor = 1, +}; + +void +abx500_pinctrl_ab8505_init(struct abx500_pinctrl_soc_data **soc) +{ + *soc = &ab8505_soc; +} diff --git a/drivers/pinctrl/pinctrl-ab8540.c b/drivers/pinctrl/pinctrl-ab8540.c new file mode 100644 index 0000000..8ee1e8d --- /dev/null +++ b/drivers/pinctrl/pinctrl-ab8540.c @@ -0,0 +1,407 @@ +/* + * Copyright (C) ST-Ericsson SA 2012 + * + * Author: Patrice Chotard <patrice.chotard@stericsson.com> for ST-Ericsson. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/mfd/abx500/ab8500.h> +#include "pinctrl-abx500.h" + +/* All the pins that can be used for GPIO and some other functions */ +#define ABX500_GPIO(offset) (offset) + +#define AB8540_PIN_J16 ABX500_GPIO(1) +#define AB8540_PIN_D17 ABX500_GPIO(2) +#define AB8540_PIN_C12 ABX500_GPIO(3) +#define AB8540_PIN_G12 ABX500_GPIO(4) +/* hole */ +#define AB8540_PIN_D16 ABX500_GPIO(14) +#define AB8540_PIN_F15 ABX500_GPIO(15) +#define AB8540_PIN_J8 ABX500_GPIO(16) +#define AB8540_PIN_K16 ABX500_GPIO(17) +#define AB8540_PIN_G15 ABX500_GPIO(18) +#define AB8540_PIN_F17 ABX500_GPIO(19) +#define AB8540_PIN_E17 ABX500_GPIO(20) +/* hole */ +#define AB8540_PIN_AA16 ABX500_GPIO(27) +#define AB8540_PIN_W18 ABX500_GPIO(28) +#define AB8540_PIN_Y15 ABX500_GPIO(29) +#define AB8540_PIN_W16 ABX500_GPIO(30) +#define AB8540_PIN_V15 ABX500_GPIO(31) +#define AB8540_PIN_W17 ABX500_GPIO(32) +/* hole */ +#define AB8540_PIN_D12 ABX500_GPIO(42) +#define AB8540_PIN_P4 ABX500_GPIO(43) +#define AB8540_PIN_AB1 ABX500_GPIO(44) +#define AB8540_PIN_K7 ABX500_GPIO(45) +#define AB8540_PIN_L7 ABX500_GPIO(46) +#define AB8540_PIN_G10 ABX500_GPIO(47) +#define AB8540_PIN_K12 ABX500_GPIO(48) +/* hole */ +#define AB8540_PIN_N8 ABX500_GPIO(51) +#define AB8540_PIN_P12 ABX500_GPIO(52) +#define AB8540_PIN_K8 ABX500_GPIO(53) +#define AB8540_PIN_J11 ABX500_GPIO(54) +#define AB8540_PIN_AC2 ABX500_GPIO(55) +#define AB8540_PIN_AB2 ABX500_GPIO(56) + +/* indicates the highest GPIO number */ +#define AB8540_GPIO_MAX_NUMBER 56 + +/* + * The names of the pins are denoted by GPIO number and ball name, even + * though they can be used for other things than GPIO, this is the first + * column in the table of the data sheet and often used on schematics and + * such. + */ +static const struct pinctrl_pin_desc ab8540_pins[] = { + PINCTRL_PIN(AB8540_PIN_J16, "GPIO1_J16"), + PINCTRL_PIN(AB8540_PIN_D17, "GPIO2_D17"), + PINCTRL_PIN(AB8540_PIN_C12, "GPIO3_C12"), + PINCTRL_PIN(AB8540_PIN_G12, "GPIO4_G12"), + /* hole */ + PINCTRL_PIN(AB8540_PIN_D16, "GPIO14_D16"), + PINCTRL_PIN(AB8540_PIN_F15, "GPIO15_F15"), + PINCTRL_PIN(AB8540_PIN_J8, "GPIO16_J8"), + PINCTRL_PIN(AB8540_PIN_K16, "GPIO17_K16"), + PINCTRL_PIN(AB8540_PIN_G15, "GPIO18_G15"), + PINCTRL_PIN(AB8540_PIN_F17, "GPIO19_F17"), + PINCTRL_PIN(AB8540_PIN_E17, "GPIO20_E17"), + /* hole */ + PINCTRL_PIN(AB8540_PIN_AA16, "GPIO27_AA16"), + PINCTRL_PIN(AB8540_PIN_W18, "GPIO28_W18"), + PINCTRL_PIN(AB8540_PIN_Y15, "GPIO29_Y15"), + PINCTRL_PIN(AB8540_PIN_W16, "GPIO30_W16"), + PINCTRL_PIN(AB8540_PIN_V15, "GPIO31_V15"), + PINCTRL_PIN(AB8540_PIN_W17, "GPIO32_W17"), + /* hole */ + PINCTRL_PIN(AB8540_PIN_D12, "GPIO42_D12"), + PINCTRL_PIN(AB8540_PIN_P4, "GPIO43_P4"), + PINCTRL_PIN(AB8540_PIN_AB1, "GPIO44_AB1"), + PINCTRL_PIN(AB8540_PIN_K7, "GPIO45_K7"), + PINCTRL_PIN(AB8540_PIN_L7, "GPIO46_L7"), + PINCTRL_PIN(AB8540_PIN_G10, "GPIO47_G10"), + PINCTRL_PIN(AB8540_PIN_K12, "GPIO48_K12"), + /* hole */ + PINCTRL_PIN(AB8540_PIN_N8, "GPIO51_N8"), + PINCTRL_PIN(AB8540_PIN_P12, "GPIO52_P12"), + PINCTRL_PIN(AB8540_PIN_K8, "GPIO53_K8"), + PINCTRL_PIN(AB8540_PIN_J11, "GPIO54_J11"), + PINCTRL_PIN(AB8540_PIN_AC2, "GPIO55_AC2"), + PINCTRL_PIN(AB8540_PIN_AB2, "GPIO56_AB2"), +}; + +/* + * Maps local GPIO offsets to local pin numbers + */ +static const struct abx500_pinrange ab8540_pinranges[] = { + ABX500_PINRANGE(1, 4, ABX500_ALT_A), + ABX500_PINRANGE(14, 7, ABX500_ALT_A), + ABX500_PINRANGE(27, 6, ABX500_ALT_A), + ABX500_PINRANGE(42, 7, ABX500_ALT_A), + ABX500_PINRANGE(51, 6, ABX500_ALT_A), +}; + +/* + * Read the pin group names like this: + * sysclkreq2_d_1 = first groups of pins for sysclkreq2 on default function + * + * The groups are arranged as sets per altfunction column, so we can + * mux in one group at a time by selecting the same altfunction for them + * all. When functions require pins on different altfunctions, you need + * to combine several groups. + */ + +/* default column */ +static const unsigned sysclkreq2_d_1_pins[] = { AB8540_PIN_J16 }; +static const unsigned sysclkreq3_d_1_pins[] = { AB8540_PIN_D17 }; +static const unsigned sysclkreq4_d_1_pins[] = { AB8540_PIN_C12 }; +static const unsigned sysclkreq6_d_1_pins[] = { AB8540_PIN_G12 }; +static const unsigned pwmout1_d_1_pins[] = { AB8540_PIN_D16 }; +static const unsigned pwmout2_d_1_pins[] = { AB8540_PIN_F15 }; +static const unsigned pwmout3_d_1_pins[] = { AB8540_PIN_J8 }; + +/* audio data interface 1*/ +static const unsigned adi1_d_1_pins[] = { AB8540_PIN_K16, AB8540_PIN_G15, + AB8540_PIN_F17, AB8540_PIN_E17 }; +/* Digital microphone 1 and 2 */ +static const unsigned dmic12_d_1_pins[] = { AB8540_PIN_AA16, AB8540_PIN_W18 }; +/* Digital microphone 3 and 4 */ +static const unsigned dmic34_d_1_pins[] = { AB8540_PIN_Y15, AB8540_PIN_W16 }; +/* Digital microphone 5 and 6 */ +static const unsigned dmic56_d_1_pins[] = { AB8540_PIN_V15, AB8540_PIN_W17 }; +static const unsigned sysclkreq5_d_1_pins[] = { AB8540_PIN_D12 }; +static const unsigned batremn_d_1_pins[] = { AB8540_PIN_P4 }; +static const unsigned service_d_1_pins[] = { AB8540_PIN_AB1 }; +static const unsigned pwrctrl0_d_1_pins[] = { AB8540_PIN_K7 }; +static const unsigned pwrctrl1_d_1_pins[] = { AB8540_PIN_L7 }; +static const unsigned pwmextvibra1_d_1_pins[] = { AB8540_PIN_G10 }; +static const unsigned pwmextvibra2_d_1_pins[] = { AB8540_PIN_K12 }; +static const unsigned gpio1_vbat_d_1_pins[] = { AB8540_PIN_N8 }; +static const unsigned gpio2_vbat_d_1_pins[] = { AB8540_PIN_P12 }; +static const unsigned gpio3_vbat_d_1_pins[] = { AB8540_PIN_K8 }; +static const unsigned gpio4_vbat_d_1_pins[] = { AB8540_PIN_J11 }; +static const unsigned pdmclkdat_d_1_pins[] = { AB8540_PIN_AC2, AB8540_PIN_AB2 }; + +/* Altfunction A column */ +static const unsigned gpio1_a_1_pins[] = { AB8540_PIN_J16 }; +static const unsigned gpio2_a_1_pins[] = { AB8540_PIN_D17 }; +static const unsigned gpio3_a_1_pins[] = { AB8540_PIN_C12 }; +static const unsigned gpio4_a_1_pins[] = { AB8540_PIN_G12 }; +static const unsigned gpio14_a_1_pins[] = { AB8540_PIN_D16 }; +static const unsigned gpio15_a_1_pins[] = { AB8540_PIN_F15 }; +static const unsigned gpio16_a_1_pins[] = { AB8540_PIN_J8 }; +static const unsigned gpio17_a_1_pins[] = { AB8540_PIN_K16 }; +static const unsigned gpio18_a_1_pins[] = { AB8540_PIN_G15 }; +static const unsigned gpio19_a_1_pins[] = { AB8540_PIN_F17 }; +static const unsigned gpio20_a_1_pins[] = { AB8540_PIN_E17 }; +static const unsigned gpio27_a_1_pins[] = { AB8540_PIN_AA16 }; +static const unsigned gpio28_a_1_pins[] = { AB8540_PIN_W18 }; +static const unsigned gpio29_a_1_pins[] = { AB8540_PIN_Y15 }; +static const unsigned gpio30_a_1_pins[] = { AB8540_PIN_W16 }; +static const unsigned gpio31_a_1_pins[] = { AB8540_PIN_V15 }; +static const unsigned gpio32_a_1_pins[] = { AB8540_PIN_W17 }; +static const unsigned gpio42_a_1_pins[] = { AB8540_PIN_D12 }; +static const unsigned gpio43_a_1_pins[] = { AB8540_PIN_P4 }; +static const unsigned gpio44_a_1_pins[] = { AB8540_PIN_AB1 }; +static const unsigned gpio45_a_1_pins[] = { AB8540_PIN_K7 }; +static const unsigned gpio46_a_1_pins[] = { AB8540_PIN_L7 }; +static const unsigned gpio47_a_1_pins[] = { AB8540_PIN_G10 }; +static const unsigned gpio48_a_1_pins[] = { AB8540_PIN_K12 }; +static const unsigned gpio51_a_1_pins[] = { AB8540_PIN_N8 }; +static const unsigned gpio52_a_1_pins[] = { AB8540_PIN_P12 }; +static const unsigned gpio53_a_1_pins[] = { AB8540_PIN_K8 }; +static const unsigned gpio54_a_1_pins[] = { AB8540_PIN_J11 }; +static const unsigned gpio55_a_1_pins[] = { AB8540_PIN_AC2 }; +static const unsigned gpio56_a_1_pins[] = { AB8540_PIN_AB2 }; + +#define AB8540_PIN_GROUP(a, b) { .name = #a, .pins = a##_pins, \ + .npins = ARRAY_SIZE(a##_pins), .altsetting = b } + +static const struct abx500_pingroup ab8540_groups[] = { + /* default column */ + AB8540_PIN_GROUP(sysclkreq2_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(sysclkreq3_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(sysclkreq4_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(sysclkreq6_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwmout1_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwmout2_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwmout3_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(adi1_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(dmic12_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(dmic34_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(dmic56_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(sysclkreq5_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(batremn_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(service_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwrctrl0_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwrctrl1_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwmextvibra1_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pwmextvibra2_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(gpio1_vbat_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(gpio2_vbat_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(gpio3_vbat_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(gpio4_vbat_d_1, ABX500_DEFAULT), + AB8540_PIN_GROUP(pdmclkdat_d_1, ABX500_DEFAULT), + /* Altfunction A column */ + AB8540_PIN_GROUP(gpio1_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio2_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio3_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio4_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio14_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio15_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio16_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio17_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio18_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio19_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio20_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio27_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio28_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio29_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio30_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio31_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio32_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio42_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio43_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio44_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio45_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio46_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio47_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio48_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio51_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio52_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio53_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio54_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio55_a_1, ABX500_ALT_A), + AB8540_PIN_GROUP(gpio56_a_1, ABX500_ALT_A), +}; + +/* We use this macro to define the groups applicable to a function */ +#define AB8540_FUNC_GROUPS(a, b...) \ +static const char * const a##_groups[] = { b }; + +AB8540_FUNC_GROUPS(sysclkreq, "sysclkreq2_d_1", "sysclkreq3_d_1", + "sysclkreq4_d_1", "sysclkreq5_d_1", "sysclkreq6_d_1"); +AB8540_FUNC_GROUPS(gpio, "gpio1_a_1", "gpio2_a_1", "gpio3_a_1", "gpio4_a_1", + "gpio14_a_1", "gpio15_a_1", "gpio16_a_1", "gpio17_a_1", + "gpio18_a_1", "gpio19_a_1", "gpio20_a_1", "gpio27_a_1", + "gpio28_a_1", "gpio29_a_1", "gpio30_a_1", "gpio31_a_1", + "gpio32_a_1", "gpio42_a_1", "gpio43_a_1", "gpio44_a_1", + "gpio45_a_1", "gpio46_a_1", "gpio47_a_1", "gpio48_a_1", + "gpio51_a_1", "gpio52_a_1", "gpio53_a_1", "gpio54_a_1", + "gpio55_a_1", "gpio56_a_1"); +AB8540_FUNC_GROUPS(pwmout, "pwmout1_d_1", "pwmout2_d_1", "pwmout3_d_1"); +AB8540_FUNC_GROUPS(adi1, "adi1_d_1"); +AB8540_FUNC_GROUPS(dmic, "dmic12_d_1", "dmic34_d_1", "dmic56_d_1"); +AB8540_FUNC_GROUPS(batremn, "batremn_d_1"); +AB8540_FUNC_GROUPS(service, "service_d_1"); +AB8540_FUNC_GROUPS(pwrctrl, "pwrctrl0_d_1", "pwrctrl1_d_1"); +AB8540_FUNC_GROUPS(pwmextvibra, "pwmextvibra1_d_1", "pwmextvibra2_d_1"); +AB8540_FUNC_GROUPS(gpio_vbat, "gpio1_vbat_d_1", "gpio2_vbat_d_1", + "gpio3_vbat_d_1", "gpio4_vbat_d_1"); +AB8540_FUNC_GROUPS(pdm, "pdmclkdat_d_1"); + +#define FUNCTION(fname) \ + { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +static const struct abx500_function ab8540_functions[] = { + FUNCTION(sysclkreq), + FUNCTION(gpio), + FUNCTION(pwmout), + FUNCTION(adi1), + FUNCTION(dmic), + FUNCTION(batremn), + FUNCTION(service), + FUNCTION(pwrctrl), + FUNCTION(pwmextvibra), + FUNCTION(gpio_vbat), + FUNCTION(pdm), +}; + +/* + * this table translates what's is in the AB8540 specification regarding the + * balls alternate functions (as for DB, default, ALT_A, ALT_B and ALT_C). + * ALTERNATE_FUNCTIONS(GPIO_NUMBER, GPIOSEL bit, ALTERNATFUNC bit1, + * ALTERNATEFUNC bit2, ALTA val, ALTB val, ALTC val), + * AB8540 only supports DEFAULT and ALTA functions, so ALTERNATFUNC + * registers is not used + * + */ + +struct alternate_functions ab8540_alternate_functions[AB8540_GPIO_MAX_NUMBER + 1] = { + /* GPIOSEL1 - bit 4-7 reserved */ + ALTERNATE_FUNCTIONS(0, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO0 */ + ALTERNATE_FUNCTIONS(1, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO1, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(2, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO2, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(3, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO3, altA controlled by bit 2*/ + ALTERNATE_FUNCTIONS(4, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO4, altA controlled by bit 3*/ + ALTERNATE_FUNCTIONS(5, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO5 */ + ALTERNATE_FUNCTIONS(6, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO6 */ + ALTERNATE_FUNCTIONS(7, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO7 */ + ALTERNATE_FUNCTIONS(8, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO8 */ + /* GPIOSEL2 - bit 0-4 reserved */ + ALTERNATE_FUNCTIONS(9, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO9 */ + ALTERNATE_FUNCTIONS(10, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO10 */ + ALTERNATE_FUNCTIONS(11, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO11 */ + ALTERNATE_FUNCTIONS(12, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO12 */ + ALTERNATE_FUNCTIONS(13, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO13 */ + ALTERNATE_FUNCTIONS(14, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO14, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(15, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO15, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(16, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO16, altA controlled by bit 7 */ + /* GPIOSEL3 - bit 4-7 reserved */ + ALTERNATE_FUNCTIONS(17, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO17, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(18, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO18, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(19, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO19, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(20, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO20, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(21, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO21 */ + ALTERNATE_FUNCTIONS(22, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO22 */ + ALTERNATE_FUNCTIONS(23, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO23 */ + ALTERNATE_FUNCTIONS(24, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO24 */ + /* GPIOSEL4 - bit 0-1 reserved */ + ALTERNATE_FUNCTIONS(25, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO25 */ + ALTERNATE_FUNCTIONS(26, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO26 */ + ALTERNATE_FUNCTIONS(27, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO27, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(28, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO28, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(29, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO29, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(30, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO30, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(31, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO31, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(32, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO32, altA controlled by bit 7 */ + /* GPIOSEL5 - bit 0-7 reserved */ + ALTERNATE_FUNCTIONS(33, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO33 */ + ALTERNATE_FUNCTIONS(34, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO34 */ + ALTERNATE_FUNCTIONS(35, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO35 */ + ALTERNATE_FUNCTIONS(36, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO36 */ + ALTERNATE_FUNCTIONS(37, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO37 */ + ALTERNATE_FUNCTIONS(38, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO38 */ + ALTERNATE_FUNCTIONS(39, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO39 */ + ALTERNATE_FUNCTIONS(40, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO40 */ + /* GPIOSEL6 - bit 0 reserved */ + ALTERNATE_FUNCTIONS(41, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO41 */ + ALTERNATE_FUNCTIONS(42, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO42, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(43, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO43, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(44, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO44, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(45, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO45, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(46, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO46, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(47, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO47, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(48, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO48, altA controlled by bit 7 */ + /* GPIOSEL7 - bit 0-1 reserved */ + ALTERNATE_FUNCTIONS(49, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO49 */ + ALTERNATE_FUNCTIONS(50, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO50 */ + ALTERNATE_FUNCTIONS(51, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO51, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(52, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO52, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(53, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO53, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(54, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO54, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(55, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO55, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(56, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO56, altA controlled by bit 7 */ +}; + +static struct pullud ab8540_pullud = { + .first_pin = 51, /* GPIO1_VBAT */ + .last_pin = 54, /* GPIO4_VBAT */ +}; + +/* + * For AB8540 Only some GPIOs are interrupt capable: + * GPIO43 to GPIO44 + * GPIO51 to GPIO54 + */ +struct abx500_gpio_irq_cluster ab8540_gpio_irq_cluster[] = { + GPIO_IRQ_CLUSTER(43, 43, AB8540_INT_GPIO43F), + GPIO_IRQ_CLUSTER(44, 44, AB8540_INT_GPIO44F), + GPIO_IRQ_CLUSTER(51, 54, AB9540_INT_GPIO51R), +}; + +static struct abx500_pinctrl_soc_data ab8540_soc = { + .gpio_ranges = ab8540_pinranges, + .gpio_num_ranges = ARRAY_SIZE(ab8540_pinranges), + .pins = ab8540_pins, + .npins = ARRAY_SIZE(ab8540_pins), + .functions = ab8540_functions, + .nfunctions = ARRAY_SIZE(ab8540_functions), + .groups = ab8540_groups, + .ngroups = ARRAY_SIZE(ab8540_groups), + .alternate_functions = ab8540_alternate_functions, + .pullud = &ab8540_pullud, + .gpio_irq_cluster = ab8540_gpio_irq_cluster, + .ngpio_irq_cluster = ARRAY_SIZE(ab8540_gpio_irq_cluster), + .irq_gpio_rising_offset = AB8540_INT_GPIO43R, + .irq_gpio_falling_offset = AB8540_INT_GPIO43F, + .irq_gpio_factor = 2, +}; + +void +abx500_pinctrl_ab8540_init(struct abx500_pinctrl_soc_data **soc) +{ + *soc = &ab8540_soc; +} diff --git a/drivers/pinctrl/pinctrl-ab9540.c b/drivers/pinctrl/pinctrl-ab9540.c new file mode 100644 index 0000000..7610bd0 --- /dev/null +++ b/drivers/pinctrl/pinctrl-ab9540.c @@ -0,0 +1,485 @@ +/* + * Copyright (C) ST-Ericsson SA 2012 + * + * Author: Patrice Chotard <patrice.chotard@stericsson.com> for ST-Ericsson. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/mfd/abx500/ab8500.h> +#include "pinctrl-abx500.h" + +/* All the pins that can be used for GPIO and some other functions */ +#define ABX500_GPIO(offset) (offset) + +#define AB9540_PIN_R4 ABX500_GPIO(1) +#define AB9540_PIN_V3 ABX500_GPIO(2) +#define AB9540_PIN_T4 ABX500_GPIO(3) +#define AB9540_PIN_T5 ABX500_GPIO(4) +/* hole */ +#define AB9540_PIN_B18 ABX500_GPIO(10) +#define AB9540_PIN_C18 ABX500_GPIO(11) +/* hole */ +#define AB9540_PIN_D18 ABX500_GPIO(13) +#define AB9540_PIN_B19 ABX500_GPIO(14) +#define AB9540_PIN_C19 ABX500_GPIO(15) +#define AB9540_PIN_D19 ABX500_GPIO(16) +#define AB9540_PIN_R3 ABX500_GPIO(17) +#define AB9540_PIN_T2 ABX500_GPIO(18) +#define AB9540_PIN_U2 ABX500_GPIO(19) +#define AB9540_PIN_V2 ABX500_GPIO(20) +#define AB9540_PIN_N17 ABX500_GPIO(21) +#define AB9540_PIN_N16 ABX500_GPIO(22) +#define AB9540_PIN_M19 ABX500_GPIO(23) +#define AB9540_PIN_T3 ABX500_GPIO(24) +#define AB9540_PIN_W2 ABX500_GPIO(25) +/* hole */ +#define AB9540_PIN_H4 ABX500_GPIO(27) +#define AB9540_PIN_F1 ABX500_GPIO(28) +#define AB9540_PIN_F4 ABX500_GPIO(29) +#define AB9540_PIN_F2 ABX500_GPIO(30) +#define AB9540_PIN_E4 ABX500_GPIO(31) +#define AB9540_PIN_F3 ABX500_GPIO(32) +/* hole */ +#define AB9540_PIN_J13 ABX500_GPIO(34) +/* hole */ +#define AB9540_PIN_L17 ABX500_GPIO(40) +#define AB9540_PIN_L16 ABX500_GPIO(41) +#define AB9540_PIN_W3 ABX500_GPIO(42) +#define AB9540_PIN_N4 ABX500_GPIO(50) +#define AB9540_PIN_G12 ABX500_GPIO(51) +#define AB9540_PIN_E17 ABX500_GPIO(52) +#define AB9540_PIN_D11 ABX500_GPIO(53) +#define AB9540_PIN_M18 ABX500_GPIO(54) + +/* indicates the highest GPIO number */ +#define AB9540_GPIO_MAX_NUMBER 54 + +/* + * The names of the pins are denoted by GPIO number and ball name, even + * though they can be used for other things than GPIO, this is the first + * column in the table of the data sheet and often used on schematics and + * such. + */ +static const struct pinctrl_pin_desc ab9540_pins[] = { + PINCTRL_PIN(AB9540_PIN_R4, "GPIO1_R4"), + PINCTRL_PIN(AB9540_PIN_V3, "GPIO2_V3"), + PINCTRL_PIN(AB9540_PIN_T4, "GPIO3_T4"), + PINCTRL_PIN(AB9540_PIN_T5, "GPIO4_T5"), + /* hole */ + PINCTRL_PIN(AB9540_PIN_B18, "GPIO10_B18"), + PINCTRL_PIN(AB9540_PIN_C18, "GPIO11_C18"), + /* hole */ + PINCTRL_PIN(AB9540_PIN_D18, "GPIO13_D18"), + PINCTRL_PIN(AB9540_PIN_B19, "GPIO14_B19"), + PINCTRL_PIN(AB9540_PIN_C19, "GPIO15_C19"), + PINCTRL_PIN(AB9540_PIN_D19, "GPIO16_D19"), + PINCTRL_PIN(AB9540_PIN_R3, "GPIO17_R3"), + PINCTRL_PIN(AB9540_PIN_T2, "GPIO18_T2"), + PINCTRL_PIN(AB9540_PIN_U2, "GPIO19_U2"), + PINCTRL_PIN(AB9540_PIN_V2, "GPIO20_V2"), + PINCTRL_PIN(AB9540_PIN_N17, "GPIO21_N17"), + PINCTRL_PIN(AB9540_PIN_N16, "GPIO22_N16"), + PINCTRL_PIN(AB9540_PIN_M19, "GPIO23_M19"), + PINCTRL_PIN(AB9540_PIN_T3, "GPIO24_T3"), + PINCTRL_PIN(AB9540_PIN_W2, "GPIO25_W2"), + /* hole */ + PINCTRL_PIN(AB9540_PIN_H4, "GPIO27_H4"), + PINCTRL_PIN(AB9540_PIN_F1, "GPIO28_F1"), + PINCTRL_PIN(AB9540_PIN_F4, "GPIO29_F4"), + PINCTRL_PIN(AB9540_PIN_F2, "GPIO30_F2"), + PINCTRL_PIN(AB9540_PIN_E4, "GPIO31_E4"), + PINCTRL_PIN(AB9540_PIN_F3, "GPIO32_F3"), + /* hole */ + PINCTRL_PIN(AB9540_PIN_J13, "GPIO34_J13"), + /* hole */ + PINCTRL_PIN(AB9540_PIN_L17, "GPIO40_L17"), + PINCTRL_PIN(AB9540_PIN_L16, "GPIO41_L16"), + PINCTRL_PIN(AB9540_PIN_W3, "GPIO42_W3"), + PINCTRL_PIN(AB9540_PIN_N4, "GPIO50_N4"), + PINCTRL_PIN(AB9540_PIN_G12, "GPIO51_G12"), + PINCTRL_PIN(AB9540_PIN_E17, "GPIO52_E17"), + PINCTRL_PIN(AB9540_PIN_D11, "GPIO53_D11"), + PINCTRL_PIN(AB9540_PIN_M18, "GPIO60_M18"), +}; + +/* + * Maps local GPIO offsets to local pin numbers + */ +static const struct abx500_pinrange ab9540_pinranges[] = { + ABX500_PINRANGE(1, 4, ABX500_ALT_A), + ABX500_PINRANGE(10, 2, ABX500_DEFAULT), + ABX500_PINRANGE(13, 1, ABX500_DEFAULT), + ABX500_PINRANGE(14, 12, ABX500_ALT_A), + ABX500_PINRANGE(27, 6, ABX500_ALT_A), + ABX500_PINRANGE(34, 1, ABX500_ALT_A), + ABX500_PINRANGE(40, 3, ABX500_ALT_A), + ABX500_PINRANGE(50, 1, ABX500_DEFAULT), + ABX500_PINRANGE(51, 3, ABX500_ALT_A), + ABX500_PINRANGE(54, 1, ABX500_DEFAULT), +}; + +/* + * Read the pin group names like this: + * sysclkreq2_d_1 = first groups of pins for sysclkreq2 on default function + * + * The groups are arranged as sets per altfunction column, so we can + * mux in one group at a time by selecting the same altfunction for them + * all. When functions require pins on different altfunctions, you need + * to combine several groups. + */ + +/* default column */ +static const unsigned sysclkreq2_d_1_pins[] = { AB9540_PIN_R4 }; +static const unsigned sysclkreq3_d_1_pins[] = { AB9540_PIN_V3 }; +static const unsigned sysclkreq4_d_1_pins[] = { AB9540_PIN_T4 }; +static const unsigned sysclkreq6_d_1_pins[] = { AB9540_PIN_T5 }; +static const unsigned gpio10_d_1_pins[] = { AB9540_PIN_B18 }; +static const unsigned gpio11_d_1_pins[] = { AB9540_PIN_C18 }; +static const unsigned gpio13_d_1_pins[] = { AB9540_PIN_D18 }; +static const unsigned pwmout1_d_1_pins[] = { AB9540_PIN_B19 }; +static const unsigned pwmout2_d_1_pins[] = { AB9540_PIN_C19 }; +static const unsigned pwmout3_d_1_pins[] = { AB9540_PIN_D19 }; +/* audio data interface 1*/ +static const unsigned adi1_d_1_pins[] = { AB9540_PIN_R3, AB9540_PIN_T2, + AB9540_PIN_U2, AB9540_PIN_V2 }; +/* USBUICC */ +static const unsigned usbuicc_d_1_pins[] = { AB9540_PIN_N17, AB9540_PIN_N16, + AB9540_PIN_M19 }; +static const unsigned sysclkreq7_d_1_pins[] = { AB9540_PIN_T3 }; +static const unsigned sysclkreq8_d_1_pins[] = { AB9540_PIN_W2 }; +/* Digital microphone 1 and 2 */ +static const unsigned dmic12_d_1_pins[] = { AB9540_PIN_H4, AB9540_PIN_F1 }; +/* Digital microphone 3 and 4 */ +static const unsigned dmic34_d_1_pins[] = { AB9540_PIN_F4, AB9540_PIN_F2 }; +/* Digital microphone 5 and 6 */ +static const unsigned dmic56_d_1_pins[] = { AB9540_PIN_E4, AB9540_PIN_F3 }; +static const unsigned extcpena_d_1_pins[] = { AB9540_PIN_J13 }; +/* modem SDA/SCL */ +static const unsigned modsclsda_d_1_pins[] = { AB9540_PIN_L17, AB9540_PIN_L16 }; +static const unsigned sysclkreq5_d_1_pins[] = { AB9540_PIN_W3 }; +static const unsigned gpio50_d_1_pins[] = { AB9540_PIN_N4 }; +static const unsigned batremn_d_1_pins[] = { AB9540_PIN_G12 }; +static const unsigned resethw_d_1_pins[] = { AB9540_PIN_E17 }; +static const unsigned service_d_1_pins[] = { AB9540_PIN_D11 }; +static const unsigned gpio60_d_1_pins[] = { AB9540_PIN_M18 }; + +/* Altfunction A column */ +static const unsigned gpio1_a_1_pins[] = { AB9540_PIN_R4 }; +static const unsigned gpio2_a_1_pins[] = { AB9540_PIN_V3 }; +static const unsigned gpio3_a_1_pins[] = { AB9540_PIN_T4 }; +static const unsigned gpio4_a_1_pins[] = { AB9540_PIN_T5 }; +static const unsigned hiqclkena_a_1_pins[] = { AB9540_PIN_B18 }; +static const unsigned pdmclk_a_1_pins[] = { AB9540_PIN_C18 }; +static const unsigned uartdata_a_1_pins[] = { AB9540_PIN_D18, AB9540_PIN_N4 }; +static const unsigned gpio14_a_1_pins[] = { AB9540_PIN_B19 }; +static const unsigned gpio15_a_1_pins[] = { AB9540_PIN_C19 }; +static const unsigned gpio16_a_1_pins[] = { AB9540_PIN_D19 }; +static const unsigned gpio17_a_1_pins[] = { AB9540_PIN_R3 }; +static const unsigned gpio18_a_1_pins[] = { AB9540_PIN_T2 }; +static const unsigned gpio19_a_1_pins[] = { AB9540_PIN_U2 }; +static const unsigned gpio20_a_1_pins[] = { AB9540_PIN_V2 }; +static const unsigned gpio21_a_1_pins[] = { AB9540_PIN_N17 }; +static const unsigned gpio22_a_1_pins[] = { AB9540_PIN_N16 }; +static const unsigned gpio23_a_1_pins[] = { AB9540_PIN_M19 }; +static const unsigned gpio24_a_1_pins[] = { AB9540_PIN_T3 }; +static const unsigned gpio25_a_1_pins[] = { AB9540_PIN_W2 }; +static const unsigned gpio27_a_1_pins[] = { AB9540_PIN_H4 }; +static const unsigned gpio28_a_1_pins[] = { AB9540_PIN_F1 }; +static const unsigned gpio29_a_1_pins[] = { AB9540_PIN_F4 }; +static const unsigned gpio30_a_1_pins[] = { AB9540_PIN_F2 }; +static const unsigned gpio31_a_1_pins[] = { AB9540_PIN_E4 }; +static const unsigned gpio32_a_1_pins[] = { AB9540_PIN_F3 }; +static const unsigned gpio34_a_1_pins[] = { AB9540_PIN_J13 }; +static const unsigned gpio40_a_1_pins[] = { AB9540_PIN_L17 }; +static const unsigned gpio41_a_1_pins[] = { AB9540_PIN_L16 }; +static const unsigned gpio42_a_1_pins[] = { AB9540_PIN_W3 }; +static const unsigned gpio51_a_1_pins[] = { AB9540_PIN_G12 }; +static const unsigned gpio52_a_1_pins[] = { AB9540_PIN_E17 }; +static const unsigned gpio53_a_1_pins[] = { AB9540_PIN_D11 }; +static const unsigned usbuiccpd_a_1_pins[] = { AB9540_PIN_M18 }; + +/* Altfunction B colum */ +static const unsigned pdmdata_b_1_pins[] = { AB9540_PIN_B18 }; +static const unsigned pwmextvibra1_b_1_pins[] = { AB9540_PIN_D18 }; +static const unsigned pwmextvibra2_b_1_pins[] = { AB9540_PIN_N4 }; + +/* Altfunction C column */ +static const unsigned usbvdat_c_1_pins[] = { AB9540_PIN_D18 }; + +#define AB9540_PIN_GROUP(a, b) { .name = #a, .pins = a##_pins, \ + .npins = ARRAY_SIZE(a##_pins), .altsetting = b } + +static const struct abx500_pingroup ab9540_groups[] = { + /* default column */ + AB9540_PIN_GROUP(sysclkreq2_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(sysclkreq3_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(sysclkreq4_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(sysclkreq6_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(gpio10_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(gpio11_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(gpio13_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(pwmout1_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(pwmout2_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(pwmout3_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(adi1_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(usbuicc_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(sysclkreq7_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(sysclkreq8_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(dmic12_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(dmic34_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(dmic56_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(extcpena_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(modsclsda_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(sysclkreq5_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(gpio50_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(batremn_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(resethw_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(service_d_1, ABX500_DEFAULT), + AB9540_PIN_GROUP(gpio60_d_1, ABX500_DEFAULT), + + /* Altfunction A column */ + AB9540_PIN_GROUP(gpio1_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio2_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio3_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio4_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(hiqclkena_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(pdmclk_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(uartdata_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio14_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio15_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio16_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio17_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio18_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio19_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio20_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio21_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio22_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio23_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio24_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio25_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio27_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio28_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio29_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio30_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio31_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio32_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio34_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio40_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio41_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio42_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio51_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio52_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(gpio53_a_1, ABX500_ALT_A), + AB9540_PIN_GROUP(usbuiccpd_a_1, ABX500_ALT_A), + + /* Altfunction B column */ + AB9540_PIN_GROUP(pdmdata_b_1, ABX500_ALT_B), + AB9540_PIN_GROUP(pwmextvibra1_b_1, ABX500_ALT_B), + AB9540_PIN_GROUP(pwmextvibra2_b_1, ABX500_ALT_B), + + /* Altfunction C column */ + AB9540_PIN_GROUP(usbvdat_c_1, ABX500_ALT_C), +}; + +/* We use this macro to define the groups applicable to a function */ +#define AB9540_FUNC_GROUPS(a, b...) \ +static const char * const a##_groups[] = { b }; + +AB9540_FUNC_GROUPS(sysclkreq, "sysclkreq2_d_1", "sysclkreq3_d_1", + "sysclkreq4_d_1", "sysclkreq5_d_1", "sysclkreq6_d_1", + "sysclkreq7_d_1", "sysclkreq8_d_1"); +AB9540_FUNC_GROUPS(gpio, "gpio1_a_1", "gpio2_a_1", "gpio3_a_1", "gpio4_a_1", + "gpio10_d_1", "gpio11_d_1", "gpio13_d_1", "gpio14_a_1", + "gpio15_a_1", "gpio16_a_1", "gpio17_a_1", "gpio18_a_1", + "gpio19_a_1", "gpio20_a_1", "gpio21_a_1", "gpio22_a_1", + "gpio23_a_1", "gpio24_a_1", "gpio25_a_1", "gpio27_a_1", + "gpio28_a_1", "gpio29_a_1", "gpio30_a_1", "gpio31_a_1", + "gpio32_a_1", "gpio34_a_1", "gpio40_a_1", "gpio41_a_1", + "gpio42_a_1", "gpio50_d_1", "gpio51_a_1", "gpio52_a_1", + "gpio53_a_1", "gpio60_d_1"); +AB9540_FUNC_GROUPS(pwmout, "pwmout1_d_1", "pwmout2_d_1", "pwmout3_d_1"); +AB9540_FUNC_GROUPS(adi1, "adi1_d_1"); +AB9540_FUNC_GROUPS(usbuicc, "usbuicc_d_1", "usbuiccpd_a_1"); +AB9540_FUNC_GROUPS(dmic, "dmic12_d_1", "dmic34_d_1", "dmic56_d_1"); +AB9540_FUNC_GROUPS(extcpena, "extcpena_d_1"); +AB9540_FUNC_GROUPS(modsclsda, "modsclsda_d_1"); +AB9540_FUNC_GROUPS(batremn, "batremn_d_1"); +AB9540_FUNC_GROUPS(resethw, "resethw_d_1"); +AB9540_FUNC_GROUPS(service, "service_d_1"); +AB9540_FUNC_GROUPS(hiqclkena, "hiqclkena_a_1"); +AB9540_FUNC_GROUPS(pdm, "pdmdata_b_1", "pdmclk_a_1"); +AB9540_FUNC_GROUPS(uartdata, "uartdata_a_1"); +AB9540_FUNC_GROUPS(pwmextvibra, "pwmextvibra1_b_1", "pwmextvibra2_b_1"); +AB9540_FUNC_GROUPS(usbvdat, "usbvdat_c_1"); + +#define FUNCTION(fname) \ + { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +static const struct abx500_function ab9540_functions[] = { + FUNCTION(sysclkreq), + FUNCTION(gpio), + FUNCTION(pwmout), + FUNCTION(adi1), + FUNCTION(usbuicc), + FUNCTION(dmic), + FUNCTION(extcpena), + FUNCTION(modsclsda), + FUNCTION(batremn), + FUNCTION(resethw), + FUNCTION(service), + FUNCTION(hiqclkena), + FUNCTION(pdm), + FUNCTION(uartdata), + FUNCTION(pwmextvibra), + FUNCTION(usbvdat), +}; + +/* + * this table translates what's is in the AB9540 specification regarding the + * balls alternate functions (as for DB, default, ALT_A, ALT_B and ALT_C). + * ALTERNATE_FUNCTIONS(GPIO_NUMBER, GPIOSEL bit, ALTERNATFUNC bit1, + * ALTERNATEFUNC bit2, ALTA val, ALTB val, ALTC val), + * + * example : + * + * ALTERNATE_FUNCTIONS(13, 4, 3, 4, 1, 0, 2), + * means that pin AB9540_PIN_D18 (pin 13) supports 4 mux (default/ALT_A, + * ALT_B and ALT_C), so GPIOSEL and ALTERNATFUNC registers are used to + * select the mux. ALTA, ALTB and ALTC val indicates values to write in + * ALTERNATFUNC register. We need to specifies these values as SOC + * designers didn't apply the same logic on how to select mux in the + * ABx500 family. + * + * As this pins supports at least ALT_B mux, default mux is + * selected by writing 1 in GPIOSEL bit : + * + * | GPIOSEL bit=4 | alternatfunc bit2=4 | alternatfunc bit1=3 + * default | 1 | 0 | 0 + * alt_A | 0 | 0 | 1 + * alt_B | 0 | 0 | 0 + * alt_C | 0 | 1 | 0 + * + * ALTERNATE_FUNCTIONS(1, 0, UNUSED, UNUSED), + * means that pin AB9540_PIN_R4 (pin 1) supports 2 mux, so only GPIOSEL + * register is used to select the mux. As this pins doesn't support at + * least ALT_B mux, default mux is by writing 0 in GPIOSEL bit : + * + * | GPIOSEL bit=0 | alternatfunc bit2= | alternatfunc bit1= + * default | 0 | 0 | 0 + * alt_A | 1 | 0 | 0 + */ + +struct alternate_functions ab9540alternate_functions[AB9540_GPIO_MAX_NUMBER + 1] = { + /* GPIOSEL1 - bits 4-7 are reserved */ + ALTERNATE_FUNCTIONS(0, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO0 */ + ALTERNATE_FUNCTIONS(1, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO1, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(2, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO2, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(3, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO3, altA controlled by bit 2*/ + ALTERNATE_FUNCTIONS(4, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO4, altA controlled by bit 3*/ + ALTERNATE_FUNCTIONS(5, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO5 */ + ALTERNATE_FUNCTIONS(6, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO6 */ + ALTERNATE_FUNCTIONS(7, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO7 */ + ALTERNATE_FUNCTIONS(8, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO8 */ + /* GPIOSEL2 - bits 0 and 3 are reserved */ + ALTERNATE_FUNCTIONS(9, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO9 */ + ALTERNATE_FUNCTIONS(10, 1, 0, UNUSED, 1, 0, 0), /* GPIO10, altA and altB controlled by bit 0 */ + ALTERNATE_FUNCTIONS(11, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO11, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(12, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO12 */ + ALTERNATE_FUNCTIONS(13, 4, 3, 4, 1, 0, 2), /* GPIO13, altA altB and altC controlled by bit 3 and 4 */ + ALTERNATE_FUNCTIONS(14, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO14, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(15, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO15, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(16, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO16, altA controlled by bit 7 */ + /* GPIOSEL3 - bit 1-3 reserved + * pins 17 to 20 are special case, only bit 0 is used to select + * alternate function for these 4 pins. + * bits 1 to 3 are reserved + */ + ALTERNATE_FUNCTIONS(17, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO17, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(18, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO18, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(19, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO19, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(20, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO20, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(21, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO21, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(22, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO22, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(23, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO23, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(24, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO24, altA controlled by bit 7 */ + /* GPIOSEL4 - bit 1 reserved */ + ALTERNATE_FUNCTIONS(25, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO25, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(26, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO26 */ + ALTERNATE_FUNCTIONS(27, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO27, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(28, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO28, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(29, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO29, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(30, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO30, altA controlled by bit 5 */ + ALTERNATE_FUNCTIONS(31, 6, UNUSED, UNUSED, 0, 0, 0), /* GPIO31, altA controlled by bit 6 */ + ALTERNATE_FUNCTIONS(32, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO32, altA controlled by bit 7 */ + /* GPIOSEL5 - bit 0, 2-6 are reserved */ + ALTERNATE_FUNCTIONS(33, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO33 */ + ALTERNATE_FUNCTIONS(34, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO34, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(35, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO35 */ + ALTERNATE_FUNCTIONS(36, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO36 */ + ALTERNATE_FUNCTIONS(37, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO37 */ + ALTERNATE_FUNCTIONS(38, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO38 */ + ALTERNATE_FUNCTIONS(39, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO39 */ + ALTERNATE_FUNCTIONS(40, 7, UNUSED, UNUSED, 0, 0, 0), /* GPIO40, altA controlled by bit 7 */ + /* GPIOSEL6 - bit 2-7 are reserved */ + ALTERNATE_FUNCTIONS(41, 0, UNUSED, UNUSED, 0, 0, 0), /* GPIO41, altA controlled by bit 0 */ + ALTERNATE_FUNCTIONS(42, 1, UNUSED, UNUSED, 0, 0, 0), /* GPIO42, altA controlled by bit 1 */ + ALTERNATE_FUNCTIONS(43, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO43 */ + ALTERNATE_FUNCTIONS(44, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO44 */ + ALTERNATE_FUNCTIONS(45, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO45 */ + ALTERNATE_FUNCTIONS(46, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO46 */ + ALTERNATE_FUNCTIONS(47, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO47 */ + ALTERNATE_FUNCTIONS(48, UNUSED, UNUSED, UNUSED, 0, 0, 0), /* no GPIO48 */ + /* + * GPIOSEL7 - bit 0 and 6-7 are reserved + * special case with GPIO60, wich is located at offset 5 of gpiosel7 + * don't know why it has been called GPIO60 in AB9540 datasheet, + * GPIO54 would be logical..., so at SOC point of view we consider + * GPIO60 = GPIO54 + */ + ALTERNATE_FUNCTIONS(49, 0, UNUSED, UNUSED, 0, 0, 0), /* no GPIO49 */ + ALTERNATE_FUNCTIONS(50, 1, 2, UNUSED, 1, 0, 0), /* GPIO50, altA and altB controlled by bit 1 */ + ALTERNATE_FUNCTIONS(51, 2, UNUSED, UNUSED, 0, 0, 0), /* GPIO51, altA controlled by bit 2 */ + ALTERNATE_FUNCTIONS(52, 3, UNUSED, UNUSED, 0, 0, 0), /* GPIO52, altA controlled by bit 3 */ + ALTERNATE_FUNCTIONS(53, 4, UNUSED, UNUSED, 0, 0, 0), /* GPIO53, altA controlled by bit 4 */ + ALTERNATE_FUNCTIONS(54, 5, UNUSED, UNUSED, 0, 0, 0), /* GPIO54 = GPIO60, altA controlled by bit 5 */ +}; + +struct abx500_gpio_irq_cluster ab9540_gpio_irq_cluster[] = { + GPIO_IRQ_CLUSTER(10, 13, AB8500_INT_GPIO10R), + GPIO_IRQ_CLUSTER(24, 25, AB8500_INT_GPIO24R), + GPIO_IRQ_CLUSTER(40, 41, AB8500_INT_GPIO40R), + GPIO_IRQ_CLUSTER(50, 54, AB9540_INT_GPIO50R), +}; + +static struct abx500_pinctrl_soc_data ab9540_soc = { + .gpio_ranges = ab9540_pinranges, + .gpio_num_ranges = ARRAY_SIZE(ab9540_pinranges), + .pins = ab9540_pins, + .npins = ARRAY_SIZE(ab9540_pins), + .functions = ab9540_functions, + .nfunctions = ARRAY_SIZE(ab9540_functions), + .groups = ab9540_groups, + .ngroups = ARRAY_SIZE(ab9540_groups), + .alternate_functions = ab9540alternate_functions, + .gpio_irq_cluster = ab9540_gpio_irq_cluster, + .ngpio_irq_cluster = ARRAY_SIZE(ab9540_gpio_irq_cluster), + .irq_gpio_rising_offset = AB8500_INT_GPIO6R, + .irq_gpio_falling_offset = AB8500_INT_GPIO6F, + .irq_gpio_factor = 1, +}; + +void +abx500_pinctrl_ab9540_init(struct abx500_pinctrl_soc_data **soc) +{ + *soc = &ab9540_soc; +} diff --git a/drivers/pinctrl/pinctrl-abx500.c b/drivers/pinctrl/pinctrl-abx500.c new file mode 100644 index 0000000..caecdd3 --- /dev/null +++ b/drivers/pinctrl/pinctrl-abx500.c @@ -0,0 +1,1012 @@ +/* + * Copyright (C) ST-Ericsson SA 2013 + * + * Author: Patrice Chotard <patrice.chotard@st.com> + * License terms: GNU General Public License (GPL) version 2 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/err.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/interrupt.h> +#include <linux/bitops.h> +#include <linux/mfd/abx500.h> +#include <linux/mfd/abx500/ab8500.h> +#include <linux/mfd/abx500/ab8500-gpio.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/pinctrl/consumer.h> +#include <linux/pinctrl/pinmux.h> +#include <linux/pinctrl/pinconf.h> +#include <linux/pinctrl/pinconf-generic.h> + +#include "pinctrl-abx500.h" + +/* + * The AB9540 and AB8540 GPIO support are extended versions + * of the AB8500 GPIO support. + * The AB9540 supports an additional (7th) register so that + * more GPIO may be configured and used. + * The AB8540 supports 4 new gpios (GPIOx_VBAT) that have + * internal pull-up and pull-down capabilities. + */ + +/* + * GPIO registers offset + * Bank: 0x10 + */ +#define AB8500_GPIO_SEL1_REG 0x00 +#define AB8500_GPIO_SEL2_REG 0x01 +#define AB8500_GPIO_SEL3_REG 0x02 +#define AB8500_GPIO_SEL4_REG 0x03 +#define AB8500_GPIO_SEL5_REG 0x04 +#define AB8500_GPIO_SEL6_REG 0x05 +#define AB9540_GPIO_SEL7_REG 0x06 + +#define AB8500_GPIO_DIR1_REG 0x10 +#define AB8500_GPIO_DIR2_REG 0x11 +#define AB8500_GPIO_DIR3_REG 0x12 +#define AB8500_GPIO_DIR4_REG 0x13 +#define AB8500_GPIO_DIR5_REG 0x14 +#define AB8500_GPIO_DIR6_REG 0x15 +#define AB9540_GPIO_DIR7_REG 0x16 + +#define AB8500_GPIO_OUT1_REG 0x20 +#define AB8500_GPIO_OUT2_REG 0x21 +#define AB8500_GPIO_OUT3_REG 0x22 +#define AB8500_GPIO_OUT4_REG 0x23 +#define AB8500_GPIO_OUT5_REG 0x24 +#define AB8500_GPIO_OUT6_REG 0x25 +#define AB9540_GPIO_OUT7_REG 0x26 + +#define AB8500_GPIO_PUD1_REG 0x30 +#define AB8500_GPIO_PUD2_REG 0x31 +#define AB8500_GPIO_PUD3_REG 0x32 +#define AB8500_GPIO_PUD4_REG 0x33 +#define AB8500_GPIO_PUD5_REG 0x34 +#define AB8500_GPIO_PUD6_REG 0x35 +#define AB9540_GPIO_PUD7_REG 0x36 + +#define AB8500_GPIO_IN1_REG 0x40 +#define AB8500_GPIO_IN2_REG 0x41 +#define AB8500_GPIO_IN3_REG 0x42 +#define AB8500_GPIO_IN4_REG 0x43 +#define AB8500_GPIO_IN5_REG 0x44 +#define AB8500_GPIO_IN6_REG 0x45 +#define AB9540_GPIO_IN7_REG 0x46 +#define AB8540_GPIO_VINSEL_REG 0x47 +#define AB8540_GPIO_PULL_UPDOWN_REG 0x48 +#define AB8500_GPIO_ALTFUN_REG 0x50 +#define AB8540_GPIO_PULL_UPDOWN_MASK 0x03 +#define AB8540_GPIO_VINSEL_MASK 0x03 +#define AB8540_GPIOX_VBAT_START 51 +#define AB8540_GPIOX_VBAT_END 54 + +struct abx500_pinctrl { + struct device *dev; + struct pinctrl_dev *pctldev; + struct abx500_pinctrl_soc_data *soc; + struct gpio_chip chip; + struct ab8500 *parent; + struct mutex lock; + struct abx500_gpio_irq_cluster *irq_cluster; + int irq_cluster_size; +}; + +/** + * to_abx500_pinctrl() - get the pointer to abx500_pinctrl + * @chip: Member of the structure abx500_pinctrl + */ +static inline struct abx500_pinctrl *to_abx500_pinctrl(struct gpio_chip *chip) +{ + return container_of(chip, struct abx500_pinctrl, chip); +} + +static int abx500_gpio_get_bit(struct gpio_chip *chip, u8 reg, + unsigned offset, bool *bit) +{ + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + u8 pos = offset % 8; + u8 val; + int ret; + + reg += offset / 8; + ret = abx500_get_register_interruptible(pct->dev, + AB8500_MISC, reg, &val); + + *bit = !!(val & BIT(pos)); + + if (ret < 0) + dev_err(pct->dev, + "%s read reg =%x, offset=%x failed\n", + __func__, reg, offset); + + return ret; +} + +static int abx500_gpio_set_bits(struct gpio_chip *chip, u8 reg, + unsigned offset, int val) +{ + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + u8 pos = offset % 8; + int ret; + + reg += offset / 8; + ret = abx500_mask_and_set_register_interruptible(pct->dev, + AB8500_MISC, reg, BIT(pos), val << pos); + if (ret < 0) + dev_err(pct->dev, "%s write failed\n", __func__); + + return ret; +} + +/** + * abx500_gpio_get() - Get the particular GPIO value + * @chip: Gpio device + * @offset: GPIO number to read + */ +static int abx500_gpio_get(struct gpio_chip *chip, unsigned offset) +{ + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + bool bit; + int ret; + + ret = abx500_gpio_get_bit(chip, AB8500_GPIO_IN1_REG, + offset, &bit); + if (ret < 0) { + dev_err(pct->dev, "%s failed\n", __func__); + return ret; + } + + return bit; +} + +static void abx500_gpio_set(struct gpio_chip *chip, unsigned offset, int val) +{ + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + int ret; + + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_OUT1_REG, offset, val); + if (ret < 0) + dev_err(pct->dev, "%s write failed\n", __func__); +} + +static int abx500_config_pull_updown(struct abx500_pinctrl *pct, + int offset, enum abx500_gpio_pull_updown val) +{ + u8 pos; + int ret; + struct pullud *pullud; + + if (!pct->soc->pullud) { + dev_err(pct->dev, "%s AB chip doesn't support pull up/down feature", + __func__); + ret = -EPERM; + goto out; + } + + pullud = pct->soc->pullud; + + if ((offset < pullud->first_pin) + || (offset > pullud->last_pin)) { + ret = -EINVAL; + goto out; + } + + pos = offset << 1; + + ret = abx500_mask_and_set_register_interruptible(pct->dev, + AB8500_MISC, AB8540_GPIO_PULL_UPDOWN_REG, + AB8540_GPIO_PULL_UPDOWN_MASK << pos, val << pos); + +out: + if (ret < 0) + dev_err(pct->dev, "%s failed (%d)\n", __func__, ret); + + return ret; +} + +static int abx500_gpio_direction_output(struct gpio_chip *chip, + unsigned offset, + int val) +{ + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + struct pullud *pullud = pct->soc->pullud; + unsigned gpio; + int ret; + + /* set direction as output */ + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_DIR1_REG, offset, 1); + if (ret < 0) + return ret; + + /* disable pull down */ + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_PUD1_REG, offset, 1); + if (ret < 0) + return ret; + + /* if supported, disable both pull down and pull up */ + gpio = offset + 1; + if (pullud && gpio >= pullud->first_pin && gpio <= pullud->last_pin) { + ret = abx500_config_pull_updown(pct, + gpio, + ABX500_GPIO_PULL_NONE); + if (ret < 0) + return ret; + } + + /* set the output as 1 or 0 */ + return abx500_gpio_set_bits(chip, AB8500_GPIO_OUT1_REG, offset, val); +} + +static int abx500_gpio_direction_input(struct gpio_chip *chip, unsigned offset) +{ + /* set the register as input */ + return abx500_gpio_set_bits(chip, AB8500_GPIO_DIR1_REG, offset, 0); +} + +static int abx500_gpio_to_irq(struct gpio_chip *chip, unsigned offset) +{ + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + /* The AB8500 GPIO numbers are off by one */ + int gpio = offset + 1; + int hwirq; + int i; + + for (i = 0; i < pct->irq_cluster_size; i++) { + struct abx500_gpio_irq_cluster *cluster = + &pct->irq_cluster[i]; + + if (gpio >= cluster->start && gpio <= cluster->end) { + /* + * The ABx500 GPIO's associated IRQs are clustered together + * throughout the interrupt numbers at irregular intervals. + * To solve this quandry, we have placed the read-in values + * into the cluster information table. + */ + hwirq = gpio - cluster->start + cluster->to_irq; + return irq_create_mapping(pct->parent->domain, hwirq); + } + } + + return -EINVAL; +} + +static int abx500_set_mode(struct pinctrl_dev *pctldev, struct gpio_chip *chip, + unsigned gpio, int alt_setting) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + struct alternate_functions af = pct->soc->alternate_functions[gpio]; + int ret; + int val; + unsigned offset; + + const char *modes[] = { + [ABX500_DEFAULT] = "default", + [ABX500_ALT_A] = "altA", + [ABX500_ALT_B] = "altB", + [ABX500_ALT_C] = "altC", + }; + + /* sanity check */ + if (((alt_setting == ABX500_ALT_A) && (af.gpiosel_bit == UNUSED)) || + ((alt_setting == ABX500_ALT_B) && (af.alt_bit1 == UNUSED)) || + ((alt_setting == ABX500_ALT_C) && (af.alt_bit2 == UNUSED))) { + dev_dbg(pct->dev, "pin %d doesn't support %s mode\n", gpio, + modes[alt_setting]); + return -EINVAL; + } + + /* on ABx5xx, there is no GPIO0, so adjust the offset */ + offset = gpio - 1; + + switch (alt_setting) { + case ABX500_DEFAULT: + /* + * for ABx5xx family, default mode is always selected by + * writing 0 to GPIOSELx register, except for pins which + * support at least ALT_B mode, default mode is selected + * by writing 1 to GPIOSELx register + */ + val = 0; + if (af.alt_bit1 != UNUSED) + val++; + + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_SEL1_REG, + offset, val); + break; + + case ABX500_ALT_A: + /* + * for ABx5xx family, alt_a mode is always selected by + * writing 1 to GPIOSELx register, except for pins which + * support at least ALT_B mode, alt_a mode is selected + * by writing 0 to GPIOSELx register and 0 in ALTFUNC + * register + */ + if (af.alt_bit1 != UNUSED) { + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_SEL1_REG, + offset, 0); + ret = abx500_gpio_set_bits(chip, + AB8500_GPIO_ALTFUN_REG, + af.alt_bit1, + !!(af.alta_val && BIT(0))); + if (af.alt_bit2 != UNUSED) + ret = abx500_gpio_set_bits(chip, + AB8500_GPIO_ALTFUN_REG, + af.alt_bit2, + !!(af.alta_val && BIT(1))); + } else + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_SEL1_REG, + offset, 1); + break; + + case ABX500_ALT_B: + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_SEL1_REG, + offset, 0); + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_ALTFUN_REG, + af.alt_bit1, !!(af.altb_val && BIT(0))); + if (af.alt_bit2 != UNUSED) + ret = abx500_gpio_set_bits(chip, + AB8500_GPIO_ALTFUN_REG, + af.alt_bit2, + !!(af.altb_val && BIT(1))); + break; + + case ABX500_ALT_C: + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_SEL1_REG, + offset, 0); + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_ALTFUN_REG, + af.alt_bit2, !!(af.altc_val && BIT(0))); + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_ALTFUN_REG, + af.alt_bit2, !!(af.altc_val && BIT(1))); + break; + + default: + dev_dbg(pct->dev, "unknow alt_setting %d\n", alt_setting); + + return -EINVAL; + } + + return ret; +} + +static u8 abx500_get_mode(struct pinctrl_dev *pctldev, struct gpio_chip *chip, + unsigned gpio) +{ + u8 mode; + bool bit_mode; + bool alt_bit1; + bool alt_bit2; + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + struct alternate_functions af = pct->soc->alternate_functions[gpio]; + /* on ABx5xx, there is no GPIO0, so adjust the offset */ + unsigned offset = gpio - 1; + + /* + * if gpiosel_bit is set to unused, + * it means no GPIO or special case + */ + if (af.gpiosel_bit == UNUSED) + return ABX500_DEFAULT; + + /* read GpioSelx register */ + abx500_gpio_get_bit(chip, AB8500_GPIO_SEL1_REG + (offset / 8), + af.gpiosel_bit, &bit_mode); + mode = bit_mode; + + /* sanity check */ + if ((af.alt_bit1 < UNUSED) || (af.alt_bit1 > 7) || + (af.alt_bit2 < UNUSED) || (af.alt_bit2 > 7)) { + dev_err(pct->dev, + "alt_bitX value not in correct range (-1 to 7)\n"); + return -EINVAL; + } + + /* if alt_bit2 is used, alt_bit1 must be used too */ + if ((af.alt_bit2 != UNUSED) && (af.alt_bit1 == UNUSED)) { + dev_err(pct->dev, + "if alt_bit2 is used, alt_bit1 can't be unused\n"); + return -EINVAL; + } + + /* check if pin use AlternateFunction register */ + if ((af.alt_bit1 == UNUSED) && (af.alt_bit1 == UNUSED)) + return mode; + /* + * if pin GPIOSEL bit is set and pin supports alternate function, + * it means DEFAULT mode + */ + if (mode) + return ABX500_DEFAULT; + + /* + * pin use the AlternatFunction register + * read alt_bit1 value + */ + abx500_gpio_get_bit(chip, AB8500_GPIO_ALTFUN_REG, + af.alt_bit1, &alt_bit1); + + if (af.alt_bit2 != UNUSED) + /* read alt_bit2 value */ + abx500_gpio_get_bit(chip, AB8500_GPIO_ALTFUN_REG, af.alt_bit2, + &alt_bit2); + else + alt_bit2 = 0; + + mode = (alt_bit2 << 1) + alt_bit1; + if (mode == af.alta_val) + return ABX500_ALT_A; + else if (mode == af.altb_val) + return ABX500_ALT_B; + else + return ABX500_ALT_C; +} + +#ifdef CONFIG_DEBUG_FS + +#include <linux/seq_file.h> + +static void abx500_gpio_dbg_show_one(struct seq_file *s, + struct pinctrl_dev *pctldev, + struct gpio_chip *chip, + unsigned offset, unsigned gpio) +{ + const char *label = gpiochip_is_requested(chip, offset - 1); + u8 gpio_offset = offset - 1; + int mode = -1; + bool is_out; + bool pull; + + const char *modes[] = { + [ABX500_DEFAULT] = "default", + [ABX500_ALT_A] = "altA", + [ABX500_ALT_B] = "altB", + [ABX500_ALT_C] = "altC", + }; + + abx500_gpio_get_bit(chip, AB8500_GPIO_DIR1_REG, gpio_offset, &is_out); + abx500_gpio_get_bit(chip, AB8500_GPIO_PUD1_REG, gpio_offset, &pull); + + if (pctldev) + mode = abx500_get_mode(pctldev, chip, offset); + + seq_printf(s, " gpio-%-3d (%-20.20s) %-3s %-9s %s", + gpio, label ?: "(none)", + is_out ? "out" : "in ", + is_out ? + (chip->get + ? (chip->get(chip, offset) ? "hi" : "lo") + : "? ") + : (pull ? "pull up" : "pull down"), + (mode < 0) ? "unknown" : modes[mode]); +} + +static void abx500_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) +{ + unsigned i; + unsigned gpio = chip->base; + struct abx500_pinctrl *pct = to_abx500_pinctrl(chip); + struct pinctrl_dev *pctldev = pct->pctldev; + + for (i = 0; i < chip->ngpio; i++, gpio++) { + /* On AB8500, there is no GPIO0, the first is the GPIO 1 */ + abx500_gpio_dbg_show_one(s, pctldev, chip, i + 1, gpio); + seq_printf(s, "\n"); + } +} + +#else +static inline void abx500_gpio_dbg_show_one(struct seq_file *s, + struct pinctrl_dev *pctldev, + struct gpio_chip *chip, + unsigned offset, unsigned gpio) +{ +} +#define abx500_gpio_dbg_show NULL +#endif + +int abx500_gpio_request(struct gpio_chip *chip, unsigned offset) +{ + int gpio = chip->base + offset; + + return pinctrl_request_gpio(gpio); +} + +void abx500_gpio_free(struct gpio_chip *chip, unsigned offset) +{ + int gpio = chip->base + offset; + + pinctrl_free_gpio(gpio); +} + +static struct gpio_chip abx500gpio_chip = { + .label = "abx500-gpio", + .owner = THIS_MODULE, + .request = abx500_gpio_request, + .free = abx500_gpio_free, + .direction_input = abx500_gpio_direction_input, + .get = abx500_gpio_get, + .direction_output = abx500_gpio_direction_output, + .set = abx500_gpio_set, + .to_irq = abx500_gpio_to_irq, + .dbg_show = abx500_gpio_dbg_show, +}; + +static int abx500_pmx_get_funcs_cnt(struct pinctrl_dev *pctldev) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + + return pct->soc->nfunctions; +} + +static const char *abx500_pmx_get_func_name(struct pinctrl_dev *pctldev, + unsigned function) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + + return pct->soc->functions[function].name; +} + +static int abx500_pmx_get_func_groups(struct pinctrl_dev *pctldev, + unsigned function, + const char * const **groups, + unsigned * const num_groups) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + + *groups = pct->soc->functions[function].groups; + *num_groups = pct->soc->functions[function].ngroups; + + return 0; +} + +static int abx500_pmx_enable(struct pinctrl_dev *pctldev, unsigned function, + unsigned group) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + struct gpio_chip *chip = &pct->chip; + const struct abx500_pingroup *g; + int i; + int ret = 0; + + g = &pct->soc->groups[group]; + if (g->altsetting < 0) + return -EINVAL; + + dev_dbg(pct->dev, "enable group %s, %u pins\n", g->name, g->npins); + + for (i = 0; i < g->npins; i++) { + dev_dbg(pct->dev, "setting pin %d to altsetting %d\n", + g->pins[i], g->altsetting); + + ret = abx500_set_mode(pctldev, chip, g->pins[i], g->altsetting); + } + + return ret; +} + +static void abx500_pmx_disable(struct pinctrl_dev *pctldev, + unsigned function, unsigned group) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + const struct abx500_pingroup *g; + + g = &pct->soc->groups[group]; + if (g->altsetting < 0) + return; + + /* FIXME: poke out the mux, set the pin to some default state? */ + dev_dbg(pct->dev, "disable group %s, %u pins\n", g->name, g->npins); +} + +int abx500_gpio_request_enable(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned offset) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + const struct abx500_pinrange *p; + int ret; + int i; + + /* + * Different ranges have different ways to enable GPIO function on a + * pin, so refer back to our local range type, where we handily define + * what altfunc enables GPIO for a certain pin. + */ + for (i = 0; i < pct->soc->gpio_num_ranges; i++) { + p = &pct->soc->gpio_ranges[i]; + if ((offset >= p->offset) && + (offset < (p->offset + p->npins))) + break; + } + + if (i == pct->soc->gpio_num_ranges) { + dev_err(pct->dev, "%s failed to locate range\n", __func__); + return -ENODEV; + } + + dev_dbg(pct->dev, "enable GPIO by altfunc %d at gpio %d\n", + p->altfunc, offset); + + ret = abx500_set_mode(pct->pctldev, &pct->chip, + offset, p->altfunc); + if (ret < 0) { + dev_err(pct->dev, "%s setting altfunc failed\n", __func__); + return ret; + } + + return ret; +} + +static void abx500_gpio_disable_free(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned offset) +{ +} + +static struct pinmux_ops abx500_pinmux_ops = { + .get_functions_count = abx500_pmx_get_funcs_cnt, + .get_function_name = abx500_pmx_get_func_name, + .get_function_groups = abx500_pmx_get_func_groups, + .enable = abx500_pmx_enable, + .disable = abx500_pmx_disable, + .gpio_request_enable = abx500_gpio_request_enable, + .gpio_disable_free = abx500_gpio_disable_free, +}; + +static int abx500_get_groups_cnt(struct pinctrl_dev *pctldev) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + + return pct->soc->ngroups; +} + +static const char *abx500_get_group_name(struct pinctrl_dev *pctldev, + unsigned selector) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + + return pct->soc->groups[selector].name; +} + +static int abx500_get_group_pins(struct pinctrl_dev *pctldev, + unsigned selector, + const unsigned **pins, + unsigned *num_pins) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + + *pins = pct->soc->groups[selector].pins; + *num_pins = pct->soc->groups[selector].npins; + + return 0; +} + +static void abx500_pin_dbg_show(struct pinctrl_dev *pctldev, + struct seq_file *s, unsigned offset) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + struct gpio_chip *chip = &pct->chip; + + abx500_gpio_dbg_show_one(s, pctldev, chip, offset, + chip->base + offset - 1); +} + +static struct pinctrl_ops abx500_pinctrl_ops = { + .get_groups_count = abx500_get_groups_cnt, + .get_group_name = abx500_get_group_name, + .get_group_pins = abx500_get_group_pins, + .pin_dbg_show = abx500_pin_dbg_show, +}; + +int abx500_pin_config_get(struct pinctrl_dev *pctldev, + unsigned pin, + unsigned long *config) +{ + return -ENOSYS; +} + +int abx500_pin_config_set(struct pinctrl_dev *pctldev, + unsigned pin, + unsigned long config) +{ + struct abx500_pinctrl *pct = pinctrl_dev_get_drvdata(pctldev); + struct pullud *pullud = pct->soc->pullud; + struct gpio_chip *chip = &pct->chip; + unsigned offset; + int ret; + enum pin_config_param param = pinconf_to_config_param(config); + enum pin_config_param argument = pinconf_to_config_argument(config); + + dev_dbg(chip->dev, "pin %d [%#lx]: %s %s\n", + pin, config, (param == PIN_CONFIG_OUTPUT) ? "output " : "input", + (param == PIN_CONFIG_OUTPUT) ? (argument ? "high" : "low") : + (argument ? "pull up" : "pull down")); + + /* on ABx500, there is no GPIO0, so adjust the offset */ + offset = pin - 1; + + switch (param) { + case PIN_CONFIG_BIAS_PULL_DOWN: + /* + * if argument = 1 set the pull down + * else clear the pull down + */ + ret = abx500_gpio_direction_input(chip, offset); + /* + * Some chips only support pull down, while some actually + * support both pull up and pull down. Such chips have + * a "pullud" range specified for the pins that support + * both features. If the pin is not within that range, we + * fall back to the old bit set that only support pull down. + */ + if (pullud && + pin >= pullud->first_pin && + pin <= pullud->last_pin) + ret = abx500_config_pull_updown(pct, + pin, + argument ? ABX500_GPIO_PULL_DOWN : ABX500_GPIO_PULL_NONE); + else + /* Chip only supports pull down */ + ret = abx500_gpio_set_bits(chip, AB8500_GPIO_PUD1_REG, + offset, argument ? 0 : 1); + break; + + case PIN_CONFIG_OUTPUT: + ret = abx500_gpio_direction_output(chip, offset, argument); + + break; + + default: + dev_err(chip->dev, "illegal configuration requested\n"); + + return -EINVAL; + } + + return ret; +} + +static struct pinconf_ops abx500_pinconf_ops = { + .pin_config_get = abx500_pin_config_get, + .pin_config_set = abx500_pin_config_set, +}; + +static struct pinctrl_desc abx500_pinctrl_desc = { + .name = "pinctrl-abx500", + .pctlops = &abx500_pinctrl_ops, + .pmxops = &abx500_pinmux_ops, + .confops = &abx500_pinconf_ops, + .owner = THIS_MODULE, +}; + +static int abx500_get_gpio_num(struct abx500_pinctrl_soc_data *soc) +{ + unsigned int lowest = 0; + unsigned int highest = 0; + unsigned int npins = 0; + int i; + + /* + * Compute number of GPIOs from the last SoC gpio range descriptors + * These ranges may include "holes" but the GPIO number space shall + * still be homogeneous, so we need to detect and account for any + * such holes so that these are included in the number of GPIO pins. + */ + for (i = 0; i < soc->gpio_num_ranges; i++) { + unsigned gstart; + unsigned gend; + const struct abx500_pinrange *p; + + p = &soc->gpio_ranges[i]; + gstart = p->offset; + gend = p->offset + p->npins - 1; + + if (i == 0) { + /* First iteration, set start values */ + lowest = gstart; + highest = gend; + } else { + if (gstart < lowest) + lowest = gstart; + if (gend > highest) + highest = gend; + } + } + /* this gives the absolute number of pins */ + npins = highest - lowest + 1; + return npins; +} + +static const struct of_device_id abx500_gpio_match[] = { + { .compatible = "stericsson,ab8500-gpio", .data = (void *)PINCTRL_AB8500, }, + { .compatible = "stericsson,ab8505-gpio", .data = (void *)PINCTRL_AB8505, }, + { .compatible = "stericsson,ab8540-gpio", .data = (void *)PINCTRL_AB8540, }, + { .compatible = "stericsson,ab9540-gpio", .data = (void *)PINCTRL_AB9540, }, +}; + +static int abx500_gpio_probe(struct platform_device *pdev) +{ + struct ab8500_platform_data *abx500_pdata = + dev_get_platdata(pdev->dev.parent); + struct abx500_gpio_platform_data *pdata = NULL; + struct device_node *np = pdev->dev.of_node; + struct abx500_pinctrl *pct; + const struct platform_device_id *platid = platform_get_device_id(pdev); + unsigned int id = -1; + int ret, err; + int i; + + if (abx500_pdata) + pdata = abx500_pdata->gpio; + if (!pdata) { + if (np) { + const struct of_device_id *match; + + match = of_match_device(abx500_gpio_match, &pdev->dev); + if (!match) + return -ENODEV; + id = (unsigned long)match->data; + } else { + dev_err(&pdev->dev, "gpio dt and platform data missing\n"); + return -ENODEV; + } + } + + if (platid) + id = platid->driver_data; + + pct = devm_kzalloc(&pdev->dev, sizeof(struct abx500_pinctrl), + GFP_KERNEL); + if (pct == NULL) { + dev_err(&pdev->dev, + "failed to allocate memory for pct\n"); + return -ENOMEM; + } + + pct->dev = &pdev->dev; + pct->parent = dev_get_drvdata(pdev->dev.parent); + pct->chip = abx500gpio_chip; + pct->chip.dev = &pdev->dev; + pct->chip.base = pdata->gpio_base; + pct->chip.base = (np) ? -1 : pdata->gpio_base; + + /* initialize the lock */ + mutex_init(&pct->lock); + + /* Poke in other ASIC variants here */ + switch (id) { + case PINCTRL_AB8500: + abx500_pinctrl_ab8500_init(&pct->soc); + break; + case PINCTRL_AB8540: + abx500_pinctrl_ab8540_init(&pct->soc); + break; + case PINCTRL_AB9540: + abx500_pinctrl_ab9540_init(&pct->soc); + break; + case PINCTRL_AB8505: + abx500_pinctrl_ab8505_init(&pct->soc); + break; + default: + dev_err(&pdev->dev, "Unsupported pinctrl sub driver (%d)\n", + (int) platid->driver_data); + mutex_destroy(&pct->lock); + return -EINVAL; + } + + if (!pct->soc) { + dev_err(&pdev->dev, "Invalid SOC data\n"); + mutex_destroy(&pct->lock); + return -EINVAL; + } + + pct->chip.ngpio = abx500_get_gpio_num(pct->soc); + pct->irq_cluster = pct->soc->gpio_irq_cluster; + pct->irq_cluster_size = pct->soc->ngpio_irq_cluster; + + ret = gpiochip_add(&pct->chip); + if (ret) { + dev_err(&pdev->dev, "unable to add gpiochip: %d\n", ret); + mutex_destroy(&pct->lock); + return ret; + } + dev_info(&pdev->dev, "added gpiochip\n"); + + abx500_pinctrl_desc.pins = pct->soc->pins; + abx500_pinctrl_desc.npins = pct->soc->npins; + pct->pctldev = pinctrl_register(&abx500_pinctrl_desc, &pdev->dev, pct); + if (!pct->pctldev) { + dev_err(&pdev->dev, + "could not register abx500 pinctrl driver\n"); + ret = -EINVAL; + goto out_rem_chip; + } + dev_info(&pdev->dev, "registered pin controller\n"); + + /* We will handle a range of GPIO pins */ + for (i = 0; i < pct->soc->gpio_num_ranges; i++) { + const struct abx500_pinrange *p = &pct->soc->gpio_ranges[i]; + + ret = gpiochip_add_pin_range(&pct->chip, + dev_name(&pdev->dev), + p->offset - 1, p->offset, p->npins); + if (ret < 0) + goto out_rem_chip; + } + + platform_set_drvdata(pdev, pct); + dev_info(&pdev->dev, "initialized abx500 pinctrl driver\n"); + + return 0; + +out_rem_chip: + err = gpiochip_remove(&pct->chip); + if (err) + dev_info(&pdev->dev, "failed to remove gpiochip\n"); + + mutex_destroy(&pct->lock); + return ret; +} + +/** + * abx500_gpio_remove() - remove Ab8500-gpio driver + * @pdev: Platform device registered + */ +static int abx500_gpio_remove(struct platform_device *pdev) +{ + struct abx500_pinctrl *pct = platform_get_drvdata(pdev); + int ret; + + ret = gpiochip_remove(&pct->chip); + if (ret < 0) { + dev_err(pct->dev, "unable to remove gpiochip: %d\n", + ret); + return ret; + } + + mutex_destroy(&pct->lock); + + return 0; +} + +static const struct platform_device_id abx500_pinctrl_id[] = { + { "pinctrl-ab8500", PINCTRL_AB8500 }, + { "pinctrl-ab8540", PINCTRL_AB8540 }, + { "pinctrl-ab9540", PINCTRL_AB9540 }, + { "pinctrl-ab8505", PINCTRL_AB8505 }, + { }, +}; + +static struct platform_driver abx500_gpio_driver = { + .driver = { + .name = "abx500-gpio", + .owner = THIS_MODULE, + .of_match_table = abx500_gpio_match, + }, + .probe = abx500_gpio_probe, + .remove = abx500_gpio_remove, + .id_table = abx500_pinctrl_id, +}; + +static int __init abx500_gpio_init(void) +{ + return platform_driver_register(&abx500_gpio_driver); +} +core_initcall(abx500_gpio_init); + +MODULE_AUTHOR("Patrice Chotard <patrice.chotard@st.com>"); +MODULE_DESCRIPTION("Driver allows to use AxB5xx unused pins to be used as GPIO"); +MODULE_ALIAS("platform:abx500-gpio"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/pinctrl-abx500.h b/drivers/pinctrl/pinctrl-abx500.h new file mode 100644 index 0000000..eeca8f9 --- /dev/null +++ b/drivers/pinctrl/pinctrl-abx500.h @@ -0,0 +1,234 @@ +#ifndef PINCTRL_PINCTRL_ABx5O0_H +#define PINCTRL_PINCTRL_ABx500_H + +/* Package definitions */ +#define PINCTRL_AB8500 0 +#define PINCTRL_AB8540 1 +#define PINCTRL_AB9540 2 +#define PINCTRL_AB8505 3 + +/* pins alternate function */ +enum abx500_pin_func { + ABX500_DEFAULT, + ABX500_ALT_A, + ABX500_ALT_B, + ABX500_ALT_C, +}; + +/** + * struct abx500_function - ABx500 pinctrl mux function + * @name: The name of the function, exported to pinctrl core. + * @groups: An array of pin groups that may select this function. + * @ngroups: The number of entries in @groups. + */ +struct abx500_function { + const char *name; + const char * const *groups; + unsigned ngroups; +}; + +/** + * struct abx500_pingroup - describes a ABx500 pin group + * @name: the name of this specific pin group + * @pins: an array of discrete physical pins used in this group, taken + * from the driver-local pin enumeration space + * @num_pins: the number of pins in this group array, i.e. the number of + * elements in .pins so we can iterate over that array + * @altsetting: the altsetting to apply to all pins in this group to + * configure them to be used by a function + */ +struct abx500_pingroup { + const char *name; + const unsigned int *pins; + const unsigned npins; + int altsetting; +}; + +#define ALTERNATE_FUNCTIONS(pin, sel_bit, alt1, alt2, alta, altb, altc) \ +{ \ + .pin_number = pin, \ + .gpiosel_bit = sel_bit, \ + .alt_bit1 = alt1, \ + .alt_bit2 = alt2, \ + .alta_val = alta, \ + .altb_val = altb, \ + .altc_val = altc, \ +} + +#define UNUSED -1 +/** + * struct alternate_functions + * @pin_number: The pin number + * @gpiosel_bit: Control bit in GPIOSEL register, + * @alt_bit1: First AlternateFunction bit used to select the + * alternate function + * @alt_bit2: Second AlternateFunction bit used to select the + * alternate function + * + * these 3 following fields are necessary due to none + * coherency on how to select the altA, altB and altC + * function between the ABx500 SOC family when using + * alternatfunc register. + * @alta_val: value to write in alternatfunc to select altA function + * @altb_val: value to write in alternatfunc to select altB function + * @altc_val: value to write in alternatfunc to select altC function + */ +struct alternate_functions { + unsigned pin_number; + s8 gpiosel_bit; + s8 alt_bit1; + s8 alt_bit2; + u8 alta_val; + u8 altb_val; + u8 altc_val; +}; + +/** + * struct pullud - specific pull up/down feature + * @first_pin: The pin number of the first pins which support + * specific pull up/down + * @last_pin: The pin number of the last pins + */ +struct pullud { + unsigned first_pin; + unsigned last_pin; +}; + +#define GPIO_IRQ_CLUSTER(a, b, c) \ +{ \ + .start = a, \ + .end = b, \ + .to_irq = c, \ +} + +/** + * struct abx500_gpio_irq_cluster - indicates GPIOs which are interrupt + * capable + * @start: The pin number of the first pin interrupt capable + * @end: The pin number of the last pin interrupt capable + * @to_irq: The ABx500 GPIO's associated IRQs are clustered + * together throughout the interrupt numbers at irregular + * intervals. To solve this quandary, we will place the + * read-in values into the cluster information table + */ + +struct abx500_gpio_irq_cluster { + int start; + int end; + int to_irq; +}; + +/** + * struct abx500_pinrange - map pin numbers to GPIO offsets + * @offset: offset into the GPIO local numberspace, incidentally + * identical to the offset into the local pin numberspace + * @npins: number of pins to map from both offsets + * @altfunc: altfunc setting to be used to enable GPIO on a pin in + * this range (may vary) + */ +struct abx500_pinrange { + unsigned int offset; + unsigned int npins; + int altfunc; +}; + +#define ABX500_PINRANGE(a, b, c) { .offset = a, .npins = b, .altfunc = c } + +/** + * struct abx500_pinctrl_soc_data - ABx500 pin controller per-SoC configuration + * @gpio_ranges: An array of GPIO ranges for this SoC + * @gpio_num_ranges: The number of GPIO ranges for this SoC + * @pins: An array describing all pins the pin controller affects. + * All pins which are also GPIOs must be listed first within the + * array, and be numbered identically to the GPIO controller's + * numbering. + * @npins: The number of entries in @pins. + * @functions: The functions supported on this SoC. + * @nfunction: The number of entries in @functions. + * @groups: An array describing all pin groups the pin SoC supports. + * @ngroups: The number of entries in @groups. + * @alternate_functions: array describing pins which supports alternate and + * how to set it. + * @pullud: array describing pins which supports pull up/down + * specific registers. + * @gpio_irq_cluster: An array of GPIO interrupt capable for this SoC + * @ngpio_irq_cluster: The number of GPIO inetrrupt capable for this SoC + * @irq_gpio_rising_offset: Interrupt offset used as base to compute specific + * setting strategy of the rising interrupt line + * @irq_gpio_falling_offset: Interrupt offset used as base to compute specific + * setting strategy of the falling interrupt line + * @irq_gpio_factor: Factor used to compute specific setting strategy of + * the interrupt line + */ + +struct abx500_pinctrl_soc_data { + const struct abx500_pinrange *gpio_ranges; + unsigned gpio_num_ranges; + const struct pinctrl_pin_desc *pins; + unsigned npins; + const struct abx500_function *functions; + unsigned nfunctions; + const struct abx500_pingroup *groups; + unsigned ngroups; + struct alternate_functions *alternate_functions; + struct pullud *pullud; + struct abx500_gpio_irq_cluster *gpio_irq_cluster; + unsigned ngpio_irq_cluster; + int irq_gpio_rising_offset; + int irq_gpio_falling_offset; + int irq_gpio_factor; +}; + +#ifdef CONFIG_PINCTRL_AB8500 + +void abx500_pinctrl_ab8500_init(struct abx500_pinctrl_soc_data **soc); + +#else + +static inline void +abx500_pinctrl_ab8500_init(struct abx500_pinctrl_soc_data **soc) +{ +} + +#endif + +#ifdef CONFIG_PINCTRL_AB8540 + +void abx500_pinctrl_ab8540_init(struct abx500_pinctrl_soc_data **soc); + +#else + +static inline void +abx500_pinctrl_ab8540_init(struct abx500_pinctrl_soc_data **soc) +{ +} + +#endif + +#ifdef CONFIG_PINCTRL_AB9540 + +void abx500_pinctrl_ab9540_init(struct abx500_pinctrl_soc_data **soc); + +#else + +static inline void +abx500_pinctrl_ab9540_init(struct abx500_pinctrl_soc_data **soc) +{ +} + +#endif + +#ifdef CONFIG_PINCTRL_AB8505 + +void abx500_pinctrl_ab8505_init(struct abx500_pinctrl_soc_data **soc); + +#else + +static inline void +abx500_pinctrl_ab8505_init(struct abx500_pinctrl_soc_data **soc) +{ +} + +#endif + +#endif /* PINCTRL_PINCTRL_ABx500_H */ diff --git a/drivers/pinctrl/pinctrl-exynos5440.c b/drivers/pinctrl/pinctrl-exynos5440.c index de05b64..1427299 100644 --- a/drivers/pinctrl/pinctrl-exynos5440.c +++ b/drivers/pinctrl/pinctrl-exynos5440.c @@ -599,7 +599,7 @@ static int exynos5440_gpio_direction_output(struct gpio_chip *gc, unsigned offse } /* parse the pin numbers listed in the 'samsung,exynos5440-pins' property */ -static int __init exynos5440_pinctrl_parse_dt_pins(struct platform_device *pdev, +static int exynos5440_pinctrl_parse_dt_pins(struct platform_device *pdev, struct device_node *cfg_np, unsigned int **pin_list, unsigned int *npins) { @@ -630,7 +630,7 @@ static int __init exynos5440_pinctrl_parse_dt_pins(struct platform_device *pdev, * Parse the information about all the available pin groups and pin functions * from device node of the pin-controller. */ -static int __init exynos5440_pinctrl_parse_dt(struct platform_device *pdev, +static int exynos5440_pinctrl_parse_dt(struct platform_device *pdev, struct exynos5440_pinctrl_priv_data *priv) { struct device *dev = &pdev->dev; @@ -723,7 +723,7 @@ static int __init exynos5440_pinctrl_parse_dt(struct platform_device *pdev, } /* register the pinctrl interface with the pinctrl subsystem */ -static int __init exynos5440_pinctrl_register(struct platform_device *pdev, +static int exynos5440_pinctrl_register(struct platform_device *pdev, struct exynos5440_pinctrl_priv_data *priv) { struct device *dev = &pdev->dev; @@ -798,7 +798,7 @@ static int __init exynos5440_pinctrl_register(struct platform_device *pdev, } /* register the gpiolib interface with the gpiolib subsystem */ -static int __init exynos5440_gpiolib_register(struct platform_device *pdev, +static int exynos5440_gpiolib_register(struct platform_device *pdev, struct exynos5440_pinctrl_priv_data *priv) { struct gpio_chip *gc; @@ -831,7 +831,7 @@ static int __init exynos5440_gpiolib_register(struct platform_device *pdev, } /* unregister the gpiolib interface with the gpiolib subsystem */ -static int __init exynos5440_gpiolib_unregister(struct platform_device *pdev, +static int exynos5440_gpiolib_unregister(struct platform_device *pdev, struct exynos5440_pinctrl_priv_data *priv) { int ret = gpiochip_remove(priv->gc); diff --git a/drivers/pinctrl/pinctrl-falcon.c b/drivers/pinctrl/pinctrl-falcon.c index 8ed20e8..4a0d54a 100644 --- a/drivers/pinctrl/pinctrl-falcon.c +++ b/drivers/pinctrl/pinctrl-falcon.c @@ -170,7 +170,7 @@ static const unsigned pins_ntr[] = {GPIO4}; static const unsigned pins_ntr8k[] = {GPIO5}; static const unsigned pins_hrst[] = {GPIO6}; static const unsigned pins_mdio[] = {GPIO7, GPIO8}; -static const unsigned pins_bled[] = {GPIO7, GPIO10, GPIO11, +static const unsigned pins_bled[] = {GPIO9, GPIO10, GPIO11, GPIO12, GPIO13, GPIO14}; static const unsigned pins_asc0[] = {GPIO32, GPIO33}; static const unsigned pins_spi[] = {GPIO34, GPIO35, GPIO36}; @@ -315,6 +315,37 @@ static int falcon_pinconf_set(struct pinctrl_dev *pctrldev, static void falcon_pinconf_dbg_show(struct pinctrl_dev *pctrldev, struct seq_file *s, unsigned offset) { + unsigned long config; + struct pin_desc *desc; + + struct ltq_pinmux_info *info = pinctrl_dev_get_drvdata(pctrldev); + int port = PORT(offset); + + seq_printf(s, " (port %d) mux %d -- ", port, + pad_r32(info->membase[port], LTQ_PADC_MUX(PORT_PIN(offset)))); + + config = LTQ_PINCONF_PACK(LTQ_PINCONF_PARAM_PULL, 0); + if (!falcon_pinconf_get(pctrldev, offset, &config)) + seq_printf(s, "pull %d ", + (int)LTQ_PINCONF_UNPACK_ARG(config)); + + config = LTQ_PINCONF_PACK(LTQ_PINCONF_PARAM_DRIVE_CURRENT, 0); + if (!falcon_pinconf_get(pctrldev, offset, &config)) + seq_printf(s, "drive-current %d ", + (int)LTQ_PINCONF_UNPACK_ARG(config)); + + config = LTQ_PINCONF_PACK(LTQ_PINCONF_PARAM_SLEW_RATE, 0); + if (!falcon_pinconf_get(pctrldev, offset, &config)) + seq_printf(s, "slew-rate %d ", + (int)LTQ_PINCONF_UNPACK_ARG(config)); + + desc = pin_desc_get(pctrldev, offset); + if (desc) { + if (desc->gpio_owner) + seq_printf(s, " owner: %s", desc->gpio_owner); + } else { + seq_printf(s, " not registered"); + } } static void falcon_pinconf_group_dbg_show(struct pinctrl_dev *pctrldev, @@ -360,6 +391,8 @@ static const struct ltq_cfg_param falcon_cfg_params[] = { static struct ltq_pinmux_info falcon_info = { .desc = &falcon_pctrl_desc, .apply_mux = falcon_mux_apply, + .params = falcon_cfg_params, + .num_params = ARRAY_SIZE(falcon_cfg_params), }; @@ -398,6 +431,9 @@ static int pinctrl_falcon_probe(struct platform_device *pdev) u32 avail; int pins; + if (!of_device_is_available(np)) + continue; + if (!ppdev) { dev_err(&pdev->dev, "failed to find pad pdev\n"); continue; diff --git a/drivers/pinctrl/pinctrl-lantiq.c b/drivers/pinctrl/pinctrl-lantiq.c index 15f501d..a703846 100644 --- a/drivers/pinctrl/pinctrl-lantiq.c +++ b/drivers/pinctrl/pinctrl-lantiq.c @@ -64,11 +64,13 @@ static void ltq_pinctrl_pin_dbg_show(struct pinctrl_dev *pctldev, seq_printf(s, " %s", dev_name(pctldev->dev)); } -static int ltq_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, +static void ltq_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, struct pinctrl_map **map) { struct ltq_pinmux_info *info = pinctrl_dev_get_drvdata(pctldev); + struct property *pins = of_find_property(np, "lantiq,pins", NULL); + struct property *groups = of_find_property(np, "lantiq,groups", NULL); unsigned long configs[3]; unsigned num_configs = 0; struct property *prop; @@ -76,8 +78,20 @@ static int ltq_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, const char *function; int ret, i; + if (!pins && !groups) { + dev_err(pctldev->dev, "%s defines neither pins nor groups\n", + np->name); + return; + } + + if (pins && groups) { + dev_err(pctldev->dev, "%s defines both pins and groups\n", + np->name); + return; + } + ret = of_property_read_string(np, "lantiq,function", &function); - if (!ret) { + if (groups && !ret) { of_property_for_each_string(np, "lantiq,groups", prop, group) { (*map)->type = PIN_MAP_TYPE_MUX_GROUP; (*map)->name = function; @@ -85,11 +99,6 @@ static int ltq_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, (*map)->data.mux.function = function; (*map)++; } - if (of_find_property(np, "lantiq,pins", NULL)) - dev_err(pctldev->dev, - "%s mixes pins and groups settings\n", - np->name); - return 0; } for (i = 0; i < info->num_params; i++) { @@ -103,7 +112,7 @@ static int ltq_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, } if (!num_configs) - return -EINVAL; + return; of_property_for_each_string(np, "lantiq,pins", prop, pin) { (*map)->data.configs.configs = kmemdup(configs, @@ -115,7 +124,16 @@ static int ltq_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, (*map)->data.configs.num_configs = num_configs; (*map)++; } - return 0; + of_property_for_each_string(np, "lantiq,groups", prop, group) { + (*map)->data.configs.configs = kmemdup(configs, + num_configs * sizeof(unsigned long), + GFP_KERNEL); + (*map)->type = PIN_MAP_TYPE_CONFIGS_GROUP; + (*map)->name = group; + (*map)->data.configs.group_or_pin = group; + (*map)->data.configs.num_configs = num_configs; + (*map)++; + } } static int ltq_pinctrl_dt_subnode_size(struct device_node *np) @@ -135,23 +153,19 @@ static int ltq_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev, { struct pinctrl_map *tmp; struct device_node *np; - int ret; + int max_maps = 0; - *num_maps = 0; for_each_child_of_node(np_config, np) - *num_maps += ltq_pinctrl_dt_subnode_size(np); - *map = kzalloc(*num_maps * sizeof(struct pinctrl_map), GFP_KERNEL); + max_maps += ltq_pinctrl_dt_subnode_size(np); + *map = kzalloc(max_maps * sizeof(struct pinctrl_map) * 2, GFP_KERNEL); if (!*map) return -ENOMEM; tmp = *map; - for_each_child_of_node(np_config, np) { - ret = ltq_pinctrl_dt_subnode_to_map(pctldev, np, &tmp); - if (ret < 0) { - ltq_pinctrl_dt_free_map(pctldev, *map, *num_maps); - return ret; - } - } + for_each_child_of_node(np_config, np) + ltq_pinctrl_dt_subnode_to_map(pctldev, np, &tmp); + *num_maps = ((int)(tmp - *map)); + return 0; } @@ -280,7 +294,7 @@ static int ltq_pmx_gpio_request_enable(struct pinctrl_dev *pctrldev, unsigned pin) { struct ltq_pinmux_info *info = pinctrl_dev_get_drvdata(pctrldev); - int mfp = match_mfp(info, pin + (range->id * 32)); + int mfp = match_mfp(info, pin); int pin_func; if (mfp < 0) { diff --git a/drivers/pinctrl/pinctrl-lantiq.h b/drivers/pinctrl/pinctrl-lantiq.h index 4419d32..6d07f02 100644 --- a/drivers/pinctrl/pinctrl-lantiq.h +++ b/drivers/pinctrl/pinctrl-lantiq.h @@ -34,6 +34,7 @@ enum ltq_pinconf_param { LTQ_PINCONF_PARAM_OPEN_DRAIN, LTQ_PINCONF_PARAM_DRIVE_CURRENT, LTQ_PINCONF_PARAM_SLEW_RATE, + LTQ_PINCONF_PARAM_OUTPUT, }; struct ltq_cfg_param { diff --git a/drivers/pinctrl/pinctrl-mxs.c b/drivers/pinctrl/pinctrl-mxs.c index dd227d2..23af9f1 100644 --- a/drivers/pinctrl/pinctrl-mxs.c +++ b/drivers/pinctrl/pinctrl-mxs.c @@ -146,7 +146,7 @@ free: static void mxs_dt_free_map(struct pinctrl_dev *pctldev, struct pinctrl_map *map, unsigned num_maps) { - int i; + u32 i; for (i = 0; i < num_maps; i++) { if (map[i].type == PIN_MAP_TYPE_MUX_GROUP) @@ -203,7 +203,7 @@ static int mxs_pinctrl_enable(struct pinctrl_dev *pctldev, unsigned selector, void __iomem *reg; u8 bank, shift; u16 pin; - int i; + u32 i; for (i = 0; i < g->npins; i++) { bank = PINID_TO_BANK(g->pins[i]); @@ -256,7 +256,7 @@ static int mxs_pinconf_group_set(struct pinctrl_dev *pctldev, void __iomem *reg; u8 ma, vol, pull, bank, shift; u16 pin; - int i; + u32 i; ma = CONFIG_TO_MA(config); vol = CONFIG_TO_VOL(config); @@ -345,8 +345,7 @@ static int mxs_pinctrl_parse_group(struct platform_device *pdev, const char *propname = "fsl,pinmux-ids"; char *group; int length = strlen(np->name) + SUFFIX_LEN; - int i; - u32 val; + u32 val, i; group = devm_kzalloc(&pdev->dev, length, GFP_KERNEL); if (!group) diff --git a/drivers/pinctrl/pinctrl-nomadik.c b/drivers/pinctrl/pinctrl-nomadik.c index 1bb16ff..de9e851 100644 --- a/drivers/pinctrl/pinctrl-nomadik.c +++ b/drivers/pinctrl/pinctrl-nomadik.c @@ -25,6 +25,8 @@ #include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/of_device.h> +#include <linux/of_address.h> +#include <linux/pinctrl/machine.h> #include <linux/pinctrl/pinctrl.h> #include <linux/pinctrl/pinmux.h> #include <linux/pinctrl/pinconf.h> @@ -32,8 +34,8 @@ #include <linux/pinctrl/consumer.h> #include <linux/platform_data/pinctrl-nomadik.h> #include <asm/mach/irq.h> -#include <mach/irqs.h> #include "pinctrl-nomadik.h" +#include "core.h" /* * The GPIO module in the Nomadik family of Systems-on-Chip is an @@ -216,7 +218,7 @@ nmk_gpio_disable_lazy_irq(struct nmk_gpio_chip *nmk_chip, unsigned offset) u32 falling = nmk_chip->fimsc & BIT(offset); u32 rising = nmk_chip->rimsc & BIT(offset); int gpio = nmk_chip->chip.base + offset; - int irq = NOMADIK_GPIO_TO_IRQ(gpio); + int irq = irq_find_mapping(nmk_chip->domain, offset); struct irq_data *d = irq_get_irq_data(irq); if (!rising && !falling) @@ -676,7 +678,7 @@ int nmk_gpio_set_mode(int gpio, int gpio_mode) } EXPORT_SYMBOL(nmk_gpio_set_mode); -static int nmk_prcm_gpiocr_get_mode(struct pinctrl_dev *pctldev, int gpio) +static int __maybe_unused nmk_prcm_gpiocr_get_mode(struct pinctrl_dev *pctldev, int gpio) { int i; u16 reg; @@ -1341,8 +1343,7 @@ static int nmk_gpio_probe(struct platform_device *dev) if (of_property_read_u32(np, "gpio-bank", &dev->id)) { dev_err(&dev->dev, "gpio-bank property not found\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } pdata->first_gpio = dev->id * NMK_GPIO_PER_CHIP; @@ -1350,41 +1351,29 @@ static int nmk_gpio_probe(struct platform_device *dev) } res = platform_get_resource(dev, IORESOURCE_MEM, 0); - if (!res) { - ret = -ENOENT; - goto out; - } + if (!res) + return -ENOENT; irq = platform_get_irq(dev, 0); - if (irq < 0) { - ret = irq; - goto out; - } + if (irq < 0) + return irq; secondary_irq = platform_get_irq(dev, 1); - if (secondary_irq >= 0 && !pdata->get_secondary_status) { - ret = -EINVAL; - goto out; - } + if (secondary_irq >= 0 && !pdata->get_secondary_status) + return -EINVAL; base = devm_request_and_ioremap(&dev->dev, res); - if (!base) { - ret = -ENOMEM; - goto out; - } + if (!base) + return -ENOMEM; clk = devm_clk_get(&dev->dev, NULL); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - goto out; - } + if (IS_ERR(clk)) + return PTR_ERR(clk); clk_prepare(clk); nmk_chip = devm_kzalloc(&dev->dev, sizeof(*nmk_chip), GFP_KERNEL); - if (!nmk_chip) { - ret = -ENOMEM; - goto out; - } + if (!nmk_chip) + return -ENOMEM; /* * The virt address in nmk_chip->addr is in the nomadik register space, @@ -1418,7 +1407,7 @@ static int nmk_gpio_probe(struct platform_device *dev) ret = gpiochip_add(&nmk_chip->chip); if (ret) - goto out; + return ret; BUG_ON(nmk_chip->bank >= ARRAY_SIZE(nmk_gpio_chips)); @@ -1427,14 +1416,15 @@ static int nmk_gpio_probe(struct platform_device *dev) platform_set_drvdata(dev, nmk_chip); if (!np) - irq_start = NOMADIK_GPIO_TO_IRQ(pdata->first_gpio); + irq_start = pdata->first_irq; nmk_chip->domain = irq_domain_add_simple(np, NMK_GPIO_PER_CHIP, irq_start, &nmk_gpio_irq_simple_ops, nmk_chip); if (!nmk_chip->domain) { dev_err(&dev->dev, "failed to create irqdomain\n"); - ret = -ENOSYS; - goto out; + /* Just do this, no matter if it fails */ + ret = gpiochip_remove(&nmk_chip->chip); + return -ENOSYS; } nmk_gpio_init_irq(nmk_chip); @@ -1442,12 +1432,6 @@ static int nmk_gpio_probe(struct platform_device *dev) dev_info(&dev->dev, "at address %p\n", nmk_chip->addr); return 0; - -out: - dev_err(&dev->dev, "Failure %i for GPIO %i-%i\n", ret, - pdata->first_gpio, pdata->first_gpio+31); - - return ret; } static int nmk_get_groups_cnt(struct pinctrl_dev *pctldev) @@ -1508,11 +1492,285 @@ static void nmk_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, nmk_gpio_dbg_show_one(s, pctldev, chip, offset - chip->base, offset); } +static void nmk_pinctrl_dt_free_map(struct pinctrl_dev *pctldev, + struct pinctrl_map *map, unsigned num_maps) +{ + int i; + + for (i = 0; i < num_maps; i++) + if (map[i].type == PIN_MAP_TYPE_CONFIGS_PIN) + kfree(map[i].data.configs.configs); + kfree(map); +} + +static int nmk_dt_reserve_map(struct pinctrl_map **map, unsigned *reserved_maps, + unsigned *num_maps, unsigned reserve) +{ + unsigned old_num = *reserved_maps; + unsigned new_num = *num_maps + reserve; + struct pinctrl_map *new_map; + + if (old_num >= new_num) + return 0; + + new_map = krealloc(*map, sizeof(*new_map) * new_num, GFP_KERNEL); + if (!new_map) + return -ENOMEM; + + memset(new_map + old_num, 0, (new_num - old_num) * sizeof(*new_map)); + + *map = new_map; + *reserved_maps = new_num; + + return 0; +} + +static int nmk_dt_add_map_mux(struct pinctrl_map **map, unsigned *reserved_maps, + unsigned *num_maps, const char *group, + const char *function) +{ + if (*num_maps == *reserved_maps) + return -ENOSPC; + + (*map)[*num_maps].type = PIN_MAP_TYPE_MUX_GROUP; + (*map)[*num_maps].data.mux.group = group; + (*map)[*num_maps].data.mux.function = function; + (*num_maps)++; + + return 0; +} + +static int nmk_dt_add_map_configs(struct pinctrl_map **map, + unsigned *reserved_maps, + unsigned *num_maps, const char *group, + unsigned long *configs, unsigned num_configs) +{ + unsigned long *dup_configs; + + if (*num_maps == *reserved_maps) + return -ENOSPC; + + dup_configs = kmemdup(configs, num_configs * sizeof(*dup_configs), + GFP_KERNEL); + if (!dup_configs) + return -ENOMEM; + + (*map)[*num_maps].type = PIN_MAP_TYPE_CONFIGS_PIN; + + (*map)[*num_maps].data.configs.group_or_pin = group; + (*map)[*num_maps].data.configs.configs = dup_configs; + (*map)[*num_maps].data.configs.num_configs = num_configs; + (*num_maps)++; + + return 0; +} + +#define NMK_CONFIG_PIN(x,y) { .property = x, .config = y, } +#define NMK_CONFIG_PIN_ARRAY(x,y) { .property = x, .choice = y, \ + .size = ARRAY_SIZE(y), } + +static const unsigned long nmk_pin_input_modes[] = { + PIN_INPUT_NOPULL, + PIN_INPUT_PULLUP, + PIN_INPUT_PULLDOWN, +}; + +static const unsigned long nmk_pin_output_modes[] = { + PIN_OUTPUT_LOW, + PIN_OUTPUT_HIGH, + PIN_DIR_OUTPUT, +}; + +static const unsigned long nmk_pin_sleep_modes[] = { + PIN_SLEEPMODE_DISABLED, + PIN_SLEEPMODE_ENABLED, +}; + +static const unsigned long nmk_pin_sleep_input_modes[] = { + PIN_SLPM_INPUT_NOPULL, + PIN_SLPM_INPUT_PULLUP, + PIN_SLPM_INPUT_PULLDOWN, + PIN_SLPM_DIR_INPUT, +}; + +static const unsigned long nmk_pin_sleep_output_modes[] = { + PIN_SLPM_OUTPUT_LOW, + PIN_SLPM_OUTPUT_HIGH, + PIN_SLPM_DIR_OUTPUT, +}; + +static const unsigned long nmk_pin_sleep_wakeup_modes[] = { + PIN_SLPM_WAKEUP_DISABLE, + PIN_SLPM_WAKEUP_ENABLE, +}; + +static const unsigned long nmk_pin_gpio_modes[] = { + PIN_GPIOMODE_DISABLED, + PIN_GPIOMODE_ENABLED, +}; + +static const unsigned long nmk_pin_sleep_pdis_modes[] = { + PIN_SLPM_PDIS_DISABLED, + PIN_SLPM_PDIS_ENABLED, +}; + +struct nmk_cfg_param { + const char *property; + unsigned long config; + const unsigned long *choice; + int size; +}; + +static const struct nmk_cfg_param nmk_cfg_params[] = { + NMK_CONFIG_PIN_ARRAY("ste,input", nmk_pin_input_modes), + NMK_CONFIG_PIN_ARRAY("ste,output", nmk_pin_output_modes), + NMK_CONFIG_PIN_ARRAY("ste,sleep", nmk_pin_sleep_modes), + NMK_CONFIG_PIN_ARRAY("ste,sleep-input", nmk_pin_sleep_input_modes), + NMK_CONFIG_PIN_ARRAY("ste,sleep-output", nmk_pin_sleep_output_modes), + NMK_CONFIG_PIN_ARRAY("ste,sleep-wakeup", nmk_pin_sleep_wakeup_modes), + NMK_CONFIG_PIN_ARRAY("ste,gpio", nmk_pin_gpio_modes), + NMK_CONFIG_PIN_ARRAY("ste,sleep-pull-disable", nmk_pin_sleep_pdis_modes), +}; + +static int nmk_dt_pin_config(int index, int val, unsigned long *config) +{ + int ret = 0; + + if (nmk_cfg_params[index].choice == NULL) + *config = nmk_cfg_params[index].config; + else { + /* test if out of range */ + if (val < nmk_cfg_params[index].size) { + *config = nmk_cfg_params[index].config | + nmk_cfg_params[index].choice[val]; + } + } + return ret; +} + +static const char *nmk_find_pin_name(struct pinctrl_dev *pctldev, const char *pin_name) +{ + int i, pin_number; + struct nmk_pinctrl *npct = pinctrl_dev_get_drvdata(pctldev); + + if (sscanf((char *)pin_name, "GPIO%d", &pin_number) == 1) + for (i = 0; i < npct->soc->npins; i++) + if (npct->soc->pins[i].number == pin_number) + return npct->soc->pins[i].name; + return NULL; +} + +static bool nmk_pinctrl_dt_get_config(struct device_node *np, + unsigned long *configs) +{ + bool has_config = 0; + unsigned long cfg = 0; + int i, val, ret; + + for (i = 0; i < ARRAY_SIZE(nmk_cfg_params); i++) { + ret = of_property_read_u32(np, + nmk_cfg_params[i].property, &val); + if (ret != -EINVAL) { + if (nmk_dt_pin_config(i, val, &cfg) == 0) { + *configs |= cfg; + has_config = 1; + } + } + } + + return has_config; +} + +int nmk_pinctrl_dt_subnode_to_map(struct pinctrl_dev *pctldev, + struct device_node *np, + struct pinctrl_map **map, + unsigned *reserved_maps, + unsigned *num_maps) +{ + int ret; + const char *function = NULL; + unsigned long configs = 0; + bool has_config = 0; + unsigned reserve = 0; + struct property *prop; + const char *group, *gpio_name; + struct device_node *np_config; + + ret = of_property_read_string(np, "ste,function", &function); + if (ret >= 0) + reserve = 1; + + has_config = nmk_pinctrl_dt_get_config(np, &configs); + + np_config = of_parse_phandle(np, "ste,config", 0); + if (np_config) + has_config |= nmk_pinctrl_dt_get_config(np_config, &configs); + + ret = of_property_count_strings(np, "ste,pins"); + if (ret < 0) + goto exit; + + if (has_config) + reserve++; + + reserve *= ret; + + ret = nmk_dt_reserve_map(map, reserved_maps, num_maps, reserve); + if (ret < 0) + goto exit; + + of_property_for_each_string(np, "ste,pins", prop, group) { + if (function) { + ret = nmk_dt_add_map_mux(map, reserved_maps, num_maps, + group, function); + if (ret < 0) + goto exit; + } + if (has_config) { + gpio_name = nmk_find_pin_name(pctldev, group); + + ret = nmk_dt_add_map_configs(map, reserved_maps, num_maps, + gpio_name, &configs, 1); + if (ret < 0) + goto exit; + } + + } +exit: + return ret; +} + +int nmk_pinctrl_dt_node_to_map(struct pinctrl_dev *pctldev, + struct device_node *np_config, + struct pinctrl_map **map, unsigned *num_maps) +{ + unsigned reserved_maps; + struct device_node *np; + int ret; + + reserved_maps = 0; + *map = NULL; + *num_maps = 0; + + for_each_child_of_node(np_config, np) { + ret = nmk_pinctrl_dt_subnode_to_map(pctldev, np, map, + &reserved_maps, num_maps); + if (ret < 0) { + nmk_pinctrl_dt_free_map(pctldev, *map, *num_maps); + return ret; + } + } + + return 0; +} + static struct pinctrl_ops nmk_pinctrl_ops = { .get_groups_count = nmk_get_groups_cnt, .get_group_name = nmk_get_group_name, .get_group_pins = nmk_get_group_pins, .pin_dbg_show = nmk_pin_dbg_show, + .dt_node_to_map = nmk_pinctrl_dt_node_to_map, + .dt_free_map = nmk_pinctrl_dt_free_map, }; static int nmk_pmx_get_funcs_cnt(struct pinctrl_dev *pctldev) @@ -1846,16 +2104,39 @@ static struct pinctrl_desc nmk_pinctrl_desc = { static const struct of_device_id nmk_pinctrl_match[] = { { - .compatible = "stericsson,nmk_pinctrl", + .compatible = "stericsson,nmk-pinctrl", .data = (void *)PINCTRL_NMK_DB8500, }, {}, }; +static int nmk_pinctrl_suspend(struct platform_device *pdev, pm_message_t state) +{ + struct nmk_pinctrl *npct; + + npct = platform_get_drvdata(pdev); + if (!npct) + return -EINVAL; + + return pinctrl_force_sleep(npct->pctl); +} + +static int nmk_pinctrl_resume(struct platform_device *pdev) +{ + struct nmk_pinctrl *npct; + + npct = platform_get_drvdata(pdev); + if (!npct) + return -EINVAL; + + return pinctrl_force_default(npct->pctl); +} + static int nmk_pinctrl_probe(struct platform_device *pdev) { const struct platform_device_id *platid = platform_get_device_id(pdev); struct device_node *np = pdev->dev.of_node; + struct device_node *prcm_np; struct nmk_pinctrl *npct; struct resource *res; unsigned int version = 0; @@ -1884,21 +2165,26 @@ static int nmk_pinctrl_probe(struct platform_device *pdev) if (version == PINCTRL_NMK_DB8540) nmk_pinctrl_db8540_init(&npct->soc); + if (np) { + prcm_np = of_parse_phandle(np, "prcm", 0); + if (prcm_np) + npct->prcm_base = of_iomap(prcm_np, 0); + } + + /* Allow platform passed information to over-write DT. */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res) { + if (res) npct->prcm_base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); - if (!npct->prcm_base) { - dev_err(&pdev->dev, - "failed to ioremap PRCM registers\n"); - return -ENOMEM; + if (!npct->prcm_base) { + if (version == PINCTRL_NMK_STN8815) { + dev_info(&pdev->dev, + "No PRCM base, " + "assuming no ALT-Cx control is available\n"); + } else { + dev_err(&pdev->dev, "missing PRCM base address\n"); + return -EINVAL; } - } else if (version == PINCTRL_NMK_STN8815) { - dev_info(&pdev->dev, - "No PRCM base, assume no ALT-Cx control is available\n"); - } else { - dev_err(&pdev->dev, "missing PRCM base address\n"); - return -EINVAL; } /* @@ -1963,6 +2249,10 @@ static struct platform_driver nmk_pinctrl_driver = { }, .probe = nmk_pinctrl_probe, .id_table = nmk_pinctrl_id, +#ifdef CONFIG_PM + .suspend = nmk_pinctrl_suspend, + .resume = nmk_pinctrl_resume, +#endif }; static int __init nmk_gpio_init(void) diff --git a/drivers/pinctrl/pinctrl-samsung.c b/drivers/pinctrl/pinctrl-samsung.c index fd7b24c..5c20ed0 100644 --- a/drivers/pinctrl/pinctrl-samsung.c +++ b/drivers/pinctrl/pinctrl-samsung.c @@ -716,7 +716,6 @@ static int samsung_pinctrl_register(struct platform_device *pdev, } ctrldesc->pins = pindesc; ctrldesc->npins = drvdata->ctrl->nr_pins; - ctrldesc->npins = drvdata->ctrl->nr_pins; /* dynamically populate the pin number and pin name for pindesc */ for (pin = 0, pdesc = pindesc; pin < ctrldesc->npins; pin++, pdesc++) diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index f6a360b..5c32e88 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -30,7 +30,6 @@ #define PCS_MUX_BITS_NAME "pinctrl-single,bits" #define PCS_REG_NAME_LEN ((sizeof(unsigned long) * 2) + 1) #define PCS_OFF_DISABLED ~0U -#define PCS_MAX_GPIO_VALUES 2 /** * struct pcs_pingroup - pingroups for a function @@ -78,16 +77,6 @@ struct pcs_function { }; /** - * struct pcs_gpio_range - pinctrl gpio range - * @range: subrange of the GPIO number space - * @gpio_func: gpio function value in the pinmux register - */ -struct pcs_gpio_range { - struct pinctrl_gpio_range range; - int gpio_func; -}; - -/** * struct pcs_data - wrapper for data needed by pinctrl framework * @pa: pindesc array * @cur: index to current element @@ -414,26 +403,9 @@ static void pcs_disable(struct pinctrl_dev *pctldev, unsigned fselector, } static int pcs_request_gpio(struct pinctrl_dev *pctldev, - struct pinctrl_gpio_range *range, unsigned pin) + struct pinctrl_gpio_range *range, unsigned offset) { - struct pcs_device *pcs = pinctrl_dev_get_drvdata(pctldev); - struct pcs_gpio_range *gpio = NULL; - int end, mux_bytes; - unsigned data; - - gpio = container_of(range, struct pcs_gpio_range, range); - end = range->pin_base + range->npins - 1; - if (pin < range->pin_base || pin > end) { - dev_err(pctldev->dev, - "pin %d isn't in the range of %d to %d\n", - pin, range->pin_base, end); - return -EINVAL; - } - mux_bytes = pcs->width / BITS_PER_BYTE; - data = pcs->read(pcs->base + pin * mux_bytes) & ~pcs->fmask; - data |= gpio->gpio_func; - pcs->write(data, pcs->base + pin * mux_bytes); - return 0; + return -ENOTSUPP; } static struct pinmux_ops pcs_pinmux_ops = { @@ -907,49 +879,6 @@ static void pcs_free_resources(struct pcs_device *pcs) static struct of_device_id pcs_of_match[]; -static int pcs_add_gpio_range(struct device_node *node, struct pcs_device *pcs) -{ - struct pcs_gpio_range *gpio; - struct device_node *child; - struct resource r; - const char name[] = "pinctrl-single"; - u32 gpiores[PCS_MAX_GPIO_VALUES]; - int ret, i = 0, mux_bytes = 0; - - for_each_child_of_node(node, child) { - ret = of_address_to_resource(child, 0, &r); - if (ret < 0) - continue; - memset(gpiores, 0, sizeof(u32) * PCS_MAX_GPIO_VALUES); - ret = of_property_read_u32_array(child, "pinctrl-single,gpio", - gpiores, PCS_MAX_GPIO_VALUES); - if (ret < 0) - continue; - gpio = devm_kzalloc(pcs->dev, sizeof(*gpio), GFP_KERNEL); - if (!gpio) { - dev_err(pcs->dev, "failed to allocate pcs gpio\n"); - return -ENOMEM; - } - gpio->range.name = devm_kzalloc(pcs->dev, sizeof(name), - GFP_KERNEL); - if (!gpio->range.name) { - dev_err(pcs->dev, "failed to allocate range name\n"); - return -ENOMEM; - } - memcpy((char *)gpio->range.name, name, sizeof(name)); - - gpio->range.id = i++; - gpio->range.base = gpiores[0]; - gpio->gpio_func = gpiores[1]; - mux_bytes = pcs->width / BITS_PER_BYTE; - gpio->range.pin_base = (r.start - pcs->res->start) / mux_bytes; - gpio->range.npins = (r.end - r.start) / mux_bytes + 1; - - pinctrl_add_gpio_range(pcs->pctl, &gpio->range); - } - return 0; -} - static int pcs_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; @@ -1046,10 +975,6 @@ static int pcs_probe(struct platform_device *pdev) goto free; } - ret = pcs_add_gpio_range(np, pcs); - if (ret < 0) - goto free; - dev_info(pcs->dev, "%i pins at pa %p size %u\n", pcs->desc.npins, pcs->base, pcs->size); diff --git a/drivers/pinctrl/pinctrl-sirf.c b/drivers/pinctrl/pinctrl-sirf.c index 498b2ba..d02498b 100644 --- a/drivers/pinctrl/pinctrl-sirf.c +++ b/drivers/pinctrl/pinctrl-sirf.c @@ -1246,6 +1246,22 @@ static void __iomem *sirfsoc_rsc_of_iomap(void) return of_iomap(np, 0); } +static int sirfsoc_gpio_of_xlate(struct gpio_chip *gc, + const struct of_phandle_args *gpiospec, + u32 *flags) +{ + if (gpiospec->args[0] > SIRFSOC_GPIO_NO_OF_BANKS * SIRFSOC_GPIO_BANK_SIZE) + return -EINVAL; + + if (gc != &sgpio_bank[gpiospec->args[0] / SIRFSOC_GPIO_BANK_SIZE].chip.gc) + return -EINVAL; + + if (flags) + *flags = gpiospec->args[1]; + + return gpiospec->args[0] % SIRFSOC_GPIO_BANK_SIZE; +} + static int sirfsoc_pinmux_probe(struct platform_device *pdev) { int ret; @@ -1736,6 +1752,8 @@ static int sirfsoc_gpio_probe(struct device_node *np) bank->chip.gc.ngpio = SIRFSOC_GPIO_BANK_SIZE; bank->chip.gc.label = kstrdup(np->full_name, GFP_KERNEL); bank->chip.gc.of_node = np; + bank->chip.gc.of_xlate = sirfsoc_gpio_of_xlate; + bank->chip.gc.of_gpio_n_cells = 2; bank->chip.regs = regs; bank->id = i; bank->is_marco = is_marco; diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c new file mode 100644 index 0000000..80b11e3 --- /dev/null +++ b/drivers/pinctrl/pinctrl-sunxi.c @@ -0,0 +1,1505 @@ +/* + * Allwinner A1X SoCs pinctrl driver. + * + * Copyright (C) 2012 Maxime Ripard + * + * Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#include <linux/io.h> +#include <linux/gpio.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/pinctrl/consumer.h> +#include <linux/pinctrl/machine.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/pinctrl/pinconf-generic.h> +#include <linux/pinctrl/pinmux.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "core.h" +#include "pinctrl-sunxi.h" + +static const struct sunxi_desc_pin sun4i_a10_pins[] = { + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* TX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* RX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* RTS */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* CTS */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* DTR */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* DSR */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* DCD */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PA17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* RING */ + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB20, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB21, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB22, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x2, "uart0")), /* TX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB23, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x2, "uart0")), /* RX */ + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC20, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC21, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC22, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC23, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC24, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD20, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD21, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD22, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD23, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD24, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD25, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD26, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD27, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart0")), /* TX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart0")), /* RX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH20, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH21, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH22, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH23, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH24, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH25, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH26, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PH27, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI20, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PI21, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), +}; + +static const struct sunxi_desc_pin sun5i_a13_pins[] = { + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB16, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB17, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PB18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PC19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD13, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD14, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD15, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD18, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD19, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD20, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD21, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD22, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD23, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD24, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD25, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD26, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PD27, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE6, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE7, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE8, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* TX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PE11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* RX */ + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PF5, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG0, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG1, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG2, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG3, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* TX */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG4, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out"), + SUNXI_FUNCTION(0x4, "uart1")), /* RX */ + /* Hole */ + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG9, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG10, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG11, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), + SUNXI_PIN(SUNXI_PINCTRL_PIN_PG12, + SUNXI_FUNCTION(0x0, "gpio_in"), + SUNXI_FUNCTION(0x1, "gpio_out")), +}; + +static const struct sunxi_pinctrl_desc sun4i_a10_pinctrl_data = { + .pins = sun4i_a10_pins, + .npins = ARRAY_SIZE(sun4i_a10_pins), +}; + +static const struct sunxi_pinctrl_desc sun5i_a13_pinctrl_data = { + .pins = sun5i_a13_pins, + .npins = ARRAY_SIZE(sun5i_a13_pins), +}; + +static struct sunxi_pinctrl_group * +sunxi_pinctrl_find_group_by_name(struct sunxi_pinctrl *pctl, const char *group) +{ + int i; + + for (i = 0; i < pctl->ngroups; i++) { + struct sunxi_pinctrl_group *grp = pctl->groups + i; + + if (!strcmp(grp->name, group)) + return grp; + } + + return NULL; +} + +static struct sunxi_pinctrl_function * +sunxi_pinctrl_find_function_by_name(struct sunxi_pinctrl *pctl, + const char *name) +{ + struct sunxi_pinctrl_function *func = pctl->functions; + int i; + + for (i = 0; i < pctl->nfunctions; i++) { + if (!func[i].name) + break; + + if (!strcmp(func[i].name, name)) + return func + i; + } + + return NULL; +} + +static struct sunxi_desc_function * +sunxi_pinctrl_desc_find_function_by_name(struct sunxi_pinctrl *pctl, + const char *pin_name, + const char *func_name) +{ + int i; + + for (i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + + if (!strcmp(pin->pin.name, pin_name)) { + struct sunxi_desc_function *func = pin->functions; + + while (func->name) { + if (!strcmp(func->name, func_name)) + return func; + + func++; + } + } + } + + return NULL; +} + +static int sunxi_pctrl_get_groups_count(struct pinctrl_dev *pctldev) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + return pctl->ngroups; +} + +static const char *sunxi_pctrl_get_group_name(struct pinctrl_dev *pctldev, + unsigned group) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + return pctl->groups[group].name; +} + +static int sunxi_pctrl_get_group_pins(struct pinctrl_dev *pctldev, + unsigned group, + const unsigned **pins, + unsigned *num_pins) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + *pins = (unsigned *)&pctl->groups[group].pin; + *num_pins = 1; + + return 0; +} + +static int sunxi_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev, + struct device_node *node, + struct pinctrl_map **map, + unsigned *num_maps) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + unsigned long *pinconfig; + struct property *prop; + const char *function; + const char *group; + int ret, nmaps, i = 0; + u32 val; + + *map = NULL; + *num_maps = 0; + + ret = of_property_read_string(node, "allwinner,function", &function); + if (ret) { + dev_err(pctl->dev, + "missing allwinner,function property in node %s\n", + node->name); + return -EINVAL; + } + + nmaps = of_property_count_strings(node, "allwinner,pins") * 2; + if (nmaps < 0) { + dev_err(pctl->dev, + "missing allwinner,pins property in node %s\n", + node->name); + return -EINVAL; + } + + *map = kmalloc(nmaps * sizeof(struct pinctrl_map), GFP_KERNEL); + if (!map) + return -ENOMEM; + + of_property_for_each_string(node, "allwinner,pins", prop, group) { + struct sunxi_pinctrl_group *grp = + sunxi_pinctrl_find_group_by_name(pctl, group); + int j = 0, configlen = 0; + + if (!grp) { + dev_err(pctl->dev, "unknown pin %s", group); + continue; + } + + if (!sunxi_pinctrl_desc_find_function_by_name(pctl, + grp->name, + function)) { + dev_err(pctl->dev, "unsupported function %s on pin %s", + function, group); + continue; + } + + (*map)[i].type = PIN_MAP_TYPE_MUX_GROUP; + (*map)[i].data.mux.group = group; + (*map)[i].data.mux.function = function; + + i++; + + (*map)[i].type = PIN_MAP_TYPE_CONFIGS_GROUP; + (*map)[i].data.configs.group_or_pin = group; + + if (of_find_property(node, "allwinner,drive", NULL)) + configlen++; + if (of_find_property(node, "allwinner,pull", NULL)) + configlen++; + + pinconfig = kzalloc(configlen * sizeof(*pinconfig), GFP_KERNEL); + + if (!of_property_read_u32(node, "allwinner,drive", &val)) { + u16 strength = (val + 1) * 10; + pinconfig[j++] = + pinconf_to_config_packed(PIN_CONFIG_DRIVE_STRENGTH, + strength); + } + + if (!of_property_read_u32(node, "allwinner,pull", &val)) { + enum pin_config_param pull = PIN_CONFIG_END; + if (val == 1) + pull = PIN_CONFIG_BIAS_PULL_UP; + else if (val == 2) + pull = PIN_CONFIG_BIAS_PULL_DOWN; + pinconfig[j++] = pinconf_to_config_packed(pull, 0); + } + + (*map)[i].data.configs.configs = pinconfig; + (*map)[i].data.configs.num_configs = configlen; + + i++; + } + + *num_maps = nmaps; + + return 0; +} + +static void sunxi_pctrl_dt_free_map(struct pinctrl_dev *pctldev, + struct pinctrl_map *map, + unsigned num_maps) +{ + int i; + + for (i = 0; i < num_maps; i++) { + if (map[i].type == PIN_MAP_TYPE_CONFIGS_GROUP) + kfree(map[i].data.configs.configs); + } + + kfree(map); +} + +static struct pinctrl_ops sunxi_pctrl_ops = { + .dt_node_to_map = sunxi_pctrl_dt_node_to_map, + .dt_free_map = sunxi_pctrl_dt_free_map, + .get_groups_count = sunxi_pctrl_get_groups_count, + .get_group_name = sunxi_pctrl_get_group_name, + .get_group_pins = sunxi_pctrl_get_group_pins, +}; + +static int sunxi_pconf_group_get(struct pinctrl_dev *pctldev, + unsigned group, + unsigned long *config) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + *config = pctl->groups[group].config; + + return 0; +} + +static int sunxi_pconf_group_set(struct pinctrl_dev *pctldev, + unsigned group, + unsigned long config) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + struct sunxi_pinctrl_group *g = &pctl->groups[group]; + u32 val, mask; + u16 strength; + u8 dlevel; + + switch (pinconf_to_config_param(config)) { + case PIN_CONFIG_DRIVE_STRENGTH: + strength = pinconf_to_config_argument(config); + if (strength > 40) + return -EINVAL; + /* + * We convert from mA to what the register expects: + * 0: 10mA + * 1: 20mA + * 2: 30mA + * 3: 40mA + */ + dlevel = strength / 10 - 1; + val = readl(pctl->membase + sunxi_dlevel_reg(g->pin)); + mask = DLEVEL_PINS_MASK << sunxi_dlevel_offset(g->pin); + writel((val & ~mask) | dlevel << sunxi_dlevel_offset(g->pin), + pctl->membase + sunxi_dlevel_reg(g->pin)); + break; + case PIN_CONFIG_BIAS_PULL_UP: + val = readl(pctl->membase + sunxi_pull_reg(g->pin)); + mask = PULL_PINS_MASK << sunxi_pull_offset(g->pin); + writel((val & ~mask) | 1 << sunxi_pull_offset(g->pin), + pctl->membase + sunxi_pull_reg(g->pin)); + break; + case PIN_CONFIG_BIAS_PULL_DOWN: + val = readl(pctl->membase + sunxi_pull_reg(g->pin)); + mask = PULL_PINS_MASK << sunxi_pull_offset(g->pin); + writel((val & ~mask) | 2 << sunxi_pull_offset(g->pin), + pctl->membase + sunxi_pull_reg(g->pin)); + break; + default: + break; + } + + /* cache the config value */ + g->config = config; + + return 0; +} + +static struct pinconf_ops sunxi_pconf_ops = { + .pin_config_group_get = sunxi_pconf_group_get, + .pin_config_group_set = sunxi_pconf_group_set, +}; + +static int sunxi_pmx_get_funcs_cnt(struct pinctrl_dev *pctldev) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + return pctl->nfunctions; +} + +static const char *sunxi_pmx_get_func_name(struct pinctrl_dev *pctldev, + unsigned function) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + return pctl->functions[function].name; +} + +static int sunxi_pmx_get_func_groups(struct pinctrl_dev *pctldev, + unsigned function, + const char * const **groups, + unsigned * const num_groups) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + *groups = pctl->functions[function].groups; + *num_groups = pctl->functions[function].ngroups; + + return 0; +} + +static void sunxi_pmx_set(struct pinctrl_dev *pctldev, + unsigned pin, + u8 config) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + + u32 val = readl(pctl->membase + sunxi_mux_reg(pin)); + u32 mask = MUX_PINS_MASK << sunxi_mux_offset(pin); + writel((val & ~mask) | config << sunxi_mux_offset(pin), + pctl->membase + sunxi_mux_reg(pin)); +} + +static int sunxi_pmx_enable(struct pinctrl_dev *pctldev, + unsigned function, + unsigned group) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + struct sunxi_pinctrl_group *g = pctl->groups + group; + struct sunxi_pinctrl_function *func = pctl->functions + function; + struct sunxi_desc_function *desc = + sunxi_pinctrl_desc_find_function_by_name(pctl, + g->name, + func->name); + + if (!desc) + return -EINVAL; + + sunxi_pmx_set(pctldev, g->pin, desc->muxval); + + return 0; +} + +static int +sunxi_pmx_gpio_set_direction(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned offset, + bool input) +{ + struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); + struct sunxi_desc_function *desc; + char pin_name[SUNXI_PIN_NAME_MAX_LEN]; + const char *func; + u8 bank, pin; + int ret; + + bank = (offset) / PINS_PER_BANK; + pin = (offset) % PINS_PER_BANK; + + ret = sprintf(pin_name, "P%c%d", 'A' + bank, pin); + if (!ret) + goto error; + + if (input) + func = "gpio_in"; + else + func = "gpio_out"; + + desc = sunxi_pinctrl_desc_find_function_by_name(pctl, + pin_name, + func); + if (!desc) { + ret = -EINVAL; + goto error; + } + + sunxi_pmx_set(pctldev, offset, desc->muxval); + + ret = 0; + +error: + return ret; +} + +static struct pinmux_ops sunxi_pmx_ops = { + .get_functions_count = sunxi_pmx_get_funcs_cnt, + .get_function_name = sunxi_pmx_get_func_name, + .get_function_groups = sunxi_pmx_get_func_groups, + .enable = sunxi_pmx_enable, + .gpio_set_direction = sunxi_pmx_gpio_set_direction, +}; + +static struct pinctrl_desc sunxi_pctrl_desc = { + .confops = &sunxi_pconf_ops, + .pctlops = &sunxi_pctrl_ops, + .pmxops = &sunxi_pmx_ops, +}; + +static int sunxi_pinctrl_gpio_request(struct gpio_chip *chip, unsigned offset) +{ + return pinctrl_request_gpio(chip->base + offset); +} + +static void sunxi_pinctrl_gpio_free(struct gpio_chip *chip, unsigned offset) +{ + pinctrl_free_gpio(chip->base + offset); +} + +static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip, + unsigned offset) +{ + return pinctrl_gpio_direction_input(chip->base + offset); +} + +static int sunxi_pinctrl_gpio_get(struct gpio_chip *chip, unsigned offset) +{ + struct sunxi_pinctrl *pctl = dev_get_drvdata(chip->dev); + + u32 reg = sunxi_data_reg(offset); + u8 index = sunxi_data_offset(offset); + u32 val = (readl(pctl->membase + reg) >> index) & DATA_PINS_MASK; + + return val; +} + +static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip, + unsigned offset, int value) +{ + return pinctrl_gpio_direction_output(chip->base + offset); +} + +static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip, + unsigned offset, int value) +{ + struct sunxi_pinctrl *pctl = dev_get_drvdata(chip->dev); + u32 reg = sunxi_data_reg(offset); + u8 index = sunxi_data_offset(offset); + + writel((value & DATA_PINS_MASK) << index, pctl->membase + reg); +} + +static int sunxi_pinctrl_gpio_of_xlate(struct gpio_chip *gc, + const struct of_phandle_args *gpiospec, + u32 *flags) +{ + int pin, base; + + base = PINS_PER_BANK * gpiospec->args[0]; + pin = base + gpiospec->args[1]; + + if (pin > (gc->base + gc->ngpio)) + return -EINVAL; + + if (flags) + *flags = gpiospec->args[2]; + + return pin; +} + +static struct gpio_chip sunxi_pinctrl_gpio_chip = { + .owner = THIS_MODULE, + .request = sunxi_pinctrl_gpio_request, + .free = sunxi_pinctrl_gpio_free, + .direction_input = sunxi_pinctrl_gpio_direction_input, + .direction_output = sunxi_pinctrl_gpio_direction_output, + .get = sunxi_pinctrl_gpio_get, + .set = sunxi_pinctrl_gpio_set, + .of_xlate = sunxi_pinctrl_gpio_of_xlate, + .of_gpio_n_cells = 3, + .can_sleep = 0, +}; + +static struct of_device_id sunxi_pinctrl_match[] = { + { .compatible = "allwinner,sun4i-a10-pinctrl", .data = (void *)&sun4i_a10_pinctrl_data }, + { .compatible = "allwinner,sun5i-a13-pinctrl", .data = (void *)&sun5i_a13_pinctrl_data }, + {} +}; +MODULE_DEVICE_TABLE(of, sunxi_pinctrl_match); + +static int sunxi_pinctrl_add_function(struct sunxi_pinctrl *pctl, + const char *name) +{ + struct sunxi_pinctrl_function *func = pctl->functions; + + while (func->name) { + /* function already there */ + if (strcmp(func->name, name) == 0) { + func->ngroups++; + return -EEXIST; + } + func++; + } + + func->name = name; + func->ngroups = 1; + + pctl->nfunctions++; + + return 0; +} + +static int sunxi_pinctrl_build_state(struct platform_device *pdev) +{ + struct sunxi_pinctrl *pctl = platform_get_drvdata(pdev); + int i; + + pctl->ngroups = pctl->desc->npins; + + /* Allocate groups */ + pctl->groups = devm_kzalloc(&pdev->dev, + pctl->ngroups * sizeof(*pctl->groups), + GFP_KERNEL); + if (!pctl->groups) + return -ENOMEM; + + for (i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + struct sunxi_pinctrl_group *group = pctl->groups + i; + + group->name = pin->pin.name; + group->pin = pin->pin.number; + } + + /* + * We suppose that we won't have any more functions than pins, + * we'll reallocate that later anyway + */ + pctl->functions = devm_kzalloc(&pdev->dev, + pctl->desc->npins * sizeof(*pctl->functions), + GFP_KERNEL); + if (!pctl->functions) + return -ENOMEM; + + /* Count functions and their associated groups */ + for (i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + struct sunxi_desc_function *func = pin->functions; + + while (func->name) { + sunxi_pinctrl_add_function(pctl, func->name); + func++; + } + } + + pctl->functions = krealloc(pctl->functions, + pctl->nfunctions * sizeof(*pctl->functions), + GFP_KERNEL); + + for (i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + struct sunxi_desc_function *func = pin->functions; + + while (func->name) { + struct sunxi_pinctrl_function *func_item; + const char **func_grp; + + func_item = sunxi_pinctrl_find_function_by_name(pctl, + func->name); + if (!func_item) + return -EINVAL; + + if (!func_item->groups) { + func_item->groups = + devm_kzalloc(&pdev->dev, + func_item->ngroups * sizeof(*func_item->groups), + GFP_KERNEL); + if (!func_item->groups) + return -ENOMEM; + } + + func_grp = func_item->groups; + while (*func_grp) + func_grp++; + + *func_grp = pin->pin.name; + func++; + } + } + + return 0; +} + +static int sunxi_pinctrl_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + const struct of_device_id *device; + struct pinctrl_pin_desc *pins; + struct sunxi_pinctrl *pctl; + int i, ret, last_pin; + + pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL); + if (!pctl) + return -ENOMEM; + platform_set_drvdata(pdev, pctl); + + pctl->membase = of_iomap(node, 0); + if (!pctl->membase) + return -ENOMEM; + + device = of_match_device(sunxi_pinctrl_match, &pdev->dev); + if (!device) + return -ENODEV; + + pctl->desc = (struct sunxi_pinctrl_desc *)device->data; + + ret = sunxi_pinctrl_build_state(pdev); + if (ret) { + dev_err(&pdev->dev, "dt probe failed: %d\n", ret); + return ret; + } + + pins = devm_kzalloc(&pdev->dev, + pctl->desc->npins * sizeof(*pins), + GFP_KERNEL); + if (!pins) + return -ENOMEM; + + for (i = 0; i < pctl->desc->npins; i++) + pins[i] = pctl->desc->pins[i].pin; + + sunxi_pctrl_desc.name = dev_name(&pdev->dev); + sunxi_pctrl_desc.owner = THIS_MODULE; + sunxi_pctrl_desc.pins = pins; + sunxi_pctrl_desc.npins = pctl->desc->npins; + pctl->dev = &pdev->dev; + pctl->pctl_dev = pinctrl_register(&sunxi_pctrl_desc, + &pdev->dev, pctl); + if (!pctl->pctl_dev) { + dev_err(&pdev->dev, "couldn't register pinctrl driver\n"); + return -EINVAL; + } + + pctl->chip = devm_kzalloc(&pdev->dev, sizeof(*pctl->chip), GFP_KERNEL); + if (!pctl->chip) { + ret = -ENOMEM; + goto pinctrl_error; + } + + last_pin = pctl->desc->pins[pctl->desc->npins - 1].pin.number; + pctl->chip = &sunxi_pinctrl_gpio_chip; + pctl->chip->ngpio = round_up(last_pin, PINS_PER_BANK); + pctl->chip->label = dev_name(&pdev->dev); + pctl->chip->dev = &pdev->dev; + pctl->chip->base = 0; + + ret = gpiochip_add(pctl->chip); + if (ret) + goto pinctrl_error; + + for (i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + + ret = gpiochip_add_pin_range(pctl->chip, dev_name(&pdev->dev), + pin->pin.number, + pin->pin.number, 1); + if (ret) + goto gpiochip_error; + } + + dev_info(&pdev->dev, "initialized sunXi PIO driver\n"); + + return 0; + +gpiochip_error: + ret = gpiochip_remove(pctl->chip); +pinctrl_error: + pinctrl_unregister(pctl->pctl_dev); + return ret; +} + +static struct platform_driver sunxi_pinctrl_driver = { + .probe = sunxi_pinctrl_probe, + .driver = { + .name = "sunxi-pinctrl", + .owner = THIS_MODULE, + .of_match_table = sunxi_pinctrl_match, + }, +}; +module_platform_driver(sunxi_pinctrl_driver); + +MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com"); +MODULE_DESCRIPTION("Allwinner A1X pinctrl driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pinctrl/pinctrl-sunxi.h b/drivers/pinctrl/pinctrl-sunxi.h new file mode 100644 index 0000000..e921621 --- /dev/null +++ b/drivers/pinctrl/pinctrl-sunxi.h @@ -0,0 +1,478 @@ +/* + * Allwinner A1X SoCs pinctrl driver. + * + * Copyright (C) 2012 Maxime Ripard + * + * Maxime Ripard <maxime.ripard@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef __PINCTRL_SUNXI_H +#define __PINCTRL_SUNXI_H + +#include <linux/kernel.h> + +#define PA_BASE 0 +#define PB_BASE 32 +#define PC_BASE 64 +#define PD_BASE 96 +#define PE_BASE 128 +#define PF_BASE 160 +#define PG_BASE 192 +#define PH_BASE 224 +#define PI_BASE 256 + +#define SUNXI_PINCTRL_PIN_PA0 PINCTRL_PIN(PA_BASE + 0, "PA0") +#define SUNXI_PINCTRL_PIN_PA1 PINCTRL_PIN(PA_BASE + 1, "PA1") +#define SUNXI_PINCTRL_PIN_PA2 PINCTRL_PIN(PA_BASE + 2, "PA2") +#define SUNXI_PINCTRL_PIN_PA3 PINCTRL_PIN(PA_BASE + 3, "PA3") +#define SUNXI_PINCTRL_PIN_PA4 PINCTRL_PIN(PA_BASE + 4, "PA4") +#define SUNXI_PINCTRL_PIN_PA5 PINCTRL_PIN(PA_BASE + 5, "PA5") +#define SUNXI_PINCTRL_PIN_PA6 PINCTRL_PIN(PA_BASE + 6, "PA6") +#define SUNXI_PINCTRL_PIN_PA7 PINCTRL_PIN(PA_BASE + 7, "PA7") +#define SUNXI_PINCTRL_PIN_PA8 PINCTRL_PIN(PA_BASE + 8, "PA8") +#define SUNXI_PINCTRL_PIN_PA9 PINCTRL_PIN(PA_BASE + 9, "PA9") +#define SUNXI_PINCTRL_PIN_PA10 PINCTRL_PIN(PA_BASE + 10, "PA10") +#define SUNXI_PINCTRL_PIN_PA11 PINCTRL_PIN(PA_BASE + 11, "PA11") +#define SUNXI_PINCTRL_PIN_PA12 PINCTRL_PIN(PA_BASE + 12, "PA12") +#define SUNXI_PINCTRL_PIN_PA13 PINCTRL_PIN(PA_BASE + 13, "PA13") +#define SUNXI_PINCTRL_PIN_PA14 PINCTRL_PIN(PA_BASE + 14, "PA14") +#define SUNXI_PINCTRL_PIN_PA15 PINCTRL_PIN(PA_BASE + 15, "PA15") +#define SUNXI_PINCTRL_PIN_PA16 PINCTRL_PIN(PA_BASE + 16, "PA16") +#define SUNXI_PINCTRL_PIN_PA17 PINCTRL_PIN(PA_BASE + 17, "PA17") +#define SUNXI_PINCTRL_PIN_PA18 PINCTRL_PIN(PA_BASE + 18, "PA18") +#define SUNXI_PINCTRL_PIN_PA19 PINCTRL_PIN(PA_BASE + 19, "PA19") +#define SUNXI_PINCTRL_PIN_PA20 PINCTRL_PIN(PA_BASE + 20, "PA20") +#define SUNXI_PINCTRL_PIN_PA21 PINCTRL_PIN(PA_BASE + 21, "PA21") +#define SUNXI_PINCTRL_PIN_PA22 PINCTRL_PIN(PA_BASE + 22, "PA22") +#define SUNXI_PINCTRL_PIN_PA23 PINCTRL_PIN(PA_BASE + 23, "PA23") +#define SUNXI_PINCTRL_PIN_PA24 PINCTRL_PIN(PA_BASE + 24, "PA24") +#define SUNXI_PINCTRL_PIN_PA25 PINCTRL_PIN(PA_BASE + 25, "PA25") +#define SUNXI_PINCTRL_PIN_PA26 PINCTRL_PIN(PA_BASE + 26, "PA26") +#define SUNXI_PINCTRL_PIN_PA27 PINCTRL_PIN(PA_BASE + 27, "PA27") +#define SUNXI_PINCTRL_PIN_PA28 PINCTRL_PIN(PA_BASE + 28, "PA28") +#define SUNXI_PINCTRL_PIN_PA29 PINCTRL_PIN(PA_BASE + 29, "PA29") +#define SUNXI_PINCTRL_PIN_PA30 PINCTRL_PIN(PA_BASE + 30, "PA30") +#define SUNXI_PINCTRL_PIN_PA31 PINCTRL_PIN(PA_BASE + 31, "PA31") + +#define SUNXI_PINCTRL_PIN_PB0 PINCTRL_PIN(PB_BASE + 0, "PB0") +#define SUNXI_PINCTRL_PIN_PB1 PINCTRL_PIN(PB_BASE + 1, "PB1") +#define SUNXI_PINCTRL_PIN_PB2 PINCTRL_PIN(PB_BASE + 2, "PB2") +#define SUNXI_PINCTRL_PIN_PB3 PINCTRL_PIN(PB_BASE + 3, "PB3") +#define SUNXI_PINCTRL_PIN_PB4 PINCTRL_PIN(PB_BASE + 4, "PB4") +#define SUNXI_PINCTRL_PIN_PB5 PINCTRL_PIN(PB_BASE + 5, "PB5") +#define SUNXI_PINCTRL_PIN_PB6 PINCTRL_PIN(PB_BASE + 6, "PB6") +#define SUNXI_PINCTRL_PIN_PB7 PINCTRL_PIN(PB_BASE + 7, "PB7") +#define SUNXI_PINCTRL_PIN_PB8 PINCTRL_PIN(PB_BASE + 8, "PB8") +#define SUNXI_PINCTRL_PIN_PB9 PINCTRL_PIN(PB_BASE + 9, "PB9") +#define SUNXI_PINCTRL_PIN_PB10 PINCTRL_PIN(PB_BASE + 10, "PB10") +#define SUNXI_PINCTRL_PIN_PB11 PINCTRL_PIN(PB_BASE + 11, "PB11") +#define SUNXI_PINCTRL_PIN_PB12 PINCTRL_PIN(PB_BASE + 12, "PB12") +#define SUNXI_PINCTRL_PIN_PB13 PINCTRL_PIN(PB_BASE + 13, "PB13") +#define SUNXI_PINCTRL_PIN_PB14 PINCTRL_PIN(PB_BASE + 14, "PB14") +#define SUNXI_PINCTRL_PIN_PB15 PINCTRL_PIN(PB_BASE + 15, "PB15") +#define SUNXI_PINCTRL_PIN_PB16 PINCTRL_PIN(PB_BASE + 16, "PB16") +#define SUNXI_PINCTRL_PIN_PB17 PINCTRL_PIN(PB_BASE + 17, "PB17") +#define SUNXI_PINCTRL_PIN_PB18 PINCTRL_PIN(PB_BASE + 18, "PB18") +#define SUNXI_PINCTRL_PIN_PB19 PINCTRL_PIN(PB_BASE + 19, "PB19") +#define SUNXI_PINCTRL_PIN_PB20 PINCTRL_PIN(PB_BASE + 20, "PB20") +#define SUNXI_PINCTRL_PIN_PB21 PINCTRL_PIN(PB_BASE + 21, "PB21") +#define SUNXI_PINCTRL_PIN_PB22 PINCTRL_PIN(PB_BASE + 22, "PB22") +#define SUNXI_PINCTRL_PIN_PB23 PINCTRL_PIN(PB_BASE + 23, "PB23") +#define SUNXI_PINCTRL_PIN_PB24 PINCTRL_PIN(PB_BASE + 24, "PB24") +#define SUNXI_PINCTRL_PIN_PB25 PINCTRL_PIN(PB_BASE + 25, "PB25") +#define SUNXI_PINCTRL_PIN_PB26 PINCTRL_PIN(PB_BASE + 26, "PB26") +#define SUNXI_PINCTRL_PIN_PB27 PINCTRL_PIN(PB_BASE + 27, "PB27") +#define SUNXI_PINCTRL_PIN_PB28 PINCTRL_PIN(PB_BASE + 28, "PB28") +#define SUNXI_PINCTRL_PIN_PB29 PINCTRL_PIN(PB_BASE + 29, "PB29") +#define SUNXI_PINCTRL_PIN_PB30 PINCTRL_PIN(PB_BASE + 30, "PB30") +#define SUNXI_PINCTRL_PIN_PB31 PINCTRL_PIN(PB_BASE + 31, "PB31") + +#define SUNXI_PINCTRL_PIN_PC0 PINCTRL_PIN(PC_BASE + 0, "PC0") +#define SUNXI_PINCTRL_PIN_PC1 PINCTRL_PIN(PC_BASE + 1, "PC1") +#define SUNXI_PINCTRL_PIN_PC2 PINCTRL_PIN(PC_BASE + 2, "PC2") +#define SUNXI_PINCTRL_PIN_PC3 PINCTRL_PIN(PC_BASE + 3, "PC3") +#define SUNXI_PINCTRL_PIN_PC4 PINCTRL_PIN(PC_BASE + 4, "PC4") +#define SUNXI_PINCTRL_PIN_PC5 PINCTRL_PIN(PC_BASE + 5, "PC5") +#define SUNXI_PINCTRL_PIN_PC6 PINCTRL_PIN(PC_BASE + 6, "PC6") +#define SUNXI_PINCTRL_PIN_PC7 PINCTRL_PIN(PC_BASE + 7, "PC7") +#define SUNXI_PINCTRL_PIN_PC8 PINCTRL_PIN(PC_BASE + 8, "PC8") +#define SUNXI_PINCTRL_PIN_PC9 PINCTRL_PIN(PC_BASE + 9, "PC9") +#define SUNXI_PINCTRL_PIN_PC10 PINCTRL_PIN(PC_BASE + 10, "PC10") +#define SUNXI_PINCTRL_PIN_PC11 PINCTRL_PIN(PC_BASE + 11, "PC11") +#define SUNXI_PINCTRL_PIN_PC12 PINCTRL_PIN(PC_BASE + 12, "PC12") +#define SUNXI_PINCTRL_PIN_PC13 PINCTRL_PIN(PC_BASE + 13, "PC13") +#define SUNXI_PINCTRL_PIN_PC14 PINCTRL_PIN(PC_BASE + 14, "PC14") +#define SUNXI_PINCTRL_PIN_PC15 PINCTRL_PIN(PC_BASE + 15, "PC15") +#define SUNXI_PINCTRL_PIN_PC16 PINCTRL_PIN(PC_BASE + 16, "PC16") +#define SUNXI_PINCTRL_PIN_PC17 PINCTRL_PIN(PC_BASE + 17, "PC17") +#define SUNXI_PINCTRL_PIN_PC18 PINCTRL_PIN(PC_BASE + 18, "PC18") +#define SUNXI_PINCTRL_PIN_PC19 PINCTRL_PIN(PC_BASE + 19, "PC19") +#define SUNXI_PINCTRL_PIN_PC20 PINCTRL_PIN(PC_BASE + 20, "PC20") +#define SUNXI_PINCTRL_PIN_PC21 PINCTRL_PIN(PC_BASE + 21, "PC21") +#define SUNXI_PINCTRL_PIN_PC22 PINCTRL_PIN(PC_BASE + 22, "PC22") +#define SUNXI_PINCTRL_PIN_PC23 PINCTRL_PIN(PC_BASE + 23, "PC23") +#define SUNXI_PINCTRL_PIN_PC24 PINCTRL_PIN(PC_BASE + 24, "PC24") +#define SUNXI_PINCTRL_PIN_PC25 PINCTRL_PIN(PC_BASE + 25, "PC25") +#define SUNXI_PINCTRL_PIN_PC26 PINCTRL_PIN(PC_BASE + 26, "PC26") +#define SUNXI_PINCTRL_PIN_PC27 PINCTRL_PIN(PC_BASE + 27, "PC27") +#define SUNXI_PINCTRL_PIN_PC28 PINCTRL_PIN(PC_BASE + 28, "PC28") +#define SUNXI_PINCTRL_PIN_PC29 PINCTRL_PIN(PC_BASE + 29, "PC29") +#define SUNXI_PINCTRL_PIN_PC30 PINCTRL_PIN(PC_BASE + 30, "PC30") +#define SUNXI_PINCTRL_PIN_PC31 PINCTRL_PIN(PC_BASE + 31, "PC31") + +#define SUNXI_PINCTRL_PIN_PD0 PINCTRL_PIN(PD_BASE + 0, "PD0") +#define SUNXI_PINCTRL_PIN_PD1 PINCTRL_PIN(PD_BASE + 1, "PD1") +#define SUNXI_PINCTRL_PIN_PD2 PINCTRL_PIN(PD_BASE + 2, "PD2") +#define SUNXI_PINCTRL_PIN_PD3 PINCTRL_PIN(PD_BASE + 3, "PD3") +#define SUNXI_PINCTRL_PIN_PD4 PINCTRL_PIN(PD_BASE + 4, "PD4") +#define SUNXI_PINCTRL_PIN_PD5 PINCTRL_PIN(PD_BASE + 5, "PD5") +#define SUNXI_PINCTRL_PIN_PD6 PINCTRL_PIN(PD_BASE + 6, "PD6") +#define SUNXI_PINCTRL_PIN_PD7 PINCTRL_PIN(PD_BASE + 7, "PD7") +#define SUNXI_PINCTRL_PIN_PD8 PINCTRL_PIN(PD_BASE + 8, "PD8") +#define SUNXI_PINCTRL_PIN_PD9 PINCTRL_PIN(PD_BASE + 9, "PD9") +#define SUNXI_PINCTRL_PIN_PD10 PINCTRL_PIN(PD_BASE + 10, "PD10") +#define SUNXI_PINCTRL_PIN_PD11 PINCTRL_PIN(PD_BASE + 11, "PD11") +#define SUNXI_PINCTRL_PIN_PD12 PINCTRL_PIN(PD_BASE + 12, "PD12") +#define SUNXI_PINCTRL_PIN_PD13 PINCTRL_PIN(PD_BASE + 13, "PD13") +#define SUNXI_PINCTRL_PIN_PD14 PINCTRL_PIN(PD_BASE + 14, "PD14") +#define SUNXI_PINCTRL_PIN_PD15 PINCTRL_PIN(PD_BASE + 15, "PD15") +#define SUNXI_PINCTRL_PIN_PD16 PINCTRL_PIN(PD_BASE + 16, "PD16") +#define SUNXI_PINCTRL_PIN_PD17 PINCTRL_PIN(PD_BASE + 17, "PD17") +#define SUNXI_PINCTRL_PIN_PD18 PINCTRL_PIN(PD_BASE + 18, "PD18") +#define SUNXI_PINCTRL_PIN_PD19 PINCTRL_PIN(PD_BASE + 19, "PD19") +#define SUNXI_PINCTRL_PIN_PD20 PINCTRL_PIN(PD_BASE + 20, "PD20") +#define SUNXI_PINCTRL_PIN_PD21 PINCTRL_PIN(PD_BASE + 21, "PD21") +#define SUNXI_PINCTRL_PIN_PD22 PINCTRL_PIN(PD_BASE + 22, "PD22") +#define SUNXI_PINCTRL_PIN_PD23 PINCTRL_PIN(PD_BASE + 23, "PD23") +#define SUNXI_PINCTRL_PIN_PD24 PINCTRL_PIN(PD_BASE + 24, "PD24") +#define SUNXI_PINCTRL_PIN_PD25 PINCTRL_PIN(PD_BASE + 25, "PD25") +#define SUNXI_PINCTRL_PIN_PD26 PINCTRL_PIN(PD_BASE + 26, "PD26") +#define SUNXI_PINCTRL_PIN_PD27 PINCTRL_PIN(PD_BASE + 27, "PD27") +#define SUNXI_PINCTRL_PIN_PD28 PINCTRL_PIN(PD_BASE + 28, "PD28") +#define SUNXI_PINCTRL_PIN_PD29 PINCTRL_PIN(PD_BASE + 29, "PD29") +#define SUNXI_PINCTRL_PIN_PD30 PINCTRL_PIN(PD_BASE + 30, "PD30") +#define SUNXI_PINCTRL_PIN_PD31 PINCTRL_PIN(PD_BASE + 31, "PD31") + +#define SUNXI_PINCTRL_PIN_PE0 PINCTRL_PIN(PE_BASE + 0, "PE0") +#define SUNXI_PINCTRL_PIN_PE1 PINCTRL_PIN(PE_BASE + 1, "PE1") +#define SUNXI_PINCTRL_PIN_PE2 PINCTRL_PIN(PE_BASE + 2, "PE2") +#define SUNXI_PINCTRL_PIN_PE3 PINCTRL_PIN(PE_BASE + 3, "PE3") +#define SUNXI_PINCTRL_PIN_PE4 PINCTRL_PIN(PE_BASE + 4, "PE4") +#define SUNXI_PINCTRL_PIN_PE5 PINCTRL_PIN(PE_BASE + 5, "PE5") +#define SUNXI_PINCTRL_PIN_PE6 PINCTRL_PIN(PE_BASE + 6, "PE6") +#define SUNXI_PINCTRL_PIN_PE7 PINCTRL_PIN(PE_BASE + 7, "PE7") +#define SUNXI_PINCTRL_PIN_PE8 PINCTRL_PIN(PE_BASE + 8, "PE8") +#define SUNXI_PINCTRL_PIN_PE9 PINCTRL_PIN(PE_BASE + 9, "PE9") +#define SUNXI_PINCTRL_PIN_PE10 PINCTRL_PIN(PE_BASE + 10, "PE10") +#define SUNXI_PINCTRL_PIN_PE11 PINCTRL_PIN(PE_BASE + 11, "PE11") +#define SUNXI_PINCTRL_PIN_PE12 PINCTRL_PIN(PE_BASE + 12, "PE12") +#define SUNXI_PINCTRL_PIN_PE13 PINCTRL_PIN(PE_BASE + 13, "PE13") +#define SUNXI_PINCTRL_PIN_PE14 PINCTRL_PIN(PE_BASE + 14, "PE14") +#define SUNXI_PINCTRL_PIN_PE15 PINCTRL_PIN(PE_BASE + 15, "PE15") +#define SUNXI_PINCTRL_PIN_PE16 PINCTRL_PIN(PE_BASE + 16, "PE16") +#define SUNXI_PINCTRL_PIN_PE17 PINCTRL_PIN(PE_BASE + 17, "PE17") +#define SUNXI_PINCTRL_PIN_PE18 PINCTRL_PIN(PE_BASE + 18, "PE18") +#define SUNXI_PINCTRL_PIN_PE19 PINCTRL_PIN(PE_BASE + 19, "PE19") +#define SUNXI_PINCTRL_PIN_PE20 PINCTRL_PIN(PE_BASE + 20, "PE20") +#define SUNXI_PINCTRL_PIN_PE21 PINCTRL_PIN(PE_BASE + 21, "PE21") +#define SUNXI_PINCTRL_PIN_PE22 PINCTRL_PIN(PE_BASE + 22, "PE22") +#define SUNXI_PINCTRL_PIN_PE23 PINCTRL_PIN(PE_BASE + 23, "PE23") +#define SUNXI_PINCTRL_PIN_PE24 PINCTRL_PIN(PE_BASE + 24, "PE24") +#define SUNXI_PINCTRL_PIN_PE25 PINCTRL_PIN(PE_BASE + 25, "PE25") +#define SUNXI_PINCTRL_PIN_PE26 PINCTRL_PIN(PE_BASE + 26, "PE26") +#define SUNXI_PINCTRL_PIN_PE27 PINCTRL_PIN(PE_BASE + 27, "PE27") +#define SUNXI_PINCTRL_PIN_PE28 PINCTRL_PIN(PE_BASE + 28, "PE28") +#define SUNXI_PINCTRL_PIN_PE29 PINCTRL_PIN(PE_BASE + 29, "PE29") +#define SUNXI_PINCTRL_PIN_PE30 PINCTRL_PIN(PE_BASE + 30, "PE30") +#define SUNXI_PINCTRL_PIN_PE31 PINCTRL_PIN(PE_BASE + 31, "PE31") + +#define SUNXI_PINCTRL_PIN_PF0 PINCTRL_PIN(PF_BASE + 0, "PF0") +#define SUNXI_PINCTRL_PIN_PF1 PINCTRL_PIN(PF_BASE + 1, "PF1") +#define SUNXI_PINCTRL_PIN_PF2 PINCTRL_PIN(PF_BASE + 2, "PF2") +#define SUNXI_PINCTRL_PIN_PF3 PINCTRL_PIN(PF_BASE + 3, "PF3") +#define SUNXI_PINCTRL_PIN_PF4 PINCTRL_PIN(PF_BASE + 4, "PF4") +#define SUNXI_PINCTRL_PIN_PF5 PINCTRL_PIN(PF_BASE + 5, "PF5") +#define SUNXI_PINCTRL_PIN_PF6 PINCTRL_PIN(PF_BASE + 6, "PF6") +#define SUNXI_PINCTRL_PIN_PF7 PINCTRL_PIN(PF_BASE + 7, "PF7") +#define SUNXI_PINCTRL_PIN_PF8 PINCTRL_PIN(PF_BASE + 8, "PF8") +#define SUNXI_PINCTRL_PIN_PF9 PINCTRL_PIN(PF_BASE + 9, "PF9") +#define SUNXI_PINCTRL_PIN_PF10 PINCTRL_PIN(PF_BASE + 10, "PF10") +#define SUNXI_PINCTRL_PIN_PF11 PINCTRL_PIN(PF_BASE + 11, "PF11") +#define SUNXI_PINCTRL_PIN_PF12 PINCTRL_PIN(PF_BASE + 12, "PF12") +#define SUNXI_PINCTRL_PIN_PF13 PINCTRL_PIN(PF_BASE + 13, "PF13") +#define SUNXI_PINCTRL_PIN_PF14 PINCTRL_PIN(PF_BASE + 14, "PF14") +#define SUNXI_PINCTRL_PIN_PF15 PINCTRL_PIN(PF_BASE + 15, "PF15") +#define SUNXI_PINCTRL_PIN_PF16 PINCTRL_PIN(PF_BASE + 16, "PF16") +#define SUNXI_PINCTRL_PIN_PF17 PINCTRL_PIN(PF_BASE + 17, "PF17") +#define SUNXI_PINCTRL_PIN_PF18 PINCTRL_PIN(PF_BASE + 18, "PF18") +#define SUNXI_PINCTRL_PIN_PF19 PINCTRL_PIN(PF_BASE + 19, "PF19") +#define SUNXI_PINCTRL_PIN_PF20 PINCTRL_PIN(PF_BASE + 20, "PF20") +#define SUNXI_PINCTRL_PIN_PF21 PINCTRL_PIN(PF_BASE + 21, "PF21") +#define SUNXI_PINCTRL_PIN_PF22 PINCTRL_PIN(PF_BASE + 22, "PF22") +#define SUNXI_PINCTRL_PIN_PF23 PINCTRL_PIN(PF_BASE + 23, "PF23") +#define SUNXI_PINCTRL_PIN_PF24 PINCTRL_PIN(PF_BASE + 24, "PF24") +#define SUNXI_PINCTRL_PIN_PF25 PINCTRL_PIN(PF_BASE + 25, "PF25") +#define SUNXI_PINCTRL_PIN_PF26 PINCTRL_PIN(PF_BASE + 26, "PF26") +#define SUNXI_PINCTRL_PIN_PF27 PINCTRL_PIN(PF_BASE + 27, "PF27") +#define SUNXI_PINCTRL_PIN_PF28 PINCTRL_PIN(PF_BASE + 28, "PF28") +#define SUNXI_PINCTRL_PIN_PF29 PINCTRL_PIN(PF_BASE + 29, "PF29") +#define SUNXI_PINCTRL_PIN_PF30 PINCTRL_PIN(PF_BASE + 30, "PF30") +#define SUNXI_PINCTRL_PIN_PF31 PINCTRL_PIN(PF_BASE + 31, "PF31") + +#define SUNXI_PINCTRL_PIN_PG0 PINCTRL_PIN(PG_BASE + 0, "PG0") +#define SUNXI_PINCTRL_PIN_PG1 PINCTRL_PIN(PG_BASE + 1, "PG1") +#define SUNXI_PINCTRL_PIN_PG2 PINCTRL_PIN(PG_BASE + 2, "PG2") +#define SUNXI_PINCTRL_PIN_PG3 PINCTRL_PIN(PG_BASE + 3, "PG3") +#define SUNXI_PINCTRL_PIN_PG4 PINCTRL_PIN(PG_BASE + 4, "PG4") +#define SUNXI_PINCTRL_PIN_PG5 PINCTRL_PIN(PG_BASE + 5, "PG5") +#define SUNXI_PINCTRL_PIN_PG6 PINCTRL_PIN(PG_BASE + 6, "PG6") +#define SUNXI_PINCTRL_PIN_PG7 PINCTRL_PIN(PG_BASE + 7, "PG7") +#define SUNXI_PINCTRL_PIN_PG8 PINCTRL_PIN(PG_BASE + 8, "PG8") +#define SUNXI_PINCTRL_PIN_PG9 PINCTRL_PIN(PG_BASE + 9, "PG9") +#define SUNXI_PINCTRL_PIN_PG10 PINCTRL_PIN(PG_BASE + 10, "PG10") +#define SUNXI_PINCTRL_PIN_PG11 PINCTRL_PIN(PG_BASE + 11, "PG11") +#define SUNXI_PINCTRL_PIN_PG12 PINCTRL_PIN(PG_BASE + 12, "PG12") +#define SUNXI_PINCTRL_PIN_PG13 PINCTRL_PIN(PG_BASE + 13, "PG13") +#define SUNXI_PINCTRL_PIN_PG14 PINCTRL_PIN(PG_BASE + 14, "PG14") +#define SUNXI_PINCTRL_PIN_PG15 PINCTRL_PIN(PG_BASE + 15, "PG15") +#define SUNXI_PINCTRL_PIN_PG16 PINCTRL_PIN(PG_BASE + 16, "PG16") +#define SUNXI_PINCTRL_PIN_PG17 PINCTRL_PIN(PG_BASE + 17, "PG17") +#define SUNXI_PINCTRL_PIN_PG18 PINCTRL_PIN(PG_BASE + 18, "PG18") +#define SUNXI_PINCTRL_PIN_PG19 PINCTRL_PIN(PG_BASE + 19, "PG19") +#define SUNXI_PINCTRL_PIN_PG20 PINCTRL_PIN(PG_BASE + 20, "PG20") +#define SUNXI_PINCTRL_PIN_PG21 PINCTRL_PIN(PG_BASE + 21, "PG21") +#define SUNXI_PINCTRL_PIN_PG22 PINCTRL_PIN(PG_BASE + 22, "PG22") +#define SUNXI_PINCTRL_PIN_PG23 PINCTRL_PIN(PG_BASE + 23, "PG23") +#define SUNXI_PINCTRL_PIN_PG24 PINCTRL_PIN(PG_BASE + 24, "PG24") +#define SUNXI_PINCTRL_PIN_PG25 PINCTRL_PIN(PG_BASE + 25, "PG25") +#define SUNXI_PINCTRL_PIN_PG26 PINCTRL_PIN(PG_BASE + 26, "PG26") +#define SUNXI_PINCTRL_PIN_PG27 PINCTRL_PIN(PG_BASE + 27, "PG27") +#define SUNXI_PINCTRL_PIN_PG28 PINCTRL_PIN(PG_BASE + 28, "PG28") +#define SUNXI_PINCTRL_PIN_PG29 PINCTRL_PIN(PG_BASE + 29, "PG29") +#define SUNXI_PINCTRL_PIN_PG30 PINCTRL_PIN(PG_BASE + 30, "PG30") +#define SUNXI_PINCTRL_PIN_PG31 PINCTRL_PIN(PG_BASE + 31, "PG31") + +#define SUNXI_PINCTRL_PIN_PH0 PINCTRL_PIN(PH_BASE + 0, "PH0") +#define SUNXI_PINCTRL_PIN_PH1 PINCTRL_PIN(PH_BASE + 1, "PH1") +#define SUNXI_PINCTRL_PIN_PH2 PINCTRL_PIN(PH_BASE + 2, "PH2") +#define SUNXI_PINCTRL_PIN_PH3 PINCTRL_PIN(PH_BASE + 3, "PH3") +#define SUNXI_PINCTRL_PIN_PH4 PINCTRL_PIN(PH_BASE + 4, "PH4") +#define SUNXI_PINCTRL_PIN_PH5 PINCTRL_PIN(PH_BASE + 5, "PH5") +#define SUNXI_PINCTRL_PIN_PH6 PINCTRL_PIN(PH_BASE + 6, "PH6") +#define SUNXI_PINCTRL_PIN_PH7 PINCTRL_PIN(PH_BASE + 7, "PH7") +#define SUNXI_PINCTRL_PIN_PH8 PINCTRL_PIN(PH_BASE + 8, "PH8") +#define SUNXI_PINCTRL_PIN_PH9 PINCTRL_PIN(PH_BASE + 9, "PH9") +#define SUNXI_PINCTRL_PIN_PH10 PINCTRL_PIN(PH_BASE + 10, "PH10") +#define SUNXI_PINCTRL_PIN_PH11 PINCTRL_PIN(PH_BASE + 11, "PH11") +#define SUNXI_PINCTRL_PIN_PH12 PINCTRL_PIN(PH_BASE + 12, "PH12") +#define SUNXI_PINCTRL_PIN_PH13 PINCTRL_PIN(PH_BASE + 13, "PH13") +#define SUNXI_PINCTRL_PIN_PH14 PINCTRL_PIN(PH_BASE + 14, "PH14") +#define SUNXI_PINCTRL_PIN_PH15 PINCTRL_PIN(PH_BASE + 15, "PH15") +#define SUNXI_PINCTRL_PIN_PH16 PINCTRL_PIN(PH_BASE + 16, "PH16") +#define SUNXI_PINCTRL_PIN_PH17 PINCTRL_PIN(PH_BASE + 17, "PH17") +#define SUNXI_PINCTRL_PIN_PH18 PINCTRL_PIN(PH_BASE + 18, "PH18") +#define SUNXI_PINCTRL_PIN_PH19 PINCTRL_PIN(PH_BASE + 19, "PH19") +#define SUNXI_PINCTRL_PIN_PH20 PINCTRL_PIN(PH_BASE + 20, "PH20") +#define SUNXI_PINCTRL_PIN_PH21 PINCTRL_PIN(PH_BASE + 21, "PH21") +#define SUNXI_PINCTRL_PIN_PH22 PINCTRL_PIN(PH_BASE + 22, "PH22") +#define SUNXI_PINCTRL_PIN_PH23 PINCTRL_PIN(PH_BASE + 23, "PH23") +#define SUNXI_PINCTRL_PIN_PH24 PINCTRL_PIN(PH_BASE + 24, "PH24") +#define SUNXI_PINCTRL_PIN_PH25 PINCTRL_PIN(PH_BASE + 25, "PH25") +#define SUNXI_PINCTRL_PIN_PH26 PINCTRL_PIN(PH_BASE + 26, "PH26") +#define SUNXI_PINCTRL_PIN_PH27 PINCTRL_PIN(PH_BASE + 27, "PH27") +#define SUNXI_PINCTRL_PIN_PH28 PINCTRL_PIN(PH_BASE + 28, "PH28") +#define SUNXI_PINCTRL_PIN_PH29 PINCTRL_PIN(PH_BASE + 29, "PH29") +#define SUNXI_PINCTRL_PIN_PH30 PINCTRL_PIN(PH_BASE + 30, "PH30") +#define SUNXI_PINCTRL_PIN_PH31 PINCTRL_PIN(PH_BASE + 31, "PH31") + +#define SUNXI_PINCTRL_PIN_PI0 PINCTRL_PIN(PI_BASE + 0, "PI0") +#define SUNXI_PINCTRL_PIN_PI1 PINCTRL_PIN(PI_BASE + 1, "PI1") +#define SUNXI_PINCTRL_PIN_PI2 PINCTRL_PIN(PI_BASE + 2, "PI2") +#define SUNXI_PINCTRL_PIN_PI3 PINCTRL_PIN(PI_BASE + 3, "PI3") +#define SUNXI_PINCTRL_PIN_PI4 PINCTRL_PIN(PI_BASE + 4, "PI4") +#define SUNXI_PINCTRL_PIN_PI5 PINCTRL_PIN(PI_BASE + 5, "PI5") +#define SUNXI_PINCTRL_PIN_PI6 PINCTRL_PIN(PI_BASE + 6, "PI6") +#define SUNXI_PINCTRL_PIN_PI7 PINCTRL_PIN(PI_BASE + 7, "PI7") +#define SUNXI_PINCTRL_PIN_PI8 PINCTRL_PIN(PI_BASE + 8, "PI8") +#define SUNXI_PINCTRL_PIN_PI9 PINCTRL_PIN(PI_BASE + 9, "PI9") +#define SUNXI_PINCTRL_PIN_PI10 PINCTRL_PIN(PI_BASE + 10, "PI10") +#define SUNXI_PINCTRL_PIN_PI11 PINCTRL_PIN(PI_BASE + 11, "PI11") +#define SUNXI_PINCTRL_PIN_PI12 PINCTRL_PIN(PI_BASE + 12, "PI12") +#define SUNXI_PINCTRL_PIN_PI13 PINCTRL_PIN(PI_BASE + 13, "PI13") +#define SUNXI_PINCTRL_PIN_PI14 PINCTRL_PIN(PI_BASE + 14, "PI14") +#define SUNXI_PINCTRL_PIN_PI15 PINCTRL_PIN(PI_BASE + 15, "PI15") +#define SUNXI_PINCTRL_PIN_PI16 PINCTRL_PIN(PI_BASE + 16, "PI16") +#define SUNXI_PINCTRL_PIN_PI17 PINCTRL_PIN(PI_BASE + 17, "PI17") +#define SUNXI_PINCTRL_PIN_PI18 PINCTRL_PIN(PI_BASE + 18, "PI18") +#define SUNXI_PINCTRL_PIN_PI19 PINCTRL_PIN(PI_BASE + 19, "PI19") +#define SUNXI_PINCTRL_PIN_PI20 PINCTRL_PIN(PI_BASE + 20, "PI20") +#define SUNXI_PINCTRL_PIN_PI21 PINCTRL_PIN(PI_BASE + 21, "PI21") +#define SUNXI_PINCTRL_PIN_PI22 PINCTRL_PIN(PI_BASE + 22, "PI22") +#define SUNXI_PINCTRL_PIN_PI23 PINCTRL_PIN(PI_BASE + 23, "PI23") +#define SUNXI_PINCTRL_PIN_PI24 PINCTRL_PIN(PI_BASE + 24, "PI24") +#define SUNXI_PINCTRL_PIN_PI25 PINCTRL_PIN(PI_BASE + 25, "PI25") +#define SUNXI_PINCTRL_PIN_PI26 PINCTRL_PIN(PI_BASE + 26, "PI26") +#define SUNXI_PINCTRL_PIN_PI27 PINCTRL_PIN(PI_BASE + 27, "PI27") +#define SUNXI_PINCTRL_PIN_PI28 PINCTRL_PIN(PI_BASE + 28, "PI28") +#define SUNXI_PINCTRL_PIN_PI29 PINCTRL_PIN(PI_BASE + 29, "PI29") +#define SUNXI_PINCTRL_PIN_PI30 PINCTRL_PIN(PI_BASE + 30, "PI30") +#define SUNXI_PINCTRL_PIN_PI31 PINCTRL_PIN(PI_BASE + 31, "PI31") + +#define SUNXI_PIN_NAME_MAX_LEN 5 + +#define BANK_MEM_SIZE 0x24 +#define MUX_REGS_OFFSET 0x0 +#define DATA_REGS_OFFSET 0x10 +#define DLEVEL_REGS_OFFSET 0x14 +#define PULL_REGS_OFFSET 0x1c + +#define PINS_PER_BANK 32 +#define MUX_PINS_PER_REG 8 +#define MUX_PINS_BITS 4 +#define MUX_PINS_MASK 0x0f +#define DATA_PINS_PER_REG 32 +#define DATA_PINS_BITS 1 +#define DATA_PINS_MASK 0x01 +#define DLEVEL_PINS_PER_REG 16 +#define DLEVEL_PINS_BITS 2 +#define DLEVEL_PINS_MASK 0x03 +#define PULL_PINS_PER_REG 16 +#define PULL_PINS_BITS 2 +#define PULL_PINS_MASK 0x03 + +struct sunxi_desc_function { + const char *name; + u8 muxval; +}; + +struct sunxi_desc_pin { + struct pinctrl_pin_desc pin; + struct sunxi_desc_function *functions; +}; + +struct sunxi_pinctrl_desc { + const struct sunxi_desc_pin *pins; + int npins; + struct pinctrl_gpio_range *ranges; + int nranges; +}; + +struct sunxi_pinctrl_function { + const char *name; + const char **groups; + unsigned ngroups; +}; + +struct sunxi_pinctrl_group { + const char *name; + unsigned long config; + unsigned pin; +}; + +struct sunxi_pinctrl { + void __iomem *membase; + struct gpio_chip *chip; + struct sunxi_pinctrl_desc *desc; + struct device *dev; + struct sunxi_pinctrl_function *functions; + unsigned nfunctions; + struct sunxi_pinctrl_group *groups; + unsigned ngroups; + struct pinctrl_dev *pctl_dev; +}; + +#define SUNXI_PIN(_pin, ...) \ + { \ + .pin = _pin, \ + .functions = (struct sunxi_desc_function[]){ \ + __VA_ARGS__, { } }, \ + } + +#define SUNXI_FUNCTION(_val, _name) \ + { \ + .name = _name, \ + .muxval = _val, \ + } + +/* + * The sunXi PIO registers are organized as is: + * 0x00 - 0x0c Muxing values. + * 8 pins per register, each pin having a 4bits value + * 0x10 Pin values + * 32 bits per register, each pin corresponding to one bit + * 0x14 - 0x18 Drive level + * 16 pins per register, each pin having a 2bits value + * 0x1c - 0x20 Pull-Up values + * 16 pins per register, each pin having a 2bits value + * + * This is for the first bank. Each bank will have the same layout, + * with an offset being a multiple of 0x24. + * + * The following functions calculate from the pin number the register + * and the bit offset that we should access. + */ +static inline u32 sunxi_mux_reg(u16 pin) +{ + u8 bank = pin / PINS_PER_BANK; + u32 offset = bank * BANK_MEM_SIZE; + offset += MUX_REGS_OFFSET; + offset += pin % PINS_PER_BANK / MUX_PINS_PER_REG * 0x04; + return round_down(offset, 4); +} + +static inline u32 sunxi_mux_offset(u16 pin) +{ + u32 pin_num = pin % MUX_PINS_PER_REG; + return pin_num * MUX_PINS_BITS; +} + +static inline u32 sunxi_data_reg(u16 pin) +{ + u8 bank = pin / PINS_PER_BANK; + u32 offset = bank * BANK_MEM_SIZE; + offset += DATA_REGS_OFFSET; + offset += pin % PINS_PER_BANK / DATA_PINS_PER_REG * 0x04; + return round_down(offset, 4); +} + +static inline u32 sunxi_data_offset(u16 pin) +{ + u32 pin_num = pin % DATA_PINS_PER_REG; + return pin_num * DATA_PINS_BITS; +} + +static inline u32 sunxi_dlevel_reg(u16 pin) +{ + u8 bank = pin / PINS_PER_BANK; + u32 offset = bank * BANK_MEM_SIZE; + offset += DLEVEL_REGS_OFFSET; + offset += pin % PINS_PER_BANK / DLEVEL_PINS_PER_REG * 0x04; + return round_down(offset, 4); +} + +static inline u32 sunxi_dlevel_offset(u16 pin) +{ + u32 pin_num = pin % DLEVEL_PINS_PER_REG; + return pin_num * DLEVEL_PINS_BITS; +} + +static inline u32 sunxi_pull_reg(u16 pin) +{ + u8 bank = pin / PINS_PER_BANK; + u32 offset = bank * BANK_MEM_SIZE; + offset += PULL_REGS_OFFSET; + offset += pin % PINS_PER_BANK / PULL_PINS_PER_REG * 0x04; + return round_down(offset, 4); +} + +static inline u32 sunxi_pull_offset(u16 pin) +{ + u32 pin_num = pin % PULL_PINS_PER_REG; + return pin_num * PULL_PINS_BITS; +} + +#endif /* __PINCTRL_SUNXI_H */ diff --git a/drivers/pinctrl/pinctrl-tegra.c b/drivers/pinctrl/pinctrl-tegra.c index ae1e4bb..f195d77 100644 --- a/drivers/pinctrl/pinctrl-tegra.c +++ b/drivers/pinctrl/pinctrl-tegra.c @@ -201,6 +201,7 @@ static const struct cfg_param { {"nvidia,open-drain", TEGRA_PINCONF_PARAM_OPEN_DRAIN}, {"nvidia,lock", TEGRA_PINCONF_PARAM_LOCK}, {"nvidia,io-reset", TEGRA_PINCONF_PARAM_IORESET}, + {"nvidia,rcv-sel", TEGRA_PINCONF_PARAM_RCV_SEL}, {"nvidia,high-speed-mode", TEGRA_PINCONF_PARAM_HIGH_SPEED_MODE}, {"nvidia,schmitt", TEGRA_PINCONF_PARAM_SCHMITT}, {"nvidia,low-power-mode", TEGRA_PINCONF_PARAM_LOW_POWER_MODE}, @@ -208,6 +209,7 @@ static const struct cfg_param { {"nvidia,pull-up-strength", TEGRA_PINCONF_PARAM_DRIVE_UP_STRENGTH}, {"nvidia,slew-rate-falling", TEGRA_PINCONF_PARAM_SLEW_RATE_FALLING}, {"nvidia,slew-rate-rising", TEGRA_PINCONF_PARAM_SLEW_RATE_RISING}, + {"nvidia,drive-type", TEGRA_PINCONF_PARAM_DRIVE_TYPE}, }; static int tegra_pinctrl_dt_subnode_to_map(struct device *dev, @@ -450,6 +452,12 @@ static int tegra_pinconf_reg(struct tegra_pmx *pmx, *bit = g->ioreset_bit; *width = 1; break; + case TEGRA_PINCONF_PARAM_RCV_SEL: + *bank = g->rcv_sel_bank; + *reg = g->rcv_sel_reg; + *bit = g->rcv_sel_bit; + *width = 1; + break; case TEGRA_PINCONF_PARAM_HIGH_SPEED_MODE: *bank = g->drv_bank; *reg = g->drv_reg; @@ -492,6 +500,12 @@ static int tegra_pinconf_reg(struct tegra_pmx *pmx, *bit = g->slwr_bit; *width = g->slwr_width; break; + case TEGRA_PINCONF_PARAM_DRIVE_TYPE: + *bank = g->drvtype_bank; + *reg = g->drvtype_reg; + *bit = g->drvtype_bit; + *width = 2; + break; default: dev_err(pmx->dev, "Invalid config param %04x\n", param); return -ENOTSUPP; diff --git a/drivers/pinctrl/pinctrl-tegra.h b/drivers/pinctrl/pinctrl-tegra.h index 62e3809..817f706 100644 --- a/drivers/pinctrl/pinctrl-tegra.h +++ b/drivers/pinctrl/pinctrl-tegra.h @@ -30,6 +30,8 @@ enum tegra_pinconf_param { /* argument: Boolean */ TEGRA_PINCONF_PARAM_IORESET, /* argument: Boolean */ + TEGRA_PINCONF_PARAM_RCV_SEL, + /* argument: Boolean */ TEGRA_PINCONF_PARAM_HIGH_SPEED_MODE, /* argument: Boolean */ TEGRA_PINCONF_PARAM_SCHMITT, @@ -43,6 +45,8 @@ enum tegra_pinconf_param { TEGRA_PINCONF_PARAM_SLEW_RATE_FALLING, /* argument: Integer, range is HW-dependant */ TEGRA_PINCONF_PARAM_SLEW_RATE_RISING, + /* argument: Integer, range is HW-dependant */ + TEGRA_PINCONF_PARAM_DRIVE_TYPE, }; enum tegra_pinconf_pull { @@ -95,6 +99,9 @@ struct tegra_function { * @ioreset_reg: IO reset register offset. -1 if unsupported. * @ioreset_bank: IO reset register bank. 0 if unsupported. * @ioreset_bit: IO reset register bit. 0 if unsupported. + * @rcv_sel_reg: Receiver select offset. -1 if unsupported. + * @rcv_sel_bank: Receiver select bank. 0 if unsupported. + * @rcv_sel_bit: Receiver select bit. 0 if unsupported. * @drv_reg: Drive fields register offset. -1 if unsupported. * This register contains the hsm, schmitt, lpmd, drvdn, * drvup, slwr, and slwf parameters. @@ -110,6 +117,9 @@ struct tegra_function { * @slwr_width: Slew Rising field width. 0 if unsupported. * @slwf_bit: Slew Falling register bit. 0 if unsupported. * @slwf_width: Slew Falling field width. 0 if unsupported. + * @drvtype_reg: Drive type fields register offset. -1 if unsupported. + * @drvtype_bank: Drive type fields register bank. 0 if unsupported. + * @drvtype_bit: Drive type register bit. 0 if unsupported. * * A representation of a group of pins (possibly just one pin) in the Tegra * pin controller. Each group allows some parameter or parameters to be @@ -131,15 +141,19 @@ struct tegra_pingroup { s16 odrain_reg; s16 lock_reg; s16 ioreset_reg; + s16 rcv_sel_reg; s16 drv_reg; + s16 drvtype_reg; u32 mux_bank:2; u32 pupd_bank:2; u32 tri_bank:2; u32 einput_bank:2; u32 odrain_bank:2; u32 ioreset_bank:2; + u32 rcv_sel_bank:2; u32 lock_bank:2; u32 drv_bank:2; + u32 drvtype_bank:2; u32 mux_bit:5; u32 pupd_bit:5; u32 tri_bit:5; @@ -147,6 +161,7 @@ struct tegra_pingroup { u32 odrain_bit:5; u32 lock_bit:5; u32 ioreset_bit:5; + u32 rcv_sel_bit:5; u32 hsm_bit:5; u32 schmitt_bit:5; u32 lpmd_bit:5; @@ -154,6 +169,7 @@ struct tegra_pingroup { u32 drvup_bit:5; u32 slwr_bit:5; u32 slwf_bit:5; + u32 drvtype_bit:5; u32 drvdn_width:6; u32 drvup_width:6; u32 slwr_width:6; diff --git a/drivers/pinctrl/pinctrl-tegra114.c b/drivers/pinctrl/pinctrl-tegra114.c new file mode 100644 index 0000000..622c485 --- /dev/null +++ b/drivers/pinctrl/pinctrl-tegra114.c @@ -0,0 +1,2769 @@ +/* + * Pinctrl data and driver for the NVIDIA Tegra114 pinmux + * + * Copyright (c) 2012-2013, NVIDIA CORPORATION. All rights reserved. + * + * Arthur: Pritesh Raithatha <praithatha@nvidia.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/pinctrl/pinmux.h> + +#include "pinctrl-tegra.h" + +/* + * Most pins affected by the pinmux can also be GPIOs. Define these first. + * These must match how the GPIO driver names/numbers its pins. + */ +#define _GPIO(offset) (offset) + +#define TEGRA_PIN_CLK_32K_OUT_PA0 _GPIO(0) +#define TEGRA_PIN_UART3_CTS_N_PA1 _GPIO(1) +#define TEGRA_PIN_DAP2_FS_PA2 _GPIO(2) +#define TEGRA_PIN_DAP2_SCLK_PA3 _GPIO(3) +#define TEGRA_PIN_DAP2_DIN_PA4 _GPIO(4) +#define TEGRA_PIN_DAP2_DOUT_PA5 _GPIO(5) +#define TEGRA_PIN_SDMMC3_CLK_PA6 _GPIO(6) +#define TEGRA_PIN_SDMMC3_CMD_PA7 _GPIO(7) +#define TEGRA_PIN_GMI_A17_PB0 _GPIO(8) +#define TEGRA_PIN_GMI_A18_PB1 _GPIO(9) +#define TEGRA_PIN_SDMMC3_DAT3_PB4 _GPIO(12) +#define TEGRA_PIN_SDMMC3_DAT2_PB5 _GPIO(13) +#define TEGRA_PIN_SDMMC3_DAT1_PB6 _GPIO(14) +#define TEGRA_PIN_SDMMC3_DAT0_PB7 _GPIO(15) +#define TEGRA_PIN_UART3_RTS_N_PC0 _GPIO(16) +#define TEGRA_PIN_UART2_TXD_PC2 _GPIO(18) +#define TEGRA_PIN_UART2_RXD_PC3 _GPIO(19) +#define TEGRA_PIN_GEN1_I2C_SCL_PC4 _GPIO(20) +#define TEGRA_PIN_GEN1_I2C_SDA_PC5 _GPIO(21) +#define TEGRA_PIN_GMI_WP_N_PC7 _GPIO(23) +#define TEGRA_PIN_GMI_AD0_PG0 _GPIO(48) +#define TEGRA_PIN_GMI_AD1_PG1 _GPIO(49) +#define TEGRA_PIN_GMI_AD2_PG2 _GPIO(50) +#define TEGRA_PIN_GMI_AD3_PG3 _GPIO(51) +#define TEGRA_PIN_GMI_AD4_PG4 _GPIO(52) +#define TEGRA_PIN_GMI_AD5_PG5 _GPIO(53) +#define TEGRA_PIN_GMI_AD6_PG6 _GPIO(54) +#define TEGRA_PIN_GMI_AD7_PG7 _GPIO(55) +#define TEGRA_PIN_GMI_AD8_PH0 _GPIO(56) +#define TEGRA_PIN_GMI_AD9_PH1 _GPIO(57) +#define TEGRA_PIN_GMI_AD10_PH2 _GPIO(58) +#define TEGRA_PIN_GMI_AD11_PH3 _GPIO(59) +#define TEGRA_PIN_GMI_AD12_PH4 _GPIO(60) +#define TEGRA_PIN_GMI_AD13_PH5 _GPIO(61) +#define TEGRA_PIN_GMI_AD14_PH6 _GPIO(62) +#define TEGRA_PIN_GMI_AD15_PH7 _GPIO(63) +#define TEGRA_PIN_GMI_WR_N_PI0 _GPIO(64) +#define TEGRA_PIN_GMI_OE_N_PI1 _GPIO(65) +#define TEGRA_PIN_GMI_CS6_N_PI3 _GPIO(67) +#define TEGRA_PIN_GMI_RST_N_PI4 _GPIO(68) +#define TEGRA_PIN_GMI_IORDY_PI5 _GPIO(69) +#define TEGRA_PIN_GMI_CS7_N_PI6 _GPIO(70) +#define TEGRA_PIN_GMI_WAIT_PI7 _GPIO(71) +#define TEGRA_PIN_GMI_CS0_N_PJ0 _GPIO(72) +#define TEGRA_PIN_GMI_CS1_N_PJ2 _GPIO(74) +#define TEGRA_PIN_GMI_DQS_P_PJ3 _GPIO(75) +#define TEGRA_PIN_UART2_CTS_N_PJ5 _GPIO(77) +#define TEGRA_PIN_UART2_RTS_N_PJ6 _GPIO(78) +#define TEGRA_PIN_GMI_A16_PJ7 _GPIO(79) +#define TEGRA_PIN_GMI_ADV_N_PK0 _GPIO(80) +#define TEGRA_PIN_GMI_CLK_PK1 _GPIO(81) +#define TEGRA_PIN_GMI_CS4_N_PK2 _GPIO(82) +#define TEGRA_PIN_GMI_CS2_N_PK3 _GPIO(83) +#define TEGRA_PIN_GMI_CS3_N_PK4 _GPIO(84) +#define TEGRA_PIN_SPDIF_OUT_PK5 _GPIO(85) +#define TEGRA_PIN_SPDIF_IN_PK6 _GPIO(86) +#define TEGRA_PIN_GMI_A19_PK7 _GPIO(87) +#define TEGRA_PIN_DAP1_FS_PN0 _GPIO(104) +#define TEGRA_PIN_DAP1_DIN_PN1 _GPIO(105) +#define TEGRA_PIN_DAP1_DOUT_PN2 _GPIO(106) +#define TEGRA_PIN_DAP1_SCLK_PN3 _GPIO(107) +#define TEGRA_PIN_USB_VBUS_EN0_PN4 _GPIO(108) +#define TEGRA_PIN_USB_VBUS_EN1_PN5 _GPIO(109) +#define TEGRA_PIN_HDMI_INT_PN7 _GPIO(111) +#define TEGRA_PIN_ULPI_DATA7_PO0 _GPIO(112) +#define TEGRA_PIN_ULPI_DATA0_PO1 _GPIO(113) +#define TEGRA_PIN_ULPI_DATA1_PO2 _GPIO(114) +#define TEGRA_PIN_ULPI_DATA2_PO3 _GPIO(115) +#define TEGRA_PIN_ULPI_DATA3_PO4 _GPIO(116) +#define TEGRA_PIN_ULPI_DATA4_PO5 _GPIO(117) +#define TEGRA_PIN_ULPI_DATA5_PO6 _GPIO(118) +#define TEGRA_PIN_ULPI_DATA6_PO7 _GPIO(119) +#define TEGRA_PIN_DAP3_FS_PP0 _GPIO(120) +#define TEGRA_PIN_DAP3_DIN_PP1 _GPIO(121) +#define TEGRA_PIN_DAP3_DOUT_PP2 _GPIO(122) +#define TEGRA_PIN_DAP3_SCLK_PP3 _GPIO(123) +#define TEGRA_PIN_DAP4_FS_PP4 _GPIO(124) +#define TEGRA_PIN_DAP4_DIN_PP5 _GPIO(125) +#define TEGRA_PIN_DAP4_DOUT_PP6 _GPIO(126) +#define TEGRA_PIN_DAP4_SCLK_PP7 _GPIO(127) +#define TEGRA_PIN_KB_COL0_PQ0 _GPIO(128) +#define TEGRA_PIN_KB_COL1_PQ1 _GPIO(129) +#define TEGRA_PIN_KB_COL2_PQ2 _GPIO(130) +#define TEGRA_PIN_KB_COL3_PQ3 _GPIO(131) +#define TEGRA_PIN_KB_COL4_PQ4 _GPIO(132) +#define TEGRA_PIN_KB_COL5_PQ5 _GPIO(133) +#define TEGRA_PIN_KB_COL6_PQ6 _GPIO(134) +#define TEGRA_PIN_KB_COL7_PQ7 _GPIO(135) +#define TEGRA_PIN_KB_ROW0_PR0 _GPIO(136) +#define TEGRA_PIN_KB_ROW1_PR1 _GPIO(137) +#define TEGRA_PIN_KB_ROW2_PR2 _GPIO(138) +#define TEGRA_PIN_KB_ROW3_PR3 _GPIO(139) +#define TEGRA_PIN_KB_ROW4_PR4 _GPIO(140) +#define TEGRA_PIN_KB_ROW5_PR5 _GPIO(141) +#define TEGRA_PIN_KB_ROW6_PR6 _GPIO(142) +#define TEGRA_PIN_KB_ROW7_PR7 _GPIO(143) +#define TEGRA_PIN_KB_ROW8_PS0 _GPIO(144) +#define TEGRA_PIN_KB_ROW9_PS1 _GPIO(145) +#define TEGRA_PIN_KB_ROW10_PS2 _GPIO(146) +#define TEGRA_PIN_GEN2_I2C_SCL_PT5 _GPIO(157) +#define TEGRA_PIN_GEN2_I2C_SDA_PT6 _GPIO(158) +#define TEGRA_PIN_SDMMC4_CMD_PT7 _GPIO(159) +#define TEGRA_PIN_PU0 _GPIO(160) +#define TEGRA_PIN_PU1 _GPIO(161) +#define TEGRA_PIN_PU2 _GPIO(162) +#define TEGRA_PIN_PU3 _GPIO(163) +#define TEGRA_PIN_PU4 _GPIO(164) +#define TEGRA_PIN_PU5 _GPIO(165) +#define TEGRA_PIN_PU6 _GPIO(166) +#define TEGRA_PIN_PV0 _GPIO(168) +#define TEGRA_PIN_PV1 _GPIO(169) +#define TEGRA_PIN_SDMMC3_CD_N_PV2 _GPIO(170) +#define TEGRA_PIN_SDMMC1_WP_N_PV3 _GPIO(171) +#define TEGRA_PIN_DDC_SCL_PV4 _GPIO(172) +#define TEGRA_PIN_DDC_SDA_PV5 _GPIO(173) +#define TEGRA_PIN_GPIO_W2_AUD_PW2 _GPIO(178) +#define TEGRA_PIN_GPIO_W3_AUD_PW3 _GPIO(179) +#define TEGRA_PIN_CLK1_OUT_PW4 _GPIO(180) +#define TEGRA_PIN_CLK2_OUT_PW5 _GPIO(181) +#define TEGRA_PIN_UART3_TXD_PW6 _GPIO(182) +#define TEGRA_PIN_UART3_RXD_PW7 _GPIO(183) +#define TEGRA_PIN_DVFS_PWM_PX0 _GPIO(184) +#define TEGRA_PIN_GPIO_X1_AUD_PX1 _GPIO(185) +#define TEGRA_PIN_DVFS_CLK_PX2 _GPIO(186) +#define TEGRA_PIN_GPIO_X3_AUD_PX3 _GPIO(187) +#define TEGRA_PIN_GPIO_X4_AUD_PX4 _GPIO(188) +#define TEGRA_PIN_GPIO_X5_AUD_PX5 _GPIO(189) +#define TEGRA_PIN_GPIO_X6_AUD_PX6 _GPIO(190) +#define TEGRA_PIN_GPIO_X7_AUD_PX7 _GPIO(191) +#define TEGRA_PIN_ULPI_CLK_PY0 _GPIO(192) +#define TEGRA_PIN_ULPI_DIR_PY1 _GPIO(193) +#define TEGRA_PIN_ULPI_NXT_PY2 _GPIO(194) +#define TEGRA_PIN_ULPI_STP_PY3 _GPIO(195) +#define TEGRA_PIN_SDMMC1_DAT3_PY4 _GPIO(196) +#define TEGRA_PIN_SDMMC1_DAT2_PY5 _GPIO(197) +#define TEGRA_PIN_SDMMC1_DAT1_PY6 _GPIO(198) +#define TEGRA_PIN_SDMMC1_DAT0_PY7 _GPIO(199) +#define TEGRA_PIN_SDMMC1_CLK_PZ0 _GPIO(200) +#define TEGRA_PIN_SDMMC1_CMD_PZ1 _GPIO(201) +#define TEGRA_PIN_SYS_CLK_REQ_PZ5 _GPIO(205) +#define TEGRA_PIN_PWR_I2C_SCL_PZ6 _GPIO(206) +#define TEGRA_PIN_PWR_I2C_SDA_PZ7 _GPIO(207) +#define TEGRA_PIN_SDMMC4_DAT0_PAA0 _GPIO(208) +#define TEGRA_PIN_SDMMC4_DAT1_PAA1 _GPIO(209) +#define TEGRA_PIN_SDMMC4_DAT2_PAA2 _GPIO(210) +#define TEGRA_PIN_SDMMC4_DAT3_PAA3 _GPIO(211) +#define TEGRA_PIN_SDMMC4_DAT4_PAA4 _GPIO(212) +#define TEGRA_PIN_SDMMC4_DAT5_PAA5 _GPIO(213) +#define TEGRA_PIN_SDMMC4_DAT6_PAA6 _GPIO(214) +#define TEGRA_PIN_SDMMC4_DAT7_PAA7 _GPIO(215) +#define TEGRA_PIN_PBB0 _GPIO(216) +#define TEGRA_PIN_CAM_I2C_SCL_PBB1 _GPIO(217) +#define TEGRA_PIN_CAM_I2C_SDA_PBB2 _GPIO(218) +#define TEGRA_PIN_PBB3 _GPIO(219) +#define TEGRA_PIN_PBB4 _GPIO(220) +#define TEGRA_PIN_PBB5 _GPIO(221) +#define TEGRA_PIN_PBB6 _GPIO(222) +#define TEGRA_PIN_PBB7 _GPIO(223) +#define TEGRA_PIN_CAM_MCLK_PCC0 _GPIO(224) +#define TEGRA_PIN_PCC1 _GPIO(225) +#define TEGRA_PIN_PCC2 _GPIO(226) +#define TEGRA_PIN_SDMMC4_CLK_PCC4 _GPIO(228) +#define TEGRA_PIN_CLK2_REQ_PCC5 _GPIO(229) +#define TEGRA_PIN_CLK3_OUT_PEE0 _GPIO(240) +#define TEGRA_PIN_CLK3_REQ_PEE1 _GPIO(241) +#define TEGRA_PIN_CLK1_REQ_PEE2 _GPIO(242) +#define TEGRA_PIN_HDMI_CEC_PEE3 _GPIO(243) +#define TEGRA_PIN_SDMMC3_CLK_LB_OUT_PEE4 _GPIO(244) +#define TEGRA_PIN_SDMMC3_CLK_LB_IN_PEE5 _GPIO(245) + +/* All non-GPIO pins follow */ +#define NUM_GPIOS (TEGRA_PIN_SDMMC3_CLK_LB_IN_PEE5 + 1) +#define _PIN(offset) (NUM_GPIOS + (offset)) + +/* Non-GPIO pins */ +#define TEGRA_PIN_CORE_PWR_REQ _PIN(0) +#define TEGRA_PIN_CPU_PWR_REQ _PIN(1) +#define TEGRA_PIN_PWR_INT_N _PIN(2) +#define TEGRA_PIN_RESET_OUT_N _PIN(3) +#define TEGRA_PIN_OWR _PIN(4) + +static const struct pinctrl_pin_desc tegra114_pins[] = { + PINCTRL_PIN(TEGRA_PIN_CLK_32K_OUT_PA0, "CLK_32K_OUT PA0"), + PINCTRL_PIN(TEGRA_PIN_UART3_CTS_N_PA1, "UART3_CTS_N PA1"), + PINCTRL_PIN(TEGRA_PIN_DAP2_FS_PA2, "DAP2_FS PA2"), + PINCTRL_PIN(TEGRA_PIN_DAP2_SCLK_PA3, "DAP2_SCLK PA3"), + PINCTRL_PIN(TEGRA_PIN_DAP2_DIN_PA4, "DAP2_DIN PA4"), + PINCTRL_PIN(TEGRA_PIN_DAP2_DOUT_PA5, "DAP2_DOUT PA5"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_CLK_PA6, "SDMMC3_CLK PA6"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_CMD_PA7, "SDMMC3_CMD PA7"), + PINCTRL_PIN(TEGRA_PIN_GMI_A17_PB0, "GMI_A17 PB0"), + PINCTRL_PIN(TEGRA_PIN_GMI_A18_PB1, "GMI_A18 PB1"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_DAT3_PB4, "SDMMC3_DAT3 PB4"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_DAT2_PB5, "SDMMC3_DAT2 PB5"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_DAT1_PB6, "SDMMC3_DAT1 PB6"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_DAT0_PB7, "SDMMC3_DAT0 PB7"), + PINCTRL_PIN(TEGRA_PIN_UART3_RTS_N_PC0, "UART3_RTS_N PC0"), + PINCTRL_PIN(TEGRA_PIN_UART2_TXD_PC2, "UART2_TXD PC2"), + PINCTRL_PIN(TEGRA_PIN_UART2_RXD_PC3, "UART2_RXD PC3"), + PINCTRL_PIN(TEGRA_PIN_GEN1_I2C_SCL_PC4, "GEN1_I2C_SCL PC4"), + PINCTRL_PIN(TEGRA_PIN_GEN1_I2C_SDA_PC5, "GEN1_I2C_SDA PC5"), + PINCTRL_PIN(TEGRA_PIN_GMI_WP_N_PC7, "GMI_WP_N PC7"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD0_PG0, "GMI_AD0 PG0"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD1_PG1, "GMI_AD1 PG1"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD2_PG2, "GMI_AD2 PG2"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD3_PG3, "GMI_AD3 PG3"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD4_PG4, "GMI_AD4 PG4"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD5_PG5, "GMI_AD5 PG5"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD6_PG6, "GMI_AD6 PG6"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD7_PG7, "GMI_AD7 PG7"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD8_PH0, "GMI_AD8 PH0"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD9_PH1, "GMI_AD9 PH1"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD10_PH2, "GMI_AD10 PH2"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD11_PH3, "GMI_AD11 PH3"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD12_PH4, "GMI_AD12 PH4"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD13_PH5, "GMI_AD13 PH5"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD14_PH6, "GMI_AD14 PH6"), + PINCTRL_PIN(TEGRA_PIN_GMI_AD15_PH7, "GMI_AD15 PH7"), + PINCTRL_PIN(TEGRA_PIN_GMI_WR_N_PI0, "GMI_WR_N PI0"), + PINCTRL_PIN(TEGRA_PIN_GMI_OE_N_PI1, "GMI_OE_N PI1"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS6_N_PI3, "GMI_CS6_N PI3"), + PINCTRL_PIN(TEGRA_PIN_GMI_RST_N_PI4, "GMI_RST_N PI4"), + PINCTRL_PIN(TEGRA_PIN_GMI_IORDY_PI5, "GMI_IORDY PI5"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS7_N_PI6, "GMI_CS7_N PI6"), + PINCTRL_PIN(TEGRA_PIN_GMI_WAIT_PI7, "GMI_WAIT PI7"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS0_N_PJ0, "GMI_CS0_N PJ0"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS1_N_PJ2, "GMI_CS1_N PJ2"), + PINCTRL_PIN(TEGRA_PIN_GMI_DQS_P_PJ3, "GMI_DQS_P PJ3"), + PINCTRL_PIN(TEGRA_PIN_UART2_CTS_N_PJ5, "UART2_CTS_N PJ5"), + PINCTRL_PIN(TEGRA_PIN_UART2_RTS_N_PJ6, "UART2_RTS_N PJ6"), + PINCTRL_PIN(TEGRA_PIN_GMI_A16_PJ7, "GMI_A16 PJ7"), + PINCTRL_PIN(TEGRA_PIN_GMI_ADV_N_PK0, "GMI_ADV_N PK0"), + PINCTRL_PIN(TEGRA_PIN_GMI_CLK_PK1, "GMI_CLK PK1"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS4_N_PK2, "GMI_CS4_N PK2"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS2_N_PK3, "GMI_CS2_N PK3"), + PINCTRL_PIN(TEGRA_PIN_GMI_CS3_N_PK4, "GMI_CS3_N PK4"), + PINCTRL_PIN(TEGRA_PIN_SPDIF_OUT_PK5, "SPDIF_OUT PK5"), + PINCTRL_PIN(TEGRA_PIN_SPDIF_IN_PK6, "SPDIF_IN PK6"), + PINCTRL_PIN(TEGRA_PIN_GMI_A19_PK7, "GMI_A19 PK7"), + PINCTRL_PIN(TEGRA_PIN_DAP1_FS_PN0, "DAP1_FS PN0"), + PINCTRL_PIN(TEGRA_PIN_DAP1_DIN_PN1, "DAP1_DIN PN1"), + PINCTRL_PIN(TEGRA_PIN_DAP1_DOUT_PN2, "DAP1_DOUT PN2"), + PINCTRL_PIN(TEGRA_PIN_DAP1_SCLK_PN3, "DAP1_SCLK PN3"), + PINCTRL_PIN(TEGRA_PIN_USB_VBUS_EN0_PN4, "USB_VBUS_EN0 PN4"), + PINCTRL_PIN(TEGRA_PIN_USB_VBUS_EN1_PN5, "USB_VBUS_EN1 PN5"), + PINCTRL_PIN(TEGRA_PIN_HDMI_INT_PN7, "HDMI_INT PN7"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA7_PO0, "ULPI_DATA7 PO0"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA0_PO1, "ULPI_DATA0 PO1"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA1_PO2, "ULPI_DATA1 PO2"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA2_PO3, "ULPI_DATA2 PO3"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA3_PO4, "ULPI_DATA3 PO4"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA4_PO5, "ULPI_DATA4 PO5"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA5_PO6, "ULPI_DATA5 PO6"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DATA6_PO7, "ULPI_DATA6 PO7"), + PINCTRL_PIN(TEGRA_PIN_DAP3_FS_PP0, "DAP3_FS PP0"), + PINCTRL_PIN(TEGRA_PIN_DAP3_DIN_PP1, "DAP3_DIN PP1"), + PINCTRL_PIN(TEGRA_PIN_DAP3_DOUT_PP2, "DAP3_DOUT PP2"), + PINCTRL_PIN(TEGRA_PIN_DAP3_SCLK_PP3, "DAP3_SCLK PP3"), + PINCTRL_PIN(TEGRA_PIN_DAP4_FS_PP4, "DAP4_FS PP4"), + PINCTRL_PIN(TEGRA_PIN_DAP4_DIN_PP5, "DAP4_DIN PP5"), + PINCTRL_PIN(TEGRA_PIN_DAP4_DOUT_PP6, "DAP4_DOUT PP6"), + PINCTRL_PIN(TEGRA_PIN_DAP4_SCLK_PP7, "DAP4_SCLK PP7"), + PINCTRL_PIN(TEGRA_PIN_KB_COL0_PQ0, "KB_COL0 PQ0"), + PINCTRL_PIN(TEGRA_PIN_KB_COL1_PQ1, "KB_COL1 PQ1"), + PINCTRL_PIN(TEGRA_PIN_KB_COL2_PQ2, "KB_COL2 PQ2"), + PINCTRL_PIN(TEGRA_PIN_KB_COL3_PQ3, "KB_COL3 PQ3"), + PINCTRL_PIN(TEGRA_PIN_KB_COL4_PQ4, "KB_COL4 PQ4"), + PINCTRL_PIN(TEGRA_PIN_KB_COL5_PQ5, "KB_COL5 PQ5"), + PINCTRL_PIN(TEGRA_PIN_KB_COL6_PQ6, "KB_COL6 PQ6"), + PINCTRL_PIN(TEGRA_PIN_KB_COL7_PQ7, "KB_COL7 PQ7"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW0_PR0, "KB_ROW0 PR0"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW1_PR1, "KB_ROW1 PR1"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW2_PR2, "KB_ROW2 PR2"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW3_PR3, "KB_ROW3 PR3"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW4_PR4, "KB_ROW4 PR4"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW5_PR5, "KB_ROW5 PR5"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW6_PR6, "KB_ROW6 PR6"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW7_PR7, "KB_ROW7 PR7"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW8_PS0, "KB_ROW8 PS0"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW9_PS1, "KB_ROW9 PS1"), + PINCTRL_PIN(TEGRA_PIN_KB_ROW10_PS2, "KB_ROW10 PS2"), + PINCTRL_PIN(TEGRA_PIN_GEN2_I2C_SCL_PT5, "GEN2_I2C_SCL PT5"), + PINCTRL_PIN(TEGRA_PIN_GEN2_I2C_SDA_PT6, "GEN2_I2C_SDA PT6"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_CMD_PT7, "SDMMC4_CMD PT7"), + PINCTRL_PIN(TEGRA_PIN_PU0, "PU0"), + PINCTRL_PIN(TEGRA_PIN_PU1, "PU1"), + PINCTRL_PIN(TEGRA_PIN_PU2, "PU2"), + PINCTRL_PIN(TEGRA_PIN_PU3, "PU3"), + PINCTRL_PIN(TEGRA_PIN_PU4, "PU4"), + PINCTRL_PIN(TEGRA_PIN_PU5, "PU5"), + PINCTRL_PIN(TEGRA_PIN_PU6, "PU6"), + PINCTRL_PIN(TEGRA_PIN_PV0, "PV0"), + PINCTRL_PIN(TEGRA_PIN_PV1, "PV1"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_CD_N_PV2, "SDMMC3_CD_N PV2"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_WP_N_PV3, "SDMMC1_WP_N PV3"), + PINCTRL_PIN(TEGRA_PIN_DDC_SCL_PV4, "DDC_SCL PV4"), + PINCTRL_PIN(TEGRA_PIN_DDC_SDA_PV5, "DDC_SDA PV5"), + PINCTRL_PIN(TEGRA_PIN_GPIO_W2_AUD_PW2, "GPIO_W2_AUD PW2"), + PINCTRL_PIN(TEGRA_PIN_GPIO_W3_AUD_PW3, "GPIO_W3_AUD PW3"), + PINCTRL_PIN(TEGRA_PIN_CLK1_OUT_PW4, "CLK1_OUT PW4"), + PINCTRL_PIN(TEGRA_PIN_CLK2_OUT_PW5, "CLK2_OUT PW5"), + PINCTRL_PIN(TEGRA_PIN_UART3_TXD_PW6, "UART3_TXD PW6"), + PINCTRL_PIN(TEGRA_PIN_UART3_RXD_PW7, "UART3_RXD PW7"), + PINCTRL_PIN(TEGRA_PIN_DVFS_PWM_PX0, "DVFS_PWM PX0"), + PINCTRL_PIN(TEGRA_PIN_GPIO_X1_AUD_PX1, "GPIO_X1_AUD PX1"), + PINCTRL_PIN(TEGRA_PIN_DVFS_CLK_PX2, "DVFS_CLK PX2"), + PINCTRL_PIN(TEGRA_PIN_GPIO_X3_AUD_PX3, "GPIO_X3_AUD PX3"), + PINCTRL_PIN(TEGRA_PIN_GPIO_X4_AUD_PX4, "GPIO_X4_AUD PX4"), + PINCTRL_PIN(TEGRA_PIN_GPIO_X5_AUD_PX5, "GPIO_X5_AUD PX5"), + PINCTRL_PIN(TEGRA_PIN_GPIO_X6_AUD_PX6, "GPIO_X6_AUD PX6"), + PINCTRL_PIN(TEGRA_PIN_GPIO_X7_AUD_PX7, "GPIO_X7_AUD PX7"), + PINCTRL_PIN(TEGRA_PIN_ULPI_CLK_PY0, "ULPI_CLK PY0"), + PINCTRL_PIN(TEGRA_PIN_ULPI_DIR_PY1, "ULPI_DIR PY1"), + PINCTRL_PIN(TEGRA_PIN_ULPI_NXT_PY2, "ULPI_NXT PY2"), + PINCTRL_PIN(TEGRA_PIN_ULPI_STP_PY3, "ULPI_STP PY3"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_DAT3_PY4, "SDMMC1_DAT3 PY4"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_DAT2_PY5, "SDMMC1_DAT2 PY5"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_DAT1_PY6, "SDMMC1_DAT1 PY6"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_DAT0_PY7, "SDMMC1_DAT0 PY7"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_CLK_PZ0, "SDMMC1_CLK PZ0"), + PINCTRL_PIN(TEGRA_PIN_SDMMC1_CMD_PZ1, "SDMMC1_CMD PZ1"), + PINCTRL_PIN(TEGRA_PIN_SYS_CLK_REQ_PZ5, "SYS_CLK_REQ PZ5"), + PINCTRL_PIN(TEGRA_PIN_PWR_I2C_SCL_PZ6, "PWR_I2C_SCL PZ6"), + PINCTRL_PIN(TEGRA_PIN_PWR_I2C_SDA_PZ7, "PWR_I2C_SDA PZ7"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT0_PAA0, "SDMMC4_DAT0 PAA0"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT1_PAA1, "SDMMC4_DAT1 PAA1"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT2_PAA2, "SDMMC4_DAT2 PAA2"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT3_PAA3, "SDMMC4_DAT3 PAA3"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT4_PAA4, "SDMMC4_DAT4 PAA4"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT5_PAA5, "SDMMC4_DAT5 PAA5"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT6_PAA6, "SDMMC4_DAT6 PAA6"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_DAT7_PAA7, "SDMMC4_DAT7 PAA7"), + PINCTRL_PIN(TEGRA_PIN_PBB0, "PBB0"), + PINCTRL_PIN(TEGRA_PIN_CAM_I2C_SCL_PBB1, "CAM_I2C_SCL PBB1"), + PINCTRL_PIN(TEGRA_PIN_CAM_I2C_SDA_PBB2, "CAM_I2C_SDA PBB2"), + PINCTRL_PIN(TEGRA_PIN_PBB3, "PBB3"), + PINCTRL_PIN(TEGRA_PIN_PBB4, "PBB4"), + PINCTRL_PIN(TEGRA_PIN_PBB5, "PBB5"), + PINCTRL_PIN(TEGRA_PIN_PBB6, "PBB6"), + PINCTRL_PIN(TEGRA_PIN_PBB7, "PBB7"), + PINCTRL_PIN(TEGRA_PIN_CAM_MCLK_PCC0, "CAM_MCLK PCC0"), + PINCTRL_PIN(TEGRA_PIN_PCC1, "PCC1"), + PINCTRL_PIN(TEGRA_PIN_PCC2, "PCC2"), + PINCTRL_PIN(TEGRA_PIN_SDMMC4_CLK_PCC4, "SDMMC4_CLK PCC4"), + PINCTRL_PIN(TEGRA_PIN_CLK2_REQ_PCC5, "CLK2_REQ PCC5"), + PINCTRL_PIN(TEGRA_PIN_CLK3_OUT_PEE0, "CLK3_OUT PEE0"), + PINCTRL_PIN(TEGRA_PIN_CLK3_REQ_PEE1, "CLK3_REQ PEE1"), + PINCTRL_PIN(TEGRA_PIN_CLK1_REQ_PEE2, "CLK1_REQ PEE2"), + PINCTRL_PIN(TEGRA_PIN_HDMI_CEC_PEE3, "HDMI_CEC PEE3"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_CLK_LB_OUT_PEE4, "SDMMC3_CLK_LB_OUT PEE4"), + PINCTRL_PIN(TEGRA_PIN_SDMMC3_CLK_LB_IN_PEE5, "SDMMC3_CLK_LB_IN PEE5"), + PINCTRL_PIN(TEGRA_PIN_CORE_PWR_REQ, "CORE_PWR_REQ"), + PINCTRL_PIN(TEGRA_PIN_CPU_PWR_REQ, "CPU_PWR_REQ"), + PINCTRL_PIN(TEGRA_PIN_OWR, "OWR"), + PINCTRL_PIN(TEGRA_PIN_PWR_INT_N, "PWR_INT_N"), + PINCTRL_PIN(TEGRA_PIN_RESET_OUT_N, "RESET_OUT_N"), +}; + +static const unsigned clk_32k_out_pa0_pins[] = { + TEGRA_PIN_CLK_32K_OUT_PA0, +}; + +static const unsigned uart3_cts_n_pa1_pins[] = { + TEGRA_PIN_UART3_CTS_N_PA1, +}; + +static const unsigned dap2_fs_pa2_pins[] = { + TEGRA_PIN_DAP2_FS_PA2, +}; + +static const unsigned dap2_sclk_pa3_pins[] = { + TEGRA_PIN_DAP2_SCLK_PA3, +}; + +static const unsigned dap2_din_pa4_pins[] = { + TEGRA_PIN_DAP2_DIN_PA4, +}; + +static const unsigned dap2_dout_pa5_pins[] = { + TEGRA_PIN_DAP2_DOUT_PA5, +}; + +static const unsigned sdmmc3_clk_pa6_pins[] = { + TEGRA_PIN_SDMMC3_CLK_PA6, +}; + +static const unsigned sdmmc3_cmd_pa7_pins[] = { + TEGRA_PIN_SDMMC3_CMD_PA7, +}; + +static const unsigned gmi_a17_pb0_pins[] = { + TEGRA_PIN_GMI_A17_PB0, +}; + +static const unsigned gmi_a18_pb1_pins[] = { + TEGRA_PIN_GMI_A18_PB1, +}; + +static const unsigned sdmmc3_dat3_pb4_pins[] = { + TEGRA_PIN_SDMMC3_DAT3_PB4, +}; + +static const unsigned sdmmc3_dat2_pb5_pins[] = { + TEGRA_PIN_SDMMC3_DAT2_PB5, +}; + +static const unsigned sdmmc3_dat1_pb6_pins[] = { + TEGRA_PIN_SDMMC3_DAT1_PB6, +}; + +static const unsigned sdmmc3_dat0_pb7_pins[] = { + TEGRA_PIN_SDMMC3_DAT0_PB7, +}; + +static const unsigned uart3_rts_n_pc0_pins[] = { + TEGRA_PIN_UART3_RTS_N_PC0, +}; + +static const unsigned uart2_txd_pc2_pins[] = { + TEGRA_PIN_UART2_TXD_PC2, +}; + +static const unsigned uart2_rxd_pc3_pins[] = { + TEGRA_PIN_UART2_RXD_PC3, +}; + +static const unsigned gen1_i2c_scl_pc4_pins[] = { + TEGRA_PIN_GEN1_I2C_SCL_PC4, +}; + +static const unsigned gen1_i2c_sda_pc5_pins[] = { + TEGRA_PIN_GEN1_I2C_SDA_PC5, +}; + +static const unsigned gmi_wp_n_pc7_pins[] = { + TEGRA_PIN_GMI_WP_N_PC7, +}; + +static const unsigned gmi_ad0_pg0_pins[] = { + TEGRA_PIN_GMI_AD0_PG0, +}; + +static const unsigned gmi_ad1_pg1_pins[] = { + TEGRA_PIN_GMI_AD1_PG1, +}; + +static const unsigned gmi_ad2_pg2_pins[] = { + TEGRA_PIN_GMI_AD2_PG2, +}; + +static const unsigned gmi_ad3_pg3_pins[] = { + TEGRA_PIN_GMI_AD3_PG3, +}; + +static const unsigned gmi_ad4_pg4_pins[] = { + TEGRA_PIN_GMI_AD4_PG4, +}; + +static const unsigned gmi_ad5_pg5_pins[] = { + TEGRA_PIN_GMI_AD5_PG5, +}; + +static const unsigned gmi_ad6_pg6_pins[] = { + TEGRA_PIN_GMI_AD6_PG6, +}; + +static const unsigned gmi_ad7_pg7_pins[] = { + TEGRA_PIN_GMI_AD7_PG7, +}; + +static const unsigned gmi_ad8_ph0_pins[] = { + TEGRA_PIN_GMI_AD8_PH0, +}; + +static const unsigned gmi_ad9_ph1_pins[] = { + TEGRA_PIN_GMI_AD9_PH1, +}; + +static const unsigned gmi_ad10_ph2_pins[] = { + TEGRA_PIN_GMI_AD10_PH2, +}; + +static const unsigned gmi_ad11_ph3_pins[] = { + TEGRA_PIN_GMI_AD11_PH3, +}; + +static const unsigned gmi_ad12_ph4_pins[] = { + TEGRA_PIN_GMI_AD12_PH4, +}; + +static const unsigned gmi_ad13_ph5_pins[] = { + TEGRA_PIN_GMI_AD13_PH5, +}; + +static const unsigned gmi_ad14_ph6_pins[] = { + TEGRA_PIN_GMI_AD14_PH6, +}; + +static const unsigned gmi_ad15_ph7_pins[] = { + TEGRA_PIN_GMI_AD15_PH7, +}; + +static const unsigned gmi_wr_n_pi0_pins[] = { + TEGRA_PIN_GMI_WR_N_PI0, +}; + +static const unsigned gmi_oe_n_pi1_pins[] = { + TEGRA_PIN_GMI_OE_N_PI1, +}; + +static const unsigned gmi_cs6_n_pi3_pins[] = { + TEGRA_PIN_GMI_CS6_N_PI3, +}; + +static const unsigned gmi_rst_n_pi4_pins[] = { + TEGRA_PIN_GMI_RST_N_PI4, +}; + +static const unsigned gmi_iordy_pi5_pins[] = { + TEGRA_PIN_GMI_IORDY_PI5, +}; + +static const unsigned gmi_cs7_n_pi6_pins[] = { + TEGRA_PIN_GMI_CS7_N_PI6, +}; + +static const unsigned gmi_wait_pi7_pins[] = { + TEGRA_PIN_GMI_WAIT_PI7, +}; + +static const unsigned gmi_cs0_n_pj0_pins[] = { + TEGRA_PIN_GMI_CS0_N_PJ0, +}; + +static const unsigned gmi_cs1_n_pj2_pins[] = { + TEGRA_PIN_GMI_CS1_N_PJ2, +}; + +static const unsigned gmi_dqs_p_pj3_pins[] = { + TEGRA_PIN_GMI_DQS_P_PJ3, +}; + +static const unsigned uart2_cts_n_pj5_pins[] = { + TEGRA_PIN_UART2_CTS_N_PJ5, +}; + +static const unsigned uart2_rts_n_pj6_pins[] = { + TEGRA_PIN_UART2_RTS_N_PJ6, +}; + +static const unsigned gmi_a16_pj7_pins[] = { + TEGRA_PIN_GMI_A16_PJ7, +}; + +static const unsigned gmi_adv_n_pk0_pins[] = { + TEGRA_PIN_GMI_ADV_N_PK0, +}; + +static const unsigned gmi_clk_pk1_pins[] = { + TEGRA_PIN_GMI_CLK_PK1, +}; + +static const unsigned gmi_cs4_n_pk2_pins[] = { + TEGRA_PIN_GMI_CS4_N_PK2, +}; + +static const unsigned gmi_cs2_n_pk3_pins[] = { + TEGRA_PIN_GMI_CS2_N_PK3, +}; + +static const unsigned gmi_cs3_n_pk4_pins[] = { + TEGRA_PIN_GMI_CS3_N_PK4, +}; + +static const unsigned spdif_out_pk5_pins[] = { + TEGRA_PIN_SPDIF_OUT_PK5, +}; + +static const unsigned spdif_in_pk6_pins[] = { + TEGRA_PIN_SPDIF_IN_PK6, +}; + +static const unsigned gmi_a19_pk7_pins[] = { + TEGRA_PIN_GMI_A19_PK7, +}; + +static const unsigned dap1_fs_pn0_pins[] = { + TEGRA_PIN_DAP1_FS_PN0, +}; + +static const unsigned dap1_din_pn1_pins[] = { + TEGRA_PIN_DAP1_DIN_PN1, +}; + +static const unsigned dap1_dout_pn2_pins[] = { + TEGRA_PIN_DAP1_DOUT_PN2, +}; + +static const unsigned dap1_sclk_pn3_pins[] = { + TEGRA_PIN_DAP1_SCLK_PN3, +}; + +static const unsigned usb_vbus_en0_pn4_pins[] = { + TEGRA_PIN_USB_VBUS_EN0_PN4, +}; + +static const unsigned usb_vbus_en1_pn5_pins[] = { + TEGRA_PIN_USB_VBUS_EN1_PN5, +}; + +static const unsigned hdmi_int_pn7_pins[] = { + TEGRA_PIN_HDMI_INT_PN7, +}; + +static const unsigned ulpi_data7_po0_pins[] = { + TEGRA_PIN_ULPI_DATA7_PO0, +}; + +static const unsigned ulpi_data0_po1_pins[] = { + TEGRA_PIN_ULPI_DATA0_PO1, +}; + +static const unsigned ulpi_data1_po2_pins[] = { + TEGRA_PIN_ULPI_DATA1_PO2, +}; + +static const unsigned ulpi_data2_po3_pins[] = { + TEGRA_PIN_ULPI_DATA2_PO3, +}; + +static const unsigned ulpi_data3_po4_pins[] = { + TEGRA_PIN_ULPI_DATA3_PO4, +}; + +static const unsigned ulpi_data4_po5_pins[] = { + TEGRA_PIN_ULPI_DATA4_PO5, +}; + +static const unsigned ulpi_data5_po6_pins[] = { + TEGRA_PIN_ULPI_DATA5_PO6, +}; + +static const unsigned ulpi_data6_po7_pins[] = { + TEGRA_PIN_ULPI_DATA6_PO7, +}; + +static const unsigned dap3_fs_pp0_pins[] = { + TEGRA_PIN_DAP3_FS_PP0, +}; + +static const unsigned dap3_din_pp1_pins[] = { + TEGRA_PIN_DAP3_DIN_PP1, +}; + +static const unsigned dap3_dout_pp2_pins[] = { + TEGRA_PIN_DAP3_DOUT_PP2, +}; + +static const unsigned dap3_sclk_pp3_pins[] = { + TEGRA_PIN_DAP3_SCLK_PP3, +}; + +static const unsigned dap4_fs_pp4_pins[] = { + TEGRA_PIN_DAP4_FS_PP4, +}; + +static const unsigned dap4_din_pp5_pins[] = { + TEGRA_PIN_DAP4_DIN_PP5, +}; + +static const unsigned dap4_dout_pp6_pins[] = { + TEGRA_PIN_DAP4_DOUT_PP6, +}; + +static const unsigned dap4_sclk_pp7_pins[] = { + TEGRA_PIN_DAP4_SCLK_PP7, +}; + +static const unsigned kb_col0_pq0_pins[] = { + TEGRA_PIN_KB_COL0_PQ0, +}; + +static const unsigned kb_col1_pq1_pins[] = { + TEGRA_PIN_KB_COL1_PQ1, +}; + +static const unsigned kb_col2_pq2_pins[] = { + TEGRA_PIN_KB_COL2_PQ2, +}; + +static const unsigned kb_col3_pq3_pins[] = { + TEGRA_PIN_KB_COL3_PQ3, +}; + +static const unsigned kb_col4_pq4_pins[] = { + TEGRA_PIN_KB_COL4_PQ4, +}; + +static const unsigned kb_col5_pq5_pins[] = { + TEGRA_PIN_KB_COL5_PQ5, +}; + +static const unsigned kb_col6_pq6_pins[] = { + TEGRA_PIN_KB_COL6_PQ6, +}; + +static const unsigned kb_col7_pq7_pins[] = { + TEGRA_PIN_KB_COL7_PQ7, +}; + +static const unsigned kb_row0_pr0_pins[] = { + TEGRA_PIN_KB_ROW0_PR0, +}; + +static const unsigned kb_row1_pr1_pins[] = { + TEGRA_PIN_KB_ROW1_PR1, +}; + +static const unsigned kb_row2_pr2_pins[] = { + TEGRA_PIN_KB_ROW2_PR2, +}; + +static const unsigned kb_row3_pr3_pins[] = { + TEGRA_PIN_KB_ROW3_PR3, +}; + +static const unsigned kb_row4_pr4_pins[] = { + TEGRA_PIN_KB_ROW4_PR4, +}; + +static const unsigned kb_row5_pr5_pins[] = { + TEGRA_PIN_KB_ROW5_PR5, +}; + +static const unsigned kb_row6_pr6_pins[] = { + TEGRA_PIN_KB_ROW6_PR6, +}; + +static const unsigned kb_row7_pr7_pins[] = { + TEGRA_PIN_KB_ROW7_PR7, +}; + +static const unsigned kb_row8_ps0_pins[] = { + TEGRA_PIN_KB_ROW8_PS0, +}; + +static const unsigned kb_row9_ps1_pins[] = { + TEGRA_PIN_KB_ROW9_PS1, +}; + +static const unsigned kb_row10_ps2_pins[] = { + TEGRA_PIN_KB_ROW10_PS2, +}; + +static const unsigned gen2_i2c_scl_pt5_pins[] = { + TEGRA_PIN_GEN2_I2C_SCL_PT5, +}; + +static const unsigned gen2_i2c_sda_pt6_pins[] = { + TEGRA_PIN_GEN2_I2C_SDA_PT6, +}; + +static const unsigned sdmmc4_cmd_pt7_pins[] = { + TEGRA_PIN_SDMMC4_CMD_PT7, +}; + +static const unsigned pu0_pins[] = { + TEGRA_PIN_PU0, +}; + +static const unsigned pu1_pins[] = { + TEGRA_PIN_PU1, +}; + +static const unsigned pu2_pins[] = { + TEGRA_PIN_PU2, +}; + +static const unsigned pu3_pins[] = { + TEGRA_PIN_PU3, +}; + +static const unsigned pu4_pins[] = { + TEGRA_PIN_PU4, +}; + +static const unsigned pu5_pins[] = { + TEGRA_PIN_PU5, +}; + +static const unsigned pu6_pins[] = { + TEGRA_PIN_PU6, +}; + +static const unsigned pv0_pins[] = { + TEGRA_PIN_PV0, +}; + +static const unsigned pv1_pins[] = { + TEGRA_PIN_PV1, +}; + +static const unsigned sdmmc3_cd_n_pv2_pins[] = { + TEGRA_PIN_SDMMC3_CD_N_PV2, +}; + +static const unsigned sdmmc1_wp_n_pv3_pins[] = { + TEGRA_PIN_SDMMC1_WP_N_PV3, +}; + +static const unsigned ddc_scl_pv4_pins[] = { + TEGRA_PIN_DDC_SCL_PV4, +}; + +static const unsigned ddc_sda_pv5_pins[] = { + TEGRA_PIN_DDC_SDA_PV5, +}; + +static const unsigned gpio_w2_aud_pw2_pins[] = { + TEGRA_PIN_GPIO_W2_AUD_PW2, +}; + +static const unsigned gpio_w3_aud_pw3_pins[] = { + TEGRA_PIN_GPIO_W3_AUD_PW3, +}; + +static const unsigned clk1_out_pw4_pins[] = { + TEGRA_PIN_CLK1_OUT_PW4, +}; + +static const unsigned clk2_out_pw5_pins[] = { + TEGRA_PIN_CLK2_OUT_PW5, +}; + +static const unsigned uart3_txd_pw6_pins[] = { + TEGRA_PIN_UART3_TXD_PW6, +}; + +static const unsigned uart3_rxd_pw7_pins[] = { + TEGRA_PIN_UART3_RXD_PW7, +}; + +static const unsigned dvfs_pwm_px0_pins[] = { + TEGRA_PIN_DVFS_PWM_PX0, +}; + +static const unsigned gpio_x1_aud_px1_pins[] = { + TEGRA_PIN_GPIO_X1_AUD_PX1, +}; + +static const unsigned dvfs_clk_px2_pins[] = { + TEGRA_PIN_DVFS_CLK_PX2, +}; + +static const unsigned gpio_x3_aud_px3_pins[] = { + TEGRA_PIN_GPIO_X3_AUD_PX3, +}; + +static const unsigned gpio_x4_aud_px4_pins[] = { + TEGRA_PIN_GPIO_X4_AUD_PX4, +}; + +static const unsigned gpio_x5_aud_px5_pins[] = { + TEGRA_PIN_GPIO_X5_AUD_PX5, +}; + +static const unsigned gpio_x6_aud_px6_pins[] = { + TEGRA_PIN_GPIO_X6_AUD_PX6, +}; + +static const unsigned gpio_x7_aud_px7_pins[] = { + TEGRA_PIN_GPIO_X7_AUD_PX7, +}; + +static const unsigned ulpi_clk_py0_pins[] = { + TEGRA_PIN_ULPI_CLK_PY0, +}; + +static const unsigned ulpi_dir_py1_pins[] = { + TEGRA_PIN_ULPI_DIR_PY1, +}; + +static const unsigned ulpi_nxt_py2_pins[] = { + TEGRA_PIN_ULPI_NXT_PY2, +}; + +static const unsigned ulpi_stp_py3_pins[] = { + TEGRA_PIN_ULPI_STP_PY3, +}; + +static const unsigned sdmmc1_dat3_py4_pins[] = { + TEGRA_PIN_SDMMC1_DAT3_PY4, +}; + +static const unsigned sdmmc1_dat2_py5_pins[] = { + TEGRA_PIN_SDMMC1_DAT2_PY5, +}; + +static const unsigned sdmmc1_dat1_py6_pins[] = { + TEGRA_PIN_SDMMC1_DAT1_PY6, +}; + +static const unsigned sdmmc1_dat0_py7_pins[] = { + TEGRA_PIN_SDMMC1_DAT0_PY7, +}; + +static const unsigned sdmmc1_clk_pz0_pins[] = { + TEGRA_PIN_SDMMC1_CLK_PZ0, +}; + +static const unsigned sdmmc1_cmd_pz1_pins[] = { + TEGRA_PIN_SDMMC1_CMD_PZ1, +}; + +static const unsigned sys_clk_req_pz5_pins[] = { + TEGRA_PIN_SYS_CLK_REQ_PZ5, +}; + +static const unsigned pwr_i2c_scl_pz6_pins[] = { + TEGRA_PIN_PWR_I2C_SCL_PZ6, +}; + +static const unsigned pwr_i2c_sda_pz7_pins[] = { + TEGRA_PIN_PWR_I2C_SDA_PZ7, +}; + +static const unsigned sdmmc4_dat0_paa0_pins[] = { + TEGRA_PIN_SDMMC4_DAT0_PAA0, +}; + +static const unsigned sdmmc4_dat1_paa1_pins[] = { + TEGRA_PIN_SDMMC4_DAT1_PAA1, +}; + +static const unsigned sdmmc4_dat2_paa2_pins[] = { + TEGRA_PIN_SDMMC4_DAT2_PAA2, +}; + +static const unsigned sdmmc4_dat3_paa3_pins[] = { + TEGRA_PIN_SDMMC4_DAT3_PAA3, +}; + +static const unsigned sdmmc4_dat4_paa4_pins[] = { + TEGRA_PIN_SDMMC4_DAT4_PAA4, +}; + +static const unsigned sdmmc4_dat5_paa5_pins[] = { + TEGRA_PIN_SDMMC4_DAT5_PAA5, +}; + +static const unsigned sdmmc4_dat6_paa6_pins[] = { + TEGRA_PIN_SDMMC4_DAT6_PAA6, +}; + +static const unsigned sdmmc4_dat7_paa7_pins[] = { + TEGRA_PIN_SDMMC4_DAT7_PAA7, +}; + +static const unsigned pbb0_pins[] = { + TEGRA_PIN_PBB0, +}; + +static const unsigned cam_i2c_scl_pbb1_pins[] = { + TEGRA_PIN_CAM_I2C_SCL_PBB1, +}; + +static const unsigned cam_i2c_sda_pbb2_pins[] = { + TEGRA_PIN_CAM_I2C_SDA_PBB2, +}; + +static const unsigned pbb3_pins[] = { + TEGRA_PIN_PBB3, +}; + +static const unsigned pbb4_pins[] = { + TEGRA_PIN_PBB4, +}; + +static const unsigned pbb5_pins[] = { + TEGRA_PIN_PBB5, +}; + +static const unsigned pbb6_pins[] = { + TEGRA_PIN_PBB6, +}; + +static const unsigned pbb7_pins[] = { + TEGRA_PIN_PBB7, +}; + +static const unsigned cam_mclk_pcc0_pins[] = { + TEGRA_PIN_CAM_MCLK_PCC0, +}; + +static const unsigned pcc1_pins[] = { + TEGRA_PIN_PCC1, +}; + +static const unsigned pcc2_pins[] = { + TEGRA_PIN_PCC2, +}; + +static const unsigned sdmmc4_clk_pcc4_pins[] = { + TEGRA_PIN_SDMMC4_CLK_PCC4, +}; + +static const unsigned clk2_req_pcc5_pins[] = { + TEGRA_PIN_CLK2_REQ_PCC5, +}; + +static const unsigned clk3_out_pee0_pins[] = { + TEGRA_PIN_CLK3_OUT_PEE0, +}; + +static const unsigned clk3_req_pee1_pins[] = { + TEGRA_PIN_CLK3_REQ_PEE1, +}; + +static const unsigned clk1_req_pee2_pins[] = { + TEGRA_PIN_CLK1_REQ_PEE2, +}; + +static const unsigned hdmi_cec_pee3_pins[] = { + TEGRA_PIN_HDMI_CEC_PEE3, +}; + +static const unsigned sdmmc3_clk_lb_out_pee4_pins[] = { + TEGRA_PIN_SDMMC3_CLK_LB_OUT_PEE4, +}; + +static const unsigned sdmmc3_clk_lb_in_pee5_pins[] = { + TEGRA_PIN_SDMMC3_CLK_LB_IN_PEE5, +}; + +static const unsigned core_pwr_req_pins[] = { + TEGRA_PIN_CORE_PWR_REQ, +}; + +static const unsigned cpu_pwr_req_pins[] = { + TEGRA_PIN_CPU_PWR_REQ, +}; + +static const unsigned owr_pins[] = { + TEGRA_PIN_OWR, +}; + +static const unsigned pwr_int_n_pins[] = { + TEGRA_PIN_PWR_INT_N, +}; + +static const unsigned reset_out_n_pins[] = { + TEGRA_PIN_RESET_OUT_N, +}; + +static const unsigned drive_ao1_pins[] = { + TEGRA_PIN_KB_ROW0_PR0, + TEGRA_PIN_KB_ROW1_PR1, + TEGRA_PIN_KB_ROW2_PR2, + TEGRA_PIN_KB_ROW3_PR3, + TEGRA_PIN_KB_ROW4_PR4, + TEGRA_PIN_KB_ROW5_PR5, + TEGRA_PIN_KB_ROW6_PR6, + TEGRA_PIN_KB_ROW7_PR7, + TEGRA_PIN_PWR_I2C_SCL_PZ6, + TEGRA_PIN_PWR_I2C_SDA_PZ7, +}; + +static const unsigned drive_ao2_pins[] = { + TEGRA_PIN_CLK_32K_OUT_PA0, + TEGRA_PIN_KB_COL0_PQ0, + TEGRA_PIN_KB_COL1_PQ1, + TEGRA_PIN_KB_COL2_PQ2, + TEGRA_PIN_KB_COL3_PQ3, + TEGRA_PIN_KB_COL4_PQ4, + TEGRA_PIN_KB_COL5_PQ5, + TEGRA_PIN_KB_COL6_PQ6, + TEGRA_PIN_KB_COL7_PQ7, + TEGRA_PIN_KB_ROW8_PS0, + TEGRA_PIN_KB_ROW9_PS1, + TEGRA_PIN_KB_ROW10_PS2, + TEGRA_PIN_SYS_CLK_REQ_PZ5, + TEGRA_PIN_CORE_PWR_REQ, + TEGRA_PIN_CPU_PWR_REQ, + TEGRA_PIN_RESET_OUT_N, +}; + +static const unsigned drive_at1_pins[] = { + TEGRA_PIN_GMI_AD8_PH0, + TEGRA_PIN_GMI_AD9_PH1, + TEGRA_PIN_GMI_AD10_PH2, + TEGRA_PIN_GMI_AD11_PH3, + TEGRA_PIN_GMI_AD12_PH4, + TEGRA_PIN_GMI_AD13_PH5, + TEGRA_PIN_GMI_AD14_PH6, + TEGRA_PIN_GMI_AD15_PH7, + + TEGRA_PIN_GMI_IORDY_PI5, + TEGRA_PIN_GMI_CS7_N_PI6, +}; + +static const unsigned drive_at2_pins[] = { + TEGRA_PIN_GMI_AD0_PG0, + TEGRA_PIN_GMI_AD1_PG1, + TEGRA_PIN_GMI_AD2_PG2, + TEGRA_PIN_GMI_AD3_PG3, + TEGRA_PIN_GMI_AD4_PG4, + TEGRA_PIN_GMI_AD5_PG5, + TEGRA_PIN_GMI_AD6_PG6, + TEGRA_PIN_GMI_AD7_PG7, + + TEGRA_PIN_GMI_WR_N_PI0, + TEGRA_PIN_GMI_OE_N_PI1, + TEGRA_PIN_GMI_CS6_N_PI3, + TEGRA_PIN_GMI_RST_N_PI4, + TEGRA_PIN_GMI_WAIT_PI7, + + TEGRA_PIN_GMI_DQS_P_PJ3, + + TEGRA_PIN_GMI_ADV_N_PK0, + TEGRA_PIN_GMI_CLK_PK1, + TEGRA_PIN_GMI_CS4_N_PK2, + TEGRA_PIN_GMI_CS2_N_PK3, + TEGRA_PIN_GMI_CS3_N_PK4, +}; + +static const unsigned drive_at3_pins[] = { + TEGRA_PIN_GMI_WP_N_PC7, + TEGRA_PIN_GMI_CS0_N_PJ0, +}; + +static const unsigned drive_at4_pins[] = { + TEGRA_PIN_GMI_A17_PB0, + TEGRA_PIN_GMI_A18_PB1, + TEGRA_PIN_GMI_CS1_N_PJ2, + TEGRA_PIN_GMI_A16_PJ7, + TEGRA_PIN_GMI_A19_PK7, +}; + +static const unsigned drive_at5_pins[] = { + TEGRA_PIN_GEN2_I2C_SCL_PT5, + TEGRA_PIN_GEN2_I2C_SDA_PT6, +}; + +static const unsigned drive_cdev1_pins[] = { + TEGRA_PIN_CLK1_OUT_PW4, + TEGRA_PIN_CLK1_REQ_PEE2, +}; + +static const unsigned drive_cdev2_pins[] = { + TEGRA_PIN_CLK2_OUT_PW5, + TEGRA_PIN_CLK2_REQ_PCC5, + TEGRA_PIN_SDMMC1_WP_N_PV3, +}; + +static const unsigned drive_dap1_pins[] = { + TEGRA_PIN_DAP1_FS_PN0, + TEGRA_PIN_DAP1_DIN_PN1, + TEGRA_PIN_DAP1_DOUT_PN2, + TEGRA_PIN_DAP1_SCLK_PN3, +}; + +static const unsigned drive_dap2_pins[] = { + TEGRA_PIN_DAP2_FS_PA2, + TEGRA_PIN_DAP2_SCLK_PA3, + TEGRA_PIN_DAP2_DIN_PA4, + TEGRA_PIN_DAP2_DOUT_PA5, +}; + +static const unsigned drive_dap3_pins[] = { + TEGRA_PIN_DAP3_FS_PP0, + TEGRA_PIN_DAP3_DIN_PP1, + TEGRA_PIN_DAP3_DOUT_PP2, + TEGRA_PIN_DAP3_SCLK_PP3, +}; + +static const unsigned drive_dap4_pins[] = { + TEGRA_PIN_DAP4_FS_PP4, + TEGRA_PIN_DAP4_DIN_PP5, + TEGRA_PIN_DAP4_DOUT_PP6, + TEGRA_PIN_DAP4_SCLK_PP7, +}; + +static const unsigned drive_dbg_pins[] = { + TEGRA_PIN_GEN1_I2C_SCL_PC4, + TEGRA_PIN_GEN1_I2C_SDA_PC5, + TEGRA_PIN_PU0, + TEGRA_PIN_PU1, + TEGRA_PIN_PU2, + TEGRA_PIN_PU3, + TEGRA_PIN_PU4, + TEGRA_PIN_PU5, + TEGRA_PIN_PU6, +}; + +static const unsigned drive_sdio3_pins[] = { + TEGRA_PIN_SDMMC3_CLK_PA6, + TEGRA_PIN_SDMMC3_CMD_PA7, + TEGRA_PIN_SDMMC3_DAT3_PB4, + TEGRA_PIN_SDMMC3_DAT2_PB5, + TEGRA_PIN_SDMMC3_DAT1_PB6, + TEGRA_PIN_SDMMC3_DAT0_PB7, + TEGRA_PIN_SDMMC3_CLK_LB_OUT_PEE4, + TEGRA_PIN_SDMMC3_CLK_LB_IN_PEE5, +}; + +static const unsigned drive_spi_pins[] = { + TEGRA_PIN_DVFS_PWM_PX0, + TEGRA_PIN_GPIO_X1_AUD_PX1, + TEGRA_PIN_DVFS_CLK_PX2, + TEGRA_PIN_GPIO_X3_AUD_PX3, + TEGRA_PIN_GPIO_X4_AUD_PX4, + TEGRA_PIN_GPIO_X5_AUD_PX5, + TEGRA_PIN_GPIO_X6_AUD_PX6, + TEGRA_PIN_GPIO_X7_AUD_PX7, + TEGRA_PIN_GPIO_W2_AUD_PW2, + TEGRA_PIN_GPIO_W3_AUD_PW3, +}; + +static const unsigned drive_uaa_pins[] = { + TEGRA_PIN_ULPI_DATA0_PO1, + TEGRA_PIN_ULPI_DATA1_PO2, + TEGRA_PIN_ULPI_DATA2_PO3, + TEGRA_PIN_ULPI_DATA3_PO4, +}; + +static const unsigned drive_uab_pins[] = { + TEGRA_PIN_ULPI_DATA7_PO0, + TEGRA_PIN_ULPI_DATA4_PO5, + TEGRA_PIN_ULPI_DATA5_PO6, + TEGRA_PIN_ULPI_DATA6_PO7, + TEGRA_PIN_PV0, + TEGRA_PIN_PV1, +}; + +static const unsigned drive_uart2_pins[] = { + TEGRA_PIN_UART2_TXD_PC2, + TEGRA_PIN_UART2_RXD_PC3, + TEGRA_PIN_UART2_CTS_N_PJ5, + TEGRA_PIN_UART2_RTS_N_PJ6, +}; + +static const unsigned drive_uart3_pins[] = { + TEGRA_PIN_UART3_CTS_N_PA1, + TEGRA_PIN_UART3_RTS_N_PC0, + TEGRA_PIN_UART3_TXD_PW6, + TEGRA_PIN_UART3_RXD_PW7, +}; + +static const unsigned drive_sdio1_pins[] = { + TEGRA_PIN_SDMMC1_DAT3_PY4, + TEGRA_PIN_SDMMC1_DAT2_PY5, + TEGRA_PIN_SDMMC1_DAT1_PY6, + TEGRA_PIN_SDMMC1_DAT0_PY7, + TEGRA_PIN_SDMMC1_CLK_PZ0, + TEGRA_PIN_SDMMC1_CMD_PZ1, +}; + +static const unsigned drive_ddc_pins[] = { + TEGRA_PIN_DDC_SCL_PV4, + TEGRA_PIN_DDC_SDA_PV5, +}; + +static const unsigned drive_gma_pins[] = { + TEGRA_PIN_SDMMC4_CLK_PCC4, + TEGRA_PIN_SDMMC4_CMD_PT7, + TEGRA_PIN_SDMMC4_DAT0_PAA0, + TEGRA_PIN_SDMMC4_DAT1_PAA1, + TEGRA_PIN_SDMMC4_DAT2_PAA2, + TEGRA_PIN_SDMMC4_DAT3_PAA3, + TEGRA_PIN_SDMMC4_DAT4_PAA4, + TEGRA_PIN_SDMMC4_DAT5_PAA5, + TEGRA_PIN_SDMMC4_DAT6_PAA6, + TEGRA_PIN_SDMMC4_DAT7_PAA7, +}; + +static const unsigned drive_gme_pins[] = { + TEGRA_PIN_PBB0, + TEGRA_PIN_CAM_I2C_SCL_PBB1, + TEGRA_PIN_CAM_I2C_SDA_PBB2, + TEGRA_PIN_PBB3, + TEGRA_PIN_PCC2, +}; + +static const unsigned drive_gmf_pins[] = { + TEGRA_PIN_PBB4, + TEGRA_PIN_PBB5, + TEGRA_PIN_PBB6, + TEGRA_PIN_PBB7, +}; + +static const unsigned drive_gmg_pins[] = { + TEGRA_PIN_CAM_MCLK_PCC0, +}; + +static const unsigned drive_gmh_pins[] = { + TEGRA_PIN_PCC1, +}; + +static const unsigned drive_owr_pins[] = { + TEGRA_PIN_SDMMC3_CD_N_PV2, +}; + +static const unsigned drive_uda_pins[] = { + TEGRA_PIN_ULPI_CLK_PY0, + TEGRA_PIN_ULPI_DIR_PY1, + TEGRA_PIN_ULPI_NXT_PY2, + TEGRA_PIN_ULPI_STP_PY3, +}; + +static const unsigned drive_dev3_pins[] = { + TEGRA_PIN_CLK3_OUT_PEE0, + TEGRA_PIN_CLK3_REQ_PEE1, +}; + +enum tegra_mux { + TEGRA_MUX_BLINK, + TEGRA_MUX_CEC, + TEGRA_MUX_CLDVFS, + TEGRA_MUX_CLK12, + TEGRA_MUX_CPU, + TEGRA_MUX_DAP, + TEGRA_MUX_DAP1, + TEGRA_MUX_DAP2, + TEGRA_MUX_DEV3, + TEGRA_MUX_DISPLAYA, + TEGRA_MUX_DISPLAYA_ALT, + TEGRA_MUX_DISPLAYB, + TEGRA_MUX_DTV, + TEGRA_MUX_EMC_DLL, + TEGRA_MUX_EXTPERIPH1, + TEGRA_MUX_EXTPERIPH2, + TEGRA_MUX_EXTPERIPH3, + TEGRA_MUX_GMI, + TEGRA_MUX_GMI_ALT, + TEGRA_MUX_HDA, + TEGRA_MUX_HSI, + TEGRA_MUX_I2C1, + TEGRA_MUX_I2C2, + TEGRA_MUX_I2C3, + TEGRA_MUX_I2C4, + TEGRA_MUX_I2CPWR, + TEGRA_MUX_I2S0, + TEGRA_MUX_I2S1, + TEGRA_MUX_I2S2, + TEGRA_MUX_I2S3, + TEGRA_MUX_I2S4, + TEGRA_MUX_IRDA, + TEGRA_MUX_KBC, + TEGRA_MUX_NAND, + TEGRA_MUX_NAND_ALT, + TEGRA_MUX_OWR, + TEGRA_MUX_PMI, + TEGRA_MUX_PWM0, + TEGRA_MUX_PWM1, + TEGRA_MUX_PWM2, + TEGRA_MUX_PWM3, + TEGRA_MUX_PWRON, + TEGRA_MUX_RESET_OUT_N, + TEGRA_MUX_RSVD1, + TEGRA_MUX_RSVD2, + TEGRA_MUX_RSVD3, + TEGRA_MUX_RSVD4, + TEGRA_MUX_SDMMC1, + TEGRA_MUX_SDMMC2, + TEGRA_MUX_SDMMC3, + TEGRA_MUX_SDMMC4, + TEGRA_MUX_SOC, + TEGRA_MUX_SPDIF, + TEGRA_MUX_SPI1, + TEGRA_MUX_SPI2, + TEGRA_MUX_SPI3, + TEGRA_MUX_SPI4, + TEGRA_MUX_SPI5, + TEGRA_MUX_SPI6, + TEGRA_MUX_SYSCLK, + TEGRA_MUX_TRACE, + TEGRA_MUX_UARTA, + TEGRA_MUX_UARTB, + TEGRA_MUX_UARTC, + TEGRA_MUX_UARTD, + TEGRA_MUX_ULPI, + TEGRA_MUX_USB, + TEGRA_MUX_VGP1, + TEGRA_MUX_VGP2, + TEGRA_MUX_VGP3, + TEGRA_MUX_VGP4, + TEGRA_MUX_VGP5, + TEGRA_MUX_VGP6, + TEGRA_MUX_VI, + TEGRA_MUX_VI_ALT1, + TEGRA_MUX_VI_ALT3, +}; + +static const char * const blink_groups[] = { + "clk_32k_out_pa0", +}; + +static const char * const cec_groups[] = { + "hdmi_cec_pee3", +}; + +static const char * const cldvfs_groups[] = { + "gmi_ad9_ph1", + "gmi_ad10_ph2", + "kb_row7_pr7", + "kb_row8_ps0", + "dvfs_pwm_px0", + "dvfs_clk_px2", +}; + +static const char * const clk12_groups[] = { + "sdmmc1_wp_n_pv3", + "sdmmc1_clk_pz0", +}; + +static const char * const cpu_groups[] = { + "cpu_pwr_req", +}; + +static const char * const dap_groups[] = { + "clk1_req_pee2", + "clk2_req_pcc5", +}; + +static const char * const dap1_groups[] = { + "clk1_req_pee2", +}; + +static const char * const dap2_groups[] = { + "clk1_out_pw4", + "gpio_x4_aud_px4", +}; + +static const char * const dev3_groups[] = { + "clk3_req_pee1", +}; + +static const char * const displaya_groups[] = { + "dap3_fs_pp0", + "dap3_din_pp1", + "dap3_dout_pp2", + "dap3_sclk_pp3", + "uart3_rts_n_pc0", + "pu3", + "pu4", + "pu5", + "pbb3", + "pbb4", + "pbb5", + "pbb6", + "kb_row3_pr3", + "kb_row4_pr4", + "kb_row5_pr5", + "kb_row6_pr6", + "kb_col3_pq3", + "sdmmc3_dat2_pb5", +}; + +static const char * const displaya_alt_groups[] = { + "kb_row6_pr6", +}; + +static const char * const displayb_groups[] = { + "dap3_fs_pp0", + "dap3_din_pp1", + "dap3_dout_pp2", + "dap3_sclk_pp3", + "pu3", + "pu4", + "pu5", + "pu6", + "pbb3", + "pbb4", + "pbb5", + "pbb6", + "kb_row3_pr3", + "kb_row4_pr4", + "kb_row5_pr5", + "kb_row6_pr6", + "sdmmc3_dat3_pb4", +}; + +static const char * const dtv_groups[] = { + "uart3_cts_n_pa1", + "uart3_rts_n_pc0", + "dap4_fs_pp4", + "dap4_dout_pp6", + "gmi_wait_pi7", + "gmi_ad8_ph0", + "gmi_ad14_ph6", + "gmi_ad15_ph7", +}; + +static const char * const emc_dll_groups[] = { + "kb_col0_pq0", + "kb_col1_pq1", +}; + +static const char * const extperiph1_groups[] = { + "clk1_out_pw4", +}; + +static const char * const extperiph2_groups[] = { + "clk2_out_pw5", +}; + +static const char * const extperiph3_groups[] = { + "clk3_out_pee0", +}; + +static const char * const gmi_groups[] = { + "gmi_wp_n_pc7", + + "gmi_ad0_pg0", + "gmi_ad1_pg1", + "gmi_ad2_pg2", + "gmi_ad3_pg3", + "gmi_ad4_pg4", + "gmi_ad5_pg5", + "gmi_ad6_pg6", + "gmi_ad7_pg7", + "gmi_ad8_ph0", + "gmi_ad9_ph1", + "gmi_ad10_ph2", + "gmi_ad11_ph3", + "gmi_ad12_ph4", + "gmi_ad13_ph5", + "gmi_ad14_ph6", + "gmi_ad15_ph7", + "gmi_wr_n_pi0", + "gmi_oe_n_pi1", + "gmi_cs6_n_pi3", + "gmi_rst_n_pi4", + "gmi_iordy_pi5", + "gmi_cs7_n_pi6", + "gmi_wait_pi7", + "gmi_cs0_n_pj0", + "gmi_cs1_n_pj2", + "gmi_dqs_p_pj3", + "gmi_adv_n_pk0", + "gmi_clk_pk1", + "gmi_cs4_n_pk2", + "gmi_cs2_n_pk3", + "gmi_cs3_n_pk4", + "gmi_a16_pj7", + "gmi_a17_pb0", + "gmi_a18_pb1", + "gmi_a19_pk7", + "gen2_i2c_scl_pt5", + "gen2_i2c_sda_pt6", + "sdmmc4_dat0_paa0", + "sdmmc4_dat1_paa1", + "sdmmc4_dat2_paa2", + "sdmmc4_dat3_paa3", + "sdmmc4_dat4_paa4", + "sdmmc4_dat5_paa5", + "sdmmc4_dat6_paa6", + "sdmmc4_dat7_paa7", + "sdmmc4_clk_pcc4", + "sdmmc4_cmd_pt7", + "dap1_fs_pn0", + "dap1_din_pn1", + "dap1_dout_pn2", + "dap1_sclk_pn3", +}; + +static const char * const gmi_alt_groups[] = { + "gmi_wp_n_pc7", + "gmi_cs3_n_pk4", + "gmi_a16_pj7", +}; + +static const char * const hda_groups[] = { + "dap1_fs_pn0", + "dap1_din_pn1", + "dap1_dout_pn2", + "dap1_sclk_pn3", + "dap2_fs_pa2", + "dap2_sclk_pa3", + "dap2_din_pa4", + "dap2_dout_pa5", +}; + +static const char * const hsi_groups[] = { + "ulpi_data0_po1", + "ulpi_data1_po2", + "ulpi_data2_po3", + "ulpi_data3_po4", + "ulpi_data4_po5", + "ulpi_data5_po6", + "ulpi_data6_po7", + "ulpi_data7_po0", +}; + +static const char * const i2c1_groups[] = { + "gen1_i2c_scl_pc4", + "gen1_i2c_sda_pc5", + "gpio_w2_aud_pw2", + "gpio_w3_aud_pw3", +}; + +static const char * const i2c2_groups[] = { + "gen2_i2c_scl_pt5", + "gen2_i2c_sda_pt6", +}; + +static const char * const i2c3_groups[] = { + "cam_i2c_scl_pbb1", + "cam_i2c_sda_pbb2", +}; + +static const char * const i2c4_groups[] = { + "ddc_scl_pv4", + "ddc_sda_pv5", +}; + +static const char * const i2cpwr_groups[] = { + "pwr_i2c_scl_pz6", + "pwr_i2c_sda_pz7", +}; + +static const char * const i2s0_groups[] = { + "dap1_fs_pn0", + "dap1_din_pn1", + "dap1_dout_pn2", + "dap1_sclk_pn3", +}; + +static const char * const i2s1_groups[] = { + "dap2_fs_pa2", + "dap2_sclk_pa3", + "dap2_din_pa4", + "dap2_dout_pa5", +}; + +static const char * const i2s2_groups[] = { + "dap3_fs_pp0", + "dap3_din_pp1", + "dap3_dout_pp2", + "dap3_sclk_pp3", +}; + +static const char * const i2s3_groups[] = { + "dap4_fs_pp4", + "dap4_din_pp5", + "dap4_dout_pp6", + "dap4_sclk_pp7", +}; + +static const char * const i2s4_groups[] = { + "pcc1", + "pbb0", + "pbb7", + "pcc2", +}; + +static const char * const irda_groups[] = { + "uart2_rxd_pc3", + "uart2_txd_pc2", +}; + +static const char * const kbc_groups[] = { + "kb_row0_pr0", + "kb_row1_pr1", + "kb_row2_pr2", + "kb_row3_pr3", + "kb_row4_pr4", + "kb_row5_pr5", + "kb_row6_pr6", + "kb_row7_pr7", + "kb_row8_ps0", + "kb_row9_ps1", + "kb_row10_ps2", + "kb_col0_pq0", + "kb_col1_pq1", + "kb_col2_pq2", + "kb_col3_pq3", + "kb_col4_pq4", + "kb_col5_pq5", + "kb_col6_pq6", + "kb_col7_pq7", +}; + +static const char * const nand_groups[] = { + "gmi_wp_n_pc7", + "gmi_wait_pi7", + "gmi_adv_n_pk0", + "gmi_clk_pk1", + "gmi_cs0_n_pj0", + "gmi_cs1_n_pj2", + "gmi_cs2_n_pk3", + "gmi_cs3_n_pk4", + "gmi_cs4_n_pk2", + "gmi_cs6_n_pi3", + "gmi_cs7_n_pi6", + "gmi_ad0_pg0", + "gmi_ad1_pg1", + "gmi_ad2_pg2", + "gmi_ad3_pg3", + "gmi_ad4_pg4", + "gmi_ad5_pg5", + "gmi_ad6_pg6", + "gmi_ad7_pg7", + "gmi_ad8_ph0", + "gmi_ad9_ph1", + "gmi_ad10_ph2", + "gmi_ad11_ph3", + "gmi_ad12_ph4", + "gmi_ad13_ph5", + "gmi_ad14_ph6", + "gmi_ad15_ph7", + "gmi_wr_n_pi0", + "gmi_oe_n_pi1", + "gmi_dqs_p_pj3", + "gmi_rst_n_pi4", +}; + +static const char * const nand_alt_groups[] = { + "gmi_cs6_n_pi3", + "gmi_cs7_n_pi6", + "gmi_rst_n_pi4", +}; + +static const char * const owr_groups[] = { + "pu0", + "kb_col4_pq4", + "owr", + "sdmmc3_cd_n_pv2", +}; + +static const char * const pmi_groups[] = { + "pwr_int_n", +}; + +static const char * const pwm0_groups[] = { + "sdmmc1_dat2_py5", + "uart3_rts_n_pc0", + "pu3", + "gmi_ad8_ph0", + "sdmmc3_dat3_pb4", +}; + +static const char * const pwm1_groups[] = { + "sdmmc1_dat1_py6", + "pu4", + "gmi_ad9_ph1", + "sdmmc3_dat2_pb5", +}; + +static const char * const pwm2_groups[] = { + "pu5", + "gmi_ad10_ph2", + "kb_col3_pq3", + "sdmmc3_dat1_pb6", +}; + +static const char * const pwm3_groups[] = { + "pu6", + "gmi_ad11_ph3", + "sdmmc3_cmd_pa7", +}; + +static const char * const pwron_groups[] = { + "core_pwr_req", +}; + +static const char * const reset_out_n_groups[] = { + "reset_out_n", +}; + +static const char * const rsvd1_groups[] = { + "pv1", + "hdmi_int_pn7", + "pu1", + "pu2", + "gmi_wp_n_pc7", + "gmi_adv_n_pk0", + "gmi_cs0_n_pj0", + "gmi_cs1_n_pj2", + "gmi_ad0_pg0", + "gmi_ad1_pg1", + "gmi_ad2_pg2", + "gmi_ad3_pg3", + "gmi_ad4_pg4", + "gmi_ad5_pg5", + "gmi_ad6_pg6", + "gmi_ad7_pg7", + "gmi_wr_n_pi0", + "gmi_oe_n_pi1", + "gpio_x4_aud_px4", + "gpio_x5_aud_px5", + "gpio_x7_aud_px7", + + "reset_out_n", +}; + +static const char * const rsvd2_groups[] = { + "pv0", + "pv1", + "sdmmc1_dat0_py7", + "clk2_out_pw5", + "clk2_req_pcc5", + "hdmi_int_pn7", + "ddc_scl_pv4", + "ddc_sda_pv5", + "uart3_txd_pw6", + "uart3_rxd_pw7", + "gen1_i2c_scl_pc4", + "gen1_i2c_sda_pc5", + "dap4_fs_pp4", + "dap4_din_pp5", + "dap4_dout_pp6", + "dap4_sclk_pp7", + "clk3_out_pee0", + "clk3_req_pee1", + "gmi_iordy_pi5", + "gmi_a17_pb0", + "gmi_a18_pb1", + "gen2_i2c_scl_pt5", + "gen2_i2c_sda_pt6", + "sdmmc4_clk_pcc4", + "sdmmc4_cmd_pt7", + "sdmmc4_dat7_paa7", + "pcc1", + "pbb7", + "pcc2", + "pwr_i2c_scl_pz6", + "pwr_i2c_sda_pz7", + "kb_row0_pr0", + "kb_row1_pr1", + "kb_row2_pr2", + "kb_row7_pr7", + "kb_row8_ps0", + "kb_row9_ps1", + "kb_row10_ps2", + "kb_col1_pq1", + "kb_col2_pq2", + "kb_col5_pq5", + "kb_col6_pq6", + "kb_col7_pq7", + "sys_clk_req_pz5", + "core_pwr_req", + "cpu_pwr_req", + "pwr_int_n", + "owr", + "spdif_out_pk5", + "gpio_x1_aud_px1", + "sdmmc3_clk_pa6", + "sdmmc3_dat0_pb7", + "gpio_w2_aud_pw2", + "usb_vbus_en0_pn4", + "usb_vbus_en1_pn5", + "sdmmc3_clk_lb_out_pee4", + "sdmmc3_clk_lb_in_pee5", + "reset_out_n", +}; + +static const char * const rsvd3_groups[] = { + "pv0", + "pv1", + "sdmmc1_clk_pz0", + "clk2_out_pw5", + "clk2_req_pcc5", + "hdmi_int_pn7", + "ddc_scl_pv4", + "ddc_sda_pv5", + "uart2_rts_n_pj6", + "uart2_cts_n_pj5", + "uart3_txd_pw6", + "uart3_rxd_pw7", + "pu0", + "pu1", + "pu2", + "gen1_i2c_scl_pc4", + "gen1_i2c_sda_pc5", + "dap4_din_pp5", + "dap4_sclk_pp7", + "clk3_out_pee0", + "clk3_req_pee1", + "pcc1", + "cam_i2c_scl_pbb1", + "cam_i2c_sda_pbb2", + "pbb7", + "pcc2", + "pwr_i2c_scl_pz6", + "pwr_i2c_sda_pz7", + "kb_row0_pr0", + "kb_row1_pr1", + "kb_row2_pr2", + "kb_row3_pr3", + "kb_row9_ps1", + "kb_row10_ps2", + "clk_32k_out_pa0", + "sys_clk_req_pz5", + "core_pwr_req", + "cpu_pwr_req", + "pwr_int_n", + "owr", + "clk1_req_pee2", + "clk1_out_pw4", + "spdif_out_pk5", + "spdif_in_pk6", + "dap2_fs_pa2", + "dap2_sclk_pa3", + "dap2_din_pa4", + "dap2_dout_pa5", + "dvfs_pwm_px0", + "gpio_x1_aud_px1", + "gpio_x3_aud_px3", + "dvfs_clk_px2", + "sdmmc3_clk_pa6", + "sdmmc3_dat0_pb7", + "hdmi_cec_pee3", + "sdmmc3_cd_n_pv2", + "usb_vbus_en0_pn4", + "usb_vbus_en1_pn5", + "sdmmc3_clk_lb_out_pee4", + "sdmmc3_clk_lb_in_pee5", + "reset_out_n", +}; + +static const char * const rsvd4_groups[] = { + "pv0", + "pv1", + "sdmmc1_clk_pz0", + "clk2_out_pw5", + "clk2_req_pcc5", + "hdmi_int_pn7", + "ddc_scl_pv4", + "ddc_sda_pv5", + "pu0", + "pu1", + "pu2", + "gen1_i2c_scl_pc4", + "gen1_i2c_sda_pc5", + "dap4_fs_pp4", + "dap4_din_pp5", + "dap4_dout_pp6", + "dap4_sclk_pp7", + "clk3_out_pee0", + "clk3_req_pee1", + "gmi_ad0_pg0", + "gmi_ad1_pg1", + "gmi_ad2_pg2", + "gmi_ad3_pg3", + "gmi_ad4_pg4", + "gmi_ad12_ph4", + "gmi_ad13_ph5", + "gmi_rst_n_pi4", + "gen2_i2c_scl_pt5", + "gen2_i2c_sda_pt6", + "sdmmc4_clk_pcc4", + "sdmmc4_cmd_pt7", + "sdmmc4_dat0_paa0", + "sdmmc4_dat1_paa1", + "sdmmc4_dat2_paa2", + "sdmmc4_dat3_paa3", + "sdmmc4_dat4_paa4", + "sdmmc4_dat5_paa5", + "sdmmc4_dat6_paa6", + "sdmmc4_dat7_paa7", + "cam_mclk_pcc0", + "pcc1", + "cam_i2c_scl_pbb1", + "cam_i2c_sda_pbb2", + "pbb3", + "pbb4", + "pbb5", + "pbb6", + "pbb7", + "pcc2", + "pwr_i2c_scl_pz6", + "pwr_i2c_sda_pz7", + "kb_row0_pr0", + "kb_row1_pr1", + "kb_row2_pr2", + "kb_col2_pq2", + "kb_col5_pq5", + "kb_col6_pq6", + "kb_col7_pq7", + "clk_32k_out_pa0", + "sys_clk_req_pz5", + "core_pwr_req", + "cpu_pwr_req", + "pwr_int_n", + "owr", + "dap1_fs_pn0", + "dap1_din_pn1", + "dap1_dout_pn2", + "dap1_sclk_pn3", + "clk1_req_pee2", + "clk1_out_pw4", + "spdif_in_pk6", + "spdif_out_pk5", + "dap2_fs_pa2", + "dap2_sclk_pa3", + "dap2_din_pa4", + "dap2_dout_pa5", + "dvfs_pwm_px0", + "gpio_x1_aud_px1", + "gpio_x3_aud_px3", + "dvfs_clk_px2", + "gpio_x5_aud_px5", + "gpio_x6_aud_px6", + "gpio_x7_aud_px7", + "sdmmc3_cd_n_pv2", + "usb_vbus_en0_pn4", + "usb_vbus_en1_pn5", + "sdmmc3_clk_lb_in_pee5", + "sdmmc3_clk_lb_out_pee4", +}; + +static const char * const sdmmc1_groups[] = { + + "sdmmc1_clk_pz0", + "sdmmc1_cmd_pz1", + "sdmmc1_dat3_py4", + "sdmmc1_dat2_py5", + "sdmmc1_dat1_py6", + "sdmmc1_dat0_py7", + "uart3_cts_n_pa1", + "kb_col5_pq5", + "sdmmc1_wp_n_pv3", +}; + +static const char * const sdmmc2_groups[] = { + "gmi_iordy_pi5", + "gmi_clk_pk1", + "gmi_cs2_n_pk3", + "gmi_cs3_n_pk4", + "gmi_cs7_n_pi6", + "gmi_ad12_ph4", + "gmi_ad13_ph5", + "gmi_ad14_ph6", + "gmi_ad15_ph7", + "gmi_dqs_p_pj3", +}; + +static const char * const sdmmc3_groups[] = { + "kb_col4_pq4", + "sdmmc3_clk_pa6", + "sdmmc3_cmd_pa7", + "sdmmc3_dat0_pb7", + "sdmmc3_dat1_pb6", + "sdmmc3_dat2_pb5", + "sdmmc3_dat3_pb4", + "hdmi_cec_pee3", + "sdmmc3_cd_n_pv2", + "sdmmc3_clk_lb_in_pee5", + "sdmmc3_clk_lb_out_pee4", +}; + +static const char * const sdmmc4_groups[] = { + "sdmmc4_clk_pcc4", + "sdmmc4_cmd_pt7", + "sdmmc4_dat0_paa0", + "sdmmc4_dat1_paa1", + "sdmmc4_dat2_paa2", + "sdmmc4_dat3_paa3", + "sdmmc4_dat4_paa4", + "sdmmc4_dat5_paa5", + "sdmmc4_dat6_paa6", + "sdmmc4_dat7_paa7", +}; + +static const char * const soc_groups[] = { + "gmi_cs1_n_pj2", + "gmi_oe_n_pi1", + "clk_32k_out_pa0", + "hdmi_cec_pee3", +}; + +static const char * const spdif_groups[] = { + "sdmmc1_cmd_pz1", + "sdmmc1_dat3_py4", + "uart2_rxd_pc3", + "uart2_txd_pc2", + "spdif_in_pk6", + "spdif_out_pk5", +}; + +static const char * const spi1_groups[] = { + "ulpi_clk_py0", + "ulpi_dir_py1", + "ulpi_nxt_py2", + "ulpi_stp_py3", + "gpio_x3_aud_px3", + "gpio_x4_aud_px4", + "gpio_x5_aud_px5", + "gpio_x6_aud_px6", + "gpio_x7_aud_px7", + "gpio_w3_aud_pw3", +}; + +static const char * const spi2_groups[] = { + "ulpi_data4_po5", + "ulpi_data5_po6", + "ulpi_data6_po7", + "ulpi_data7_po0", + "kb_row4_pr4", + "kb_row5_pr5", + "kb_col0_pq0", + "kb_col1_pq1", + "kb_col2_pq2", + "kb_col6_pq6", + "kb_col7_pq7", + "gpio_x4_aud_px4", + "gpio_x5_aud_px5", + "gpio_x6_aud_px6", + "gpio_x7_aud_px7", + "gpio_w2_aud_pw2", + "gpio_w3_aud_pw3", +}; + +static const char * const spi3_groups[] = { + "ulpi_data0_po1", + "ulpi_data1_po2", + "ulpi_data2_po3", + "ulpi_data3_po4", + "sdmmc4_dat0_paa0", + "sdmmc4_dat1_paa1", + "sdmmc4_dat2_paa2", + "sdmmc4_dat3_paa3", + "sdmmc4_dat4_paa4", + "sdmmc4_dat5_paa5", + "sdmmc4_dat6_paa6", + "sdmmc3_clk_pa6", + "sdmmc3_cmd_pa7", + "sdmmc3_dat0_pb7", + "sdmmc3_dat1_pb6", + "sdmmc3_dat2_pb5", + "sdmmc3_dat3_pb4", +}; + +static const char * const spi4_groups[] = { + "sdmmc1_cmd_pz1", + "sdmmc1_dat3_py4", + "sdmmc1_dat2_py5", + "sdmmc1_dat1_py6", + "sdmmc1_dat0_py7", + "uart2_rxd_pc3", + "uart2_txd_pc2", + "uart2_rts_n_pj6", + "uart2_cts_n_pj5", + "uart3_txd_pw6", + "uart3_rxd_pw7", + "uart3_cts_n_pa1", + "gmi_wait_pi7", + "gmi_cs6_n_pi3", + "gmi_ad5_pg5", + "gmi_ad6_pg6", + "gmi_ad7_pg7", + "gmi_a19_pk7", + "gmi_wr_n_pi0", + "sdmmc1_wp_n_pv3", +}; + +static const char * const spi5_groups[] = { + "ulpi_clk_py0", + "ulpi_dir_py1", + "ulpi_nxt_py2", + "ulpi_stp_py3", + "dap3_fs_pp0", + "dap3_din_pp1", + "dap3_dout_pp2", + "dap3_sclk_pp3", +}; + +static const char * const spi6_groups[] = { + "dvfs_pwm_px0", + "gpio_x1_aud_px1", + "gpio_x3_aud_px3", + "dvfs_clk_px2", + "gpio_x6_aud_px6", + "gpio_w2_aud_pw2", + "gpio_w3_aud_pw3", +}; + +static const char * const sysclk_groups[] = { + "sys_clk_req_pz5", +}; + +static const char * const trace_groups[] = { + "gmi_iordy_pi5", + "gmi_adv_n_pk0", + "gmi_clk_pk1", + "gmi_cs2_n_pk3", + "gmi_cs4_n_pk2", + "gmi_a16_pj7", + "gmi_a17_pb0", + "gmi_a18_pb1", + "gmi_a19_pk7", + "gmi_dqs_p_pj3", +}; + +static const char * const uarta_groups[] = { + "ulpi_data0_po1", + "ulpi_data1_po2", + "ulpi_data2_po3", + "ulpi_data3_po4", + "ulpi_data4_po5", + "ulpi_data5_po6", + "ulpi_data6_po7", + "ulpi_data7_po0", + "sdmmc1_cmd_pz1", + "sdmmc1_dat3_py4", + "sdmmc1_dat2_py5", + "sdmmc1_dat1_py6", + "sdmmc1_dat0_py7", + "uart2_rxd_pc3", + "uart2_txd_pc2", + "uart2_rts_n_pj6", + "uart2_cts_n_pj5", + "pu0", + "pu1", + "pu2", + "pu3", + "pu4", + "pu5", + "pu6", + "kb_row7_pr7", + "kb_row8_ps0", + "kb_row9_ps1", + "kb_row10_ps2", + "kb_col3_pq3", + "kb_col4_pq4", + "sdmmc3_cmd_pa7", + "sdmmc3_dat1_pb6", + "sdmmc1_wp_n_pv3", +}; + +static const char * const uartb_groups[] = { + "uart2_rts_n_pj6", + "uart2_cts_n_pj5", +}; + +static const char * const uartc_groups[] = { + "uart3_txd_pw6", + "uart3_rxd_pw7", + "uart3_cts_n_pa1", + "uart3_rts_n_pc0", +}; + +static const char * const uartd_groups[] = { + "ulpi_clk_py0", + "ulpi_dir_py1", + "ulpi_nxt_py2", + "ulpi_stp_py3", + "gmi_a16_pj7", + "gmi_a17_pb0", + "gmi_a18_pb1", + "gmi_a19_pk7", +}; + +static const char * const ulpi_groups[] = { + "ulpi_data0_po1", + "ulpi_data1_po2", + "ulpi_data2_po3", + "ulpi_data3_po4", + "ulpi_data4_po5", + "ulpi_data5_po6", + "ulpi_data6_po7", + "ulpi_data7_po0", + "ulpi_clk_py0", + "ulpi_dir_py1", + "ulpi_nxt_py2", + "ulpi_stp_py3", +}; + +static const char * const usb_groups[] = { + "pv0", + "pu6", + "gmi_cs0_n_pj0", + "gmi_cs4_n_pk2", + "gmi_ad11_ph3", + "kb_col0_pq0", + "spdif_in_pk6", + "usb_vbus_en0_pn4", + "usb_vbus_en1_pn5", +}; + +static const char * const vgp1_groups[] = { + "cam_i2c_scl_pbb1", +}; + +static const char * const vgp2_groups[] = { + "cam_i2c_sda_pbb2", +}; + +static const char * const vgp3_groups[] = { + "pbb3", +}; + +static const char * const vgp4_groups[] = { + "pbb4", +}; + +static const char * const vgp5_groups[] = { + "pbb5", +}; + +static const char * const vgp6_groups[] = { + "pbb6", +}; + +static const char * const vi_groups[] = { + "cam_mclk_pcc0", + "pbb0", +}; + +static const char * const vi_alt1_groups[] = { + "cam_mclk_pcc0", + "pbb0", +}; + +static const char * const vi_alt3_groups[] = { + "cam_mclk_pcc0", + "pbb0", +}; + +#define FUNCTION(fname) \ + { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +static const struct tegra_function tegra114_functions[] = { + FUNCTION(blink), + FUNCTION(cec), + FUNCTION(cldvfs), + FUNCTION(clk12), + FUNCTION(cpu), + FUNCTION(dap), + FUNCTION(dap1), + FUNCTION(dap2), + FUNCTION(dev3), + FUNCTION(displaya), + FUNCTION(displaya_alt), + FUNCTION(displayb), + FUNCTION(dtv), + FUNCTION(emc_dll), + FUNCTION(extperiph1), + FUNCTION(extperiph2), + FUNCTION(extperiph3), + FUNCTION(gmi), + FUNCTION(gmi_alt), + FUNCTION(hda), + FUNCTION(hsi), + FUNCTION(i2c1), + FUNCTION(i2c2), + FUNCTION(i2c3), + FUNCTION(i2c4), + FUNCTION(i2cpwr), + FUNCTION(i2s0), + FUNCTION(i2s1), + FUNCTION(i2s2), + FUNCTION(i2s3), + FUNCTION(i2s4), + FUNCTION(irda), + FUNCTION(kbc), + FUNCTION(nand), + FUNCTION(nand_alt), + FUNCTION(owr), + FUNCTION(pmi), + FUNCTION(pwm0), + FUNCTION(pwm1), + FUNCTION(pwm2), + FUNCTION(pwm3), + FUNCTION(pwron), + FUNCTION(reset_out_n), + FUNCTION(rsvd1), + FUNCTION(rsvd2), + FUNCTION(rsvd3), + FUNCTION(rsvd4), + FUNCTION(sdmmc1), + FUNCTION(sdmmc2), + FUNCTION(sdmmc3), + FUNCTION(sdmmc4), + FUNCTION(soc), + FUNCTION(spdif), + FUNCTION(spi1), + FUNCTION(spi2), + FUNCTION(spi3), + FUNCTION(spi4), + FUNCTION(spi5), + FUNCTION(spi6), + FUNCTION(sysclk), + FUNCTION(trace), + FUNCTION(uarta), + FUNCTION(uartb), + FUNCTION(uartc), + FUNCTION(uartd), + FUNCTION(ulpi), + FUNCTION(usb), + FUNCTION(vgp1), + FUNCTION(vgp2), + FUNCTION(vgp3), + FUNCTION(vgp4), + FUNCTION(vgp5), + FUNCTION(vgp6), + FUNCTION(vi), + FUNCTION(vi_alt1), + FUNCTION(vi_alt3), +}; + +#define DRV_PINGROUP_REG_START 0x868 /* bank 0 */ +#define PINGROUP_REG_START 0x3000 /* bank 1 */ + +#define PINGROUP_REG_Y(r) ((r) - PINGROUP_REG_START) +#define PINGROUP_REG_N(r) -1 + +#define PINGROUP(pg_name, f0, f1, f2, f3, f_safe, r, od, ior, rcv_sel) \ + { \ + .name = #pg_name, \ + .pins = pg_name##_pins, \ + .npins = ARRAY_SIZE(pg_name##_pins), \ + .funcs = { \ + TEGRA_MUX_##f0, \ + TEGRA_MUX_##f1, \ + TEGRA_MUX_##f2, \ + TEGRA_MUX_##f3, \ + }, \ + .func_safe = TEGRA_MUX_##f_safe, \ + .mux_reg = PINGROUP_REG_Y(r), \ + .mux_bank = 1, \ + .mux_bit = 0, \ + .pupd_reg = PINGROUP_REG_Y(r), \ + .pupd_bank = 1, \ + .pupd_bit = 2, \ + .tri_reg = PINGROUP_REG_Y(r), \ + .tri_bank = 1, \ + .tri_bit = 4, \ + .einput_reg = PINGROUP_REG_Y(r), \ + .einput_bank = 1, \ + .einput_bit = 5, \ + .odrain_reg = PINGROUP_REG_##od(r), \ + .odrain_bank = 1, \ + .odrain_bit = 6, \ + .lock_reg = PINGROUP_REG_Y(r), \ + .lock_bank = 1, \ + .lock_bit = 7, \ + .ioreset_reg = PINGROUP_REG_##ior(r), \ + .ioreset_bank = 1, \ + .ioreset_bit = 8, \ + .rcv_sel_reg = PINGROUP_REG_##rcv_sel(r), \ + .rcv_sel_bank = 1, \ + .rcv_sel_bit = 9, \ + .drv_reg = -1, \ + .drvtype_reg = -1, \ + } + +#define DRV_PINGROUP_DVRTYPE_Y(r) ((r) - DRV_PINGROUP_REG_START) +#define DRV_PINGROUP_DVRTYPE_N(r) -1 + +#define DRV_PINGROUP(pg_name, r, hsm_b, schmitt_b, lpmd_b, \ + drvdn_b, drvdn_w, drvup_b, drvup_w, \ + slwr_b, slwr_w, slwf_b, slwf_w, \ + drvtype) \ + { \ + .name = "drive_" #pg_name, \ + .pins = drive_##pg_name##_pins, \ + .npins = ARRAY_SIZE(drive_##pg_name##_pins), \ + .mux_reg = -1, \ + .pupd_reg = -1, \ + .tri_reg = -1, \ + .einput_reg = -1, \ + .odrain_reg = -1, \ + .lock_reg = -1, \ + .ioreset_reg = -1, \ + .rcv_sel_reg = -1, \ + .drv_reg = DRV_PINGROUP_DVRTYPE_Y(r), \ + .drv_bank = 0, \ + .hsm_bit = hsm_b, \ + .schmitt_bit = schmitt_b, \ + .lpmd_bit = lpmd_b, \ + .drvdn_bit = drvdn_b, \ + .drvdn_width = drvdn_w, \ + .drvup_bit = drvup_b, \ + .drvup_width = drvup_w, \ + .slwr_bit = slwr_b, \ + .slwr_width = slwr_w, \ + .slwf_bit = slwf_b, \ + .slwf_width = slwf_w, \ + .drvtype_reg = DRV_PINGROUP_DVRTYPE_##drvtype(r), \ + .drvtype_bank = 0, \ + .drvtype_bit = 6, \ + } + +static const struct tegra_pingroup tegra114_groups[] = { + /* pg_name, f0, f1, f2, f3, safe, r, od, ior, rcv_sel */ + /* FIXME: Fill in correct data in safe column */ + PINGROUP(ulpi_data0_po1, SPI3, HSI, UARTA, ULPI, ULPI, 0x3000, N, N, N), + PINGROUP(ulpi_data1_po2, SPI3, HSI, UARTA, ULPI, ULPI, 0x3004, N, N, N), + PINGROUP(ulpi_data2_po3, SPI3, HSI, UARTA, ULPI, ULPI, 0x3008, N, N, N), + PINGROUP(ulpi_data3_po4, SPI3, HSI, UARTA, ULPI, ULPI, 0x300c, N, N, N), + PINGROUP(ulpi_data4_po5, SPI2, HSI, UARTA, ULPI, ULPI, 0x3010, N, N, N), + PINGROUP(ulpi_data5_po6, SPI2, HSI, UARTA, ULPI, ULPI, 0x3014, N, N, N), + PINGROUP(ulpi_data6_po7, SPI2, HSI, UARTA, ULPI, ULPI, 0x3018, N, N, N), + PINGROUP(ulpi_data7_po0, SPI2, HSI, UARTA, ULPI, ULPI, 0x301c, N, N, N), + PINGROUP(ulpi_clk_py0, SPI1, SPI5, UARTD, ULPI, ULPI, 0x3020, N, N, N), + PINGROUP(ulpi_dir_py1, SPI1, SPI5, UARTD, ULPI, ULPI, 0x3024, N, N, N), + PINGROUP(ulpi_nxt_py2, SPI1, SPI5, UARTD, ULPI, ULPI, 0x3028, N, N, N), + PINGROUP(ulpi_stp_py3, SPI1, SPI5, UARTD, ULPI, ULPI, 0x302c, N, N, N), + PINGROUP(dap3_fs_pp0, I2S2, SPI5, DISPLAYA, DISPLAYB, I2S2, 0x3030, N, N, N), + PINGROUP(dap3_din_pp1, I2S2, SPI5, DISPLAYA, DISPLAYB, I2S2, 0x3034, N, N, N), + PINGROUP(dap3_dout_pp2, I2S2, SPI5, DISPLAYA, DISPLAYB, I2S2, 0x3038, N, N, N), + PINGROUP(dap3_sclk_pp3, I2S2, SPI5, DISPLAYA, DISPLAYB, I2S2, 0x303c, N, N, N), + PINGROUP(pv0, USB, RSVD2, RSVD3, RSVD4, RSVD4, 0x3040, N, N, N), + PINGROUP(pv1, RSVD1, RSVD2, RSVD3, RSVD4, RSVD4, 0x3044, N, N, N), + PINGROUP(sdmmc1_clk_pz0, SDMMC1, CLK12, RSVD3, RSVD4, RSVD4, 0x3048, N, N, N), + PINGROUP(sdmmc1_cmd_pz1, SDMMC1, SPDIF, SPI4, UARTA, SDMMC1, 0x304c, N, N, N), + PINGROUP(sdmmc1_dat3_py4, SDMMC1, SPDIF, SPI4, UARTA, SDMMC1, 0x3050, N, N, N), + PINGROUP(sdmmc1_dat2_py5, SDMMC1, PWM0, SPI4, UARTA, SDMMC1, 0x3054, N, N, N), + PINGROUP(sdmmc1_dat1_py6, SDMMC1, PWM1, SPI4, UARTA, SDMMC1, 0x3058, N, N, N), + PINGROUP(sdmmc1_dat0_py7, SDMMC1, RSVD2, SPI4, UARTA, RSVD2, 0x305c, N, N, N), + PINGROUP(clk2_out_pw5, EXTPERIPH2, RSVD2, RSVD3, RSVD4, RSVD4, 0x3068, N, N, N), + PINGROUP(clk2_req_pcc5, DAP, RSVD2, RSVD3, RSVD4, RSVD4, 0x306c, N, N, N), + PINGROUP(hdmi_int_pn7, RSVD1, RSVD2, RSVD3, RSVD4, RSVD4, 0x3110, N, N, Y), + PINGROUP(ddc_scl_pv4, I2C4, RSVD2, RSVD3, RSVD4, RSVD4, 0x3114, N, N, Y), + PINGROUP(ddc_sda_pv5, I2C4, RSVD2, RSVD3, RSVD4, RSVD4, 0x3118, N, N, Y), + PINGROUP(uart2_rxd_pc3, IRDA, SPDIF, UARTA, SPI4, IRDA, 0x3164, N, N, N), + PINGROUP(uart2_txd_pc2, IRDA, SPDIF, UARTA, SPI4, IRDA, 0x3168, N, N, N), + PINGROUP(uart2_rts_n_pj6, UARTA, UARTB, RSVD3, SPI4, RSVD3, 0x316c, N, N, N), + PINGROUP(uart2_cts_n_pj5, UARTA, UARTB, RSVD3, SPI4, RSVD3, 0x3170, N, N, N), + PINGROUP(uart3_txd_pw6, UARTC, RSVD2, RSVD3, SPI4, RSVD3, 0x3174, N, N, N), + PINGROUP(uart3_rxd_pw7, UARTC, RSVD2, RSVD3, SPI4, RSVD3, 0x3178, N, N, N), + PINGROUP(uart3_cts_n_pa1, UARTC, SDMMC1, DTV, SPI4, UARTC, 0x317c, N, N, N), + PINGROUP(uart3_rts_n_pc0, UARTC, PWM0, DTV, DISPLAYA, UARTC, 0x3180, N, N, N), + PINGROUP(pu0, OWR, UARTA, RSVD3, RSVD4, RSVD4, 0x3184, N, N, N), + PINGROUP(pu1, RSVD1, UARTA, RSVD3, RSVD4, RSVD4, 0x3188, N, N, N), + PINGROUP(pu2, RSVD1, UARTA, RSVD3, RSVD4, RSVD4, 0x318c, N, N, N), + PINGROUP(pu3, PWM0, UARTA, DISPLAYA, DISPLAYB, PWM0, 0x3190, N, N, N), + PINGROUP(pu4, PWM1, UARTA, DISPLAYA, DISPLAYB, PWM1, 0x3194, N, N, N), + PINGROUP(pu5, PWM2, UARTA, DISPLAYA, DISPLAYB, PWM2, 0x3198, N, N, N), + PINGROUP(pu6, PWM3, UARTA, USB, DISPLAYB, PWM3, 0x319c, N, N, N), + PINGROUP(gen1_i2c_sda_pc5, I2C1, RSVD2, RSVD3, RSVD4, RSVD4, 0x31a0, Y, N, N), + PINGROUP(gen1_i2c_scl_pc4, I2C1, RSVD2, RSVD3, RSVD4, RSVD4, 0x31a4, Y, N, N), + PINGROUP(dap4_fs_pp4, I2S3, RSVD2, DTV, RSVD4, RSVD4, 0x31a8, N, N, N), + PINGROUP(dap4_din_pp5, I2S3, RSVD2, RSVD3, RSVD4, RSVD4, 0x31ac, N, N, N), + PINGROUP(dap4_dout_pp6, I2S3, RSVD2, DTV, RSVD4, RSVD4, 0x31b0, N, N, N), + PINGROUP(dap4_sclk_pp7, I2S3, RSVD2, RSVD3, RSVD4, RSVD4, 0x31b4, N, N, N), + PINGROUP(clk3_out_pee0, EXTPERIPH3, RSVD2, RSVD3, RSVD4, RSVD4, 0x31b8, N, N, N), + PINGROUP(clk3_req_pee1, DEV3, RSVD2, RSVD3, RSVD4, RSVD4, 0x31bc, N, N, N), + PINGROUP(gmi_wp_n_pc7, RSVD1, NAND, GMI, GMI_ALT, RSVD1, 0x31c0, N, N, N), + PINGROUP(gmi_iordy_pi5, SDMMC2, RSVD2, GMI, TRACE, RSVD2, 0x31c4, N, N, N), + PINGROUP(gmi_wait_pi7, SPI4, NAND, GMI, DTV, NAND, 0x31c8, N, N, N), + PINGROUP(gmi_adv_n_pk0, RSVD1, NAND, GMI, TRACE, RSVD1, 0x31cc, N, N, N), + PINGROUP(gmi_clk_pk1, SDMMC2, NAND, GMI, TRACE, GMI, 0x31d0, N, N, N), + PINGROUP(gmi_cs0_n_pj0, RSVD1, NAND, GMI, USB, RSVD1, 0x31d4, N, N, N), + PINGROUP(gmi_cs1_n_pj2, RSVD1, NAND, GMI, SOC, RSVD1, 0x31d8, N, N, N), + PINGROUP(gmi_cs2_n_pk3, SDMMC2, NAND, GMI, TRACE, GMI, 0x31dc, N, N, N), + PINGROUP(gmi_cs3_n_pk4, SDMMC2, NAND, GMI, GMI_ALT, GMI, 0x31e0, N, N, N), + PINGROUP(gmi_cs4_n_pk2, USB, NAND, GMI, TRACE, GMI, 0x31e4, N, N, N), + PINGROUP(gmi_cs6_n_pi3, NAND, NAND_ALT, GMI, SPI4, NAND, 0x31e8, N, N, N), + PINGROUP(gmi_cs7_n_pi6, NAND, NAND_ALT, GMI, SDMMC2, NAND, 0x31ec, N, N, N), + PINGROUP(gmi_ad0_pg0, RSVD1, NAND, GMI, RSVD4, RSVD4, 0x31f0, N, N, N), + PINGROUP(gmi_ad1_pg1, RSVD1, NAND, GMI, RSVD4, RSVD4, 0x31f4, N, N, N), + PINGROUP(gmi_ad2_pg2, RSVD1, NAND, GMI, RSVD4, RSVD4, 0x31f8, N, N, N), + PINGROUP(gmi_ad3_pg3, RSVD1, NAND, GMI, RSVD4, RSVD4, 0x31fc, N, N, N), + PINGROUP(gmi_ad4_pg4, RSVD1, NAND, GMI, RSVD4, RSVD4, 0x3200, N, N, N), + PINGROUP(gmi_ad5_pg5, RSVD1, NAND, GMI, SPI4, RSVD1, 0x3204, N, N, N), + PINGROUP(gmi_ad6_pg6, RSVD1, NAND, GMI, SPI4, RSVD1, 0x3208, N, N, N), + PINGROUP(gmi_ad7_pg7, RSVD1, NAND, GMI, SPI4, RSVD1, 0x320c, N, N, N), + PINGROUP(gmi_ad8_ph0, PWM0, NAND, GMI, DTV, GMI, 0x3210, N, N, N), + PINGROUP(gmi_ad9_ph1, PWM1, NAND, GMI, CLDVFS, GMI, 0x3214, N, N, N), + PINGROUP(gmi_ad10_ph2, PWM2, NAND, GMI, CLDVFS, GMI, 0x3218, N, N, N), + PINGROUP(gmi_ad11_ph3, PWM3, NAND, GMI, USB, GMI, 0x321c, N, N, N), + PINGROUP(gmi_ad12_ph4, SDMMC2, NAND, GMI, RSVD4, RSVD4, 0x3220, N, N, N), + PINGROUP(gmi_ad13_ph5, SDMMC2, NAND, GMI, RSVD4, RSVD4, 0x3224, N, N, N), + PINGROUP(gmi_ad14_ph6, SDMMC2, NAND, GMI, DTV, GMI, 0x3228, N, N, N), + PINGROUP(gmi_ad15_ph7, SDMMC2, NAND, GMI, DTV, GMI, 0x322c, N, N, N), + PINGROUP(gmi_a16_pj7, UARTD, TRACE, GMI, GMI_ALT, GMI, 0x3230, N, N, N), + PINGROUP(gmi_a17_pb0, UARTD, RSVD2, GMI, TRACE, RSVD2, 0x3234, N, N, N), + PINGROUP(gmi_a18_pb1, UARTD, RSVD2, GMI, TRACE, RSVD2, 0x3238, N, N, N), + PINGROUP(gmi_a19_pk7, UARTD, SPI4, GMI, TRACE, GMI, 0x323c, N, N, N), + PINGROUP(gmi_wr_n_pi0, RSVD1, NAND, GMI, SPI4, RSVD1, 0x3240, N, N, N), + PINGROUP(gmi_oe_n_pi1, RSVD1, NAND, GMI, SOC, RSVD1, 0x3244, N, N, N), + PINGROUP(gmi_dqs_p_pj3, SDMMC2, NAND, GMI, TRACE, NAND, 0x3248, N, N, N), + PINGROUP(gmi_rst_n_pi4, NAND, NAND_ALT, GMI, RSVD4, RSVD4, 0x324c, N, N, N), + PINGROUP(gen2_i2c_scl_pt5, I2C2, RSVD2, GMI, RSVD4, RSVD4, 0x3250, Y, N, N), + PINGROUP(gen2_i2c_sda_pt6, I2C2, RSVD2, GMI, RSVD4, RSVD4, 0x3254, Y, N, N), + PINGROUP(sdmmc4_clk_pcc4, SDMMC4, RSVD2, GMI, RSVD4, RSVD4, 0x3258, N, Y, N), + PINGROUP(sdmmc4_cmd_pt7, SDMMC4, RSVD2, GMI, RSVD4, RSVD4, 0x325c, N, Y, N), + PINGROUP(sdmmc4_dat0_paa0, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x3260, N, Y, N), + PINGROUP(sdmmc4_dat1_paa1, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x3264, N, Y, N), + PINGROUP(sdmmc4_dat2_paa2, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x3268, N, Y, N), + PINGROUP(sdmmc4_dat3_paa3, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x326c, N, Y, N), + PINGROUP(sdmmc4_dat4_paa4, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x3270, N, Y, N), + PINGROUP(sdmmc4_dat5_paa5, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x3274, N, Y, N), + PINGROUP(sdmmc4_dat6_paa6, SDMMC4, SPI3, GMI, RSVD4, RSVD4, 0x3278, N, Y, N), + PINGROUP(sdmmc4_dat7_paa7, SDMMC4, RSVD2, GMI, RSVD4, RSVD4, 0x327c, N, Y, N), + PINGROUP(cam_mclk_pcc0, VI, VI_ALT1, VI_ALT3, RSVD4, RSVD4, 0x3284, N, N, N), + PINGROUP(pcc1, I2S4, RSVD2, RSVD3, RSVD4, RSVD4, 0x3288, N, N, N), + PINGROUP(pbb0, I2S4, VI, VI_ALT1, VI_ALT3, I2S4, 0x328c, N, N, N), + PINGROUP(cam_i2c_scl_pbb1, VGP1, I2C3, RSVD3, RSVD4, RSVD4, 0x3290, Y, N, N), + PINGROUP(cam_i2c_sda_pbb2, VGP2, I2C3, RSVD3, RSVD4, RSVD4, 0x3294, Y, N, N), + PINGROUP(pbb3, VGP3, DISPLAYA, DISPLAYB, RSVD4, RSVD4, 0x3298, N, N, N), + PINGROUP(pbb4, VGP4, DISPLAYA, DISPLAYB, RSVD4, RSVD4, 0x329c, N, N, N), + PINGROUP(pbb5, VGP5, DISPLAYA, DISPLAYB, RSVD4, RSVD4, 0x32a0, N, N, N), + PINGROUP(pbb6, VGP6, DISPLAYA, DISPLAYB, RSVD4, RSVD4, 0x32a4, N, N, N), + PINGROUP(pbb7, I2S4, RSVD2, RSVD3, RSVD4, RSVD4, 0x32a8, N, N, N), + PINGROUP(pcc2, I2S4, RSVD2, RSVD3, RSVD4, RSVD4, 0x32ac, N, N, N), + PINGROUP(pwr_i2c_scl_pz6, I2CPWR, RSVD2, RSVD3, RSVD4, RSVD4, 0x32b4, Y, N, N), + PINGROUP(pwr_i2c_sda_pz7, I2CPWR, RSVD2, RSVD3, RSVD4, RSVD4, 0x32b8, Y, N, N), + PINGROUP(kb_row0_pr0, KBC, RSVD2, RSVD3, RSVD4, RSVD4, 0x32bc, N, N, N), + PINGROUP(kb_row1_pr1, KBC, RSVD2, RSVD3, RSVD4, RSVD4, 0x32c0, N, N, N), + PINGROUP(kb_row2_pr2, KBC, RSVD2, RSVD3, RSVD4, RSVD4, 0x32c4, N, N, N), + PINGROUP(kb_row3_pr3, KBC, DISPLAYA, RSVD3, DISPLAYB, RSVD3, 0x32c8, N, N, N), + PINGROUP(kb_row4_pr4, KBC, DISPLAYA, SPI2, DISPLAYB, KBC, 0x32cc, N, N, N), + PINGROUP(kb_row5_pr5, KBC, DISPLAYA, SPI2, DISPLAYB, KBC, 0x32d0, N, N, N), + PINGROUP(kb_row6_pr6, KBC, DISPLAYA, DISPLAYA_ALT, DISPLAYB, KBC, 0x32d4, N, N, N), + PINGROUP(kb_row7_pr7, KBC, RSVD2, CLDVFS, UARTA, RSVD2, 0x32d8, N, N, N), + PINGROUP(kb_row8_ps0, KBC, RSVD2, CLDVFS, UARTA, RSVD2, 0x32dc, N, N, N), + PINGROUP(kb_row9_ps1, KBC, RSVD2, RSVD3, UARTA, RSVD3, 0x32e0, N, N, N), + PINGROUP(kb_row10_ps2, KBC, RSVD2, RSVD3, UARTA, RSVD3, 0x32e4, N, N, N), + PINGROUP(kb_col0_pq0, KBC, USB, SPI2, EMC_DLL, KBC, 0x32fc, N, N, N), + PINGROUP(kb_col1_pq1, KBC, RSVD2, SPI2, EMC_DLL, RSVD2, 0x3300, N, N, N), + PINGROUP(kb_col2_pq2, KBC, RSVD2, SPI2, RSVD4, RSVD2, 0x3304, N, N, N), + PINGROUP(kb_col3_pq3, KBC, DISPLAYA, PWM2, UARTA, KBC, 0x3308, N, N, N), + PINGROUP(kb_col4_pq4, KBC, OWR, SDMMC3, UARTA, KBC, 0x330c, N, N, N), + PINGROUP(kb_col5_pq5, KBC, RSVD2, SDMMC1, RSVD4, RSVD4, 0x3310, N, N, N), + PINGROUP(kb_col6_pq6, KBC, RSVD2, SPI2, RSVD4, RSVD4, 0x3314, N, N, N), + PINGROUP(kb_col7_pq7, KBC, RSVD2, SPI2, RSVD4, RSVD4, 0x3318, N, N, N), + PINGROUP(clk_32k_out_pa0, BLINK, SOC, RSVD3, RSVD4, RSVD4, 0x331c, N, N, N), + PINGROUP(sys_clk_req_pz5, SYSCLK, RSVD2, RSVD3, RSVD4, RSVD4, 0x3320, N, N, N), + PINGROUP(core_pwr_req, PWRON, RSVD2, RSVD3, RSVD4, RSVD4, 0x3324, N, N, N), + PINGROUP(cpu_pwr_req, CPU, RSVD2, RSVD3, RSVD4, RSVD4, 0x3328, N, N, N), + PINGROUP(pwr_int_n, PMI, RSVD2, RSVD3, RSVD4, RSVD4, 0x332c, N, N, N), + PINGROUP(owr, OWR, RSVD2, RSVD3, RSVD4, RSVD4, 0x3334, N, N, Y), + PINGROUP(dap1_fs_pn0, I2S0, HDA, GMI, RSVD4, RSVD4, 0x3338, N, N, N), + PINGROUP(dap1_din_pn1, I2S0, HDA, GMI, RSVD4, RSVD4, 0x333c, N, N, N), + PINGROUP(dap1_dout_pn2, I2S0, HDA, GMI, RSVD4, RSVD4, 0x3340, N, N, N), + PINGROUP(dap1_sclk_pn3, I2S0, HDA, GMI, RSVD4, RSVD4, 0x3344, N, N, N), + PINGROUP(clk1_req_pee2, DAP, DAP1, RSVD3, RSVD4, RSVD4, 0x3348, N, N, N), + PINGROUP(clk1_out_pw4, EXTPERIPH1, DAP2, RSVD3, RSVD4, RSVD4, 0x334c, N, N, N), + PINGROUP(spdif_in_pk6, SPDIF, USB, RSVD3, RSVD4, RSVD4, 0x3350, N, N, N), + PINGROUP(spdif_out_pk5, SPDIF, RSVD2, RSVD3, RSVD4, RSVD4, 0x3354, N, N, N), + PINGROUP(dap2_fs_pa2, I2S1, HDA, RSVD3, RSVD4, RSVD4, 0x3358, N, N, N), + PINGROUP(dap2_din_pa4, I2S1, HDA, RSVD3, RSVD4, RSVD4, 0x335c, N, N, N), + PINGROUP(dap2_dout_pa5, I2S1, HDA, RSVD3, RSVD4, RSVD4, 0x3360, N, N, N), + PINGROUP(dap2_sclk_pa3, I2S1, HDA, RSVD3, RSVD4, RSVD4, 0x3364, N, N, N), + PINGROUP(dvfs_pwm_px0, SPI6, CLDVFS, RSVD3, RSVD4, RSVD4, 0x3368, N, N, N), + PINGROUP(gpio_x1_aud_px1, SPI6, RSVD2, RSVD3, RSVD4, RSVD4, 0x336c, N, N, N), + PINGROUP(gpio_x3_aud_px3, SPI6, SPI1, RSVD3, RSVD4, RSVD4, 0x3370, N, N, N), + PINGROUP(dvfs_clk_px2, SPI6, CLDVFS, RSVD3, RSVD4, RSVD4, 0x3374, N, N, N), + PINGROUP(gpio_x4_aud_px4, RSVD1, SPI1, SPI2, DAP2, RSVD1, 0x3378, N, N, N), + PINGROUP(gpio_x5_aud_px5, RSVD1, SPI1, SPI2, RSVD4, RSVD1, 0x337c, N, N, N), + PINGROUP(gpio_x6_aud_px6, SPI6, SPI1, SPI2, RSVD4, RSVD4, 0x3380, N, N, N), + PINGROUP(gpio_x7_aud_px7, RSVD1, SPI1, SPI2, RSVD4, RSVD4, 0x3384, N, N, N), + PINGROUP(sdmmc3_clk_pa6, SDMMC3, RSVD2, RSVD3, SPI3, RSVD3, 0x3390, N, N, N), + PINGROUP(sdmmc3_cmd_pa7, SDMMC3, PWM3, UARTA, SPI3, SDMMC3, 0x3394, N, N, N), + PINGROUP(sdmmc3_dat0_pb7, SDMMC3, RSVD2, RSVD3, SPI3, RSVD3, 0x3398, N, N, N), + PINGROUP(sdmmc3_dat1_pb6, SDMMC3, PWM2, UARTA, SPI3, SDMMC3, 0x339c, N, N, N), + PINGROUP(sdmmc3_dat2_pb5, SDMMC3, PWM1, DISPLAYA, SPI3, SDMMC3, 0x33a0, N, N, N), + PINGROUP(sdmmc3_dat3_pb4, SDMMC3, PWM0, DISPLAYB, SPI3, SDMMC3, 0x33a4, N, N, N), + PINGROUP(hdmi_cec_pee3, CEC, SDMMC3, RSVD3, SOC, RSVD3, 0x33e0, Y, N, N), + PINGROUP(sdmmc1_wp_n_pv3, SDMMC1, CLK12, SPI4, UARTA, SDMMC1, 0x33e4, N, N, N), + PINGROUP(sdmmc3_cd_n_pv2, SDMMC3, OWR, RSVD3, RSVD4, RSVD4, 0x33e8, N, N, N), + PINGROUP(gpio_w2_aud_pw2, SPI6, RSVD2, SPI2, I2C1, RSVD2, 0x33ec, N, N, N), + PINGROUP(gpio_w3_aud_pw3, SPI6, SPI1, SPI2, I2C1, SPI6, 0x33f0, N, N, N), + PINGROUP(usb_vbus_en0_pn4, USB, RSVD2, RSVD3, RSVD4, RSVD4, 0x33f4, Y, N, N), + PINGROUP(usb_vbus_en1_pn5, USB, RSVD2, RSVD3, RSVD4, RSVD4, 0x33f8, Y, N, N), + PINGROUP(sdmmc3_clk_lb_in_pee5, SDMMC3, RSVD2, RSVD3, RSVD4, RSVD4, 0x33fc, N, N, N), + PINGROUP(sdmmc3_clk_lb_out_pee4, SDMMC3, RSVD2, RSVD3, RSVD4, RSVD4, 0x3400, N, N, N), + PINGROUP(reset_out_n, RSVD1, RSVD2, RSVD3, RESET_OUT_N, RSVD3, 0x3408, N, N, N), + + /* pg_name, r, hsm_b, schmitt_b, lpmd_b, drvdn_b, drvdn_w, drvup_b, drvup_w, slwr_b, slwr_w, slwf_b, slwf_w, drvtype */ + DRV_PINGROUP(ao1, 0x868, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(ao2, 0x86c, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(at1, 0x870, 2, 3, 4, 12, 7, 20, 7, 28, 2, 30, 2, Y), + DRV_PINGROUP(at2, 0x874, 2, 3, 4, 12, 7, 20, 7, 28, 2, 30, 2, Y), + DRV_PINGROUP(at3, 0x878, 2, 3, 4, 12, 7, 20, 7, 28, 2, 30, 2, Y), + DRV_PINGROUP(at4, 0x87c, 2, 3, 4, 12, 7, 20, 7, 28, 2, 30, 2, Y), + DRV_PINGROUP(at5, 0x880, 2, 3, 4, 14, 5, 19, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(cdev1, 0x884, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(cdev2, 0x888, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(dap1, 0x890, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(dap2, 0x894, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(dap3, 0x898, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(dap4, 0x89c, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(dbg, 0x8a0, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(sdio3, 0x8b0, 2, 3, -1, 12, 7, 20, 7, 28, 2, 30, 2, N), + DRV_PINGROUP(spi, 0x8b4, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(uaa, 0x8b8, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(uab, 0x8bc, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(uart2, 0x8c0, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(uart3, 0x8c4, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(sdio1, 0x8ec, 2, 3, -1, 12, 7, 20, 7, 28, 2, 30, 2, N), + DRV_PINGROUP(ddc, 0x8fc, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(gma, 0x900, 2, 3, 4, 14, 5, 20, 5, 28, 2, 30, 2, Y), + DRV_PINGROUP(gme, 0x910, 2, 3, 4, 14, 5, 19, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(gmf, 0x914, 2, 3, 4, 14, 5, 19, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(gmg, 0x918, 2, 3, 4, 14, 5, 19, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(gmh, 0x91c, 2, 3, 4, 14, 5, 19, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(owr, 0x920, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), + DRV_PINGROUP(uda, 0x924, 2, 3, 4, 12, 5, 20, 5, 28, 2, 30, 2, N), +}; + +static const struct tegra_pinctrl_soc_data tegra114_pinctrl = { + .ngpios = NUM_GPIOS, + .pins = tegra114_pins, + .npins = ARRAY_SIZE(tegra114_pins), + .functions = tegra114_functions, + .nfunctions = ARRAY_SIZE(tegra114_functions), + .groups = tegra114_groups, + .ngroups = ARRAY_SIZE(tegra114_groups), +}; + +static int tegra114_pinctrl_probe(struct platform_device *pdev) +{ + return tegra_pinctrl_probe(pdev, &tegra114_pinctrl); +} + +static struct of_device_id tegra114_pinctrl_of_match[] = { + { .compatible = "nvidia,tegra114-pinmux", }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra114_pinctrl_of_match); + +static struct platform_driver tegra114_pinctrl_driver = { + .driver = { + .name = "tegra114-pinctrl", + .owner = THIS_MODULE, + .of_match_table = tegra114_pinctrl_of_match, + }, + .probe = tegra114_pinctrl_probe, + .remove = tegra_pinctrl_remove, +}; +module_platform_driver(tegra114_pinctrl_driver); + +MODULE_ALIAS("platform:tegra114-pinctrl"); +MODULE_AUTHOR("Pritesh Raithatha <praithatha@nvidia.com>"); +MODULE_DESCRIPTION("NVIDIA Tegra114 pincontrol driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/pinctrl-tegra20.c b/drivers/pinctrl/pinctrl-tegra20.c index e848189..fcfb7d0 100644 --- a/drivers/pinctrl/pinctrl-tegra20.c +++ b/drivers/pinctrl/pinctrl-tegra20.c @@ -2624,7 +2624,9 @@ static const struct tegra_function tegra20_functions[] = { .odrain_reg = -1, \ .lock_reg = -1, \ .ioreset_reg = -1, \ + .rcv_sel_reg = -1, \ .drv_reg = -1, \ + .drvtype_reg = -1, \ } /* Pin groups with only pull up and pull down control */ @@ -2642,7 +2644,9 @@ static const struct tegra_function tegra20_functions[] = { .odrain_reg = -1, \ .lock_reg = -1, \ .ioreset_reg = -1, \ + .rcv_sel_reg = -1, \ .drv_reg = -1, \ + .drvtype_reg = -1, \ } /* Pin groups for drive strength registers (configurable version) */ @@ -2660,6 +2664,7 @@ static const struct tegra_function tegra20_functions[] = { .odrain_reg = -1, \ .lock_reg = -1, \ .ioreset_reg = -1, \ + .rcv_sel_reg = -1, \ .drv_reg = ((r) - PINGROUP_REG_A), \ .drv_bank = 3, \ .hsm_bit = hsm_b, \ @@ -2673,6 +2678,7 @@ static const struct tegra_function tegra20_functions[] = { .slwr_width = slwr_w, \ .slwf_bit = slwf_b, \ .slwf_width = slwf_w, \ + .drvtype_reg = -1, \ } /* Pin groups for drive strength registers (simple version) */ diff --git a/drivers/pinctrl/pinctrl-tegra30.c b/drivers/pinctrl/pinctrl-tegra30.c index 9ad87ea..2300deb 100644 --- a/drivers/pinctrl/pinctrl-tegra30.c +++ b/drivers/pinctrl/pinctrl-tegra30.c @@ -3384,7 +3384,9 @@ static const struct tegra_function tegra30_functions[] = { .ioreset_reg = PINGROUP_REG_##ior(r), \ .ioreset_bank = 1, \ .ioreset_bit = 8, \ + .rcv_sel_reg = -1, \ .drv_reg = -1, \ + .drvtype_reg = -1, \ } #define DRV_PINGROUP(pg_name, r, hsm_b, schmitt_b, lpmd_b, \ @@ -3401,6 +3403,7 @@ static const struct tegra_function tegra30_functions[] = { .odrain_reg = -1, \ .lock_reg = -1, \ .ioreset_reg = -1, \ + .rcv_sel_reg = -1, \ .drv_reg = ((r) - DRV_PINGROUP_REG_A), \ .drv_bank = 0, \ .hsm_bit = hsm_b, \ @@ -3414,6 +3417,7 @@ static const struct tegra_function tegra30_functions[] = { .slwr_width = slwr_w, \ .slwf_bit = slwf_b, \ .slwf_width = slwf_w, \ + .drvtype_reg = -1, \ } static const struct tegra_pingroup tegra30_groups[] = { diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c index 5f0eb04..53cb6a3 100644 --- a/drivers/pinctrl/pinctrl-xway.c +++ b/drivers/pinctrl/pinctrl-xway.c @@ -441,17 +441,17 @@ static int xway_pinconf_get(struct pinctrl_dev *pctldev, if (port == PORT3) reg = GPIO3_OD; else - reg = GPIO_OD(port); + reg = GPIO_OD(pin); *config = LTQ_PINCONF_PACK(param, - !!gpio_getbit(info->membase[0], reg, PORT_PIN(port))); + !gpio_getbit(info->membase[0], reg, PORT_PIN(pin))); break; case LTQ_PINCONF_PARAM_PULL: if (port == PORT3) reg = GPIO3_PUDEN; else - reg = GPIO_PUDEN(port); - if (!gpio_getbit(info->membase[0], reg, PORT_PIN(port))) { + reg = GPIO_PUDEN(pin); + if (!gpio_getbit(info->membase[0], reg, PORT_PIN(pin))) { *config = LTQ_PINCONF_PACK(param, 0); break; } @@ -459,13 +459,18 @@ static int xway_pinconf_get(struct pinctrl_dev *pctldev, if (port == PORT3) reg = GPIO3_PUDSEL; else - reg = GPIO_PUDSEL(port); - if (!gpio_getbit(info->membase[0], reg, PORT_PIN(port))) + reg = GPIO_PUDSEL(pin); + if (!gpio_getbit(info->membase[0], reg, PORT_PIN(pin))) *config = LTQ_PINCONF_PACK(param, 2); else *config = LTQ_PINCONF_PACK(param, 1); break; + case LTQ_PINCONF_PARAM_OUTPUT: + reg = GPIO_DIR(pin); + *config = LTQ_PINCONF_PACK(param, + gpio_getbit(info->membase[0], reg, PORT_PIN(pin))); + break; default: dev_err(pctldev->dev, "Invalid config param %04x\n", param); return -ENOTSUPP; @@ -488,33 +493,44 @@ static int xway_pinconf_set(struct pinctrl_dev *pctldev, if (port == PORT3) reg = GPIO3_OD; else - reg = GPIO_OD(port); - gpio_setbit(info->membase[0], reg, PORT_PIN(port)); + reg = GPIO_OD(pin); + if (arg == 0) + gpio_setbit(info->membase[0], reg, PORT_PIN(pin)); + else + gpio_clearbit(info->membase[0], reg, PORT_PIN(pin)); break; case LTQ_PINCONF_PARAM_PULL: if (port == PORT3) reg = GPIO3_PUDEN; else - reg = GPIO_PUDEN(port); + reg = GPIO_PUDEN(pin); if (arg == 0) { - gpio_clearbit(info->membase[0], reg, PORT_PIN(port)); + gpio_clearbit(info->membase[0], reg, PORT_PIN(pin)); break; } - gpio_setbit(info->membase[0], reg, PORT_PIN(port)); + gpio_setbit(info->membase[0], reg, PORT_PIN(pin)); if (port == PORT3) reg = GPIO3_PUDSEL; else - reg = GPIO_PUDSEL(port); + reg = GPIO_PUDSEL(pin); if (arg == 1) - gpio_clearbit(info->membase[0], reg, PORT_PIN(port)); + gpio_clearbit(info->membase[0], reg, PORT_PIN(pin)); else if (arg == 2) - gpio_setbit(info->membase[0], reg, PORT_PIN(port)); + gpio_setbit(info->membase[0], reg, PORT_PIN(pin)); else dev_err(pctldev->dev, "Invalid pull value %d\n", arg); break; + case LTQ_PINCONF_PARAM_OUTPUT: + reg = GPIO_DIR(pin); + if (arg == 0) + gpio_clearbit(info->membase[0], reg, PORT_PIN(pin)); + else + gpio_setbit(info->membase[0], reg, PORT_PIN(pin)); + break; + default: dev_err(pctldev->dev, "Invalid config param %04x\n", param); return -ENOTSUPP; @@ -522,9 +538,24 @@ static int xway_pinconf_set(struct pinctrl_dev *pctldev, return 0; } +int xway_pinconf_group_set(struct pinctrl_dev *pctldev, + unsigned selector, + unsigned long config) +{ + struct ltq_pinmux_info *info = pinctrl_dev_get_drvdata(pctldev); + int i, ret = 0; + + for (i = 0; i < info->grps[selector].npins && !ret; i++) + ret = xway_pinconf_set(pctldev, + info->grps[selector].pins[i], config); + + return ret; +} + static struct pinconf_ops xway_pinconf_ops = { .pin_config_get = xway_pinconf_get, .pin_config_set = xway_pinconf_set, + .pin_config_group_set = xway_pinconf_group_set, }; static struct pinctrl_desc xway_pctrl_desc = { @@ -558,6 +589,7 @@ static inline int xway_mux_apply(struct pinctrl_dev *pctrldev, static const struct ltq_cfg_param xway_cfg_params[] = { {"lantiq,pull", LTQ_PINCONF_PARAM_PULL}, {"lantiq,open-drain", LTQ_PINCONF_PARAM_OPEN_DRAIN}, + {"lantiq,output", LTQ_PINCONF_PARAM_OUTPUT}, }; static struct ltq_pinmux_info xway_info = { diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c index 7481146..97c2be1 100644 --- a/drivers/platform/x86/ibm_rtl.c +++ b/drivers/platform/x86/ibm_rtl.c @@ -244,7 +244,7 @@ static int __init ibm_rtl_init(void) { if (force) pr_warn("module loaded by force\n"); /* first ensure that we are running on IBM HW */ - else if (efi_enabled || !dmi_check_system(ibm_rtl_dmi_table)) + else if (efi_enabled(EFI_BOOT) || !dmi_check_system(ibm_rtl_dmi_table)) return -ENODEV; /* Get the address for the Extended BIOS Data Area */ diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index 71623a2..d1f03005 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -26,6 +26,7 @@ #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/ctype.h> +#include <linux/efi.h> #include <acpi/video.h> /* @@ -1544,6 +1545,9 @@ static int __init samsung_init(void) struct samsung_laptop *samsung; int ret; + if (efi_enabled(EFI_BOOT)) + return -ENODEV; + quirks = &samsung_unknown; if (!force && !dmi_check_system(samsung_dmi_table)) return -ENODEV; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index f946ca7..ebcb461 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4877,8 +4877,7 @@ static int __init light_init(struct ibm_init_struct *iibm) static void light_exit(void) { led_classdev_unregister(&tpacpi_led_thinklight.led_classdev); - if (work_pending(&tpacpi_led_thinklight.work)) - flush_workqueue(tpacpi_wq); + flush_workqueue(tpacpi_wq); } static int light_read(struct seq_file *m) diff --git a/drivers/regulator/88pm8607.c b/drivers/regulator/88pm8607.c index 2b55711..c79ab84 100644 --- a/drivers/regulator/88pm8607.c +++ b/drivers/regulator/88pm8607.c @@ -30,8 +30,6 @@ struct pm8607_regulator_info { unsigned int *vol_table; unsigned int *vol_suspend; - int update_reg; - int update_bit; int slope_double; }; @@ -222,29 +220,6 @@ static int pm8607_list_voltage(struct regulator_dev *rdev, unsigned index) return ret; } -static int pm8607_set_voltage_sel(struct regulator_dev *rdev, unsigned selector) -{ - struct pm8607_regulator_info *info = rdev_get_drvdata(rdev); - uint8_t val; - int ret; - - val = (uint8_t)(selector << (ffs(rdev->desc->vsel_mask) - 1)); - - ret = pm860x_set_bits(info->i2c, rdev->desc->vsel_reg, - rdev->desc->vsel_mask, val); - if (ret) - return ret; - switch (info->desc.id) { - case PM8607_ID_BUCK1: - case PM8607_ID_BUCK3: - ret = pm860x_set_bits(info->i2c, info->update_reg, - 1 << info->update_bit, - 1 << info->update_bit); - break; - } - return ret; -} - static int pm8606_preg_enable(struct regulator_dev *rdev) { struct pm8607_regulator_info *info = rdev_get_drvdata(rdev); @@ -276,7 +251,7 @@ static int pm8606_preg_is_enabled(struct regulator_dev *rdev) static struct regulator_ops pm8607_regulator_ops = { .list_voltage = pm8607_list_voltage, - .set_voltage_sel = pm8607_set_voltage_sel, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -313,11 +288,11 @@ static struct regulator_ops pm8606_preg_ops = { .n_voltages = ARRAY_SIZE(vreg##_table), \ .vsel_reg = PM8607_##vreg, \ .vsel_mask = ARRAY_SIZE(vreg##_table) - 1, \ + .apply_reg = PM8607_##ureg, \ + .apply_bit = (ubit), \ .enable_reg = PM8607_##ereg, \ .enable_mask = 1 << (ebit), \ }, \ - .update_reg = PM8607_##ureg, \ - .update_bit = (ubit), \ .slope_double = (0), \ .vol_table = (unsigned int *)&vreg##_table, \ .vol_suspend = (unsigned int *)&vreg##_suspend_table, \ @@ -343,9 +318,9 @@ static struct regulator_ops pm8606_preg_ops = { } static struct pm8607_regulator_info pm8607_regulator_info[] = { - PM8607_DVC(BUCK1, GO, 0, SUPPLIES_EN11, 0), - PM8607_DVC(BUCK2, GO, 1, SUPPLIES_EN11, 1), - PM8607_DVC(BUCK3, GO, 2, SUPPLIES_EN11, 2), + PM8607_DVC(BUCK1, GO, BIT(0), SUPPLIES_EN11, 0), + PM8607_DVC(BUCK2, GO, BIT(1), SUPPLIES_EN11, 1), + PM8607_DVC(BUCK3, GO, BIT(2), SUPPLIES_EN11, 2), PM8607_LDO(1, LDO1, 0, SUPPLIES_EN11, 3), PM8607_LDO(2, LDO2, 0, SUPPLIES_EN11, 4), @@ -372,7 +347,7 @@ static int pm8607_regulator_dt_init(struct platform_device *pdev, struct regulator_config *config) { struct device_node *nproot, *np; - nproot = pdev->dev.parent->of_node; + nproot = of_node_get(pdev->dev.parent->of_node); if (!nproot) return -ENODEV; nproot = of_find_node_by_name(nproot, "regulators"); @@ -388,6 +363,7 @@ static int pm8607_regulator_dt_init(struct platform_device *pdev, break; } } + of_node_put(nproot); return 0; } #else diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index 551a22b..a5d97ea 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -91,6 +91,7 @@ config REGULATOR_AAT2870 config REGULATOR_ARIZONA tristate "Wolfson Arizona class devices" depends on MFD_ARIZONA + depends on SND_SOC help Support for the regulators found on Wolfson Arizona class devices. @@ -277,6 +278,15 @@ config REGULATOR_LP872X help This driver supports LP8720/LP8725 PMIC +config REGULATOR_LP8755 + tristate "TI LP8755 High Performance PMU driver" + depends on I2C + select REGMAP_I2C + help + This driver supports LP8755 High Performance PMU driver. This + chip contains six step-down DC/DC converters which can support + 9 mode multiphase configuration. + config REGULATOR_LP8788 bool "TI LP8788 Power Regulators" depends on MFD_LP8788 diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index b802b0c..6e82503 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_REGULATOR_LP3972) += lp3972.o obj-$(CONFIG_REGULATOR_LP872X) += lp872x.o obj-$(CONFIG_REGULATOR_LP8788) += lp8788-buck.o obj-$(CONFIG_REGULATOR_LP8788) += lp8788-ldo.o +obj-$(CONFIG_REGULATOR_LP8755) += lp8755.o obj-$(CONFIG_REGULATOR_MAX1586) += max1586.o obj-$(CONFIG_REGULATOR_MAX8649) += max8649.o obj-$(CONFIG_REGULATOR_MAX8660) += max8660.o diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c index 8f39cac..0d4a8cc 100644 --- a/drivers/regulator/anatop-regulator.c +++ b/drivers/regulator/anatop-regulator.c @@ -31,12 +31,18 @@ #include <linux/regulator/driver.h> #include <linux/regulator/of_regulator.h> +#define LDO_RAMP_UP_UNIT_IN_CYCLES 64 /* 64 cycles per step */ +#define LDO_RAMP_UP_FREQ_IN_MHZ 24 /* cycle based on 24M OSC */ + struct anatop_regulator { const char *name; u32 control_reg; struct regmap *anatop; int vol_bit_shift; int vol_bit_width; + u32 delay_reg; + int delay_bit_shift; + int delay_bit_width; int min_bit_val; int min_voltage; int max_voltage; @@ -55,6 +61,32 @@ static int anatop_regmap_set_voltage_sel(struct regulator_dev *reg, return regulator_set_voltage_sel_regmap(reg, selector); } +static int anatop_regmap_set_voltage_time_sel(struct regulator_dev *reg, + unsigned int old_sel, + unsigned int new_sel) +{ + struct anatop_regulator *anatop_reg = rdev_get_drvdata(reg); + u32 val; + int ret = 0; + + /* check whether need to care about LDO ramp up speed */ + if (anatop_reg->delay_bit_width && new_sel > old_sel) { + /* + * the delay for LDO ramp up time is + * based on the register setting, we need + * to calculate how many steps LDO need to + * ramp up, and how much delay needed. (us) + */ + regmap_read(anatop_reg->anatop, anatop_reg->delay_reg, &val); + val = (val >> anatop_reg->delay_bit_shift) & + ((1 << anatop_reg->delay_bit_width) - 1); + ret = (new_sel - old_sel) * (LDO_RAMP_UP_UNIT_IN_CYCLES << + val) / LDO_RAMP_UP_FREQ_IN_MHZ + 1; + } + + return ret; +} + static int anatop_regmap_get_voltage_sel(struct regulator_dev *reg) { struct anatop_regulator *anatop_reg = rdev_get_drvdata(reg); @@ -67,6 +99,7 @@ static int anatop_regmap_get_voltage_sel(struct regulator_dev *reg) static struct regulator_ops anatop_rops = { .set_voltage_sel = anatop_regmap_set_voltage_sel, + .set_voltage_time_sel = anatop_regmap_set_voltage_time_sel, .get_voltage_sel = anatop_regmap_get_voltage_sel, .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, @@ -143,6 +176,14 @@ static int anatop_regulator_probe(struct platform_device *pdev) goto anatop_probe_end; } + /* read LDO ramp up setting, only for core reg */ + of_property_read_u32(np, "anatop-delay-reg-offset", + &sreg->delay_reg); + of_property_read_u32(np, "anatop-delay-bit-width", + &sreg->delay_bit_width); + of_property_read_u32(np, "anatop-delay-bit-shift", + &sreg->delay_bit_shift); + rdesc->n_voltages = (sreg->max_voltage - sreg->min_voltage) / 25000 + 1 + sreg->min_bit_val; rdesc->min_uV = sreg->min_voltage; diff --git a/drivers/regulator/arizona-micsupp.c b/drivers/regulator/arizona-micsupp.c index a6d040c..e87536b 100644 --- a/drivers/regulator/arizona-micsupp.c +++ b/drivers/regulator/arizona-micsupp.c @@ -21,6 +21,8 @@ #include <linux/regulator/machine.h> #include <linux/gpio.h> #include <linux/slab.h> +#include <linux/workqueue.h> +#include <sound/soc.h> #include <linux/mfd/arizona/core.h> #include <linux/mfd/arizona/pdata.h> @@ -34,6 +36,8 @@ struct arizona_micsupp { struct regulator_consumer_supply supply; struct regulator_init_data init_data; + + struct work_struct check_cp_work; }; static int arizona_micsupp_list_voltage(struct regulator_dev *rdev, @@ -72,9 +76,73 @@ static int arizona_micsupp_map_voltage(struct regulator_dev *rdev, return selector; } +static void arizona_micsupp_check_cp(struct work_struct *work) +{ + struct arizona_micsupp *micsupp = + container_of(work, struct arizona_micsupp, check_cp_work); + struct snd_soc_dapm_context *dapm = micsupp->arizona->dapm; + struct arizona *arizona = micsupp->arizona; + struct regmap *regmap = arizona->regmap; + unsigned int reg; + int ret; + + ret = regmap_read(regmap, ARIZONA_MIC_CHARGE_PUMP_1, ®); + if (ret != 0) { + dev_err(arizona->dev, "Failed to read CP state: %d\n", ret); + return; + } + + if (dapm) { + if ((reg & (ARIZONA_CPMIC_ENA | ARIZONA_CPMIC_BYPASS)) == + ARIZONA_CPMIC_ENA) + snd_soc_dapm_force_enable_pin(dapm, "MICSUPP"); + else + snd_soc_dapm_disable_pin(dapm, "MICSUPP"); + + snd_soc_dapm_sync(dapm); + } +} + +static int arizona_micsupp_enable(struct regulator_dev *rdev) +{ + struct arizona_micsupp *micsupp = rdev_get_drvdata(rdev); + int ret; + + ret = regulator_enable_regmap(rdev); + + if (ret == 0) + schedule_work(&micsupp->check_cp_work); + + return ret; +} + +static int arizona_micsupp_disable(struct regulator_dev *rdev) +{ + struct arizona_micsupp *micsupp = rdev_get_drvdata(rdev); + int ret; + + ret = regulator_disable_regmap(rdev); + if (ret == 0) + schedule_work(&micsupp->check_cp_work); + + return ret; +} + +static int arizona_micsupp_set_bypass(struct regulator_dev *rdev, bool ena) +{ + struct arizona_micsupp *micsupp = rdev_get_drvdata(rdev); + int ret; + + ret = regulator_set_bypass_regmap(rdev, ena); + if (ret == 0) + schedule_work(&micsupp->check_cp_work); + + return ret; +} + static struct regulator_ops arizona_micsupp_ops = { - .enable = regulator_enable_regmap, - .disable = regulator_disable_regmap, + .enable = arizona_micsupp_enable, + .disable = arizona_micsupp_disable, .is_enabled = regulator_is_enabled_regmap, .list_voltage = arizona_micsupp_list_voltage, @@ -84,7 +152,7 @@ static struct regulator_ops arizona_micsupp_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_bypass = regulator_get_bypass_regmap, - .set_bypass = regulator_set_bypass_regmap, + .set_bypass = arizona_micsupp_set_bypass, }; static const struct regulator_desc arizona_micsupp = { @@ -109,7 +177,8 @@ static const struct regulator_desc arizona_micsupp = { static const struct regulator_init_data arizona_micsupp_default = { .constraints = { .valid_ops_mask = REGULATOR_CHANGE_STATUS | - REGULATOR_CHANGE_VOLTAGE, + REGULATOR_CHANGE_VOLTAGE | + REGULATOR_CHANGE_BYPASS, .min_uV = 1700000, .max_uV = 3300000, }, @@ -131,6 +200,7 @@ static int arizona_micsupp_probe(struct platform_device *pdev) } micsupp->arizona = arizona; + INIT_WORK(&micsupp->check_cp_work, arizona_micsupp_check_cp); /* * Since the chip usually supplies itself we provide some diff --git a/drivers/regulator/as3711-regulator.c b/drivers/regulator/as3711-regulator.c index 2f1341d..f0ba8c4 100644 --- a/drivers/regulator/as3711-regulator.c +++ b/drivers/regulator/as3711-regulator.c @@ -303,7 +303,7 @@ static int as3711_regulator_probe(struct platform_device *pdev) reg_data = pdata ? pdata->init_data[id] : NULL; /* No need to register if there is no regulator data */ - if (!ri->desc.name) + if (!reg_data) continue; reg = ®s[id]; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 2785843..da9782b 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -200,8 +200,8 @@ static int regulator_check_consumers(struct regulator_dev *rdev, } if (*min_uV > *max_uV) { - dev_err(regulator->dev, "Restricting voltage, %u-%uuV\n", - regulator->min_uV, regulator->max_uV); + rdev_err(rdev, "Restricting voltage, %u-%uuV\n", + *min_uV, *max_uV); return -EINVAL; } @@ -2080,10 +2080,20 @@ EXPORT_SYMBOL_GPL(regulator_get_voltage_sel_regmap); */ int regulator_set_voltage_sel_regmap(struct regulator_dev *rdev, unsigned sel) { + int ret; + sel <<= ffs(rdev->desc->vsel_mask) - 1; - return regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, + ret = regmap_update_bits(rdev->regmap, rdev->desc->vsel_reg, rdev->desc->vsel_mask, sel); + if (ret) + return ret; + + if (rdev->desc->apply_bit) + ret = regmap_update_bits(rdev->regmap, rdev->desc->apply_reg, + rdev->desc->apply_bit, + rdev->desc->apply_bit); + return ret; } EXPORT_SYMBOL_GPL(regulator_set_voltage_sel_regmap); @@ -2229,8 +2239,11 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, best_val = rdev->desc->ops->list_voltage(rdev, ret); if (min_uV <= best_val && max_uV >= best_val) { selector = ret; - ret = rdev->desc->ops->set_voltage_sel(rdev, - ret); + if (old_selector == selector) + ret = 0; + else + ret = rdev->desc->ops->set_voltage_sel( + rdev, ret); } else { ret = -EINVAL; } @@ -2241,7 +2254,7 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, /* Call set_voltage_time_sel if successfully obtained old_selector */ if (ret == 0 && _regulator_is_enabled(rdev) && old_selector >= 0 && - rdev->desc->ops->set_voltage_time_sel) { + old_selector != selector && rdev->desc->ops->set_voltage_time_sel) { delay = rdev->desc->ops->set_voltage_time_sel(rdev, old_selector, selector); @@ -2294,6 +2307,7 @@ int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV) { struct regulator_dev *rdev = regulator->rdev; int ret = 0; + int old_min_uV, old_max_uV; mutex_lock(&rdev->mutex); @@ -2315,18 +2329,29 @@ int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV) ret = regulator_check_voltage(rdev, &min_uV, &max_uV); if (ret < 0) goto out; + + /* restore original values in case of error */ + old_min_uV = regulator->min_uV; + old_max_uV = regulator->max_uV; regulator->min_uV = min_uV; regulator->max_uV = max_uV; ret = regulator_check_consumers(rdev, &min_uV, &max_uV); if (ret < 0) - goto out; + goto out2; ret = _regulator_do_set_voltage(rdev, min_uV, max_uV); - + if (ret < 0) + goto out2; + out: mutex_unlock(&rdev->mutex); return ret; +out2: + regulator->min_uV = old_min_uV; + regulator->max_uV = old_max_uV; + mutex_unlock(&rdev->mutex); + return ret; } EXPORT_SYMBOL_GPL(regulator_set_voltage); @@ -3208,7 +3233,7 @@ static int add_regulator_attributes(struct regulator_dev *rdev) if (status < 0) return status; } - if (ops->is_enabled) { + if (rdev->ena_gpio || ops->is_enabled) { status = device_create_file(dev, &dev_attr_state); if (status < 0) return status; diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c index d096309..96b569a 100644 --- a/drivers/regulator/da9052-regulator.c +++ b/drivers/regulator/da9052-regulator.c @@ -70,7 +70,6 @@ struct da9052_regulator_info { int step_uV; int min_uV; int max_uV; - unsigned char activate_bit; }; struct da9052_regulator { @@ -210,36 +209,6 @@ static int da9052_map_voltage(struct regulator_dev *rdev, return sel; } -static int da9052_regulator_set_voltage_sel(struct regulator_dev *rdev, - unsigned int selector) -{ - struct da9052_regulator *regulator = rdev_get_drvdata(rdev); - struct da9052_regulator_info *info = regulator->info; - int id = rdev_get_id(rdev); - int ret; - - ret = da9052_reg_update(regulator->da9052, rdev->desc->vsel_reg, - rdev->desc->vsel_mask, selector); - if (ret < 0) - return ret; - - /* Some LDOs and DCDCs are DVC controlled which requires enabling of - * the activate bit to implment the changes on the output. - */ - switch (id) { - case DA9052_ID_BUCK1: - case DA9052_ID_BUCK2: - case DA9052_ID_BUCK3: - case DA9052_ID_LDO2: - case DA9052_ID_LDO3: - ret = da9052_reg_update(regulator->da9052, DA9052_SUPPLY_REG, - info->activate_bit, info->activate_bit); - break; - } - - return ret; -} - static struct regulator_ops da9052_dcdc_ops = { .get_current_limit = da9052_dcdc_get_current_limit, .set_current_limit = da9052_dcdc_set_current_limit, @@ -247,7 +216,7 @@ static struct regulator_ops da9052_dcdc_ops = { .list_voltage = da9052_list_voltage, .map_voltage = da9052_map_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .set_voltage_sel = da9052_regulator_set_voltage_sel, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -257,7 +226,7 @@ static struct regulator_ops da9052_ldo_ops = { .list_voltage = da9052_list_voltage, .map_voltage = da9052_map_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .set_voltage_sel = da9052_regulator_set_voltage_sel, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -274,13 +243,14 @@ static struct regulator_ops da9052_ldo_ops = { .owner = THIS_MODULE,\ .vsel_reg = DA9052_BUCKCORE_REG + DA9052_ID_##_id, \ .vsel_mask = (1 << (sbits)) - 1,\ + .apply_reg = DA9052_SUPPLY_REG, \ + .apply_bit = (abits), \ .enable_reg = DA9052_BUCKCORE_REG + DA9052_ID_##_id, \ .enable_mask = 1 << (ebits),\ },\ .min_uV = (min) * 1000,\ .max_uV = (max) * 1000,\ .step_uV = (step) * 1000,\ - .activate_bit = (abits),\ } #define DA9052_DCDC(_id, step, min, max, sbits, ebits, abits) \ @@ -294,13 +264,14 @@ static struct regulator_ops da9052_ldo_ops = { .owner = THIS_MODULE,\ .vsel_reg = DA9052_BUCKCORE_REG + DA9052_ID_##_id, \ .vsel_mask = (1 << (sbits)) - 1,\ + .apply_reg = DA9052_SUPPLY_REG, \ + .apply_bit = (abits), \ .enable_reg = DA9052_BUCKCORE_REG + DA9052_ID_##_id, \ .enable_mask = 1 << (ebits),\ },\ .min_uV = (min) * 1000,\ .max_uV = (max) * 1000,\ .step_uV = (step) * 1000,\ - .activate_bit = (abits),\ } static struct da9052_regulator_info da9052_regulator_info[] = { @@ -395,9 +366,9 @@ static int da9052_regulator_probe(struct platform_device *pdev) config.init_data = pdata->regulators[pdev->id]; } else { #ifdef CONFIG_OF - struct device_node *nproot = da9052->dev->of_node; - struct device_node *np; + struct device_node *nproot, *np; + nproot = of_node_get(da9052->dev->of_node); if (!nproot) return -ENODEV; @@ -414,6 +385,7 @@ static int da9052_regulator_probe(struct platform_device *pdev) break; } } + of_node_put(nproot); #endif } diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c index 1a05ac6..3022109 100644 --- a/drivers/regulator/da9055-regulator.c +++ b/drivers/regulator/da9055-regulator.c @@ -58,7 +58,6 @@ struct da9055_volt_reg { int reg_b; int sl_shift; int v_mask; - int v_shift; }; struct da9055_mode_reg { @@ -388,7 +387,6 @@ static struct regulator_ops da9055_ldo_ops = { .reg_b = DA9055_REG_VBCORE_B + DA9055_ID_##_id, \ .sl_shift = 7,\ .v_mask = (1 << (vbits)) - 1,\ - .v_shift = (vbits),\ },\ } @@ -417,7 +415,6 @@ static struct regulator_ops da9055_ldo_ops = { .reg_b = DA9055_REG_VBCORE_B + DA9055_ID_##_id, \ .sl_shift = 7,\ .v_mask = (1 << (vbits)) - 1,\ - .v_shift = (vbits),\ },\ .mode = {\ .reg = DA9055_REG_BCORE_MODE,\ diff --git a/drivers/regulator/dbx500-prcmu.c b/drivers/regulator/dbx500-prcmu.c index 261f3d2..89bd2fa 100644 --- a/drivers/regulator/dbx500-prcmu.c +++ b/drivers/regulator/dbx500-prcmu.c @@ -14,6 +14,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/module.h> #include "dbx500-prcmu.h" diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c index bae681c..9d39eb4 100644 --- a/drivers/regulator/gpio-regulator.c +++ b/drivers/regulator/gpio-regulator.c @@ -132,7 +132,7 @@ static struct regulator_ops gpio_regulator_voltage_ops = { .list_voltage = gpio_regulator_list_voltage, }; -struct gpio_regulator_config * +static struct gpio_regulator_config * of_get_gpio_regulator_config(struct device *dev, struct device_node *np) { struct gpio_regulator_config *config; @@ -163,10 +163,7 @@ of_get_gpio_regulator_config(struct device *dev, struct device_node *np) config->enable_gpio = of_get_named_gpio(np, "enable-gpio", 0); /* Fetch GPIOs. */ - for (i = 0; ; i++) - if (of_get_named_gpio(np, "gpios", i) < 0) - break; - config->nr_gpios = i; + config->nr_gpios = of_gpio_count(np); config->gpios = devm_kzalloc(dev, sizeof(struct gpio) * config->nr_gpios, diff --git a/drivers/regulator/lp3971.c b/drivers/regulator/lp3971.c index 5f68ff1..9cb2c0f 100644 --- a/drivers/regulator/lp3971.c +++ b/drivers/regulator/lp3971.c @@ -73,8 +73,6 @@ static const unsigned int buck_voltage_map[] = { }; #define BUCK_TARGET_VOL_MASK 0x3f -#define BUCK_TARGET_VOL_MIN_IDX 0x01 -#define BUCK_TARGET_VOL_MAX_IDX 0x19 #define LP3971_BUCK_RAMP_REG(x) (buck_base_addr[x]+2) @@ -140,7 +138,7 @@ static int lp3971_ldo_disable(struct regulator_dev *dev) return lp3971_set_bits(lp3971, LP3971_LDO_ENABLE_REG, mask, 0); } -static int lp3971_ldo_get_voltage(struct regulator_dev *dev) +static int lp3971_ldo_get_voltage_sel(struct regulator_dev *dev) { struct lp3971 *lp3971 = rdev_get_drvdata(dev); int ldo = rdev_get_id(dev) - LP3971_LDO1; @@ -149,7 +147,7 @@ static int lp3971_ldo_get_voltage(struct regulator_dev *dev) reg = lp3971_reg_read(lp3971, LP3971_LDO_VOL_CONTR_REG(ldo)); val = (reg >> LDO_VOL_CONTR_SHIFT(ldo)) & LDO_VOL_CONTR_MASK; - return dev->desc->volt_table[val]; + return val; } static int lp3971_ldo_set_voltage_sel(struct regulator_dev *dev, @@ -168,7 +166,7 @@ static struct regulator_ops lp3971_ldo_ops = { .is_enabled = lp3971_ldo_is_enabled, .enable = lp3971_ldo_enable, .disable = lp3971_ldo_disable, - .get_voltage = lp3971_ldo_get_voltage, + .get_voltage_sel = lp3971_ldo_get_voltage_sel, .set_voltage_sel = lp3971_ldo_set_voltage_sel, }; @@ -201,24 +199,16 @@ static int lp3971_dcdc_disable(struct regulator_dev *dev) return lp3971_set_bits(lp3971, LP3971_BUCK_VOL_ENABLE_REG, mask, 0); } -static int lp3971_dcdc_get_voltage(struct regulator_dev *dev) +static int lp3971_dcdc_get_voltage_sel(struct regulator_dev *dev) { struct lp3971 *lp3971 = rdev_get_drvdata(dev); int buck = rdev_get_id(dev) - LP3971_DCDC1; u16 reg; - int val; reg = lp3971_reg_read(lp3971, LP3971_BUCK_TARGET_VOL1_REG(buck)); reg &= BUCK_TARGET_VOL_MASK; - if (reg <= BUCK_TARGET_VOL_MAX_IDX) - val = buck_voltage_map[reg]; - else { - val = 0; - dev_warn(&dev->dev, "chip reported incorrect voltage value.\n"); - } - - return val; + return reg; } static int lp3971_dcdc_set_voltage_sel(struct regulator_dev *dev, @@ -249,7 +239,7 @@ static struct regulator_ops lp3971_dcdc_ops = { .is_enabled = lp3971_dcdc_is_enabled, .enable = lp3971_dcdc_enable, .disable = lp3971_dcdc_disable, - .get_voltage = lp3971_dcdc_get_voltage, + .get_voltage_sel = lp3971_dcdc_get_voltage_sel, .set_voltage_sel = lp3971_dcdc_set_voltage_sel, }; diff --git a/drivers/regulator/lp3972.c b/drivers/regulator/lp3972.c index 69c42c3..0baabcf 100644 --- a/drivers/regulator/lp3972.c +++ b/drivers/regulator/lp3972.c @@ -165,8 +165,6 @@ static const int buck_base_addr[] = { #define LP3972_BUCK_VOL_ENABLE_REG(x) (buck_vol_enable_addr[x]) #define LP3972_BUCK_VOL1_REG(x) (buck_base_addr[x]) #define LP3972_BUCK_VOL_MASK 0x1f -#define LP3972_BUCK_VOL_MIN_IDX(x) ((x) ? 0x01 : 0x00) -#define LP3972_BUCK_VOL_MAX_IDX(x) ((x) ? 0x19 : 0x1f) static int lp3972_i2c_read(struct i2c_client *i2c, char reg, int count, u16 *dest) @@ -257,7 +255,7 @@ static int lp3972_ldo_disable(struct regulator_dev *dev) mask, 0); } -static int lp3972_ldo_get_voltage(struct regulator_dev *dev) +static int lp3972_ldo_get_voltage_sel(struct regulator_dev *dev) { struct lp3972 *lp3972 = rdev_get_drvdata(dev); int ldo = rdev_get_id(dev) - LP3972_LDO1; @@ -267,7 +265,7 @@ static int lp3972_ldo_get_voltage(struct regulator_dev *dev) reg = lp3972_reg_read(lp3972, LP3972_LDO_VOL_CONTR_REG(ldo)); val = (reg >> LP3972_LDO_VOL_CONTR_SHIFT(ldo)) & mask; - return dev->desc->volt_table[val]; + return val; } static int lp3972_ldo_set_voltage_sel(struct regulator_dev *dev, @@ -314,7 +312,7 @@ static struct regulator_ops lp3972_ldo_ops = { .is_enabled = lp3972_ldo_is_enabled, .enable = lp3972_ldo_enable, .disable = lp3972_ldo_disable, - .get_voltage = lp3972_ldo_get_voltage, + .get_voltage_sel = lp3972_ldo_get_voltage_sel, .set_voltage_sel = lp3972_ldo_set_voltage_sel, }; @@ -353,24 +351,16 @@ static int lp3972_dcdc_disable(struct regulator_dev *dev) return val; } -static int lp3972_dcdc_get_voltage(struct regulator_dev *dev) +static int lp3972_dcdc_get_voltage_sel(struct regulator_dev *dev) { struct lp3972 *lp3972 = rdev_get_drvdata(dev); int buck = rdev_get_id(dev) - LP3972_DCDC1; u16 reg; - int val; reg = lp3972_reg_read(lp3972, LP3972_BUCK_VOL1_REG(buck)); reg &= LP3972_BUCK_VOL_MASK; - if (reg <= LP3972_BUCK_VOL_MAX_IDX(buck)) - val = dev->desc->volt_table[reg]; - else { - val = 0; - dev_warn(&dev->dev, "chip reported incorrect voltage value." - " reg = %d\n", reg); - } - return val; + return reg; } static int lp3972_dcdc_set_voltage_sel(struct regulator_dev *dev, @@ -402,7 +392,7 @@ static struct regulator_ops lp3972_dcdc_ops = { .is_enabled = lp3972_dcdc_is_enabled, .enable = lp3972_dcdc_enable, .disable = lp3972_dcdc_disable, - .get_voltage = lp3972_dcdc_get_voltage, + .get_voltage_sel = lp3972_dcdc_get_voltage_sel, .set_voltage_sel = lp3972_dcdc_set_voltage_sel, }; diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c index 9289ead..8e3c7ae 100644 --- a/drivers/regulator/lp872x.c +++ b/drivers/regulator/lp872x.c @@ -181,20 +181,6 @@ static inline int lp872x_update_bits(struct lp872x *lp, u8 addr, return regmap_update_bits(lp->regmap, addr, mask, data); } -static int _rdev_to_offset(struct regulator_dev *rdev) -{ - enum lp872x_regulator_id id = rdev_get_id(rdev); - - switch (id) { - case LP8720_ID_LDO1 ... LP8720_ID_BUCK: - return id; - case LP8725_ID_LDO1 ... LP8725_ID_BUCK2: - return id - LP8725_ID_BASE; - default: - return -EINVAL; - } -} - static int lp872x_get_timestep_usec(struct lp872x *lp) { enum lp872x_id chip = lp->chipid; @@ -234,28 +220,20 @@ static int lp872x_get_timestep_usec(struct lp872x *lp) static int lp872x_regulator_enable_time(struct regulator_dev *rdev) { struct lp872x *lp = rdev_get_drvdata(rdev); - enum lp872x_regulator_id regulator = rdev_get_id(rdev); + enum lp872x_regulator_id rid = rdev_get_id(rdev); int time_step_us = lp872x_get_timestep_usec(lp); - int ret, offset; + int ret; u8 addr, val; if (time_step_us < 0) return -EINVAL; - switch (regulator) { - case LP8720_ID_LDO1 ... LP8720_ID_LDO5: - case LP8725_ID_LDO1 ... LP8725_ID_LILO2: - offset = _rdev_to_offset(rdev); - if (offset < 0) - return -EINVAL; - - addr = LP872X_LDO1_VOUT + offset; - break; - case LP8720_ID_BUCK: - addr = LP8720_BUCK_VOUT1; + switch (rid) { + case LP8720_ID_LDO1 ... LP8720_ID_BUCK: + addr = LP872X_LDO1_VOUT + rid; break; - case LP8725_ID_BUCK1: - addr = LP8725_BUCK1_VOUT1; + case LP8725_ID_LDO1 ... LP8725_ID_BUCK1: + addr = LP872X_LDO1_VOUT + rid - LP8725_ID_BASE; break; case LP8725_ID_BUCK2: addr = LP8725_BUCK2_VOUT1; diff --git a/drivers/regulator/lp8755.c b/drivers/regulator/lp8755.c new file mode 100644 index 0000000..f0f6ea0 --- /dev/null +++ b/drivers/regulator/lp8755.c @@ -0,0 +1,566 @@ +/* + * LP8755 High Performance Power Management Unit : System Interface Driver + * (based on rev. 0.26) + * Copyright 2012 Texas Instruments + * + * Author: Daniel(Geon Si) Jeong <daniel.jeong@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/i2c.h> +#include <linux/err.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/gpio.h> +#include <linux/regmap.h> +#include <linux/delay.h> +#include <linux/uaccess.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/platform_data/lp8755.h> + +#define LP8755_REG_BUCK0 0x00 +#define LP8755_REG_BUCK1 0x03 +#define LP8755_REG_BUCK2 0x04 +#define LP8755_REG_BUCK3 0x01 +#define LP8755_REG_BUCK4 0x05 +#define LP8755_REG_BUCK5 0x02 +#define LP8755_REG_MAX 0xFF + +#define LP8755_BUCK_EN_M BIT(7) +#define LP8755_BUCK_LINEAR_OUT_MAX 0x76 +#define LP8755_BUCK_VOUT_M 0x7F + +struct lp8755_mphase { + int nreg; + int buck_num[LP8755_BUCK_MAX]; +}; + +struct lp8755_chip { + struct device *dev; + struct regmap *regmap; + struct lp8755_platform_data *pdata; + + int irq; + unsigned int irqmask; + + int mphase; + struct regulator_dev *rdev[LP8755_BUCK_MAX]; +}; + +/** + *lp8755_read : read a single register value from lp8755. + *@pchip : device to read from + *@reg : register to read from + *@val : pointer to store read value + */ +static int lp8755_read(struct lp8755_chip *pchip, unsigned int reg, + unsigned int *val) +{ + return regmap_read(pchip->regmap, reg, val); +} + +/** + *lp8755_write : write a single register value to lp8755. + *@pchip : device to write to + *@reg : register to write to + *@val : value to be written + */ +static int lp8755_write(struct lp8755_chip *pchip, unsigned int reg, + unsigned int val) +{ + return regmap_write(pchip->regmap, reg, val); +} + +/** + *lp8755_update_bits : set the values of bit fields in lp8755 register. + *@pchip : device to read from + *@reg : register to update + *@mask : bitmask to be changed + *@val : value for bitmask + */ +static int lp8755_update_bits(struct lp8755_chip *pchip, unsigned int reg, + unsigned int mask, unsigned int val) +{ + return regmap_update_bits(pchip->regmap, reg, mask, val); +} + +static int lp8755_buck_enable_time(struct regulator_dev *rdev) +{ + int ret; + unsigned int regval; + enum lp8755_bucks id = rdev_get_id(rdev); + struct lp8755_chip *pchip = rdev_get_drvdata(rdev); + + ret = lp8755_read(pchip, 0x12 + id, ®val); + if (ret < 0) { + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return ret; + } + return (regval & 0xff) * 100; +} + +static int lp8755_buck_set_mode(struct regulator_dev *rdev, unsigned int mode) +{ + int ret; + unsigned int regbval = 0x0; + enum lp8755_bucks id = rdev_get_id(rdev); + struct lp8755_chip *pchip = rdev_get_drvdata(rdev); + + switch (mode) { + case REGULATOR_MODE_FAST: + /* forced pwm mode */ + regbval = (0x01 << id); + break; + case REGULATOR_MODE_NORMAL: + /* enable automatic pwm/pfm mode */ + ret = lp8755_update_bits(pchip, 0x08 + id, 0x20, 0x00); + if (ret < 0) + goto err_i2c; + break; + case REGULATOR_MODE_IDLE: + /* enable automatic pwm/pfm/lppfm mode */ + ret = lp8755_update_bits(pchip, 0x08 + id, 0x20, 0x20); + if (ret < 0) + goto err_i2c; + + ret = lp8755_update_bits(pchip, 0x10, 0x01, 0x01); + if (ret < 0) + goto err_i2c; + break; + default: + dev_err(pchip->dev, "Not supported buck mode %s\n", __func__); + /* forced pwm mode */ + regbval = (0x01 << id); + } + + ret = lp8755_update_bits(pchip, 0x06, 0x01 << id, regbval); + if (ret < 0) + goto err_i2c; + return ret; +err_i2c: + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return ret; +} + +static unsigned int lp8755_buck_get_mode(struct regulator_dev *rdev) +{ + int ret; + unsigned int regval; + enum lp8755_bucks id = rdev_get_id(rdev); + struct lp8755_chip *pchip = rdev_get_drvdata(rdev); + + ret = lp8755_read(pchip, 0x06, ®val); + if (ret < 0) + goto err_i2c; + + /* mode fast means forced pwm mode */ + if (regval & (0x01 << id)) + return REGULATOR_MODE_FAST; + + ret = lp8755_read(pchip, 0x08 + id, ®val); + if (ret < 0) + goto err_i2c; + + /* mode idle means automatic pwm/pfm/lppfm mode */ + if (regval & 0x20) + return REGULATOR_MODE_IDLE; + + /* mode normal means automatic pwm/pfm mode */ + return REGULATOR_MODE_NORMAL; + +err_i2c: + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return 0; +} + +static int lp8755_buck_set_ramp(struct regulator_dev *rdev, int ramp) +{ + int ret; + unsigned int regval = 0x00; + enum lp8755_bucks id = rdev_get_id(rdev); + struct lp8755_chip *pchip = rdev_get_drvdata(rdev); + + /* uV/us */ + switch (ramp) { + case 0 ... 230: + regval = 0x07; + break; + case 231 ... 470: + regval = 0x06; + break; + case 471 ... 940: + regval = 0x05; + break; + case 941 ... 1900: + regval = 0x04; + break; + case 1901 ... 3800: + regval = 0x03; + break; + case 3801 ... 7500: + regval = 0x02; + break; + case 7501 ... 15000: + regval = 0x01; + break; + case 15001 ... 30000: + regval = 0x00; + break; + default: + dev_err(pchip->dev, + "Not supported ramp value %d %s\n", ramp, __func__); + return -EINVAL; + } + + ret = lp8755_update_bits(pchip, 0x07 + id, 0x07, regval); + if (ret < 0) + goto err_i2c; + return ret; +err_i2c: + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return ret; +} + +static struct regulator_ops lp8755_buck_ops = { + .list_voltage = regulator_list_voltage_linear, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lp8755_buck_enable_time, + .set_mode = lp8755_buck_set_mode, + .get_mode = lp8755_buck_get_mode, + .set_ramp_delay = lp8755_buck_set_ramp, +}; + +#define lp8755_rail(_id) "lp8755_buck"#_id +#define lp8755_buck_init(_id)\ +{\ + .constraints = {\ + .name = lp8755_rail(_id),\ + .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE,\ + .min_uV = 500000,\ + .max_uV = 1675000,\ + },\ +} + +static struct regulator_init_data lp8755_reg_default[LP8755_BUCK_MAX] = { + [LP8755_BUCK0] = lp8755_buck_init(0), + [LP8755_BUCK1] = lp8755_buck_init(1), + [LP8755_BUCK2] = lp8755_buck_init(2), + [LP8755_BUCK3] = lp8755_buck_init(3), + [LP8755_BUCK4] = lp8755_buck_init(4), + [LP8755_BUCK5] = lp8755_buck_init(5), +}; + +static const struct lp8755_mphase mphase_buck[MPHASE_CONF_MAX] = { + { 3, { LP8755_BUCK0, LP8755_BUCK3, LP8755_BUCK5 } }, + { 6, { LP8755_BUCK0, LP8755_BUCK1, LP8755_BUCK2, LP8755_BUCK3, + LP8755_BUCK4, LP8755_BUCK5 } }, + { 5, { LP8755_BUCK0, LP8755_BUCK2, LP8755_BUCK3, LP8755_BUCK4, + LP8755_BUCK5} }, + { 4, { LP8755_BUCK0, LP8755_BUCK3, LP8755_BUCK4, LP8755_BUCK5} }, + { 3, { LP8755_BUCK0, LP8755_BUCK4, LP8755_BUCK5} }, + { 2, { LP8755_BUCK0, LP8755_BUCK5} }, + { 1, { LP8755_BUCK0} }, + { 2, { LP8755_BUCK0, LP8755_BUCK3} }, + { 4, { LP8755_BUCK0, LP8755_BUCK2, LP8755_BUCK3, LP8755_BUCK5} }, +}; + +static int lp8755_init_data(struct lp8755_chip *pchip) +{ + unsigned int regval; + int ret, icnt, buck_num; + struct lp8755_platform_data *pdata = pchip->pdata; + + /* read back muti-phase configuration */ + ret = lp8755_read(pchip, 0x3D, ®val); + if (ret < 0) + goto out_i2c_error; + pchip->mphase = regval & 0x0F; + + /* set default data based on multi-phase config */ + for (icnt = 0; icnt < mphase_buck[pchip->mphase].nreg; icnt++) { + buck_num = mphase_buck[pchip->mphase].buck_num[icnt]; + pdata->buck_data[buck_num] = &lp8755_reg_default[buck_num]; + } + return ret; + +out_i2c_error: + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return ret; +} + +#define lp8755_buck_desc(_id)\ +{\ + .name = lp8755_rail(_id),\ + .id = LP8755_BUCK##_id,\ + .ops = &lp8755_buck_ops,\ + .n_voltages = LP8755_BUCK_LINEAR_OUT_MAX+1,\ + .uV_step = 10000,\ + .min_uV = 500000,\ + .type = REGULATOR_VOLTAGE,\ + .owner = THIS_MODULE,\ + .enable_reg = LP8755_REG_BUCK##_id,\ + .enable_mask = LP8755_BUCK_EN_M,\ + .vsel_reg = LP8755_REG_BUCK##_id,\ + .vsel_mask = LP8755_BUCK_VOUT_M,\ +} + +static struct regulator_desc lp8755_regulators[] = { + lp8755_buck_desc(0), + lp8755_buck_desc(1), + lp8755_buck_desc(2), + lp8755_buck_desc(3), + lp8755_buck_desc(4), + lp8755_buck_desc(5), +}; + +static int lp8755_regulator_init(struct lp8755_chip *pchip) +{ + int ret, icnt, buck_num; + struct lp8755_platform_data *pdata = pchip->pdata; + struct regulator_config rconfig = { }; + + rconfig.regmap = pchip->regmap; + rconfig.dev = pchip->dev; + rconfig.driver_data = pchip; + + for (icnt = 0; icnt < mphase_buck[pchip->mphase].nreg; icnt++) { + buck_num = mphase_buck[pchip->mphase].buck_num[icnt]; + rconfig.init_data = pdata->buck_data[buck_num]; + rconfig.of_node = pchip->dev->of_node; + pchip->rdev[buck_num] = + regulator_register(&lp8755_regulators[buck_num], &rconfig); + if (IS_ERR(pchip->rdev[buck_num])) { + ret = PTR_ERR(pchip->rdev[buck_num]); + pchip->rdev[buck_num] = NULL; + dev_err(pchip->dev, "regulator init failed: buck %d\n", + buck_num); + goto err_buck; + } + } + + return 0; + +err_buck: + for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++) + regulator_unregister(pchip->rdev[icnt]); + return ret; +} + +static irqreturn_t lp8755_irq_handler(int irq, void *data) +{ + int ret, icnt; + unsigned int flag0, flag1; + struct lp8755_chip *pchip = data; + + /* read flag0 register */ + ret = lp8755_read(pchip, 0x0D, &flag0); + if (ret < 0) + goto err_i2c; + /* clear flag register to pull up int. pin */ + ret = lp8755_write(pchip, 0x0D, 0x00); + if (ret < 0) + goto err_i2c; + + /* sent power fault detection event to specific regulator */ + for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++) + if ((flag0 & (0x4 << icnt)) + && (pchip->irqmask & (0x04 << icnt)) + && (pchip->rdev[icnt] != NULL)) + regulator_notifier_call_chain(pchip->rdev[icnt], + LP8755_EVENT_PWR_FAULT, + NULL); + + /* read flag1 register */ + ret = lp8755_read(pchip, 0x0E, &flag1); + if (ret < 0) + goto err_i2c; + /* clear flag register to pull up int. pin */ + ret = lp8755_write(pchip, 0x0E, 0x00); + if (ret < 0) + goto err_i2c; + + /* send OCP event to all regualtor devices */ + if ((flag1 & 0x01) && (pchip->irqmask & 0x01)) + for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++) + if (pchip->rdev[icnt] != NULL) + regulator_notifier_call_chain(pchip->rdev[icnt], + LP8755_EVENT_OCP, + NULL); + + /* send OVP event to all regualtor devices */ + if ((flag1 & 0x02) && (pchip->irqmask & 0x02)) + for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++) + if (pchip->rdev[icnt] != NULL) + regulator_notifier_call_chain(pchip->rdev[icnt], + LP8755_EVENT_OVP, + NULL); + return IRQ_HANDLED; + +err_i2c: + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return IRQ_NONE; +} + +static int lp8755_int_config(struct lp8755_chip *pchip) +{ + int ret; + unsigned int regval; + + if (pchip->irq == 0) { + dev_warn(pchip->dev, "not use interrupt : %s\n", __func__); + return 0; + } + + ret = lp8755_read(pchip, 0x0F, ®val); + if (ret < 0) + goto err_i2c; + pchip->irqmask = regval; + ret = request_threaded_irq(pchip->irq, NULL, lp8755_irq_handler, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "lp8755-irq", pchip); + if (ret) + return ret; + + return ret; + +err_i2c: + dev_err(pchip->dev, "i2c acceess error %s\n", __func__); + return ret; +} + +static const struct regmap_config lp8755_regmap = { + .reg_bits = 8, + .val_bits = 8, + .max_register = LP8755_REG_MAX, +}; + +static int lp8755_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + int ret, icnt; + struct lp8755_chip *pchip; + struct lp8755_platform_data *pdata = client->dev.platform_data; + + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { + dev_err(&client->dev, "i2c functionality check fail.\n"); + return -EOPNOTSUPP; + } + + pchip = devm_kzalloc(&client->dev, + sizeof(struct lp8755_chip), GFP_KERNEL); + if (!pchip) + return -ENOMEM; + + pchip->dev = &client->dev; + pchip->regmap = devm_regmap_init_i2c(client, &lp8755_regmap); + if (IS_ERR(pchip->regmap)) { + ret = PTR_ERR(pchip->regmap); + dev_err(&client->dev, "fail to allocate regmap %d\n", ret); + return ret; + } + i2c_set_clientdata(client, pchip); + + if (pdata != NULL) { + pchip->pdata = pdata; + pchip->mphase = pdata->mphase; + } else { + pchip->pdata = devm_kzalloc(pchip->dev, + sizeof(struct lp8755_platform_data), + GFP_KERNEL); + if (!pchip->pdata) + return -ENOMEM; + ret = lp8755_init_data(pchip); + if (ret < 0) { + dev_err(&client->dev, "fail to initialize chip\n"); + return ret; + } + } + + ret = lp8755_regulator_init(pchip); + if (ret < 0) { + dev_err(&client->dev, "fail to initialize regulators\n"); + goto err_regulator; + } + + pchip->irq = client->irq; + ret = lp8755_int_config(pchip); + if (ret < 0) { + dev_err(&client->dev, "fail to irq config\n"); + goto err_irq; + } + + return ret; + +err_irq: + for (icnt = 0; icnt < mphase_buck[pchip->mphase].nreg; icnt++) + regulator_unregister(pchip->rdev[icnt]); + +err_regulator: + /* output disable */ + for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++) + lp8755_write(pchip, icnt, 0x00); + + return ret; +} + +static int lp8755_remove(struct i2c_client *client) +{ + int icnt; + struct lp8755_chip *pchip = i2c_get_clientdata(client); + + for (icnt = 0; icnt < mphase_buck[pchip->mphase].nreg; icnt++) + regulator_unregister(pchip->rdev[icnt]); + + for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++) + lp8755_write(pchip, icnt, 0x00); + + if (pchip->irq != 0) + free_irq(pchip->irq, pchip); + + return 0; +} + +static const struct i2c_device_id lp8755_id[] = { + {LP8755_NAME, 0}, + {} +}; + +MODULE_DEVICE_TABLE(i2c, lp8755_id); + +static struct i2c_driver lp8755_i2c_driver = { + .driver = { + .name = LP8755_NAME, + }, + .probe = lp8755_probe, + .remove = lp8755_remove, + .id_table = lp8755_id, +}; + +static int __init lp8755_init(void) +{ + return i2c_add_driver(&lp8755_i2c_driver); +} + +subsys_initcall(lp8755_init); + +static void __exit lp8755_exit(void) +{ + i2c_del_driver(&lp8755_i2c_driver); +} + +module_exit(lp8755_exit); + +MODULE_DESCRIPTION("Texas Instruments lp8755 driver"); +MODULE_AUTHOR("Daniel Jeong <daniel.jeong@ti.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/regulator/lp8788-buck.c b/drivers/regulator/lp8788-buck.c index aef3f2b..97891a7 100644 --- a/drivers/regulator/lp8788-buck.c +++ b/drivers/regulator/lp8788-buck.c @@ -103,16 +103,6 @@ static const int lp8788_buck_vtbl[] = { 1950000, 2000000, }; -static const u8 buck1_vout_addr[] = { - LP8788_BUCK1_VOUT0, LP8788_BUCK1_VOUT1, - LP8788_BUCK1_VOUT2, LP8788_BUCK1_VOUT3, -}; - -static const u8 buck2_vout_addr[] = { - LP8788_BUCK2_VOUT0, LP8788_BUCK2_VOUT1, - LP8788_BUCK2_VOUT2, LP8788_BUCK2_VOUT3, -}; - static void lp8788_buck1_set_dvs(struct lp8788_buck *buck) { struct lp8788_buck1_dvs *dvs = (struct lp8788_buck1_dvs *)buck->dvs; @@ -235,7 +225,7 @@ static u8 lp8788_select_buck_vout_addr(struct lp8788_buck *buck, lp8788_read_byte(buck->lp, LP8788_BUCK_DVS_SEL, &val); idx = (val & LP8788_BUCK1_DVS_M) >> LP8788_BUCK1_DVS_S; } - addr = buck1_vout_addr[idx]; + addr = LP8788_BUCK1_VOUT0 + idx; break; case BUCK2: if (mode == EXTPIN) { @@ -258,7 +248,7 @@ static u8 lp8788_select_buck_vout_addr(struct lp8788_buck *buck, lp8788_read_byte(buck->lp, LP8788_BUCK_DVS_SEL, &val); idx = (val & LP8788_BUCK2_DVS_M) >> LP8788_BUCK2_DVS_S; } - addr = buck2_vout_addr[idx]; + addr = LP8788_BUCK2_VOUT0 + idx; break; default: goto err; @@ -429,7 +419,8 @@ static struct regulator_desc lp8788_buck_desc[] = { }, }; -static int lp8788_dvs_gpio_request(struct lp8788_buck *buck, +static int lp8788_dvs_gpio_request(struct platform_device *pdev, + struct lp8788_buck *buck, enum lp8788_buck_id id) { struct lp8788_platform_data *pdata = buck->lp->pdata; @@ -440,7 +431,7 @@ static int lp8788_dvs_gpio_request(struct lp8788_buck *buck, switch (id) { case BUCK1: gpio = pdata->buck1_dvs->gpio; - ret = devm_gpio_request_one(buck->lp->dev, gpio, DVS_LOW, + ret = devm_gpio_request_one(&pdev->dev, gpio, DVS_LOW, b1_name); if (ret) return ret; @@ -448,9 +439,9 @@ static int lp8788_dvs_gpio_request(struct lp8788_buck *buck, buck->dvs = pdata->buck1_dvs; break; case BUCK2: - for (i = 0 ; i < LP8788_NUM_BUCK2_DVS ; i++) { + for (i = 0; i < LP8788_NUM_BUCK2_DVS; i++) { gpio = pdata->buck2_dvs->gpio[i]; - ret = devm_gpio_request_one(buck->lp->dev, gpio, + ret = devm_gpio_request_one(&pdev->dev, gpio, DVS_LOW, b2_name[i]); if (ret) return ret; @@ -464,7 +455,8 @@ static int lp8788_dvs_gpio_request(struct lp8788_buck *buck, return 0; } -static int lp8788_init_dvs(struct lp8788_buck *buck, enum lp8788_buck_id id) +static int lp8788_init_dvs(struct platform_device *pdev, + struct lp8788_buck *buck, enum lp8788_buck_id id) { struct lp8788_platform_data *pdata = buck->lp->pdata; u8 mask[] = { LP8788_BUCK1_DVS_SEL_M, LP8788_BUCK2_DVS_SEL_M }; @@ -472,7 +464,7 @@ static int lp8788_init_dvs(struct lp8788_buck *buck, enum lp8788_buck_id id) u8 default_dvs_mode[] = { LP8788_BUCK1_DVS_I2C, LP8788_BUCK2_DVS_I2C }; /* no dvs for buck3, 4 */ - if (id == BUCK3 || id == BUCK4) + if (id > BUCK2) return 0; /* no dvs platform data, then dvs will be selected by I2C registers */ @@ -483,7 +475,7 @@ static int lp8788_init_dvs(struct lp8788_buck *buck, enum lp8788_buck_id id) (id == BUCK2 && !pdata->buck2_dvs)) goto set_default_dvs_mode; - if (lp8788_dvs_gpio_request(buck, id)) + if (lp8788_dvs_gpio_request(pdev, buck, id)) goto set_default_dvs_mode; return lp8788_update_bits(buck->lp, LP8788_BUCK_DVS_SEL, mask[id], @@ -503,17 +495,20 @@ static int lp8788_buck_probe(struct platform_device *pdev) struct regulator_dev *rdev; int ret; - buck = devm_kzalloc(lp->dev, sizeof(struct lp8788_buck), GFP_KERNEL); + if (id >= LP8788_NUM_BUCKS) + return -EINVAL; + + buck = devm_kzalloc(&pdev->dev, sizeof(struct lp8788_buck), GFP_KERNEL); if (!buck) return -ENOMEM; buck->lp = lp; - ret = lp8788_init_dvs(buck, id); + ret = lp8788_init_dvs(pdev, buck, id); if (ret) return ret; - cfg.dev = lp->dev; + cfg.dev = pdev->dev.parent; cfg.init_data = lp->pdata ? lp->pdata->buck_data[id] : NULL; cfg.driver_data = buck; cfg.regmap = lp->regmap; @@ -521,7 +516,7 @@ static int lp8788_buck_probe(struct platform_device *pdev) rdev = regulator_register(&lp8788_buck_desc[id], &cfg); if (IS_ERR(rdev)) { ret = PTR_ERR(rdev); - dev_err(lp->dev, "BUCK%d regulator register err = %d\n", + dev_err(&pdev->dev, "BUCK%d regulator register err = %d\n", id + 1, ret); return ret; } diff --git a/drivers/regulator/lp8788-ldo.c b/drivers/regulator/lp8788-ldo.c index 3792741..cd5a14a 100644 --- a/drivers/regulator/lp8788-ldo.c +++ b/drivers/regulator/lp8788-ldo.c @@ -88,11 +88,6 @@ #define ENABLE GPIOF_OUT_INIT_HIGH #define DISABLE GPIOF_OUT_INIT_LOW -enum lp8788_enable_mode { - REGISTER, - EXTPIN, -}; - enum lp8788_ldo_id { DLDO1, DLDO2, @@ -189,114 +184,38 @@ static enum lp8788_ldo_id lp8788_aldo_id[] = { ALDO10, }; -/* DLDO 7, 9 and 11, ALDO 1 ~ 5 and 7 - : can be enabled either by external pin or by i2c register */ -static enum lp8788_enable_mode -lp8788_get_ldo_enable_mode(struct lp8788_ldo *ldo, enum lp8788_ldo_id id) -{ - int ret; - u8 val, mask; - - ret = lp8788_read_byte(ldo->lp, LP8788_EN_SEL, &val); - if (ret) - return ret; - - switch (id) { - case DLDO7: - mask = LP8788_EN_SEL_DLDO7_M; - break; - case DLDO9: - case DLDO11: - mask = LP8788_EN_SEL_DLDO911_M; - break; - case ALDO1: - mask = LP8788_EN_SEL_ALDO1_M; - break; - case ALDO2 ... ALDO4: - mask = LP8788_EN_SEL_ALDO234_M; - break; - case ALDO5: - mask = LP8788_EN_SEL_ALDO5_M; - break; - case ALDO7: - mask = LP8788_EN_SEL_ALDO7_M; - break; - default: - return REGISTER; - } - - return val & mask ? EXTPIN : REGISTER; -} - -static int lp8788_ldo_ctrl_by_extern_pin(struct lp8788_ldo *ldo, int pinstate) -{ - struct lp8788_ldo_enable_pin *pin = ldo->en_pin; - - if (!pin) - return -EINVAL; - - if (gpio_is_valid(pin->gpio)) - gpio_set_value(pin->gpio, pinstate); - - return 0; -} - -static int lp8788_ldo_is_enabled_by_extern_pin(struct lp8788_ldo *ldo) -{ - struct lp8788_ldo_enable_pin *pin = ldo->en_pin; - - if (!pin) - return -EINVAL; - - return gpio_get_value(pin->gpio) ? 1 : 0; -} - static int lp8788_ldo_enable(struct regulator_dev *rdev) { struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); - enum lp8788_ldo_id id = rdev_get_id(rdev); - enum lp8788_enable_mode mode = lp8788_get_ldo_enable_mode(ldo, id); - switch (mode) { - case EXTPIN: - return lp8788_ldo_ctrl_by_extern_pin(ldo, ENABLE); - case REGISTER: + if (ldo->en_pin) { + gpio_set_value(ldo->en_pin->gpio, ENABLE); + return 0; + } else { return regulator_enable_regmap(rdev); - default: - return -EINVAL; } } static int lp8788_ldo_disable(struct regulator_dev *rdev) { struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); - enum lp8788_ldo_id id = rdev_get_id(rdev); - enum lp8788_enable_mode mode = lp8788_get_ldo_enable_mode(ldo, id); - switch (mode) { - case EXTPIN: - return lp8788_ldo_ctrl_by_extern_pin(ldo, DISABLE); - case REGISTER: + if (ldo->en_pin) { + gpio_set_value(ldo->en_pin->gpio, DISABLE); + return 0; + } else { return regulator_disable_regmap(rdev); - default: - return -EINVAL; } } static int lp8788_ldo_is_enabled(struct regulator_dev *rdev) { struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); - enum lp8788_ldo_id id = rdev_get_id(rdev); - enum lp8788_enable_mode mode = lp8788_get_ldo_enable_mode(ldo, id); - switch (mode) { - case EXTPIN: - return lp8788_ldo_is_enabled_by_extern_pin(ldo); - case REGISTER: + if (ldo->en_pin) + return gpio_get_value(ldo->en_pin->gpio) ? 1 : 0; + else return regulator_is_enabled_regmap(rdev); - default: - return -EINVAL; - } } static int lp8788_ldo_enable_time(struct regulator_dev *rdev) @@ -616,10 +535,11 @@ static struct regulator_desc lp8788_aldo_desc[] = { }, }; -static int lp8788_gpio_request_ldo_en(struct lp8788_ldo *ldo, +static int lp8788_gpio_request_ldo_en(struct platform_device *pdev, + struct lp8788_ldo *ldo, enum lp8788_ext_ldo_en_id id) { - struct device *dev = ldo->lp->dev; + struct device *dev = &pdev->dev; struct lp8788_ldo_enable_pin *pin = ldo->en_pin; int ret, gpio, pinstate; char *name[] = { @@ -647,7 +567,8 @@ static int lp8788_gpio_request_ldo_en(struct lp8788_ldo *ldo, return ret; } -static int lp8788_config_ldo_enable_mode(struct lp8788_ldo *ldo, +static int lp8788_config_ldo_enable_mode(struct platform_device *pdev, + struct lp8788_ldo *ldo, enum lp8788_ldo_id id) { int ret; @@ -693,9 +614,11 @@ static int lp8788_config_ldo_enable_mode(struct lp8788_ldo *ldo, ldo->en_pin = pdata->ldo_pin[enable_id]; - ret = lp8788_gpio_request_ldo_en(ldo, enable_id); - if (ret) + ret = lp8788_gpio_request_ldo_en(pdev, ldo, enable_id); + if (ret) { + ldo->en_pin = NULL; goto set_default_ldo_enable_mode; + } return ret; @@ -712,16 +635,16 @@ static int lp8788_dldo_probe(struct platform_device *pdev) struct regulator_dev *rdev; int ret; - ldo = devm_kzalloc(lp->dev, sizeof(struct lp8788_ldo), GFP_KERNEL); + ldo = devm_kzalloc(&pdev->dev, sizeof(struct lp8788_ldo), GFP_KERNEL); if (!ldo) return -ENOMEM; ldo->lp = lp; - ret = lp8788_config_ldo_enable_mode(ldo, lp8788_dldo_id[id]); + ret = lp8788_config_ldo_enable_mode(pdev, ldo, lp8788_dldo_id[id]); if (ret) return ret; - cfg.dev = lp->dev; + cfg.dev = pdev->dev.parent; cfg.init_data = lp->pdata ? lp->pdata->dldo_data[id] : NULL; cfg.driver_data = ldo; cfg.regmap = lp->regmap; @@ -729,7 +652,7 @@ static int lp8788_dldo_probe(struct platform_device *pdev) rdev = regulator_register(&lp8788_dldo_desc[id], &cfg); if (IS_ERR(rdev)) { ret = PTR_ERR(rdev); - dev_err(lp->dev, "DLDO%d regulator register err = %d\n", + dev_err(&pdev->dev, "DLDO%d regulator register err = %d\n", id + 1, ret); return ret; } @@ -768,16 +691,16 @@ static int lp8788_aldo_probe(struct platform_device *pdev) struct regulator_dev *rdev; int ret; - ldo = devm_kzalloc(lp->dev, sizeof(struct lp8788_ldo), GFP_KERNEL); + ldo = devm_kzalloc(&pdev->dev, sizeof(struct lp8788_ldo), GFP_KERNEL); if (!ldo) return -ENOMEM; ldo->lp = lp; - ret = lp8788_config_ldo_enable_mode(ldo, lp8788_aldo_id[id]); + ret = lp8788_config_ldo_enable_mode(pdev, ldo, lp8788_aldo_id[id]); if (ret) return ret; - cfg.dev = lp->dev; + cfg.dev = pdev->dev.parent; cfg.init_data = lp->pdata ? lp->pdata->aldo_data[id] : NULL; cfg.driver_data = ldo; cfg.regmap = lp->regmap; @@ -785,7 +708,7 @@ static int lp8788_aldo_probe(struct platform_device *pdev) rdev = regulator_register(&lp8788_aldo_desc[id], &cfg); if (IS_ERR(rdev)) { ret = PTR_ERR(rdev); - dev_err(lp->dev, "ALDO%d regulator register err = %d\n", + dev_err(&pdev->dev, "ALDO%d regulator register err = %d\n", id + 1, ret); return ret; } diff --git a/drivers/regulator/max77686.c b/drivers/regulator/max77686.c index b85040c..e4586ee 100644 --- a/drivers/regulator/max77686.c +++ b/drivers/regulator/max77686.c @@ -75,13 +75,14 @@ static int max77686_buck_set_suspend_disable(struct regulator_dev *rdev) { unsigned int val; struct max77686_data *max77686 = rdev_get_drvdata(rdev); + int id = rdev_get_id(rdev); - if (rdev->desc->id == MAX77686_BUCK1) + if (id == MAX77686_BUCK1) val = 0x1; else val = 0x1 << MAX77686_OPMODE_BUCK234_SHIFT; - max77686->opmode[rdev->desc->id] = val; + max77686->opmode[id] = val; return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, val); @@ -93,9 +94,10 @@ static int max77686_set_suspend_mode(struct regulator_dev *rdev, { struct max77686_data *max77686 = rdev_get_drvdata(rdev); unsigned int val; + int id = rdev_get_id(rdev); /* BUCK[5-9] doesn't support this feature */ - if (rdev->desc->id >= MAX77686_BUCK5) + if (id >= MAX77686_BUCK5) return 0; switch (mode) { @@ -111,7 +113,7 @@ static int max77686_set_suspend_mode(struct regulator_dev *rdev, return -EINVAL; } - max77686->opmode[rdev->desc->id] = val; + max77686->opmode[id] = val; return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, val); @@ -140,7 +142,7 @@ static int max77686_ldo_set_suspend_mode(struct regulator_dev *rdev, return -EINVAL; } - max77686->opmode[rdev->desc->id] = val; + max77686->opmode[rdev_get_id(rdev)] = val; return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, val); @@ -152,7 +154,7 @@ static int max77686_enable(struct regulator_dev *rdev) return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, rdev->desc->enable_mask, - max77686->opmode[rdev->desc->id]); + max77686->opmode[rdev_get_id(rdev)]); } static int max77686_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) @@ -379,9 +381,10 @@ static struct regulator_desc regulators[] = { }; #ifdef CONFIG_OF -static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, +static int max77686_pmic_dt_parse_pdata(struct platform_device *pdev, struct max77686_platform_data *pdata) { + struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent); struct device_node *pmic_np, *regulators_np; struct max77686_regulator_data *rdata; struct of_regulator_match rmatch; @@ -390,15 +393,15 @@ static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, pmic_np = iodev->dev->of_node; regulators_np = of_find_node_by_name(pmic_np, "voltage-regulators"); if (!regulators_np) { - dev_err(iodev->dev, "could not find regulators sub-node\n"); + dev_err(&pdev->dev, "could not find regulators sub-node\n"); return -EINVAL; } pdata->num_regulators = ARRAY_SIZE(regulators); - rdata = devm_kzalloc(iodev->dev, sizeof(*rdata) * + rdata = devm_kzalloc(&pdev->dev, sizeof(*rdata) * pdata->num_regulators, GFP_KERNEL); if (!rdata) { - dev_err(iodev->dev, + dev_err(&pdev->dev, "could not allocate memory for regulator data\n"); return -ENOMEM; } @@ -407,7 +410,7 @@ static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, rmatch.name = regulators[i].name; rmatch.init_data = NULL; rmatch.of_node = NULL; - of_regulator_match(iodev->dev, regulators_np, &rmatch, 1); + of_regulator_match(&pdev->dev, regulators_np, &rmatch, 1); rdata[i].initdata = rmatch.init_data; rdata[i].of_node = rmatch.of_node; } @@ -417,7 +420,7 @@ static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, return 0; } #else -static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, +static int max77686_pmic_dt_parse_pdata(struct platform_device *pdev, struct max77686_platform_data *pdata) { return 0; @@ -440,7 +443,7 @@ static int max77686_pmic_probe(struct platform_device *pdev) } if (iodev->dev->of_node) { - ret = max77686_pmic_dt_parse_pdata(iodev, pdata); + ret = max77686_pmic_dt_parse_pdata(pdev, pdata); if (ret) return ret; } diff --git a/drivers/regulator/max8907-regulator.c b/drivers/regulator/max8907-regulator.c index d1a7751..4568c15 100644 --- a/drivers/regulator/max8907-regulator.c +++ b/drivers/regulator/max8907-regulator.c @@ -224,11 +224,11 @@ static struct of_regulator_match max8907_matches[] = { static int max8907_regulator_parse_dt(struct platform_device *pdev) { - struct device_node *np = pdev->dev.parent->of_node; - struct device_node *regulators; + struct device_node *np, *regulators; int ret; - if (!pdev->dev.parent->of_node) + np = of_node_get(pdev->dev.parent->of_node); + if (!np) return 0; regulators = of_find_node_by_name(np, "regulators"); @@ -237,9 +237,9 @@ static int max8907_regulator_parse_dt(struct platform_device *pdev) return -EINVAL; } - ret = of_regulator_match(pdev->dev.parent, regulators, - max8907_matches, + ret = of_regulator_match(&pdev->dev, regulators, max8907_matches, ARRAY_SIZE(max8907_matches)); + of_node_put(regulators); if (ret < 0) { dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret); diff --git a/drivers/regulator/max8925-regulator.c b/drivers/regulator/max8925-regulator.c index 446a854..0d5f64a 100644 --- a/drivers/regulator/max8925-regulator.c +++ b/drivers/regulator/max8925-regulator.c @@ -252,7 +252,7 @@ static int max8925_regulator_dt_init(struct platform_device *pdev, { struct device_node *nproot, *np; int rcount; - nproot = pdev->dev.parent->of_node; + nproot = of_node_get(pdev->dev.parent->of_node); if (!nproot) return -ENODEV; np = of_find_node_by_name(nproot, "regulators"); @@ -263,6 +263,7 @@ static int max8925_regulator_dt_init(struct platform_device *pdev, rcount = of_regulator_match(&pdev->dev, np, &max8925_regulator_matches[ridx], 1); + of_node_put(np); if (rcount < 0) return -ENODEV; config->init_data = max8925_regulator_matches[ridx].init_data; diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c index 02be7fc..0ac7a87 100644 --- a/drivers/regulator/max8997.c +++ b/drivers/regulator/max8997.c @@ -54,6 +54,13 @@ struct max8997_data { u8 saved_states[MAX8997_REG_MAX]; }; +static const unsigned int safeoutvolt[] = { + 4850000, + 4900000, + 4950000, + 3300000, +}; + static inline void max8997_set_gpio(struct max8997_data *max8997) { int set3 = (max8997->buck125_gpioindex) & 0x1; @@ -130,29 +137,6 @@ static const struct voltage_map_desc *reg_voltage_map[] = { [MAX8997_CHARGER_TOPOFF] = &topoff_current_map_desc, }; -static int max8997_list_voltage_safeout(struct regulator_dev *rdev, - unsigned int selector) -{ - int rid = rdev_get_id(rdev); - - if (rid == MAX8997_ESAFEOUT1 || rid == MAX8997_ESAFEOUT2) { - switch (selector) { - case 0: - return 4850000; - case 1: - return 4900000; - case 2: - return 4950000; - case 3: - return 3300000; - default: - return -EINVAL; - } - } - - return -EINVAL; -} - static int max8997_list_voltage_charger_cv(struct regulator_dev *rdev, unsigned int selector) { @@ -522,7 +506,7 @@ static int max8997_set_voltage_ldobuck(struct regulator_dev *rdev, return ret; } -static int max8997_set_voltage_ldobuck_time_sel(struct regulator_dev *rdev, +static int max8997_set_voltage_buck_time_sel(struct regulator_dev *rdev, unsigned int old_selector, unsigned int new_selector) { @@ -720,49 +704,23 @@ out: return 0; } -static const int safeoutvolt[] = { - 3300000, - 4850000, - 4900000, - 4950000, -}; - /* For SAFEOUT1 and SAFEOUT2 */ -static int max8997_set_voltage_safeout(struct regulator_dev *rdev, - int min_uV, int max_uV, unsigned *selector) +static int max8997_set_voltage_safeout_sel(struct regulator_dev *rdev, + unsigned selector) { struct max8997_data *max8997 = rdev_get_drvdata(rdev); struct i2c_client *i2c = max8997->iodev->i2c; int rid = rdev_get_id(rdev); int reg, shift = 0, mask, ret; - int i = 0; - u8 val; if (rid != MAX8997_ESAFEOUT1 && rid != MAX8997_ESAFEOUT2) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(safeoutvolt); i++) { - if (min_uV <= safeoutvolt[i] && - max_uV >= safeoutvolt[i]) - break; - } - - if (i >= ARRAY_SIZE(safeoutvolt)) - return -EINVAL; - - if (i == 0) - val = 0x3; - else - val = i - 1; - ret = max8997_get_voltage_register(rdev, ®, &shift, &mask); if (ret) return ret; - ret = max8997_update_reg(i2c, reg, val << shift, mask << shift); - *selector = val; - - return ret; + return max8997_update_reg(i2c, reg, selector << shift, mask << shift); } static int max8997_reg_disable_suspend(struct regulator_dev *rdev) @@ -799,7 +757,6 @@ static struct regulator_ops max8997_ldo_ops = { .disable = max8997_reg_disable, .get_voltage_sel = max8997_get_voltage_sel, .set_voltage = max8997_set_voltage_ldobuck, - .set_voltage_time_sel = max8997_set_voltage_ldobuck_time_sel, .set_suspend_disable = max8997_reg_disable_suspend, }; @@ -810,7 +767,7 @@ static struct regulator_ops max8997_buck_ops = { .disable = max8997_reg_disable, .get_voltage_sel = max8997_get_voltage_sel, .set_voltage = max8997_set_voltage_buck, - .set_voltage_time_sel = max8997_set_voltage_ldobuck_time_sel, + .set_voltage_time_sel = max8997_set_voltage_buck_time_sel, .set_suspend_disable = max8997_reg_disable_suspend, }; @@ -823,12 +780,12 @@ static struct regulator_ops max8997_fixedvolt_ops = { }; static struct regulator_ops max8997_safeout_ops = { - .list_voltage = max8997_list_voltage_safeout, + .list_voltage = regulator_list_voltage_table, .is_enabled = max8997_reg_is_enabled, .enable = max8997_reg_enable, .disable = max8997_reg_disable, .get_voltage_sel = max8997_get_voltage_sel, - .set_voltage = max8997_set_voltage_safeout, + .set_voltage_sel = max8997_set_voltage_safeout_sel, .set_suspend_disable = max8997_reg_disable_suspend, }; @@ -934,7 +891,7 @@ static struct regulator_desc regulators[] = { }; #ifdef CONFIG_OF -static int max8997_pmic_dt_parse_dvs_gpio(struct max8997_dev *iodev, +static int max8997_pmic_dt_parse_dvs_gpio(struct platform_device *pdev, struct max8997_platform_data *pdata, struct device_node *pmic_np) { @@ -944,7 +901,7 @@ static int max8997_pmic_dt_parse_dvs_gpio(struct max8997_dev *iodev, gpio = of_get_named_gpio(pmic_np, "max8997,pmic-buck125-dvs-gpios", i); if (!gpio_is_valid(gpio)) { - dev_err(iodev->dev, "invalid gpio[%d]: %d\n", i, gpio); + dev_err(&pdev->dev, "invalid gpio[%d]: %d\n", i, gpio); return -EINVAL; } pdata->buck125_gpios[i] = gpio; @@ -952,35 +909,34 @@ static int max8997_pmic_dt_parse_dvs_gpio(struct max8997_dev *iodev, return 0; } -static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev, +static int max8997_pmic_dt_parse_pdata(struct platform_device *pdev, struct max8997_platform_data *pdata) { + struct max8997_dev *iodev = dev_get_drvdata(pdev->dev.parent); struct device_node *pmic_np, *regulators_np, *reg_np; struct max8997_regulator_data *rdata; unsigned int i, dvs_voltage_nr = 1, ret; - pmic_np = iodev->dev->of_node; + pmic_np = of_node_get(iodev->dev->of_node); if (!pmic_np) { - dev_err(iodev->dev, "could not find pmic sub-node\n"); + dev_err(&pdev->dev, "could not find pmic sub-node\n"); return -ENODEV; } regulators_np = of_find_node_by_name(pmic_np, "regulators"); if (!regulators_np) { - dev_err(iodev->dev, "could not find regulators sub-node\n"); + dev_err(&pdev->dev, "could not find regulators sub-node\n"); return -EINVAL; } /* count the number of regulators to be supported in pmic */ - pdata->num_regulators = 0; - for_each_child_of_node(regulators_np, reg_np) - pdata->num_regulators++; + pdata->num_regulators = of_get_child_count(regulators_np); - rdata = devm_kzalloc(iodev->dev, sizeof(*rdata) * + rdata = devm_kzalloc(&pdev->dev, sizeof(*rdata) * pdata->num_regulators, GFP_KERNEL); if (!rdata) { - dev_err(iodev->dev, "could not allocate memory for " - "regulator data\n"); + of_node_put(regulators_np); + dev_err(&pdev->dev, "could not allocate memory for regulator data\n"); return -ENOMEM; } @@ -991,17 +947,18 @@ static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev, break; if (i == ARRAY_SIZE(regulators)) { - dev_warn(iodev->dev, "don't know how to configure " - "regulator %s\n", reg_np->name); + dev_warn(&pdev->dev, "don't know how to configure regulator %s\n", + reg_np->name); continue; } rdata->id = i; - rdata->initdata = of_get_regulator_init_data( - iodev->dev, reg_np); + rdata->initdata = of_get_regulator_init_data(&pdev->dev, + reg_np); rdata->reg_node = reg_np; rdata++; } + of_node_put(regulators_np); if (of_get_property(pmic_np, "max8997,pmic-buck1-uses-gpio-dvs", NULL)) pdata->buck1_gpiodvs = true; @@ -1014,7 +971,7 @@ static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev, if (pdata->buck1_gpiodvs || pdata->buck2_gpiodvs || pdata->buck5_gpiodvs) { - ret = max8997_pmic_dt_parse_dvs_gpio(iodev, pdata, pmic_np); + ret = max8997_pmic_dt_parse_dvs_gpio(pdev, pdata, pmic_np); if (ret) return -EINVAL; @@ -1025,8 +982,7 @@ static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev, } else { if (pdata->buck125_default_idx >= 8) { pdata->buck125_default_idx = 0; - dev_info(iodev->dev, "invalid value for " - "default dvs index, using 0 instead\n"); + dev_info(&pdev->dev, "invalid value for default dvs index, using 0 instead\n"); } } @@ -1040,28 +996,28 @@ static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev, if (of_property_read_u32_array(pmic_np, "max8997,pmic-buck1-dvs-voltage", pdata->buck1_voltage, dvs_voltage_nr)) { - dev_err(iodev->dev, "buck1 voltages not specified\n"); + dev_err(&pdev->dev, "buck1 voltages not specified\n"); return -EINVAL; } if (of_property_read_u32_array(pmic_np, "max8997,pmic-buck2-dvs-voltage", pdata->buck2_voltage, dvs_voltage_nr)) { - dev_err(iodev->dev, "buck2 voltages not specified\n"); + dev_err(&pdev->dev, "buck2 voltages not specified\n"); return -EINVAL; } if (of_property_read_u32_array(pmic_np, "max8997,pmic-buck5-dvs-voltage", pdata->buck5_voltage, dvs_voltage_nr)) { - dev_err(iodev->dev, "buck5 voltages not specified\n"); + dev_err(&pdev->dev, "buck5 voltages not specified\n"); return -EINVAL; } return 0; } #else -static int max8997_pmic_dt_parse_pdata(struct max8997_dev *iodev, +static int max8997_pmic_dt_parse_pdata(struct platform_device *pdev, struct max8997_platform_data *pdata) { return 0; @@ -1085,7 +1041,7 @@ static int max8997_pmic_probe(struct platform_device *pdev) } if (iodev->dev->of_node) { - ret = max8997_pmic_dt_parse_pdata(iodev, pdata); + ret = max8997_pmic_dt_parse_pdata(pdev, pdata); if (ret) return ret; } @@ -1234,13 +1190,15 @@ static int max8997_pmic_probe(struct platform_device *pdev) int id = pdata->regulators[i].id; desc = reg_voltage_map[id]; - if (desc) + if (desc) { regulators[id].n_voltages = (desc->max - desc->min) / desc->step + 1; - else if (id == MAX8997_ESAFEOUT1 || id == MAX8997_ESAFEOUT2) - regulators[id].n_voltages = 4; - else if (id == MAX8997_CHARGER_CV) + } else if (id == MAX8997_ESAFEOUT1 || id == MAX8997_ESAFEOUT2) { + regulators[id].volt_table = safeoutvolt; + regulators[id].n_voltages = ARRAY_SIZE(safeoutvolt); + } else if (id == MAX8997_CHARGER_CV) { regulators[id].n_voltages = 16; + } config.dev = max8997->dev; config.init_data = pdata->regulators[i].initdata; diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c index 1f0df40..b588f07 100644 --- a/drivers/regulator/max8998.c +++ b/drivers/regulator/max8998.c @@ -65,7 +65,7 @@ static const struct voltage_map_desc ldo9_voltage_map_desc = { .min = 2800000, .step = 100000, .max = 3100000, }; static const struct voltage_map_desc ldo10_voltage_map_desc = { - .min = 95000, .step = 50000, .max = 1300000, + .min = 950000, .step = 50000, .max = 1300000, }; static const struct voltage_map_desc ldo1213_voltage_map_desc = { .min = 800000, .step = 100000, .max = 3300000, @@ -311,25 +311,13 @@ static int max8998_set_voltage_buck_sel(struct regulator_dev *rdev, dev_get_platdata(max8998->iodev->dev); struct i2c_client *i2c = max8998->iodev->i2c; int buck = rdev_get_id(rdev); - int reg, shift = 0, mask, ret; - int j, previous_sel; + int reg, shift = 0, mask, ret, j; static u8 buck1_last_val; ret = max8998_get_voltage_register(rdev, ®, &shift, &mask); if (ret) return ret; - previous_sel = max8998_get_voltage_sel(rdev); - - /* Check if voltage needs to be changed */ - /* if previous_voltage equal new voltage, return */ - if (previous_sel == selector) { - dev_dbg(max8998->dev, "No voltage change, old:%d, new:%d\n", - regulator_list_voltage_linear(rdev, previous_sel), - regulator_list_voltage_linear(rdev, selector)); - return ret; - } - switch (buck) { case MAX8998_BUCK1: dev_dbg(max8998->dev, diff --git a/drivers/regulator/mc13892-regulator.c b/drivers/regulator/mc13892-regulator.c index 0d84b1f..9891aec 100644 --- a/drivers/regulator/mc13892-regulator.c +++ b/drivers/regulator/mc13892-regulator.c @@ -164,6 +164,14 @@ static const unsigned int mc13892_sw1[] = { 1350000, 1375000 }; +/* + * Note: this table is used to derive SWxVSEL by index into + * the array. Offset the values by the index of 1100000uV + * to get the actual register value for that voltage selector + * if the HI bit is to be set as well. + */ +#define MC13892_SWxHI_SEL_OFFSET 20 + static const unsigned int mc13892_sw[] = { 600000, 625000, 650000, 675000, 700000, 725000, 750000, 775000, 800000, 825000, 850000, 875000, @@ -239,7 +247,6 @@ static const unsigned int mc13892_pwgtdrv[] = { }; static struct regulator_ops mc13892_gpo_regulator_ops; -/* sw regulators need special care due to the "hi bit" */ static struct regulator_ops mc13892_sw_regulator_ops; @@ -396,7 +403,7 @@ static int mc13892_sw_regulator_get_voltage_sel(struct regulator_dev *rdev) { struct mc13xxx_regulator_priv *priv = rdev_get_drvdata(rdev); int ret, id = rdev_get_id(rdev); - unsigned int val; + unsigned int val, selector; dev_dbg(rdev_get_dev(rdev), "%s id: %d\n", __func__, id); @@ -407,12 +414,28 @@ static int mc13892_sw_regulator_get_voltage_sel(struct regulator_dev *rdev) if (ret) return ret; - val = (val & mc13892_regulators[id].vsel_mask) - >> mc13892_regulators[id].vsel_shift; + /* + * Figure out if the HI bit is set inside the switcher mode register + * since this means the selector value we return is at a different + * offset into the selector table. + * + * According to the MC13892 documentation note 59 (Table 47) the SW1 + * buck switcher does not support output range programming therefore + * the HI bit must always remain 0. So do not do anything strange if + * our register is MC13892_SWITCHERS0. + */ + + selector = val & mc13892_regulators[id].vsel_mask; + + if ((mc13892_regulators[id].vsel_reg != MC13892_SWITCHERS0) && + (val & MC13892_SWITCHERS0_SWxHI)) { + selector += MC13892_SWxHI_SEL_OFFSET; + } - dev_dbg(rdev_get_dev(rdev), "%s id: %d val: %d\n", __func__, id, val); + dev_dbg(rdev_get_dev(rdev), "%s id: %d val: 0x%08x selector: %d\n", + __func__, id, val, selector); - return val; + return selector; } static int mc13892_sw_regulator_set_voltage_sel(struct regulator_dev *rdev, @@ -425,18 +448,35 @@ static int mc13892_sw_regulator_set_voltage_sel(struct regulator_dev *rdev, volt = rdev->desc->volt_table[selector]; mask = mc13892_regulators[id].vsel_mask; - reg_value = selector << mc13892_regulators[id].vsel_shift; - - if (volt > 1375000) { - mask |= MC13892_SWITCHERS0_SWxHI; - reg_value |= MC13892_SWITCHERS0_SWxHI; - } else if (volt < 1100000) { - mask |= MC13892_SWITCHERS0_SWxHI; - reg_value &= ~MC13892_SWITCHERS0_SWxHI; + reg_value = selector; + + /* + * Don't mess with the HI bit or support HI voltage offsets for SW1. + * + * Since the get_voltage_sel callback has given a fudged value for + * the selector offset, we need to back out that offset if HI is + * to be set so we write the correct value to the register. + * + * The HI bit addition and selector offset handling COULD be more + * complicated by shifting and masking off the voltage selector part + * of the register then logical OR it back in, but since the selector + * is at bits 4:0 there is very little point. This makes the whole + * thing more readable and we do far less work. + */ + + if (mc13892_regulators[id].vsel_reg != MC13892_SWITCHERS0) { + if (volt > 1375000) { + reg_value -= MC13892_SWxHI_SEL_OFFSET; + reg_value |= MC13892_SWITCHERS0_SWxHI; + mask |= MC13892_SWITCHERS0_SWxHI; + } else if (volt < 1100000) { + reg_value &= ~MC13892_SWITCHERS0_SWxHI; + mask |= MC13892_SWITCHERS0_SWxHI; + } } mc13xxx_lock(priv->mc13xxx); - ret = mc13xxx_reg_rmw(priv->mc13xxx, mc13892_regulators[id].reg, mask, + ret = mc13xxx_reg_rmw(priv->mc13xxx, mc13892_regulators[id].vsel_reg, mask, reg_value); mc13xxx_unlock(priv->mc13xxx); @@ -495,15 +535,18 @@ static int mc13892_regulator_probe(struct platform_device *pdev) struct mc13xxx_regulator_init_data *mc13xxx_data; struct regulator_config config = { }; int i, ret; - int num_regulators = 0; + int num_regulators = 0, num_parsed; u32 val; num_regulators = mc13xxx_get_num_regulators_dt(pdev); + if (num_regulators <= 0 && pdata) num_regulators = pdata->num_regulators; if (num_regulators <= 0) return -EINVAL; + num_parsed = num_regulators; + priv = devm_kzalloc(&pdev->dev, sizeof(*priv) + num_regulators * sizeof(priv->regulators[0]), GFP_KERNEL); @@ -520,7 +563,7 @@ static int mc13892_regulator_probe(struct platform_device *pdev) if (ret) goto err_unlock; - /* enable switch auto mode */ + /* enable switch auto mode (on 2.0A silicon only) */ if ((val & 0x0000FFFF) == 0x45d0) { ret = mc13xxx_reg_rmw(mc13892, MC13892_SWITCHERS4, MC13892_SWITCHERS4_SW1MODE_M | @@ -546,7 +589,39 @@ static int mc13892_regulator_probe(struct platform_device *pdev) = mc13892_vcam_get_mode; mc13xxx_data = mc13xxx_parse_regulators_dt(pdev, mc13892_regulators, - ARRAY_SIZE(mc13892_regulators)); + ARRAY_SIZE(mc13892_regulators), + &num_parsed); + + /* + * Perform a little sanity check on the regulator tree - if we found + * a number of regulators from mc13xxx_get_num_regulators_dt and + * then parsed a smaller number in mc13xxx_parse_regulators_dt then + * there is a regulator defined in the regulators node which has + * not matched any usable regulator in the driver. In this case, + * there is one missing and what will happen is the first regulator + * will get registered again. + * + * Fix this by basically making our number of registerable regulators + * equal to the number of regulators we parsed. We are allocating + * too much memory for priv, but this is unavoidable at this point. + * + * As an example of how this can happen, try making a typo in your + * regulators node (vviohi {} instead of viohi {}) so that the name + * does not match.. + * + * The check will basically pass for platform data (non-DT) because + * mc13xxx_parse_regulators_dt for !CONFIG_OF will not touch num_parsed. + * + */ + if (num_parsed != num_regulators) { + dev_warn(&pdev->dev, + "parsed %d != regulators %d - check your device tree!\n", + num_parsed, num_regulators); + + num_regulators = num_parsed; + priv->num_regulators = num_regulators; + } + for (i = 0; i < num_regulators; i++) { struct regulator_init_data *init_data; struct regulator_desc *desc; diff --git a/drivers/regulator/mc13xxx-regulator-core.c b/drivers/regulator/mc13xxx-regulator-core.c index 4ed89c6..23cf9f9 100644 --- a/drivers/regulator/mc13xxx-regulator-core.c +++ b/drivers/regulator/mc13xxx-regulator-core.c @@ -164,29 +164,30 @@ EXPORT_SYMBOL_GPL(mc13xxx_fixed_regulator_ops); #ifdef CONFIG_OF int mc13xxx_get_num_regulators_dt(struct platform_device *pdev) { - struct device_node *parent, *child; - int num = 0; + struct device_node *parent; + int num; of_node_get(pdev->dev.parent->of_node); parent = of_find_node_by_name(pdev->dev.parent->of_node, "regulators"); if (!parent) return -ENODEV; - for_each_child_of_node(parent, child) - num++; - + num = of_get_child_count(parent); + of_node_put(parent); return num; } EXPORT_SYMBOL_GPL(mc13xxx_get_num_regulators_dt); struct mc13xxx_regulator_init_data *mc13xxx_parse_regulators_dt( struct platform_device *pdev, struct mc13xxx_regulator *regulators, - int num_regulators) + int num_regulators, int *num_parsed) { struct mc13xxx_regulator_priv *priv = platform_get_drvdata(pdev); struct mc13xxx_regulator_init_data *data, *p; struct device_node *parent, *child; - int i; + int i, parsed = 0; + + *num_parsed = 0; of_node_get(pdev->dev.parent->of_node); parent = of_find_node_by_name(pdev->dev.parent->of_node, "regulators"); @@ -195,24 +196,32 @@ struct mc13xxx_regulator_init_data *mc13xxx_parse_regulators_dt( data = devm_kzalloc(&pdev->dev, sizeof(*data) * priv->num_regulators, GFP_KERNEL); - if (!data) + if (!data) { + of_node_put(parent); return NULL; + } + p = data; for_each_child_of_node(parent, child) { for (i = 0; i < num_regulators; i++) { if (!of_node_cmp(child->name, regulators[i].desc.name)) { + p->id = i; p->init_data = of_get_regulator_init_data( &pdev->dev, child); p->node = child; p++; + + parsed++; break; } } } + of_node_put(parent); + *num_parsed = parsed; return data; } EXPORT_SYMBOL_GPL(mc13xxx_parse_regulators_dt); diff --git a/drivers/regulator/mc13xxx.h b/drivers/regulator/mc13xxx.h index 06c8903..007f833 100644 --- a/drivers/regulator/mc13xxx.h +++ b/drivers/regulator/mc13xxx.h @@ -39,7 +39,7 @@ extern int mc13xxx_fixed_regulator_set_voltage(struct regulator_dev *rdev, extern int mc13xxx_get_num_regulators_dt(struct platform_device *pdev); extern struct mc13xxx_regulator_init_data *mc13xxx_parse_regulators_dt( struct platform_device *pdev, struct mc13xxx_regulator *regulators, - int num_regulators); + int num_regulators, int *num_parsed); #else static inline int mc13xxx_get_num_regulators_dt(struct platform_device *pdev) { @@ -48,7 +48,7 @@ static inline int mc13xxx_get_num_regulators_dt(struct platform_device *pdev) static inline struct mc13xxx_regulator_init_data *mc13xxx_parse_regulators_dt( struct platform_device *pdev, struct mc13xxx_regulator *regulators, - int num_regulators) + int num_regulators, int *num_parsed) { return NULL; } diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 6f68491..66ca769 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -120,6 +120,12 @@ int of_regulator_match(struct device *dev, struct device_node *node, if (!dev || !node) return -EINVAL; + for (i = 0; i < num_matches; i++) { + struct of_regulator_match *match = &matches[i]; + match->init_data = NULL; + match->of_node = NULL; + } + for_each_child_of_node(node, child) { name = of_get_property(child, "regulator-compatible", NULL); diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index c9e912f..cde13bb 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -527,6 +527,7 @@ static void palmas_dt_to_pdata(struct device *dev, u32 prop; int idx, ret; + node = of_node_get(node); regulators = of_find_node_by_name(node, "regulators"); if (!regulators) { dev_info(dev, "regulator node not found\n"); @@ -535,6 +536,7 @@ static void palmas_dt_to_pdata(struct device *dev, ret = of_regulator_match(dev, regulators, palmas_matches, PALMAS_NUM_REGS); + of_node_put(regulators); if (ret < 0) { dev_err(dev, "Error parsing regulator init data: %d\n", ret); return; @@ -566,11 +568,6 @@ static void palmas_dt_to_pdata(struct device *dev, pdata->reg_init[idx]->mode_sleep = prop; ret = of_property_read_u32(palmas_matches[idx].of_node, - "ti,warm_reset", &prop); - if (!ret) - pdata->reg_init[idx]->warm_reset = prop; - - ret = of_property_read_u32(palmas_matches[idx].of_node, "ti,tstep", &prop); if (!ret) pdata->reg_init[idx]->tstep = prop; diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index bd062a2..cd9ea2e 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -174,9 +174,9 @@ static struct regulator_ops s2mps11_buck_ops = { .min_uV = S2MPS11_BUCK_MIN2, \ .uV_step = S2MPS11_BUCK_STEP2, \ .n_voltages = S2MPS11_BUCK_N_VOLTAGES, \ - .vsel_reg = S2MPS11_REG_B9CTRL2, \ + .vsel_reg = S2MPS11_REG_B10CTRL2, \ .vsel_mask = S2MPS11_BUCK_VSEL_MASK, \ - .enable_reg = S2MPS11_REG_B9CTRL1, \ + .enable_reg = S2MPS11_REG_B10CTRL1, \ .enable_mask = S2MPS11_ENABLE_MASK \ } diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c index 33b65c9..8a83194 100644 --- a/drivers/regulator/s5m8767.c +++ b/drivers/regulator/s5m8767.c @@ -14,6 +14,7 @@ #include <linux/bug.h> #include <linux/err.h> #include <linux/gpio.h> +#include <linux/of_gpio.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/platform_device.h> @@ -21,6 +22,9 @@ #include <linux/regulator/machine.h> #include <linux/mfd/samsung/core.h> #include <linux/mfd/samsung/s5m8767.h> +#include <linux/regulator/of_regulator.h> + +#define S5M8767_OPMODE_NORMAL_MODE 0x1 struct s5m8767_info { struct device *dev; @@ -255,10 +259,8 @@ static int s5m8767_reg_disable(struct regulator_dev *rdev) return sec_reg_update(s5m8767->iodev, reg, ~mask, mask); } -static int s5m8767_get_voltage_register(struct regulator_dev *rdev, int *_reg) +static int s5m8767_get_vsel_reg(int reg_id, struct s5m8767_info *s5m8767) { - struct s5m8767_info *s5m8767 = rdev_get_drvdata(rdev); - int reg_id = rdev_get_id(rdev); int reg; switch (reg_id) { @@ -296,43 +298,18 @@ static int s5m8767_get_voltage_register(struct regulator_dev *rdev, int *_reg) return -EINVAL; } - *_reg = reg; - - return 0; -} - -static int s5m8767_get_voltage_sel(struct regulator_dev *rdev) -{ - struct s5m8767_info *s5m8767 = rdev_get_drvdata(rdev); - int reg, mask, ret; - int reg_id = rdev_get_id(rdev); - unsigned int val; - - ret = s5m8767_get_voltage_register(rdev, ®); - if (ret) - return ret; - - mask = (reg_id < S5M8767_BUCK1) ? 0x3f : 0xff; - - ret = sec_reg_read(s5m8767->iodev, reg, &val); - if (ret) - return ret; - - val &= mask; - - return val; + return reg; } -static int s5m8767_convert_voltage_to_sel( - const struct sec_voltage_desc *desc, - int min_vol, int max_vol) +static int s5m8767_convert_voltage_to_sel(const struct sec_voltage_desc *desc, + int min_vol) { int selector = 0; if (desc == NULL) return -EINVAL; - if (max_vol < desc->min || min_vol > desc->max) + if (min_vol > desc->max) return -EINVAL; if (min_vol < desc->min) @@ -340,7 +317,7 @@ static int s5m8767_convert_voltage_to_sel( selector = DIV_ROUND_UP(min_vol - desc->min, desc->step); - if (desc->min + desc->step * selector > max_vol) + if (desc->min + desc->step * selector > desc->max) return -EINVAL; return selector; @@ -373,15 +350,13 @@ static int s5m8767_set_voltage_sel(struct regulator_dev *rdev, { struct s5m8767_info *s5m8767 = rdev_get_drvdata(rdev); int reg_id = rdev_get_id(rdev); - int reg, mask, ret = 0, old_index, index = 0; + int old_index, index = 0; u8 *buck234_vol = NULL; switch (reg_id) { case S5M8767_LDO1 ... S5M8767_LDO28: - mask = 0x3f; break; case S5M8767_BUCK1 ... S5M8767_BUCK6: - mask = 0xff; if (reg_id == S5M8767_BUCK2 && s5m8767->buck2_gpiodvs) buck234_vol = &s5m8767->buck2_vol[0]; else if (reg_id == S5M8767_BUCK3 && s5m8767->buck3_gpiodvs) @@ -392,7 +367,6 @@ static int s5m8767_set_voltage_sel(struct regulator_dev *rdev, case S5M8767_BUCK7 ... S5M8767_BUCK8: return -EINVAL; case S5M8767_BUCK9: - mask = 0xff; break; default: return -EINVAL; @@ -412,11 +386,7 @@ static int s5m8767_set_voltage_sel(struct regulator_dev *rdev, else return s5m8767_set_low(s5m8767); } else { - ret = s5m8767_get_voltage_register(rdev, ®); - if (ret) - return ret; - - return sec_reg_update(s5m8767->iodev, reg, selector, mask); + return regulator_set_voltage_sel_regmap(rdev, selector); } } @@ -441,7 +411,7 @@ static struct regulator_ops s5m8767_ops = { .is_enabled = s5m8767_reg_is_enabled, .enable = s5m8767_reg_enable, .disable = s5m8767_reg_disable, - .get_voltage_sel = s5m8767_get_voltage_sel, + .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = s5m8767_set_voltage_sel, .set_voltage_time_sel = s5m8767_set_voltage_time_sel, }; @@ -508,10 +478,182 @@ static struct regulator_desc regulators[] = { s5m8767_regulator_desc(BUCK9), }; +#ifdef CONFIG_OF +static int s5m8767_pmic_dt_parse_dvs_gpio(struct sec_pmic_dev *iodev, + struct sec_platform_data *pdata, + struct device_node *pmic_np) +{ + int i, gpio; + + for (i = 0; i < 3; i++) { + gpio = of_get_named_gpio(pmic_np, + "s5m8767,pmic-buck-dvs-gpios", i); + if (!gpio_is_valid(gpio)) { + dev_err(iodev->dev, "invalid gpio[%d]: %d\n", i, gpio); + return -EINVAL; + } + pdata->buck_gpios[i] = gpio; + } + return 0; +} + +static int s5m8767_pmic_dt_parse_ds_gpio(struct sec_pmic_dev *iodev, + struct sec_platform_data *pdata, + struct device_node *pmic_np) +{ + int i, gpio; + + for (i = 0; i < 3; i++) { + gpio = of_get_named_gpio(pmic_np, + "s5m8767,pmic-buck-ds-gpios", i); + if (!gpio_is_valid(gpio)) { + dev_err(iodev->dev, "invalid gpio[%d]: %d\n", i, gpio); + return -EINVAL; + } + pdata->buck_ds[i] = gpio; + } + return 0; +} + +static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev, + struct sec_platform_data *pdata) +{ + struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent); + struct device_node *pmic_np, *regulators_np, *reg_np; + struct sec_regulator_data *rdata; + struct sec_opmode_data *rmode; + unsigned int i, dvs_voltage_nr = 1, ret; + + pmic_np = iodev->dev->of_node; + if (!pmic_np) { + dev_err(iodev->dev, "could not find pmic sub-node\n"); + return -ENODEV; + } + + regulators_np = of_find_node_by_name(pmic_np, "regulators"); + if (!regulators_np) { + dev_err(iodev->dev, "could not find regulators sub-node\n"); + return -EINVAL; + } + + /* count the number of regulators to be supported in pmic */ + pdata->num_regulators = of_get_child_count(regulators_np); + + rdata = devm_kzalloc(&pdev->dev, sizeof(*rdata) * + pdata->num_regulators, GFP_KERNEL); + if (!rdata) { + dev_err(iodev->dev, + "could not allocate memory for regulator data\n"); + return -ENOMEM; + } + + rmode = devm_kzalloc(&pdev->dev, sizeof(*rmode) * + pdata->num_regulators, GFP_KERNEL); + if (!rdata) { + dev_err(iodev->dev, + "could not allocate memory for regulator mode\n"); + return -ENOMEM; + } + + pdata->regulators = rdata; + pdata->opmode = rmode; + for_each_child_of_node(regulators_np, reg_np) { + for (i = 0; i < ARRAY_SIZE(regulators); i++) + if (!of_node_cmp(reg_np->name, regulators[i].name)) + break; + + if (i == ARRAY_SIZE(regulators)) { + dev_warn(iodev->dev, + "don't know how to configure regulator %s\n", + reg_np->name); + continue; + } + + rdata->id = i; + rdata->initdata = of_get_regulator_init_data( + &pdev->dev, reg_np); + rdata->reg_node = reg_np; + rdata++; + rmode->id = i; + if (of_property_read_u32(reg_np, "op_mode", + &rmode->mode)) { + dev_warn(iodev->dev, + "no op_mode property property at %s\n", + reg_np->full_name); + + rmode->mode = S5M8767_OPMODE_NORMAL_MODE; + } + rmode++; + } + + if (of_get_property(pmic_np, "s5m8767,pmic-buck2-uses-gpio-dvs", NULL)) + pdata->buck2_gpiodvs = true; + + if (of_get_property(pmic_np, "s5m8767,pmic-buck3-uses-gpio-dvs", NULL)) + pdata->buck3_gpiodvs = true; + + if (of_get_property(pmic_np, "s5m8767,pmic-buck4-uses-gpio-dvs", NULL)) + pdata->buck4_gpiodvs = true; + + if (pdata->buck2_gpiodvs || pdata->buck3_gpiodvs || + pdata->buck4_gpiodvs) { + ret = s5m8767_pmic_dt_parse_dvs_gpio(iodev, pdata, pmic_np); + if (ret) + return -EINVAL; + + if (of_property_read_u32(pmic_np, + "s5m8767,pmic-buck-default-dvs-idx", + &pdata->buck_default_idx)) { + pdata->buck_default_idx = 0; + } else { + if (pdata->buck_default_idx >= 8) { + pdata->buck_default_idx = 0; + dev_info(iodev->dev, + "invalid value for default dvs index, use 0\n"); + } + } + dvs_voltage_nr = 8; + } + + ret = s5m8767_pmic_dt_parse_ds_gpio(iodev, pdata, pmic_np); + if (ret) + return -EINVAL; + + if (of_property_read_u32_array(pmic_np, + "s5m8767,pmic-buck2-dvs-voltage", + pdata->buck2_voltage, dvs_voltage_nr)) { + dev_err(iodev->dev, "buck2 voltages not specified\n"); + return -EINVAL; + } + + if (of_property_read_u32_array(pmic_np, + "s5m8767,pmic-buck3-dvs-voltage", + pdata->buck3_voltage, dvs_voltage_nr)) { + dev_err(iodev->dev, "buck3 voltages not specified\n"); + return -EINVAL; + } + + if (of_property_read_u32_array(pmic_np, + "s5m8767,pmic-buck4-dvs-voltage", + pdata->buck4_voltage, dvs_voltage_nr)) { + dev_err(iodev->dev, "buck4 voltages not specified\n"); + return -EINVAL; + } + + return 0; +} +#else +static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev, + struct sec_platform_data *pdata) +{ + return 0; +} +#endif /* CONFIG_OF */ + static int s5m8767_pmic_probe(struct platform_device *pdev) { struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent); - struct sec_platform_data *pdata = dev_get_platdata(iodev->dev); + struct sec_platform_data *pdata = iodev->pdata; struct regulator_config config = { }; struct regulator_dev **rdev; struct s5m8767_info *s5m8767; @@ -522,6 +664,12 @@ static int s5m8767_pmic_probe(struct platform_device *pdev) return -ENODEV; } + if (iodev->dev->of_node) { + ret = s5m8767_pmic_dt_parse_pdata(pdev, pdata); + if (ret) + return ret; + } + if (pdata->buck2_gpiodvs) { if (pdata->buck3_gpiodvs || pdata->buck4_gpiodvs) { dev_err(&pdev->dev, "S5M8767 GPIO DVS NOT VALID\n"); @@ -577,23 +725,17 @@ static int s5m8767_pmic_probe(struct platform_device *pdev) s5m8767->opmode = pdata->opmode; buck_init = s5m8767_convert_voltage_to_sel(&buck_voltage_val2, - pdata->buck2_init, - pdata->buck2_init + - buck_voltage_val2.step); + pdata->buck2_init); sec_reg_write(s5m8767->iodev, S5M8767_REG_BUCK2DVS2, buck_init); buck_init = s5m8767_convert_voltage_to_sel(&buck_voltage_val2, - pdata->buck3_init, - pdata->buck3_init + - buck_voltage_val2.step); + pdata->buck3_init); sec_reg_write(s5m8767->iodev, S5M8767_REG_BUCK3DVS2, buck_init); buck_init = s5m8767_convert_voltage_to_sel(&buck_voltage_val2, - pdata->buck4_init, - pdata->buck4_init + - buck_voltage_val2.step); + pdata->buck4_init); sec_reg_write(s5m8767->iodev, S5M8767_REG_BUCK4DVS2, buck_init); @@ -602,27 +744,21 @@ static int s5m8767_pmic_probe(struct platform_device *pdev) s5m8767->buck2_vol[i] = s5m8767_convert_voltage_to_sel( &buck_voltage_val2, - pdata->buck2_voltage[i], - pdata->buck2_voltage[i] + - buck_voltage_val2.step); + pdata->buck2_voltage[i]); } if (s5m8767->buck3_gpiodvs) { s5m8767->buck3_vol[i] = s5m8767_convert_voltage_to_sel( &buck_voltage_val2, - pdata->buck3_voltage[i], - pdata->buck3_voltage[i] + - buck_voltage_val2.step); + pdata->buck3_voltage[i]); } if (s5m8767->buck4_gpiodvs) { s5m8767->buck4_vol[i] = s5m8767_convert_voltage_to_sel( &buck_voltage_val2, - pdata->buck4_voltage[i], - pdata->buck4_voltage[i] + - buck_voltage_val2.step); + pdata->buck4_voltage[i]); } } @@ -760,11 +896,19 @@ static int s5m8767_pmic_probe(struct platform_device *pdev) (desc->max - desc->min) / desc->step + 1; regulators[id].min_uV = desc->min; regulators[id].uV_step = desc->step; + regulators[id].vsel_reg = + s5m8767_get_vsel_reg(id, s5m8767); + if (id < S5M8767_BUCK1) + regulators[id].vsel_mask = 0x3f; + else + regulators[id].vsel_mask = 0xff; } config.dev = s5m8767->dev; config.init_data = pdata->regulators[i].initdata; config.driver_data = s5m8767; + config.regmap = iodev->regmap; + config.of_node = pdata->regulators[i].reg_node; rdev[i] = regulator_register(®ulators[id], &config); if (IS_ERR(rdev[i])) { diff --git a/drivers/regulator/tps51632-regulator.c b/drivers/regulator/tps51632-regulator.c index ab21133..6e67be7 100644 --- a/drivers/regulator/tps51632-regulator.c +++ b/drivers/regulator/tps51632-regulator.c @@ -28,10 +28,13 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/regmap.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> +#include <linux/regulator/of_regulator.h> #include <linux/regulator/tps51632-regulator.h> #include <linux/slab.h> @@ -85,49 +88,8 @@ struct tps51632_chip { struct regulator_desc desc; struct regulator_dev *rdev; struct regmap *regmap; - bool enable_pwm_dvfs; }; -static int tps51632_dcdc_get_voltage_sel(struct regulator_dev *rdev) -{ - struct tps51632_chip *tps = rdev_get_drvdata(rdev); - unsigned int data; - int ret; - unsigned int reg = TPS51632_VOLTAGE_SELECT_REG; - int vsel; - - if (tps->enable_pwm_dvfs) - reg = TPS51632_VOLTAGE_BASE_REG; - - ret = regmap_read(tps->regmap, reg, &data); - if (ret < 0) { - dev_err(tps->dev, "reg read failed, err %d\n", ret); - return ret; - } - - vsel = data & TPS51632_VOUT_MASK; - return vsel; -} - -static int tps51632_dcdc_set_voltage_sel(struct regulator_dev *rdev, - unsigned selector) -{ - struct tps51632_chip *tps = rdev_get_drvdata(rdev); - int ret; - unsigned int reg = TPS51632_VOLTAGE_SELECT_REG; - - if (tps->enable_pwm_dvfs) - reg = TPS51632_VOLTAGE_BASE_REG; - - if (selector > TPS51632_MAX_VSEL) - return -EINVAL; - - ret = regmap_write(tps->regmap, reg, selector); - if (ret < 0) - dev_err(tps->dev, "reg write failed, err %d\n", ret); - return ret; -} - static int tps51632_dcdc_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) { @@ -144,8 +106,8 @@ static int tps51632_dcdc_set_ramp_delay(struct regulator_dev *rdev, } static struct regulator_ops tps51632_dcdc_ops = { - .get_voltage_sel = tps51632_dcdc_get_voltage_sel, - .set_voltage_sel = tps51632_dcdc_set_voltage_sel, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .list_voltage = regulator_list_voltage_linear, .set_voltage_time_sel = regulator_set_voltage_time_sel, .set_ramp_delay = tps51632_dcdc_set_ramp_delay, @@ -162,7 +124,6 @@ static int tps51632_init_dcdc(struct tps51632_chip *tps, goto skip_pwm_config; control |= TPS51632_DVFS_PWMEN; - tps->enable_pwm_dvfs = pdata->enable_pwm_dvfs; vsel = TPS51632_VOLT_VSEL(pdata->base_voltage_uV); ret = regmap_write(tps->regmap, TPS51632_VOLTAGE_BASE_REG, vsel); if (ret < 0) { @@ -205,22 +166,96 @@ skip_pwm_config: return ret; } -static bool rd_wr_reg(struct device *dev, unsigned int reg) +static bool is_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case TPS51632_OFFSET_REG: + case TPS51632_FAULT_REG: + case TPS51632_IMON_REG: + return true; + default: + return false; + } +} + +static bool is_read_reg(struct device *dev, unsigned int reg) { - if ((reg >= 0x8) && (reg <= 0x10)) + switch (reg) { + case 0x08 ... 0x0F: return false; - return true; + default: + return true; + } +} + +static bool is_write_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case TPS51632_VOLTAGE_SELECT_REG: + case TPS51632_VOLTAGE_BASE_REG: + case TPS51632_VMAX_REG: + case TPS51632_DVFS_CONTROL_REG: + case TPS51632_POWER_STATE_REG: + case TPS51632_SLEW_REGS: + return true; + default: + return false; + } } static const struct regmap_config tps51632_regmap_config = { .reg_bits = 8, .val_bits = 8, - .writeable_reg = rd_wr_reg, - .readable_reg = rd_wr_reg, + .writeable_reg = is_write_reg, + .readable_reg = is_read_reg, + .volatile_reg = is_volatile_reg, .max_register = TPS51632_MAX_REG - 1, .cache_type = REGCACHE_RBTREE, }; +#if defined(CONFIG_OF) +static const struct of_device_id tps51632_of_match[] = { + { .compatible = "ti,tps51632",}, + {}, +}; +MODULE_DEVICE_TABLE(of, tps51632_of_match); + +static struct tps51632_regulator_platform_data * + of_get_tps51632_platform_data(struct device *dev) +{ + struct tps51632_regulator_platform_data *pdata; + struct device_node *np = dev->of_node; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) { + dev_err(dev, "Memory alloc failed for platform data\n"); + return NULL; + } + + pdata->reg_init_data = of_get_regulator_init_data(dev, dev->of_node); + if (!pdata->reg_init_data) { + dev_err(dev, "Not able to get OF regulator init data\n"); + return NULL; + } + + pdata->enable_pwm_dvfs = + of_property_read_bool(np, "ti,enable-pwm-dvfs"); + pdata->dvfs_step_20mV = of_property_read_bool(np, "ti,dvfs-step-20mV"); + + pdata->base_voltage_uV = pdata->reg_init_data->constraints.min_uV ? : + TPS51632_MIN_VOLATGE; + pdata->max_voltage_uV = pdata->reg_init_data->constraints.max_uV ? : + TPS51632_MAX_VOLATGE; + return pdata; +} +#else +static struct tps51632_regulator_platform_data * + of_get_tps51632_platform_data(struct device *dev) +{ + return NULL; +} +#endif + static int tps51632_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -230,7 +265,19 @@ static int tps51632_probe(struct i2c_client *client, int ret; struct regulator_config config = { }; + if (client->dev.of_node) { + const struct of_device_id *match; + match = of_match_device(of_match_ptr(tps51632_of_match), + &client->dev); + if (!match) { + dev_err(&client->dev, "Error: No device match found\n"); + return -ENODEV; + } + } + pdata = client->dev.platform_data; + if (!pdata && client->dev.of_node) + pdata = of_get_tps51632_platform_data(&client->dev); if (!pdata) { dev_err(&client->dev, "No Platform data\n"); return -EINVAL; @@ -269,6 +316,12 @@ static int tps51632_probe(struct i2c_client *client, tps->desc.type = REGULATOR_VOLTAGE; tps->desc.owner = THIS_MODULE; + if (pdata->enable_pwm_dvfs) + tps->desc.vsel_reg = TPS51632_VOLTAGE_BASE_REG; + else + tps->desc.vsel_reg = TPS51632_VOLTAGE_SELECT_REG; + tps->desc.vsel_mask = TPS51632_VOUT_MASK; + tps->regmap = devm_regmap_init_i2c(client, &tps51632_regmap_config); if (IS_ERR(tps->regmap)) { ret = PTR_ERR(tps->regmap); @@ -319,6 +372,7 @@ static struct i2c_driver tps51632_i2c_driver = { .driver = { .name = "tps51632", .owner = THIS_MODULE, + .of_match_table = of_match_ptr(tps51632_of_match), }, .probe = tps51632_probe, .remove = tps51632_remove, diff --git a/drivers/regulator/tps6507x-regulator.c b/drivers/regulator/tps6507x-regulator.c index 0233cfb..54aa2da 100644 --- a/drivers/regulator/tps6507x-regulator.c +++ b/drivers/regulator/tps6507x-regulator.c @@ -23,8 +23,10 @@ #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> #include <linux/regulator/tps6507x.h> +#include <linux/of.h> #include <linux/slab.h> #include <linux/mfd/tps6507x.h> +#include <linux/regulator/of_regulator.h> /* DCDC's */ #define TPS6507X_DCDC_1 0 @@ -356,6 +358,80 @@ static struct regulator_ops tps6507x_pmic_ops = { .list_voltage = regulator_list_voltage_table, }; +#ifdef CONFIG_OF +static struct of_regulator_match tps6507x_matches[] = { + { .name = "VDCDC1"}, + { .name = "VDCDC2"}, + { .name = "VDCDC3"}, + { .name = "LDO1"}, + { .name = "LDO2"}, +}; + +static struct tps6507x_board *tps6507x_parse_dt_reg_data( + struct platform_device *pdev, + struct of_regulator_match **tps6507x_reg_matches) +{ + struct tps6507x_board *tps_board; + struct device_node *np = pdev->dev.parent->of_node; + struct device_node *regulators; + struct of_regulator_match *matches; + static struct regulator_init_data *reg_data; + int idx = 0, count, ret; + + tps_board = devm_kzalloc(&pdev->dev, sizeof(*tps_board), + GFP_KERNEL); + if (!tps_board) { + dev_err(&pdev->dev, "Failure to alloc pdata for regulators.\n"); + return NULL; + } + + regulators = of_find_node_by_name(np, "regulators"); + if (!regulators) { + dev_err(&pdev->dev, "regulator node not found\n"); + return NULL; + } + + count = ARRAY_SIZE(tps6507x_matches); + matches = tps6507x_matches; + + ret = of_regulator_match(&pdev->dev, regulators, matches, count); + if (ret < 0) { + dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", + ret); + return NULL; + } + + *tps6507x_reg_matches = matches; + + reg_data = devm_kzalloc(&pdev->dev, (sizeof(struct regulator_init_data) + * TPS6507X_NUM_REGULATOR), GFP_KERNEL); + if (!reg_data) { + dev_err(&pdev->dev, "Failure to alloc init data for regulators.\n"); + return NULL; + } + + tps_board->tps6507x_pmic_init_data = reg_data; + + for (idx = 0; idx < count; idx++) { + if (!matches[idx].init_data || !matches[idx].of_node) + continue; + + memcpy(®_data[idx], matches[idx].init_data, + sizeof(struct regulator_init_data)); + + } + + return tps_board; +} +#else +static inline struct tps6507x_board *tps6507x_parse_dt_reg_data( + struct platform_device *pdev, + struct of_regulator_match **tps6507x_reg_matches) +{ + *tps6507x_reg_matches = NULL; + return NULL; +} +#endif static int tps6507x_pmic_probe(struct platform_device *pdev) { struct tps6507x_dev *tps6507x_dev = dev_get_drvdata(pdev->dev.parent); @@ -365,8 +441,10 @@ static int tps6507x_pmic_probe(struct platform_device *pdev) struct regulator_dev *rdev; struct tps6507x_pmic *tps; struct tps6507x_board *tps_board; + struct of_regulator_match *tps6507x_reg_matches = NULL; int i; int error; + unsigned int prop; /** * tps_board points to pmic related constants @@ -374,6 +452,9 @@ static int tps6507x_pmic_probe(struct platform_device *pdev) */ tps_board = dev_get_platdata(tps6507x_dev->dev); + if (!tps_board && tps6507x_dev->dev->of_node) + tps_board = tps6507x_parse_dt_reg_data(pdev, + &tps6507x_reg_matches); if (!tps_board) return -EINVAL; @@ -415,6 +496,17 @@ static int tps6507x_pmic_probe(struct platform_device *pdev) config.init_data = init_data; config.driver_data = tps; + if (tps6507x_reg_matches) { + error = of_property_read_u32( + tps6507x_reg_matches[i].of_node, + "ti,defdcdc_default", &prop); + + if (!error) + tps->info[i]->defdcdc_default = prop; + + config.of_node = tps6507x_reg_matches[i].of_node; + } + rdev = regulator_register(&tps->desc[i], &config); if (IS_ERR(rdev)) { dev_err(tps6507x_dev->dev, diff --git a/drivers/regulator/tps65090-regulator.c b/drivers/regulator/tps65090-regulator.c index 41c3917..c8e7045 100644 --- a/drivers/regulator/tps65090-regulator.c +++ b/drivers/regulator/tps65090-regulator.c @@ -19,11 +19,13 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/gpio.h> +#include <linux/of_gpio.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/platform_device.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> +#include <linux/regulator/of_regulator.h> #include <linux/mfd/tps65090.h> struct tps65090_regulator { @@ -67,8 +69,8 @@ static struct regulator_desc tps65090_regulator_desc[] = { tps65090_REG_DESC(FET5, "infet5", 0x13, tps65090_reg_contol_ops), tps65090_REG_DESC(FET6, "infet6", 0x14, tps65090_reg_contol_ops), tps65090_REG_DESC(FET7, "infet7", 0x15, tps65090_reg_contol_ops), - tps65090_REG_DESC(LDO1, "vsys_l1", 0, tps65090_ldo_ops), - tps65090_REG_DESC(LDO2, "vsys_l2", 0, tps65090_ldo_ops), + tps65090_REG_DESC(LDO1, "vsys-l1", 0, tps65090_ldo_ops), + tps65090_REG_DESC(LDO2, "vsys-l2", 0, tps65090_ldo_ops), }; static inline bool is_dcdc(int id) @@ -138,6 +140,92 @@ static void tps65090_configure_regulator_config( } } +#ifdef CONFIG_OF +static struct of_regulator_match tps65090_matches[] = { + { .name = "dcdc1", }, + { .name = "dcdc2", }, + { .name = "dcdc3", }, + { .name = "fet1", }, + { .name = "fet2", }, + { .name = "fet3", }, + { .name = "fet4", }, + { .name = "fet5", }, + { .name = "fet6", }, + { .name = "fet7", }, + { .name = "ldo1", }, + { .name = "ldo2", }, +}; + +static struct tps65090_platform_data *tps65090_parse_dt_reg_data( + struct platform_device *pdev, + struct of_regulator_match **tps65090_reg_matches) +{ + struct tps65090_platform_data *tps65090_pdata; + struct device_node *np = pdev->dev.parent->of_node; + struct device_node *regulators; + int idx = 0, ret; + struct tps65090_regulator_plat_data *reg_pdata; + + tps65090_pdata = devm_kzalloc(&pdev->dev, sizeof(*tps65090_pdata), + GFP_KERNEL); + if (!tps65090_pdata) { + dev_err(&pdev->dev, "Memory alloc for tps65090_pdata failed\n"); + return ERR_PTR(-ENOMEM); + } + + reg_pdata = devm_kzalloc(&pdev->dev, TPS65090_REGULATOR_MAX * + sizeof(*reg_pdata), GFP_KERNEL); + if (!reg_pdata) { + dev_err(&pdev->dev, "Memory alloc for reg_pdata failed\n"); + return ERR_PTR(-ENOMEM); + } + + regulators = of_find_node_by_name(np, "regulators"); + if (!regulators) { + dev_err(&pdev->dev, "regulator node not found\n"); + return ERR_PTR(-ENODEV); + } + + ret = of_regulator_match(&pdev->dev, regulators, tps65090_matches, + ARRAY_SIZE(tps65090_matches)); + if (ret < 0) { + dev_err(&pdev->dev, + "Error parsing regulator init data: %d\n", ret); + return ERR_PTR(ret); + } + + *tps65090_reg_matches = tps65090_matches; + for (idx = 0; idx < ARRAY_SIZE(tps65090_matches); idx++) { + struct regulator_init_data *ri_data; + struct tps65090_regulator_plat_data *rpdata; + + rpdata = ®_pdata[idx]; + ri_data = tps65090_matches[idx].init_data; + if (!ri_data || !tps65090_matches[idx].of_node) + continue; + + rpdata->reg_init_data = ri_data; + rpdata->enable_ext_control = of_property_read_bool( + tps65090_matches[idx].of_node, + "ti,enable-ext-control"); + if (rpdata->enable_ext_control) + rpdata->gpio = of_get_named_gpio(np, + "dcdc-ext-control-gpios", 0); + + tps65090_pdata->reg_pdata[idx] = rpdata; + } + return tps65090_pdata; +} +#else +static inline struct tps65090_platform_data *tps65090_parse_dt_reg_data( + struct platform_device *pdev, + struct of_regulator_match **tps65090_reg_matches) +{ + *tps65090_reg_matches = NULL; + return NULL; +} +#endif + static int tps65090_regulator_probe(struct platform_device *pdev) { struct tps65090 *tps65090_mfd = dev_get_drvdata(pdev->dev.parent); @@ -147,15 +235,19 @@ static int tps65090_regulator_probe(struct platform_device *pdev) struct tps65090_regulator_plat_data *tps_pdata; struct tps65090_regulator *pmic; struct tps65090_platform_data *tps65090_pdata; + struct of_regulator_match *tps65090_reg_matches = NULL; int num; int ret; dev_dbg(&pdev->dev, "Probing regulator\n"); tps65090_pdata = dev_get_platdata(pdev->dev.parent); - if (!tps65090_pdata) { + if (!tps65090_pdata && tps65090_mfd->dev->of_node) + tps65090_pdata = tps65090_parse_dt_reg_data(pdev, + &tps65090_reg_matches); + if (IS_ERR_OR_NULL(tps65090_pdata)) { dev_err(&pdev->dev, "Platform data missing\n"); - return -EINVAL; + return tps65090_pdata ? PTR_ERR(tps65090_pdata) : -EINVAL; } pmic = devm_kzalloc(&pdev->dev, TPS65090_REGULATOR_MAX * sizeof(*pmic), @@ -192,13 +284,17 @@ static int tps65090_regulator_probe(struct platform_device *pdev) } } - config.dev = &pdev->dev; + config.dev = pdev->dev.parent; config.driver_data = ri; config.regmap = tps65090_mfd->rmap; if (tps_pdata) config.init_data = tps_pdata->reg_init_data; else config.init_data = NULL; + if (tps65090_reg_matches) + config.of_node = tps65090_reg_matches[num].of_node; + else + config.of_node = NULL; rdev = regulator_register(ri->desc, &config); if (IS_ERR(rdev)) { diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c index 73dce76..df39518 100644 --- a/drivers/regulator/tps65217-regulator.c +++ b/drivers/regulator/tps65217-regulator.c @@ -305,8 +305,8 @@ static struct tps65217_board *tps65217_parse_dt(struct platform_device *pdev) if (!regs) return NULL; - count = of_regulator_match(pdev->dev.parent, regs, - reg_matches, TPS65217_NUM_REGULATOR); + count = of_regulator_match(&pdev->dev, regs, reg_matches, + TPS65217_NUM_REGULATOR); of_node_put(regs); if ((count < 0) || (count > TPS65217_NUM_REGULATOR)) return NULL; diff --git a/drivers/regulator/tps6586x-regulator.c b/drivers/regulator/tps6586x-regulator.c index f86da67..e68382d 100644 --- a/drivers/regulator/tps6586x-regulator.c +++ b/drivers/regulator/tps6586x-regulator.c @@ -61,10 +61,6 @@ struct tps6586x_regulator { int enable_bit[2]; int enable_reg[2]; - - /* for DVM regulators */ - int go_reg; - int go_bit; }; static inline struct device *to_tps6586x_dev(struct regulator_dev *rdev) @@ -72,37 +68,10 @@ static inline struct device *to_tps6586x_dev(struct regulator_dev *rdev) return rdev_get_dev(rdev)->parent; } -static int tps6586x_set_voltage_sel(struct regulator_dev *rdev, - unsigned selector) -{ - struct tps6586x_regulator *ri = rdev_get_drvdata(rdev); - struct device *parent = to_tps6586x_dev(rdev); - int ret, val, rid = rdev_get_id(rdev); - uint8_t mask; - - val = selector << (ffs(rdev->desc->vsel_mask) - 1); - mask = rdev->desc->vsel_mask; - - ret = tps6586x_update(parent, rdev->desc->vsel_reg, val, mask); - if (ret) - return ret; - - /* Update go bit for DVM regulators */ - switch (rid) { - case TPS6586X_ID_LDO_2: - case TPS6586X_ID_LDO_4: - case TPS6586X_ID_SM_0: - case TPS6586X_ID_SM_1: - ret = tps6586x_set_bits(parent, ri->go_reg, 1 << ri->go_bit); - break; - } - return ret; -} - static struct regulator_ops tps6586x_regulator_ops = { .list_voltage = regulator_list_voltage_table, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .set_voltage_sel = tps6586x_set_voltage_sel, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, @@ -142,7 +111,7 @@ static const unsigned int tps6586x_dvm_voltages[] = { }; #define TPS6586X_REGULATOR(_id, _pin_name, vdata, vreg, shift, nbits, \ - ereg0, ebit0, ereg1, ebit1) \ + ereg0, ebit0, ereg1, ebit1, goreg, gobit) \ .desc = { \ .supply_name = _pin_name, \ .name = "REG-" #_id, \ @@ -156,29 +125,26 @@ static const unsigned int tps6586x_dvm_voltages[] = { .enable_mask = 1 << (ebit0), \ .vsel_reg = TPS6586X_##vreg, \ .vsel_mask = ((1 << (nbits)) - 1) << (shift), \ + .apply_reg = (goreg), \ + .apply_bit = (gobit), \ }, \ .enable_reg[0] = TPS6586X_SUPPLY##ereg0, \ .enable_bit[0] = (ebit0), \ .enable_reg[1] = TPS6586X_SUPPLY##ereg1, \ .enable_bit[1] = (ebit1), -#define TPS6586X_REGULATOR_DVM_GOREG(goreg, gobit) \ - .go_reg = TPS6586X_##goreg, \ - .go_bit = (gobit), - #define TPS6586X_LDO(_id, _pname, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1) \ { \ TPS6586X_REGULATOR(_id, _pname, vdata, vreg, shift, nbits, \ - ereg0, ebit0, ereg1, ebit1) \ + ereg0, ebit0, ereg1, ebit1, 0, 0) \ } #define TPS6586X_DVM(_id, _pname, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1, goreg, gobit) \ { \ TPS6586X_REGULATOR(_id, _pname, vdata, vreg, shift, nbits, \ - ereg0, ebit0, ereg1, ebit1) \ - TPS6586X_REGULATOR_DVM_GOREG(goreg, gobit) \ + ereg0, ebit0, ereg1, ebit1, goreg, gobit) \ } #define TPS6586X_SYS_REGULATOR() \ @@ -207,13 +173,13 @@ static struct tps6586x_regulator tps6586x_regulator[] = { TPS6586X_LDO(SM_2, "vin-sm2", sm2, SUPPLYV2, 0, 5, ENC, 7, END, 7), TPS6586X_DVM(LDO_2, "vinldo23", dvm, LDO2BV1, 0, 5, ENA, 3, - ENB, 3, VCC2, 6), + ENB, 3, TPS6586X_VCC2, BIT(6)), TPS6586X_DVM(LDO_4, "vinldo4", ldo4, LDO4V1, 0, 5, ENC, 3, - END, 3, VCC1, 6), + END, 3, TPS6586X_VCC1, BIT(6)), TPS6586X_DVM(SM_0, "vin-sm0", dvm, SM0V1, 0, 5, ENA, 1, - ENB, 1, VCC1, 2), + ENB, 1, TPS6586X_VCC1, BIT(2)), TPS6586X_DVM(SM_1, "vin-sm1", dvm, SM1V1, 0, 5, ENA, 0, - ENB, 0, VCC1, 0), + ENB, 0, TPS6586X_VCC1, BIT(0)), }; /* diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c index 59c3770..6ba6931 100644 --- a/drivers/regulator/tps65910-regulator.c +++ b/drivers/regulator/tps65910-regulator.c @@ -964,8 +964,7 @@ static struct tps65910_board *tps65910_parse_dt_reg_data( { struct tps65910_board *pmic_plat_data; struct tps65910 *tps65910 = dev_get_drvdata(pdev->dev.parent); - struct device_node *np = pdev->dev.parent->of_node; - struct device_node *regulators; + struct device_node *np, *regulators; struct of_regulator_match *matches; unsigned int prop; int idx = 0, ret, count; @@ -978,6 +977,7 @@ static struct tps65910_board *tps65910_parse_dt_reg_data( return NULL; } + np = of_node_get(pdev->dev.parent->of_node); regulators = of_find_node_by_name(np, "regulators"); if (!regulators) { dev_err(&pdev->dev, "regulator node not found\n"); @@ -994,11 +994,13 @@ static struct tps65910_board *tps65910_parse_dt_reg_data( matches = tps65911_matches; break; default: + of_node_put(regulators); dev_err(&pdev->dev, "Invalid tps chip version\n"); return NULL; } - ret = of_regulator_match(pdev->dev.parent, regulators, matches, count); + ret = of_regulator_match(&pdev->dev, regulators, matches, count); + of_node_put(regulators); if (ret < 0) { dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret); diff --git a/drivers/regulator/tps80031-regulator.c b/drivers/regulator/tps80031-regulator.c index b15d711..9019d0e 100644 --- a/drivers/regulator/tps80031-regulator.c +++ b/drivers/regulator/tps80031-regulator.c @@ -728,7 +728,7 @@ static int tps80031_regulator_probe(struct platform_device *pdev) } } rdev = regulator_register(&ri->rinfo->desc, &config); - if (IS_ERR_OR_NULL(rdev)) { + if (IS_ERR(rdev)) { dev_err(&pdev->dev, "register regulator failed %s\n", ri->rinfo->desc.name); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 923a9da..5e44eaa 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -20,14 +20,24 @@ if RTC_CLASS config RTC_HCTOSYS bool "Set system time from RTC on startup and resume" default y + depends on !ALWAYS_USE_PERSISTENT_CLOCK help If you say yes here, the system time (wall clock) will be set using the value read from a specified RTC device. This is useful to avoid unnecessary fsck runs at boot time, and to network better. +config RTC_SYSTOHC + bool "Set the RTC time based on NTP synchronization" + default y + depends on !ALWAYS_USE_PERSISTENT_CLOCK + help + If you say yes here, the system time (wall clock) will be stored + in the RTC specified by RTC_HCTOSYS_DEVICE approximately every 11 + minutes if userspace reports synchronized NTP status. + config RTC_HCTOSYS_DEVICE string "RTC used to set the system time" - depends on RTC_HCTOSYS = y + depends on RTC_HCTOSYS = y || RTC_SYSTOHC = y default "rtc0" help The RTC device that will be used to (re)initialize the system diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 4418ef3..ec2988b 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -6,6 +6,7 @@ ccflags-$(CONFIG_RTC_DEBUG) := -DDEBUG obj-$(CONFIG_RTC_LIB) += rtc-lib.o obj-$(CONFIG_RTC_HCTOSYS) += hctosys.o +obj-$(CONFIG_RTC_SYSTOHC) += systohc.o obj-$(CONFIG_RTC_CLASS) += rtc-core.o rtc-core-y := class.o interface.o diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 5143629..26388f1 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -50,6 +50,10 @@ static int rtc_suspend(struct device *dev, pm_message_t mesg) struct rtc_device *rtc = to_rtc_device(dev); struct rtc_time tm; struct timespec delta, delta_delta; + + if (has_persistent_clock()) + return 0; + if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0) return 0; @@ -88,6 +92,9 @@ static int rtc_resume(struct device *dev) struct timespec new_system, new_rtc; struct timespec sleep_time; + if (has_persistent_clock()) + return 0; + rtc_hctosys_ret = -ENODEV; if (strcmp(dev_name(&rtc->dev), CONFIG_RTC_HCTOSYS_DEVICE) != 0) return 0; diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index afb7cfa..c016ad8 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -506,6 +506,7 @@ isl1208_rtc_interrupt(int irq, void *data) { unsigned long timeout = jiffies + msecs_to_jiffies(1000); struct i2c_client *client = data; + struct rtc_device *rtc = i2c_get_clientdata(client); int handled = 0, sr, err; /* @@ -528,6 +529,8 @@ isl1208_rtc_interrupt(int irq, void *data) if (sr & ISL1208_REG_SR_ALM) { dev_dbg(&client->dev, "alarm!\n"); + rtc_update_irq(rtc, 1, RTC_IRQF | RTC_AF); + /* Clear the alarm */ sr &= ~ISL1208_REG_SR_ALM; sr = i2c_smbus_write_byte_data(client, ISL1208_REG_SR, sr); diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c index 08378e3..81c5077 100644 --- a/drivers/rtc/rtc-pl031.c +++ b/drivers/rtc/rtc-pl031.c @@ -44,6 +44,7 @@ #define RTC_YMR 0x34 /* Year match register */ #define RTC_YLR 0x38 /* Year data load register */ +#define RTC_CR_EN (1 << 0) /* counter enable bit */ #define RTC_CR_CWEN (1 << 26) /* Clockwatch enable bit */ #define RTC_TCR_EN (1 << 1) /* Periodic timer enable bit */ @@ -320,7 +321,7 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id) struct pl031_local *ldata; struct pl031_vendor_data *vendor = id->data; struct rtc_class_ops *ops = &vendor->ops; - unsigned long time; + unsigned long time, data; ret = amba_request_regions(adev, NULL); if (ret) @@ -345,10 +346,13 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id) dev_dbg(&adev->dev, "designer ID = 0x%02x\n", amba_manf(adev)); dev_dbg(&adev->dev, "revision = 0x%01x\n", amba_rev(adev)); + data = readl(ldata->base + RTC_CR); /* Enable the clockwatch on ST Variants */ if (vendor->clockwatch) - writel(readl(ldata->base + RTC_CR) | RTC_CR_CWEN, - ldata->base + RTC_CR); + data |= RTC_CR_CWEN; + else + data |= RTC_CR_EN; + writel(data, ldata->base + RTC_CR); /* * On ST PL031 variants, the RTC reset value does not provide correct diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c index 00c930f..2730533 100644 --- a/drivers/rtc/rtc-vt8500.c +++ b/drivers/rtc/rtc-vt8500.c @@ -137,7 +137,7 @@ static int vt8500_rtc_set_time(struct device *dev, struct rtc_time *tm) return -EINVAL; } - writel((bin2bcd(tm->tm_year - 100) << DATE_YEAR_S) + writel((bin2bcd(tm->tm_year % 100) << DATE_YEAR_S) | (bin2bcd(tm->tm_mon + 1) << DATE_MONTH_S) | (bin2bcd(tm->tm_mday)) | ((tm->tm_year >= 200) << DATE_CENTURY_S), diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c new file mode 100644 index 0000000..bf3e242 --- /dev/null +++ b/drivers/rtc/systohc.c @@ -0,0 +1,44 @@ +/* + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + */ +#include <linux/rtc.h> +#include <linux/time.h> + +/** + * rtc_set_ntp_time - Save NTP synchronized time to the RTC + * @now: Current time of day + * + * Replacement for the NTP platform function update_persistent_clock + * that stores time for later retrieval by rtc_hctosys. + * + * Returns 0 on successful RTC update, -ENODEV if a RTC update is not + * possible at all, and various other -errno for specific temporary failure + * cases. + * + * If temporary failure is indicated the caller should try again 'soon' + */ +int rtc_set_ntp_time(struct timespec now) +{ + struct rtc_device *rtc; + struct rtc_time tm; + int err = -ENODEV; + + if (now.tv_nsec < (NSEC_PER_SEC >> 1)) + rtc_time_to_tm(now.tv_sec, &tm); + else + rtc_time_to_tm(now.tv_sec + 1, &tm); + + rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE); + if (rtc) { + /* rtc_hctosys exclusively uses UTC, so we call set_time here, + * not set_mmss. */ + if (rtc->ops && (rtc->ops->set_time || rtc->ops->set_mmss)) + err = rtc_set_time(rtc, &tm); + rtc_class_close(rtc); + } + + return err; +} diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c index d73fdcf..2839baa 100644 --- a/drivers/scsi/isci/init.c +++ b/drivers/scsi/isci/init.c @@ -633,7 +633,7 @@ static int isci_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENOMEM; pci_set_drvdata(pdev, pci_info); - if (efi_enabled) + if (efi_enabled(EFI_RUNTIME_SERVICES)) orom = isci_get_efi_var(pdev); if (!orom) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 19ee901..3a6083b 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -33,7 +33,7 @@ #include <linux/of_gpio.h> #include <linux/pm_runtime.h> #include <linux/export.h> -#include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/ioport.h> diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c index 97ac0a3..eb27530 100644 --- a/drivers/ssb/driver_gpio.c +++ b/drivers/ssb/driver_gpio.c @@ -174,3 +174,15 @@ int ssb_gpio_init(struct ssb_bus *bus) return -1; } + +int ssb_gpio_unregister(struct ssb_bus *bus) +{ + if (ssb_chipco_available(&bus->chipco) || + ssb_extif_available(&bus->extif)) { + return gpiochip_remove(&bus->gpio); + } else { + SSB_WARN_ON(1); + } + + return -1; +} diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 772ad9b..24dc331 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -443,6 +443,15 @@ static void ssb_devices_unregister(struct ssb_bus *bus) void ssb_bus_unregister(struct ssb_bus *bus) { + int err; + + err = ssb_gpio_unregister(bus); + if (err == -EBUSY) + ssb_dprintk(KERN_ERR PFX "Some GPIOs are still in use.\n"); + else if (err) + ssb_dprintk(KERN_ERR PFX + "Can not unregister GPIO driver: %i\n", err); + ssb_buses_lock(); ssb_devices_unregister(bus); list_del(&bus->list); diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h index 6c10b66..da38305 100644 --- a/drivers/ssb/ssb_private.h +++ b/drivers/ssb/ssb_private.h @@ -252,11 +252,16 @@ static inline void ssb_extif_init(struct ssb_extif *extif) #ifdef CONFIG_SSB_DRIVER_GPIO extern int ssb_gpio_init(struct ssb_bus *bus); +extern int ssb_gpio_unregister(struct ssb_bus *bus); #else /* CONFIG_SSB_DRIVER_GPIO */ static inline int ssb_gpio_init(struct ssb_bus *bus) { return -ENOTSUPP; } +static inline int ssb_gpio_unregister(struct ssb_bus *bus) +{ + return 0; +} #endif /* CONFIG_SSB_DRIVER_GPIO */ #endif /* LINUX_SSB_PRIVATE_H_ */ diff --git a/drivers/staging/csr/bh.c b/drivers/staging/csr/bh.c index 1a1f5c7..7b13359 100644 --- a/drivers/staging/csr/bh.c +++ b/drivers/staging/csr/bh.c @@ -15,7 +15,7 @@ */ #include "csr_wifi_hip_unifi.h" #include "unifi_priv.h" - +#include <linux/sched/rt.h> /* * --------------------------------------------------------------------------- diff --git a/drivers/staging/csr/unifi_sme.c b/drivers/staging/csr/unifi_sme.c index 7c6c413..49395da 100644 --- a/drivers/staging/csr/unifi_sme.c +++ b/drivers/staging/csr/unifi_sme.c @@ -15,7 +15,7 @@ #include "unifi_priv.h" #include "csr_wifi_hip_unifi.h" #include "csr_wifi_hip_conversions.h" - +#include <linux/sched/rt.h> diff --git a/drivers/staging/iio/trigger/Kconfig b/drivers/staging/iio/trigger/Kconfig index 7d32075..d44d3ad 100644 --- a/drivers/staging/iio/trigger/Kconfig +++ b/drivers/staging/iio/trigger/Kconfig @@ -21,7 +21,6 @@ config IIO_GPIO_TRIGGER config IIO_SYSFS_TRIGGER tristate "SYSFS trigger" depends on SYSFS - depends on HAVE_IRQ_WORK select IRQ_WORK help Provides support for using SYSFS entry as IIO triggers. diff --git a/drivers/staging/omapdrm/Kconfig b/drivers/staging/omapdrm/Kconfig index b724a41..09f65dc 100644 --- a/drivers/staging/omapdrm/Kconfig +++ b/drivers/staging/omapdrm/Kconfig @@ -3,8 +3,8 @@ config DRM_OMAP tristate "OMAP DRM" depends on DRM && !CONFIG_FB_OMAP2 depends on ARCH_OMAP2PLUS || ARCH_MULTIPLATFORM + depends on OMAP2_DSS select DRM_KMS_HELPER - select OMAP2_DSS select FB_SYS_FILLRECT select FB_SYS_COPYAREA select FB_SYS_IMAGEBLIT diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index e269510..f2aa754 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -941,6 +941,8 @@ int se_dev_set_queue_depth(struct se_device *dev, u32 queue_depth) int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors) { + int block_size = dev->dev_attrib.block_size; + if (dev->export_count) { pr_err("dev[%p]: Unable to change SE Device" " fabric_max_sectors while export_count is %d\n", @@ -978,8 +980,12 @@ int se_dev_set_fabric_max_sectors(struct se_device *dev, u32 fabric_max_sectors) /* * Align max_sectors down to PAGE_SIZE to follow transport_allocate_data_tasks() */ + if (!block_size) { + block_size = 512; + pr_warn("Defaulting to 512 for zero block_size\n"); + } fabric_max_sectors = se_dev_align_max_sectors(fabric_max_sectors, - dev->dev_attrib.block_size); + block_size); dev->dev_attrib.fabric_max_sectors = fabric_max_sectors; pr_debug("dev[%p]: SE Device max_sectors changed to %u\n", diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 810263d..c57bbbc 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -754,6 +754,11 @@ static int target_fabric_port_link( return -EFAULT; } + if (!(dev->dev_flags & DF_CONFIGURED)) { + pr_err("se_device not configured yet, cannot port link\n"); + return -ENODEV; + } + tpg_ci = &lun_ci->ci_parent->ci_group->cg_item; se_tpg = container_of(to_config_group(tpg_ci), struct se_portal_group, tpg_group); diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 26a6d18..a664c66 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -58,11 +58,10 @@ sbc_emulate_readcapacity(struct se_cmd *cmd) buf[7] = dev->dev_attrib.block_size & 0xff; rbuf = transport_kmap_data_sg(cmd); - if (!rbuf) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - - memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); - transport_kunmap_data_sg(cmd); + if (rbuf) { + memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); + transport_kunmap_data_sg(cmd); + } target_complete_cmd(cmd, GOOD); return 0; @@ -97,11 +96,10 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd) buf[14] = 0x80; rbuf = transport_kmap_data_sg(cmd); - if (!rbuf) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - - memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); - transport_kunmap_data_sg(cmd); + if (rbuf) { + memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); + transport_kunmap_data_sg(cmd); + } target_complete_cmd(cmd, GOOD); return 0; diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 84f9e96..2d88f08 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -641,11 +641,10 @@ spc_emulate_inquiry(struct se_cmd *cmd) out: rbuf = transport_kmap_data_sg(cmd); - if (!rbuf) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - - memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); - transport_kunmap_data_sg(cmd); + if (rbuf) { + memcpy(rbuf, buf, min_t(u32, sizeof(buf), cmd->data_length)); + transport_kunmap_data_sg(cmd); + } if (!ret) target_complete_cmd(cmd, GOOD); @@ -851,7 +850,7 @@ static sense_reason_t spc_emulate_modesense(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; char *cdb = cmd->t_task_cdb; - unsigned char *buf, *map_buf; + unsigned char buf[SE_MODE_PAGE_BUF], *rbuf; int type = dev->transport->get_device_type(dev); int ten = (cmd->t_task_cdb[0] == MODE_SENSE_10); bool dbd = !!(cdb[1] & 0x08); @@ -863,26 +862,8 @@ static sense_reason_t spc_emulate_modesense(struct se_cmd *cmd) int ret; int i; - map_buf = transport_kmap_data_sg(cmd); - if (!map_buf) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - /* - * If SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC is not set, then we - * know we actually allocated a full page. Otherwise, if the - * data buffer is too small, allocate a temporary buffer so we - * don't have to worry about overruns in all our INQUIRY - * emulation handling. - */ - if (cmd->data_length < SE_MODE_PAGE_BUF && - (cmd->se_cmd_flags & SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC)) { - buf = kzalloc(SE_MODE_PAGE_BUF, GFP_KERNEL); - if (!buf) { - transport_kunmap_data_sg(cmd); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } - } else { - buf = map_buf; - } + memset(buf, 0, SE_MODE_PAGE_BUF); + /* * Skip over MODE DATA LENGTH + MEDIUM TYPE fields to byte 3 for * MODE_SENSE_10 and byte 2 for MODE_SENSE (6). @@ -934,8 +915,6 @@ static sense_reason_t spc_emulate_modesense(struct se_cmd *cmd) if (page == 0x3f) { if (subpage != 0x00 && subpage != 0xff) { pr_warn("MODE_SENSE: Invalid subpage code: 0x%02x\n", subpage); - kfree(buf); - transport_kunmap_data_sg(cmd); return TCM_INVALID_CDB_FIELD; } @@ -972,7 +951,6 @@ static sense_reason_t spc_emulate_modesense(struct se_cmd *cmd) pr_err("MODE SENSE: unimplemented page/subpage: 0x%02x/0x%02x\n", page, subpage); - transport_kunmap_data_sg(cmd); return TCM_UNKNOWN_MODE_PAGE; set_length: @@ -981,12 +959,12 @@ set_length: else buf[0] = length - 1; - if (buf != map_buf) { - memcpy(map_buf, buf, cmd->data_length); - kfree(buf); + rbuf = transport_kmap_data_sg(cmd); + if (rbuf) { + memcpy(rbuf, buf, min_t(u32, SE_MODE_PAGE_BUF, cmd->data_length)); + transport_kunmap_data_sg(cmd); } - transport_kunmap_data_sg(cmd); target_complete_cmd(cmd, GOOD); return 0; } diff --git a/drivers/tty/serial/max3100.c b/drivers/tty/serial/max3100.c index 7ce3197..dd6277e 100644 --- a/drivers/tty/serial/max3100.c +++ b/drivers/tty/serial/max3100.c @@ -179,8 +179,7 @@ static void max3100_work(struct work_struct *w); static void max3100_dowork(struct max3100_port *s) { - if (!s->force_end_work && !work_pending(&s->work) && - !freezing(current) && !s->suspending) + if (!s->force_end_work && !freezing(current) && !s->suspending) queue_work(s->workqueue, &s->work); } diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index b3c4a25..40e5b39 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -15,6 +15,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/fs.h> diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 4225d5e..8e64adf 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -39,6 +39,7 @@ #include <asm/unaligned.h> #include <linux/platform_device.h> #include <linux/workqueue.h> +#include <linux/pm_runtime.h> #include <linux/usb.h> #include <linux/usb/hcd.h> @@ -1025,6 +1026,49 @@ static int register_root_hub(struct usb_hcd *hcd) return retval; } +/* + * usb_hcd_start_port_resume - a root-hub port is sending a resume signal + * @bus: the bus which the root hub belongs to + * @portnum: the port which is being resumed + * + * HCDs should call this function when they know that a resume signal is + * being sent to a root-hub port. The root hub will be prevented from + * going into autosuspend until usb_hcd_end_port_resume() is called. + * + * The bus's private lock must be held by the caller. + */ +void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum) +{ + unsigned bit = 1 << portnum; + + if (!(bus->resuming_ports & bit)) { + bus->resuming_ports |= bit; + pm_runtime_get_noresume(&bus->root_hub->dev); + } +} +EXPORT_SYMBOL_GPL(usb_hcd_start_port_resume); + +/* + * usb_hcd_end_port_resume - a root-hub port has stopped sending a resume signal + * @bus: the bus which the root hub belongs to + * @portnum: the port which is being resumed + * + * HCDs should call this function when they know that a resume signal has + * stopped being sent to a root-hub port. The root hub will be allowed to + * autosuspend again. + * + * The bus's private lock must be held by the caller. + */ +void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum) +{ + unsigned bit = 1 << portnum; + + if (bus->resuming_ports & bit) { + bus->resuming_ports &= ~bit; + pm_runtime_put_noidle(&bus->root_hub->dev); + } +} +EXPORT_SYMBOL_GPL(usb_hcd_end_port_resume); /*-------------------------------------------------------------------------*/ diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 957ed2c..cbf7168 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2838,6 +2838,23 @@ void usb_enable_ltm(struct usb_device *udev) EXPORT_SYMBOL_GPL(usb_enable_ltm); #ifdef CONFIG_USB_SUSPEND +/* + * usb_disable_function_remotewakeup - disable usb3.0 + * device's function remote wakeup + * @udev: target device + * + * Assume there's only one function on the USB 3.0 + * device and disable remote wake for the first + * interface. FIXME if the interface association + * descriptor shows there's more than one function. + */ +static int usb_disable_function_remotewakeup(struct usb_device *udev) +{ + return usb_control_msg(udev, usb_sndctrlpipe(udev, 0), + USB_REQ_CLEAR_FEATURE, USB_RECIP_INTERFACE, + USB_INTRF_FUNC_SUSPEND, 0, NULL, 0, + USB_CTRL_SET_TIMEOUT); +} /* * usb_port_suspend - suspend a usb device's upstream port @@ -2955,12 +2972,19 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg) dev_dbg(hub->intfdev, "can't suspend port %d, status %d\n", port1, status); /* paranoia: "should not happen" */ - if (udev->do_remote_wakeup) - (void) usb_control_msg(udev, usb_sndctrlpipe(udev, 0), - USB_REQ_CLEAR_FEATURE, USB_RECIP_DEVICE, - USB_DEVICE_REMOTE_WAKEUP, 0, - NULL, 0, - USB_CTRL_SET_TIMEOUT); + if (udev->do_remote_wakeup) { + if (!hub_is_superspeed(hub->hdev)) { + (void) usb_control_msg(udev, + usb_sndctrlpipe(udev, 0), + USB_REQ_CLEAR_FEATURE, + USB_RECIP_DEVICE, + USB_DEVICE_REMOTE_WAKEUP, 0, + NULL, 0, + USB_CTRL_SET_TIMEOUT); + } else + (void) usb_disable_function_remotewakeup(udev); + + } /* Try to enable USB2 hardware LPM again */ if (udev->usb2_hw_lpm_capable == 1) @@ -3052,20 +3076,30 @@ static int finish_port_resume(struct usb_device *udev) * udev->reset_resume */ } else if (udev->actconfig && !udev->reset_resume) { - le16_to_cpus(&devstatus); - if (devstatus & (1 << USB_DEVICE_REMOTE_WAKEUP)) { - status = usb_control_msg(udev, - usb_sndctrlpipe(udev, 0), - USB_REQ_CLEAR_FEATURE, + if (!hub_is_superspeed(udev->parent)) { + le16_to_cpus(&devstatus); + if (devstatus & (1 << USB_DEVICE_REMOTE_WAKEUP)) + status = usb_control_msg(udev, + usb_sndctrlpipe(udev, 0), + USB_REQ_CLEAR_FEATURE, USB_RECIP_DEVICE, - USB_DEVICE_REMOTE_WAKEUP, 0, - NULL, 0, - USB_CTRL_SET_TIMEOUT); - if (status) - dev_dbg(&udev->dev, - "disable remote wakeup, status %d\n", - status); + USB_DEVICE_REMOTE_WAKEUP, 0, + NULL, 0, + USB_CTRL_SET_TIMEOUT); + } else { + status = usb_get_status(udev, USB_RECIP_INTERFACE, 0, + &devstatus); + le16_to_cpus(&devstatus); + if (!status && devstatus & (USB_INTRF_STAT_FUNC_RW_CAP + | USB_INTRF_STAT_FUNC_RW)) + status = + usb_disable_function_remotewakeup(udev); } + + if (status) + dev_dbg(&udev->dev, + "disable remote wakeup, status %d\n", + status); status = 0; } return status; diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 09537b2..b416a3f 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -797,6 +797,7 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) ehci->reset_done[i] = jiffies + msecs_to_jiffies(25); set_bit(i, &ehci->resuming_ports); ehci_dbg (ehci, "port %d remote wakeup\n", i + 1); + usb_hcd_start_port_resume(&hcd->self, i); mod_timer(&hcd->rh_timer, ehci->reset_done[i]); } } diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index 4ccb97c..4d3b294 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -649,7 +649,11 @@ ehci_hub_status_data (struct usb_hcd *hcd, char *buf) status = STS_PCD; } } - /* FIXME autosuspend idle root hubs */ + + /* If a resume is in progress, make sure it can finish */ + if (ehci->resuming_ports) + mod_timer(&hcd->rh_timer, jiffies + msecs_to_jiffies(25)); + spin_unlock_irqrestore (&ehci->lock, flags); return status ? retval : 0; } @@ -851,6 +855,7 @@ static int ehci_hub_control ( /* resume signaling for 20 msec */ ehci->reset_done[wIndex] = jiffies + msecs_to_jiffies(20); + usb_hcd_start_port_resume(&hcd->self, wIndex); /* check the port again */ mod_timer(&ehci_to_hcd(ehci)->rh_timer, ehci->reset_done[wIndex]); @@ -862,6 +867,7 @@ static int ehci_hub_control ( clear_bit(wIndex, &ehci->suspended_ports); set_bit(wIndex, &ehci->port_c_suspend); ehci->reset_done[wIndex] = 0; + usb_hcd_end_port_resume(&hcd->self, wIndex); /* stop resume signaling */ temp = ehci_readl(ehci, status_reg); @@ -950,6 +956,7 @@ static int ehci_hub_control ( ehci->reset_done[wIndex] = 0; if (temp & PORT_PE) set_bit(wIndex, &ehci->port_c_suspend); + usb_hcd_end_port_resume(&hcd->self, wIndex); } if (temp & PORT_OC) diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 3d98902..fd252f0 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -1197,17 +1197,26 @@ static void start_iaa_cycle(struct ehci_hcd *ehci, bool nested) if (ehci->async_iaa || ehci->async_unlinking) return; - /* Do all the waiting QHs at once */ - ehci->async_iaa = ehci->async_unlink; - ehci->async_unlink = NULL; - /* If the controller isn't running, we don't have to wait for it */ if (unlikely(ehci->rh_state < EHCI_RH_RUNNING)) { + + /* Do all the waiting QHs */ + ehci->async_iaa = ehci->async_unlink; + ehci->async_unlink = NULL; + if (!nested) /* Avoid recursion */ end_unlink_async(ehci); /* Otherwise start a new IAA cycle */ } else if (likely(ehci->rh_state == EHCI_RH_RUNNING)) { + struct ehci_qh *qh; + + /* Do only the first waiting QH (nVidia bug?) */ + qh = ehci->async_unlink; + ehci->async_iaa = qh; + ehci->async_unlink = qh->unlink_next; + qh->unlink_next = NULL; + /* Make sure the unlinks are all visible to the hardware */ wmb(); @@ -1255,34 +1264,35 @@ static void end_unlink_async(struct ehci_hcd *ehci) } } +static void start_unlink_async(struct ehci_hcd *ehci, struct ehci_qh *qh); + static void unlink_empty_async(struct ehci_hcd *ehci) { - struct ehci_qh *qh, *next; - bool stopped = (ehci->rh_state < EHCI_RH_RUNNING); + struct ehci_qh *qh; + struct ehci_qh *qh_to_unlink = NULL; bool check_unlinks_later = false; + int count = 0; - /* Unlink all the async QHs that have been empty for a timer cycle */ - next = ehci->async->qh_next.qh; - while (next) { - qh = next; - next = qh->qh_next.qh; - + /* Find the last async QH which has been empty for a timer cycle */ + for (qh = ehci->async->qh_next.qh; qh; qh = qh->qh_next.qh) { if (list_empty(&qh->qtd_list) && qh->qh_state == QH_STATE_LINKED) { - if (!stopped && qh->unlink_cycle == - ehci->async_unlink_cycle) + ++count; + if (qh->unlink_cycle == ehci->async_unlink_cycle) check_unlinks_later = true; else - single_unlink_async(ehci, qh); + qh_to_unlink = qh; } } - /* Start a new IAA cycle if any QHs are waiting for it */ - if (ehci->async_unlink) - start_iaa_cycle(ehci, false); + /* If nothing else is being unlinked, unlink the last empty QH */ + if (!ehci->async_iaa && !ehci->async_unlink && qh_to_unlink) { + start_unlink_async(ehci, qh_to_unlink); + --count; + } - /* QHs that haven't been empty for long enough will be handled later */ - if (check_unlinks_later) { + /* Other QHs will be handled later */ + if (count > 0) { ehci_enable_event(ehci, EHCI_HRTIMER_ASYNC_UNLINKS, true); ++ehci->async_unlink_cycle; } diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index 69ebee7..b476daf 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -213,7 +213,7 @@ static inline unsigned char tt_start_uframe(struct ehci_hcd *ehci, __hc32 mask) } static const unsigned char -max_tt_usecs[] = { 125, 125, 125, 125, 125, 125, 30, 0 }; +max_tt_usecs[] = { 125, 125, 125, 125, 125, 125, 125, 25 }; /* carryover low/fullspeed bandwidth that crosses uframe boundries */ static inline void carryover_tt_bandwidth(unsigned short tt_usecs[8]) @@ -2212,11 +2212,11 @@ static void scan_isoc(struct ehci_hcd *ehci) } ehci->now_frame = now_frame; + frame = ehci->last_iso_frame; for (;;) { union ehci_shadow q, *q_p; __hc32 type, *hw_p; - frame = ehci->last_iso_frame; restart: /* scan each element in frame's queue for completions */ q_p = &ehci->pshadow [frame]; @@ -2321,6 +2321,9 @@ restart: /* Stop when we have reached the current frame */ if (frame == now_frame) break; - ehci->last_iso_frame = (frame + 1) & fmask; + + /* The last frame may still have active siTDs */ + ehci->last_iso_frame = frame; + frame = (frame + 1) & fmask; } } diff --git a/drivers/usb/host/ehci-timer.c b/drivers/usb/host/ehci-timer.c index 20dbdcb..f904071 100644 --- a/drivers/usb/host/ehci-timer.c +++ b/drivers/usb/host/ehci-timer.c @@ -113,14 +113,15 @@ static void ehci_poll_ASS(struct ehci_hcd *ehci) if (want != actual) { - /* Poll again later, but give up after about 20 ms */ - if (ehci->ASS_poll_count++ < 20) { - ehci_enable_event(ehci, EHCI_HRTIMER_POLL_ASS, true); - return; - } - ehci_dbg(ehci, "Waited too long for the async schedule status (%x/%x), giving up\n", - want, actual); + /* Poll again later */ + ehci_enable_event(ehci, EHCI_HRTIMER_POLL_ASS, true); + ++ehci->ASS_poll_count; + return; } + + if (ehci->ASS_poll_count > 20) + ehci_dbg(ehci, "ASS poll count reached %d\n", + ehci->ASS_poll_count); ehci->ASS_poll_count = 0; /* The status is up-to-date; restart or stop the schedule as needed */ @@ -159,14 +160,14 @@ static void ehci_poll_PSS(struct ehci_hcd *ehci) if (want != actual) { - /* Poll again later, but give up after about 20 ms */ - if (ehci->PSS_poll_count++ < 20) { - ehci_enable_event(ehci, EHCI_HRTIMER_POLL_PSS, true); - return; - } - ehci_dbg(ehci, "Waited too long for the periodic schedule status (%x/%x), giving up\n", - want, actual); + /* Poll again later */ + ehci_enable_event(ehci, EHCI_HRTIMER_POLL_PSS, true); + return; } + + if (ehci->PSS_poll_count > 20) + ehci_dbg(ehci, "PSS poll count reached %d\n", + ehci->PSS_poll_count); ehci->PSS_poll_count = 0; /* The status is up-to-date; restart or stop the schedule as needed */ diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index a3b6d71..4c338ec 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -780,6 +780,7 @@ void usb_enable_xhci_ports(struct pci_dev *xhci_pdev) "defaulting to EHCI.\n"); dev_warn(&xhci_pdev->dev, "USB 3.0 devices will work at USB 2.0 speeds.\n"); + usb_disable_xhci_ports(xhci_pdev); return; } diff --git a/drivers/usb/host/uhci-hub.c b/drivers/usb/host/uhci-hub.c index 768d542..15d1322 100644 --- a/drivers/usb/host/uhci-hub.c +++ b/drivers/usb/host/uhci-hub.c @@ -116,6 +116,7 @@ static void uhci_finish_suspend(struct uhci_hcd *uhci, int port, } } clear_bit(port, &uhci->resuming_ports); + usb_hcd_end_port_resume(&uhci_to_hcd(uhci)->self, port); } /* Wait for the UHCI controller in HP's iLO2 server management chip. @@ -167,6 +168,8 @@ static void uhci_check_ports(struct uhci_hcd *uhci) set_bit(port, &uhci->resuming_ports); uhci->ports_timeout = jiffies + msecs_to_jiffies(25); + usb_hcd_start_port_resume( + &uhci_to_hcd(uhci)->self, port); /* Make sure we see the port again * after the resuming period is over. */ diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 59fb5c6..7f76a49 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1698,7 +1698,7 @@ static void handle_port_status(struct xhci_hcd *xhci, faked_port_index + 1); if (slot_id && xhci->devs[slot_id]) xhci_ring_device(xhci, slot_id); - if (bus_state->port_remote_wakeup && (1 << faked_port_index)) { + if (bus_state->port_remote_wakeup & (1 << faked_port_index)) { bus_state->port_remote_wakeup &= ~(1 << faked_port_index); xhci_test_and_clear_bit(xhci, port_array, @@ -2589,6 +2589,8 @@ cleanup: (trb_comp_code != COMP_STALL && trb_comp_code != COMP_BABBLE)) xhci_urb_free_priv(xhci, urb_priv); + else + kfree(urb_priv); usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb); if ((urb->actual_length != urb->transfer_buffer_length && @@ -3108,7 +3110,7 @@ static u32 xhci_v1_0_td_remainder(int running_total, int trb_buff_len, * running_total. */ packets_transferred = (running_total + trb_buff_len) / - usb_endpoint_maxp(&urb->ep->desc); + GET_MAX_PACKET(usb_endpoint_maxp(&urb->ep->desc)); if ((total_packet_count - packets_transferred) > 31) return 31 << 17; @@ -3642,7 +3644,8 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, td_len = urb->iso_frame_desc[i].length; td_remain_len = td_len; total_packet_count = DIV_ROUND_UP(td_len, - usb_endpoint_maxp(&urb->ep->desc)); + GET_MAX_PACKET( + usb_endpoint_maxp(&urb->ep->desc))); /* A zero-length transfer still involves at least one packet. */ if (total_packet_count == 0) total_packet_count++; @@ -3664,9 +3667,11 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, td = urb_priv->td[i]; for (j = 0; j < trbs_per_td; j++) { u32 remainder = 0; - field = TRB_TBC(burst_count) | TRB_TLBPC(residue); + field = 0; if (first_trb) { + field = TRB_TBC(burst_count) | + TRB_TLBPC(residue); /* Queue the isoc TRB */ field |= TRB_TYPE(TRB_ISOC); /* Assume URB_ISO_ASAP is set */ diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index f14736f..edc0f0d 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -60,6 +60,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */ { USB_DEVICE(0x0FCF, 0x1004) }, /* Dynastream ANT2USB */ { USB_DEVICE(0x0FCF, 0x1006) }, /* Dynastream ANT development board */ + { USB_DEVICE(0x0FDE, 0xCA05) }, /* OWL Wireless Electricity Monitor CM-160 */ { USB_DEVICE(0x10A6, 0xAA26) }, /* Knock-off DCU-11 cable */ { USB_DEVICE(0x10AB, 0x10C5) }, /* Siemens MC60 Cable */ { USB_DEVICE(0x10B5, 0xAC70) }, /* Nokia CA-42 USB */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index ba68835..90ceef1 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -584,6 +584,7 @@ static struct usb_device_id id_table_combined [] = { /* * ELV devices: */ + { USB_DEVICE(FTDI_ELV_VID, FTDI_ELV_WS300_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_USR_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_MSM1_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_KL100_PID) }, @@ -670,6 +671,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) }, { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_OMNI1509) }, { USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) }, { USB_DEVICE(FTDI_VID, FTDI_MHAM_KW_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index fa5d560..9d359e1 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -147,6 +147,11 @@ #define XSENS_CONVERTER_6_PID 0xD38E #define XSENS_CONVERTER_7_PID 0xD38F +/** + * Zolix (www.zolix.com.cb) product ids + */ +#define FTDI_OMNI1509 0xD491 /* Omni1509 embedded USB-serial */ + /* * NDI (www.ndigital.com) product ids */ @@ -204,7 +209,7 @@ /* * ELV USB devices submitted by Christian Abt of ELV (www.elv.de). - * All of these devices use FTDI's vendor ID (0x0403). + * Almost all of these devices use FTDI's vendor ID (0x0403). * Further IDs taken from ELV Windows .inf file. * * The previously included PID for the UO 100 module was incorrect. @@ -212,6 +217,8 @@ * * Armin Laeuger originally sent the PID for the UM 100 module. */ +#define FTDI_ELV_VID 0x1B1F /* ELV AG */ +#define FTDI_ELV_WS300_PID 0xC006 /* eQ3 WS 300 PC II */ #define FTDI_ELV_USR_PID 0xE000 /* ELV Universal-Sound-Recorder */ #define FTDI_ELV_MSM1_PID 0xE001 /* ELV Mini-Sound-Modul */ #define FTDI_ELV_KL100_PID 0xE002 /* ELV Kfz-Leistungsmesser KL 100 */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 0d9dac9..567bc77 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -242,6 +242,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_CC864_DUAL 0x1005 #define TELIT_PRODUCT_CC864_SINGLE 0x1006 #define TELIT_PRODUCT_DE910_DUAL 0x1010 +#define TELIT_PRODUCT_LE920 0x1200 /* ZTE PRODUCTS */ #define ZTE_VENDOR_ID 0x19d2 @@ -453,6 +454,10 @@ static void option_instat_callback(struct urb *urb); #define TPLINK_VENDOR_ID 0x2357 #define TPLINK_PRODUCT_MA180 0x0201 +/* Changhong products */ +#define CHANGHONG_VENDOR_ID 0x2077 +#define CHANGHONG_PRODUCT_CH690 0x7001 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -534,6 +539,11 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info telit_le920_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(5), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -784,6 +794,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), + .driver_info = (kernel_ulong_t)&telit_le920_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&net_intf1_blacklist }, @@ -1318,6 +1330,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T) }, { USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE(CHANGHONG_VENDOR_ID, CHANGHONG_PRODUCT_CH690) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index aa148c2..2466254 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -53,6 +53,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_G1K(0x05c6, 0x9221)}, /* Generic Gobi QDL device */ {DEVICE_G1K(0x05c6, 0x9231)}, /* Generic Gobi QDL device */ {DEVICE_G1K(0x1f45, 0x0001)}, /* Unknown Gobi QDL device */ + {DEVICE_G1K(0x1bc7, 0x900e)}, /* Telit Gobi QDL device */ /* Gobi 2000 devices */ {USB_DEVICE(0x1410, 0xa010)}, /* Novatel Gobi 2000 QDL device */ diff --git a/drivers/usb/storage/initializers.c b/drivers/usb/storage/initializers.c index 105d900..16b0bf0 100644 --- a/drivers/usb/storage/initializers.c +++ b/drivers/usb/storage/initializers.c @@ -92,8 +92,8 @@ int usb_stor_ucr61s2b_init(struct us_data *us) return 0; } -/* This places the HUAWEI E220 devices in multi-port mode */ -int usb_stor_huawei_e220_init(struct us_data *us) +/* This places the HUAWEI usb dongles in multi-port mode */ +static int usb_stor_huawei_feature_init(struct us_data *us) { int result; @@ -104,3 +104,75 @@ int usb_stor_huawei_e220_init(struct us_data *us) US_DEBUGP("Huawei mode set result is %d\n", result); return 0; } + +/* + * It will send a scsi switch command called rewind' to huawei dongle. + * When the dongle receives this command at the first time, + * it will reboot immediately. After rebooted, it will ignore this command. + * So it is unnecessary to read its response. + */ +static int usb_stor_huawei_scsi_init(struct us_data *us) +{ + int result = 0; + int act_len = 0; + struct bulk_cb_wrap *bcbw = (struct bulk_cb_wrap *) us->iobuf; + char rewind_cmd[] = {0x11, 0x06, 0x20, 0x00, 0x00, 0x01, 0x01, 0x00, + 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + + bcbw->Signature = cpu_to_le32(US_BULK_CB_SIGN); + bcbw->Tag = 0; + bcbw->DataTransferLength = 0; + bcbw->Flags = bcbw->Lun = 0; + bcbw->Length = sizeof(rewind_cmd); + memset(bcbw->CDB, 0, sizeof(bcbw->CDB)); + memcpy(bcbw->CDB, rewind_cmd, sizeof(rewind_cmd)); + + result = usb_stor_bulk_transfer_buf(us, us->send_bulk_pipe, bcbw, + US_BULK_CB_WRAP_LEN, &act_len); + US_DEBUGP("transfer actual length=%d, result=%d\n", act_len, result); + return result; +} + +/* + * It tries to find the supported Huawei USB dongles. + * In Huawei, they assign the following product IDs + * for all of their mobile broadband dongles, + * including the new dongles in the future. + * So if the product ID is not included in this list, + * it means it is not Huawei's mobile broadband dongles. + */ +static int usb_stor_huawei_dongles_pid(struct us_data *us) +{ + struct usb_interface_descriptor *idesc; + int idProduct; + + idesc = &us->pusb_intf->cur_altsetting->desc; + idProduct = us->pusb_dev->descriptor.idProduct; + /* The first port is CDROM, + * means the dongle in the single port mode, + * and a switch command is required to be sent. */ + if (idesc && idesc->bInterfaceNumber == 0) { + if ((idProduct == 0x1001) + || (idProduct == 0x1003) + || (idProduct == 0x1004) + || (idProduct >= 0x1401 && idProduct <= 0x1500) + || (idProduct >= 0x1505 && idProduct <= 0x1600) + || (idProduct >= 0x1c02 && idProduct <= 0x2202)) { + return 1; + } + } + return 0; +} + +int usb_stor_huawei_init(struct us_data *us) +{ + int result = 0; + + if (usb_stor_huawei_dongles_pid(us)) { + if (us->pusb_dev->descriptor.idProduct >= 0x1446) + result = usb_stor_huawei_scsi_init(us); + else + result = usb_stor_huawei_feature_init(us); + } + return result; +} diff --git a/drivers/usb/storage/initializers.h b/drivers/usb/storage/initializers.h index 529327f..5376d4f 100644 --- a/drivers/usb/storage/initializers.h +++ b/drivers/usb/storage/initializers.h @@ -46,5 +46,5 @@ int usb_stor_euscsi_init(struct us_data *us); * flash reader */ int usb_stor_ucr61s2b_init(struct us_data *us); -/* This places the HUAWEI E220 devices in multi-port mode */ -int usb_stor_huawei_e220_init(struct us_data *us); +/* This places the HUAWEI usb dongles in multi-port mode */ +int usb_stor_huawei_init(struct us_data *us); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index d305a5a..72923b5 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1527,335 +1527,10 @@ UNUSUAL_DEV( 0x1210, 0x0003, 0x0100, 0x0100, /* Reported by fangxiaozhi <huananhu@huawei.com> * This brings the HUAWEI data card devices into multi-port mode */ -UNUSUAL_DEV( 0x12d1, 0x1001, 0x0000, 0x0000, +UNUSUAL_VENDOR_INTF(0x12d1, 0x08, 0x06, 0x50, "HUAWEI MOBILE", "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1003, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1004, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1401, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1402, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1403, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1404, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1405, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1406, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1407, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1408, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1409, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x140A, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x140B, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x140C, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x140D, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x140E, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x140F, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1410, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1411, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1412, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1413, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1414, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1415, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1416, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1417, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1418, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1419, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x141A, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x141B, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x141C, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x141D, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x141E, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x141F, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1420, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1421, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1422, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1423, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1424, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1425, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1426, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1427, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1428, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1429, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x142A, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x142B, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x142C, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x142D, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x142E, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x142F, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1430, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1431, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1432, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1433, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1434, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1435, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1436, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1437, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1438, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x1439, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x143A, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x143B, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x143C, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x143D, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x143E, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, - 0), -UNUSUAL_DEV( 0x12d1, 0x143F, 0x0000, 0x0000, - "HUAWEI MOBILE", - "Mass Storage", - USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_e220_init, + USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_huawei_init, 0), /* Reported by Vilius Bilinkevicius <vilisas AT xxx DOT lt) */ diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index 31b3e1a..cf09b6b 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -120,6 +120,17 @@ MODULE_PARM_DESC(quirks, "supplemental list of device IDs and their quirks"); .useTransport = use_transport, \ } +#define UNUSUAL_VENDOR_INTF(idVendor, cl, sc, pr, \ + vendor_name, product_name, use_protocol, use_transport, \ + init_function, Flags) \ +{ \ + .vendorName = vendor_name, \ + .productName = product_name, \ + .useProtocol = use_protocol, \ + .useTransport = use_transport, \ + .initFunction = init_function, \ +} + static struct us_unusual_dev us_unusual_dev_list[] = { # include "unusual_devs.h" { } /* Terminating entry */ @@ -131,6 +142,7 @@ static struct us_unusual_dev for_dynamic_ids = #undef UNUSUAL_DEV #undef COMPLIANT_DEV #undef USUAL_DEV +#undef UNUSUAL_VENDOR_INTF #ifdef CONFIG_LOCKDEP diff --git a/drivers/usb/storage/usual-tables.c b/drivers/usb/storage/usual-tables.c index b78a526..5ef8ce7 100644 --- a/drivers/usb/storage/usual-tables.c +++ b/drivers/usb/storage/usual-tables.c @@ -41,6 +41,20 @@ #define USUAL_DEV(useProto, useTrans) \ { USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, useProto, useTrans) } +/* Define the device is matched with Vendor ID and interface descriptors */ +#define UNUSUAL_VENDOR_INTF(id_vendor, cl, sc, pr, \ + vendorName, productName, useProtocol, useTransport, \ + initFunction, flags) \ +{ \ + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO \ + | USB_DEVICE_ID_MATCH_VENDOR, \ + .idVendor = (id_vendor), \ + .bInterfaceClass = (cl), \ + .bInterfaceSubClass = (sc), \ + .bInterfaceProtocol = (pr), \ + .driver_info = (flags) \ +} + struct usb_device_id usb_storage_usb_ids[] = { # include "unusual_devs.h" { } /* Terminating entry */ @@ -50,6 +64,7 @@ MODULE_DEVICE_TABLE(usb, usb_storage_usb_ids); #undef UNUSUAL_DEV #undef COMPLIANT_DEV #undef USUAL_DEV +#undef UNUSUAL_VENDOR_INTF /* * The table of devices to ignore diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index ebd08b2..959b1cd 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -165,12 +165,16 @@ static void tx_poll_stop(struct vhost_net *net) } /* Caller must have TX VQ lock */ -static void tx_poll_start(struct vhost_net *net, struct socket *sock) +static int tx_poll_start(struct vhost_net *net, struct socket *sock) { + int ret; + if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED)) - return; - vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file); - net->tx_poll_state = VHOST_NET_POLL_STARTED; + return 0; + ret = vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file); + if (!ret) + net->tx_poll_state = VHOST_NET_POLL_STARTED; + return ret; } /* In case of DMA done not in order in lower device driver for some reason. @@ -642,20 +646,23 @@ static void vhost_net_disable_vq(struct vhost_net *n, vhost_poll_stop(n->poll + VHOST_NET_VQ_RX); } -static void vhost_net_enable_vq(struct vhost_net *n, +static int vhost_net_enable_vq(struct vhost_net *n, struct vhost_virtqueue *vq) { struct socket *sock; + int ret; sock = rcu_dereference_protected(vq->private_data, lockdep_is_held(&vq->mutex)); if (!sock) - return; + return 0; if (vq == n->vqs + VHOST_NET_VQ_TX) { n->tx_poll_state = VHOST_NET_POLL_STOPPED; - tx_poll_start(n, sock); + ret = tx_poll_start(n, sock); } else - vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file); + ret = vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file); + + return ret; } static struct socket *vhost_net_stop_vq(struct vhost_net *n, @@ -827,15 +834,18 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = PTR_ERR(ubufs); goto err_ubufs; } - oldubufs = vq->ubufs; - vq->ubufs = ubufs; + vhost_net_disable_vq(n, vq); rcu_assign_pointer(vq->private_data, sock); - vhost_net_enable_vq(n, vq); - r = vhost_init_used(vq); if (r) - goto err_vq; + goto err_used; + r = vhost_net_enable_vq(n, vq); + if (r) + goto err_used; + + oldubufs = vq->ubufs; + vq->ubufs = ubufs; n->tx_packets = 0; n->tx_zcopy_err = 0; @@ -859,6 +869,11 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) mutex_unlock(&n->dev.mutex); return 0; +err_used: + rcu_assign_pointer(vq->private_data, oldsock); + vhost_net_enable_vq(n, vq); + if (ubufs) + vhost_ubuf_put_and_wait(ubufs); err_ubufs: fput(sock->file); err_vq: diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c index b20df5c..22321cf 100644 --- a/drivers/vhost/tcm_vhost.c +++ b/drivers/vhost/tcm_vhost.c @@ -575,10 +575,8 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs) /* Must use ioctl VHOST_SCSI_SET_ENDPOINT */ tv_tpg = vs->vs_tpg; - if (unlikely(!tv_tpg)) { - pr_err("%s endpoint not set\n", __func__); + if (unlikely(!tv_tpg)) return; - } mutex_lock(&vq->mutex); vhost_disable_notify(&vs->dev, vq); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 34389f7..9759249 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -77,26 +77,38 @@ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, init_poll_funcptr(&poll->table, vhost_poll_func); poll->mask = mask; poll->dev = dev; + poll->wqh = NULL; vhost_work_init(&poll->work, fn); } /* Start polling a file. We add ourselves to file's wait queue. The caller must * keep a reference to a file until after vhost_poll_stop is called. */ -void vhost_poll_start(struct vhost_poll *poll, struct file *file) +int vhost_poll_start(struct vhost_poll *poll, struct file *file) { unsigned long mask; + int ret = 0; mask = file->f_op->poll(file, &poll->table); if (mask) vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask); + if (mask & POLLERR) { + if (poll->wqh) + remove_wait_queue(poll->wqh, &poll->wait); + ret = -EINVAL; + } + + return ret; } /* Stop polling a file. After this function returns, it becomes safe to drop the * file reference. You must also flush afterwards. */ void vhost_poll_stop(struct vhost_poll *poll) { - remove_wait_queue(poll->wqh, &poll->wait); + if (poll->wqh) { + remove_wait_queue(poll->wqh, &poll->wait); + poll->wqh = NULL; + } } static bool vhost_work_seq_done(struct vhost_dev *dev, struct vhost_work *work, @@ -792,7 +804,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) fput(filep); if (pollstart && vq->handle_kick) - vhost_poll_start(&vq->poll, vq->kick); + r = vhost_poll_start(&vq->poll, vq->kick); mutex_unlock(&vq->mutex); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 2639c58..17261e2 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -42,7 +42,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work); void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, unsigned long mask, struct vhost_dev *dev); -void vhost_poll_start(struct vhost_poll *poll, struct file *file); +int vhost_poll_start(struct vhost_poll *poll, struct file *file); void vhost_poll_stop(struct vhost_poll *poll); void vhost_poll_flush(struct vhost_poll *poll); void vhost_poll_queue(struct vhost_poll *poll); diff --git a/drivers/video/exynos/exynos_dp_core.c b/drivers/video/exynos/exynos_dp_core.c index 4ef18e2..2d0d144 100644 --- a/drivers/video/exynos/exynos_dp_core.c +++ b/drivers/video/exynos/exynos_dp_core.c @@ -1121,8 +1121,7 @@ static int exynos_dp_remove(struct platform_device *pdev) disable_irq(dp->irq); - if (work_pending(&dp->hotplug_work)) - flush_work(&dp->hotplug_work); + flush_work(&dp->hotplug_work); if (pdev->dev.of_node) { if (dp->phy_addr) @@ -1144,8 +1143,7 @@ static int exynos_dp_suspend(struct device *dev) struct exynos_dp_platdata *pdata = dev->platform_data; struct exynos_dp_device *dp = dev_get_drvdata(dev); - if (work_pending(&dp->hotplug_work)) - flush_work(&dp->hotplug_work); + flush_work(&dp->hotplug_work); if (dev->of_node) { if (dp->phy_addr) diff --git a/drivers/video/omap2/dss/dss_features.c b/drivers/video/omap2/dss/dss_features.c index 18688c1..d7d66ef 100644 --- a/drivers/video/omap2/dss/dss_features.c +++ b/drivers/video/omap2/dss/dss_features.c @@ -538,6 +538,7 @@ static const enum dss_feat_id omap3630_dss_feat_list[] = { FEAT_ALPHA_FIXED_ZORDER, FEAT_FIFO_MERGE, FEAT_OMAP3_DSI_FIFO_BUG, + FEAT_DPI_USES_VDDS_DSI, }; static const enum dss_feat_id omap4430_es1_0_dss_feat_list[] = { diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 0be4df3..22f77c5 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -840,7 +840,7 @@ int bind_evtchn_to_irq(unsigned int evtchn) if (irq == -1) { irq = xen_allocate_irq_dynamic(); - if (irq == -1) + if (irq < 0) goto out; irq_set_chip_and_handler_name(irq, &xen_dynamic_chip, @@ -944,7 +944,7 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu) if (irq == -1) { irq = xen_allocate_irq_dynamic(); - if (irq == -1) + if (irq < 0) goto out; irq_set_chip_and_handler_name(irq, &xen_percpu_chip, @@ -1787,7 +1787,7 @@ void xen_callback_vector(void) int rc; uint64_t callback_via; if (xen_have_vector_callback) { - callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK); + callback_via = HVM_CALLBACK_VECTOR(HYPERVISOR_CALLBACK_VECTOR); rc = xen_set_callback_via(callback_via); if (rc) { printk(KERN_ERR "Request for Xen HVM callback vector" @@ -1798,8 +1798,9 @@ void xen_callback_vector(void) printk(KERN_INFO "Xen HVM callback vector for event delivery is " "enabled\n"); /* in the restore case the vector has already been allocated */ - if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors)) - alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector); + if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, + xen_hvm_callback_vector); } } #else diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 067fcfa..5a27a45 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -278,8 +278,7 @@ static int sync_pcpu(uint32_t cpu, uint32_t *max_cpu) * Only those at cpu present map has its sys interface. */ if (info->flags & XEN_PCPU_FLAGS_INVALID) { - if (pcpu) - unregister_and_remove_pcpu(pcpu); + unregister_and_remove_pcpu(pcpu); return 0; } diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 97f5d26..37c1f82 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -135,7 +135,6 @@ int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev, struct pci_dev *dev, struct xen_pci_op *op) { struct xen_pcibk_dev_data *dev_data; - int otherend = pdev->xdev->otherend_id; int status; if (unlikely(verbose_request)) @@ -144,8 +143,9 @@ int xen_pcibk_enable_msi(struct xen_pcibk_device *pdev, status = pci_enable_msi(dev); if (status) { - printk(KERN_ERR "error enable msi for guest %x status %x\n", - otherend, status); + pr_warn_ratelimited(DRV_NAME ": %s: error enabling MSI for guest %u: err %d\n", + pci_name(dev), pdev->xdev->otherend_id, + status); op->value = 0; return XEN_PCI_ERR_op_failed; } @@ -223,10 +223,10 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, pci_name(dev), i, op->msix_entries[i].vector); } - } else { - printk(KERN_WARNING DRV_NAME ": %s: failed to enable MSI-X: err %d!\n", - pci_name(dev), result); - } + } else + pr_warn_ratelimited(DRV_NAME ": %s: error enabling MSI-X for guest %u: err %d!\n", + pci_name(dev), pdev->xdev->otherend_id, + result); kfree(entries); op->value = result; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0c42cdb..49d0b43 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -33,6 +33,7 @@ #include <linux/elf.h> #include <linux/utsname.h> #include <linux/coredump.h> +#include <linux/sched.h> #include <asm/uaccess.h> #include <asm/param.h> #include <asm/page.h> @@ -1320,8 +1321,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus, cputime_to_timeval(cputime.utime, &prstatus->pr_utime); cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { - cputime_to_timeval(p->utime, &prstatus->pr_utime); - cputime_to_timeval(p->stime, &prstatus->pr_stime); + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + cputime_to_timeval(utime, &prstatus->pr_utime); + cputime_to_timeval(stime, &prstatus->pr_stime); } cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index dc84732..cb240dd 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1375,8 +1375,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus, cputime_to_timeval(cputime.utime, &prstatus->pr_utime); cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { - cputime_to_timeval(p->utime, &prstatus->pr_utime); - cputime_to_timeval(p->stime, &prstatus->pr_stime); + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + cputime_to_timeval(utime, &prstatus->pr_utime); + cputime_to_timeval(stime, &prstatus->pr_stime); } cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a8b8adc..5a3327b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4534,7 +4534,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) unsigned nr_extents = 0; int extra_reserve = 0; enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL; - int ret; + int ret = 0; bool delalloc_lock = true; /* If we are a free space inode we need to not flush since we will be in @@ -4579,20 +4579,18 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) csum_bytes = BTRFS_I(inode)->csum_bytes; spin_unlock(&BTRFS_I(inode)->lock); - if (root->fs_info->quota_enabled) { + if (root->fs_info->quota_enabled) ret = btrfs_qgroup_reserve(root, num_bytes + nr_extents * root->leafsize); - if (ret) { - spin_lock(&BTRFS_I(inode)->lock); - calc_csum_metadata_size(inode, num_bytes, 0); - spin_unlock(&BTRFS_I(inode)->lock); - if (delalloc_lock) - mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); - return ret; - } - } - ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush); + /* + * ret != 0 here means the qgroup reservation failed, we go straight to + * the shared error handling then. + */ + if (ret == 0) + ret = reserve_metadata_bytes(root, block_rsv, + to_reserve, flush); + if (ret) { u64 to_free = 0; unsigned dropped; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 2e8cae6..fdb7a8d 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -288,7 +288,8 @@ out: void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em) { clear_bit(EXTENT_FLAG_LOGGING, &em->flags); - try_merge_map(tree, em); + if (em->in_tree) + try_merge_map(tree, em); } /** diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f76b1fd..aeb8446 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -293,15 +293,24 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, struct btrfs_key key; struct btrfs_ioctl_defrag_range_args range; int num_defrag; + int index; + int ret; /* get the inode */ key.objectid = defrag->root; btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY); key.offset = (u64)-1; + + index = srcu_read_lock(&fs_info->subvol_srcu); + inode_root = btrfs_read_fs_root_no_name(fs_info, &key); if (IS_ERR(inode_root)) { - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - return PTR_ERR(inode_root); + ret = PTR_ERR(inode_root); + goto cleanup; + } + if (btrfs_root_refs(&inode_root->root_item) == 0) { + ret = -ENOENT; + goto cleanup; } key.objectid = defrag->ino; @@ -309,9 +318,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, key.offset = 0; inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL); if (IS_ERR(inode)) { - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - return PTR_ERR(inode); + ret = PTR_ERR(inode); + goto cleanup; } + srcu_read_unlock(&fs_info->subvol_srcu, index); /* do a chunk of defrag */ clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); @@ -346,6 +356,10 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, iput(inode); return 0; +cleanup: + srcu_read_unlock(&fs_info->subvol_srcu, index); + kmem_cache_free(btrfs_inode_defrag_cachep, defrag); + return ret; } /* @@ -1594,9 +1608,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, if (err < 0 && num_written > 0) num_written = err; } -out: + if (sync) atomic_dec(&BTRFS_I(inode)->sync_writers); +out: sb_end_write(inode->i_sb); current->backing_dev_info = NULL; return num_written ? num_written : err; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5b22d45..338f259 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -515,7 +515,6 @@ static noinline int create_subvol(struct btrfs_root *root, BUG_ON(ret); - d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry)); fail: if (async_transid) { *async_transid = trans->transid; @@ -525,6 +524,10 @@ fail: } if (err && !ret) ret = err; + + if (!ret) + d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry)); + return ret; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index f107312..e5ed567 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -836,9 +836,16 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, * if the disk i_size is already at the inode->i_size, or * this ordered extent is inside the disk i_size, we're done */ - if (disk_i_size == i_size || offset <= disk_i_size) { + if (disk_i_size == i_size) + goto out; + + /* + * We still need to update disk_i_size if outstanding_isize is greater + * than disk_i_size. + */ + if (offset <= disk_i_size && + (!ordered || ordered->outstanding_isize <= disk_i_size)) goto out; - } /* * walk backward from this ordered extent to disk_i_size. @@ -870,7 +877,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, break; if (test->file_offset >= i_size) break; - if (test->file_offset >= disk_i_size) { + if (entry_end(test) > disk_i_size) { /* * we don't update disk_i_size now, so record this * undealt i_size. Or we will not know the real diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index bdbb94f..67783e0 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -580,20 +580,29 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) int corrected = 0; struct btrfs_key key; struct inode *inode = NULL; + struct btrfs_fs_info *fs_info; u64 end = offset + PAGE_SIZE - 1; struct btrfs_root *local_root; + int srcu_index; key.objectid = root; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; - local_root = btrfs_read_fs_root_no_name(fixup->root->fs_info, &key); - if (IS_ERR(local_root)) + + fs_info = fixup->root->fs_info; + srcu_index = srcu_read_lock(&fs_info->subvol_srcu); + + local_root = btrfs_read_fs_root_no_name(fs_info, &key); + if (IS_ERR(local_root)) { + srcu_read_unlock(&fs_info->subvol_srcu, srcu_index); return PTR_ERR(local_root); + } key.type = BTRFS_INODE_ITEM_KEY; key.objectid = inum; key.offset = 0; - inode = btrfs_iget(fixup->root->fs_info->sb, &key, local_root, NULL); + inode = btrfs_iget(fs_info->sb, &key, local_root, NULL); + srcu_read_unlock(&fs_info->subvol_srcu, srcu_index); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -606,7 +615,6 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) } if (PageUptodate(page)) { - struct btrfs_fs_info *fs_info; if (PageDirty(page)) { /* * we need to write the data to the defect sector. the @@ -3180,18 +3188,25 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) u64 physical_for_dev_replace; u64 len; struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info; + int srcu_index; key.objectid = root; key.type = BTRFS_ROOT_ITEM_KEY; key.offset = (u64)-1; + + srcu_index = srcu_read_lock(&fs_info->subvol_srcu); + local_root = btrfs_read_fs_root_no_name(fs_info, &key); - if (IS_ERR(local_root)) + if (IS_ERR(local_root)) { + srcu_read_unlock(&fs_info->subvol_srcu, srcu_index); return PTR_ERR(local_root); + } key.type = BTRFS_INODE_ITEM_KEY; key.objectid = inum; key.offset = 0; inode = btrfs_iget(fs_info->sb, &key, local_root, NULL); + srcu_read_unlock(&fs_info->subvol_srcu, srcu_index); if (IS_ERR(inode)) return PTR_ERR(inode); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index f154946..fc03aa6 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -333,12 +333,14 @@ start_transaction(struct btrfs_root *root, u64 num_items, int type, &root->fs_info->trans_block_rsv, num_bytes, flush); if (ret) - return ERR_PTR(ret); + goto reserve_fail; } again: h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS); - if (!h) - return ERR_PTR(-ENOMEM); + if (!h) { + ret = -ENOMEM; + goto alloc_fail; + } /* * If we are JOIN_NOLOCK we're already committing a transaction and @@ -365,11 +367,7 @@ again: if (ret < 0) { /* We must get the transaction if we are JOIN_NOLOCK. */ BUG_ON(type == TRANS_JOIN_NOLOCK); - - if (type < TRANS_JOIN_NOLOCK) - sb_end_intwrite(root->fs_info->sb); - kmem_cache_free(btrfs_trans_handle_cachep, h); - return ERR_PTR(ret); + goto join_fail; } cur_trans = root->fs_info->running_transaction; @@ -410,6 +408,19 @@ got_it: if (!current->journal_info && type != TRANS_USERSPACE) current->journal_info = h; return h; + +join_fail: + if (type < TRANS_JOIN_NOLOCK) + sb_end_intwrite(root->fs_info->sb); + kmem_cache_free(btrfs_trans_handle_cachep, h); +alloc_fail: + if (num_bytes) + btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv, + num_bytes); +reserve_fail: + if (qgroup_reserved) + btrfs_qgroup_free(root, qgroup_reserved); + return ERR_PTR(ret); } struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 15f6efd..5cbb7f4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1556,7 +1556,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) ret = 0; /* Notify udev that device has changed */ - btrfs_kobject_uevent(bdev, KOBJ_CHANGE); + if (bdev) + btrfs_kobject_uevent(bdev, KOBJ_CHANGE); error_brelse: brelse(bh); diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 7ff4985..911649a 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -503,11 +503,11 @@ static ssize_t device_write(struct file *file, const char __user *buf, #endif return -EINVAL; -#ifdef CONFIG_COMPAT - if (count > sizeof(struct dlm_write_request32) + DLM_RESNAME_MAXLEN) -#else + /* + * can't compare against COMPAT/dlm_write_request32 because + * we don't yet know if is64bit is zero + */ if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN) -#endif return -EINVAL; kbuf = kzalloc(count + 1, GFP_NOFS); diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index b906ed1..9802de0 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -281,6 +281,7 @@ static void gdlm_put_lock(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_sbd; struct lm_lockstruct *ls = &sdp->sd_lockstruct; + int lvb_needs_unlock = 0; int error; if (gl->gl_lksb.sb_lkid == 0) { @@ -294,8 +295,12 @@ static void gdlm_put_lock(struct gfs2_glock *gl) gfs2_update_request_times(gl); /* don't want to skip dlm_unlock writing the lvb when lock is ex */ + + if (gl->gl_lksb.sb_lvbptr && (gl->gl_state == LM_ST_EXCLUSIVE)) + lvb_needs_unlock = 1; + if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) && - gl->gl_lksb.sb_lvbptr && (gl->gl_state != LM_ST_EXCLUSIVE)) { + !lvb_needs_unlock) { gfs2_glock_free(gl); return; } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index dd057bc..fc8dc20 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -177,11 +177,31 @@ out_nofree: return mnt; } +static int +nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + if (NFS_FH(dentry->d_inode)->size != 0) + return nfs_getattr(mnt, dentry, stat); + generic_fillattr(dentry->d_inode, stat); + return 0; +} + +static int +nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr) +{ + if (NFS_FH(dentry->d_inode)->size != 0) + return nfs_setattr(dentry, attr); + return -EACCES; +} + const struct inode_operations nfs_mountpoint_inode_operations = { .getattr = nfs_getattr, + .setattr = nfs_setattr, }; const struct inode_operations nfs_referral_inode_operations = { + .getattr = nfs_namespace_getattr, + .setattr = nfs_namespace_setattr, }; static void nfs_expire_automounts(struct work_struct *work) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index acc3472..2e9779b 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -236,11 +236,10 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, error = nfs4_discover_server_trunking(clp, &old); if (error < 0) goto error; + nfs_put_client(clp); if (clp != old) { clp->cl_preserve_clid = true; - nfs_put_client(clp); clp = old; - atomic_inc(&clp->cl_count); } return clp; @@ -306,7 +305,7 @@ int nfs40_walk_client_list(struct nfs_client *new, .clientid = new->cl_clientid, .confirm = new->cl_confirm, }; - int status; + int status = -NFS4ERR_STALE_CLIENTID; spin_lock(&nn->nfs_client_lock); list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) { @@ -332,40 +331,33 @@ int nfs40_walk_client_list(struct nfs_client *new, if (prev) nfs_put_client(prev); + prev = pos; status = nfs4_proc_setclientid_confirm(pos, &clid, cred); - if (status == 0) { + switch (status) { + case -NFS4ERR_STALE_CLIENTID: + break; + case 0: nfs4_swap_callback_idents(pos, new); - nfs_put_client(pos); + prev = NULL; *result = pos; dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n", __func__, pos, atomic_read(&pos->cl_count)); - return 0; - } - if (status != -NFS4ERR_STALE_CLIENTID) { - nfs_put_client(pos); - dprintk("NFS: <-- %s status = %d, no result\n", - __func__, status); - return status; + default: + goto out; } spin_lock(&nn->nfs_client_lock); - prev = pos; } + spin_unlock(&nn->nfs_client_lock); - /* - * No matching nfs_client found. This should be impossible, - * because the new nfs_client has already been added to - * nfs_client_list by nfs_get_client(). - * - * Don't BUG(), since the caller is holding a mutex. - */ + /* No match found. The server lost our clientid */ +out: if (prev) nfs_put_client(prev); - spin_unlock(&nn->nfs_client_lock); - pr_err("NFS: %s Error: no matching nfs_client found\n", __func__); - return -NFS4ERR_STALE_CLIENTID; + dprintk("NFS: <-- %s status = %d\n", __func__, status); + return status; } #ifdef CONFIG_NFS_V4_1 @@ -432,7 +424,7 @@ int nfs41_walk_client_list(struct nfs_client *new, { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); struct nfs_client *pos, *n, *prev = NULL; - int error; + int status = -NFS4ERR_STALE_CLIENTID; spin_lock(&nn->nfs_client_lock); list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) { @@ -448,14 +440,17 @@ int nfs41_walk_client_list(struct nfs_client *new, nfs_put_client(prev); prev = pos; - error = nfs_wait_client_init_complete(pos); - if (error < 0) { + nfs4_schedule_lease_recovery(pos); + status = nfs_wait_client_init_complete(pos); + if (status < 0) { nfs_put_client(pos); spin_lock(&nn->nfs_client_lock); continue; } - + status = pos->cl_cons_state; spin_lock(&nn->nfs_client_lock); + if (status < 0) + continue; } if (pos->rpc_ops != new->rpc_ops) @@ -473,6 +468,7 @@ int nfs41_walk_client_list(struct nfs_client *new, if (!nfs4_match_serverowners(pos, new)) continue; + atomic_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n", __func__, pos, atomic_read(&pos->cl_count)); @@ -481,16 +477,10 @@ int nfs41_walk_client_list(struct nfs_client *new, return 0; } - /* - * No matching nfs_client found. This should be impossible, - * because the new nfs_client has already been added to - * nfs_client_list by nfs_get_client(). - * - * Don't BUG(), since the caller is holding a mutex. - */ + /* No matching nfs_client found. */ spin_unlock(&nn->nfs_client_lock); - pr_err("NFS: %s Error: no matching nfs_client found\n", __func__); - return -NFS4ERR_STALE_CLIENTID; + dprintk("NFS: <-- %s status = %d\n", __func__, status); + return status; } #endif /* CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 9448c57..e61f68d 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -136,16 +136,11 @@ int nfs40_discover_server_trunking(struct nfs_client *clp, clp->cl_confirm = clid.confirm; status = nfs40_walk_client_list(clp, result, cred); - switch (status) { - case -NFS4ERR_STALE_CLIENTID: - set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - case 0: + if (status == 0) { /* Sustain the lease, even if it's empty. If the clientid4 * goes stale it's of no use for trunking discovery. */ nfs4_schedule_state_renewal(*result); - break; } - out: return status; } @@ -1863,6 +1858,7 @@ again: case -ETIMEDOUT: case -EAGAIN: ssleep(1); + case -NFS4ERR_STALE_CLIENTID: dprintk("NFS: %s after status %d, retrying\n", __func__, status); goto again; @@ -2022,8 +2018,18 @@ static int nfs4_reset_session(struct nfs_client *clp) nfs4_begin_drain_session(clp); cred = nfs4_get_exchange_id_cred(clp); status = nfs4_proc_destroy_session(clp->cl_session, cred); - if (status && status != -NFS4ERR_BADSESSION && - status != -NFS4ERR_DEADSESSION) { + switch (status) { + case 0: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_DEADSESSION: + break; + case -NFS4ERR_BACK_CHAN_BUSY: + case -NFS4ERR_DELAY: + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + status = 0; + ssleep(1); + goto out; + default: status = nfs4_recovery_handle_error(clp, status); goto out; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2e7e8c8..b056b16 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2589,27 +2589,23 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags, struct nfs_server *server; struct dentry *mntroot = ERR_PTR(-ENOMEM); struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod; - int error; - dprintk("--> nfs_xdev_mount_common()\n"); + dprintk("--> nfs_xdev_mount()\n"); mount_info.mntfh = mount_info.cloned->fh; /* create a new volume representation */ server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); - if (IS_ERR(server)) { - error = PTR_ERR(server); - goto out_err; - } - mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod); - dprintk("<-- nfs_xdev_mount_common() = 0\n"); -out: - return mntroot; + if (IS_ERR(server)) + mntroot = ERR_CAST(server); + else + mntroot = nfs_fs_mount_common(server, flags, + dev_name, &mount_info, nfs_mod); -out_err: - dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error); - goto out; + dprintk("<-- nfs_xdev_mount() = %ld\n", + IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L); + return mntroot; } #if IS_ENABLED(CONFIG_NFS_V4) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index fdb1807..f385935 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -664,8 +664,11 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, if (ret < 0) printk(KERN_ERR "NILFS: GC failed during preparation: " "cannot read source blocks: err=%d\n", ret); - else + else { + if (nilfs_sb_need_update(nilfs)) + set_nilfs_discontinued(nilfs); ret = nilfs_clean_segments(inode->i_sb, argv, kbufs); + } nilfs_remove_all_gcinodes(nilfs); clear_nilfs_gc_running(nilfs); diff --git a/fs/proc/array.c b/fs/proc/array.c index 6a91e6f..f7ed9ee 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -449,7 +449,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, do { min_flt += t->min_flt; maj_flt += t->maj_flt; - gtime += t->gtime; + gtime += task_gtime(t); t = next_thread(t); } while (t != task); @@ -472,7 +472,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt = task->min_flt; maj_flt = task->maj_flt; task_cputime_adjusted(task, &utime, &stime); - gtime = task->gtime; + gtime = task_gtime(task); } /* scale priority and nice values from timeslices to -20..20 */ diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 7003e52..288f068 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -167,12 +167,16 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) { char *hdr; - struct timeval timestamp; + struct timespec timestamp; size_t len; - do_gettimeofday(×tamp); + /* Report zeroed timestamp if called before timekeeping has resumed. */ + if (__getnstimeofday(×tamp)) { + timestamp.tv_sec = 0; + timestamp.tv_nsec = 0; + } hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n", - (long)timestamp.tv_sec, (long)timestamp.tv_usec); + (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000)); WARN_ON_ONCE(!hdr); len = hdr ? strlen(hdr) : 0; persistent_ram_write(prz, hdr, len); diff --git a/fs/select.c b/fs/select.c index 2ef72d9..8c1c96c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -26,6 +26,7 @@ #include <linux/fs.h> #include <linux/rcupdate.h> #include <linux/hrtimer.h> +#include <linux/sched/rt.h> #include <asm/uaccess.h> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 4111a40..5f707e5 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -86,11 +86,11 @@ xfs_destroy_ioend( } if (ioend->io_iocb) { + inode_dio_done(ioend->io_inode); if (ioend->io_isasync) { aio_complete(ioend->io_iocb, ioend->io_error ? ioend->io_error : ioend->io_result, 0); } - inode_dio_done(ioend->io_inode); } mempool_free(ioend, xfs_ioend_pool); diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 0e92d12..cdb2d33 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -4680,9 +4680,6 @@ __xfs_bmapi_allocate( return error; } - if (bma->flags & XFS_BMAPI_STACK_SWITCH) - bma->stack_switch = 1; - error = xfs_bmap_alloc(bma); if (error) return error; @@ -4956,6 +4953,9 @@ xfs_bmapi_write( bma.flist = flist; bma.firstblock = firstblock; + if (flags & XFS_BMAPI_STACK_SWITCH) + bma.stack_switch = 1; + while (bno < end && n < *nmap) { inhole = eof || bma.got.br_startoff > bno; wasdelay = !inhole && isnullstartblock(bma.got.br_startblock); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 56d1614..fbbb9eb 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -487,6 +487,7 @@ _xfs_buf_find( struct rb_node *parent; xfs_buf_t *bp; xfs_daddr_t blkno = map[0].bm_bn; + xfs_daddr_t eofs; int numblks = 0; int i; @@ -498,6 +499,23 @@ _xfs_buf_find( ASSERT(!(numbytes < (1 << btp->bt_sshift))); ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask)); + /* + * Corrupted block numbers can get through to here, unfortunately, so we + * have to check that the buffer falls within the filesystem bounds. + */ + eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks); + if (blkno >= eofs) { + /* + * XXX (dgc): we should really be returning EFSCORRUPTED here, + * but none of the higher level infrastructure supports + * returning a specific error on buffer lookup failures. + */ + xfs_alert(btp->bt_mount, + "%s: Block out of range: block 0x%llx, EOFS 0x%llx ", + __func__, blkno, eofs); + return NULL; + } + /* get tree root */ pag = xfs_perag_get(btp->bt_mount, xfs_daddr_to_agno(btp->bt_mount, blkno)); @@ -1487,6 +1505,8 @@ restart: while (!list_empty(&btp->bt_lru)) { bp = list_first_entry(&btp->bt_lru, struct xfs_buf, b_lru); if (atomic_read(&bp->b_hold) > 1) { + trace_xfs_buf_wait_buftarg(bp, _RET_IP_); + list_move_tail(&bp->b_lru, &btp->bt_lru); spin_unlock(&btp->bt_lru_lock); delay(100); goto restart; diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 77b0975..3f9949f 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -652,7 +652,10 @@ xfs_buf_item_unlock( /* * If the buf item isn't tracking any data, free it, otherwise drop the - * reference we hold to it. + * reference we hold to it. If we are aborting the transaction, this may + * be the only reference to the buf item, so we free it anyway + * regardless of whether it is dirty or not. A dirty abort implies a + * shutdown, anyway. */ clean = 1; for (i = 0; i < bip->bli_format_count; i++) { @@ -664,7 +667,12 @@ xfs_buf_item_unlock( } if (clean) xfs_buf_item_relse(bp); - else + else if (aborted) { + if (atomic_dec_and_test(&bip->bli_refcount)) { + ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); + xfs_buf_item_relse(bp); + } + } else atomic_dec(&bip->bli_refcount); if (!hold) diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index d0e9c74..a8bd26b 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -246,10 +246,10 @@ xfs_swap_extents( goto out_unlock; } - error = -filemap_write_and_wait(VFS_I(ip)->i_mapping); + error = -filemap_write_and_wait(VFS_I(tip)->i_mapping); if (error) goto out_unlock; - truncate_pagecache_range(VFS_I(ip), 0, -1); + truncate_pagecache_range(VFS_I(tip), 0, -1); /* Verify O_DIRECT for ftmp */ if (VN_CACHED(VFS_I(tip)) != 0) { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index add06b4..364818e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -351,6 +351,15 @@ xfs_iomap_prealloc_size( } if (shift) alloc_blocks >>= shift; + + /* + * If we are still trying to allocate more space than is + * available, squash the prealloc hard. This can happen if we + * have a large file on a small filesystem and the above + * lowspace thresholds are smaller than MAXEXTLEN. + */ + while (alloc_blocks >= freesp) + alloc_blocks >>= 4; } if (alloc_blocks < mp->m_writeio_blocks) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index da50846..7d6df7c 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -658,7 +658,7 @@ xfs_sb_quiet_read_verify( return; } /* quietly fail */ - xfs_buf_ioerror(bp, EFSCORRUPTED); + xfs_buf_ioerror(bp, EWRONGFS); } static void diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 2e137d4..16a8129 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -341,6 +341,7 @@ DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_item_iodone); DEFINE_BUF_EVENT(xfs_buf_item_iodone_async); DEFINE_BUF_EVENT(xfs_buf_error_relse); +DEFINE_BUF_EVENT(xfs_buf_wait_buftarg); DEFINE_BUF_EVENT(xfs_trans_read_buf_io); DEFINE_BUF_EVENT(xfs_trans_read_buf_shut); diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h index 9a62937..5196943 100644 --- a/include/asm-generic/cputime.h +++ b/include/asm-generic/cputime.h @@ -4,66 +4,12 @@ #include <linux/time.h> #include <linux/jiffies.h> -typedef unsigned long __nocast cputime_t; - -#define cputime_one_jiffy jiffies_to_cputime(1) -#define cputime_to_jiffies(__ct) (__force unsigned long)(__ct) -#define cputime_to_scaled(__ct) (__ct) -#define jiffies_to_cputime(__hz) (__force cputime_t)(__hz) - -typedef u64 __nocast cputime64_t; - -#define cputime64_to_jiffies64(__ct) (__force u64)(__ct) -#define jiffies64_to_cputime64(__jif) (__force cputime64_t)(__jif) - -#define nsecs_to_cputime64(__ct) \ - jiffies64_to_cputime64(nsecs_to_jiffies64(__ct)) - - -/* - * Convert cputime to microseconds and back. - */ -#define cputime_to_usecs(__ct) \ - jiffies_to_usecs(cputime_to_jiffies(__ct)) -#define usecs_to_cputime(__usec) \ - jiffies_to_cputime(usecs_to_jiffies(__usec)) -#define usecs_to_cputime64(__usec) \ - jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000)) - -/* - * Convert cputime to seconds and back. - */ -#define cputime_to_secs(jif) (cputime_to_jiffies(jif) / HZ) -#define secs_to_cputime(sec) jiffies_to_cputime((sec) * HZ) - -/* - * Convert cputime to timespec and back. - */ -#define timespec_to_cputime(__val) \ - jiffies_to_cputime(timespec_to_jiffies(__val)) -#define cputime_to_timespec(__ct,__val) \ - jiffies_to_timespec(cputime_to_jiffies(__ct),__val) - -/* - * Convert cputime to timeval and back. - */ -#define timeval_to_cputime(__val) \ - jiffies_to_cputime(timeval_to_jiffies(__val)) -#define cputime_to_timeval(__ct,__val) \ - jiffies_to_timeval(cputime_to_jiffies(__ct),__val) - -/* - * Convert cputime to clock and back. - */ -#define cputime_to_clock_t(__ct) \ - jiffies_to_clock_t(cputime_to_jiffies(__ct)) -#define clock_t_to_cputime(__x) \ - jiffies_to_cputime(clock_t_to_jiffies(__x)) +#ifndef CONFIG_VIRT_CPU_ACCOUNTING +# include <asm-generic/cputime_jiffies.h> +#endif -/* - * Convert cputime64 to clock. - */ -#define cputime64_to_clock_t(__ct) \ - jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct)) +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +# include <asm-generic/cputime_nsecs.h> +#endif #endif diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h new file mode 100644 index 0000000..272ecba --- /dev/null +++ b/include/asm-generic/cputime_jiffies.h @@ -0,0 +1,72 @@ +#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H +#define _ASM_GENERIC_CPUTIME_JIFFIES_H + +typedef unsigned long __nocast cputime_t; + +#define cputime_one_jiffy jiffies_to_cputime(1) +#define cputime_to_jiffies(__ct) (__force unsigned long)(__ct) +#define cputime_to_scaled(__ct) (__ct) +#define jiffies_to_cputime(__hz) (__force cputime_t)(__hz) + +typedef u64 __nocast cputime64_t; + +#define cputime64_to_jiffies64(__ct) (__force u64)(__ct) +#define jiffies64_to_cputime64(__jif) (__force cputime64_t)(__jif) + + +/* + * Convert nanoseconds to cputime + */ +#define nsecs_to_cputime64(__nsec) \ + jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec)) +#define nsecs_to_cputime(__nsec) \ + jiffies_to_cputime(nsecs_to_jiffies(__nsec)) + + +/* + * Convert cputime to microseconds and back. + */ +#define cputime_to_usecs(__ct) \ + jiffies_to_usecs(cputime_to_jiffies(__ct)) +#define usecs_to_cputime(__usec) \ + jiffies_to_cputime(usecs_to_jiffies(__usec)) +#define usecs_to_cputime64(__usec) \ + jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000)) + +/* + * Convert cputime to seconds and back. + */ +#define cputime_to_secs(jif) (cputime_to_jiffies(jif) / HZ) +#define secs_to_cputime(sec) jiffies_to_cputime((sec) * HZ) + +/* + * Convert cputime to timespec and back. + */ +#define timespec_to_cputime(__val) \ + jiffies_to_cputime(timespec_to_jiffies(__val)) +#define cputime_to_timespec(__ct,__val) \ + jiffies_to_timespec(cputime_to_jiffies(__ct),__val) + +/* + * Convert cputime to timeval and back. + */ +#define timeval_to_cputime(__val) \ + jiffies_to_cputime(timeval_to_jiffies(__val)) +#define cputime_to_timeval(__ct,__val) \ + jiffies_to_timeval(cputime_to_jiffies(__ct),__val) + +/* + * Convert cputime to clock and back. + */ +#define cputime_to_clock_t(__ct) \ + jiffies_to_clock_t(cputime_to_jiffies(__ct)) +#define clock_t_to_cputime(__x) \ + jiffies_to_cputime(clock_t_to_jiffies(__x)) + +/* + * Convert cputime64 to clock. + */ +#define cputime64_to_clock_t(__ct) \ + jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct)) + +#endif diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h new file mode 100644 index 0000000..b6485ca --- /dev/null +++ b/include/asm-generic/cputime_nsecs.h @@ -0,0 +1,104 @@ +/* + * Definitions for measuring cputime in nsecs resolution. + * + * Based on <arch/ia64/include/asm/cputime.h> + * + * Copyright (C) 2007 FUJITSU LIMITED + * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#ifndef _ASM_GENERIC_CPUTIME_NSECS_H +#define _ASM_GENERIC_CPUTIME_NSECS_H + +typedef u64 __nocast cputime_t; +typedef u64 __nocast cputime64_t; + +#define cputime_one_jiffy jiffies_to_cputime(1) + +/* + * Convert cputime <-> jiffies (HZ) + */ +#define cputime_to_jiffies(__ct) \ + ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) +#define cputime_to_scaled(__ct) (__ct) +#define jiffies_to_cputime(__jif) \ + (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ)) +#define cputime64_to_jiffies64(__ct) \ + ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) +#define jiffies64_to_cputime64(__jif) \ + (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ)) + + +/* + * Convert cputime <-> nanoseconds + */ +#define nsecs_to_cputime(__nsecs) ((__force u64)(__nsecs)) + + +/* + * Convert cputime <-> microseconds + */ +#define cputime_to_usecs(__ct) \ + ((__force u64)(__ct) / NSEC_PER_USEC) +#define usecs_to_cputime(__usecs) \ + (__force cputime_t)((__usecs) * NSEC_PER_USEC) +#define usecs_to_cputime64(__usecs) \ + (__force cputime64_t)((__usecs) * NSEC_PER_USEC) + +/* + * Convert cputime <-> seconds + */ +#define cputime_to_secs(__ct) \ + ((__force u64)(__ct) / NSEC_PER_SEC) +#define secs_to_cputime(__secs) \ + (__force cputime_t)((__secs) * NSEC_PER_SEC) + +/* + * Convert cputime <-> timespec (nsec) + */ +static inline cputime_t timespec_to_cputime(const struct timespec *val) +{ + u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec; + return (__force cputime_t) ret; +} +static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) +{ + val->tv_sec = (__force u64) ct / NSEC_PER_SEC; + val->tv_nsec = (__force u64) ct % NSEC_PER_SEC; +} + +/* + * Convert cputime <-> timeval (msec) + */ +static inline cputime_t timeval_to_cputime(struct timeval *val) +{ + u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC; + return (__force cputime_t) ret; +} +static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) +{ + val->tv_sec = (__force u64) ct / NSEC_PER_SEC; + val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC; +} + +/* + * Convert cputime <-> clock (USER_HZ) + */ +#define cputime_to_clock_t(__ct) \ + ((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ)) +#define clock_t_to_cputime(__x) \ + (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ)) + +/* + * Convert cputime64 to clock. + */ +#define cputime64_to_clock_t(__ct) \ + cputime_to_clock_t((__force cputime_t)__ct) + +#endif diff --git a/include/linux/aer.h b/include/linux/aer.h index 544abdb..ec10e1b 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -49,8 +49,8 @@ static inline int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev) } #endif -extern void cper_print_aer(const char *prefix, int cper_severity, - struct aer_capability_regs *aer); +extern void cper_print_aer(const char *prefix, struct pci_dev *dev, + int cper_severity, struct aer_capability_regs *aer); extern int cper_severity_to_aer(int cper_severity); extern void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, int severity); diff --git a/include/linux/async.h b/include/linux/async.h index 7a24fe9..a2e3f18 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -19,8 +19,7 @@ typedef u64 async_cookie_t; typedef void (async_func_ptr) (void *data, async_cookie_t cookie); struct async_domain { struct list_head node; - struct list_head domain; - int count; + struct list_head pending; unsigned registered:1; }; @@ -29,8 +28,7 @@ struct async_domain { */ #define ASYNC_DOMAIN(_name) \ struct async_domain _name = { .node = LIST_HEAD_INIT(_name.node), \ - .domain = LIST_HEAD_INIT(_name.domain), \ - .count = 0, \ + .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 1 } /* @@ -39,8 +37,7 @@ struct async_domain { */ #define ASYNC_DOMAIN_EXCLUSIVE(_name) \ struct async_domain _name = { .node = LIST_HEAD_INIT(_name.node), \ - .domain = LIST_HEAD_INIT(_name.domain), \ - .count = 0, \ + .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 0 } extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data); @@ -52,4 +49,5 @@ extern void async_synchronize_full_domain(struct async_domain *domain); extern void async_synchronize_cookie(async_cookie_t cookie); extern void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain); +extern bool current_is_async(void); #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7d73905..900af59 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -203,6 +203,7 @@ struct cgroup { /* For RCU-protected deletion */ struct rcu_head rcu_head; + struct work_struct free_work; /* List of events which userspace want to receive */ struct list_head event_list; @@ -558,6 +559,7 @@ static inline struct cgroup* task_cgroup(struct task_struct *task, struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, struct cgroup *cgroup); +struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos); /** * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants @@ -706,7 +708,6 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_fork(struct task_struct *p) {} -static inline void cgroup_fork_callbacks(struct task_struct *p) {} static inline void cgroup_post_fork(struct task_struct *p) {} static inline void cgroup_exit(struct task_struct *p, int callbacks) {} diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 8a7096f..6634652 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -161,6 +161,15 @@ clockevents_calc_mult_shift(struct clock_event_device *ce, u32 freq, u32 minsec) extern void clockevents_suspend(void); extern void clockevents_resume(void); +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +#ifdef CONFIG_ARCH_HAS_TICK_BROADCAST +extern void tick_broadcast(const struct cpumask *mask); +#else +#define tick_broadcast NULL +#endif +extern int tick_receive_broadcast(void); +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void clockevents_notify(unsigned long reason, void *arg); #else diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index e24339c..b28d161 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -3,12 +3,40 @@ #ifdef CONFIG_CONTEXT_TRACKING #include <linux/sched.h> +#include <linux/percpu.h> + +struct context_tracking { + /* + * When active is false, probes are unset in order + * to minimize overhead: TIF flags are cleared + * and calls to user_enter/exit are ignored. This + * may be further optimized using static keys. + */ + bool active; + enum { + IN_KERNEL = 0, + IN_USER, + } state; +}; + +DECLARE_PER_CPU(struct context_tracking, context_tracking); + +static inline bool context_tracking_in_user(void) +{ + return __this_cpu_read(context_tracking.state) == IN_USER; +} + +static inline bool context_tracking_active(void) +{ + return __this_cpu_read(context_tracking.active); +} extern void user_enter(void); extern void user_exit(void); extern void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next); #else +static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } static inline void context_tracking_task_switch(struct task_struct *prev, diff --git a/include/linux/device.h b/include/linux/device.h index 43dcda9..001f663 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -21,6 +21,7 @@ #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> +#include <linux/pinctrl/devinfo.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/ratelimit.h> @@ -620,6 +621,8 @@ struct acpi_dev_node { * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. + * @pins: For device pin management. + * See Documentation/pinctrl.txt for details. * @numa_node: NUMA node this device is close to. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all @@ -672,6 +675,10 @@ struct device { struct dev_pm_info power; struct dev_pm_domain *pm_domain; +#ifdef CONFIG_PINCTRL + struct dev_pin_info *pins; +#endif + #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index 8b84916..7a9498a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -618,18 +618,30 @@ extern int __init efi_setup_pcdp_console(char *); #endif /* - * We play games with efi_enabled so that the compiler will, if possible, remove - * EFI-related code altogether. + * We play games with efi_enabled so that the compiler will, if + * possible, remove EFI-related code altogether. */ +#define EFI_BOOT 0 /* Were we booted from EFI? */ +#define EFI_SYSTEM_TABLES 1 /* Can we use EFI system tables? */ +#define EFI_CONFIG_TABLES 2 /* Can we use EFI config tables? */ +#define EFI_RUNTIME_SERVICES 3 /* Can we use runtime services? */ +#define EFI_MEMMAP 4 /* Can we use EFI memory map? */ +#define EFI_64BIT 5 /* Is the firmware 64-bit? */ + #ifdef CONFIG_EFI # ifdef CONFIG_X86 - extern int efi_enabled; - extern bool efi_64bit; +extern int efi_enabled(int facility); # else -# define efi_enabled 1 +static inline int efi_enabled(int facility) +{ + return 1; +} # endif #else -# define efi_enabled 0 +static inline int efi_enabled(int facility) +{ + return 0; +} #endif /* diff --git a/include/linux/elevator.h b/include/linux/elevator.h index c03af76..1866206 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -138,6 +138,7 @@ extern void elv_drain_elevator(struct request_queue *); /* * io scheduler registration */ +extern void __init load_default_elevator_module(void); extern int elv_register(struct elevator_type *); extern void elv_unregister(struct elevator_type *); @@ -206,5 +207,9 @@ enum { INIT_LIST_HEAD(&(rq)->csd.list); \ } while (0) +#else /* CONFIG_BLOCK */ + +static inline void load_default_elevator_module(void) { } + #endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 92691d8..e5ca8ef 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -74,7 +74,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * SAVE_REGS - The ftrace_ops wants regs saved at each function called * and passed to the callback. If this flag is set, but the * architecture does not support passing regs - * (ARCH_SUPPORTS_FTRACE_SAVE_REGS is not defined), then the + * (CONFIG_DYNAMIC_FTRACE_WITH_REGS is not defined), then the * ftrace_ops will fail to register, unless the next flag * is set. * SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the @@ -418,7 +418,7 @@ void ftrace_modify_all_code(int command); #endif #ifndef FTRACE_REGS_ADDR -#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS # define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller) #else # define FTRACE_REGS_ADDR FTRACE_ADDR @@ -480,7 +480,7 @@ extern int ftrace_make_nop(struct module *mod, */ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); -#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS /** * ftrace_modify_call - convert from one addr to another (no nop) * @rec: the mcount call site record diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index a3d4895..13a54d0 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -49,7 +49,6 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; - int padding; }; #define FTRACE_MAX_EVENT \ @@ -84,6 +83,9 @@ struct trace_iterator { long idx; cpumask_var_t started; + + /* it's true when current open file is snapshot */ + bool snapshot; }; enum trace_iter_flags { @@ -272,7 +274,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type, extern int trace_add_event_call(struct ftrace_event_call *call); extern void trace_remove_event_call(struct ftrace_event_call *call); -#define is_signed_type(type) (((type)(-1)) < 0) +#define is_signed_type(type) (((type)(-1)) < (type)0) int trace_set_clr_event(const char *system, const char *event, int set); diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 624ef3f..29eb805 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -153,7 +153,7 @@ extern void rcu_nmi_exit(void); */ #define __irq_enter() \ do { \ - vtime_account_irq_enter(current); \ + account_irq_enter_time(current); \ add_preempt_count(HARDIRQ_OFFSET); \ trace_hardirq_enter(); \ } while (0) @@ -169,7 +169,7 @@ extern void irq_enter(void); #define __irq_exit() \ do { \ trace_hardirq_exit(); \ - vtime_account_irq_exit(current); \ + account_irq_exit_time(current); \ sub_preempt_count(HARDIRQ_OFFSET); \ } while (0) @@ -180,10 +180,10 @@ extern void irq_exit(void); #define nmi_enter() \ do { \ + lockdep_off(); \ ftrace_nmi_enter(); \ BUG_ON(in_nmi()); \ add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET); \ - lockdep_off(); \ rcu_nmi_enter(); \ trace_hardirq_enter(); \ } while (0) @@ -192,10 +192,10 @@ extern void irq_exit(void); do { \ trace_hardirq_exit(); \ rcu_nmi_exit(); \ - lockdep_on(); \ BUG_ON(!in_nmi()); \ sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET); \ ftrace_nmi_exit(); \ + lockdep_on(); \ } while (0) #endif /* LINUX_HARDIRQ_H */ diff --git a/include/linux/init.h b/include/linux/init.h index 10ed4f4..8618147 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -153,6 +153,7 @@ extern unsigned int reset_devices; /* used by init/main.c */ void setup_arch(char **); void prepare_namespace(void); +void __init load_default_modules(void); extern void (*late_time_init)(void); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 6d087c5..5cd0f09 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -10,7 +10,9 @@ #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/securebits.h> +#include <linux/seqlock.h> #include <net/net_namespace.h> +#include <linux/sched/rt.h> #ifdef CONFIG_SMP # define INIT_PUSHABLE_TASKS(tsk) \ @@ -141,6 +143,15 @@ extern struct task_group root_task_group; # define INIT_PERF_EVENTS(tsk) #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +# define INIT_VTIME(tsk) \ + .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ + .vtime_snap = 0, \ + .vtime_snap_whence = VTIME_SYS, +#else +# define INIT_VTIME(tsk) +#endif + #define INIT_TASK_COMM "swapper" /* @@ -210,6 +221,7 @@ extern struct task_group root_task_group; INIT_TRACE_RECURSION \ INIT_TASK_RCU_PREEMPT(tsk) \ INIT_CPUSET_SEQ \ + INIT_VTIME(tsk) \ } diff --git a/include/linux/irq.h b/include/linux/irq.h index fdf2c4a..bc4e066 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -509,8 +509,11 @@ static inline void irq_set_percpu_devid_flags(unsigned int irq) /* Handle dynamic irq creation and destruction */ extern unsigned int create_irq_nr(unsigned int irq_want, int node); +extern unsigned int __create_irqs(unsigned int from, unsigned int count, + int node); extern int create_irq(void); extern void destroy_irq(unsigned int irq); +extern void destroy_irqs(unsigned int irq, unsigned int count); /* * Dynamic irq helper functions. Obsolete. Use irq_alloc_desc* and @@ -528,6 +531,8 @@ extern int irq_set_handler_data(unsigned int irq, void *data); extern int irq_set_chip_data(unsigned int irq, void *data); extern int irq_set_irq_type(unsigned int irq, unsigned int type); extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry); +extern int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, + struct msi_desc *entry); extern struct irq_data *irq_get_irq_data(unsigned int irq); static inline struct irq_chip *irq_get_chip(unsigned int irq) @@ -590,6 +595,9 @@ int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, #define irq_alloc_desc_from(from, node) \ irq_alloc_descs(-1, from, 1, node) +#define irq_alloc_descs_from(from, cnt, node) \ + irq_alloc_descs(-1, from, cnt, node) + void irq_free_descs(unsigned int irq, unsigned int cnt); int irq_reserve_irqs(unsigned int from, unsigned int cnt); diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 6a9e8f5..f5dbce5 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -3,6 +3,20 @@ #include <linux/llist.h> +/* + * An entry can be in one of four states: + * + * free NULL, 0 -> {claimed} : free to be used + * claimed NULL, 3 -> {pending} : claimed to be enqueued + * pending next, 3 -> {busy} : queued, pending callback + * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed + */ + +#define IRQ_WORK_PENDING 1UL +#define IRQ_WORK_BUSY 2UL +#define IRQ_WORK_FLAGS 3UL +#define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */ + struct irq_work { unsigned long flags; struct llist_node llnode; @@ -16,8 +30,14 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) work->func = func; } -bool irq_work_queue(struct irq_work *work); +void irq_work_queue(struct irq_work *work); void irq_work_run(void); void irq_work_sync(struct irq_work *work); +#ifdef CONFIG_IRQ_WORK +bool irq_work_needs_cpu(void); +#else +static bool irq_work_needs_cpu(void) { return false; } +#endif + #endif /* _LINUX_IRQ_WORK_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 66b7078..ed5f6ed 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -127,7 +127,7 @@ extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t) extern void account_steal_time(cputime_t); extern void account_idle_time(cputime_t); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE static inline void account_process_tick(struct task_struct *tsk, int user) { vtime_account_user(tsk); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 23755ba..4b6ef4d 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -49,16 +49,6 @@ #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 -/* - * If function tracer is enabled and the arch supports full - * passing of pt_regs to function tracing, then kprobes can - * optimize on top of function tracing. - */ -#if defined(CONFIG_FUNCTION_TRACER) && defined(ARCH_SUPPORTS_FTRACE_SAVE_REGS) \ - && defined(ARCH_SUPPORTS_KPROBES_ON_FTRACE) -# define KPROBES_CAN_USE_FTRACE -#endif - /* Attach to insert probes on any functions which should be ignored*/ #define __kprobes __attribute__((__section__(".kprobes.text"))) @@ -316,7 +306,7 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table, #endif #endif /* CONFIG_OPTPROBES */ -#ifdef KPROBES_CAN_USE_FTRACE +#ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2c497ab..b7996a7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -22,6 +22,7 @@ #include <linux/rcupdate.h> #include <linux/ratelimit.h> #include <linux/err.h> +#include <linux/irqflags.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -740,15 +741,52 @@ static inline int kvm_deassign_device(struct kvm *kvm, } #endif /* CONFIG_IOMMU_API */ -static inline void kvm_guest_enter(void) +static inline void __guest_enter(void) { - BUG_ON(preemptible()); /* * This is running in ioctl context so we can avoid * the call to vtime_account() with its unnecessary idle check. */ - vtime_account_system_irqsafe(current); + vtime_account_system(current); current->flags |= PF_VCPU; +} + +static inline void __guest_exit(void) +{ + /* + * This is running in ioctl context so we can avoid + * the call to vtime_account() with its unnecessary idle check. + */ + vtime_account_system(current); + current->flags &= ~PF_VCPU; +} + +#ifdef CONFIG_CONTEXT_TRACKING +extern void guest_enter(void); +extern void guest_exit(void); + +#else /* !CONFIG_CONTEXT_TRACKING */ +static inline void guest_enter(void) +{ + __guest_enter(); +} + +static inline void guest_exit(void) +{ + __guest_exit(); +} +#endif /* !CONFIG_CONTEXT_TRACKING */ + +static inline void kvm_guest_enter(void) +{ + unsigned long flags; + + BUG_ON(preemptible()); + + local_irq_save(flags); + guest_enter(); + local_irq_restore(flags); + /* KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode * is very similar to exiting to userspase from rcu point of view. In @@ -761,12 +799,11 @@ static inline void kvm_guest_enter(void) static inline void kvm_guest_exit(void) { - /* - * This is running in ioctl context so we can avoid - * the call to vtime_account() with its unnecessary idle check. - */ - vtime_account_system_irqsafe(current); - current->flags &= ~PF_VCPU; + unsigned long flags; + + local_irq_save(flags); + guest_exit(); + local_irq_restore(flags); } /* diff --git a/include/linux/llist.h b/include/linux/llist.h index a5199f6..d0ab98f 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -125,6 +125,31 @@ static inline void init_llist_head(struct llist_head *list) (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** + * llist_for_each_entry_safe - iterate safely against remove over some entries + * of lock-less list of given type. + * @pos: the type * to use as a loop cursor. + * @n: another type * to use as a temporary storage. + * @node: the fist entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. This variant allows removal of entries + * as we iterate. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry_safe(pos, n, node, member) \ + for ((pos) = llist_entry((node), typeof(*(pos)), member), \ + (n) = (pos)->member.next; \ + &(pos)->member != NULL; \ + (pos) = llist_entry(n, typeof(*(pos)), member), \ + (n) = (&(pos)->member != NULL) ? (pos)->member.next : NULL) + +/** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0108a56..28bd5fa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -429,7 +429,7 @@ extern int memcg_limited_groups_array_size; * the slab_mutex must be held when looping through those caches */ #define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++) + for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++) static inline bool memcg_kmem_enabled(void) { diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 2138bd3..e53dcfe 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -272,8 +272,6 @@ struct abx500_bm_data { const struct abx500_fg_parameters *fg_params; }; -extern struct abx500_bm_data ab8500_bm_data; - enum { NTC_EXTERNAL = 0, NTC_INTERNAL, diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index 44310c9..9bd037d 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -422,7 +422,10 @@ struct ab8500_chargalg_platform_data { struct ab8500_btemp; struct ab8500_gpadc; struct ab8500_fg; + #ifdef CONFIG_AB8500_BM +extern struct abx500_bm_data ab8500_bm_data; + void ab8500_fg_reinit(void); void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA); struct ab8500_btemp *ab8500_btemp_get(void); @@ -434,31 +437,7 @@ int ab8500_fg_inst_curr_finalize(struct ab8500_fg *di, int *res); int ab8500_fg_inst_curr_done(struct ab8500_fg *di); #else -int ab8500_fg_inst_curr_done(struct ab8500_fg *di) -{ -} -static void ab8500_fg_reinit(void) -{ -} -static void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA) -{ -} -static struct ab8500_btemp *ab8500_btemp_get(void) -{ - return NULL; -} -static int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp) -{ - return 0; -} -struct ab8500_fg *ab8500_fg_get(void) -{ - return NULL; -} -static int ab8500_fg_inst_curr_blocking(struct ab8500_fg *dev) -{ - return -ENODEV; -} +static struct abx500_bm_data ab8500_bm_data; static inline int ab8500_fg_inst_curr_start(struct ab8500_fg *di) { diff --git a/include/linux/mfd/abx500/ab8500-gpio.h b/include/linux/mfd/abx500/ab8500-gpio.h index 2387c20..172b2f2 100644 --- a/include/linux/mfd/abx500/ab8500-gpio.h +++ b/include/linux/mfd/abx500/ab8500-gpio.h @@ -14,10 +14,20 @@ * registers. */ -struct ab8500_gpio_platform_data { +struct abx500_gpio_platform_data { int gpio_base; - u32 irq_base; - u8 config_reg[8]; +}; + +enum abx500_gpio_pull_updown { + ABX500_GPIO_PULL_DOWN = 0x0, + ABX500_GPIO_PULL_NONE = 0x1, + ABX500_GPIO_PULL_UP = 0x3, +}; + +enum abx500_gpio_vinsel { + ABX500_GPIO_VINSEL_VBAT = 0x0, + ABX500_GPIO_VINSEL_VIN_1V8 = 0x1, + ABX500_GPIO_VINSEL_VDD_BIF = 0x2, }; #endif /* _AB8500_GPIO_H */ diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 1cb5698..fc05344 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -24,7 +24,7 @@ enum ab8500_version { AB8500_VERSION_AB8500 = 0x0, AB8500_VERSION_AB8505 = 0x1, AB8500_VERSION_AB9540 = 0x2, - AB8500_VERSION_AB8540 = 0x3, + AB8500_VERSION_AB8540 = 0x4, AB8500_VERSION_UNDEFINED, }; @@ -32,6 +32,7 @@ enum ab8500_version { #define AB8500_CUTEARLY 0x00 #define AB8500_CUT1P0 0x10 #define AB8500_CUT1P1 0x11 +#define AB8500_CUT1P2 0x12 /* Only valid for AB8540 */ #define AB8500_CUT2P0 0x20 #define AB8500_CUT3P0 0x30 #define AB8500_CUT3P3 0x33 @@ -39,6 +40,7 @@ enum ab8500_version { /* * AB8500 bank addresses */ +#define AB8500_M_FSM_RANK 0x0 #define AB8500_SYS_CTRL1_BLOCK 0x1 #define AB8500_SYS_CTRL2_BLOCK 0x2 #define AB8500_REGU_CTRL1 0x3 @@ -58,6 +60,7 @@ enum ab8500_version { #define AB8500_DEVELOPMENT 0x11 #define AB8500_DEBUG 0x12 #define AB8500_PROD_TEST 0x13 +#define AB8500_STE_TEST 0x14 #define AB8500_OTP_EMUL 0x15 /* @@ -65,11 +68,11 @@ enum ab8500_version { * Values used to index into array ab8500_irq_regoffset[] defined in * drivers/mdf/ab8500-core.c */ -/* Definitions for AB8500 and AB9540 */ +/* Definitions for AB8500, AB9540 and AB8540 */ /* ab8500_irq_regoffset[0] -> IT[Source|Latch|Mask]1 */ #define AB8500_INT_MAIN_EXT_CH_NOT_OK 0 /* not 8505/9540 */ -#define AB8500_INT_UN_PLUG_TV_DET 1 /* not 8505/9540 */ -#define AB8500_INT_PLUG_TV_DET 2 /* not 8505/9540 */ +#define AB8500_INT_UN_PLUG_TV_DET 1 /* not 8505/9540/8540 */ +#define AB8500_INT_PLUG_TV_DET 2 /* not 8505/9540/8540 */ #define AB8500_INT_TEMP_WARM 3 #define AB8500_INT_PON_KEY2DB_F 4 #define AB8500_INT_PON_KEY2DB_R 5 @@ -77,18 +80,19 @@ enum ab8500_version { #define AB8500_INT_PON_KEY1DB_R 7 /* ab8500_irq_regoffset[1] -> IT[Source|Latch|Mask]2 */ #define AB8500_INT_BATT_OVV 8 -#define AB8500_INT_MAIN_CH_UNPLUG_DET 10 /* not 8505 */ -#define AB8500_INT_MAIN_CH_PLUG_DET 11 /* not 8505 */ +#define AB8500_INT_MAIN_CH_UNPLUG_DET 10 /* not 8505/8540 */ +#define AB8500_INT_MAIN_CH_PLUG_DET 11 /* not 8505/8540 */ #define AB8500_INT_VBUS_DET_F 14 #define AB8500_INT_VBUS_DET_R 15 /* ab8500_irq_regoffset[2] -> IT[Source|Latch|Mask]3 */ #define AB8500_INT_VBUS_CH_DROP_END 16 #define AB8500_INT_RTC_60S 17 #define AB8500_INT_RTC_ALARM 18 +#define AB8540_INT_BIF_INT 19 #define AB8500_INT_BAT_CTRL_INDB 20 #define AB8500_INT_CH_WD_EXP 21 #define AB8500_INT_VBUS_OVV 22 -#define AB8500_INT_MAIN_CH_DROP_END 23 /* not 8505/9540 */ +#define AB8500_INT_MAIN_CH_DROP_END 23 /* not 8505/9540/8540 */ /* ab8500_irq_regoffset[3] -> IT[Source|Latch|Mask]4 */ #define AB8500_INT_CCN_CONV_ACC 24 #define AB8500_INT_INT_AUD 25 @@ -99,7 +103,7 @@ enum ab8500_version { #define AB8500_INT_BUP_CHG_NOT_OK 30 #define AB8500_INT_BUP_CHG_OK 31 /* ab8500_irq_regoffset[4] -> IT[Source|Latch|Mask]5 */ -#define AB8500_INT_GP_HW_ADC_CONV_END 32 /* not 8505 */ +#define AB8500_INT_GP_HW_ADC_CONV_END 32 /* not 8505/8540 */ #define AB8500_INT_ACC_DETECT_1DB_F 33 #define AB8500_INT_ACC_DETECT_1DB_R 34 #define AB8500_INT_ACC_DETECT_22DB_F 35 @@ -108,23 +112,23 @@ enum ab8500_version { #define AB8500_INT_ACC_DETECT_21DB_R 38 #define AB8500_INT_GP_SW_ADC_CONV_END 39 /* ab8500_irq_regoffset[5] -> IT[Source|Latch|Mask]7 */ -#define AB8500_INT_GPIO6R 40 /* not 8505/9540 */ -#define AB8500_INT_GPIO7R 41 /* not 8505/9540 */ -#define AB8500_INT_GPIO8R 42 /* not 8505/9540 */ -#define AB8500_INT_GPIO9R 43 /* not 8505/9540 */ -#define AB8500_INT_GPIO10R 44 -#define AB8500_INT_GPIO11R 45 -#define AB8500_INT_GPIO12R 46 /* not 8505 */ -#define AB8500_INT_GPIO13R 47 +#define AB8500_INT_GPIO6R 40 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO7R 41 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO8R 42 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO9R 43 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO10R 44 /* not 8540 */ +#define AB8500_INT_GPIO11R 45 /* not 8540 */ +#define AB8500_INT_GPIO12R 46 /* not 8505/8540 */ +#define AB8500_INT_GPIO13R 47 /* not 8540 */ /* ab8500_irq_regoffset[6] -> IT[Source|Latch|Mask]8 */ -#define AB8500_INT_GPIO24R 48 /* not 8505 */ -#define AB8500_INT_GPIO25R 49 /* not 8505 */ -#define AB8500_INT_GPIO36R 50 /* not 8505/9540 */ -#define AB8500_INT_GPIO37R 51 /* not 8505/9540 */ -#define AB8500_INT_GPIO38R 52 /* not 8505/9540 */ -#define AB8500_INT_GPIO39R 53 /* not 8505/9540 */ -#define AB8500_INT_GPIO40R 54 -#define AB8500_INT_GPIO41R 55 +#define AB8500_INT_GPIO24R 48 /* not 8505/8540 */ +#define AB8500_INT_GPIO25R 49 /* not 8505/8540 */ +#define AB8500_INT_GPIO36R 50 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO37R 51 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO38R 52 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO39R 53 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO40R 54 /* not 8540 */ +#define AB8500_INT_GPIO41R 55 /* not 8540 */ /* ab8500_irq_regoffset[7] -> IT[Source|Latch|Mask]9 */ #define AB8500_INT_GPIO6F 56 /* not 8505/9540 */ #define AB8500_INT_GPIO7F 57 /* not 8505/9540 */ @@ -135,14 +139,14 @@ enum ab8500_version { #define AB8500_INT_GPIO12F 62 /* not 8505 */ #define AB8500_INT_GPIO13F 63 /* ab8500_irq_regoffset[8] -> IT[Source|Latch|Mask]10 */ -#define AB8500_INT_GPIO24F 64 /* not 8505 */ -#define AB8500_INT_GPIO25F 65 /* not 8505 */ -#define AB8500_INT_GPIO36F 66 /* not 8505/9540 */ -#define AB8500_INT_GPIO37F 67 /* not 8505/9540 */ -#define AB8500_INT_GPIO38F 68 /* not 8505/9540 */ -#define AB8500_INT_GPIO39F 69 /* not 8505/9540 */ -#define AB8500_INT_GPIO40F 70 -#define AB8500_INT_GPIO41F 71 +#define AB8500_INT_GPIO24F 64 /* not 8505/8540 */ +#define AB8500_INT_GPIO25F 65 /* not 8505/8540 */ +#define AB8500_INT_GPIO36F 66 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO37F 67 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO38F 68 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO39F 69 /* not 8505/9540/8540 */ +#define AB8500_INT_GPIO40F 70 /* not 8540 */ +#define AB8500_INT_GPIO41F 71 /* not 8540 */ /* ab8500_irq_regoffset[9] -> IT[Source|Latch|Mask]12 */ #define AB8500_INT_ADP_SOURCE_ERROR 72 #define AB8500_INT_ADP_SINK_ERROR 73 @@ -160,42 +164,44 @@ enum ab8500_version { #define AB8500_INT_SRP_DETECT 88 #define AB8500_INT_USB_CHARGER_NOT_OKR 89 #define AB8500_INT_ID_WAKEUP_R 90 +#define AB8500_INT_ID_DET_PLUGR 91 /* 8505/9540 cut2.0 */ #define AB8500_INT_ID_DET_R1R 92 #define AB8500_INT_ID_DET_R2R 93 #define AB8500_INT_ID_DET_R3R 94 #define AB8500_INT_ID_DET_R4R 95 /* ab8500_irq_regoffset[12] -> IT[Source|Latch|Mask]21 */ -#define AB8500_INT_ID_WAKEUP_F 96 -#define AB8500_INT_ID_DET_R1F 98 -#define AB8500_INT_ID_DET_R2F 99 -#define AB8500_INT_ID_DET_R3F 100 -#define AB8500_INT_ID_DET_R4F 101 -#define AB8500_INT_CHAUTORESTARTAFTSEC 102 +#define AB8500_INT_ID_WAKEUP_F 96 /* not 8505/9540 */ +#define AB8500_INT_ID_DET_PLUGF 97 /* 8505/9540 cut2.0 */ +#define AB8500_INT_ID_DET_R1F 98 /* not 8505/9540 */ +#define AB8500_INT_ID_DET_R2F 99 /* not 8505/9540 */ +#define AB8500_INT_ID_DET_R3F 100 /* not 8505/9540 */ +#define AB8500_INT_ID_DET_R4F 101 /* not 8505/9540 */ +#define AB8500_INT_CHAUTORESTARTAFTSEC 102 /* not 8505/9540 */ #define AB8500_INT_CHSTOPBYSEC 103 /* ab8500_irq_regoffset[13] -> IT[Source|Latch|Mask]22 */ #define AB8500_INT_USB_CH_TH_PROT_F 104 -#define AB8500_INT_USB_CH_TH_PROT_R 105 +#define AB8500_INT_USB_CH_TH_PROT_R 105 #define AB8500_INT_MAIN_CH_TH_PROT_F 106 /* not 8505/9540 */ #define AB8500_INT_MAIN_CH_TH_PROT_R 107 /* not 8505/9540 */ #define AB8500_INT_CHCURLIMNOHSCHIRP 109 #define AB8500_INT_CHCURLIMHSCHIRP 110 #define AB8500_INT_XTAL32K_KO 111 -/* Definitions for AB9540 */ +/* Definitions for AB9540 / AB8505 */ /* ab8500_irq_regoffset[14] -> IT[Source|Latch|Mask]13 */ -#define AB9540_INT_GPIO50R 113 -#define AB9540_INT_GPIO51R 114 /* not 8505 */ -#define AB9540_INT_GPIO52R 115 -#define AB9540_INT_GPIO53R 116 -#define AB9540_INT_GPIO54R 117 /* not 8505 */ +#define AB9540_INT_GPIO50R 113 /* not 8540 */ +#define AB9540_INT_GPIO51R 114 /* not 8505/8540 */ +#define AB9540_INT_GPIO52R 115 /* not 8540 */ +#define AB9540_INT_GPIO53R 116 /* not 8540 */ +#define AB9540_INT_GPIO54R 117 /* not 8505/8540 */ #define AB9540_INT_IEXT_CH_RF_BFN_R 118 -#define AB9540_INT_IEXT_CH_RF_BFN_F 119 /* ab8500_irq_regoffset[15] -> IT[Source|Latch|Mask]14 */ -#define AB9540_INT_GPIO50F 121 -#define AB9540_INT_GPIO51F 122 /* not 8505 */ -#define AB9540_INT_GPIO52F 123 -#define AB9540_INT_GPIO53F 124 -#define AB9540_INT_GPIO54F 125 /* not 8505 */ +#define AB9540_INT_GPIO50F 121 /* not 8540 */ +#define AB9540_INT_GPIO51F 122 /* not 8505/8540 */ +#define AB9540_INT_GPIO52F 123 /* not 8540 */ +#define AB9540_INT_GPIO53F 124 /* not 8540 */ +#define AB9540_INT_GPIO54F 125 /* not 8505/8540 */ +#define AB9540_INT_IEXT_CH_RF_BFN_F 126 /* ab8500_irq_regoffset[16] -> IT[Source|Latch|Mask]25 */ #define AB8505_INT_KEYSTUCK 128 #define AB8505_INT_IKR 129 @@ -204,6 +210,87 @@ enum ab8500_version { #define AB8505_INT_KEYDEGLITCH 132 #define AB8505_INT_MODPWRSTATUSF 134 #define AB8505_INT_MODPWRSTATUSR 135 +/* ab8500_irq_regoffset[17] -> IT[Source|Latch|Mask]6 */ +#define AB8500_INT_HOOK_DET_NEG_F 138 +#define AB8500_INT_HOOK_DET_NEG_R 139 +#define AB8500_INT_HOOK_DET_POS_F 140 +#define AB8500_INT_HOOK_DET_POS_R 141 +#define AB8500_INT_PLUG_DET_COMP_F 142 +#define AB8500_INT_PLUG_DET_COMP_R 143 +/* ab8500_irq_regoffset[18] -> IT[Source|Latch|Mask]23 */ +#define AB8505_INT_COLL 144 +#define AB8505_INT_RESERR 145 +#define AB8505_INT_FRAERR 146 +#define AB8505_INT_COMERR 147 +#define AB8505_INT_SPDSET 148 +#define AB8505_INT_DSENT 149 +#define AB8505_INT_DREC 150 +#define AB8505_INT_ACC_INT 151 +/* ab8500_irq_regoffset[19] -> IT[Source|Latch|Mask]24 */ +#define AB8505_INT_NOPINT 152 +/* ab8540_irq_regoffset[20] -> IT[Source|Latch|Mask]26 */ +#define AB8540_INT_IDPLUGDETCOMPF 160 +#define AB8540_INT_IDPLUGDETCOMPR 161 +#define AB8540_INT_FMDETCOMPLOF 162 +#define AB8540_INT_FMDETCOMPLOR 163 +#define AB8540_INT_FMDETCOMPHIF 164 +#define AB8540_INT_FMDETCOMPHIR 165 +#define AB8540_INT_ID5VDETCOMPF 166 +#define AB8540_INT_ID5VDETCOMPR 167 +/* ab8540_irq_regoffset[21] -> IT[Source|Latch|Mask]27 */ +#define AB8540_INT_GPIO43F 168 +#define AB8540_INT_GPIO43R 169 +#define AB8540_INT_GPIO44F 170 +#define AB8540_INT_GPIO44R 171 +#define AB8540_INT_KEYPOSDETCOMPF 172 +#define AB8540_INT_KEYPOSDETCOMPR 173 +#define AB8540_INT_KEYNEGDETCOMPF 174 +#define AB8540_INT_KEYNEGDETCOMPR 175 +/* ab8540_irq_regoffset[22] -> IT[Source|Latch|Mask]28 */ +#define AB8540_INT_GPIO1VBATF 176 +#define AB8540_INT_GPIO1VBATR 177 +#define AB8540_INT_GPIO2VBATF 178 +#define AB8540_INT_GPIO2VBATR 179 +#define AB8540_INT_GPIO3VBATF 180 +#define AB8540_INT_GPIO3VBATR 181 +#define AB8540_INT_GPIO4VBATF 182 +#define AB8540_INT_GPIO4VBATR 183 +/* ab8540_irq_regoffset[23] -> IT[Source|Latch|Mask]29 */ +#define AB8540_INT_SYSCLKREQ2F 184 +#define AB8540_INT_SYSCLKREQ2R 185 +#define AB8540_INT_SYSCLKREQ3F 186 +#define AB8540_INT_SYSCLKREQ3R 187 +#define AB8540_INT_SYSCLKREQ4F 188 +#define AB8540_INT_SYSCLKREQ4R 189 +#define AB8540_INT_SYSCLKREQ5F 190 +#define AB8540_INT_SYSCLKREQ5R 191 +/* ab8540_irq_regoffset[24] -> IT[Source|Latch|Mask]30 */ +#define AB8540_INT_PWMOUT1F 192 +#define AB8540_INT_PWMOUT1R 193 +#define AB8540_INT_PWMCTRL0F 194 +#define AB8540_INT_PWMCTRL0R 195 +#define AB8540_INT_PWMCTRL1F 196 +#define AB8540_INT_PWMCTRL1R 197 +#define AB8540_INT_SYSCLKREQ6F 198 +#define AB8540_INT_SYSCLKREQ6R 199 +/* ab8540_irq_regoffset[25] -> IT[Source|Latch|Mask]31 */ +#define AB8540_INT_PWMEXTVIBRA1F 200 +#define AB8540_INT_PWMEXTVIBRA1R 201 +#define AB8540_INT_PWMEXTVIBRA2F 202 +#define AB8540_INT_PWMEXTVIBRA2R 203 +#define AB8540_INT_PWMOUT2F 204 +#define AB8540_INT_PWMOUT2R 205 +#define AB8540_INT_PWMOUT3F 206 +#define AB8540_INT_PWMOUT3R 207 +/* ab8540_irq_regoffset[26] -> IT[Source|Latch|Mask]32 */ +#define AB8540_INT_ADDATA2F 208 +#define AB8540_INT_ADDATA2R 209 +#define AB8540_INT_DADATA2F 210 +#define AB8540_INT_DADATA2R 211 +#define AB8540_INT_FSYNC2F 212 +#define AB8540_INT_FSYNC2R 213 +#define AB8540_INT_BITCLK2F 214 +#define AB8540_INT_BITCLK2R 215 /* * AB8500_AB9540_NR_IRQS is used when configuring the IRQ numbers for the @@ -213,13 +300,24 @@ enum ab8500_version { * which is larger. */ #define AB8500_NR_IRQS 112 -#define AB8505_NR_IRQS 136 -#define AB9540_NR_IRQS 136 +#define AB8505_NR_IRQS 153 +#define AB9540_NR_IRQS 153 +#define AB8540_NR_IRQS 216 /* This is set to the roof of any AB8500 chip variant IRQ counts */ -#define AB8500_MAX_NR_IRQS AB9540_NR_IRQS +#define AB8500_MAX_NR_IRQS AB8540_NR_IRQS #define AB8500_NUM_IRQ_REGS 14 -#define AB9540_NUM_IRQ_REGS 17 +#define AB9540_NUM_IRQ_REGS 20 +#define AB8540_NUM_IRQ_REGS 27 + +/* Turn On Status Event */ +#define AB8500_POR_ON_VBAT 0x01 +#define AB8500_POW_KEY_1_ON 0x02 +#define AB8500_POW_KEY_2_ON 0x04 +#define AB8500_RTC_ALARM 0x08 +#define AB8500_MAIN_CH_DET 0x10 +#define AB8500_VBUS_DET 0x20 +#define AB8500_USB_ID_DET 0x40 /** * struct ab8500 - ab8500 internal structure @@ -287,7 +385,7 @@ struct ab8500_platform_data { struct ab8500_regulator_reg_init *regulator_reg_init; int num_regulator; struct regulator_init_data *regulator; - struct ab8500_gpio_platform_data *gpio; + struct abx500_gpio_platform_data *gpio; struct ab8500_codec_platform_data *codec; }; @@ -335,10 +433,79 @@ static inline int is_ab8500_2p0_or_earlier(struct ab8500 *ab) return (is_ab8500(ab) && (ab->chip_id <= AB8500_CUT2P0)); } +static inline int is_ab8500_3p3_or_earlier(struct ab8500 *ab) +{ + return (is_ab8500(ab) && (ab->chip_id <= AB8500_CUT3P3)); +} + /* exclude also ab8505, ab9540... */ static inline int is_ab8500_2p0(struct ab8500 *ab) { return (is_ab8500(ab) && (ab->chip_id == AB8500_CUT2P0)); } +static inline int is_ab8505_1p0_or_earlier(struct ab8500 *ab) +{ + return (is_ab8505(ab) && (ab->chip_id <= AB8500_CUT1P0)); +} + +static inline int is_ab8505_2p0(struct ab8500 *ab) +{ + return (is_ab8505(ab) && (ab->chip_id == AB8500_CUT2P0)); +} + +static inline int is_ab9540_1p0_or_earlier(struct ab8500 *ab) +{ + return (is_ab9540(ab) && (ab->chip_id <= AB8500_CUT1P0)); +} + +static inline int is_ab9540_2p0(struct ab8500 *ab) +{ + return (is_ab9540(ab) && (ab->chip_id == AB8500_CUT2P0)); +} + +/* + * Be careful, the marketing name for this chip is 2.1 + * but the value read from the chip is 3.0 (0x30) + */ +static inline int is_ab9540_3p0(struct ab8500 *ab) +{ + return (is_ab9540(ab) && (ab->chip_id == AB8500_CUT3P0)); +} + +static inline int is_ab8540_1p0_or_earlier(struct ab8500 *ab) +{ + return is_ab8540(ab) && (ab->chip_id <= AB8500_CUT1P0); +} + +static inline int is_ab8540_1p1_or_earlier(struct ab8500 *ab) +{ + return is_ab8540(ab) && (ab->chip_id <= AB8500_CUT1P1); +} + +static inline int is_ab8540_1p2_or_earlier(struct ab8500 *ab) +{ + return is_ab8540(ab) && (ab->chip_id <= AB8500_CUT1P2); +} + +static inline int is_ab8540_2p0_or_earlier(struct ab8500 *ab) +{ + return is_ab8540(ab) && (ab->chip_id <= AB8500_CUT2P0); +} + +static inline int is_ab8540_2p0(struct ab8500 *ab) +{ + return is_ab8540(ab) && (ab->chip_id == AB8500_CUT2P0); +} + +static inline int is_ab8505_2p0_earlier(struct ab8500 *ab) +{ + return (is_ab8505(ab) && (ab->chip_id < AB8500_CUT2P0)); +} + +static inline int is_ab9540_2p0_or_earlier(struct ab8500 *ab) +{ + return (is_ab9540(ab) && (ab->chip_id < AB8500_CUT2P0)); +} + #endif /* MFD_AB8500_H */ diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index 86dd93d..786d02e 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -99,6 +99,9 @@ struct da9052 { u8 chip_id; int chip_irq; + + /* SOC I/O transfer related fixes for DA9052/53 */ + int (*fix_io) (struct da9052 *da9052, unsigned char reg); }; /* ADC API */ @@ -113,32 +116,87 @@ static inline int da9052_reg_read(struct da9052 *da9052, unsigned char reg) ret = regmap_read(da9052->regmap, reg, &val); if (ret < 0) return ret; + + if (da9052->fix_io) { + ret = da9052->fix_io(da9052, reg); + if (ret < 0) + return ret; + } + return val; } static inline int da9052_reg_write(struct da9052 *da9052, unsigned char reg, unsigned char val) { - return regmap_write(da9052->regmap, reg, val); + int ret; + + ret = regmap_write(da9052->regmap, reg, val); + if (ret < 0) + return ret; + + if (da9052->fix_io) { + ret = da9052->fix_io(da9052, reg); + if (ret < 0) + return ret; + } + + return ret; } static inline int da9052_group_read(struct da9052 *da9052, unsigned char reg, unsigned reg_cnt, unsigned char *val) { - return regmap_bulk_read(da9052->regmap, reg, val, reg_cnt); + int ret; + + ret = regmap_bulk_read(da9052->regmap, reg, val, reg_cnt); + if (ret < 0) + return ret; + + if (da9052->fix_io) { + ret = da9052->fix_io(da9052, reg); + if (ret < 0) + return ret; + } + + return ret; } static inline int da9052_group_write(struct da9052 *da9052, unsigned char reg, unsigned reg_cnt, unsigned char *val) { - return regmap_raw_write(da9052->regmap, reg, val, reg_cnt); + int ret; + + ret = regmap_raw_write(da9052->regmap, reg, val, reg_cnt); + if (ret < 0) + return ret; + + if (da9052->fix_io) { + ret = da9052->fix_io(da9052, reg); + if (ret < 0) + return ret; + } + + return ret; } static inline int da9052_reg_update(struct da9052 *da9052, unsigned char reg, unsigned char bit_mask, unsigned char reg_val) { - return regmap_update_bits(da9052->regmap, reg, bit_mask, reg_val); + int ret; + + ret = regmap_update_bits(da9052->regmap, reg, bit_mask, reg_val); + if (ret < 0) + return ret; + + if (da9052->fix_io) { + ret = da9052->fix_io(da9052, reg); + if (ret < 0) + return ret; + } + + return ret; } int da9052_device_init(struct da9052 *da9052, u8 chip_id); diff --git a/include/linux/mfd/da9052/reg.h b/include/linux/mfd/da9052/reg.h index b97f730..c4dd3a8 100644 --- a/include/linux/mfd/da9052/reg.h +++ b/include/linux/mfd/da9052/reg.h @@ -34,6 +34,9 @@ #define DA9052_STATUS_C_REG 3 #define DA9052_STATUS_D_REG 4 +/* PARK REGISTER */ +#define DA9052_PARK_REGISTER DA9052_STATUS_D_REG + /* EVENT REGISTERS */ #define DA9052_EVENT_A_REG 5 #define DA9052_EVENT_B_REG 6 diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h index a8d393e..2b13970 100644 --- a/include/linux/mfd/rtsx_common.h +++ b/include/linux/mfd/rtsx_common.h @@ -38,6 +38,9 @@ #define RTSX_SD_CARD 0 #define RTSX_MS_CARD 1 +#define CLK_TO_DIV_N 0 +#define DIV_N_TO_CLK 1 + struct platform_device; struct rtsx_slot { diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 060b721..4b117a3 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -158,10 +158,9 @@ #define SG_TRANS_DATA (0x02 << 4) #define SG_LINK_DESC (0x03 << 4) -/* SD bank voltage */ -#define SD_IO_3V3 0 -#define SD_IO_1V8 1 - +/* Output voltage */ +#define OUTPUT_3V3 0 +#define OUTPUT_1V8 1 /* Card Clock Enable Register */ #define SD_CLK_EN 0x04 @@ -201,6 +200,20 @@ #define CHANGE_CLK 0x01 /* LDO_CTL */ +#define BPP_ASIC_1V7 0x00 +#define BPP_ASIC_1V8 0x01 +#define BPP_ASIC_1V9 0x02 +#define BPP_ASIC_2V0 0x03 +#define BPP_ASIC_2V7 0x04 +#define BPP_ASIC_2V8 0x05 +#define BPP_ASIC_3V2 0x06 +#define BPP_ASIC_3V3 0x07 +#define BPP_REG_TUNED18 0x07 +#define BPP_TUNED18_SHIFT_8402 5 +#define BPP_TUNED18_SHIFT_8411 4 +#define BPP_PAD_MASK 0x04 +#define BPP_PAD_3V3 0x04 +#define BPP_PAD_1V8 0x00 #define BPP_LDO_POWB 0x03 #define BPP_LDO_ON 0x00 #define BPP_LDO_SUSPEND 0x02 @@ -688,7 +701,10 @@ struct pcr_ops { int (*disable_auto_blink)(struct rtsx_pcr *pcr); int (*card_power_on)(struct rtsx_pcr *pcr, int card); int (*card_power_off)(struct rtsx_pcr *pcr, int card); + int (*switch_output_voltage)(struct rtsx_pcr *pcr, + u8 voltage); unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); + int (*conv_clk_and_div_n)(int clk, int dir); }; enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; @@ -783,6 +799,7 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk); int rtsx_pci_card_power_on(struct rtsx_pcr *pcr, int card); int rtsx_pci_card_power_off(struct rtsx_pcr *pcr, int card); +int rtsx_pci_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage); unsigned int rtsx_pci_card_exist(struct rtsx_pcr *pcr); void rtsx_pci_complete_unfinished_transfer(struct rtsx_pcr *pcr); diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index b50c38f..f0f4de3 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -26,6 +26,7 @@ enum sec_device_type { /** * struct sec_pmic_dev - s5m87xx master device for sub-drivers * @dev: master device of the chip (can be used to access platform data) + * @pdata: pointer to private data used to pass platform data to child * @i2c: i2c client private data for regulator * @rtc: i2c client private data for rtc * @iolock: mutex for serializing io access @@ -39,6 +40,7 @@ enum sec_device_type { */ struct sec_pmic_dev { struct device *dev; + struct sec_platform_data *pdata; struct regmap *regmap; struct i2c_client *i2c; struct i2c_client *rtc; @@ -82,11 +84,11 @@ struct sec_platform_data { int buck_gpios[3]; int buck_ds[3]; - int buck2_voltage[8]; + unsigned int buck2_voltage[8]; bool buck2_gpiodvs; - int buck3_voltage[8]; + unsigned int buck3_voltage[8]; bool buck3_gpiodvs; - int buck4_voltage[8]; + unsigned int buck4_voltage[8]; bool buck4_gpiodvs; int buck_set1; @@ -127,6 +129,7 @@ struct sec_platform_data { struct sec_regulator_data { int id; struct regulator_init_data *initdata; + struct device_node *reg_node; }; /* @@ -136,7 +139,7 @@ struct sec_regulator_data { */ struct sec_opmode_data { int id; - int mode; + unsigned int mode; }; /* diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index bc823c4..deca874 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -151,7 +151,7 @@ struct mmu_notifier_ops { * Therefore notifier chains can only be traversed when either * * 1. mmap_sem is held. - * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->mutex). + * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { diff --git a/include/linux/pci.h b/include/linux/pci.h index 15472d6..6fa4dd2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1101,6 +1101,12 @@ static inline int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec) return -1; } +static inline int +pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec) +{ + return -1; +} + static inline void pci_msi_shutdown(struct pci_dev *dev) { } static inline void pci_disable_msi(struct pci_dev *dev) @@ -1132,6 +1138,7 @@ static inline int pci_msi_enabled(void) } #else extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec); +extern int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec); extern void pci_msi_shutdown(struct pci_dev *dev); extern void pci_disable_msi(struct pci_dev *dev); extern int pci_msix_table_size(struct pci_dev *dev); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6bfb2faa..e47ee46 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -135,16 +135,21 @@ struct hw_perf_event { struct { /* software */ struct hrtimer hrtimer; }; + struct { /* tracepoint */ + struct task_struct *tp_target; + /* for tp_event->class */ + struct list_head tp_list; + }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ - struct arch_hw_breakpoint info; - struct list_head bp_list; /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct task_struct *bp_target; + struct arch_hw_breakpoint info; + struct list_head bp_list; }; #endif }; @@ -817,6 +822,17 @@ do { \ } while (0) +struct perf_pmu_events_attr { + struct device_attribute attr; + u64 id; +}; + +#define PMU_EVENT_ATTR(_name, _var, _id, _show) \ +static struct perf_pmu_events_attr _var = { \ + .attr = __ATTR(_name, 0444, _show, NULL), \ + .id = _id, \ +}; + #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ diff --git a/include/linux/pinctrl/devinfo.h b/include/linux/pinctrl/devinfo.h new file mode 100644 index 0000000..6e5f8a9 --- /dev/null +++ b/include/linux/pinctrl/devinfo.h @@ -0,0 +1,45 @@ +/* + * Per-device information from the pin control system. + * This is the stuff that get included into the device + * core. + * + * Copyright (C) 2012 ST-Ericsson SA + * Written on behalf of Linaro for ST-Ericsson + * This interface is used in the core to keep track of pins. + * + * Author: Linus Walleij <linus.walleij@linaro.org> + * + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef PINCTRL_DEVINFO_H +#define PINCTRL_DEVINFO_H + +#ifdef CONFIG_PINCTRL + +/* The device core acts as a consumer toward pinctrl */ +#include <linux/pinctrl/consumer.h> + +/** + * struct dev_pin_info - pin state container for devices + * @p: pinctrl handle for the containing device + * @default_state: the default state for the handle, if found + */ +struct dev_pin_info { + struct pinctrl *p; + struct pinctrl_state *default_state; +}; + +extern int pinctrl_bind_pins(struct device *dev); + +#else + +/* Stubs if we're not using pinctrl */ + +static inline int pinctrl_bind_pins(struct device *dev) +{ + return 0; +} + +#endif /* CONFIG_PINCTRL */ +#endif /* PINCTRL_DEVINFO_H */ diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 47a1bdd..72474e1 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -46,7 +46,11 @@ * @PIN_CONFIG_DRIVE_OPEN_SOURCE: the pin will be driven with open source * (open emitter). Sending this config will enabale open drain mode, the * argument is ignored. - * @PIN_CONFIG_INPUT_SCHMITT_DISABLE: disable schmitt-trigger mode on the pin. + * @PIN_CONFIG_DRIVE_STRENGTH: the pin will output the current passed as + * argument. The argument is in mA. + * @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin. + * If the argument != 0, schmitt-trigger mode is enabled. If it's 0, + * schmitt-trigger mode is disabled. * @PIN_CONFIG_INPUT_SCHMITT: this will configure an input pin to run in * schmitt-trigger mode. If the schmitt-trigger has adjustable hysteresis, * the threshold value is given on a custom format as argument when @@ -58,10 +62,15 @@ * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. + * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to + * this parameter (on a custom format) tells the driver which alternative + * slew rate to use. * @PIN_CONFIG_LOW_POWER_MODE: this will configure the pin for low power * operation, if several modes of operation are supported these can be * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. + * @PIN_CONFIG_OUTPUT: this will configure the pin in output, use argument + * 1 to indicate high level, argument 0 to indicate low level. * @PIN_CONFIG_END: this is the last enumerator for pin configurations, if * you need to pass in custom configurations to the pin controller, use * PIN_CONFIG_END+1 as the base offset. @@ -74,11 +83,14 @@ enum pin_config_param { PIN_CONFIG_DRIVE_PUSH_PULL, PIN_CONFIG_DRIVE_OPEN_DRAIN, PIN_CONFIG_DRIVE_OPEN_SOURCE, - PIN_CONFIG_INPUT_SCHMITT_DISABLE, + PIN_CONFIG_DRIVE_STRENGTH, + PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_INPUT_SCHMITT, PIN_CONFIG_INPUT_DEBOUNCE, PIN_CONFIG_POWER_SOURCE, + PIN_CONFIG_SLEW_RATE, PIN_CONFIG_LOW_POWER_MODE, + PIN_CONFIG_OUTPUT, PIN_CONFIG_END = 0x7FFF, }; diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 04d6700..778804d 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -154,6 +154,7 @@ struct pinctrl_dev *of_pinctrl_get(struct device_node *np) #endif /* CONFIG_OF */ extern const char *pinctrl_dev_get_name(struct pinctrl_dev *pctldev); +extern const char *pinctrl_dev_get_devname(struct pinctrl_dev *pctldev); extern void *pinctrl_dev_get_drvdata(struct pinctrl_dev *pctldev); #else diff --git a/include/linux/platform_data/lp8755.h b/include/linux/platform_data/lp8755.h new file mode 100644 index 0000000..a7fd077 --- /dev/null +++ b/include/linux/platform_data/lp8755.h @@ -0,0 +1,71 @@ +/* + * LP8755 High Performance Power Management Unit Driver:System Interface Driver + * + * Copyright (C) 2012 Texas Instruments + * + * Author: Daniel(Geon Si) Jeong <daniel.jeong@ti.com> + * G.Shark Jeong <gshark.jeong@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef _LP8755_H +#define _LP8755_H + +#include <linux/regulator/consumer.h> + +#define LP8755_NAME "lp8755-regulator" +/* + *PWR FAULT : power fault detected + *OCP : over current protect activated + *OVP : over voltage protect activated + *TEMP_WARN : thermal warning + *TEMP_SHDN : thermal shutdonw detected + *I_LOAD : current measured + */ +#define LP8755_EVENT_PWR_FAULT REGULATOR_EVENT_FAIL +#define LP8755_EVENT_OCP REGULATOR_EVENT_OVER_CURRENT +#define LP8755_EVENT_OVP 0x10000 +#define LP8755_EVENT_TEMP_WARN 0x2000 +#define LP8755_EVENT_TEMP_SHDN REGULATOR_EVENT_OVER_TEMP +#define LP8755_EVENT_I_LOAD 0x40000 + +enum lp8755_bucks { + LP8755_BUCK0 = 0, + LP8755_BUCK1, + LP8755_BUCK2, + LP8755_BUCK3, + LP8755_BUCK4, + LP8755_BUCK5, + LP8755_BUCK_MAX, +}; + +/** + * multiphase configuration options + */ +enum lp8755_mphase_config { + MPHASE_CONF0, + MPHASE_CONF1, + MPHASE_CONF2, + MPHASE_CONF3, + MPHASE_CONF4, + MPHASE_CONF5, + MPHASE_CONF6, + MPHASE_CONF7, + MPHASE_CONF8, + MPHASE_CONF_MAX +}; + +/** + * struct lp8755_platform_data + * @mphase_type : Multiphase Switcher Configurations. + * @buck_data : buck0~6 init voltage in uV + */ +struct lp8755_platform_data { + int mphase; + struct regulator_init_data *buck_data[LP8755_BUCK_MAX]; +}; +#endif diff --git a/include/linux/printk.h b/include/linux/printk.h index 9afc01e..86c4b62 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -98,9 +98,6 @@ int no_printk(const char *fmt, ...) extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); -extern int printk_needs_cpu(int cpu); -extern void printk_tick(void); - #ifdef CONFIG_PRINTK asmlinkage __printf(5, 0) int vprintk_emit(int facility, int level, diff --git a/include/linux/profile.h b/include/linux/profile.h index a0fc322..2112390 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -82,9 +82,6 @@ int task_handoff_unregister(struct notifier_block * n); int profile_event_register(enum profile_type, struct notifier_block * n); int profile_event_unregister(enum profile_type, struct notifier_block * n); -int register_timer_hook(int (*hook)(struct pt_regs *)); -void unregister_timer_hook(int (*hook)(struct pt_regs *)); - struct pt_regs; #else @@ -135,16 +132,6 @@ static inline int profile_event_unregister(enum profile_type t, struct notifier_ #define profile_handoff_task(a) (0) #define profile_munmap(a) do { } while (0) -static inline int register_timer_hook(int (*hook)(struct pt_regs *)) -{ - return -ENOSYS; -} - -static inline void unregister_timer_hook(int (*hook)(struct pt_regs *)) -{ - return; -} - #endif /* CONFIG_PROFILING */ #endif /* _LINUX_PROFILE_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 275aa3f1..b758ce1 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -53,7 +53,10 @@ extern int rcutorture_runnable; /* for sysctl */ extern void rcutorture_record_test_transition(void); extern void rcutorture_record_progress(unsigned long vernum); extern void do_trace_rcu_torture_read(char *rcutorturename, - struct rcu_head *rhp); + struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, + unsigned long c); #else static inline void rcutorture_record_test_transition(void) { @@ -63,9 +66,13 @@ static inline void rcutorture_record_progress(unsigned long vernum) } #ifdef CONFIG_RCU_TRACE extern void do_trace_rcu_torture_read(char *rcutorturename, - struct rcu_head *rhp); + struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, + unsigned long c); #else -#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) #endif #endif @@ -749,7 +756,7 @@ static inline void rcu_preempt_sleep_check(void) * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU) * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may * be preempted, but explicit blocking is illegal. Finally, in preemptible - * RCU implementations in real-time (CONFIG_PREEMPT_RT) kernel builds, + * RCU implementations in real-time (with -rt patchset) kernel builds, * RCU read-side critical sections may be preempted and they may also * block, but only when acquiring spinlocks that are subject to priority * inheritance. diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b7e95bf..bf77dfd 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -28,7 +28,8 @@ struct regmap_range_cfg; enum regcache_type { REGCACHE_NONE, REGCACHE_RBTREE, - REGCACHE_COMPRESSED + REGCACHE_COMPRESSED, + REGCACHE_FLAT, }; /** @@ -127,7 +128,18 @@ typedef void (*regmap_unlock)(void *); * @lock_arg: this field is passed as the only argument of lock/unlock * functions (ignored in case regular lock/unlock functions * are not overridden). - * + * @reg_read: Optional callback that if filled will be used to perform + * all the reads from the registers. Should only be provided for + * devices whos read operation cannot be represented as a simple read + * operation on a bus such as SPI, I2C, etc. Most of the devices do + * not need this. + * @reg_write: Same as above for writing. + * @fast_io: Register IO is fast. Use a spinlock instead of a mutex + * to perform locking. This field is ignored if custom lock/unlock + * functions are used (see fields lock/unlock of struct regmap_config). + * This field is a duplicate of a similar file in + * 'struct regmap_bus' and serves exact same purpose. + * Use it only for "no-bus" cases. * @max_register: Optional, specifies the maximum valid register index. * @wr_table: Optional, points to a struct regmap_access_table specifying * valid ranges for write access. @@ -177,6 +189,11 @@ struct regmap_config { regmap_unlock unlock; void *lock_arg; + int (*reg_read)(void *context, unsigned int reg, unsigned int *val); + int (*reg_write)(void *context, unsigned int reg, unsigned int val); + + bool fast_io; + unsigned int max_register; const struct regmap_access_table *wr_table; const struct regmap_access_table *rd_table; @@ -235,14 +252,21 @@ struct regmap_range_cfg { unsigned int window_len; }; +struct regmap_async; + typedef int (*regmap_hw_write)(void *context, const void *data, size_t count); typedef int (*regmap_hw_gather_write)(void *context, const void *reg, size_t reg_len, const void *val, size_t val_len); +typedef int (*regmap_hw_async_write)(void *context, + const void *reg, size_t reg_len, + const void *val, size_t val_len, + struct regmap_async *async); typedef int (*regmap_hw_read)(void *context, const void *reg_buf, size_t reg_size, void *val_buf, size_t val_size); +typedef struct regmap_async *(*regmap_hw_async_alloc)(void); typedef void (*regmap_hw_free_context)(void *context); /** @@ -255,8 +279,11 @@ typedef void (*regmap_hw_free_context)(void *context); * @write: Write operation. * @gather_write: Write operation with split register/value, return -ENOTSUPP * if not implemented on a given device. + * @async_write: Write operation which completes asynchronously, optional and + * must serialise with respect to non-async I/O. * @read: Read operation. Data is returned in the buffer used to transmit * data. + * @async_alloc: Allocate a regmap_async() structure. * @read_flag_mask: Mask to be set in the top byte of the register when doing * a read. * @reg_format_endian_default: Default endianness for formatted register @@ -265,13 +292,16 @@ typedef void (*regmap_hw_free_context)(void *context); * @val_format_endian_default: Default endianness for formatted register * values. Used when the regmap_config specifies DEFAULT. If this is * DEFAULT, BIG is assumed. + * @async_size: Size of struct used for async work. */ struct regmap_bus { bool fast_io; regmap_hw_write write; regmap_hw_gather_write gather_write; + regmap_hw_async_write async_write; regmap_hw_read read; regmap_hw_free_context free_context; + regmap_hw_async_alloc async_alloc; u8 read_flag_mask; enum regmap_endian reg_format_endian_default; enum regmap_endian val_format_endian_default; @@ -285,9 +315,9 @@ struct regmap *regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); struct regmap *regmap_init_spi(struct spi_device *dev, const struct regmap_config *config); -struct regmap *regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config); +struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id, + void __iomem *regs, + const struct regmap_config *config); struct regmap *devm_regmap_init(struct device *dev, const struct regmap_bus *bus, @@ -297,9 +327,44 @@ struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); struct regmap *devm_regmap_init_spi(struct spi_device *dev, const struct regmap_config *config); -struct regmap *devm_regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config); +struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id, + void __iomem *regs, + const struct regmap_config *config); + +/** + * regmap_init_mmio(): Initialise register map + * + * @dev: Device that will be interacted with + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +static inline struct regmap *regmap_init_mmio(struct device *dev, + void __iomem *regs, + const struct regmap_config *config) +{ + return regmap_init_mmio_clk(dev, NULL, regs, config); +} + +/** + * devm_regmap_init_mmio(): Initialise managed register map + * + * @dev: Device that will be interacted with + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +static inline struct regmap *devm_regmap_init_mmio(struct device *dev, + void __iomem *regs, + const struct regmap_config *config) +{ + return devm_regmap_init_mmio_clk(dev, NULL, regs, config); +} void regmap_exit(struct regmap *map); int regmap_reinit_cache(struct regmap *map, @@ -310,6 +375,8 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count); +int regmap_raw_write_async(struct regmap *map, unsigned int reg, + const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); @@ -321,6 +388,7 @@ int regmap_update_bits_check(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change); int regmap_get_val_bytes(struct regmap *map); +int regmap_async_complete(struct regmap *map); int regcache_sync(struct regmap *map); int regcache_sync_region(struct regmap *map, unsigned int min, @@ -381,6 +449,7 @@ struct regmap_irq_chip { unsigned int wake_base; unsigned int irq_reg_stride; unsigned int mask_invert; + unsigned int wake_invert; bool runtime_pm; int num_regs; @@ -422,6 +491,13 @@ static inline int regmap_raw_write(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_raw_write_async(struct regmap *map, unsigned int reg, + const void *val, size_t val_len) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, size_t val_count) { @@ -500,6 +576,11 @@ static inline void regcache_mark_dirty(struct regmap *map) WARN_ONCE(1, "regmap API is disabled"); } +static inline void regmap_async_complete(struct regmap *map) +{ + WARN_ONCE(1, "regmap API is disabled"); +} + static inline int regmap_register_patch(struct regmap *map, const struct reg_default *regs, int num_regs) diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index d10bb0f..23070fd 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -193,6 +193,10 @@ enum regulator_type { * * @vsel_reg: Register for selector when using regulator_regmap_X_voltage_ * @vsel_mask: Mask for register bitfield used for selector + * @apply_reg: Register for initiate voltage change on the output when + * using regulator_set_voltage_sel_regmap + * @apply_bit: Register bitfield used for initiate voltage change on the + * output when using regulator_set_voltage_sel_regmap * @enable_reg: Register for control when using regmap enable/disable ops * @enable_mask: Mask for control when using regmap enable/disable ops * @@ -218,6 +222,8 @@ struct regulator_desc { unsigned int vsel_reg; unsigned int vsel_mask; + unsigned int apply_reg; + unsigned int apply_bit; unsigned int enable_reg; unsigned int enable_mask; unsigned int bypass_reg; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 519777e..1342e69 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -167,6 +167,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu); +unsigned long ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu); u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu); void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 9531845c..11d05f9 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -138,6 +138,7 @@ extern void rtc_device_unregister(struct rtc_device *rtc); extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs); +extern int rtc_set_ntp_time(struct timespec now); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); diff --git a/include/linux/sched.h b/include/linux/sched.h index d2112477..e4112aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -304,19 +304,6 @@ static inline void lockup_detector_init(void) } #endif -#ifdef CONFIG_DETECT_HUNG_TASK -extern unsigned int sysctl_hung_task_panic; -extern unsigned long sysctl_hung_task_check_count; -extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_warnings; -extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); -#else -/* Avoid need for ifdefs elsewhere in the code */ -enum { sysctl_hung_task_timeout_secs = 0 }; -#endif - /* Attach to any functions which should be ignored in wchan output. */ #define __sched __attribute__((__section__(".sched.text"))) @@ -338,23 +325,6 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; -/* - * Default maximum number of active map areas, this limits the number of vmas - * per mm struct. Users can overwrite this number by sysctl but there is a - * problem. - * - * When a program's coredump is generated as ELF format, a section is created - * per a vma. In ELF, the number of sections is represented in unsigned short. - * This means the number of sections should be smaller than 65535 at coredump. - * Because the kernel adds some informative sections to a image of program at - * generating coredump, we need some margin. The number of extra sections is - * 1-3 now and depends on arch. We use "5" as safe margin, here. - */ -#define MAPCOUNT_ELF_CORE_MARGIN (5) -#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) - -extern int sysctl_max_map_count; - #include <linux/aio.h> #ifdef CONFIG_MMU @@ -1194,6 +1164,7 @@ struct sched_entity { /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; #endif + /* * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be * removed when useful for applications beyond shares distribution (e.g. @@ -1208,6 +1179,7 @@ struct sched_entity { struct sched_rt_entity { struct list_head run_list; unsigned long timeout; + unsigned long watchdog_stamp; unsigned int time_slice; struct sched_rt_entity *back; @@ -1220,11 +1192,6 @@ struct sched_rt_entity { #endif }; -/* - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. - */ -#define RR_TIMESLICE (100 * HZ / 1000) struct rcu_node; @@ -1368,6 +1335,15 @@ struct task_struct { #ifndef CONFIG_VIRT_CPU_ACCOUNTING struct cputime prev_cputime; #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + seqlock_t vtime_seqlock; + unsigned long long vtime_snap; + enum { + VTIME_SLEEPING = 0, + VTIME_USER, + VTIME_SYS, + } vtime_snap_whence; +#endif unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ struct timespec real_start_time; /* boot based time */ @@ -1622,37 +1598,6 @@ static inline void set_numabalancing_state(bool enabled) } #endif -/* - * Priority of a process goes from 0..MAX_PRIO-1, valid RT - * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH - * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority - * values are inverted: lower p->prio value means higher priority. - * - * The MAX_USER_RT_PRIO value allows the actual maximum - * RT priority to be separate from the value exported to - * user-space. This allows kernel threads to set their - * priority to a value higher than any user task. Note: - * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. - */ - -#define MAX_USER_RT_PRIO 100 -#define MAX_RT_PRIO MAX_USER_RT_PRIO - -#define MAX_PRIO (MAX_RT_PRIO + 40) -#define DEFAULT_PRIO (MAX_RT_PRIO + 20) - -static inline int rt_prio(int prio) -{ - if (unlikely(prio < MAX_RT_PRIO)) - return 1; - return 0; -} - -static inline int rt_task(struct task_struct *p) -{ - return rt_prio(p->prio); -} - static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; @@ -1792,6 +1737,37 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void task_cputime(struct task_struct *t, + cputime_t *utime, cputime_t *stime); +extern void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, cputime_t *stimescaled); +extern cputime_t task_gtime(struct task_struct *t); +#else +static inline void task_cputime(struct task_struct *t, + cputime_t *utime, cputime_t *stime) +{ + if (utime) + *utime = t->utime; + if (stime) + *stime = t->stime; +} + +static inline void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, + cputime_t *stimescaled) +{ + if (utimescaled) + *utimescaled = t->utimescaled; + if (stimescaled) + *stimescaled = t->stimescaled; +} + +static inline cputime_t task_gtime(struct task_struct *t) +{ + return t->gtime; +} +#endif extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); @@ -2033,58 +2009,7 @@ extern void wake_up_idle_cpu(int cpu); static inline void wake_up_idle_cpu(int cpu) { } #endif -extern unsigned int sysctl_sched_latency; -extern unsigned int sysctl_sched_min_granularity; -extern unsigned int sysctl_sched_wakeup_granularity; -extern unsigned int sysctl_sched_child_runs_first; - -enum sched_tunable_scaling { - SCHED_TUNABLESCALING_NONE, - SCHED_TUNABLESCALING_LOG, - SCHED_TUNABLESCALING_LINEAR, - SCHED_TUNABLESCALING_END, -}; -extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; - -extern unsigned int sysctl_numa_balancing_scan_delay; -extern unsigned int sysctl_numa_balancing_scan_period_min; -extern unsigned int sysctl_numa_balancing_scan_period_max; -extern unsigned int sysctl_numa_balancing_scan_period_reset; -extern unsigned int sysctl_numa_balancing_scan_size; -extern unsigned int sysctl_numa_balancing_settle_count; - -#ifdef CONFIG_SCHED_DEBUG -extern unsigned int sysctl_sched_migration_cost; -extern unsigned int sysctl_sched_nr_migrate; -extern unsigned int sysctl_sched_time_avg; -extern unsigned int sysctl_timer_migration; -extern unsigned int sysctl_sched_shares_window; - -int sched_proc_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, - loff_t *ppos); -#endif -#ifdef CONFIG_SCHED_DEBUG -static inline unsigned int get_sysctl_timer_migration(void) -{ - return sysctl_timer_migration; -} -#else -static inline unsigned int get_sysctl_timer_migration(void) -{ - return 1; -} -#endif -extern unsigned int sysctl_sched_rt_period; -extern int sysctl_sched_rt_runtime; - -int sched_rt_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); - #ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; - extern void sched_autogroup_create_attach(struct task_struct *p); extern void sched_autogroup_detach(struct task_struct *p); extern void sched_autogroup_fork(struct signal_struct *sig); @@ -2100,30 +2025,6 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { } static inline void sched_autogroup_exit(struct signal_struct *sig) { } #endif -#ifdef CONFIG_CFS_BANDWIDTH -extern unsigned int sysctl_sched_cfs_bandwidth_slice; -#endif - -#ifdef CONFIG_RT_MUTEXES -extern int rt_mutex_getprio(struct task_struct *p); -extern void rt_mutex_setprio(struct task_struct *p, int prio); -extern void rt_mutex_adjust_pi(struct task_struct *p); -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return tsk->pi_blocked_on != NULL; -} -#else -static inline int rt_mutex_getprio(struct task_struct *p) -{ - return p->normal_prio; -} -# define rt_mutex_adjust_pi(p) do { } while (0) -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return false; -} -#endif - extern bool yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); @@ -2753,14 +2654,15 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); -extern void normalize_rt_tasks(void); - #ifdef CONFIG_CGROUP_SCHED extern struct task_group root_task_group; extern struct task_group *sched_create_group(struct task_group *parent); +extern void sched_online_group(struct task_group *tg, + struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); +extern void sched_offline_group(struct task_group *tg); extern void sched_move_task(struct task_struct *tsk); #ifdef CONFIG_FAIR_GROUP_SCHED extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h new file mode 100644 index 0000000..94e19ea --- /dev/null +++ b/include/linux/sched/rt.h @@ -0,0 +1,58 @@ +#ifndef _SCHED_RT_H +#define _SCHED_RT_H + +/* + * Priority of a process goes from 0..MAX_PRIO-1, valid RT + * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH + * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority + * values are inverted: lower p->prio value means higher priority. + * + * The MAX_USER_RT_PRIO value allows the actual maximum + * RT priority to be separate from the value exported to + * user-space. This allows kernel threads to set their + * priority to a value higher than any user task. Note: + * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. + */ + +#define MAX_USER_RT_PRIO 100 +#define MAX_RT_PRIO MAX_USER_RT_PRIO + +#define MAX_PRIO (MAX_RT_PRIO + 40) +#define DEFAULT_PRIO (MAX_RT_PRIO + 20) + +static inline int rt_prio(int prio) +{ + if (unlikely(prio < MAX_RT_PRIO)) + return 1; + return 0; +} + +static inline int rt_task(struct task_struct *p) +{ + return rt_prio(p->prio); +} + +#ifdef CONFIG_RT_MUTEXES +extern int rt_mutex_getprio(struct task_struct *p); +extern void rt_mutex_setprio(struct task_struct *p, int prio); +extern void rt_mutex_adjust_pi(struct task_struct *p); +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return tsk->pi_blocked_on != NULL; +} +#else +static inline int rt_mutex_getprio(struct task_struct *p) +{ + return p->normal_prio; +} +# define rt_mutex_adjust_pi(p) do { } while (0) +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return false; +} +#endif + +extern void normalize_rt_tasks(void); + + +#endif /* _SCHED_RT_H */ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h new file mode 100644 index 0000000..d2bb0ae --- /dev/null +++ b/include/linux/sched/sysctl.h @@ -0,0 +1,110 @@ +#ifndef _SCHED_SYSCTL_H +#define _SCHED_SYSCTL_H + +#ifdef CONFIG_DETECT_HUNG_TASK +extern unsigned int sysctl_hung_task_panic; +extern unsigned long sysctl_hung_task_check_count; +extern unsigned long sysctl_hung_task_timeout_secs; +extern unsigned long sysctl_hung_task_warnings; +extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos); +#else +/* Avoid need for ifdefs elsewhere in the code */ +enum { sysctl_hung_task_timeout_secs = 0 }; +#endif + +/* + * Default maximum number of active map areas, this limits the number of vmas + * per mm struct. Users can overwrite this number by sysctl but there is a + * problem. + * + * When a program's coredump is generated as ELF format, a section is created + * per a vma. In ELF, the number of sections is represented in unsigned short. + * This means the number of sections should be smaller than 65535 at coredump. + * Because the kernel adds some informative sections to a image of program at + * generating coredump, we need some margin. The number of extra sections is + * 1-3 now and depends on arch. We use "5" as safe margin, here. + */ +#define MAPCOUNT_ELF_CORE_MARGIN (5) +#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) + +extern int sysctl_max_map_count; + +extern unsigned int sysctl_sched_latency; +extern unsigned int sysctl_sched_min_granularity; +extern unsigned int sysctl_sched_wakeup_granularity; +extern unsigned int sysctl_sched_child_runs_first; + +enum sched_tunable_scaling { + SCHED_TUNABLESCALING_NONE, + SCHED_TUNABLESCALING_LOG, + SCHED_TUNABLESCALING_LINEAR, + SCHED_TUNABLESCALING_END, +}; +extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; + +extern unsigned int sysctl_numa_balancing_scan_delay; +extern unsigned int sysctl_numa_balancing_scan_period_min; +extern unsigned int sysctl_numa_balancing_scan_period_max; +extern unsigned int sysctl_numa_balancing_scan_period_reset; +extern unsigned int sysctl_numa_balancing_scan_size; +extern unsigned int sysctl_numa_balancing_settle_count; + +#ifdef CONFIG_SCHED_DEBUG +extern unsigned int sysctl_sched_migration_cost; +extern unsigned int sysctl_sched_nr_migrate; +extern unsigned int sysctl_sched_time_avg; +extern unsigned int sysctl_timer_migration; +extern unsigned int sysctl_sched_shares_window; + +int sched_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, + loff_t *ppos); +#endif +#ifdef CONFIG_SCHED_DEBUG +static inline unsigned int get_sysctl_timer_migration(void) +{ + return sysctl_timer_migration; +} +#else +static inline unsigned int get_sysctl_timer_migration(void) +{ + return 1; +} +#endif + +/* + * control realtime throttling: + * + * /proc/sys/kernel/sched_rt_period_us + * /proc/sys/kernel/sched_rt_runtime_us + */ +extern unsigned int sysctl_sched_rt_period; +extern int sysctl_sched_rt_runtime; + +#ifdef CONFIG_CFS_BANDWIDTH +extern unsigned int sysctl_sched_cfs_bandwidth_slice; +#endif + +#ifdef CONFIG_SCHED_AUTOGROUP +extern unsigned int sysctl_sched_autogroup_enabled; +#endif + +/* + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define RR_TIMESLICE (100 * HZ / 1000) + +extern int sched_rr_timeslice; + +extern int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); + +extern int sched_rt_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); + +#endif /* _SCHED_SYSCTL_H */ diff --git a/include/linux/security.h b/include/linux/security.h index 0f6afc6..eee7478 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -989,17 +989,29 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * tells the LSM to decrement the number of secmark labeling rules loaded * @req_classify_flow: * Sets the flow's sid to the openreq sid. + * @tun_dev_alloc_security: + * This hook allows a module to allocate a security structure for a TUN + * device. + * @security pointer to a security structure pointer. + * Returns a zero on success, negative values on failure. + * @tun_dev_free_security: + * This hook allows a module to free the security structure for a TUN + * device. + * @security pointer to the TUN device's security structure * @tun_dev_create: * Check permissions prior to creating a new TUN device. - * @tun_dev_post_create: - * This hook allows a module to update or allocate a per-socket security - * structure. - * @sk contains the newly created sock structure. + * @tun_dev_attach_queue: + * Check permissions prior to attaching to a TUN device queue. + * @security pointer to the TUN device's security structure. * @tun_dev_attach: - * Check permissions prior to attaching to a persistent TUN device. This - * hook can also be used by the module to update any security state + * This hook can be used by the module to update any security state * associated with the TUN device's sock structure. * @sk contains the existing sock structure. + * @security pointer to the TUN device's security structure. + * @tun_dev_open: + * This hook can be used by the module to update any security state + * associated with the TUN device's security structure. + * @security pointer to the TUN devices's security structure. * * Security hooks for XFRM operations. * @@ -1620,9 +1632,12 @@ struct security_operations { void (*secmark_refcount_inc) (void); void (*secmark_refcount_dec) (void); void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl); - int (*tun_dev_create)(void); - void (*tun_dev_post_create)(struct sock *sk); - int (*tun_dev_attach)(struct sock *sk); + int (*tun_dev_alloc_security) (void **security); + void (*tun_dev_free_security) (void *security); + int (*tun_dev_create) (void); + int (*tun_dev_attach_queue) (void *security); + int (*tun_dev_attach) (struct sock *sk, void *security); + int (*tun_dev_open) (void *security); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2566,9 +2581,12 @@ void security_inet_conn_established(struct sock *sk, int security_secmark_relabel_packet(u32 secid); void security_secmark_refcount_inc(void); void security_secmark_refcount_dec(void); +int security_tun_dev_alloc_security(void **security); +void security_tun_dev_free_security(void *security); int security_tun_dev_create(void); -void security_tun_dev_post_create(struct sock *sk); -int security_tun_dev_attach(struct sock *sk); +int security_tun_dev_attach_queue(void *security); +int security_tun_dev_attach(struct sock *sk, void *security); +int security_tun_dev_open(void *security); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -2733,16 +2751,31 @@ static inline void security_secmark_refcount_dec(void) { } +static inline int security_tun_dev_alloc_security(void **security) +{ + return 0; +} + +static inline void security_tun_dev_free_security(void *security) +{ +} + static inline int security_tun_dev_create(void) { return 0; } -static inline void security_tun_dev_post_create(struct sock *sk) +static inline int security_tun_dev_attach_queue(void *security) +{ + return 0; +} + +static inline int security_tun_dev_attach(struct sock *sk, void *security) { + return 0; } -static inline int security_tun_dev_attach(struct sock *sk) +static inline int security_tun_dev_open(void *security) { return 0; } diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index e0106d8..c65dee0 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -14,6 +14,8 @@ struct smpboot_thread_data; * @thread_should_run: Check whether the thread should run or not. Called with * preemption disabled. * @thread_fn: The associated thread function + * @create: Optional setup function, called when the thread gets + * created (Not called from the thread context) * @setup: Optional setup function, called when the thread gets * operational the first time * @cleanup: Optional cleanup function, called when the thread @@ -22,6 +24,7 @@ struct smpboot_thread_data; * parked (cpu offline) * @unpark: Optional unpark function, called when the thread is * unparked (cpu online) + * @selfparking: Thread is not parked by the park function. * @thread_comm: The base name of the thread */ struct smp_hotplug_thread { @@ -29,10 +32,12 @@ struct smp_hotplug_thread { struct list_head list; int (*thread_should_run)(unsigned int cpu); void (*thread_fn)(unsigned int cpu); + void (*create)(unsigned int cpu); void (*setup)(unsigned int cpu); void (*cleanup)(unsigned int cpu, bool online); void (*park)(unsigned int cpu); void (*unpark)(unsigned int cpu); + bool selfparking; const char *thread_comm; }; diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 6eb691b..04f4121 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -151,30 +151,14 @@ void srcu_barrier(struct srcu_struct *sp); * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * - * Note that if the CPU is in the idle loop from an RCU point of view - * (ie: that we are in the section between rcu_idle_enter() and - * rcu_idle_exit()) then srcu_read_lock_held() returns false even if - * the CPU did an srcu_read_lock(). The reason for this is that RCU - * ignores CPUs that are in such a section, considering these as in - * extended quiescent state, so such a CPU is effectively never in an - * RCU read-side critical section regardless of what RCU primitives it - * invokes. This state of affairs is required --- we need to keep an - * RCU-free window in idle where the CPU may possibly enter into low - * power mode. This way we can notice an extended quiescent state to - * other CPUs that started a grace period. Otherwise we would delay any - * grace period as long as we run in the idle task. - * - * Similarly, we avoid claiming an SRCU read lock held if the current - * CPU is offline. + * Note that SRCU is based on its own statemachine and it doesn't + * relies on normal RCU, it can be called from the CPU which + * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(struct srcu_struct *sp) { if (!debug_lockdep_rcu_enabled()) return 1; - if (rcu_is_cpu_idle()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; return lock_is_held(&sp->dep_map); } @@ -236,8 +220,6 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) int retval = __srcu_read_lock(sp); rcu_lock_acquire(&(sp)->dep_map); - rcu_lockdep_assert(!rcu_is_cpu_idle(), - "srcu_read_lock() used illegally while idle"); return retval; } @@ -251,8 +233,6 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp) { - rcu_lockdep_assert(!rcu_is_cpu_idle(), - "srcu_read_unlock() used illegally while idle"); rcu_lock_release(&(sp)->dep_map); __srcu_read_unlock(sp, idx); } diff --git a/include/linux/tick.h b/include/linux/tick.h index 1a6567b..553272e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -8,6 +8,8 @@ #include <linux/clockchips.h> #include <linux/irqflags.h> +#include <linux/percpu.h> +#include <linux/hrtimer.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -122,13 +124,26 @@ static inline int tick_oneshot_mode_active(void) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ # ifdef CONFIG_NO_HZ +DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched); + +static inline int tick_nohz_tick_stopped(void) +{ + return __this_cpu_read(tick_cpu_sched.tick_stopped); +} + extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); -# else + +# else /* !CONFIG_NO_HZ */ +static inline int tick_nohz_tick_stopped(void) +{ + return 0; +} + static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } diff --git a/include/linux/time.h b/include/linux/time.h index 4d358e9..a3ab6a8 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -115,8 +115,20 @@ static inline bool timespec_valid_strict(const struct timespec *ts) return true; } +extern bool persistent_clock_exist; + +#ifdef ALWAYS_USE_PERSISTENT_CLOCK +#define has_persistent_clock() true +#else +static inline bool has_persistent_clock(void) +{ + return persistent_clock_exist; +} +#endif + extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); +extern int persistent_clock_is_local; extern int update_persistent_clock(struct timespec now); void timekeeping_init(void); extern int timekeeping_suspended; @@ -158,6 +170,7 @@ extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); extern unsigned int alarm_setitimer(unsigned int seconds); extern int do_getitimer(int which, struct itimerval *value); +extern int __getnstimeofday(struct timespec *tv); extern void getnstimeofday(struct timespec *tv); extern void getrawmonotonic(struct timespec *ts); extern void getnstime_raw_and_real(struct timespec *ts_raw, diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h index 44893e5..3251965 100644 --- a/include/linux/tsacct_kern.h +++ b/include/linux/tsacct_kern.h @@ -23,12 +23,15 @@ static inline void bacct_add_tsk(struct user_namespace *user_ns, #ifdef CONFIG_TASK_XACCT extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p); extern void acct_update_integrals(struct task_struct *tsk); +extern void acct_account_cputime(struct task_struct *tsk); extern void acct_clear_integrals(struct task_struct *tsk); #else static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) {} static inline void acct_update_integrals(struct task_struct *tsk) {} +static inline void acct_account_cputime(struct task_struct *tsk) +{} static inline void acct_clear_integrals(struct task_struct *tsk) {} #endif /* CONFIG_TASK_XACCT */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 4f628a6..02b83db 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -35,13 +35,20 @@ struct inode; # include <asm/uprobes.h> #endif +#define UPROBE_HANDLER_REMOVE 1 +#define UPROBE_HANDLER_MASK 1 + +enum uprobe_filter_ctx { + UPROBE_FILTER_REGISTER, + UPROBE_FILTER_UNREGISTER, + UPROBE_FILTER_MMAP, +}; + struct uprobe_consumer { int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); - /* - * filter is optional; If a filter exists, handler is run - * if and only if filter returns true. - */ - bool (*filter)(struct uprobe_consumer *self, struct task_struct *task); + bool (*filter)(struct uprobe_consumer *self, + enum uprobe_filter_ctx ctx, + struct mm_struct *mm); struct uprobe_consumer *next; }; @@ -94,6 +101,7 @@ extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsign extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool __weak is_swbp_insn(uprobe_opcode_t *insn); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -117,6 +125,11 @@ uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return -ENOSYS; } +static inline int +uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) +{ + return -ENOSYS; +} static inline void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { diff --git a/include/linux/usb.h b/include/linux/usb.h index 689b14b..4d22d0f 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -357,6 +357,8 @@ struct usb_bus { int bandwidth_int_reqs; /* number of Interrupt requests */ int bandwidth_isoc_reqs; /* number of Isoc. requests */ + unsigned resuming_ports; /* bit array: resuming root-hub ports */ + #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE) struct mon_bus *mon_bus; /* non-null when associated */ int monitored; /* non-zero when monitored */ diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 608050b..0a78df5 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -430,6 +430,9 @@ extern void usb_hcd_poll_rh_status(struct usb_hcd *hcd); extern void usb_wakeup_notification(struct usb_device *hdev, unsigned int portnum); +extern void usb_hcd_start_port_resume(struct usb_bus *bus, int portnum); +extern void usb_hcd_end_port_resume(struct usb_bus *bus, int portnum); + /* The D0/D1 toggle bits ... USE WITH CAUTION (they're almost hcd-internal) */ #define usb_gettoggle(dev, ep, out) (((dev)->toggle[out] >> (ep)) & 1) #define usb_dotoggle(dev, ep, out) ((dev)->toggle[out] ^= (1 << (ep))) diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index bd45eb7..0e5ac93 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -33,6 +33,7 @@ struct usbnet { wait_queue_head_t *wait; struct mutex phy_mutex; unsigned char suspend_count; + unsigned char pkt_cnt, pkt_err; /* i/o info: pipes etc */ unsigned in, out; @@ -70,6 +71,7 @@ struct usbnet { # define EVENT_DEV_OPEN 7 # define EVENT_DEVICE_REPORT_IDLE 8 # define EVENT_NO_RUNTIME_PM 9 +# define EVENT_RX_KILL 10 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) @@ -107,6 +109,7 @@ struct driver_info { */ #define FLAG_MULTI_PACKET 0x2000 #define FLAG_RX_ASSEMBLE 0x4000 /* rx packets may span >1 frames */ +#define FLAG_NOARP 0x8000 /* device can't do ARP */ /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); diff --git a/include/linux/vtime.h b/include/linux/vtime.h index ae30ab5..71a5782 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -6,15 +6,46 @@ struct task_struct; #ifdef CONFIG_VIRT_CPU_ACCOUNTING extern void vtime_task_switch(struct task_struct *prev); extern void vtime_account_system(struct task_struct *tsk); -extern void vtime_account_system_irqsafe(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); extern void vtime_account_user(struct task_struct *tsk); -extern void vtime_account(struct task_struct *tsk); -#else +extern void vtime_account_irq_enter(struct task_struct *tsk); + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +static inline bool vtime_accounting_enabled(void) { return true; } +#endif + +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ + static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } -static inline void vtime_account_system_irqsafe(struct task_struct *tsk) { } -static inline void vtime_account(struct task_struct *tsk) { } +static inline void vtime_account_user(struct task_struct *tsk) { } +static inline void vtime_account_irq_enter(struct task_struct *tsk) { } +static inline bool vtime_accounting_enabled(void) { return false; } +#endif + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void arch_vtime_task_switch(struct task_struct *tsk); +extern void vtime_account_irq_exit(struct task_struct *tsk); +extern bool vtime_accounting_enabled(void); +extern void vtime_user_enter(struct task_struct *tsk); +static inline void vtime_user_exit(struct task_struct *tsk) +{ + vtime_account_user(tsk); +} +extern void vtime_guest_enter(struct task_struct *tsk); +extern void vtime_guest_exit(struct task_struct *tsk); +extern void vtime_init_idle(struct task_struct *tsk); +#else +static inline void vtime_account_irq_exit(struct task_struct *tsk) +{ + /* On hard|softirq exit we always account to hard|softirq cputime */ + vtime_account_system(tsk); +} +static inline void vtime_user_enter(struct task_struct *tsk) { } +static inline void vtime_user_exit(struct task_struct *tsk) { } +static inline void vtime_guest_enter(struct task_struct *tsk) { } +static inline void vtime_guest_exit(struct task_struct *tsk) { } +static inline void vtime_init_idle(struct task_struct *tsk) { } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -23,25 +54,15 @@ extern void irqtime_account_irq(struct task_struct *tsk); static inline void irqtime_account_irq(struct task_struct *tsk) { } #endif -static inline void vtime_account_irq_enter(struct task_struct *tsk) +static inline void account_irq_enter_time(struct task_struct *tsk) { - /* - * Hardirq can interrupt idle task anytime. So we need vtime_account() - * that performs the idle check in CONFIG_VIRT_CPU_ACCOUNTING. - * Softirq can also interrupt idle task directly if it calls - * local_bh_enable(). Such case probably don't exist but we never know. - * Ksoftirqd is not concerned because idle time is flushed on context - * switch. Softirqs in the end of hardirqs are also not a problem because - * the idle time is flushed on hardirq time already. - */ - vtime_account(tsk); + vtime_account_irq_enter(tsk); irqtime_account_irq(tsk); } -static inline void vtime_account_irq_exit(struct task_struct *tsk) +static inline void account_irq_exit_time(struct task_struct *tsk) { - /* On hard|softirq exit we always account to hard|softirq cputime */ - vtime_account_system(tsk); + vtime_account_irq_exit(tsk); irqtime_account_irq(tsk); } diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 2b58905..8afab27 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -27,7 +27,7 @@ void delayed_work_timer_fn(unsigned long __data); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ - WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */ + WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ @@ -40,7 +40,7 @@ enum { WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, - WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, + WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, @@ -57,29 +57,36 @@ enum { /* special cpu IDs */ WORK_CPU_UNBOUND = NR_CPUS, - WORK_CPU_NONE = NR_CPUS + 1, - WORK_CPU_LAST = WORK_CPU_NONE, + WORK_CPU_END = NR_CPUS + 1, /* - * Reserve 7 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 256 bytes and allows 15 - * workqueue flush colors. + * Reserve 7 bits off of pwq pointer w/ debugobjects turned off. + * This makes pwqs aligned to 256 bytes and allows 15 workqueue + * flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, - /* data contains off-queue information when !WORK_STRUCT_CWQ */ + /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_FLAG_BITS, WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE), + /* + * When a work item is off queue, its high bits point to the last + * pool it was on. Cap at 31 bits and use the highest number to + * indicate that no pool is associated. + */ WORK_OFFQ_FLAG_BITS = 1, - WORK_OFFQ_CPU_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, + WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, + WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, /* convenience constants */ WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_CPU = (unsigned long)WORK_CPU_NONE << WORK_OFFQ_CPU_SHIFT, + WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -95,13 +102,16 @@ struct work_struct { #endif }; -#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU) +#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ - ATOMIC_LONG_INIT(WORK_STRUCT_NO_CPU | WORK_STRUCT_STATIC) + ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC) struct delayed_work { struct work_struct work; struct timer_list timer; + + /* target workqueue and CPU ->timer uses to queue ->work */ + struct workqueue_struct *wq; int cpu; }; @@ -426,7 +436,6 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq); -extern unsigned int work_cpu(struct work_struct *work); extern unsigned int work_busy(struct work_struct *work); /* diff --git a/include/net/ip.h b/include/net/ip.h index 0707fb9..a68f838 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -143,6 +143,8 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) extern int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +extern void ip4_datagram_release_cb(struct sock *sk); + struct ip_reply_arg { struct kvec iov[1]; int flags; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index d8f5b9f..e98aeb3 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -31,6 +31,8 @@ extern void nf_conntrack_cleanup(struct net *net); extern int nf_conntrack_proto_init(struct net *net); extern void nf_conntrack_proto_fini(struct net *net); +extern void nf_conntrack_cleanup_end(void); + extern bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 498433d..938b7fd 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -34,17 +34,17 @@ extern int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); -extern int datagram_recv_ctl(struct sock *sk, - struct msghdr *msg, - struct sk_buff *skb); - -extern int datagram_send_ctl(struct net *net, - struct sock *sk, - struct msghdr *msg, - struct flowi6 *fl6, - struct ipv6_txoptions *opt, - int *hlimit, int *tclass, - int *dontfrag); +extern int ip6_datagram_recv_ctl(struct sock *sk, + struct msghdr *msg, + struct sk_buff *skb); + +extern int ip6_datagram_send_ctl(struct net *net, + struct sock *sk, + struct msghdr *msg, + struct flowi6 *fl6, + struct ipv6_txoptions *opt, + int *hlimit, int *tclass, + int *dontfrag); #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006) diff --git a/include/trace/events/ras.h b/include/trace/events/ras.h new file mode 100644 index 0000000..88b8783 --- /dev/null +++ b/include/trace/events/ras.h @@ -0,0 +1,77 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ras + +#if !defined(_TRACE_AER_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_AER_H + +#include <linux/tracepoint.h> +#include <linux/edac.h> + + +/* + * PCIe AER Trace event + * + * These events are generated when hardware detects a corrected or + * uncorrected event on a PCIe device. The event report has + * the following structure: + * + * char * dev_name - The name of the slot where the device resides + * ([domain:]bus:device.function). + * u32 status - Either the correctable or uncorrectable register + * indicating what error or errors have been seen + * u8 severity - error severity 0:NONFATAL 1:FATAL 2:CORRECTED + */ + +#define aer_correctable_errors \ + {BIT(0), "Receiver Error"}, \ + {BIT(6), "Bad TLP"}, \ + {BIT(7), "Bad DLLP"}, \ + {BIT(8), "RELAY_NUM Rollover"}, \ + {BIT(12), "Replay Timer Timeout"}, \ + {BIT(13), "Advisory Non-Fatal"} + +#define aer_uncorrectable_errors \ + {BIT(4), "Data Link Protocol"}, \ + {BIT(12), "Poisoned TLP"}, \ + {BIT(13), "Flow Control Protocol"}, \ + {BIT(14), "Completion Timeout"}, \ + {BIT(15), "Completer Abort"}, \ + {BIT(16), "Unexpected Completion"}, \ + {BIT(17), "Receiver Overflow"}, \ + {BIT(18), "Malformed TLP"}, \ + {BIT(19), "ECRC"}, \ + {BIT(20), "Unsupported Request"} + +TRACE_EVENT(aer_event, + TP_PROTO(const char *dev_name, + const u32 status, + const u8 severity), + + TP_ARGS(dev_name, status, severity), + + TP_STRUCT__entry( + __string( dev_name, dev_name ) + __field( u32, status ) + __field( u8, severity ) + ), + + TP_fast_assign( + __assign_str(dev_name, dev_name); + __entry->status = status; + __entry->severity = severity; + ), + + TP_printk("%s PCIe Bus Error: severity=%s, %s\n", + __get_str(dev_name), + __entry->severity == HW_EVENT_ERR_CORRECTED ? "Corrected" : + __entry->severity == HW_EVENT_ERR_FATAL ? + "Fatal" : "Uncorrected", + __entry->severity == HW_EVENT_ERR_CORRECTED ? + __print_flags(__entry->status, "|", aer_correctable_errors) : + __print_flags(__entry->status, "|", aer_uncorrectable_errors)) +); + +#endif /* _TRACE_AER_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index d4f559b..1918e83 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -44,8 +44,10 @@ TRACE_EVENT(rcu_utilization, * of a new grace period or the end of an old grace period ("cpustart" * and "cpuend", respectively), a CPU passing through a quiescent * state ("cpuqs"), a CPU coming online or going offline ("cpuonl" - * and "cpuofl", respectively), and a CPU being kicked for being too - * long in dyntick-idle mode ("kick"). + * and "cpuofl", respectively), a CPU being kicked for being too + * long in dyntick-idle mode ("kick"), a CPU accelerating its new + * callbacks to RCU_NEXT_READY_TAIL ("AccReadyCB"), and a CPU + * accelerating its new callbacks to RCU_WAIT_TAIL ("AccWaitCB"). */ TRACE_EVENT(rcu_grace_period, @@ -393,7 +395,7 @@ TRACE_EVENT(rcu_kfree_callback, */ TRACE_EVENT(rcu_batch_start, - TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit), + TP_PROTO(char *rcuname, long qlen_lazy, long qlen, long blimit), TP_ARGS(rcuname, qlen_lazy, qlen, blimit), @@ -401,7 +403,7 @@ TRACE_EVENT(rcu_batch_start, __field(char *, rcuname) __field(long, qlen_lazy) __field(long, qlen) - __field(int, blimit) + __field(long, blimit) ), TP_fast_assign( @@ -411,7 +413,7 @@ TRACE_EVENT(rcu_batch_start, __entry->blimit = blimit; ), - TP_printk("%s CBs=%ld/%ld bl=%d", + TP_printk("%s CBs=%ld/%ld bl=%ld", __entry->rcuname, __entry->qlen_lazy, __entry->qlen, __entry->blimit) ); @@ -523,22 +525,30 @@ TRACE_EVENT(rcu_batch_end, */ TRACE_EVENT(rcu_torture_read, - TP_PROTO(char *rcutorturename, struct rcu_head *rhp), + TP_PROTO(char *rcutorturename, struct rcu_head *rhp, + unsigned long secs, unsigned long c_old, unsigned long c), - TP_ARGS(rcutorturename, rhp), + TP_ARGS(rcutorturename, rhp, secs, c_old, c), TP_STRUCT__entry( __field(char *, rcutorturename) __field(struct rcu_head *, rhp) + __field(unsigned long, secs) + __field(unsigned long, c_old) + __field(unsigned long, c) ), TP_fast_assign( __entry->rcutorturename = rcutorturename; __entry->rhp = rhp; + __entry->secs = secs; + __entry->c_old = c_old; + __entry->c = c; ), - TP_printk("%s torture read %p", - __entry->rcutorturename, __entry->rhp) + TP_printk("%s torture read %p %luus c: %lu %lu", + __entry->rcutorturename, __entry->rhp, + __entry->secs, __entry->c_old, __entry->c) ); /* @@ -608,7 +618,8 @@ TRACE_EVENT(rcu_barrier, #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0) #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ do { } while (0) -#define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) #define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0) #endif /* #else #ifdef CONFIG_RCU_TRACE */ diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index f28d1b6..bf0e18b 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -27,7 +27,7 @@ DECLARE_EVENT_CLASS(workqueue_work, /** * workqueue_queue_work - called when a work gets queued * @req_cpu: the requested cpu - * @cwq: pointer to struct cpu_workqueue_struct + * @pwq: pointer to struct pool_workqueue * @work: pointer to struct work_struct * * This event occurs when a work is queued immediately or once a @@ -36,10 +36,10 @@ DECLARE_EVENT_CLASS(workqueue_work, */ TRACE_EVENT(workqueue_queue_work, - TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq, + TP_PROTO(unsigned int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), - TP_ARGS(req_cpu, cwq, work), + TP_ARGS(req_cpu, pwq, work), TP_STRUCT__entry( __field( void *, work ) @@ -52,9 +52,9 @@ TRACE_EVENT(workqueue_queue_work, TP_fast_assign( __entry->work = work; __entry->function = work->func; - __entry->workqueue = cwq->wq; + __entry->workqueue = pwq->wq; __entry->req_cpu = req_cpu; - __entry->cpu = cwq->pool->gcwq->cpu; + __entry->cpu = pwq->pool->cpu; ), TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u", diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h index 77cdba9..bb991df 100644 --- a/include/uapi/linux/auto_fs.h +++ b/include/uapi/linux/auto_fs.h @@ -28,25 +28,16 @@ #define AUTOFS_MIN_PROTO_VERSION AUTOFS_PROTO_VERSION /* - * Architectures where both 32- and 64-bit binaries can be executed - * on 64-bit kernels need this. This keeps the structure format - * uniform, and makes sure the wait_queue_token isn't too big to be - * passed back down to the kernel. - * - * This assumes that on these architectures: - * mode 32 bit 64 bit - * ------------------------- - * int 32 bit 32 bit - * long 32 bit 64 bit - * - * If so, 32-bit user-space code should be backwards compatible. + * The wait_queue_token (autofs_wqt_t) is part of a structure which is passed + * back to the kernel via ioctl from userspace. On architectures where 32- and + * 64-bit userspace binaries can be executed it's important that the size of + * autofs_wqt_t stays constant between 32- and 64-bit Linux kernels so that we + * do not break the binary ABI interface by changing the structure size. */ - -#if defined(__sparc__) || defined(__mips__) || defined(__x86_64__) \ - || defined(__powerpc__) || defined(__s390__) -typedef unsigned int autofs_wqt_t; -#else +#if defined(__ia64__) || defined(__alpha__) /* pure 64bit architectures */ typedef unsigned long autofs_wqt_t; +#else +typedef unsigned int autofs_wqt_t; #endif /* Packet types */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 4f63c05..9fa9c62 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -579,7 +579,8 @@ enum perf_event_type { * { u32 size; * char data[size];}&& PERF_SAMPLE_RAW * - * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK + * { u64 nr; + * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK * * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 5059847..f738e25 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -152,6 +152,12 @@ #define USB_INTRF_FUNC_SUSPEND_LP (1 << (8 + 0)) #define USB_INTRF_FUNC_SUSPEND_RW (1 << (8 + 1)) +/* + * Interface status, Figure 9-5 USB 3.0 spec + */ +#define USB_INTRF_STAT_FUNC_RW_CAP 1 +#define USB_INTRF_STAT_FUNC_RW 2 + #define USB_ENDPOINT_HALT 0 /* IN/OUT will STALL */ /* Bit array elements as returned by the USB_REQ_GET_STATUS request. */ diff --git a/init/Kconfig b/init/Kconfig index be8b7f5..7000d96 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -20,12 +20,8 @@ config CONSTRUCTORS bool depends on !UML -config HAVE_IRQ_WORK - bool - config IRQ_WORK bool - depends on HAVE_IRQ_WORK config BUILDTIME_EXTABLE_SORT bool @@ -326,10 +322,13 @@ source "kernel/time/Kconfig" menu "CPU/Task time and stats accounting" +config VIRT_CPU_ACCOUNTING + bool + choice prompt "Cputime accounting" default TICK_CPU_ACCOUNTING if !PPC64 - default VIRT_CPU_ACCOUNTING if PPC64 + default VIRT_CPU_ACCOUNTING_NATIVE if PPC64 # Kind of a stub config for the pure tick based cputime accounting config TICK_CPU_ACCOUNTING @@ -342,9 +341,10 @@ config TICK_CPU_ACCOUNTING If unsure, say Y. -config VIRT_CPU_ACCOUNTING +config VIRT_CPU_ACCOUNTING_NATIVE bool "Deterministic task and CPU time accounting" depends on HAVE_VIRT_CPU_ACCOUNTING + select VIRT_CPU_ACCOUNTING help Select this option to enable more accurate task and CPU time accounting. This is done by reading a CPU counter on each @@ -354,6 +354,23 @@ config VIRT_CPU_ACCOUNTING this also enables accounting of stolen time on logically-partitioned systems. +config VIRT_CPU_ACCOUNTING_GEN + bool "Full dynticks CPU time accounting" + depends on HAVE_CONTEXT_TRACKING && 64BIT + select VIRT_CPU_ACCOUNTING + select CONTEXT_TRACKING + help + Select this option to enable task and CPU time accounting on full + dynticks systems. This accounting is implemented by watching every + kernel-user boundaries using the context tracking subsystem. + The accounting is thus performed at the expense of some significant + overhead. + + For now this is only useful if you are working on the full + dynticks subsystem development. + + If unsure, say N. + config IRQ_TIME_ACCOUNTING bool "Fine granularity task level IRQ time accounting" depends on HAVE_IRQ_TIME_ACCOUNTING @@ -453,7 +470,7 @@ config TREE_RCU config TREE_PREEMPT_RCU bool "Preemptible tree-based hierarchical RCU" - depends on PREEMPT && SMP + depends on PREEMPT help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -461,6 +478,8 @@ config TREE_PREEMPT_RCU is also required. It also scales down nicely to smaller systems. + Select this option if you are unsure. + config TINY_RCU bool "UP-only small-memory-footprint RCU" depends on !PREEMPT && !SMP @@ -486,6 +505,14 @@ config PREEMPT_RCU This option enables preemptible-RCU code that is common between the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. +config RCU_STALL_COMMON + def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) + help + This option enables RCU CPU stall code that is common between + the TINY and TREE variants of RCU. The purpose is to allow + the tiny variants to disable RCU CPU stall warnings, while + making these warnings mandatory for the tree variants. + config CONTEXT_TRACKING bool @@ -1263,6 +1290,7 @@ config HOTPLUG config PRINTK default y bool "Enable support for printk" if EXPERT + select IRQ_WORK help This option enables normal printk support. Removing it eliminates most of the message strings from the kernel image diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index f9acf71..a32ec1c 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -61,6 +61,9 @@ static void __init handle_initrd(void) sys_mkdir("/old", 0700); sys_chdir("/old"); + /* try loading default modules from initrd */ + load_default_modules(); + /* * In case that a resume from disk is carried out by linuxrc or one of * its children, we need to tell the freezer not to wait for us. diff --git a/init/init_task.c b/init/init_task.c index 8b2f399..ba0a7f36 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -2,6 +2,8 @@ #include <linux/export.h> #include <linux/mqueue.h> #include <linux/sched.h> +#include <linux/sched/sysctl.h> +#include <linux/sched/rt.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mm.h> diff --git a/init/initramfs.c b/init/initramfs.c index 84c6bf1..a67ef9d 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -592,7 +592,7 @@ static int __init populate_rootfs(void) initrd_end - initrd_start); if (!err) { free_initrd(); - return 0; + goto done; } else { clean_rootfs(); unpack_to_rootfs(__initramfs_start, __initramfs_size); @@ -607,6 +607,7 @@ static int __init populate_rootfs(void) sys_close(fd); free_initrd(); } + done: #else printk(KERN_INFO "Unpacking initramfs...\n"); err = unpack_to_rootfs((char *)initrd_start, @@ -615,6 +616,11 @@ static int __init populate_rootfs(void) printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); free_initrd(); #endif + /* + * Try loading default modules from initramfs. This gives + * us a chance to load before device_initcalls. + */ + load_default_modules(); } return 0; } diff --git a/init/main.c b/init/main.c index 92d728a..63534a1 100644 --- a/init/main.c +++ b/init/main.c @@ -70,6 +70,8 @@ #include <linux/perf_event.h> #include <linux/file.h> #include <linux/ptrace.h> +#include <linux/blkdev.h> +#include <linux/elevator.h> #include <asm/io.h> #include <asm/bugs.h> @@ -604,7 +606,7 @@ asmlinkage void __init start_kernel(void) pidmap_init(); anon_vma_init(); #ifdef CONFIG_X86 - if (efi_enabled) + if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif thread_info_cache_init(); @@ -632,7 +634,7 @@ asmlinkage void __init start_kernel(void) acpi_early_init(); /* before LAPIC and SMP init */ sfi_init_late(); - if (efi_enabled) { + if (efi_enabled(EFI_RUNTIME_SERVICES)) { efi_late_init(); efi_free_boot_services(); } @@ -794,6 +796,17 @@ static void __init do_pre_smp_initcalls(void) do_one_initcall(*fn); } +/* + * This function requests modules which should be loaded by default and is + * called twice right after initrd is mounted and right before init is + * exec'd. If such modules are on either initrd or rootfs, they will be + * loaded before control is passed to userland. + */ +void __init load_default_modules(void) +{ + load_default_elevator_module(); +} + static int run_init_process(const char *init_filename) { argv_init[0] = init_filename; @@ -900,4 +913,7 @@ static noinline void __init kernel_init_freeable(void) * we're essentially up and running. Get rid of the * initmem segments and start the user-mode stuff.. */ + + /* rootfs is available now, try loading default modules */ + load_default_modules(); } diff --git a/kernel/acct.c b/kernel/acct.c index 051e071..e8b1627 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -566,6 +566,7 @@ out: void acct_collect(long exitcode, int group_dead) { struct pacct_struct *pacct = ¤t->signal->pacct; + cputime_t utime, stime; unsigned long vsize = 0; if (group_dead && current->mm) { @@ -593,8 +594,9 @@ void acct_collect(long exitcode, int group_dead) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; - pacct->ac_utime += current->utime; - pacct->ac_stime += current->stime; + task_cputime(current, &utime, &stime); + pacct->ac_utime += utime; + pacct->ac_stime += stime; pacct->ac_minflt += current->min_flt; pacct->ac_majflt += current->maj_flt; spin_unlock_irq(¤t->sighand->siglock); diff --git a/kernel/async.c b/kernel/async.c index 6f34904..8ddee2c 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -57,65 +57,52 @@ asynchronous and synchronous parts of the kernel. #include <linux/slab.h> #include <linux/workqueue.h> +#include "workqueue_internal.h" + static async_cookie_t next_cookie = 1; -#define MAX_WORK 32768 +#define MAX_WORK 32768 +#define ASYNC_COOKIE_MAX ULLONG_MAX /* infinity cookie */ -static LIST_HEAD(async_pending); -static ASYNC_DOMAIN(async_running); -static LIST_HEAD(async_domains); +static LIST_HEAD(async_global_pending); /* pending from all registered doms */ +static ASYNC_DOMAIN(async_dfl_domain); static DEFINE_SPINLOCK(async_lock); -static DEFINE_MUTEX(async_register_mutex); struct async_entry { - struct list_head list; + struct list_head domain_list; + struct list_head global_list; struct work_struct work; async_cookie_t cookie; async_func_ptr *func; void *data; - struct async_domain *running; + struct async_domain *domain; }; static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; - -/* - * MUST be called with the lock held! - */ -static async_cookie_t __lowest_in_progress(struct async_domain *running) +static async_cookie_t lowest_in_progress(struct async_domain *domain) { - async_cookie_t first_running = next_cookie; /* infinity value */ - async_cookie_t first_pending = next_cookie; /* ditto */ - struct async_entry *entry; + struct async_entry *first = NULL; + async_cookie_t ret = ASYNC_COOKIE_MAX; + unsigned long flags; - /* - * Both running and pending lists are sorted but not disjoint. - * Take the first cookies from both and return the min. - */ - if (!list_empty(&running->domain)) { - entry = list_first_entry(&running->domain, typeof(*entry), list); - first_running = entry->cookie; - } + spin_lock_irqsave(&async_lock, flags); - list_for_each_entry(entry, &async_pending, list) { - if (entry->running == running) { - first_pending = entry->cookie; - break; - } + if (domain) { + if (!list_empty(&domain->pending)) + first = list_first_entry(&domain->pending, + struct async_entry, domain_list); + } else { + if (!list_empty(&async_global_pending)) + first = list_first_entry(&async_global_pending, + struct async_entry, global_list); } - return min(first_running, first_pending); -} - -static async_cookie_t lowest_in_progress(struct async_domain *running) -{ - unsigned long flags; - async_cookie_t ret; + if (first) + ret = first->cookie; - spin_lock_irqsave(&async_lock, flags); - ret = __lowest_in_progress(running); spin_unlock_irqrestore(&async_lock, flags); return ret; } @@ -127,20 +114,10 @@ static void async_run_entry_fn(struct work_struct *work) { struct async_entry *entry = container_of(work, struct async_entry, work); - struct async_entry *pos; unsigned long flags; ktime_t uninitialized_var(calltime), delta, rettime; - struct async_domain *running = entry->running; - /* 1) move self to the running queue, make sure it stays sorted */ - spin_lock_irqsave(&async_lock, flags); - list_for_each_entry_reverse(pos, &running->domain, list) - if (entry->cookie < pos->cookie) - break; - list_move_tail(&entry->list, &pos->list); - spin_unlock_irqrestore(&async_lock, flags); - - /* 2) run (and print duration) */ + /* 1) run (and print duration) */ if (initcall_debug && system_state == SYSTEM_BOOTING) { printk(KERN_DEBUG "calling %lli_%pF @ %i\n", (long long)entry->cookie, @@ -157,23 +134,22 @@ static void async_run_entry_fn(struct work_struct *work) (long long)ktime_to_ns(delta) >> 10); } - /* 3) remove self from the running queue */ + /* 2) remove self from the pending queues */ spin_lock_irqsave(&async_lock, flags); - list_del(&entry->list); - if (running->registered && --running->count == 0) - list_del_init(&running->node); + list_del_init(&entry->domain_list); + list_del_init(&entry->global_list); - /* 4) free the entry */ + /* 3) free the entry */ kfree(entry); atomic_dec(&entry_count); spin_unlock_irqrestore(&async_lock, flags); - /* 5) wake up any waiters */ + /* 4) wake up any waiters */ wake_up(&async_done); } -static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct async_domain *running) +static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; @@ -196,16 +172,22 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a ptr(data, newcookie); return newcookie; } + INIT_LIST_HEAD(&entry->domain_list); + INIT_LIST_HEAD(&entry->global_list); INIT_WORK(&entry->work, async_run_entry_fn); entry->func = ptr; entry->data = data; - entry->running = running; + entry->domain = domain; spin_lock_irqsave(&async_lock, flags); + + /* allocate cookie and queue */ newcookie = entry->cookie = next_cookie++; - list_add_tail(&entry->list, &async_pending); - if (running->registered && running->count++ == 0) - list_add_tail(&running->node, &async_domains); + + list_add_tail(&entry->domain_list, &domain->pending); + if (domain->registered) + list_add_tail(&entry->global_list, &async_global_pending); + atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); @@ -228,7 +210,7 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct a */ async_cookie_t async_schedule(async_func_ptr *ptr, void *data) { - return __async_schedule(ptr, data, &async_running); + return __async_schedule(ptr, data, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_schedule); @@ -236,18 +218,18 @@ EXPORT_SYMBOL_GPL(async_schedule); * async_schedule_domain - schedule a function for asynchronous execution within a certain domain * @ptr: function to execute asynchronously * @data: data pointer to pass to the function - * @running: running list for the domain + * @domain: the domain * * Returns an async_cookie_t that may be used for checkpointing later. - * @running may be used in the async_synchronize_*_domain() functions - * to wait within a certain synchronization domain rather than globally. - * A synchronization domain is specified via the running queue @running to use. - * Note: This function may be called from atomic or non-atomic contexts. + * @domain may be used in the async_synchronize_*_domain() functions to + * wait within a certain synchronization domain rather than globally. A + * synchronization domain is specified via @domain. Note: This function + * may be called from atomic or non-atomic contexts. */ async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data, - struct async_domain *running) + struct async_domain *domain) { - return __async_schedule(ptr, data, running); + return __async_schedule(ptr, data, domain); } EXPORT_SYMBOL_GPL(async_schedule_domain); @@ -258,18 +240,7 @@ EXPORT_SYMBOL_GPL(async_schedule_domain); */ void async_synchronize_full(void) { - mutex_lock(&async_register_mutex); - do { - struct async_domain *domain = NULL; - - spin_lock_irq(&async_lock); - if (!list_empty(&async_domains)) - domain = list_first_entry(&async_domains, typeof(*domain), node); - spin_unlock_irq(&async_lock); - - async_synchronize_cookie_domain(next_cookie, domain); - } while (!list_empty(&async_domains)); - mutex_unlock(&async_register_mutex); + async_synchronize_full_domain(NULL); } EXPORT_SYMBOL_GPL(async_synchronize_full); @@ -284,51 +255,45 @@ EXPORT_SYMBOL_GPL(async_synchronize_full); */ void async_unregister_domain(struct async_domain *domain) { - mutex_lock(&async_register_mutex); spin_lock_irq(&async_lock); - WARN_ON(!domain->registered || !list_empty(&domain->node) || - !list_empty(&domain->domain)); + WARN_ON(!domain->registered || !list_empty(&domain->pending)); domain->registered = 0; spin_unlock_irq(&async_lock); - mutex_unlock(&async_register_mutex); } EXPORT_SYMBOL_GPL(async_unregister_domain); /** * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain - * @domain: running list to synchronize on + * @domain: the domain to synchronize * * This function waits until all asynchronous function calls for the - * synchronization domain specified by the running list @domain have been done. + * synchronization domain specified by @domain have been done. */ void async_synchronize_full_domain(struct async_domain *domain) { - async_synchronize_cookie_domain(next_cookie, domain); + async_synchronize_cookie_domain(ASYNC_COOKIE_MAX, domain); } EXPORT_SYMBOL_GPL(async_synchronize_full_domain); /** * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint - * @running: running list to synchronize on + * @domain: the domain to synchronize (%NULL for all registered domains) * * This function waits until all asynchronous function calls for the - * synchronization domain specified by running list @running submitted - * prior to @cookie have been done. + * synchronization domain specified by @domain submitted prior to @cookie + * have been done. */ -void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *running) +void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) { ktime_t uninitialized_var(starttime), delta, endtime; - if (!running) - return; - if (initcall_debug && system_state == SYSTEM_BOOTING) { printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); } - wait_event(async_done, lowest_in_progress(running) >= cookie); + wait_event(async_done, lowest_in_progress(domain) >= cookie); if (initcall_debug && system_state == SYSTEM_BOOTING) { endtime = ktime_get(); @@ -350,6 +315,18 @@ EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); */ void async_synchronize_cookie(async_cookie_t cookie) { - async_synchronize_cookie_domain(cookie, &async_running); + async_synchronize_cookie_domain(cookie, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_synchronize_cookie); + +/** + * current_is_async - is %current an async worker task? + * + * Returns %true if %current is an async worker task. + */ +bool current_is_async(void) +{ + struct worker *worker = current_wq_worker(); + + return worker && worker->current_func == async_run_entry_fn; +} diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4855892..b5c6432 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -52,7 +52,7 @@ #include <linux/module.h> #include <linux/delayacct.h> #include <linux/cgroupstats.h> -#include <linux/hash.h> +#include <linux/hashtable.h> #include <linux/namei.h> #include <linux/pid_namespace.h> #include <linux/idr.h> @@ -376,22 +376,18 @@ static int css_set_count; * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 -#define CSS_SET_TABLE_SIZE (1 << CSS_SET_HASH_BITS) -static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE]; +static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); -static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[]) +static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) { int i; - int index; - unsigned long tmp = 0UL; + unsigned long key = 0UL; for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) - tmp += (unsigned long)css[i]; - tmp = (tmp >> 16) ^ tmp; + key += (unsigned long)css[i]; + key = (key >> 16) ^ key; - index = hash_long(tmp, CSS_SET_HASH_BITS); - - return &css_set_table[index]; + return key; } /* We don't maintain the lists running through each css_set to its @@ -418,7 +414,7 @@ static void __put_css_set(struct css_set *cg, int taskexit) } /* This css_set is dead. unlink it and release cgroup refcounts */ - hlist_del(&cg->hlist); + hash_del(&cg->hlist); css_set_count--; list_for_each_entry_safe(link, saved_link, &cg->cg_links, @@ -426,12 +422,20 @@ static void __put_css_set(struct css_set *cg, int taskexit) struct cgroup *cgrp = link->cgrp; list_del(&link->cg_link_list); list_del(&link->cgrp_link_list); + + /* + * We may not be holding cgroup_mutex, and if cgrp->count is + * dropped to 0 the cgroup can be destroyed at any time, hence + * rcu_read_lock is used to keep it alive. + */ + rcu_read_lock(); if (atomic_dec_and_test(&cgrp->count) && notify_on_release(cgrp)) { if (taskexit) set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } + rcu_read_unlock(); kfree(link); } @@ -550,9 +554,9 @@ static struct css_set *find_existing_css_set( { int i; struct cgroupfs_root *root = cgrp->root; - struct hlist_head *hhead; struct hlist_node *node; struct css_set *cg; + unsigned long key; /* * Build the set of subsystem state objects that we want to see in the @@ -572,8 +576,8 @@ static struct css_set *find_existing_css_set( } } - hhead = css_set_hash(template); - hlist_for_each_entry(cg, node, hhead, hlist) { + key = css_set_hash(template); + hash_for_each_possible(css_set_table, cg, node, hlist, key) { if (!compare_css_sets(cg, oldcg, cgrp, template)) continue; @@ -657,8 +661,8 @@ static struct css_set *find_css_set( struct list_head tmp_cg_links; - struct hlist_head *hhead; struct cg_cgroup_link *link; + unsigned long key; /* First see if we already have a cgroup group that matches * the desired set */ @@ -704,8 +708,8 @@ static struct css_set *find_css_set( css_set_count++; /* Add this cgroup group to the hash table */ - hhead = css_set_hash(res->subsys); - hlist_add_head(&res->hlist, hhead); + key = css_set_hash(res->subsys); + hash_add(css_set_table, &res->hlist, key); write_unlock(&css_set_lock); @@ -856,47 +860,54 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb) return inode; } -static void cgroup_diput(struct dentry *dentry, struct inode *inode) +static void cgroup_free_fn(struct work_struct *work) { - /* is dentry a directory ? if so, kfree() associated cgroup */ - if (S_ISDIR(inode->i_mode)) { - struct cgroup *cgrp = dentry->d_fsdata; - struct cgroup_subsys *ss; - BUG_ON(!(cgroup_is_removed(cgrp))); - /* It's possible for external users to be holding css - * reference counts on a cgroup; css_put() needs to - * be able to access the cgroup after decrementing - * the reference count in order to know if it needs to - * queue the cgroup to be handled by the release - * agent */ - synchronize_rcu(); + struct cgroup *cgrp = container_of(work, struct cgroup, free_work); + struct cgroup_subsys *ss; - mutex_lock(&cgroup_mutex); - /* - * Release the subsystem state objects. - */ - for_each_subsys(cgrp->root, ss) - ss->css_free(cgrp); + mutex_lock(&cgroup_mutex); + /* + * Release the subsystem state objects. + */ + for_each_subsys(cgrp->root, ss) + ss->css_free(cgrp); - cgrp->root->number_of_cgroups--; - mutex_unlock(&cgroup_mutex); + cgrp->root->number_of_cgroups--; + mutex_unlock(&cgroup_mutex); - /* - * Drop the active superblock reference that we took when we - * created the cgroup - */ - deactivate_super(cgrp->root->sb); + /* + * Drop the active superblock reference that we took when we + * created the cgroup + */ + deactivate_super(cgrp->root->sb); - /* - * if we're getting rid of the cgroup, refcount should ensure - * that there are no pidlists left. - */ - BUG_ON(!list_empty(&cgrp->pidlists)); + /* + * if we're getting rid of the cgroup, refcount should ensure + * that there are no pidlists left. + */ + BUG_ON(!list_empty(&cgrp->pidlists)); - simple_xattrs_free(&cgrp->xattrs); + simple_xattrs_free(&cgrp->xattrs); - ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id); - kfree_rcu(cgrp, rcu_head); + ida_simple_remove(&cgrp->root->cgroup_ida, cgrp->id); + kfree(cgrp); +} + +static void cgroup_free_rcu(struct rcu_head *head) +{ + struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head); + + schedule_work(&cgrp->free_work); +} + +static void cgroup_diput(struct dentry *dentry, struct inode *inode) +{ + /* is dentry a directory ? if so, kfree() associated cgroup */ + if (S_ISDIR(inode->i_mode)) { + struct cgroup *cgrp = dentry->d_fsdata; + + BUG_ON(!(cgroup_is_removed(cgrp))); + call_rcu(&cgrp->rcu_head, cgroup_free_rcu); } else { struct cfent *cfe = __d_cfe(dentry); struct cgroup *cgrp = dentry->d_parent->d_fsdata; @@ -925,13 +936,17 @@ static void remove_dir(struct dentry *d) dput(parent); } -static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) +static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { struct cfent *cfe; lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex); lockdep_assert_held(&cgroup_mutex); + /* + * If we're doing cleanup due to failure of cgroup_create(), + * the corresponding @cfe may not exist. + */ list_for_each_entry(cfe, &cgrp->files, node) { struct dentry *d = cfe->dentry; @@ -944,9 +959,8 @@ static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) list_del_init(&cfe->node); dput(d); - return 0; + break; } - return -ENOENT; } /** @@ -1083,7 +1097,6 @@ static int rebind_subsystems(struct cgroupfs_root *root, } } root->subsys_mask = root->actual_subsys_mask = final_subsys_mask; - synchronize_rcu(); return 0; } @@ -1393,6 +1406,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->allcg_node); INIT_LIST_HEAD(&cgrp->release_list); INIT_LIST_HEAD(&cgrp->pidlists); + INIT_WORK(&cgrp->free_work, cgroup_free_fn); mutex_init(&cgrp->pidlist_mutex); INIT_LIST_HEAD(&cgrp->event_list); spin_lock_init(&cgrp->event_list_lock); @@ -1597,6 +1611,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, struct cgroupfs_root *existing_root; const struct cred *cred; int i; + struct hlist_node *node; + struct css_set *cg; BUG_ON(sb->s_root != NULL); @@ -1650,14 +1666,8 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, /* Link the top cgroup in this hierarchy into all * the css_set objects */ write_lock(&css_set_lock); - for (i = 0; i < CSS_SET_TABLE_SIZE; i++) { - struct hlist_head *hhead = &css_set_table[i]; - struct hlist_node *node; - struct css_set *cg; - - hlist_for_each_entry(cg, node, hhead, hlist) - link_css_set(&tmp_cg_links, cg, root_cgrp); - } + hash_for_each(css_set_table, i, node, cg, hlist) + link_css_set(&tmp_cg_links, cg, root_cgrp); write_unlock(&css_set_lock); free_cg_links(&tmp_cg_links); @@ -1773,7 +1783,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) rcu_lockdep_assert(rcu_read_lock_held() || cgroup_lock_is_held(), "cgroup_path() called without proper locking"); - if (!dentry || cgrp == dummytop) { + if (cgrp == dummytop) { /* * Inactive subsystems have no dentry for their root * cgroup @@ -1982,7 +1992,6 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) ss->attach(cgrp, &tset); } - synchronize_rcu(); out: if (retval) { for_each_subsys(root, ss) { @@ -2151,7 +2160,6 @@ static int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) /* * step 5: success! and cleanup */ - synchronize_rcu(); retval = 0; out_put_css_set_refs: if (retval) { @@ -2769,14 +2777,14 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent) continue; - if (is_add) + if (is_add) { err = cgroup_add_file(cgrp, subsys, cft); - else - err = cgroup_rm_file(cgrp, cft); - if (err) { - pr_warning("cgroup_addrm_files: failed to %s %s, err=%d\n", - is_add ? "add" : "remove", cft->name, err); + if (err) + pr_warn("cgroup_addrm_files: failed to add %s, err=%d\n", + cft->name, err); ret = err; + } else { + cgroup_rm_file(cgrp, cft); } } return ret; @@ -3017,6 +3025,32 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, } EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre); +/** + * cgroup_rightmost_descendant - return the rightmost descendant of a cgroup + * @pos: cgroup of interest + * + * Return the rightmost descendant of @pos. If there's no descendant, + * @pos is returned. This can be used during pre-order traversal to skip + * subtree of @pos. + */ +struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos) +{ + struct cgroup *last, *tmp; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + do { + last = pos; + /* ->prev isn't RCU safe, walk ->next till the end */ + pos = NULL; + list_for_each_entry_rcu(tmp, &last->children, sibling) + pos = tmp; + } while (pos); + + return last; +} +EXPORT_SYMBOL_GPL(cgroup_rightmost_descendant); + static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos) { struct cgroup *last; @@ -3752,8 +3786,13 @@ static void cgroup_event_remove(struct work_struct *work) remove); struct cgroup *cgrp = event->cgrp; + remove_wait_queue(event->wqh, &event->wait); + event->cft->unregister_event(cgrp, event->cft, event->eventfd); + /* Notify userspace the event is going away. */ + eventfd_signal(event->eventfd, 1); + eventfd_ctx_put(event->eventfd); kfree(event); dput(cgrp->dentry); @@ -3773,15 +3812,25 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode, unsigned long flags = (unsigned long)key; if (flags & POLLHUP) { - __remove_wait_queue(event->wqh, &event->wait); - spin_lock(&cgrp->event_list_lock); - list_del_init(&event->list); - spin_unlock(&cgrp->event_list_lock); /* - * We are in atomic context, but cgroup_event_remove() may - * sleep, so we have to call it in workqueue. + * If the event has been detached at cgroup removal, we + * can simply return knowing the other side will cleanup + * for us. + * + * We can't race against event freeing since the other + * side will require wqh->lock via remove_wait_queue(), + * which we hold. */ - schedule_work(&event->remove); + spin_lock(&cgrp->event_list_lock); + if (!list_empty(&event->list)) { + list_del_init(&event->list); + /* + * We are in atomic context, but cgroup_event_remove() + * may sleep, so we have to call it in workqueue. + */ + schedule_work(&event->remove); + } + spin_unlock(&cgrp->event_list_lock); } return 0; @@ -3807,6 +3856,7 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, const char *buffer) { struct cgroup_event *event = NULL; + struct cgroup *cgrp_cfile; unsigned int efd, cfd; struct file *efile = NULL; struct file *cfile = NULL; @@ -3862,6 +3912,16 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, goto fail; } + /* + * The file to be monitored must be in the same cgroup as + * cgroup.event_control is. + */ + cgrp_cfile = __d_cgrp(cfile->f_dentry->d_parent); + if (cgrp_cfile != cgrp) { + ret = -EINVAL; + goto fail; + } + if (!event->cft->register_event || !event->cft->unregister_event) { ret = -EINVAL; goto fail; @@ -4135,6 +4195,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, init_cgroup_housekeeping(cgrp); + dentry->d_fsdata = cgrp; + cgrp->dentry = dentry; + cgrp->parent = parent; cgrp->root = parent->root; cgrp->top_cgroup = parent->top_cgroup; @@ -4172,8 +4235,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, lockdep_assert_held(&dentry->d_inode->i_mutex); /* allocation complete, commit to creation */ - dentry->d_fsdata = cgrp; - cgrp->dentry = dentry; list_add_tail(&cgrp->allcg_node, &root->allcg_list); list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children); root->number_of_cgroups++; @@ -4340,20 +4401,14 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) /* * Unregister events and notify userspace. * Notify userspace about cgroup removing only after rmdir of cgroup - * directory to avoid race between userspace and kernelspace. Use - * a temporary list to avoid a deadlock with cgroup_event_wake(). Since - * cgroup_event_wake() is called with the wait queue head locked, - * remove_wait_queue() cannot be called while holding event_list_lock. + * directory to avoid race between userspace and kernelspace. */ spin_lock(&cgrp->event_list_lock); - list_splice_init(&cgrp->event_list, &tmp_list); - spin_unlock(&cgrp->event_list_lock); - list_for_each_entry_safe(event, tmp, &tmp_list, list) { + list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) { list_del_init(&event->list); - remove_wait_queue(event->wqh, &event->wait); - eventfd_signal(event->eventfd, 1); schedule_work(&event->remove); } + spin_unlock(&cgrp->event_list_lock); return 0; } @@ -4438,6 +4493,9 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; int i, ret; + struct hlist_node *node, *tmp; + struct css_set *cg; + unsigned long key; /* check name and function validity */ if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN || @@ -4503,23 +4561,17 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) * this is all done under the css_set_lock. */ write_lock(&css_set_lock); - for (i = 0; i < CSS_SET_TABLE_SIZE; i++) { - struct css_set *cg; - struct hlist_node *node, *tmp; - struct hlist_head *bucket = &css_set_table[i], *new_bucket; - - hlist_for_each_entry_safe(cg, node, tmp, bucket, hlist) { - /* skip entries that we already rehashed */ - if (cg->subsys[ss->subsys_id]) - continue; - /* remove existing entry */ - hlist_del(&cg->hlist); - /* set new value */ - cg->subsys[ss->subsys_id] = css; - /* recompute hash and restore entry */ - new_bucket = css_set_hash(cg->subsys); - hlist_add_head(&cg->hlist, new_bucket); - } + hash_for_each_safe(css_set_table, i, node, tmp, cg, hlist) { + /* skip entries that we already rehashed */ + if (cg->subsys[ss->subsys_id]) + continue; + /* remove existing entry */ + hash_del(&cg->hlist); + /* set new value */ + cg->subsys[ss->subsys_id] = css; + /* recompute hash and restore entry */ + key = css_set_hash(cg->subsys); + hash_add(css_set_table, node, key); } write_unlock(&css_set_lock); @@ -4551,7 +4603,6 @@ EXPORT_SYMBOL_GPL(cgroup_load_subsys); void cgroup_unload_subsys(struct cgroup_subsys *ss) { struct cg_cgroup_link *link; - struct hlist_head *hhead; BUG_ON(ss->module == NULL); @@ -4585,11 +4636,12 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) write_lock(&css_set_lock); list_for_each_entry(link, &dummytop->css_sets, cgrp_link_list) { struct css_set *cg = link->cg; + unsigned long key; - hlist_del(&cg->hlist); + hash_del(&cg->hlist); cg->subsys[ss->subsys_id] = NULL; - hhead = css_set_hash(cg->subsys); - hlist_add_head(&cg->hlist, hhead); + key = css_set_hash(cg->subsys); + hash_add(css_set_table, &cg->hlist, key); } write_unlock(&css_set_lock); @@ -4631,9 +4683,6 @@ int __init cgroup_init_early(void) list_add(&init_css_set_link.cg_link_list, &init_css_set.cg_links); - for (i = 0; i < CSS_SET_TABLE_SIZE; i++) - INIT_HLIST_HEAD(&css_set_table[i]); - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; @@ -4667,7 +4716,7 @@ int __init cgroup_init(void) { int err; int i; - struct hlist_head *hhead; + unsigned long key; err = bdi_init(&cgroup_backing_dev_info); if (err) @@ -4686,8 +4735,8 @@ int __init cgroup_init(void) } /* Add init_css_set to the hash table */ - hhead = css_set_hash(init_css_set.subsys); - hlist_add_head(&init_css_set.hlist, hhead); + key = css_set_hash(init_css_set.subsys); + hash_add(css_set_table, &init_css_set.hlist, key); BUG_ON(!init_root_id(&rootnode)); cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj); @@ -4982,8 +5031,7 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) } task_unlock(tsk); - if (cg) - put_css_set_taskexit(cg); + put_css_set_taskexit(cg); } /** diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index e0e07fd..65349f0 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -1,29 +1,41 @@ +/* + * Context tracking: Probe on high level context boundaries such as kernel + * and userspace. This includes syscalls and exceptions entry/exit. + * + * This is used by RCU to remove its dependency on the timer tick while a CPU + * runs in userspace. + * + * Started by Frederic Weisbecker: + * + * Copyright (C) 2012 Red Hat, Inc., Frederic Weisbecker <fweisbec@redhat.com> + * + * Many thanks to Gilad Ben-Yossef, Paul McKenney, Ingo Molnar, Andrew Morton, + * Steven Rostedt, Peter Zijlstra for suggestions and improvements. + * + */ + #include <linux/context_tracking.h> +#include <linux/kvm_host.h> #include <linux/rcupdate.h> #include <linux/sched.h> -#include <linux/percpu.h> #include <linux/hardirq.h> +#include <linux/export.h> -struct context_tracking { - /* - * When active is false, hooks are not set to - * minimize overhead: TIF flags are cleared - * and calls to user_enter/exit are ignored. This - * may be further optimized using static keys. - */ - bool active; - enum { - IN_KERNEL = 0, - IN_USER, - } state; -}; - -static DEFINE_PER_CPU(struct context_tracking, context_tracking) = { +DEFINE_PER_CPU(struct context_tracking, context_tracking) = { #ifdef CONFIG_CONTEXT_TRACKING_FORCE .active = true, #endif }; +/** + * user_enter - Inform the context tracking that the CPU is going to + * enter userspace mode. + * + * This function must be called right before we switch from the kernel + * to userspace, when it's guaranteed the remaining kernel instructions + * to execute won't use any RCU read side critical section because this + * function sets RCU in extended quiescent state. + */ void user_enter(void) { unsigned long flags; @@ -39,40 +51,90 @@ void user_enter(void) if (in_interrupt()) return; + /* Kernel threads aren't supposed to go to userspace */ WARN_ON_ONCE(!current->mm); local_irq_save(flags); if (__this_cpu_read(context_tracking.active) && __this_cpu_read(context_tracking.state) != IN_USER) { - __this_cpu_write(context_tracking.state, IN_USER); + /* + * At this stage, only low level arch entry code remains and + * then we'll run in userspace. We can assume there won't be + * any RCU read-side critical section until the next call to + * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency + * on the tick. + */ + vtime_user_enter(current); rcu_user_enter(); + __this_cpu_write(context_tracking.state, IN_USER); } local_irq_restore(flags); } + +/** + * user_exit - Inform the context tracking that the CPU is + * exiting userspace mode and entering the kernel. + * + * This function must be called after we entered the kernel from userspace + * before any use of RCU read side critical section. This potentially include + * any high level kernel code like syscalls, exceptions, signal handling, etc... + * + * This call supports re-entrancy. This way it can be called from any exception + * handler without needing to know if we came from userspace or not. + */ void user_exit(void) { unsigned long flags; - /* - * Some contexts may involve an exception occuring in an irq, - * leading to that nesting: - * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() - * This would mess up the dyntick_nesting count though. And rcu_irq_*() - * helpers are enough to protect RCU uses inside the exception. So - * just return immediately if we detect we are in an IRQ. - */ if (in_interrupt()) return; local_irq_save(flags); if (__this_cpu_read(context_tracking.state) == IN_USER) { - __this_cpu_write(context_tracking.state, IN_KERNEL); + /* + * We are going to run code that may use RCU. Inform + * RCU core about that (ie: we may need the tick again). + */ rcu_user_exit(); + vtime_user_exit(current); + __this_cpu_write(context_tracking.state, IN_KERNEL); } local_irq_restore(flags); } +void guest_enter(void) +{ + if (vtime_accounting_enabled()) + vtime_guest_enter(current); + else + __guest_enter(); +} +EXPORT_SYMBOL_GPL(guest_enter); + +void guest_exit(void) +{ + if (vtime_accounting_enabled()) + vtime_guest_exit(current); + else + __guest_exit(); +} +EXPORT_SYMBOL_GPL(guest_exit); + + +/** + * context_tracking_task_switch - context switch the syscall callbacks + * @prev: the task that is being switched out + * @next: the task that is being switched in + * + * The context tracking uses the syscall slow path to implement its user-kernel + * boundaries probes on syscalls. This way it doesn't impact the syscall fast + * path on CPUs that don't do context tracking. + * + * But we need to clear the flag on the previous task because it may later + * migrate to some CPU that doesn't do the context tracking. As such the TIF + * flag may not be desired there. + */ void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { diff --git a/kernel/cpu.c b/kernel/cpu.c index 3046a50..b5e4ab2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -224,11 +224,13 @@ void clear_tasks_mm_cpumask(int cpu) static inline void check_for_tasks(int cpu) { struct task_struct *p; + cputime_t utime, stime; write_lock_irq(&tasklist_lock); for_each_process(p) { + task_cputime(p, &utime, &stime); if (task_cpu(p) == cpu && p->state == TASK_RUNNING && - (p->utime || p->stime)) + (utime || stime)) printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d " "(state = %ld, flags = %x)\n", p->comm, task_pid_nr(p), cpu, @@ -254,6 +256,8 @@ static int __ref take_cpu_down(void *_param) return err; cpu_notify(CPU_DYING | param->mod, param->hcpu); + /* Park the stopper thread */ + kthread_park(current); return 0; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 7bb63ee..4f9dfe4 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -61,14 +61,6 @@ #include <linux/cgroup.h> /* - * Workqueue for cpuset related tasks. - * - * Using kevent workqueue may cause deadlock when memory_migrate - * is set. So we create a separate workqueue thread for cpuset. - */ -static struct workqueue_struct *cpuset_wq; - -/* * Tracks how many cpusets are currently defined in system. * When there is only one cpuset (the root cpuset) we can * short circuit some hooks. @@ -95,18 +87,21 @@ struct cpuset { cpumask_var_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */ - struct cpuset *parent; /* my parent */ - struct fmeter fmeter; /* memory_pressure filter */ + /* + * Tasks are being attached to this cpuset. Used to prevent + * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). + */ + int attach_in_progress; + /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; - /* used for walking a cpuset hierarchy */ - struct list_head stack_list; + struct work_struct hotplug_work; }; /* Retrieve the cpuset for a cgroup */ @@ -123,6 +118,15 @@ static inline struct cpuset *task_cs(struct task_struct *task) struct cpuset, css); } +static inline struct cpuset *parent_cs(const struct cpuset *cs) +{ + struct cgroup *pcgrp = cs->css.cgroup->parent; + + if (pcgrp) + return cgroup_cs(pcgrp); + return NULL; +} + #ifdef CONFIG_NUMA static inline bool task_has_mempolicy(struct task_struct *task) { @@ -138,6 +142,7 @@ static inline bool task_has_mempolicy(struct task_struct *task) /* bits in struct cpuset flags field */ typedef enum { + CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, @@ -147,13 +152,12 @@ typedef enum { CS_SPREAD_SLAB, } cpuset_flagbits_t; -/* the type of hotplug event */ -enum hotplug_event { - CPUSET_CPU_OFFLINE, - CPUSET_MEM_OFFLINE, -}; - /* convenient tests for these bits */ +static inline bool is_cpuset_online(const struct cpuset *cs) +{ + return test_bit(CS_ONLINE, &cs->flags); +} + static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); @@ -190,27 +194,52 @@ static inline int is_spread_slab(const struct cpuset *cs) } static struct cpuset top_cpuset = { - .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), + .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | + (1 << CS_MEM_EXCLUSIVE)), }; +/** + * cpuset_for_each_child - traverse online children of a cpuset + * @child_cs: loop cursor pointing to the current child + * @pos_cgrp: used for iteration + * @parent_cs: target cpuset to walk children of + * + * Walk @child_cs through the online children of @parent_cs. Must be used + * with RCU read locked. + */ +#define cpuset_for_each_child(child_cs, pos_cgrp, parent_cs) \ + cgroup_for_each_child((pos_cgrp), (parent_cs)->css.cgroup) \ + if (is_cpuset_online(((child_cs) = cgroup_cs((pos_cgrp))))) + +/** + * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants + * @des_cs: loop cursor pointing to the current descendant + * @pos_cgrp: used for iteration + * @root_cs: target cpuset to walk ancestor of + * + * Walk @des_cs through the online descendants of @root_cs. Must be used + * with RCU read locked. The caller may modify @pos_cgrp by calling + * cgroup_rightmost_descendant() to skip subtree. + */ +#define cpuset_for_each_descendant_pre(des_cs, pos_cgrp, root_cs) \ + cgroup_for_each_descendant_pre((pos_cgrp), (root_cs)->css.cgroup) \ + if (is_cpuset_online(((des_cs) = cgroup_cs((pos_cgrp))))) + /* - * There are two global mutexes guarding cpuset structures. The first - * is the main control groups cgroup_mutex, accessed via - * cgroup_lock()/cgroup_unlock(). The second is the cpuset-specific - * callback_mutex, below. They can nest. It is ok to first take - * cgroup_mutex, then nest callback_mutex. We also require taking - * task_lock() when dereferencing a task's cpuset pointer. See "The - * task_lock() exception", at the end of this comment. - * - * A task must hold both mutexes to modify cpusets. If a task - * holds cgroup_mutex, then it blocks others wanting that mutex, - * ensuring that it is the only task able to also acquire callback_mutex - * and be able to modify cpusets. It can perform various checks on - * the cpuset structure first, knowing nothing will change. It can - * also allocate memory while just holding cgroup_mutex. While it is - * performing these checks, various callback routines can briefly - * acquire callback_mutex to query cpusets. Once it is ready to make - * the changes, it takes callback_mutex, blocking everyone else. + * There are two global mutexes guarding cpuset structures - cpuset_mutex + * and callback_mutex. The latter may nest inside the former. We also + * require taking task_lock() when dereferencing a task's cpuset pointer. + * See "The task_lock() exception", at the end of this comment. + * + * A task must hold both mutexes to modify cpusets. If a task holds + * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it + * is the only task able to also acquire callback_mutex and be able to + * modify cpusets. It can perform various checks on the cpuset structure + * first, knowing nothing will change. It can also allocate memory while + * just holding cpuset_mutex. While it is performing these checks, various + * callback routines can briefly acquire callback_mutex to query cpusets. + * Once it is ready to make the changes, it takes callback_mutex, blocking + * everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_mutex, as that would risk double tripping on callback_mutex @@ -232,6 +261,7 @@ static struct cpuset top_cpuset = { * guidelines for accessing subsystem state in kernel/cgroup.c */ +static DEFINE_MUTEX(cpuset_mutex); static DEFINE_MUTEX(callback_mutex); /* @@ -246,6 +276,17 @@ static char cpuset_nodelist[CPUSET_NODELIST_LEN]; static DEFINE_SPINLOCK(cpuset_buffer_lock); /* + * CPU / memory hotplug is handled asynchronously. + */ +static struct workqueue_struct *cpuset_propagate_hotplug_wq; + +static void cpuset_hotplug_workfn(struct work_struct *work); +static void cpuset_propagate_hotplug_workfn(struct work_struct *work); +static void schedule_cpuset_propagate_hotplug(struct cpuset *cs); + +static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); + +/* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead @@ -289,7 +330,7 @@ static void guarantee_online_cpus(const struct cpuset *cs, struct cpumask *pmask) { while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask)) - cs = cs->parent; + cs = parent_cs(cs); if (cs) cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask); else @@ -314,7 +355,7 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) { while (cs && !nodes_intersects(cs->mems_allowed, node_states[N_MEMORY])) - cs = cs->parent; + cs = parent_cs(cs); if (cs) nodes_and(*pmask, cs->mems_allowed, node_states[N_MEMORY]); @@ -326,7 +367,7 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Called with callback_mutex/cgroup_mutex held + * Called with callback_mutex/cpuset_mutex held */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) @@ -346,7 +387,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cgroup_mutex. + * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -395,7 +436,7 @@ static void free_trial_cpuset(struct cpuset *trial) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cgroup_mutex held. + * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -412,48 +453,58 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) { struct cgroup *cont; struct cpuset *c, *par; + int ret; + + rcu_read_lock(); /* Each of our child cpusets must be a subset of us */ - list_for_each_entry(cont, &cur->css.cgroup->children, sibling) { - if (!is_cpuset_subset(cgroup_cs(cont), trial)) - return -EBUSY; - } + ret = -EBUSY; + cpuset_for_each_child(c, cont, cur) + if (!is_cpuset_subset(c, trial)) + goto out; /* Remaining checks don't apply to root cpuset */ + ret = 0; if (cur == &top_cpuset) - return 0; + goto out; - par = cur->parent; + par = parent_cs(cur); /* We must be a subset of our parent cpuset */ + ret = -EACCES; if (!is_cpuset_subset(trial, par)) - return -EACCES; + goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap */ - list_for_each_entry(cont, &par->css.cgroup->children, sibling) { - c = cgroup_cs(cont); + ret = -EINVAL; + cpuset_for_each_child(c, cont, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) - return -EINVAL; + goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) - return -EINVAL; + goto out; } - /* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */ - if (cgroup_task_count(cur->css.cgroup)) { - if (cpumask_empty(trial->cpus_allowed) || - nodes_empty(trial->mems_allowed)) { - return -ENOSPC; - } - } + /* + * Cpusets with tasks - existing or newly being attached - can't + * have empty cpus_allowed or mems_allowed. + */ + ret = -ENOSPC; + if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress) && + (cpumask_empty(trial->cpus_allowed) || + nodes_empty(trial->mems_allowed))) + goto out; - return 0; + ret = 0; +out: + rcu_read_unlock(); + return ret; } #ifdef CONFIG_SMP @@ -474,31 +525,24 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) return; } -static void -update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) +static void update_domain_attr_tree(struct sched_domain_attr *dattr, + struct cpuset *root_cs) { - LIST_HEAD(q); - - list_add(&c->stack_list, &q); - while (!list_empty(&q)) { - struct cpuset *cp; - struct cgroup *cont; - struct cpuset *child; - - cp = list_first_entry(&q, struct cpuset, stack_list); - list_del(q.next); + struct cpuset *cp; + struct cgroup *pos_cgrp; - if (cpumask_empty(cp->cpus_allowed)) + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) { + /* skip the whole subtree if @cp doesn't have any CPU */ + if (cpumask_empty(cp->cpus_allowed)) { + pos_cgrp = cgroup_rightmost_descendant(pos_cgrp); continue; + } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); - - list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { - child = cgroup_cs(cont); - list_add_tail(&child->stack_list, &q); - } } + rcu_read_unlock(); } /* @@ -520,7 +564,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cgroup_lock held. + * Must be called with cpuset_mutex held. * * The three key local variables below are: * q - a linked-list queue of cpuset pointers, used to implement a @@ -558,7 +602,6 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { - LIST_HEAD(q); /* queue of cpusets to be scanned */ struct cpuset *cp; /* scans q */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ @@ -567,6 +610,7 @@ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ + struct cgroup *pos_cgrp; doms = NULL; dattr = NULL; @@ -594,33 +638,27 @@ static int generate_sched_domains(cpumask_var_t **domains, goto done; csn = 0; - list_add(&top_cpuset.stack_list, &q); - while (!list_empty(&q)) { - struct cgroup *cont; - struct cpuset *child; /* scans child cpusets of cp */ - - cp = list_first_entry(&q, struct cpuset, stack_list); - list_del(q.next); - - if (cpumask_empty(cp->cpus_allowed)) - continue; - + rcu_read_lock(); + cpuset_for_each_descendant_pre(cp, pos_cgrp, &top_cpuset) { /* - * All child cpusets contain a subset of the parent's cpus, so - * just skip them, and then we call update_domain_attr_tree() - * to calc relax_domain_level of the corresponding sched - * domain. + * Continue traversing beyond @cp iff @cp has some CPUs and + * isn't load balancing. The former is obvious. The + * latter: All child cpusets contain a subset of the + * parent's cpus, so just skip them, and then we call + * update_domain_attr_tree() to calc relax_domain_level of + * the corresponding sched domain. */ - if (is_sched_load_balance(cp)) { - csa[csn++] = cp; + if (!cpumask_empty(cp->cpus_allowed) && + !is_sched_load_balance(cp)) continue; - } - list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { - child = cgroup_cs(cont); - list_add_tail(&child->stack_list, &q); - } - } + if (is_sched_load_balance(cp)) + csa[csn++] = cp; + + /* skip @cp's subtree */ + pos_cgrp = cgroup_rightmost_descendant(pos_cgrp); + } + rcu_read_unlock(); for (i = 0; i < csn; i++) csa[i]->pn = i; @@ -725,25 +763,25 @@ done: /* * Rebuild scheduler domains. * - * Call with neither cgroup_mutex held nor within get_online_cpus(). - * Takes both cgroup_mutex and get_online_cpus(). + * If the flag 'sched_load_balance' of any cpuset with non-empty + * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset + * which has that flag enabled, or if any cpuset with a non-empty + * 'cpus' is removed, then call this routine to rebuild the + * scheduler's dynamic sched domains. * - * Cannot be directly called from cpuset code handling changes - * to the cpuset pseudo-filesystem, because it cannot be called - * from code that already holds cgroup_mutex. + * Call with cpuset_mutex held. Takes get_online_cpus(). */ -static void do_rebuild_sched_domains(struct work_struct *unused) +static void rebuild_sched_domains_locked(void) { struct sched_domain_attr *attr; cpumask_var_t *doms; int ndoms; + lockdep_assert_held(&cpuset_mutex); get_online_cpus(); /* Generate domain masks and attrs */ - cgroup_lock(); ndoms = generate_sched_domains(&doms, &attr); - cgroup_unlock(); /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); @@ -751,7 +789,7 @@ static void do_rebuild_sched_domains(struct work_struct *unused) put_online_cpus(); } #else /* !CONFIG_SMP */ -static void do_rebuild_sched_domains(struct work_struct *unused) +static void rebuild_sched_domains_locked(void) { } @@ -763,44 +801,11 @@ static int generate_sched_domains(cpumask_var_t **domains, } #endif /* CONFIG_SMP */ -static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains); - -/* - * Rebuild scheduler domains, asynchronously via workqueue. - * - * If the flag 'sched_load_balance' of any cpuset with non-empty - * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset - * which has that flag enabled, or if any cpuset with a non-empty - * 'cpus' is removed, then call this routine to rebuild the - * scheduler's dynamic sched domains. - * - * The rebuild_sched_domains() and partition_sched_domains() - * routines must nest cgroup_lock() inside get_online_cpus(), - * but such cpuset changes as these must nest that locking the - * other way, holding cgroup_lock() for much of the code. - * - * So in order to avoid an ABBA deadlock, the cpuset code handling - * these user changes delegates the actual sched domain rebuilding - * to a separate workqueue thread, which ends up processing the - * above do_rebuild_sched_domains() function. - */ -static void async_rebuild_sched_domains(void) -{ - queue_work(cpuset_wq, &rebuild_sched_domains_work); -} - -/* - * Accomplishes the same scheduler domain rebuild as the above - * async_rebuild_sched_domains(), however it directly calls the - * rebuild routine synchronously rather than calling it via an - * asynchronous work thread. - * - * This can only be called from code that is not holding - * cgroup_mutex (not nested in a cgroup_lock() call.) - */ void rebuild_sched_domains(void) { - do_rebuild_sched_domains(NULL); + mutex_lock(&cpuset_mutex); + rebuild_sched_domains_locked(); + mutex_unlock(&cpuset_mutex); } /** @@ -808,7 +813,7 @@ void rebuild_sched_domains(void) * @tsk: task to test * @scan: struct cgroup_scanner contained in its struct cpuset_hotplug_scanner * - * Call with cgroup_mutex held. May take callback_mutex during call. + * Call with cpuset_mutex held. May take callback_mutex during call. * Called for each task in a cgroup by cgroup_scan_tasks(). * Return nonzero if this tasks's cpus_allowed mask should be changed (in other * words, if its mask is not equal to its cpuset's mask). @@ -829,7 +834,7 @@ static int cpuset_test_cpumask(struct task_struct *tsk, * cpus_allowed mask needs to be changed. * * We don't need to re-check for the cgroup/cpuset membership, since we're - * holding cgroup_lock() at this point. + * holding cpuset_mutex at this point. */ static void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) @@ -842,7 +847,7 @@ static void cpuset_change_cpumask(struct task_struct *tsk, * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() * - * Called with cgroup_mutex held + * Called with cpuset_mutex held * * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, * calling callback functions for each. @@ -920,7 +925,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, heap_free(&heap); if (is_load_balanced) - async_rebuild_sched_domains(); + rebuild_sched_domains_locked(); return 0; } @@ -932,7 +937,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Temporarilly set tasks mems_allowed to target nodes of migration, * so that the migration code can allocate pages on these nodes. * - * Call holding cgroup_mutex, so current's cpuset won't change + * Call holding cpuset_mutex, so current's cpuset won't change * during this call, as manage_mutex holds off any cpuset_attach() * calls. Therefore we don't need to take task_lock around the * call to guarantee_online_mems(), as we know no one is changing @@ -1007,7 +1012,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, /* * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy * of it to cpuset's new mems_allowed, and migrate pages to new nodes if - * memory_migrate flag is set. Called with cgroup_mutex held. + * memory_migrate flag is set. Called with cpuset_mutex held. */ static void cpuset_change_nodemask(struct task_struct *p, struct cgroup_scanner *scan) @@ -1016,7 +1021,7 @@ static void cpuset_change_nodemask(struct task_struct *p, struct cpuset *cs; int migrate; const nodemask_t *oldmem = scan->data; - static nodemask_t newmems; /* protected by cgroup_mutex */ + static nodemask_t newmems; /* protected by cpuset_mutex */ cs = cgroup_cs(scan->cg); guarantee_online_mems(cs, &newmems); @@ -1043,7 +1048,7 @@ static void *cpuset_being_rebound; * @oldmem: old mems_allowed of cpuset cs * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() * - * Called with cgroup_mutex held + * Called with cpuset_mutex held * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 * if @heap != NULL. */ @@ -1065,7 +1070,7 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cgroup_mutex, we know that no other rebind effort + * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -1084,7 +1089,7 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cgroup_mutex held. May take callback_mutex during call. + * Call with cpuset_mutex held. May take callback_mutex during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_sem, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -1168,7 +1173,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) - async_rebuild_sched_domains(); + rebuild_sched_domains_locked(); } return 0; @@ -1182,7 +1187,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * Called by cgroup_scan_tasks() for each task in a cgroup. * * We don't need to re-check for the cgroup/cpuset membership, since we're - * holding cgroup_lock() at this point. + * holding cpuset_mutex at this point. */ static void cpuset_change_flag(struct task_struct *tsk, struct cgroup_scanner *scan) @@ -1195,7 +1200,7 @@ static void cpuset_change_flag(struct task_struct *tsk, * @cs: the cpuset in which each task's spread flags needs to be changed * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() * - * Called with cgroup_mutex held + * Called with cpuset_mutex held * * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, * calling callback functions for each. @@ -1220,7 +1225,7 @@ static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cgroup_mutex held. + * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -1260,7 +1265,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, mutex_unlock(&callback_mutex); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) - async_rebuild_sched_domains(); + rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs, &heap); @@ -1368,24 +1373,18 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } -/* - * Protected by cgroup_lock. The nodemasks must be stored globally because - * dynamically allocating them is not allowed in can_attach, and they must - * persist until attach. - */ -static cpumask_var_t cpus_attach; -static nodemask_t cpuset_attach_nodemask_from; -static nodemask_t cpuset_attach_nodemask_to; - -/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ +/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { struct cpuset *cs = cgroup_cs(cgrp); struct task_struct *task; int ret; + mutex_lock(&cpuset_mutex); + + ret = -ENOSPC; if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) - return -ENOSPC; + goto out_unlock; cgroup_taskset_for_each(task, cgrp, tset) { /* @@ -1397,25 +1396,45 @@ static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) * set_cpus_allowed_ptr() on all attached tasks before * cpus_allowed may be changed. */ + ret = -EINVAL; if (task->flags & PF_THREAD_BOUND) - return -EINVAL; - if ((ret = security_task_setscheduler(task))) - return ret; + goto out_unlock; + ret = security_task_setscheduler(task); + if (ret) + goto out_unlock; } - /* prepare for attach */ - if (cs == &top_cpuset) - cpumask_copy(cpus_attach, cpu_possible_mask); - else - guarantee_online_cpus(cs, cpus_attach); - - guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + /* + * Mark attach is in progress. This makes validate_change() fail + * changes which zero cpus/mems_allowed. + */ + cs->attach_in_progress++; + ret = 0; +out_unlock: + mutex_unlock(&cpuset_mutex); + return ret; +} - return 0; +static void cpuset_cancel_attach(struct cgroup *cgrp, + struct cgroup_taskset *tset) +{ + mutex_lock(&cpuset_mutex); + cgroup_cs(cgrp)->attach_in_progress--; + mutex_unlock(&cpuset_mutex); } +/* + * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() + * but we can't allocate it dynamically there. Define it global and + * allocate from cpuset_init(). + */ +static cpumask_var_t cpus_attach; + static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { + /* static bufs protected by cpuset_mutex */ + static nodemask_t cpuset_attach_nodemask_from; + static nodemask_t cpuset_attach_nodemask_to; struct mm_struct *mm; struct task_struct *task; struct task_struct *leader = cgroup_taskset_first(tset); @@ -1423,6 +1442,16 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) struct cpuset *cs = cgroup_cs(cgrp); struct cpuset *oldcs = cgroup_cs(oldcgrp); + mutex_lock(&cpuset_mutex); + + /* prepare for attach */ + if (cs == &top_cpuset) + cpumask_copy(cpus_attach, cpu_possible_mask); + else + guarantee_online_cpus(cs, cpus_attach); + + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); + cgroup_taskset_for_each(task, cgrp, tset) { /* * can_attach beforehand should guarantee that this doesn't @@ -1448,6 +1477,18 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) &cpuset_attach_nodemask_to); mmput(mm); } + + cs->attach_in_progress--; + + /* + * We may have raced with CPU/memory hotunplug. Trigger hotplug + * propagation if @cs doesn't have any CPU or memory. It will move + * the newly added tasks to the nearest parent which can execute. + */ + if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) + schedule_cpuset_propagate_hotplug(cs); + + mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ @@ -1469,12 +1510,13 @@ typedef enum { static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val) { - int retval = 0; struct cpuset *cs = cgroup_cs(cgrp); cpuset_filetype_t type = cft->private; + int retval = -ENODEV; - if (!cgroup_lock_live_group(cgrp)) - return -ENODEV; + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; switch (type) { case FILE_CPU_EXCLUSIVE: @@ -1508,18 +1550,20 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val) retval = -EINVAL; break; } - cgroup_unlock(); +out_unlock: + mutex_unlock(&cpuset_mutex); return retval; } static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val) { - int retval = 0; struct cpuset *cs = cgroup_cs(cgrp); cpuset_filetype_t type = cft->private; + int retval = -ENODEV; - if (!cgroup_lock_live_group(cgrp)) - return -ENODEV; + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: @@ -1529,7 +1573,8 @@ static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val) retval = -EINVAL; break; } - cgroup_unlock(); +out_unlock: + mutex_unlock(&cpuset_mutex); return retval; } @@ -1539,17 +1584,36 @@ static int cpuset_write_s64(struct cgroup *cgrp, struct cftype *cft, s64 val) static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, const char *buf) { - int retval = 0; struct cpuset *cs = cgroup_cs(cgrp); struct cpuset *trialcs; + int retval = -ENODEV; + + /* + * CPU or memory hotunplug may leave @cs w/o any execution + * resources, in which case the hotplug code asynchronously updates + * configuration and transfers all tasks to the nearest ancestor + * which can execute. + * + * As writes to "cpus" or "mems" may restore @cs's execution + * resources, wait for the previously scheduled operations before + * proceeding, so that we don't end up keep removing tasks added + * after execution capability is restored. + * + * Flushing cpuset_hotplug_work is enough to synchronize against + * hotplug hanlding; however, cpuset_attach() may schedule + * propagation work directly. Flush the workqueue too. + */ + flush_work(&cpuset_hotplug_work); + flush_workqueue(cpuset_propagate_hotplug_wq); - if (!cgroup_lock_live_group(cgrp)) - return -ENODEV; + mutex_lock(&cpuset_mutex); + if (!is_cpuset_online(cs)) + goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; - goto out; + goto out_unlock; } switch (cft->private) { @@ -1565,8 +1629,8 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, } free_trial_cpuset(trialcs); -out: - cgroup_unlock(); +out_unlock: + mutex_unlock(&cpuset_mutex); return retval; } @@ -1790,15 +1854,12 @@ static struct cftype files[] = { static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont) { - struct cgroup *parent_cg = cont->parent; - struct cgroup *tmp_cg; - struct cpuset *parent, *cs; + struct cpuset *cs; - if (!parent_cg) + if (!cont->parent) return &top_cpuset.css; - parent = cgroup_cs(parent_cg); - cs = kmalloc(sizeof(*cs), GFP_KERNEL); + cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) { @@ -1806,22 +1867,38 @@ static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont) return ERR_PTR(-ENOMEM); } - cs->flags = 0; - if (is_spread_page(parent)) - set_bit(CS_SPREAD_PAGE, &cs->flags); - if (is_spread_slab(parent)) - set_bit(CS_SPREAD_SLAB, &cs->flags); set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpumask_clear(cs->cpus_allowed); nodes_clear(cs->mems_allowed); fmeter_init(&cs->fmeter); + INIT_WORK(&cs->hotplug_work, cpuset_propagate_hotplug_workfn); cs->relax_domain_level = -1; - cs->parent = parent; + return &cs->css; +} + +static int cpuset_css_online(struct cgroup *cgrp) +{ + struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *parent = parent_cs(cs); + struct cpuset *tmp_cs; + struct cgroup *pos_cg; + + if (!parent) + return 0; + + mutex_lock(&cpuset_mutex); + + set_bit(CS_ONLINE, &cs->flags); + if (is_spread_page(parent)) + set_bit(CS_SPREAD_PAGE, &cs->flags); + if (is_spread_slab(parent)) + set_bit(CS_SPREAD_SLAB, &cs->flags); + number_of_cpusets++; - if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cont->flags)) - goto skip_clone; + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags)) + goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is @@ -1836,35 +1913,49 @@ static struct cgroup_subsys_state *cpuset_css_alloc(struct cgroup *cont) * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ - list_for_each_entry(tmp_cg, &parent_cg->children, sibling) { - struct cpuset *tmp_cs = cgroup_cs(tmp_cg); - - if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) - goto skip_clone; + rcu_read_lock(); + cpuset_for_each_child(tmp_cs, pos_cg, parent) { + if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { + rcu_read_unlock(); + goto out_unlock; + } } + rcu_read_unlock(); mutex_lock(&callback_mutex); cs->mems_allowed = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); mutex_unlock(&callback_mutex); -skip_clone: - return &cs->css; +out_unlock: + mutex_unlock(&cpuset_mutex); + return 0; +} + +static void cpuset_css_offline(struct cgroup *cgrp) +{ + struct cpuset *cs = cgroup_cs(cgrp); + + mutex_lock(&cpuset_mutex); + + if (is_sched_load_balance(cs)) + update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); + + number_of_cpusets--; + clear_bit(CS_ONLINE, &cs->flags); + + mutex_unlock(&cpuset_mutex); } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which - * will call async_rebuild_sched_domains(). + * will call rebuild_sched_domains_locked(). */ static void cpuset_css_free(struct cgroup *cont) { struct cpuset *cs = cgroup_cs(cont); - if (is_sched_load_balance(cs)) - update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); - - number_of_cpusets--; free_cpumask_var(cs->cpus_allowed); kfree(cs); } @@ -1872,8 +1963,11 @@ static void cpuset_css_free(struct cgroup *cont) struct cgroup_subsys cpuset_subsys = { .name = "cpuset", .css_alloc = cpuset_css_alloc, + .css_online = cpuset_css_online, + .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, + .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .subsys_id = cpuset_subsys_id, .base_cftypes = files, @@ -1924,7 +2018,9 @@ static void cpuset_do_move_task(struct task_struct *tsk, { struct cgroup *new_cgroup = scan->data; + cgroup_lock(); cgroup_attach_task(new_cgroup, tsk); + cgroup_unlock(); } /** @@ -1932,7 +2028,7 @@ static void cpuset_do_move_task(struct task_struct *tsk, * @from: cpuset in which the tasks currently reside * @to: cpuset to which the tasks will be moved * - * Called with cgroup_mutex held + * Called with cpuset_mutex held * callback_mutex must not be held, as cpuset_attach() will take it. * * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, @@ -1959,169 +2055,200 @@ static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to) * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. - * - * Called with cgroup_mutex held - * callback_mutex must not be held, as cpuset_attach() will take it. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* - * The cgroup's css_sets list is in use if there are tasks - * in the cpuset; the list is empty if there are none; - * the cs->css.refcnt seems always 0. - */ - if (list_empty(&cs->css.cgroup->css_sets)) - return; - - /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ - parent = cs->parent; + parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) - parent = parent->parent; + parent = parent_cs(parent); move_member_tasks_to_cpuset(cs, parent); } -/* - * Helper function to traverse cpusets. - * It can be used to walk the cpuset tree from top to bottom, completing - * one layer before dropping down to the next (thus always processing a - * node before any of its children). +/** + * cpuset_propagate_hotplug_workfn - propagate CPU/memory hotplug to a cpuset + * @cs: cpuset in interest + * + * Compare @cs's cpu and mem masks against top_cpuset and if some have gone + * offline, update @cs accordingly. If @cs ends up with no CPU or memory, + * all its tasks are moved to the nearest ancestor with both resources. */ -static struct cpuset *cpuset_next(struct list_head *queue) +static void cpuset_propagate_hotplug_workfn(struct work_struct *work) { - struct cpuset *cp; - struct cpuset *child; /* scans child cpusets of cp */ - struct cgroup *cont; + static cpumask_t off_cpus; + static nodemask_t off_mems, tmp_mems; + struct cpuset *cs = container_of(work, struct cpuset, hotplug_work); + bool is_empty; - if (list_empty(queue)) - return NULL; + mutex_lock(&cpuset_mutex); + + cpumask_andnot(&off_cpus, cs->cpus_allowed, top_cpuset.cpus_allowed); + nodes_andnot(off_mems, cs->mems_allowed, top_cpuset.mems_allowed); - cp = list_first_entry(queue, struct cpuset, stack_list); - list_del(queue->next); - list_for_each_entry(cont, &cp->css.cgroup->children, sibling) { - child = cgroup_cs(cont); - list_add_tail(&child->stack_list, queue); + /* remove offline cpus from @cs */ + if (!cpumask_empty(&off_cpus)) { + mutex_lock(&callback_mutex); + cpumask_andnot(cs->cpus_allowed, cs->cpus_allowed, &off_cpus); + mutex_unlock(&callback_mutex); + update_tasks_cpumask(cs, NULL); + } + + /* remove offline mems from @cs */ + if (!nodes_empty(off_mems)) { + tmp_mems = cs->mems_allowed; + mutex_lock(&callback_mutex); + nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems); + mutex_unlock(&callback_mutex); + update_tasks_nodemask(cs, &tmp_mems, NULL); } - return cp; + is_empty = cpumask_empty(cs->cpus_allowed) || + nodes_empty(cs->mems_allowed); + + mutex_unlock(&cpuset_mutex); + + /* + * If @cs became empty, move tasks to the nearest ancestor with + * execution resources. This is full cgroup operation which will + * also call back into cpuset. Should be done outside any lock. + */ + if (is_empty) + remove_tasks_in_empty_cpuset(cs); + + /* the following may free @cs, should be the last operation */ + css_put(&cs->css); } +/** + * schedule_cpuset_propagate_hotplug - schedule hotplug propagation to a cpuset + * @cs: cpuset of interest + * + * Schedule cpuset_propagate_hotplug_workfn() which will update CPU and + * memory masks according to top_cpuset. + */ +static void schedule_cpuset_propagate_hotplug(struct cpuset *cs) +{ + /* + * Pin @cs. The refcnt will be released when the work item + * finishes executing. + */ + if (!css_tryget(&cs->css)) + return; -/* - * Walk the specified cpuset subtree upon a hotplug operation (CPU/Memory - * online/offline) and update the cpusets accordingly. - * For regular CPU/Mem hotplug, look for empty cpusets; the tasks of such - * cpuset must be moved to a parent cpuset. + /* + * Queue @cs->hotplug_work. If already pending, lose the css ref. + * cpuset_propagate_hotplug_wq is ordered and propagation will + * happen in the order this function is called. + */ + if (!queue_work(cpuset_propagate_hotplug_wq, &cs->hotplug_work)) + css_put(&cs->css); +} + +/** + * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * - * Called with cgroup_mutex held. We take callback_mutex to modify - * cpus_allowed and mems_allowed. + * This function is called after either CPU or memory configuration has + * changed and updates cpuset accordingly. The top_cpuset is always + * synchronized to cpu_active_mask and N_MEMORY, which is necessary in + * order to make cpusets transparent (of no affect) on systems that are + * actively using CPU hotplug but making no active use of cpusets. * - * This walk processes the tree from top to bottom, completing one layer - * before dropping down to the next. It always processes a node before - * any of its children. + * Non-root cpusets are only affected by offlining. If any CPUs or memory + * nodes have been taken down, cpuset_propagate_hotplug() is invoked on all + * descendants. * - * In the case of memory hot-unplug, it will remove nodes from N_MEMORY - * if all present pages from a node are offlined. + * Note that CPU offlining during suspend is ignored. We don't modify + * cpusets across suspend/resume cycles at all. */ -static void -scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event) +static void cpuset_hotplug_workfn(struct work_struct *work) { - LIST_HEAD(queue); - struct cpuset *cp; /* scans cpusets being updated */ - static nodemask_t oldmems; /* protected by cgroup_mutex */ + static cpumask_t new_cpus, tmp_cpus; + static nodemask_t new_mems, tmp_mems; + bool cpus_updated, mems_updated; + bool cpus_offlined, mems_offlined; - list_add_tail((struct list_head *)&root->stack_list, &queue); + mutex_lock(&cpuset_mutex); - switch (event) { - case CPUSET_CPU_OFFLINE: - while ((cp = cpuset_next(&queue)) != NULL) { + /* fetch the available cpus/mems and find out which changed how */ + cpumask_copy(&new_cpus, cpu_active_mask); + new_mems = node_states[N_MEMORY]; - /* Continue past cpusets with all cpus online */ - if (cpumask_subset(cp->cpus_allowed, cpu_active_mask)) - continue; + cpus_updated = !cpumask_equal(top_cpuset.cpus_allowed, &new_cpus); + cpus_offlined = cpumask_andnot(&tmp_cpus, top_cpuset.cpus_allowed, + &new_cpus); - /* Remove offline cpus from this cpuset. */ - mutex_lock(&callback_mutex); - cpumask_and(cp->cpus_allowed, cp->cpus_allowed, - cpu_active_mask); - mutex_unlock(&callback_mutex); + mems_updated = !nodes_equal(top_cpuset.mems_allowed, new_mems); + nodes_andnot(tmp_mems, top_cpuset.mems_allowed, new_mems); + mems_offlined = !nodes_empty(tmp_mems); - /* Move tasks from the empty cpuset to a parent */ - if (cpumask_empty(cp->cpus_allowed)) - remove_tasks_in_empty_cpuset(cp); - else - update_tasks_cpumask(cp, NULL); - } - break; + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { + mutex_lock(&callback_mutex); + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + mutex_unlock(&callback_mutex); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } - case CPUSET_MEM_OFFLINE: - while ((cp = cpuset_next(&queue)) != NULL) { + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { + tmp_mems = top_cpuset.mems_allowed; + mutex_lock(&callback_mutex); + top_cpuset.mems_allowed = new_mems; + mutex_unlock(&callback_mutex); + update_tasks_nodemask(&top_cpuset, &tmp_mems, NULL); + } - /* Continue past cpusets with all mems online */ - if (nodes_subset(cp->mems_allowed, - node_states[N_MEMORY])) - continue; + /* if cpus or mems went down, we need to propagate to descendants */ + if (cpus_offlined || mems_offlined) { + struct cpuset *cs; + struct cgroup *pos_cgrp; - oldmems = cp->mems_allowed; + rcu_read_lock(); + cpuset_for_each_descendant_pre(cs, pos_cgrp, &top_cpuset) + schedule_cpuset_propagate_hotplug(cs); + rcu_read_unlock(); + } - /* Remove offline mems from this cpuset. */ - mutex_lock(&callback_mutex); - nodes_and(cp->mems_allowed, cp->mems_allowed, - node_states[N_MEMORY]); - mutex_unlock(&callback_mutex); + mutex_unlock(&cpuset_mutex); - /* Move tasks from the empty cpuset to a parent */ - if (nodes_empty(cp->mems_allowed)) - remove_tasks_in_empty_cpuset(cp); - else - update_tasks_nodemask(cp, &oldmems, NULL); - } + /* wait for propagations to finish */ + flush_workqueue(cpuset_propagate_hotplug_wq); + + /* rebuild sched domains if cpus_allowed has changed */ + if (cpus_updated) { + struct sched_domain_attr *attr; + cpumask_var_t *doms; + int ndoms; + + mutex_lock(&cpuset_mutex); + ndoms = generate_sched_domains(&doms, &attr); + mutex_unlock(&cpuset_mutex); + + partition_sched_domains(ndoms, doms, attr); } } -/* - * The top_cpuset tracks what CPUs and Memory Nodes are online, - * period. This is necessary in order to make cpusets transparent - * (of no affect) on systems that are actively using CPU hotplug - * but making no active use of cpusets. - * - * The only exception to this is suspend/resume, where we don't - * modify cpusets at all. - * - * This routine ensures that top_cpuset.cpus_allowed tracks - * cpu_active_mask on each CPU hotplug (cpuhp) event. - * - * Called within get_online_cpus(). Needs to call cgroup_lock() - * before calling generate_sched_domains(). - * - * @cpu_online: Indicates whether this is a CPU online event (true) or - * a CPU offline event (false). - */ void cpuset_update_active_cpus(bool cpu_online) { - struct sched_domain_attr *attr; - cpumask_var_t *doms; - int ndoms; - - cgroup_lock(); - mutex_lock(&callback_mutex); - cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); - mutex_unlock(&callback_mutex); - - if (!cpu_online) - scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_CPU_OFFLINE); - - ndoms = generate_sched_domains(&doms, &attr); - cgroup_unlock(); - - /* Have scheduler rebuild the domains */ - partition_sched_domains(ndoms, doms, attr); + /* + * We're inside cpu hotplug critical region which usually nests + * inside cgroup synchronization. Bounce actual hotplug processing + * to a work item to avoid reverse locking order. + * + * We still need to do partition_sched_domains() synchronously; + * otherwise, the scheduler will get confused and put tasks to the + * dead CPU. Fall back to the default single domain. + * cpuset_hotplug_workfn() will rebuild it as necessary. + */ + partition_sched_domains(1, NULL, NULL); + schedule_work(&cpuset_hotplug_work); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -2133,29 +2260,7 @@ void cpuset_update_active_cpus(bool cpu_online) static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { - static nodemask_t oldmems; /* protected by cgroup_mutex */ - - cgroup_lock(); - switch (action) { - case MEM_ONLINE: - oldmems = top_cpuset.mems_allowed; - mutex_lock(&callback_mutex); - top_cpuset.mems_allowed = node_states[N_MEMORY]; - mutex_unlock(&callback_mutex); - update_tasks_nodemask(&top_cpuset, &oldmems, NULL); - break; - case MEM_OFFLINE: - /* - * needn't update top_cpuset.mems_allowed explicitly because - * scan_cpusets_upon_hotplug() will update it. - */ - scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_MEM_OFFLINE); - break; - default: - break; - } - cgroup_unlock(); - + schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } #endif @@ -2173,8 +2278,9 @@ void __init cpuset_init_smp(void) hotplug_memory_notifier(cpuset_track_online_nodes, 10); - cpuset_wq = create_singlethread_workqueue("cpuset"); - BUG_ON(!cpuset_wq); + cpuset_propagate_hotplug_wq = + alloc_ordered_workqueue("cpuset_hotplug", 0); + BUG_ON(!cpuset_propagate_hotplug_wq); } /** @@ -2273,8 +2379,8 @@ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) */ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs) { - while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && cs->parent) - cs = cs->parent; + while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) + cs = parent_cs(cs); return cs; } @@ -2412,17 +2518,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) } /** - * cpuset_unlock - release lock on cpuset changes - * - * Undo the lock taken in a previous cpuset_lock() call. - */ - -void cpuset_unlock(void) -{ - mutex_unlock(&callback_mutex); -} - -/** * cpuset_mem_spread_node() - On which node to begin search for a file page * cpuset_slab_spread_node() - On which node to begin search for a slab page * @@ -2511,8 +2606,16 @@ void cpuset_print_task_mems_allowed(struct task_struct *tsk) dentry = task_cs(tsk)->css.cgroup->dentry; spin_lock(&cpuset_buffer_lock); - snprintf(cpuset_name, CPUSET_NAME_LEN, - dentry ? (const char *)dentry->d_name.name : "/"); + + if (!dentry) { + strcpy(cpuset_name, "/"); + } else { + spin_lock(&dentry->d_lock); + strlcpy(cpuset_name, (const char *)dentry->d_name.name, + CPUSET_NAME_LEN); + spin_unlock(&dentry->d_lock); + } + nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN, tsk->mems_allowed); printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n", @@ -2560,7 +2663,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cgroup_mutex, keeping cpuset_attach() from changing it + * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ static int proc_cpuset_show(struct seq_file *m, void *unused_v) @@ -2582,16 +2685,15 @@ static int proc_cpuset_show(struct seq_file *m, void *unused_v) if (!tsk) goto out_free; - retval = -EINVAL; - cgroup_lock(); + rcu_read_lock(); css = task_subsys_state(tsk, cpuset_subsys_id); retval = cgroup_path(css->cgroup, buf, PAGE_SIZE); + rcu_read_unlock(); if (retval < 0) - goto out_unlock; + goto out_put_task; seq_puts(m, buf); seq_putc(m, '\n'); -out_unlock: - cgroup_unlock(); +out_put_task: put_task_struct(tsk); out_free: kfree(buf); diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 418b3f7..d473988 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -106,6 +106,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) unsigned long long t2, t3; unsigned long flags; struct timespec ts; + cputime_t utime, stime, stimescaled, utimescaled; /* Though tsk->delays accessed later, early exit avoids * unnecessary returning of other data @@ -114,12 +115,14 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) goto done; tmp = (s64)d->cpu_run_real_total; - cputime_to_timespec(tsk->utime + tsk->stime, &ts); + task_cputime(tsk, &utime, &stime); + cputime_to_timespec(utime + stime, &ts); tmp += timespec_to_ns(&ts); d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; tmp = (s64)d->cpu_scaled_run_real_total; - cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts); + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + cputime_to_timespec(utimescaled + stimescaled, &ts); tmp += timespec_to_ns(&ts); d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; diff --git a/kernel/events/core.c b/kernel/events/core.c index 301079d..5c75791 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -908,6 +908,15 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) } /* + * Initialize event state based on the perf_event_attr::disabled. + */ +static inline void perf_event__state_init(struct perf_event *event) +{ + event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF : + PERF_EVENT_STATE_INACTIVE; +} + +/* * Called at perf_event creation and when events are attached/detached from a * group. */ @@ -6162,11 +6171,14 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (task) { event->attach_state = PERF_ATTACH_TASK; + + if (attr->type == PERF_TYPE_TRACEPOINT) + event->hw.tp_target = task; #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * hw_breakpoint is a bit difficult here.. */ - if (attr->type == PERF_TYPE_BREAKPOINT) + else if (attr->type == PERF_TYPE_BREAKPOINT) event->hw.bp_target = task; #endif } @@ -6179,8 +6191,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->overflow_handler = overflow_handler; event->overflow_handler_context = context; - if (attr->disabled) - event->state = PERF_EVENT_STATE_OFF; + perf_event__state_init(event); pmu = NULL; @@ -6609,9 +6620,17 @@ SYSCALL_DEFINE5(perf_event_open, mutex_lock(&gctx->mutex); perf_remove_from_context(group_leader); + + /* + * Removing from the context ends up with disabled + * event. What we want here is event in the initial + * startup state, ready to be add into new context. + */ + perf_event__state_init(group_leader); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { perf_remove_from_context(sibling); + perf_event__state_init(sibling); put_ctx(gctx); } mutex_unlock(&gctx->mutex); diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index fe8a916..a64f8ae 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -676,7 +676,7 @@ int __init init_hw_breakpoint(void) err_alloc: for_each_possible_cpu(err_cpu) { for (i = 0; i < TYPE_MAX; i++) - kfree(per_cpu(nr_task_bp_pinned[i], cpu)); + kfree(per_cpu(nr_task_bp_pinned[i], err_cpu)); if (err_cpu == cpu) break; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index dea7acf..a567c8c 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -27,6 +27,7 @@ #include <linux/pagemap.h> /* read_mapping_page */ #include <linux/slab.h> #include <linux/sched.h> +#include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ #include <linux/mmu_notifier.h> /* set_pte_at_notify */ #include <linux/swap.h> /* try_to_free_swap */ @@ -41,58 +42,31 @@ #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE static struct rb_root uprobes_tree = RB_ROOT; - -static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ - -#define UPROBES_HASH_SZ 13 - /* - * We need separate register/unregister and mmap/munmap lock hashes because - * of mmap_sem nesting. - * - * uprobe_register() needs to install probes on (potentially) all processes - * and thus needs to acquire multiple mmap_sems (consequtively, not - * concurrently), whereas uprobe_mmap() is called while holding mmap_sem - * for the particular process doing the mmap. - * - * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem - * because of lock order against i_mmap_mutex. This means there's a hole in - * the register vma iteration where a mmap() can happen. - * - * Thus uprobe_register() can race with uprobe_mmap() and we can try and - * install a probe where one is already installed. + * allows us to skip the uprobe_mmap if there are no uprobe events active + * at this time. Probably a fine grained per inode count is better? */ +#define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree) -/* serialize (un)register */ -static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; - -#define uprobes_hash(v) (&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) +static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ +#define UPROBES_HASH_SZ 13 /* serialize uprobe->pending_list */ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; #define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) static struct percpu_rw_semaphore dup_mmap_sem; -/* - * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe - * events active at this time. Probably a fine grained per inode count is - * better? - */ -static atomic_t uprobe_events = ATOMIC_INIT(0); - /* Have a copy of original instruction */ #define UPROBE_COPY_INSN 0 -/* Dont run handlers when first register/ last unregister in progress*/ -#define UPROBE_RUN_HANDLER 1 /* Can skip singlestep */ -#define UPROBE_SKIP_SSTEP 2 +#define UPROBE_SKIP_SSTEP 1 struct uprobe { struct rb_node rb_node; /* node in the rb tree */ atomic_t ref; + struct rw_semaphore register_rwsem; struct rw_semaphore consumer_rwsem; - struct mutex copy_mutex; /* TODO: kill me and UPROBE_COPY_INSN */ struct list_head pending_list; struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ @@ -430,9 +404,6 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe) u = __insert_uprobe(uprobe); spin_unlock(&uprobes_treelock); - /* For now assume that the instruction need not be single-stepped */ - __set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags); - return u; } @@ -452,8 +423,10 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = igrab(inode); uprobe->offset = offset; + init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); - mutex_init(&uprobe->copy_mutex); + /* For now assume that the instruction need not be single-stepped */ + __set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); @@ -463,38 +436,17 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) kfree(uprobe); uprobe = cur_uprobe; iput(inode); - } else { - atomic_inc(&uprobe_events); } return uprobe; } -static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) -{ - struct uprobe_consumer *uc; - - if (!test_bit(UPROBE_RUN_HANDLER, &uprobe->flags)) - return; - - down_read(&uprobe->consumer_rwsem); - for (uc = uprobe->consumers; uc; uc = uc->next) { - if (!uc->filter || uc->filter(uc, current)) - uc->handler(uc, regs); - } - up_read(&uprobe->consumer_rwsem); -} - -/* Returns the previous consumer */ -static struct uprobe_consumer * -consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) +static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) { down_write(&uprobe->consumer_rwsem); uc->next = uprobe->consumers; uprobe->consumers = uc; up_write(&uprobe->consumer_rwsem); - - return uc->next; } /* @@ -588,7 +540,8 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) return ret; - mutex_lock(&uprobe->copy_mutex); + /* TODO: move this into _register, until then we abuse this sem. */ + down_write(&uprobe->consumer_rwsem); if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) goto out; @@ -612,7 +565,30 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: - mutex_unlock(&uprobe->copy_mutex); + up_write(&uprobe->consumer_rwsem); + + return ret; +} + +static inline bool consumer_filter(struct uprobe_consumer *uc, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + return !uc->filter || uc->filter(uc, ctx, mm); +} + +static bool filter_chain(struct uprobe *uprobe, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + struct uprobe_consumer *uc; + bool ret = false; + + down_read(&uprobe->consumer_rwsem); + for (uc = uprobe->consumers; uc; uc = uc->next) { + ret = consumer_filter(uc, ctx, mm); + if (ret) + break; + } + up_read(&uprobe->consumer_rwsem); return ret; } @@ -624,16 +600,6 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, bool first_uprobe; int ret; - /* - * If probe is being deleted, unregister thread could be done with - * the vma-rmap-walk through. Adding a probe now can be fatal since - * nobody will be able to cleanup. Also we could be from fork or - * mremap path, where the probe might have already been inserted. - * Hence behave as if probe already existed. - */ - if (!uprobe->consumers) - return 0; - ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr); if (ret) return ret; @@ -658,14 +624,14 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, static int remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - /* can happen if uprobe_register() fails */ - if (!test_bit(MMF_HAS_UPROBES, &mm->flags)) - return 0; - set_bit(MMF_RECALC_UPROBES, &mm->flags); return set_orig_insn(&uprobe->arch, mm, vaddr); } +static inline bool uprobe_is_active(struct uprobe *uprobe) +{ + return !RB_EMPTY_NODE(&uprobe->rb_node); +} /* * There could be threads that have already hit the breakpoint. They * will recheck the current insn and restart if find_uprobe() fails. @@ -673,12 +639,15 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vad */ static void delete_uprobe(struct uprobe *uprobe) { + if (WARN_ON(!uprobe_is_active(uprobe))) + return; + spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock(&uprobes_treelock); + RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ iput(uprobe->inode); put_uprobe(uprobe); - atomic_dec(&uprobe_events); } struct map_info { @@ -764,8 +733,10 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register) return curr; } -static int register_for_each_vma(struct uprobe *uprobe, bool is_register) +static int +register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) { + bool is_register = !!new; struct map_info *info; int err = 0; @@ -794,10 +765,16 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) vaddr_to_offset(vma, info->vaddr) != uprobe->offset) goto unlock; - if (is_register) - err = install_breakpoint(uprobe, mm, vma, info->vaddr); - else - err |= remove_breakpoint(uprobe, mm, info->vaddr); + if (is_register) { + /* consult only the "caller", new consumer. */ + if (consumer_filter(new, + UPROBE_FILTER_REGISTER, mm)) + err = install_breakpoint(uprobe, mm, vma, info->vaddr); + } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { + if (!filter_chain(uprobe, + UPROBE_FILTER_UNREGISTER, mm)) + err |= remove_breakpoint(uprobe, mm, info->vaddr); + } unlock: up_write(&mm->mmap_sem); @@ -810,17 +787,23 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) return err; } -static int __uprobe_register(struct uprobe *uprobe) +static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc) { - return register_for_each_vma(uprobe, true); + consumer_add(uprobe, uc); + return register_for_each_vma(uprobe, uc); } -static void __uprobe_unregister(struct uprobe *uprobe) +static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { - if (!register_for_each_vma(uprobe, false)) - delete_uprobe(uprobe); + int err; + + if (!consumer_del(uprobe, uc)) /* WARN? */ + return; + err = register_for_each_vma(uprobe, NULL); /* TODO : cant unregister? schedule a worker thread */ + if (!uprobe->consumers && !err) + delete_uprobe(uprobe); } /* @@ -845,31 +828,59 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * struct uprobe *uprobe; int ret; - if (!inode || !uc || uc->next) - return -EINVAL; - + /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) return -EINVAL; - ret = 0; - mutex_lock(uprobes_hash(inode)); + retry: uprobe = alloc_uprobe(inode, offset); - - if (!uprobe) { - ret = -ENOMEM; - } else if (!consumer_add(uprobe, uc)) { - ret = __uprobe_register(uprobe); - if (ret) { - uprobe->consumers = NULL; - __uprobe_unregister(uprobe); - } else { - set_bit(UPROBE_RUN_HANDLER, &uprobe->flags); - } + if (!uprobe) + return -ENOMEM; + /* + * We can race with uprobe_unregister()->delete_uprobe(). + * Check uprobe_is_active() and retry if it is false. + */ + down_write(&uprobe->register_rwsem); + ret = -EAGAIN; + if (likely(uprobe_is_active(uprobe))) { + ret = __uprobe_register(uprobe, uc); + if (ret) + __uprobe_unregister(uprobe, uc); } + up_write(&uprobe->register_rwsem); + put_uprobe(uprobe); - mutex_unlock(uprobes_hash(inode)); - if (uprobe) - put_uprobe(uprobe); + if (unlikely(ret == -EAGAIN)) + goto retry; + return ret; +} +EXPORT_SYMBOL_GPL(uprobe_register); + +/* + * uprobe_apply - unregister a already registered probe. + * @inode: the file in which the probe has to be removed. + * @offset: offset from the start of the file. + * @uc: consumer which wants to add more or remove some breakpoints + * @add: add or remove the breakpoints + */ +int uprobe_apply(struct inode *inode, loff_t offset, + struct uprobe_consumer *uc, bool add) +{ + struct uprobe *uprobe; + struct uprobe_consumer *con; + int ret = -ENOENT; + + uprobe = find_uprobe(inode, offset); + if (!uprobe) + return ret; + + down_write(&uprobe->register_rwsem); + for (con = uprobe->consumers; con && con != uc ; con = con->next) + ; + if (con) + ret = register_for_each_vma(uprobe, add ? uc : NULL); + up_write(&uprobe->register_rwsem); + put_uprobe(uprobe); return ret; } @@ -884,25 +895,42 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume { struct uprobe *uprobe; - if (!inode || !uc) - return; - uprobe = find_uprobe(inode, offset); if (!uprobe) return; - mutex_lock(uprobes_hash(inode)); + down_write(&uprobe->register_rwsem); + __uprobe_unregister(uprobe, uc); + up_write(&uprobe->register_rwsem); + put_uprobe(uprobe); +} +EXPORT_SYMBOL_GPL(uprobe_unregister); - if (consumer_del(uprobe, uc)) { - if (!uprobe->consumers) { - __uprobe_unregister(uprobe); - clear_bit(UPROBE_RUN_HANDLER, &uprobe->flags); - } +static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct vm_area_struct *vma; + int err = 0; + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long vaddr; + loff_t offset; + + if (!valid_vma(vma, false) || + vma->vm_file->f_mapping->host != uprobe->inode) + continue; + + offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; + if (uprobe->offset < offset || + uprobe->offset >= offset + vma->vm_end - vma->vm_start) + continue; + + vaddr = offset_to_vaddr(vma, uprobe->offset); + err |= remove_breakpoint(uprobe, mm, vaddr); } + up_read(&mm->mmap_sem); - mutex_unlock(uprobes_hash(inode)); - if (uprobe) - put_uprobe(uprobe); + return err; } static struct rb_node * @@ -979,7 +1007,7 @@ int uprobe_mmap(struct vm_area_struct *vma) struct uprobe *uprobe, *u; struct inode *inode; - if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) + if (no_uprobe_events() || !valid_vma(vma, true)) return 0; inode = vma->vm_file->f_mapping->host; @@ -988,9 +1016,14 @@ int uprobe_mmap(struct vm_area_struct *vma) mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); - + /* + * We can race with uprobe_unregister(), this uprobe can be already + * removed. But in this case filter_chain() must return false, all + * consumers have gone away. + */ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - if (!fatal_signal_pending(current)) { + if (!fatal_signal_pending(current) && + filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } @@ -1025,7 +1058,7 @@ vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long e */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) + if (no_uprobe_events() || !valid_vma(vma, false)) return; if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ @@ -1042,22 +1075,14 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon /* Slot allocation for XOL */ static int xol_add_vma(struct xol_area *area) { - struct mm_struct *mm; - int ret; - - area->page = alloc_page(GFP_HIGHUSER); - if (!area->page) - return -ENOMEM; - - ret = -EALREADY; - mm = current->mm; + struct mm_struct *mm = current->mm; + int ret = -EALREADY; down_write(&mm->mmap_sem); if (mm->uprobes_state.xol_area) goto fail; ret = -ENOMEM; - /* Try to map as high as possible, this is only a hint. */ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0); if (area->vaddr & ~PAGE_MASK) { @@ -1073,54 +1098,53 @@ static int xol_add_vma(struct xol_area *area) smp_wmb(); /* pairs with get_xol_area() */ mm->uprobes_state.xol_area = area; ret = 0; - -fail: + fail: up_write(&mm->mmap_sem); - if (ret) - __free_page(area->page); return ret; } -static struct xol_area *get_xol_area(struct mm_struct *mm) -{ - struct xol_area *area; - - area = mm->uprobes_state.xol_area; - smp_read_barrier_depends(); /* pairs with wmb in xol_add_vma() */ - - return area; -} - /* - * xol_alloc_area - Allocate process's xol_area. - * This area will be used for storing instructions for execution out of - * line. + * get_xol_area - Allocate process's xol_area if necessary. + * This area will be used for storing instructions for execution out of line. * * Returns the allocated area or NULL. */ -static struct xol_area *xol_alloc_area(void) +static struct xol_area *get_xol_area(void) { + struct mm_struct *mm = current->mm; struct xol_area *area; + area = mm->uprobes_state.xol_area; + if (area) + goto ret; + area = kzalloc(sizeof(*area), GFP_KERNEL); if (unlikely(!area)) - return NULL; + goto out; area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL); - if (!area->bitmap) - goto fail; + goto free_area; + + area->page = alloc_page(GFP_HIGHUSER); + if (!area->page) + goto free_bitmap; init_waitqueue_head(&area->wq); if (!xol_add_vma(area)) return area; -fail: + __free_page(area->page); + free_bitmap: kfree(area->bitmap); + free_area: kfree(area); - - return get_xol_area(current->mm); + out: + area = mm->uprobes_state.xol_area; + ret: + smp_read_barrier_depends(); /* pairs with wmb in xol_add_vma() */ + return area; } /* @@ -1186,33 +1210,26 @@ static unsigned long xol_take_insn_slot(struct xol_area *area) } /* - * xol_get_insn_slot - If was not allocated a slot, then - * allocate a slot. + * xol_get_insn_slot - allocate a slot for xol. * Returns the allocated slot address or 0. */ -static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot_addr) +static unsigned long xol_get_insn_slot(struct uprobe *uprobe) { struct xol_area *area; unsigned long offset; + unsigned long xol_vaddr; void *vaddr; - area = get_xol_area(current->mm); - if (!area) { - area = xol_alloc_area(); - if (!area) - return 0; - } - current->utask->xol_vaddr = xol_take_insn_slot(area); + area = get_xol_area(); + if (!area) + return 0; - /* - * Initialize the slot if xol_vaddr points to valid - * instruction slot. - */ - if (unlikely(!current->utask->xol_vaddr)) + xol_vaddr = xol_take_insn_slot(area); + if (unlikely(!xol_vaddr)) return 0; - current->utask->vaddr = slot_addr; - offset = current->utask->xol_vaddr & ~PAGE_MASK; + /* Initialize the slot */ + offset = xol_vaddr & ~PAGE_MASK; vaddr = kmap_atomic(area->page); memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES); kunmap_atomic(vaddr); @@ -1222,7 +1239,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot */ flush_dcache_page(area->page); - return current->utask->xol_vaddr; + return xol_vaddr; } /* @@ -1240,8 +1257,7 @@ static void xol_free_insn_slot(struct task_struct *tsk) return; slot_addr = tsk->utask->xol_vaddr; - - if (unlikely(!slot_addr || IS_ERR_VALUE(slot_addr))) + if (unlikely(!slot_addr)) return; area = tsk->mm->uprobes_state.xol_area; @@ -1303,33 +1319,48 @@ void uprobe_copy_process(struct task_struct *t) } /* - * Allocate a uprobe_task object for the task. - * Called when the thread hits a breakpoint for the first time. + * Allocate a uprobe_task object for the task if if necessary. + * Called when the thread hits a breakpoint. * * Returns: * - pointer to new uprobe_task on success * - NULL otherwise */ -static struct uprobe_task *add_utask(void) +static struct uprobe_task *get_utask(void) { - struct uprobe_task *utask; - - utask = kzalloc(sizeof *utask, GFP_KERNEL); - if (unlikely(!utask)) - return NULL; - - current->utask = utask; - return utask; + if (!current->utask) + current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); + return current->utask; } /* Prepare to single-step probed instruction out of line. */ static int -pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long vaddr) +pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr) { - if (xol_get_insn_slot(uprobe, vaddr) && !arch_uprobe_pre_xol(&uprobe->arch, regs)) - return 0; + struct uprobe_task *utask; + unsigned long xol_vaddr; + int err; + + utask = get_utask(); + if (!utask) + return -ENOMEM; + + xol_vaddr = xol_get_insn_slot(uprobe); + if (!xol_vaddr) + return -ENOMEM; + + utask->xol_vaddr = xol_vaddr; + utask->vaddr = bp_vaddr; + + err = arch_uprobe_pre_xol(&uprobe->arch, regs); + if (unlikely(err)) { + xol_free_insn_slot(current); + return err; + } - return -EFAULT; + utask->active_uprobe = uprobe; + utask->state = UTASK_SSTEP; + return 0; } /* @@ -1391,6 +1422,7 @@ static void mmf_recalc_uprobes(struct mm_struct *mm) * This is not strictly accurate, we can race with * uprobe_unregister() and see the already removed * uprobe if delete_uprobe() was not yet called. + * Or this uprobe can be filtered out. */ if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) return; @@ -1452,13 +1484,33 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) return uprobe; } +static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) +{ + struct uprobe_consumer *uc; + int remove = UPROBE_HANDLER_REMOVE; + + down_read(&uprobe->register_rwsem); + for (uc = uprobe->consumers; uc; uc = uc->next) { + int rc = uc->handler(uc, regs); + + WARN(rc & ~UPROBE_HANDLER_MASK, + "bad rc=0x%x from %pf()\n", rc, uc->handler); + remove &= rc; + } + + if (remove && uprobe->consumers) { + WARN_ON(!uprobe_is_active(uprobe)); + unapply_uprobe(uprobe, current->mm); + } + up_read(&uprobe->register_rwsem); +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { - struct uprobe_task *utask; struct uprobe *uprobe; unsigned long bp_vaddr; int uninitialized_var(is_swbp); @@ -1483,6 +1535,10 @@ static void handle_swbp(struct pt_regs *regs) } return; } + + /* change it in advance for ->handler() and restart */ + instruction_pointer_set(regs, bp_vaddr); + /* * TODO: move copy_insn/etc into _register and remove this hack. * After we hit the bp, _unregister + _register can install the @@ -1490,32 +1546,16 @@ static void handle_swbp(struct pt_regs *regs) */ smp_rmb(); /* pairs with wmb() in install_breakpoint() */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) - goto restart; - - utask = current->utask; - if (!utask) { - utask = add_utask(); - /* Cannot allocate; re-execute the instruction. */ - if (!utask) - goto restart; - } + goto out; handler_chain(uprobe, regs); if (can_skip_sstep(uprobe, regs)) goto out; - if (!pre_ssout(uprobe, regs, bp_vaddr)) { - utask->active_uprobe = uprobe; - utask->state = UTASK_SSTEP; + if (!pre_ssout(uprobe, regs, bp_vaddr)) return; - } -restart: - /* - * cannot singlestep; cannot skip instruction; - * re-execute the instruction. - */ - instruction_pointer_set(regs, bp_vaddr); + /* can_skip_sstep() succeeded, or restart if can't singlestep */ out: put_uprobe(uprobe); } @@ -1609,10 +1649,8 @@ static int __init init_uprobes(void) { int i; - for (i = 0; i < UPROBES_HASH_SZ; i++) { - mutex_init(&uprobes_mutex[i]); + for (i = 0; i < UPROBES_HASH_SZ; i++) mutex_init(&uprobes_mmap_mutex[i]); - } if (percpu_init_rwsem(&dup_mmap_sem)) return -ENOMEM; diff --git a/kernel/exit.c b/kernel/exit.c index b4df219..7dd2040 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,6 +85,7 @@ static void __exit_signal(struct task_struct *tsk) bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *uninitialized_var(tty); + cputime_t utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); @@ -123,9 +124,10 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime += tsk->utime; - sig->stime += tsk->stime; - sig->gtime += tsk->gtime; + task_cputime(tsk, &utime, &stime); + sig->utime += utime; + sig->stime += stime; + sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -1092,7 +1094,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) sig = p->signal; psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; - psig->cgtime += p->gtime + sig->gtime + sig->cgtime; + psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += diff --git a/kernel/fork.c b/kernel/fork.c index c535f33..4133876 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1233,6 +1233,12 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifndef CONFIG_VIRT_CPU_ACCOUNTING p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + seqlock_init(&p->vtime_seqlock); + p->vtime_snap = 0; + p->vtime_snap_whence = VTIME_SLEEPING; +#endif + #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif diff --git a/kernel/futex.c b/kernel/futex.c index 19eb089..9618b6e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -60,6 +60,7 @@ #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/ptrace.h> +#include <linux/sched/rt.h> #include <asm/futex.h> diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 6db7a5e..cc47812 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -44,6 +44,8 @@ #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched.h> +#include <linux/sched/sysctl.h> +#include <linux/sched/rt.h> #include <linux/timer.h> #include <asm/uaccess.h> @@ -640,21 +642,9 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) * and expiry check is done in the hrtimer_interrupt or in the softirq. */ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base, - int wakeup) + struct hrtimer_clock_base *base) { - if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) { - if (wakeup) { - raw_spin_unlock(&base->cpu_base->lock); - raise_softirq_irqoff(HRTIMER_SOFTIRQ); - raw_spin_lock(&base->cpu_base->lock); - } else - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); - - return 1; - } - - return 0; + return base->cpu_base->hres_active && hrtimer_reprogram(timer, base); } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) @@ -735,8 +725,7 @@ static inline int hrtimer_switch_to_hres(void) { return 0; } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base, - int wakeup) + struct hrtimer_clock_base *base) { return 0; } @@ -995,8 +984,21 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * * XXX send_remote_softirq() ? */ - if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) - hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases) + && hrtimer_enqueue_reprogram(timer, new_base)) { + if (wakeup) { + /* + * We need to drop cpu_base->lock to avoid a + * lock ordering issue vs. rq->lock. + */ + raw_spin_unlock(&new_base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + local_irq_restore(flags); + return ret; + } else { + __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + } unlock_hrtimer_base(timer, &flags); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 3aca9f2..cbd97ce 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -90,27 +90,41 @@ int irq_set_handler_data(unsigned int irq, void *data) EXPORT_SYMBOL(irq_set_handler_data); /** - * irq_set_msi_desc - set MSI descriptor data for an irq - * @irq: Interrupt number - * @entry: Pointer to MSI descriptor data + * irq_set_msi_desc_off - set MSI descriptor data for an irq at offset + * @irq_base: Interrupt number base + * @irq_offset: Interrupt number offset + * @entry: Pointer to MSI descriptor data * - * Set the MSI descriptor entry for an irq + * Set the MSI descriptor entry for an irq at offset */ -int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry) +int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, + struct msi_desc *entry) { unsigned long flags; - struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + struct irq_desc *desc = irq_get_desc_lock(irq_base + irq_offset, &flags, IRQ_GET_DESC_CHECK_GLOBAL); if (!desc) return -EINVAL; desc->irq_data.msi_desc = entry; - if (entry) - entry->irq = irq; + if (entry && !irq_offset) + entry->irq = irq_base; irq_put_desc_unlock(desc, flags); return 0; } /** + * irq_set_msi_desc - set MSI descriptor data for an irq + * @irq: Interrupt number + * @entry: Pointer to MSI descriptor data + * + * Set the MSI descriptor entry for an irq + */ +int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry) +{ + return irq_set_msi_desc_off(irq, 0, entry); +} + +/** * irq_set_chip_data - set irq chip data for an irq * @irq: Interrupt number * @data: Pointer to chip specific data diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e49a288..fa17855 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -16,6 +16,7 @@ #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/task_work.h> #include "internals.h" @@ -1524,6 +1525,7 @@ void enable_percpu_irq(unsigned int irq, unsigned int type) out: irq_put_desc_unlock(desc, flags); } +EXPORT_SYMBOL_GPL(enable_percpu_irq); void disable_percpu_irq(unsigned int irq) { @@ -1537,6 +1539,7 @@ void disable_percpu_irq(unsigned int irq) irq_percpu_disable(desc, cpu); irq_put_desc_unlock(desc, flags); } +EXPORT_SYMBOL_GPL(disable_percpu_irq); /* * Internal function to unregister a percpu irqaction. diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 611cd60..7b5f012 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -80,13 +80,11 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force) /* * All handlers must agree on IRQF_SHARED, so we test just the - * first. Check for action->next as well. + * first. */ action = desc->action; if (!action || !(action->flags & IRQF_SHARED) || - (action->flags & __IRQF_TIMER) || - (action->handler(irq, action->dev_id) == IRQ_HANDLED) || - !action->next) + (action->flags & __IRQF_TIMER)) goto out; /* Already running on another processor */ @@ -104,6 +102,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force) do { if (handle_irq_event(desc) == IRQ_HANDLED) ret = IRQ_HANDLED; + /* Make sure that there is still a valid action */ action = desc->action; } while ((desc->istate & IRQS_PENDING) && action); desc->istate &= ~IRQS_POLL_INPROGRESS; diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 1588e3b..55fcce6 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -12,37 +12,36 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> +#include <linux/sched.h> +#include <linux/tick.h> +#include <linux/cpu.h> +#include <linux/notifier.h> #include <asm/processor.h> -/* - * An entry can be in one of four states: - * - * free NULL, 0 -> {claimed} : free to be used - * claimed NULL, 3 -> {pending} : claimed to be enqueued - * pending next, 3 -> {busy} : queued, pending callback - * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed - */ - -#define IRQ_WORK_PENDING 1UL -#define IRQ_WORK_BUSY 2UL -#define IRQ_WORK_FLAGS 3UL static DEFINE_PER_CPU(struct llist_head, irq_work_list); +static DEFINE_PER_CPU(int, irq_work_raised); /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { - unsigned long flags, nflags; + unsigned long flags, oflags, nflags; + /* + * Start with our best wish as a premise but only trust any + * flag value after cmpxchg() result. + */ + flags = work->flags & ~IRQ_WORK_PENDING; for (;;) { - flags = work->flags; - if (flags & IRQ_WORK_PENDING) - return false; nflags = flags | IRQ_WORK_FLAGS; - if (cmpxchg(&work->flags, flags, nflags) == flags) + oflags = cmpxchg(&work->flags, flags, nflags); + if (oflags == flags) break; + if (oflags & IRQ_WORK_PENDING) + return false; + flags = oflags; cpu_relax(); } @@ -57,57 +56,69 @@ void __weak arch_irq_work_raise(void) } /* - * Queue the entry and raise the IPI if needed. + * Enqueue the irq_work @entry unless it's already pending + * somewhere. + * + * Can be re-enqueued while the callback is still in progress. */ -static void __irq_work_queue(struct irq_work *work) +void irq_work_queue(struct irq_work *work) { - bool empty; + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return; + /* Queue the entry and raise the IPI if needed. */ preempt_disable(); - empty = llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); - /* The list was empty, raise self-interrupt to start processing. */ - if (empty) - arch_irq_work_raise(); + llist_add(&work->llnode, &__get_cpu_var(irq_work_list)); + + /* + * If the work is not "lazy" or the tick is stopped, raise the irq + * work interrupt (if supported by the arch), otherwise, just wait + * for the next tick. + */ + if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) { + if (!this_cpu_cmpxchg(irq_work_raised, 0, 1)) + arch_irq_work_raise(); + } preempt_enable(); } +EXPORT_SYMBOL_GPL(irq_work_queue); -/* - * Enqueue the irq_work @entry, returns true on success, failure when the - * @entry was already enqueued by someone else. - * - * Can be re-enqueued while the callback is still in progress. - */ -bool irq_work_queue(struct irq_work *work) +bool irq_work_needs_cpu(void) { - if (!irq_work_claim(work)) { - /* - * Already enqueued, can't do! - */ + struct llist_head *this_list; + + this_list = &__get_cpu_var(irq_work_list); + if (llist_empty(this_list)) return false; - } - __irq_work_queue(work); + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); + return true; } -EXPORT_SYMBOL_GPL(irq_work_queue); -/* - * Run the irq_work entries on this cpu. Requires to be ran from hardirq - * context with local IRQs disabled. - */ -void irq_work_run(void) +static void __irq_work_run(void) { + unsigned long flags; struct irq_work *work; struct llist_head *this_list; struct llist_node *llnode; + + /* + * Reset the "raised" state right before we check the list because + * an NMI may enqueue after we find the list empty from the runner. + */ + __this_cpu_write(irq_work_raised, 0); + barrier(); + this_list = &__get_cpu_var(irq_work_list); if (llist_empty(this_list)) return; - BUG_ON(!in_irq()); BUG_ON(!irqs_disabled()); llnode = llist_del_all(this_list); @@ -119,16 +130,31 @@ void irq_work_run(void) /* * Clear the PENDING bit, after this point the @work * can be re-used. + * Make it immediately visible so that other CPUs trying + * to claim that work don't rely on us to handle their data + * while we are in the middle of the func. */ - work->flags = IRQ_WORK_BUSY; + flags = work->flags & ~IRQ_WORK_PENDING; + xchg(&work->flags, flags); + work->func(work); /* * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ - (void)cmpxchg(&work->flags, IRQ_WORK_BUSY, 0); + (void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); } } + +/* + * Run the irq_work entries on this cpu. Requires to be ran from hardirq + * context with local IRQs disabled. + */ +void irq_work_run(void) +{ + BUG_ON(!in_irq()); + __irq_work_run(); +} EXPORT_SYMBOL_GPL(irq_work_run); /* @@ -143,3 +169,35 @@ void irq_work_sync(struct irq_work *work) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); + +#ifdef CONFIG_HOTPLUG_CPU +static int irq_work_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + case CPU_DYING: + /* Called from stop_machine */ + if (WARN_ON_ONCE(cpu != smp_processor_id())) + break; + __irq_work_run(); + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block cpu_notify; + +static __init int irq_work_init_cpu_notifier(void) +{ + cpu_notify.notifier_call = irq_work_cpu_notify; + cpu_notify.priority = 0; + register_cpu_notifier(&cpu_notify); + return 0; +} +device_initcall(irq_work_init_cpu_notifier); + +#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/kmod.c b/kernel/kmod.c index 0023a87..56dd349 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -38,6 +38,7 @@ #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> +#include <linux/async.h> #include <asm/uaccess.h> #include <trace/events/module.h> @@ -130,6 +131,14 @@ int __request_module(bool wait, const char *fmt, ...) #define MAX_KMOD_CONCURRENT 50 /* Completely arbitrary value - KAO */ static int kmod_loop_msg; + /* + * We don't allow synchronous module loading from async. Module + * init may invoke async_synchronize_full() which will end up + * waiting for this task which already is waiting for the module + * loading to complete, leading to a deadlock. + */ + WARN_ON_ONCE(wait && current_is_async()); + va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 098f396..550294d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -471,7 +471,6 @@ static LIST_HEAD(unoptimizing_list); static void kprobe_optimizer(struct work_struct *work); static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); -static DECLARE_COMPLETION(optimizer_comp); #define OPTIMIZE_DELAY 5 /* @@ -552,8 +551,7 @@ static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list) /* Start optimizer after OPTIMIZE_DELAY passed */ static __kprobes void kick_kprobe_optimizer(void) { - if (!delayed_work_pending(&optimizing_work)) - schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); + schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); } /* Kprobe jump optimizer */ @@ -592,16 +590,25 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); - else - /* Wake up all waiters */ - complete_all(&optimizer_comp); } /* Wait for completing optimization and unoptimization */ static __kprobes void wait_for_kprobe_optimizer(void) { - if (delayed_work_pending(&optimizing_work)) - wait_for_completion(&optimizer_comp); + mutex_lock(&kprobe_mutex); + + while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { + mutex_unlock(&kprobe_mutex); + + /* this will also make optimizing_work execute immmediately */ + flush_delayed_work(&optimizing_work); + /* @optimizing_work might not have been queued yet, relax */ + cpu_relax(); + + mutex_lock(&kprobe_mutex); + } + + mutex_unlock(&kprobe_mutex); } /* Optimize kprobe if p is ready to be optimized */ @@ -919,7 +926,7 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) } #endif /* CONFIG_OPTPROBES */ -#ifdef KPROBES_CAN_USE_FTRACE +#ifdef CONFIG_KPROBES_ON_FTRACE static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS, @@ -964,7 +971,7 @@ static void __kprobes disarm_kprobe_ftrace(struct kprobe *p) (unsigned long)p->addr, 1, 0); WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); } -#else /* !KPROBES_CAN_USE_FTRACE */ +#else /* !CONFIG_KPROBES_ON_FTRACE */ #define prepare_kprobe(p) arch_prepare_kprobe(p) #define arm_kprobe_ftrace(p) do {} while (0) #define disarm_kprobe_ftrace(p) do {} while (0) @@ -1414,12 +1421,12 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p, */ ftrace_addr = ftrace_location((unsigned long)p->addr); if (ftrace_addr) { -#ifdef KPROBES_CAN_USE_FTRACE +#ifdef CONFIG_KPROBES_ON_FTRACE /* Given address is not on the instruction boundary */ if ((unsigned long)p->addr != ftrace_addr) return -EILSEQ; p->flags |= KPROBE_FLAG_FTRACE; -#else /* !KPROBES_CAN_USE_FTRACE */ +#else /* !CONFIG_KPROBES_ON_FTRACE */ return -EINVAL; #endif } diff --git a/kernel/mutex.c b/kernel/mutex.c index a307cc9..52f2301 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -19,6 +19,7 @@ */ #include <linux/mutex.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/interrupt.h> diff --git a/kernel/pid.c b/kernel/pid.c index de9af60..f2c6a68 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -331,7 +331,7 @@ out: return pid; out_unlock: - spin_unlock(&pidmap_lock); + spin_unlock_irq(&pidmap_lock); out_free: while (++i <= ns->level) free_pidmap(pid->numbers + i); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index a278cad..8fd709c 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -155,11 +155,19 @@ static void bump_cpu_timer(struct k_itimer *timer, static inline cputime_t prof_ticks(struct task_struct *p) { - return p->utime + p->stime; + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + + return utime + stime; } static inline cputime_t virt_ticks(struct task_struct *p) { - return p->utime; + cputime_t utime; + + task_cputime(p, &utime, NULL); + + return utime; } static int @@ -471,18 +479,23 @@ static void cleanup_timers(struct list_head *head, */ void posix_cpu_timers_exit(struct task_struct *tsk) { + cputime_t utime, stime; + add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); + task_cputime(tsk, &utime, &stime); cleanup_timers(tsk->cpu_timers, - tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); + utime, stime, tsk->se.sum_exec_runtime); } void posix_cpu_timers_exit_group(struct task_struct *tsk) { struct signal_struct *const sig = tsk->signal; + cputime_t utime, stime; + task_cputime(tsk, &utime, &stime); cleanup_timers(tsk->signal->cpu_timers, - tsk->utime + sig->utime, tsk->stime + sig->stime, + utime + sig->utime, stime + sig->stime, tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } @@ -1226,11 +1239,14 @@ static inline int task_cputime_expired(const struct task_cputime *sample, static inline int fastpath_timer_check(struct task_struct *tsk) { struct signal_struct *sig; + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); if (!task_cputime_zero(&tsk->cputime_expires)) { struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, + .utime = utime, + .stime = stime, .sum_exec_runtime = tsk->se.sum_exec_runtime }; @@ -1401,8 +1417,10 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, while (!signal_pending(current)) { if (timer.it.cpu.expires.sched == 0) { /* - * Our timer fired and was reset. + * Our timer fired and was reset, below + * deletion can not fail. */ + posix_cpu_timer_del(&timer); spin_unlock_irq(&timer.it_lock); return 0; } @@ -1420,9 +1438,26 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, * We were interrupted by a signal. */ sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp); - posix_cpu_timer_set(&timer, 0, &zero_it, it); + error = posix_cpu_timer_set(&timer, 0, &zero_it, it); + if (!error) { + /* + * Timer is now unarmed, deletion can not fail. + */ + posix_cpu_timer_del(&timer); + } spin_unlock_irq(&timer.it_lock); + while (error == TIMER_RETRY) { + /* + * We need to handle case when timer was or is in the + * middle of firing. In other cases we already freed + * resources. + */ + spin_lock_irq(&timer.it_lock); + error = posix_cpu_timer_del(&timer); + spin_unlock_irq(&timer.it_lock); + } + if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) { /* * It actually did fire already. diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 69185ae..10349d5 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -997,7 +997,7 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, err = kc->clock_adj(which_clock, &ktx); - if (!err && copy_to_user(utx, &ktx, sizeof(ktx))) + if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx))) return -EFAULT; return err; diff --git a/kernel/printk.c b/kernel/printk.c index 357f714..f24633a 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -42,6 +42,7 @@ #include <linux/notifier.h> #include <linux/rculist.h> #include <linux/poll.h> +#include <linux/irq_work.h> #include <asm/uaccess.h> @@ -87,12 +88,6 @@ static DEFINE_SEMAPHORE(console_sem); struct console *console_drivers; EXPORT_SYMBOL_GPL(console_drivers); -#ifdef CONFIG_LOCKDEP -static struct lockdep_map console_lock_dep_map = { - .name = "console_lock" -}; -#endif - /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's @@ -1924,7 +1919,6 @@ void console_lock(void) return; console_locked = 1; console_may_schedule = 1; - mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_); } EXPORT_SYMBOL(console_lock); @@ -1946,7 +1940,6 @@ int console_trylock(void) } console_locked = 1; console_may_schedule = 0; - mutex_acquire(&console_lock_dep_map, 0, 1, _RET_IP_); return 1; } EXPORT_SYMBOL(console_trylock); @@ -1967,30 +1960,32 @@ int is_console_locked(void) static DEFINE_PER_CPU(int, printk_pending); static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); -void printk_tick(void) +static void wake_up_klogd_work_func(struct irq_work *irq_work) { - if (__this_cpu_read(printk_pending)) { - int pending = __this_cpu_xchg(printk_pending, 0); - if (pending & PRINTK_PENDING_SCHED) { - char *buf = __get_cpu_var(printk_sched_buf); - printk(KERN_WARNING "[sched_delayed] %s", buf); - } - if (pending & PRINTK_PENDING_WAKEUP) - wake_up_interruptible(&log_wait); + int pending = __this_cpu_xchg(printk_pending, 0); + + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); } -} -int printk_needs_cpu(int cpu) -{ - if (cpu_is_offline(cpu)) - printk_tick(); - return __this_cpu_read(printk_pending); + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); } +static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { + .func = wake_up_klogd_work_func, + .flags = IRQ_WORK_LAZY, +}; + void wake_up_klogd(void) { - if (waitqueue_active(&log_wait)) + preempt_disable(); + if (waitqueue_active(&log_wait)) { this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); + irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + } + preempt_enable(); } static void console_cont_flush(char *text, size_t size) @@ -2107,7 +2102,6 @@ skip: local_irq_restore(flags); } console_locked = 0; - mutex_release(&console_lock_dep_map, 1, _RET_IP_); /* Release the exclusive_console once it is used */ if (unlikely(exclusive_console)) @@ -2471,6 +2465,7 @@ int printk_sched(const char *fmt, ...) va_end(args); __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); + irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); local_irq_restore(flags); return r; diff --git a/kernel/profile.c b/kernel/profile.c index 1f39181..dc3384e 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -37,9 +37,6 @@ struct profile_hit { #define NR_PROFILE_HIT (PAGE_SIZE/sizeof(struct profile_hit)) #define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ) -/* Oprofile timer tick hook */ -static int (*timer_hook)(struct pt_regs *) __read_mostly; - static atomic_t *prof_buffer; static unsigned long prof_len, prof_shift; @@ -208,25 +205,6 @@ int profile_event_unregister(enum profile_type type, struct notifier_block *n) } EXPORT_SYMBOL_GPL(profile_event_unregister); -int register_timer_hook(int (*hook)(struct pt_regs *)) -{ - if (timer_hook) - return -EBUSY; - timer_hook = hook; - return 0; -} -EXPORT_SYMBOL_GPL(register_timer_hook); - -void unregister_timer_hook(int (*hook)(struct pt_regs *)) -{ - WARN_ON(hook != timer_hook); - timer_hook = NULL; - /* make sure all CPUs see the NULL hook */ - synchronize_sched(); /* Allow ongoing interrupts to complete. */ -} -EXPORT_SYMBOL_GPL(unregister_timer_hook); - - #ifdef CONFIG_SMP /* * Each cpu has a pair of open-addressed hashtables for pending @@ -436,8 +414,6 @@ void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); - if (type == CPU_PROFILING && timer_hook) - timer_hook(regs); if (!user_mode(regs) && prof_cpu_mask != NULL && cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) profile_hit(type, (void *)profile_pc(regs)); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 6cbeaae..acbd284 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -712,6 +712,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type, kiov->iov_len, kiov->iov_base); } +/* + * This is declared in linux/regset.h and defined in machine-dependent + * code. We put the export here, near the primary machine-neutral use, + * to ensure no machine forgets it. + */ +EXPORT_SYMBOL_GPL(task_user_regset_view); #endif int ptrace_request(struct task_struct *child, long request, diff --git a/kernel/rcu.h b/kernel/rcu.h index 20dfba5..7f8e759 100644 --- a/kernel/rcu.h +++ b/kernel/rcu.h @@ -111,4 +111,11 @@ static inline bool __rcu_reclaim(char *rn, struct rcu_head *head) extern int rcu_expedited; +#ifdef CONFIG_RCU_STALL_COMMON + +extern int rcu_cpu_stall_suppress; +int rcu_jiffies_till_stall_check(void); + +#endif /* #ifdef CONFIG_RCU_STALL_COMMON */ + #endif /* __LINUX_RCU_H */ diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index a2cf761..48ab703 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -404,11 +404,65 @@ EXPORT_SYMBOL_GPL(rcuhead_debug_descr); #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE) -void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp) +void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp, + unsigned long secs, + unsigned long c_old, unsigned long c) { - trace_rcu_torture_read(rcutorturename, rhp); + trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c); } EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); #else -#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) #endif + +#ifdef CONFIG_RCU_STALL_COMMON + +#ifdef CONFIG_PROVE_RCU +#define RCU_STALL_DELAY_DELTA (5 * HZ) +#else +#define RCU_STALL_DELAY_DELTA 0 +#endif + +int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ +int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; + +module_param(rcu_cpu_stall_suppress, int, 0644); +module_param(rcu_cpu_stall_timeout, int, 0644); + +int rcu_jiffies_till_stall_check(void) +{ + int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout); + + /* + * Limit check must be consistent with the Kconfig limits + * for CONFIG_RCU_CPU_STALL_TIMEOUT. + */ + if (till_stall_check < 3) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 3; + till_stall_check = 3; + } else if (till_stall_check > 300) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 300; + till_stall_check = 300; + } + return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; +} + +static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) +{ + rcu_cpu_stall_suppress = 1; + return NOTIFY_DONE; +} + +static struct notifier_block rcu_panic_block = { + .notifier_call = rcu_panic, +}; + +static int __init check_cpu_stall_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block); + return 0; +} +early_initcall(check_cpu_stall_init); + +#endif /* #ifdef CONFIG_RCU_STALL_COMMON */ diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index e7dce58..a0714a5 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -51,10 +51,10 @@ static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_ctrlblk *rcp); -#include "rcutiny_plugin.h" - static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; +#include "rcutiny_plugin.h" + /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ static void rcu_idle_enter_common(long long newval) { @@ -193,7 +193,7 @@ EXPORT_SYMBOL(rcu_is_cpu_idle); * interrupts don't count, we must be running at the first interrupt * level. */ -int rcu_is_cpu_rrupt_from_idle(void) +static int rcu_is_cpu_rrupt_from_idle(void) { return rcu_dynticks_nesting <= 1; } @@ -205,6 +205,7 @@ int rcu_is_cpu_rrupt_from_idle(void) */ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) { + reset_cpu_stall_ticks(rcp); if (rcp->rcucblist != NULL && rcp->donetail != rcp->curtail) { rcp->donetail = rcp->curtail; @@ -251,6 +252,7 @@ void rcu_bh_qs(int cpu) */ void rcu_check_callbacks(int cpu, int user) { + check_cpu_stalls(); if (user || rcu_is_cpu_rrupt_from_idle()) rcu_sched_qs(cpu); else if (!in_softirq()) diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index f85016a..8a23300 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -33,6 +33,9 @@ struct rcu_ctrlblk { struct rcu_head **donetail; /* ->next pointer of last "done" CB. */ struct rcu_head **curtail; /* ->next pointer of last CB. */ RCU_TRACE(long qlen); /* Number of pending CBs. */ + RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */ + RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */ + RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */ RCU_TRACE(char *name); /* Name of RCU type. */ }; @@ -54,6 +57,51 @@ int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +#ifdef CONFIG_RCU_TRACE + +static void check_cpu_stall(struct rcu_ctrlblk *rcp) +{ + unsigned long j; + unsigned long js; + + if (rcu_cpu_stall_suppress) + return; + rcp->ticks_this_gp++; + j = jiffies; + js = rcp->jiffies_stall; + if (*rcp->curtail && ULONG_CMP_GE(j, js)) { + pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", + rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting, + jiffies - rcp->gp_start, rcp->qlen); + dump_stack(); + } + if (*rcp->curtail && ULONG_CMP_GE(j, js)) + rcp->jiffies_stall = jiffies + + 3 * rcu_jiffies_till_stall_check() + 3; + else if (ULONG_CMP_GE(j, js)) + rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check(); +} + +static void check_cpu_stall_preempt(void); + +#endif /* #ifdef CONFIG_RCU_TRACE */ + +static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) +{ +#ifdef CONFIG_RCU_TRACE + rcp->ticks_this_gp = 0; + rcp->gp_start = jiffies; + rcp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check(); +#endif /* #ifdef CONFIG_RCU_TRACE */ +} + +static void check_cpu_stalls(void) +{ + RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk)); + RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk)); + RCU_TRACE(check_cpu_stall_preempt()); +} + #ifdef CONFIG_TINY_PREEMPT_RCU #include <linux/delay.h> @@ -448,6 +496,7 @@ static void rcu_preempt_start_gp(void) /* Official start of GP. */ rcu_preempt_ctrlblk.gpnum++; RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++); + reset_cpu_stall_ticks(&rcu_preempt_ctrlblk.rcb); /* Any blocked RCU readers block new GP. */ if (rcu_preempt_blocked_readers_any()) @@ -1054,4 +1103,11 @@ MODULE_AUTHOR("Paul E. McKenney"); MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation"); MODULE_LICENSE("GPL"); +static void check_cpu_stall_preempt(void) +{ +#ifdef CONFIG_TINY_PREEMPT_RCU + check_cpu_stall(&rcu_preempt_ctrlblk.rcb); +#endif /* #ifdef CONFIG_TINY_PREEMPT_RCU */ +} + #endif /* #ifdef CONFIG_RCU_TRACE */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 31dea01..e1f3a8c 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -46,6 +46,7 @@ #include <linux/stat.h> #include <linux/srcu.h> #include <linux/slab.h> +#include <linux/trace_clock.h> #include <asm/byteorder.h> MODULE_LICENSE("GPL"); @@ -207,6 +208,20 @@ MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot"); #define rcu_can_boost() 0 #endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */ +#ifdef CONFIG_RCU_TRACE +static u64 notrace rcu_trace_clock_local(void) +{ + u64 ts = trace_clock_local(); + unsigned long __maybe_unused ts_rem = do_div(ts, NSEC_PER_USEC); + return ts; +} +#else /* #ifdef CONFIG_RCU_TRACE */ +static u64 notrace rcu_trace_clock_local(void) +{ + return 0ULL; +} +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + static unsigned long shutdown_time; /* jiffies to system shutdown. */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ @@ -845,7 +860,7 @@ static int rcu_torture_boost(void *arg) /* Wait for the next test interval. */ oldstarttime = boost_starttime; while (ULONG_CMP_LT(jiffies, oldstarttime)) { - schedule_timeout_uninterruptible(1); + schedule_timeout_interruptible(oldstarttime - jiffies); rcu_stutter_wait("rcu_torture_boost"); if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) @@ -1028,7 +1043,6 @@ void rcutorture_trace_dump(void) return; if (atomic_xchg(&beenhere, 1) != 0) return; - do_trace_rcu_torture_read(cur_ops->name, (struct rcu_head *)~0UL); ftrace_dump(DUMP_ALL); } @@ -1042,13 +1056,16 @@ static void rcu_torture_timer(unsigned long unused) { int idx; int completed; + int completed_end; static DEFINE_RCU_RANDOM(rand); static DEFINE_SPINLOCK(rand_lock); struct rcu_torture *p; int pipe_count; + unsigned long long ts; idx = cur_ops->readlock(); completed = cur_ops->completed(); + ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || @@ -1058,7 +1075,6 @@ static void rcu_torture_timer(unsigned long unused) cur_ops->readunlock(idx); return; } - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); spin_lock(&rand_lock); @@ -1071,10 +1087,14 @@ static void rcu_torture_timer(unsigned long unused) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - if (pipe_count > 1) + completed_end = cur_ops->completed(); + if (pipe_count > 1) { + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts, + completed, completed_end); rcutorture_trace_dump(); + } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = cur_ops->completed() - completed; + completed = completed_end - completed; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; @@ -1094,11 +1114,13 @@ static int rcu_torture_reader(void *arg) { int completed; + int completed_end; int idx; DEFINE_RCU_RANDOM(rand); struct rcu_torture *p; int pipe_count; struct timer_list t; + unsigned long long ts; VERBOSE_PRINTK_STRING("rcu_torture_reader task started"); set_user_nice(current, 19); @@ -1112,6 +1134,7 @@ rcu_torture_reader(void *arg) } idx = cur_ops->readlock(); completed = cur_ops->completed(); + ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || @@ -1122,7 +1145,6 @@ rcu_torture_reader(void *arg) schedule_timeout_interruptible(HZ); continue; } - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); cur_ops->read_delay(&rand); @@ -1132,10 +1154,14 @@ rcu_torture_reader(void *arg) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } - if (pipe_count > 1) + completed_end = cur_ops->completed(); + if (pipe_count > 1) { + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, + ts, completed, completed_end); rcutorture_trace_dump(); + } __this_cpu_inc(rcu_torture_count[pipe_count]); - completed = cur_ops->completed() - completed; + completed = completed_end - completed; if (completed > RCU_TORTURE_PIPE_LEN) { /* Should not happen, but... */ completed = RCU_TORTURE_PIPE_LEN; @@ -1301,19 +1327,35 @@ static void rcu_torture_shuffle_tasks(void) set_cpus_allowed_ptr(reader_tasks[i], shuffle_tmp_mask); } - if (fakewriter_tasks) { for (i = 0; i < nfakewriters; i++) if (fakewriter_tasks[i]) set_cpus_allowed_ptr(fakewriter_tasks[i], shuffle_tmp_mask); } - if (writer_task) set_cpus_allowed_ptr(writer_task, shuffle_tmp_mask); - if (stats_task) set_cpus_allowed_ptr(stats_task, shuffle_tmp_mask); + if (stutter_task) + set_cpus_allowed_ptr(stutter_task, shuffle_tmp_mask); + if (fqs_task) + set_cpus_allowed_ptr(fqs_task, shuffle_tmp_mask); + if (shutdown_task) + set_cpus_allowed_ptr(shutdown_task, shuffle_tmp_mask); +#ifdef CONFIG_HOTPLUG_CPU + if (onoff_task) + set_cpus_allowed_ptr(onoff_task, shuffle_tmp_mask); +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + if (stall_task) + set_cpus_allowed_ptr(stall_task, shuffle_tmp_mask); + if (barrier_cbs_tasks) + for (i = 0; i < n_barrier_cbs; i++) + if (barrier_cbs_tasks[i]) + set_cpus_allowed_ptr(barrier_cbs_tasks[i], + shuffle_tmp_mask); + if (barrier_task) + set_cpus_allowed_ptr(barrier_task, shuffle_tmp_mask); if (rcu_idle_cpu == -1) rcu_idle_cpu = num_online_cpus() - 1; @@ -1749,7 +1791,7 @@ static int rcu_torture_barrier_init(void) barrier_cbs_wq = kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]), GFP_KERNEL); - if (barrier_cbs_tasks == NULL || barrier_cbs_wq == 0) + if (barrier_cbs_tasks == NULL || !barrier_cbs_wq) return -ENOMEM; for (i = 0; i < n_barrier_cbs; i++) { init_waitqueue_head(&barrier_cbs_wq[i]); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index e441b77..5b8ad82 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -105,7 +105,7 @@ int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ * The rcu_scheduler_active variable transitions from zero to one just * before the first task is spawned. So when this variable is zero, RCU * can assume that there is but one task, allowing RCU to (for example) - * optimized synchronize_sched() to a simple barrier(). When this variable + * optimize synchronize_sched() to a simple barrier(). When this variable * is one, RCU must actually do all the hard work required to detect real * grace periods. This variable is also used to suppress boot-time false * positives from lockdep-RCU error checking. @@ -217,12 +217,6 @@ module_param(blimit, long, 0444); module_param(qhimark, long, 0444); module_param(qlowmark, long, 0444); -int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ -int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; - -module_param(rcu_cpu_stall_suppress, int, 0644); -module_param(rcu_cpu_stall_timeout, int, 0644); - static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS; static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS; @@ -305,17 +299,27 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) } /* - * Does the current CPU require a yet-as-unscheduled grace period? + * Does the current CPU require a not-yet-started grace period? + * The caller must have disabled interrupts to prevent races with + * normal callback registry. */ static int cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { - struct rcu_head **ntp; + int i; - ntp = rdp->nxttail[RCU_DONE_TAIL + - (ACCESS_ONCE(rsp->completed) != rdp->completed)]; - return rdp->nxttail[RCU_DONE_TAIL] && ntp && *ntp && - !rcu_gp_in_progress(rsp); + if (rcu_gp_in_progress(rsp)) + return 0; /* No, a grace period is already in progress. */ + if (!rdp->nxttail[RCU_NEXT_TAIL]) + return 0; /* No, this is a no-CBs (or offline) CPU. */ + if (*rdp->nxttail[RCU_NEXT_READY_TAIL]) + return 1; /* Yes, this CPU has newly registered callbacks. */ + for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) + if (rdp->nxttail[i - 1] != rdp->nxttail[i] && + ULONG_CMP_LT(ACCESS_ONCE(rsp->completed), + rdp->nxtcompleted[i])) + return 1; /* Yes, CBs for future grace period. */ + return 0; /* No grace period needed. */ } /* @@ -336,7 +340,7 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval, bool user) { - trace_rcu_dyntick("Start", oldval, 0); + trace_rcu_dyntick("Start", oldval, rdtp->dynticks_nesting); if (!user && !is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); @@ -727,7 +731,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); * interrupt from idle, return true. The caller must have at least * disabled preemption. */ -int rcu_is_cpu_rrupt_from_idle(void) +static int rcu_is_cpu_rrupt_from_idle(void) { return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1; } @@ -793,28 +797,10 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 0; } -static int jiffies_till_stall_check(void) -{ - int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout); - - /* - * Limit check must be consistent with the Kconfig limits - * for CONFIG_RCU_CPU_STALL_TIMEOUT. - */ - if (till_stall_check < 3) { - ACCESS_ONCE(rcu_cpu_stall_timeout) = 3; - till_stall_check = 3; - } else if (till_stall_check > 300) { - ACCESS_ONCE(rcu_cpu_stall_timeout) = 300; - till_stall_check = 300; - } - return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; -} - static void record_gp_stall_check_time(struct rcu_state *rsp) { rsp->gp_start = jiffies; - rsp->jiffies_stall = jiffies + jiffies_till_stall_check(); + rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check(); } /* @@ -857,7 +843,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } - rsp->jiffies_stall = jiffies + 3 * jiffies_till_stall_check() + 3; + rsp->jiffies_stall = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -935,7 +921,7 @@ static void print_cpu_stall(struct rcu_state *rsp) raw_spin_lock_irqsave(&rnp->lock, flags); if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall)) rsp->jiffies_stall = jiffies + - 3 * jiffies_till_stall_check() + 3; + 3 * rcu_jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); set_need_resched(); /* kick ourselves to get things going. */ @@ -966,12 +952,6 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) } } -static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) -{ - rcu_cpu_stall_suppress = 1; - return NOTIFY_DONE; -} - /** * rcu_cpu_stall_reset - prevent further stall warnings in current grace period * @@ -989,15 +969,6 @@ void rcu_cpu_stall_reset(void) rsp->jiffies_stall = jiffies + ULONG_MAX / 2; } -static struct notifier_block rcu_panic_block = { - .notifier_call = rcu_panic, -}; - -static void __init check_cpu_stall_init(void) -{ - atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block); -} - /* * Update CPU-local rcu_data state to record the newly noticed grace period. * This is used both when we started the grace period and when we notice @@ -1071,6 +1042,145 @@ static void init_callback_list(struct rcu_data *rdp) } /* + * Determine the value that ->completed will have at the end of the + * next subsequent grace period. This is used to tag callbacks so that + * a CPU can invoke callbacks in a timely fashion even if that CPU has + * been dyntick-idle for an extended period with callbacks under the + * influence of RCU_FAST_NO_HZ. + * + * The caller must hold rnp->lock with interrupts disabled. + */ +static unsigned long rcu_cbs_completed(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + /* + * If RCU is idle, we just wait for the next grace period. + * But we can only be sure that RCU is idle if we are looking + * at the root rcu_node structure -- otherwise, a new grace + * period might have started, but just not yet gotten around + * to initializing the current non-root rcu_node structure. + */ + if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed) + return rnp->completed + 1; + + /* + * Otherwise, wait for a possible partial grace period and + * then the subsequent full grace period. + */ + return rnp->completed + 2; +} + +/* + * If there is room, assign a ->completed number to any callbacks on + * this CPU that have not already been assigned. Also accelerate any + * callbacks that were previously assigned a ->completed number that has + * since proven to be too conservative, which can happen if callbacks get + * assigned a ->completed number while RCU is idle, but with reference to + * a non-root rcu_node structure. This function is idempotent, so it does + * not hurt to call it repeatedly. + * + * The caller must hold rnp->lock with interrupts disabled. + */ +static void rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + unsigned long c; + int i; + + /* If the CPU has no callbacks, nothing to do. */ + if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) + return; + + /* + * Starting from the sublist containing the callbacks most + * recently assigned a ->completed number and working down, find the + * first sublist that is not assignable to an upcoming grace period. + * Such a sublist has something in it (first two tests) and has + * a ->completed number assigned that will complete sooner than + * the ->completed number for newly arrived callbacks (last test). + * + * The key point is that any later sublist can be assigned the + * same ->completed number as the newly arrived callbacks, which + * means that the callbacks in any of these later sublist can be + * grouped into a single sublist, whether or not they have already + * been assigned a ->completed number. + */ + c = rcu_cbs_completed(rsp, rnp); + for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--) + if (rdp->nxttail[i] != rdp->nxttail[i - 1] && + !ULONG_CMP_GE(rdp->nxtcompleted[i], c)) + break; + + /* + * If there are no sublist for unassigned callbacks, leave. + * At the same time, advance "i" one sublist, so that "i" will + * index into the sublist where all the remaining callbacks should + * be grouped into. + */ + if (++i >= RCU_NEXT_TAIL) + return; + + /* + * Assign all subsequent callbacks' ->completed number to the next + * full grace period and group them all in the sublist initially + * indexed by "i". + */ + for (; i <= RCU_NEXT_TAIL; i++) { + rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxtcompleted[i] = c; + } + + /* Trace depending on how much we were able to accelerate. */ + if (!*rdp->nxttail[RCU_WAIT_TAIL]) + trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccWaitCB"); + else + trace_rcu_grace_period(rsp->name, rdp->gpnum, "AccReadyCB"); +} + +/* + * Move any callbacks whose grace period has completed to the + * RCU_DONE_TAIL sublist, then compact the remaining sublists and + * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL + * sublist. This function is idempotent, so it does not hurt to + * invoke it repeatedly. As long as it is not invoked -too- often... + * + * The caller must hold rnp->lock with interrupts disabled. + */ +static void rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, + struct rcu_data *rdp) +{ + int i, j; + + /* If the CPU has no callbacks, nothing to do. */ + if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL]) + return; + + /* + * Find all callbacks whose ->completed numbers indicate that they + * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. + */ + for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) { + if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i])) + break; + rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i]; + } + /* Clean up any sublist tail pointers that were misordered above. */ + for (j = RCU_WAIT_TAIL; j < i; j++) + rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL]; + + /* Copy down callbacks to fill in empty sublists. */ + for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) { + if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL]) + break; + rdp->nxttail[j] = rdp->nxttail[i]; + rdp->nxtcompleted[j] = rdp->nxtcompleted[i]; + } + + /* Classify any remaining callbacks. */ + rcu_accelerate_cbs(rsp, rnp, rdp); +} + +/* * Advance this CPU's callbacks, but only if the current grace period * has ended. This may be called only from the CPU to whom the rdp * belongs. In addition, the corresponding leaf rcu_node structure's @@ -1080,12 +1190,15 @@ static void __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { /* Did another grace period end? */ - if (rdp->completed != rnp->completed) { + if (rdp->completed == rnp->completed) { - /* Advance callbacks. No harm if list empty. */ - rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + /* No, so just accelerate recent callbacks. */ + rcu_accelerate_cbs(rsp, rnp, rdp); + + } else { + + /* Advance callbacks. */ + rcu_advance_cbs(rsp, rnp, rdp); /* Remember that we saw this grace-period completion. */ rdp->completed = rnp->completed; @@ -1392,17 +1505,10 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) /* * Because there is no grace period in progress right now, * any callbacks we have up to this point will be satisfied - * by the next grace period. So promote all callbacks to be - * handled after the end of the next grace period. If the - * CPU is not yet aware of the end of the previous grace period, - * we need to allow for the callback advancement that will - * occur when it does become aware. Deadlock prevents us from - * making it aware at this point: We cannot acquire a leaf - * rcu_node ->lock while holding the root rcu_node ->lock. + * by the next grace period. So this is a good place to + * assign a grace period number to recently posted callbacks. */ - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - if (rdp->completed == rsp->completed) - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rcu_accelerate_cbs(rsp, rnp, rdp); rsp->gp_flags = RCU_GP_FLAG_INIT; raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */ @@ -1527,7 +1633,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. */ - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rcu_accelerate_cbs(rsp, rnp, rdp); rcu_report_qs_rnp(mask, rsp, rnp, flags); /* rlses rnp->lock */ } @@ -1779,7 +1885,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) long bl, count, count_lazy; int i; - /* If no callbacks are ready, just return.*/ + /* If no callbacks are ready, just return. */ if (!cpu_has_callbacks_ready_to_invoke(rdp)) { trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0); trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist), @@ -2008,19 +2114,19 @@ __rcu_process_callbacks(struct rcu_state *rsp) WARN_ON_ONCE(rdp->beenonline == 0); - /* - * Advance callbacks in response to end of earlier grace - * period that some other CPU ended. - */ + /* Handle the end of a grace period that some other CPU ended. */ rcu_process_gp_end(rsp, rdp); /* Update RCU state based on any recent quiescent states. */ rcu_check_quiescent_state(rsp, rdp); /* Does this CPU require a not-yet-started grace period? */ + local_irq_save(flags); if (cpu_needs_another_gp(rsp, rdp)) { - raw_spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags); + raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */ rcu_start_gp(rsp, flags); /* releases above lock */ + } else { + local_irq_restore(flags); } /* If there are callbacks ready, invoke them. */ @@ -2719,9 +2825,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); -#ifdef CONFIG_RCU_USER_QS - WARN_ON_ONCE(rdp->dynticks->in_user); -#endif rdp->cpu = cpu; rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); @@ -2938,6 +3041,10 @@ static void __init rcu_init_one(struct rcu_state *rsp, BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */ + /* Silence gcc 4.8 warning about array index out of range. */ + if (rcu_num_lvls > RCU_NUM_LVLS) + panic("rcu_init_one: rcu_num_lvls overflow"); + /* Initialize the level-tracking arrays. */ for (i = 0; i < rcu_num_lvls; i++) @@ -3074,7 +3181,6 @@ void __init rcu_init(void) cpu_notifier(rcu_cpu_notify, 0); for_each_online_cpu(cpu) rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu); - check_cpu_stall_init(); } #include "rcutree_plugin.h" diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 4b69291..c896b50 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -102,10 +102,6 @@ struct rcu_dynticks { /* idle-period nonlazy_posted snapshot. */ int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ -#ifdef CONFIG_RCU_USER_QS - bool ignore_user_qs; /* Treat userspace as extended QS or not */ - bool in_user; /* Is the CPU in userland from RCU POV? */ -#endif }; /* RCU's kthread states for tracing. */ @@ -282,6 +278,8 @@ struct rcu_data { */ struct rcu_head *nxtlist; struct rcu_head **nxttail[RCU_NEXT_SIZE]; + unsigned long nxtcompleted[RCU_NEXT_SIZE]; + /* grace periods for sublists. */ long qlen_lazy; /* # of lazy queued callbacks */ long qlen; /* # of queued callbacks, incl lazy */ long qlen_last_fqs_check; @@ -343,11 +341,6 @@ struct rcu_data { #define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ -#ifdef CONFIG_PROVE_RCU -#define RCU_STALL_DELAY_DELTA (5 * HZ) -#else -#define RCU_STALL_DELAY_DELTA 0 -#endif #define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */ /* to take at least one */ /* scheduling clock irq */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index f6e5ec2..c1cc7e1 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -40,8 +40,7 @@ #ifdef CONFIG_RCU_NOCB_CPU static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ -static bool rcu_nocb_poll; /* Offload kthread are to poll. */ -module_param(rcu_nocb_poll, bool, 0444); +static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ static char __initdata nocb_buf[NR_CPUS * 5]; #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ @@ -2159,6 +2158,13 @@ static int __init rcu_nocb_setup(char *str) } __setup("rcu_nocbs=", rcu_nocb_setup); +static int __init parse_rcu_nocb_poll(char *arg) +{ + rcu_nocb_poll = 1; + return 0; +} +early_param("rcu_nocb_poll", parse_rcu_nocb_poll); + /* Is the specified CPU a no-CPUs CPU? */ static bool is_nocb_cpu(int cpu) { @@ -2366,10 +2372,11 @@ static int rcu_nocb_kthread(void *arg) for (;;) { /* If not polling, wait for next batch of callbacks. */ if (!rcu_nocb_poll) - wait_event(rdp->nocb_wq, rdp->nocb_head); + wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head); list = ACCESS_ONCE(rdp->nocb_head); if (!list) { schedule_timeout_interruptible(1); + flush_signals(current); continue; } diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c index 16502d3..13b243a 100644 --- a/kernel/rtmutex-debug.c +++ b/kernel/rtmutex-debug.c @@ -17,6 +17,7 @@ * See rt.c in preempt-rt for proper credits and further information */ #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/spinlock.h> diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c index 98ec494..7890b10 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/rtmutex-tester.c @@ -10,6 +10,7 @@ #include <linux/kthread.h> #include <linux/export.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/spinlock.h> #include <linux/timer.h> #include <linux/freezer.h> diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index a242e69..1e09308 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -13,6 +13,7 @@ #include <linux/spinlock.h> #include <linux/export.h> #include <linux/sched.h> +#include <linux/sched/rt.h> #include <linux/timer.h> #include "rtmutex_common.h" diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index 0984a21..64de5f8 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -35,6 +35,7 @@ static inline void autogroup_destroy(struct kref *kref) ag->tg->rt_se = NULL; ag->tg->rt_rq = NULL; #endif + sched_offline_group(ag->tg); sched_destroy_group(ag->tg); } @@ -76,6 +77,8 @@ static inline struct autogroup *autogroup_create(void) if (IS_ERR(tg)) goto out_free; + sched_online_group(tg, &root_task_group); + kref_init(&ag->kref); init_rwsem(&ag->lock); ag->id = atomic_inc_return(&autogroup_seq_nr); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 26058d0..3a673a3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -83,7 +83,7 @@ #endif #include "sched.h" -#include "../workqueue_sched.h" +#include "../workqueue_internal.h" #include "../smpboot.h" #define CREATE_TRACE_POINTS @@ -4371,7 +4371,7 @@ bool __sched yield_to(struct task_struct *p, bool preempt) struct task_struct *curr = current; struct rq *rq, *p_rq; unsigned long flags; - bool yielded = 0; + int yielded = 0; local_irq_save(flags); rq = this_rq(); @@ -4667,6 +4667,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif @@ -7160,7 +7161,6 @@ static void free_sched_group(struct task_group *tg) struct task_group *sched_create_group(struct task_group *parent) { struct task_group *tg; - unsigned long flags; tg = kzalloc(sizeof(*tg), GFP_KERNEL); if (!tg) @@ -7172,6 +7172,17 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_rt_sched_group(tg, parent)) goto err; + return tg; + +err: + free_sched_group(tg); + return ERR_PTR(-ENOMEM); +} + +void sched_online_group(struct task_group *tg, struct task_group *parent) +{ + unsigned long flags; + spin_lock_irqsave(&task_group_lock, flags); list_add_rcu(&tg->list, &task_groups); @@ -7181,12 +7192,6 @@ struct task_group *sched_create_group(struct task_group *parent) INIT_LIST_HEAD(&tg->children); list_add_rcu(&tg->siblings, &parent->children); spin_unlock_irqrestore(&task_group_lock, flags); - - return tg; - -err: - free_sched_group(tg); - return ERR_PTR(-ENOMEM); } /* rcu callback to free various structures associated with a task group */ @@ -7199,6 +7204,12 @@ static void free_sched_group_rcu(struct rcu_head *rhp) /* Destroy runqueue etc associated with a task group */ void sched_destroy_group(struct task_group *tg) { + /* wait for possible concurrent references to cfs_rqs complete */ + call_rcu(&tg->rcu, free_sched_group_rcu); +} + +void sched_offline_group(struct task_group *tg) +{ unsigned long flags; int i; @@ -7210,9 +7221,6 @@ void sched_destroy_group(struct task_group *tg) list_del_rcu(&tg->list); list_del_rcu(&tg->siblings); spin_unlock_irqrestore(&task_group_lock, flags); - - /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&tg->rcu, free_sched_group_rcu); } /* change task's runqueue when it moves between groups. @@ -7508,6 +7516,25 @@ static int sched_rt_global_constraints(void) } #endif /* CONFIG_RT_GROUP_SCHED */ +int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + /* make sure that internally we keep jiffies */ + /* also, writing zero resets timeslice to default */ + if (!ret && write) { + sched_rr_timeslice = sched_rr_timeslice <= 0 ? + RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice); + } + mutex_unlock(&mutex); + return ret; +} + int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -7564,6 +7591,19 @@ static struct cgroup_subsys_state *cpu_cgroup_css_alloc(struct cgroup *cgrp) return &tg->css; } +static int cpu_cgroup_css_online(struct cgroup *cgrp) +{ + struct task_group *tg = cgroup_tg(cgrp); + struct task_group *parent; + + if (!cgrp->parent) + return 0; + + parent = cgroup_tg(cgrp->parent); + sched_online_group(tg, parent); + return 0; +} + static void cpu_cgroup_css_free(struct cgroup *cgrp) { struct task_group *tg = cgroup_tg(cgrp); @@ -7571,6 +7611,13 @@ static void cpu_cgroup_css_free(struct cgroup *cgrp) sched_destroy_group(tg); } +static void cpu_cgroup_css_offline(struct cgroup *cgrp) +{ + struct task_group *tg = cgroup_tg(cgrp); + + sched_offline_group(tg); +} + static int cpu_cgroup_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset) { @@ -7926,6 +7973,8 @@ struct cgroup_subsys cpu_cgroup_subsys = { .name = "cpu", .css_alloc = cpu_cgroup_css_alloc, .css_free = cpu_cgroup_css_free, + .css_online = cpu_cgroup_css_online, + .css_offline = cpu_cgroup_css_offline, .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, .exit = cpu_cgroup_exit, diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 23aa789..1095e87 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -28,6 +28,8 @@ */ #include <linux/gfp.h> +#include <linux/sched.h> +#include <linux/sched/rt.h> #include "cpupri.h" /* Convert between a 140 based task->prio, and our 102 based cpupri */ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 293b202..9857329 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -3,6 +3,7 @@ #include <linux/tsacct_kern.h> #include <linux/kernel_stat.h> #include <linux/static_key.h> +#include <linux/context_tracking.h> #include "sched.h" @@ -163,7 +164,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime, task_group_account_field(p, index, (__force u64) cputime); /* Account for user time used */ - acct_update_integrals(p); + acct_account_cputime(p); } /* @@ -213,7 +214,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, task_group_account_field(p, index, (__force u64) cputime); /* Account for system time used */ - acct_update_integrals(p); + acct_account_cputime(p); } /* @@ -295,6 +296,7 @@ static __always_inline bool steal_account_process_tick(void) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) { struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; struct task_struct *t; times->utime = sig->utime; @@ -308,16 +310,15 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) t = tsk; do { - times->utime += t->utime; - times->stime += t->stime; + task_cputime(tsk, &utime, &stime); + times->utime += utime; + times->stime += stime; times->sum_exec_runtime += task_sched_runtime(t); } while_each_thread(tsk, t); out: rcu_read_unlock(); } -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* * Account a tick to a process and cpustat @@ -382,11 +383,12 @@ static void irqtime_account_idle_ticks(int ticks) irqtime_account_process_tick(current, 0, rq); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ -static void irqtime_account_idle_ticks(int ticks) {} -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, +static inline void irqtime_account_idle_ticks(int ticks) {} +static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, struct rq *rq) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Account a single tick of cpu time. * @p: the process that the cpu time gets accounted to @@ -397,6 +399,9 @@ void account_process_tick(struct task_struct *p, int user_tick) cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); + if (vtime_accounting_enabled()) + return; + if (sched_clock_irqtime) { irqtime_account_process_tick(p, user_tick, rq); return; @@ -438,8 +443,7 @@ void account_idle_ticks(unsigned long ticks) account_idle_time(jiffies_to_cputime(ticks)); } - -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ /* * Use precise platform statistics if available: @@ -461,25 +465,20 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime *st = cputime.stime; } -void vtime_account_system_irqsafe(struct task_struct *tsk) -{ - unsigned long flags; - - local_irq_save(flags); - vtime_account_system(tsk); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe); - #ifndef __ARCH_HAS_VTIME_TASK_SWITCH void vtime_task_switch(struct task_struct *prev) { + if (!vtime_accounting_enabled()) + return; + if (is_idle_task(prev)) vtime_account_idle(prev); else vtime_account_system(prev); +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE vtime_account_user(prev); +#endif arch_vtime_task_switch(prev); } #endif @@ -493,27 +492,40 @@ void vtime_task_switch(struct task_struct *prev) * vtime_account(). */ #ifndef __ARCH_HAS_VTIME_ACCOUNT -void vtime_account(struct task_struct *tsk) +void vtime_account_irq_enter(struct task_struct *tsk) { - if (in_interrupt() || !is_idle_task(tsk)) - vtime_account_system(tsk); - else - vtime_account_idle(tsk); + if (!vtime_accounting_enabled()) + return; + + if (!in_interrupt()) { + /* + * If we interrupted user, context_tracking_in_user() + * is 1 because the context tracking don't hook + * on irq entry/exit. This way we know if + * we need to flush user time on kernel entry. + */ + if (context_tracking_in_user()) { + vtime_account_user(tsk); + return; + } + + if (is_idle_task(tsk)) { + vtime_account_idle(tsk); + return; + } + } + vtime_account_system(tsk); } -EXPORT_SYMBOL_GPL(vtime_account); +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ -#else - -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) -#endif +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) +static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total) { u64 temp = (__force u64) rtime; - temp *= (__force u64) utime; + temp *= (__force u64) stime; if (sizeof(cputime_t) == 4) temp = div_u64(temp, (__force u32) total); @@ -531,10 +543,10 @@ static void cputime_adjust(struct task_cputime *curr, struct cputime *prev, cputime_t *ut, cputime_t *st) { - cputime_t rtime, utime, total; + cputime_t rtime, stime, total; - utime = curr->utime; - total = utime + curr->stime; + stime = curr->stime; + total = stime + curr->utime; /* * Tick based cputime accounting depend on random scheduling @@ -549,17 +561,17 @@ static void cputime_adjust(struct task_cputime *curr, rtime = nsecs_to_cputime(curr->sum_exec_runtime); if (total) - utime = scale_utime(utime, rtime, total); + stime = scale_stime(stime, rtime, total); else - utime = rtime; + stime = rtime; /* * If the tick based count grows faster than the scheduler one, * the result of the scaling may go backward. * Let's enforce monotonicity. */ - prev->utime = max(prev->utime, utime); - prev->stime = max(prev->stime, rtime - prev->utime); + prev->stime = max(prev->stime, stime); + prev->utime = max(prev->utime, rtime - prev->stime); *ut = prev->utime; *st = prev->stime; @@ -568,11 +580,10 @@ static void cputime_adjust(struct task_cputime *curr, void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { struct task_cputime cputime = { - .utime = p->utime, - .stime = p->stime, .sum_exec_runtime = p->se.sum_exec_runtime, }; + task_cputime(p, &cputime.utime, &cputime.stime); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } @@ -586,4 +597,221 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime thread_group_cputime(p, &cputime); cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); } -#endif +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +static unsigned long long vtime_delta(struct task_struct *tsk) +{ + unsigned long long clock; + + clock = sched_clock(); + if (clock < tsk->vtime_snap) + return 0; + + return clock - tsk->vtime_snap; +} + +static cputime_t get_vtime_delta(struct task_struct *tsk) +{ + unsigned long long delta = vtime_delta(tsk); + + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); + tsk->vtime_snap += delta; + + /* CHECKME: always safe to convert nsecs to cputime? */ + return nsecs_to_cputime(delta); +} + +static void __vtime_account_system(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); +} + +void vtime_account_system(struct task_struct *tsk) +{ + if (!vtime_accounting_enabled()) + return; + + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_account_irq_exit(struct task_struct *tsk) +{ + if (!vtime_accounting_enabled()) + return; + + write_seqlock(&tsk->vtime_seqlock); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_account_user(struct task_struct *tsk) +{ + cputime_t delta_cpu; + + if (!vtime_accounting_enabled()) + return; + + delta_cpu = get_vtime_delta(tsk); + + write_seqlock(&tsk->vtime_seqlock); + tsk->vtime_snap_whence = VTIME_SYS; + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_user_enter(struct task_struct *tsk) +{ + if (!vtime_accounting_enabled()) + return; + + write_seqlock(&tsk->vtime_seqlock); + tsk->vtime_snap_whence = VTIME_USER; + __vtime_account_system(tsk); + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_guest_enter(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_guest_exit(struct task_struct *tsk) +{ + write_seqlock(&tsk->vtime_seqlock); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; + write_sequnlock(&tsk->vtime_seqlock); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + cputime_t delta_cpu = get_vtime_delta(tsk); + + account_idle_time(delta_cpu); +} + +bool vtime_accounting_enabled(void) +{ + return context_tracking_active(); +} + +void arch_vtime_task_switch(struct task_struct *prev) +{ + write_seqlock(&prev->vtime_seqlock); + prev->vtime_snap_whence = VTIME_SLEEPING; + write_sequnlock(&prev->vtime_seqlock); + + write_seqlock(¤t->vtime_seqlock); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock(); + write_sequnlock(¤t->vtime_seqlock); +} + +void vtime_init_idle(struct task_struct *t) +{ + unsigned long flags; + + write_seqlock_irqsave(&t->vtime_seqlock, flags); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock(); + write_sequnlock_irqrestore(&t->vtime_seqlock, flags); +} + +cputime_t task_gtime(struct task_struct *t) +{ + unsigned int seq; + cputime_t gtime; + + do { + seq = read_seqbegin(&t->vtime_seqlock); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + + } while (read_seqretry(&t->vtime_seqlock, seq)); + + return gtime; +} + +/* + * Fetch cputime raw values from fields of task_struct and + * add up the pending nohz execution time since the last + * cputime snapshot. + */ +static void +fetch_task_cputime(struct task_struct *t, + cputime_t *u_dst, cputime_t *s_dst, + cputime_t *u_src, cputime_t *s_src, + cputime_t *udelta, cputime_t *sdelta) +{ + unsigned int seq; + unsigned long long delta; + + do { + *udelta = 0; + *sdelta = 0; + + seq = read_seqbegin(&t->vtime_seqlock); + + if (u_dst) + *u_dst = *u_src; + if (s_dst) + *s_dst = *s_src; + + /* Task is sleeping, nothing to add */ + if (t->vtime_snap_whence == VTIME_SLEEPING || + is_idle_task(t)) + continue; + + delta = vtime_delta(t); + + /* + * Task runs either in user or kernel space, add pending nohz time to + * the right place. + */ + if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) { + *udelta = delta; + } else { + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } + } while (read_seqretry(&t->vtime_seqlock, seq)); +} + + +void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utime, stime, &t->utime, + &t->stime, &udelta, &sdelta); + if (utime) + *utime += udelta; + if (stime) + *stime += sdelta; +} + +void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, cputime_t *stimescaled) +{ + cputime_t udelta, sdelta; + + fetch_task_cputime(t, utimescaled, stimescaled, + &t->utimescaled, &t->stimescaled, &udelta, &sdelta); + if (utimescaled) + *utimescaled += cputime_to_scaled(udelta); + if (stimescaled) + *stimescaled += cputime_to_scaled(sdelta); +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 2cd3c1b..557e7b5 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -110,13 +110,6 @@ static char *task_group_path(struct task_group *tg) if (autogroup_path(tg, group_path, PATH_MAX)) return group_path; - /* - * May be NULL if the underlying cgroup isn't fully-created yet - */ - if (!tg->css.cgroup) { - group_path[0] = '\0'; - return group_path; - } cgroup_path(tg->css.cgroup, group_path, PATH_MAX); return group_path; } @@ -222,8 +215,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cfs_rq->runnable_load_avg); SEQ_printf(m, " .%-30s: %lld\n", "blocked_load_avg", cfs_rq->blocked_load_avg); - SEQ_printf(m, " .%-30s: %ld\n", "tg_load_avg", - atomic64_read(&cfs_rq->tg->load_avg)); + SEQ_printf(m, " .%-30s: %lld\n", "tg_load_avg", + (unsigned long long)atomic64_read(&cfs_rq->tg->load_avg)); SEQ_printf(m, " .%-30s: %lld\n", "tg_load_contrib", cfs_rq->tg_load_contrib); SEQ_printf(m, " .%-30s: %d\n", "tg_runnable_contrib", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5eea870..7a33e59 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1680,9 +1680,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) } /* ensure we never gain time by being placed backwards. */ - vruntime = max_vruntime(se->vruntime, vruntime); - - se->vruntime = vruntime; + se->vruntime = max_vruntime(se->vruntime, vruntime); } static void check_enqueue_throttle(struct cfs_rq *cfs_rq); @@ -2663,7 +2661,7 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_cancel(&cfs_b->slack_timer); } -static void unthrottle_offline_cfs_rqs(struct rq *rq) +static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) { struct cfs_rq *cfs_rq; @@ -3254,25 +3252,18 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) */ static int select_idle_sibling(struct task_struct *p, int target) { - int cpu = smp_processor_id(); - int prev_cpu = task_cpu(p); struct sched_domain *sd; struct sched_group *sg; - int i; + int i = task_cpu(p); - /* - * If the task is going to be woken-up on this cpu and if it is - * already idle, then it is the right target. - */ - if (target == cpu && idle_cpu(cpu)) - return cpu; + if (idle_cpu(target)) + return target; /* - * If the task is going to be woken-up on the cpu where it previously - * ran and if it is currently idle, then it the right target. + * If the prevous cpu is cache affine and idle, don't be stupid. */ - if (target == prev_cpu && idle_cpu(prev_cpu)) - return prev_cpu; + if (i != target && cpus_share_cache(i, target) && idle_cpu(i)) + return i; /* * Otherwise, iterate the domains and find an elegible idle cpu. @@ -3286,7 +3277,7 @@ static int select_idle_sibling(struct task_struct *p, int target) goto next; for_each_cpu(i, sched_group_cpus(sg)) { - if (!idle_cpu(i)) + if (i == target || !idle_cpu(i)) goto next; } @@ -6101,7 +6092,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task * idle runqueue: */ if (rq->cfs.load.weight) - rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); + rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); return rr_interval; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 418feb0..127a2c4 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -7,6 +7,8 @@ #include <linux/slab.h> +int sched_rr_timeslice = RR_TIMESLICE; + static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); struct rt_bandwidth def_rt_bandwidth; @@ -566,7 +568,7 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) static int do_balance_runtime(struct rt_rq *rt_rq) { struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); - struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + struct root_domain *rd = rq_of_rt_rq(rt_rq)->rd; int i, weight, more = 0; u64 rt_period; @@ -925,8 +927,8 @@ static void update_curr_rt(struct rq *rq) return; delta_exec = rq->clock_task - curr->se.exec_start; - if (unlikely((s64)delta_exec < 0)) - delta_exec = 0; + if (unlikely((s64)delta_exec <= 0)) + return; schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); @@ -1427,8 +1429,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - (cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) && - (p->nr_cpus_allowed > 1)) + cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) return 1; return 0; } @@ -1889,8 +1890,11 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (p->on_rq && !rq->rt.rt_nr_running) - pull_rt_task(rq); + if (!p->on_rq || rq->rt.rt_nr_running) + return; + + if (pull_rt_task(rq)) + resched_task(rq->curr); } void init_sched_rt_class(void) @@ -1985,7 +1989,11 @@ static void watchdog(struct rq *rq, struct task_struct *p) if (soft != RLIM_INFINITY) { unsigned long next; - p->rt.timeout++; + if (p->rt.watchdog_stamp != jiffies) { + p->rt.timeout++; + p->rt.watchdog_stamp = jiffies; + } + next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); if (p->rt.timeout > next) p->cputime_expires.sched_exp = p->se.sum_exec_runtime; @@ -2010,7 +2018,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) if (--p->rt.time_slice) return; - p->rt.time_slice = RR_TIMESLICE; + p->rt.time_slice = sched_rr_timeslice; /* * Requeue to the end of queue if we (and all of our ancestors) are the @@ -2041,7 +2049,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) * Time slice is 0 for SCHED_FIFO tasks */ if (task->policy == SCHED_RR) - return RR_TIMESLICE; + return sched_rr_timeslice; else return 0; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index fc88644..cc03cfd 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1,5 +1,7 @@ #include <linux/sched.h> +#include <linux/sched/sysctl.h> +#include <linux/sched/rt.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> diff --git a/kernel/signal.c b/kernel/signal.c index 3d09cf6..7f82adb 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1632,6 +1632,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) unsigned long flags; struct sighand_struct *psig; bool autoreap = false; + cputime_t utime, stime; BUG_ON(sig == -1); @@ -1669,8 +1670,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig) task_uid(tsk)); rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime); - info.si_stime = cputime_to_clock_t(tsk->stime + tsk->signal->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime); + info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) @@ -1734,6 +1736,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; + cputime_t utime, stime; if (for_ptracer) { parent = tsk->parent; @@ -1752,8 +1755,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(tsk->utime); - info.si_stime = cputime_to_clock_t(tsk->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime); + info.si_stime = cputime_to_clock_t(stime); info.si_code = why; switch (why) { diff --git a/kernel/smp.c b/kernel/smp.c index 29dd40a..69f38bd 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -33,6 +33,7 @@ struct call_function_data { struct call_single_data csd; atomic_t refs; cpumask_var_t cpumask; + cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data); @@ -56,6 +57,9 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return notifier_from_errno(-ENOMEM); + if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, + cpu_to_node(cpu))) + return notifier_from_errno(-ENOMEM); break; #ifdef CONFIG_HOTPLUG_CPU @@ -65,6 +69,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD: case CPU_DEAD_FROZEN: free_cpumask_var(cfd->cpumask); + free_cpumask_var(cfd->cpumask_ipi); break; #endif }; @@ -526,6 +531,12 @@ void smp_call_function_many(const struct cpumask *mask, return; } + /* + * After we put an entry into the list, data->cpumask + * may be cleared again when another CPU sends another IPI for + * a SMP function call, so data->cpumask will be zero. + */ + cpumask_copy(data->cpumask_ipi, data->cpumask); raw_spin_lock_irqsave(&call_function.lock, flags); /* * Place entry at the _HEAD_ of the list, so that any cpu still @@ -549,7 +560,7 @@ void smp_call_function_many(const struct cpumask *mask, smp_mb(); /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi_mask(data->cpumask); + arch_send_call_function_ipi_mask(data->cpumask_ipi); /* Optionally wait for the CPUs to complete */ if (wait) diff --git a/kernel/smpboot.c b/kernel/smpboot.c index d6c5fc0..d4abac2 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -183,9 +183,10 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } - get_task_struct(tsk); *per_cpu_ptr(ht->store, cpu) = tsk; + if (ht->create) + ht->create(cpu); return 0; } @@ -225,7 +226,7 @@ static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) { struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); - if (tsk) + if (tsk && !ht->selfparking) kthread_park(tsk); } diff --git a/kernel/softirq.c b/kernel/softirq.c index ed567ba..f5cc25f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -221,7 +221,7 @@ asmlinkage void __do_softirq(void) current->flags &= ~PF_MEMALLOC; pending = local_softirq_pending(); - vtime_account_irq_enter(current); + account_irq_enter_time(current); __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); @@ -272,7 +272,7 @@ restart: lockdep_softirq_exit(); - vtime_account_irq_exit(current); + account_irq_exit_time(current); __local_bh_enable(SOFTIRQ_OFFSET); tsk_restore_flags(current, old_flags, PF_MEMALLOC); } @@ -341,7 +341,7 @@ static inline void invoke_softirq(void) */ void irq_exit(void) { - vtime_account_irq_exit(current); + account_irq_exit_time(current); trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) diff --git a/kernel/srcu.c b/kernel/srcu.c index 2b85982..01d5ccb 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -282,12 +282,8 @@ static int srcu_readers_active(struct srcu_struct *sp) */ void cleanup_srcu_struct(struct srcu_struct *sp) { - int sum; - - sum = srcu_readers_active(sp); - WARN_ON(sum); /* Leakage unless caller handles error. */ - if (sum != 0) - return; + if (WARN_ON(srcu_readers_active(sp))) + return; /* Leakage unless caller handles error. */ free_percpu(sp->per_cpu_ref); sp->per_cpu_ref = NULL; } @@ -302,9 +298,8 @@ int __srcu_read_lock(struct srcu_struct *sp) { int idx; + idx = ACCESS_ONCE(sp->completed) & 0x1; preempt_disable(); - idx = rcu_dereference_index_check(sp->completed, - rcu_read_lock_sched_held()) & 0x1; ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1; smp_mb(); /* B */ /* Avoid leaking the critical section. */ ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1; @@ -321,10 +316,8 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock); */ void __srcu_read_unlock(struct srcu_struct *sp, int idx) { - preempt_disable(); smp_mb(); /* C */ /* Avoid leaking the critical section. */ - ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1; - preempt_enable(); + this_cpu_dec(sp->per_cpu_ref->c[idx]); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -423,6 +416,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) !lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section"); + might_sleep(); init_completion(&rcu.completion); head->next = NULL; @@ -455,10 +449,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) * synchronize_srcu - wait for prior SRCU read-side critical-section completion * @sp: srcu_struct with which to synchronize. * - * Flip the completed counter, and wait for the old count to drain to zero. - * As with classic RCU, the updater must use some separate means of - * synchronizing concurrent updates. Can block; must be called from - * process context. + * Wait for the count to drain to zero of both indexes. To avoid the + * possible starvation of synchronize_srcu(), it waits for the count of + * the index=((->completed & 1) ^ 1) to drain to zero at first, + * and then flip the completed and wait for the count of the other index. + * + * Can block; must be called from process context. * * Note that it is illegal to call synchronize_srcu() from the corresponding * SRCU read-side critical section; doing so will result in deadlock. @@ -480,12 +476,11 @@ EXPORT_SYMBOL_GPL(synchronize_srcu); * Wait for an SRCU grace period to elapse, but be more aggressive about * spinning rather than blocking when waiting. * - * Note that it is illegal to call this function while holding any lock - * that is acquired by a CPU-hotplug notifier. It is also illegal to call - * synchronize_srcu_expedited() from the corresponding SRCU read-side - * critical section; doing so will result in deadlock. However, it is - * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct - * from some other srcu_struct's read-side critical section, as long as + * Note that it is also illegal to call synchronize_srcu_expedited() + * from the corresponding SRCU read-side critical section; + * doing so will result in deadlock. However, it is perfectly legal + * to call synchronize_srcu_expedited() on one srcu_struct from some + * other srcu_struct's read-side critical section, as long as * the resulting graph of srcu_structs is acyclic. */ void synchronize_srcu_expedited(struct srcu_struct *sp) diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 2f194e9..95d178c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -18,7 +18,7 @@ #include <linux/stop_machine.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> - +#include <linux/smpboot.h> #include <linux/atomic.h> /* @@ -37,10 +37,10 @@ struct cpu_stopper { spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ - struct task_struct *thread; /* stopper thread */ }; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper); +static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task); static bool stop_machine_initialized = false; static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) @@ -62,16 +62,18 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed) } /* queue @work to @stopper. if offline, @work is completed immediately */ -static void cpu_stop_queue_work(struct cpu_stopper *stopper, - struct cpu_stop_work *work) +static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + struct task_struct *p = per_cpu(cpu_stopper_task, cpu); + unsigned long flags; spin_lock_irqsave(&stopper->lock, flags); if (stopper->enabled) { list_add_tail(&work->list, &stopper->works); - wake_up_process(stopper->thread); + wake_up_process(p); } else cpu_stop_signal_done(work->done, false); @@ -108,7 +110,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done }; cpu_stop_init_done(&done, 1); - cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work); + cpu_stop_queue_work(cpu, &work); wait_for_completion(&done.completion); return done.executed ? done.ret : -ENOENT; } @@ -130,7 +132,7 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, }; - cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf); + cpu_stop_queue_work(cpu, work_buf); } /* static data for stop_cpus */ @@ -159,8 +161,7 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask, */ preempt_disable(); for_each_cpu(cpu, cpumask) - cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), - &per_cpu(stop_cpus_work, cpu)); + cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); preempt_enable(); } @@ -244,20 +245,25 @@ int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) return ret; } -static int cpu_stopper_thread(void *data) +static int cpu_stop_should_run(unsigned int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + unsigned long flags; + int run; + + spin_lock_irqsave(&stopper->lock, flags); + run = !list_empty(&stopper->works); + spin_unlock_irqrestore(&stopper->lock, flags); + return run; +} + +static void cpu_stopper_thread(unsigned int cpu) { - struct cpu_stopper *stopper = data; + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); struct cpu_stop_work *work; int ret; repeat: - set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ - - if (kthread_should_stop()) { - __set_current_state(TASK_RUNNING); - return 0; - } - work = NULL; spin_lock_irq(&stopper->lock); if (!list_empty(&stopper->works)) { @@ -273,8 +279,6 @@ repeat: struct cpu_stop_done *done = work->done; char ksym_buf[KSYM_NAME_LEN] __maybe_unused; - __set_current_state(TASK_RUNNING); - /* cpu stop callbacks are not allowed to sleep */ preempt_disable(); @@ -290,88 +294,55 @@ repeat: ksym_buf), arg); cpu_stop_signal_done(done, true); - } else - schedule(); - - goto repeat; + goto repeat; + } } extern void sched_set_stop_task(int cpu, struct task_struct *stop); -/* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */ -static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static void cpu_stop_create(unsigned int cpu) +{ + sched_set_stop_task(cpu, per_cpu(cpu_stopper_task, cpu)); +} + +static void cpu_stop_park(unsigned int cpu) { - unsigned int cpu = (unsigned long)hcpu; struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - struct task_struct *p; - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - BUG_ON(stopper->thread || stopper->enabled || - !list_empty(&stopper->works)); - p = kthread_create_on_node(cpu_stopper_thread, - stopper, - cpu_to_node(cpu), - "migration/%d", cpu); - if (IS_ERR(p)) - return notifier_from_errno(PTR_ERR(p)); - get_task_struct(p); - kthread_bind(p, cpu); - sched_set_stop_task(cpu, p); - stopper->thread = p; - break; - - case CPU_ONLINE: - /* strictly unnecessary, as first user will wake it */ - wake_up_process(stopper->thread); - /* mark enabled */ - spin_lock_irq(&stopper->lock); - stopper->enabled = true; - spin_unlock_irq(&stopper->lock); - break; - -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_POST_DEAD: - { - struct cpu_stop_work *work; - - sched_set_stop_task(cpu, NULL); - /* kill the stopper */ - kthread_stop(stopper->thread); - /* drain remaining works */ - spin_lock_irq(&stopper->lock); - list_for_each_entry(work, &stopper->works, list) - cpu_stop_signal_done(work->done, false); - stopper->enabled = false; - spin_unlock_irq(&stopper->lock); - /* release the stopper */ - put_task_struct(stopper->thread); - stopper->thread = NULL; - break; - } -#endif - } + struct cpu_stop_work *work; + unsigned long flags; - return NOTIFY_OK; + /* drain remaining works */ + spin_lock_irqsave(&stopper->lock, flags); + list_for_each_entry(work, &stopper->works, list) + cpu_stop_signal_done(work->done, false); + stopper->enabled = false; + spin_unlock_irqrestore(&stopper->lock, flags); } -/* - * Give it a higher priority so that cpu stopper is available to other - * cpu notifiers. It currently shares the same priority as sched - * migration_notifier. - */ -static struct notifier_block __cpuinitdata cpu_stop_cpu_notifier = { - .notifier_call = cpu_stop_cpu_callback, - .priority = 10, +static void cpu_stop_unpark(unsigned int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + + spin_lock_irq(&stopper->lock); + stopper->enabled = true; + spin_unlock_irq(&stopper->lock); +} + +static struct smp_hotplug_thread cpu_stop_threads = { + .store = &cpu_stopper_task, + .thread_should_run = cpu_stop_should_run, + .thread_fn = cpu_stopper_thread, + .thread_comm = "migration/%u", + .create = cpu_stop_create, + .setup = cpu_stop_unpark, + .park = cpu_stop_park, + .unpark = cpu_stop_unpark, + .selfparking = true, }; static int __init cpu_stop_init(void) { - void *bcpu = (void *)(long)smp_processor_id(); unsigned int cpu; - int err; for_each_possible_cpu(cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); @@ -380,15 +351,8 @@ static int __init cpu_stop_init(void) INIT_LIST_HEAD(&stopper->works); } - /* start one for the boot cpu */ - err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE, - bcpu); - BUG_ON(err != NOTIFY_OK); - cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu); - register_cpu_notifier(&cpu_stop_cpu_notifier); - + BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); stop_machine_initialized = true; - return 0; } early_initcall(cpu_stop_init); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c88878d..4fc9be9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -61,6 +61,7 @@ #include <linux/kmod.h> #include <linux/capability.h> #include <linux/binfmts.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -403,6 +404,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sched_rt_handler, }, + { + .procname = "sched_rr_timeslice_ms", + .data = &sched_rr_timeslice, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rr_handler, + }, #ifdef CONFIG_SCHED_AUTOGROUP { .procname = "sched_autogroup_enabled", diff --git a/kernel/time.c b/kernel/time.c index d226c6a..c2a27dd 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -115,6 +115,12 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, } /* + * Indicates if there is an offset between the system clock and the hardware + * clock/persistent clock/rtc. + */ +int persistent_clock_is_local; + +/* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * @@ -135,6 +141,8 @@ static inline void warp_clock(void) struct timespec adjust; adjust = current_kernel_time(); + if (sys_tz.tz_minuteswest != 0) + persistent_clock_is_local = 1; adjust.tv_sec += sys_tz.tz_minuteswest * 60; do_settimeofday(&adjust); } diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 8601f0d..24510d8 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,6 +12,11 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool +# Platforms has a persistent clock +config ALWAYS_USE_PERSISTENT_CLOCK + bool + default n + # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool @@ -38,6 +43,10 @@ config GENERIC_CLOCKEVENTS_BUILD default y depends on GENERIC_CLOCKEVENTS +# Architecture can handle broadcast in a driver-agnostic way +config ARCH_HAS_TICK_BROADCAST + bool + # Clockevents broadcasting infrastructure config GENERIC_CLOCKEVENTS_BROADCAST bool diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 24174b4..b10a42b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -15,6 +15,7 @@ #include <linux/time.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/rtc.h> #include "tick-internal.h" @@ -483,8 +484,7 @@ out: return leap; } -#ifdef CONFIG_GENERIC_CMOS_UPDATE - +#if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) static void sync_cmos_clock(struct work_struct *work); static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); @@ -510,14 +510,26 @@ static void sync_cmos_clock(struct work_struct *work) } getnstimeofday(&now); - if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) - fail = update_persistent_clock(now); + if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) { + struct timespec adjust = now; + + fail = -ENODEV; + if (persistent_clock_is_local) + adjust.tv_sec -= (sys_tz.tz_minuteswest * 60); +#ifdef CONFIG_GENERIC_CMOS_UPDATE + fail = update_persistent_clock(adjust); +#endif +#ifdef CONFIG_RTC_SYSTOHC + if (fail == -ENODEV) + fail = rtc_set_ntp_time(adjust); +#endif + } next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2); if (next.tv_nsec <= 0) next.tv_nsec += NSEC_PER_SEC; - if (!fail) + if (!fail || fail == -ENODEV) next.tv_sec = 659; else next.tv_sec = 0; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index f113755..2fb8cb8 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -18,6 +18,7 @@ #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> +#include <linux/smp.h> #include "tick-internal.h" @@ -86,6 +87,22 @@ int tick_is_broadcast_device(struct clock_event_device *dev) return (dev && tick_broadcast_device.evtdev == dev); } +static void err_broadcast(const struct cpumask *mask) +{ + pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n"); +} + +static void tick_device_setup_broadcast_func(struct clock_event_device *dev) +{ + if (!dev->broadcast) + dev->broadcast = tick_broadcast; + if (!dev->broadcast) { + pr_warn_once("%s depends on broadcast, but no broadcast function available\n", + dev->name); + dev->broadcast = err_broadcast; + } +} + /* * Check, if the device is disfunctional and a place holder, which * needs to be handled by the broadcast device. @@ -105,6 +122,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) */ if (!tick_device_is_functional(dev)) { dev->event_handler = tick_handle_periodic; + tick_device_setup_broadcast_func(dev); cpumask_set_cpu(cpu, tick_get_broadcast_mask()); tick_broadcast_start_periodic(tick_broadcast_device.evtdev); ret = 1; @@ -116,15 +134,33 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) */ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) { int cpu = smp_processor_id(); - cpumask_clear_cpu(cpu, tick_get_broadcast_mask()); tick_broadcast_clear_oneshot(cpu); + } else { + tick_device_setup_broadcast_func(dev); } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); return ret; } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +int tick_receive_broadcast(void) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + struct clock_event_device *evt = td->evtdev; + + if (!evt) + return -ENODEV; + + if (!evt->event_handler) + return -EINVAL; + + evt->event_handler(evt); + return 0; +} +#endif + /* * Broadcast the event to the cpus, which are set in the mask (mangled). */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d58e552..314b9ee 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -20,6 +20,7 @@ #include <linux/profile.h> #include <linux/sched.h> #include <linux/module.h> +#include <linux/irq_work.h> #include <asm/irq_regs.h> @@ -28,7 +29,7 @@ /* * Per cpu nohz control structure */ -static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); +DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); /* * The time, when the last jiffy update happened. Protected by jiffies_lock. @@ -331,8 +332,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, time_delta = timekeeping_max_deferment(); } while (read_seqretry(&jiffies_lock, seq)); - if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) || - arch_needs_cpu(cpu)) { + if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || + arch_needs_cpu(cpu) || irq_work_needs_cpu()) { next_jiffies = last_jiffies + 1; delta_jiffies = 1; } else { @@ -631,8 +632,11 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) static void tick_nohz_account_idle_ticks(struct tick_sched *ts) { -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE unsigned long ticks; + + if (vtime_accounting_enabled()) + return; /* * We stopped the tick in idle. Update process times would miss the * time we slept as update_process_times does only a 1 tick diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index cbc6acb..1e35515 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -29,6 +29,9 @@ static struct timekeeper timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; +/* Flag for if there is a persistent clock on this platform */ +bool __read_mostly persistent_clock_exist = false; + static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) { @@ -264,19 +267,18 @@ static void timekeeping_forward_now(struct timekeeper *tk) } /** - * getnstimeofday - Returns the time of day in a timespec + * __getnstimeofday - Returns the time of day in a timespec. * @ts: pointer to the timespec to be set * - * Returns the time of day in a timespec. + * Updates the time of day in the timespec. + * Returns 0 on success, or -ve when suspended (timespec will be undefined). */ -void getnstimeofday(struct timespec *ts) +int __getnstimeofday(struct timespec *ts) { struct timekeeper *tk = &timekeeper; unsigned long seq; s64 nsecs = 0; - WARN_ON(timekeeping_suspended); - do { seq = read_seqbegin(&tk->lock); @@ -287,6 +289,26 @@ void getnstimeofday(struct timespec *ts) ts->tv_nsec = 0; timespec_add_ns(ts, nsecs); + + /* + * Do not bail out early, in case there were callers still using + * the value, even in the face of the WARN_ON. + */ + if (unlikely(timekeeping_suspended)) + return -EAGAIN; + return 0; +} +EXPORT_SYMBOL(__getnstimeofday); + +/** + * getnstimeofday - Returns the time of day in a timespec. + * @ts: pointer to the timespec to be set + * + * Returns the time of day in a timespec (WARN if suspended). + */ +void getnstimeofday(struct timespec *ts) +{ + WARN_ON(__getnstimeofday(ts)); } EXPORT_SYMBOL(getnstimeofday); @@ -640,12 +662,14 @@ void __init timekeeping_init(void) struct timespec now, boot, tmp; read_persistent_clock(&now); + if (!timespec_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; now.tv_nsec = 0; - } + } else if (now.tv_sec || now.tv_nsec) + persistent_clock_exist = true; read_boot_clock(&boot); if (!timespec_valid_strict(&boot)) { @@ -718,11 +742,12 @@ void timekeeping_inject_sleeptime(struct timespec *delta) { struct timekeeper *tk = &timekeeper; unsigned long flags; - struct timespec ts; - /* Make sure we don't set the clock twice */ - read_persistent_clock(&ts); - if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) + /* + * Make sure we don't set the clock twice, as timekeeping_resume() + * already did it + */ + if (has_persistent_clock()) return; write_seqlock_irqsave(&tk->lock, flags); diff --git a/kernel/timeconst.pl b/kernel/timeconst.pl index eb51d76..3f42652 100644 --- a/kernel/timeconst.pl +++ b/kernel/timeconst.pl @@ -369,10 +369,8 @@ if ($hz eq '--can') { die "Usage: $0 HZ\n"; } - @val = @{$canned_values{$hz}}; - if (!defined(@val)) { - @val = compute_values($hz); - } + $cv = $canned_values{$hz}; + @val = defined($cv) ? @$cv : compute_values($hz); output($hz, @val); } exit 0; diff --git a/kernel/timer.c b/kernel/timer.c index 367d008..dbf7a78 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -39,6 +39,7 @@ #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched.h> +#include <linux/sched/sysctl.h> #include <linux/slab.h> #include <asm/uaccess.h> @@ -1351,7 +1352,6 @@ void update_process_times(int user_tick) account_process_tick(p, user_tick); run_local_timers(); rcu_check_callbacks(cpu, user_tick); - printk_tick(); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_run(); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 5d89335..3656756 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -39,6 +39,9 @@ config HAVE_DYNAMIC_FTRACE help See Documentation/trace/ftrace-design.txt +config HAVE_DYNAMIC_FTRACE_WITH_REGS + bool + config HAVE_FTRACE_MCOUNT_RECORD bool help @@ -250,6 +253,16 @@ config FTRACE_SYSCALLS help Basic tracer to catch the syscall entry and exit events. +config TRACER_SNAPSHOT + bool "Create a snapshot trace buffer" + select TRACER_MAX_TRACE + help + Allow tracing users to take snapshot of the current buffer using the + ftrace interface, e.g.: + + echo 1 > /sys/kernel/debug/tracing/snapshot + cat snapshot + config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER @@ -434,6 +447,11 @@ config DYNAMIC_FTRACE were made. If so, it runs stop_machine (stops all CPUS) and modifies the code to jump over the call to ftrace. +config DYNAMIC_FTRACE_WITH_REGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_REGS + config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index c0bd030..71259e2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -147,7 +147,7 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) return; local_irq_save(flags); - buf = per_cpu_ptr(bt->msg_data, smp_processor_id()); + buf = this_cpu_ptr(bt->msg_data); va_start(args, fmt); n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 41473b4..ce8c3d6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -111,6 +111,26 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); #define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) #endif +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /** * ftrace_nr_registered_ops - return number of ops registered * @@ -132,29 +152,21 @@ int ftrace_nr_registered_ops(void) return cnt; } -/* - * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw() is that elements removed from this list - * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw() calls are needed to handle - * concurrent insertions into the ftrace_global_list. - * - * Silly Alpha and silly pointer-speculation compiler optimizations! - */ static void ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs) { - if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) + int bit; + + bit = trace_test_and_set_recursion(TRACE_GLOBAL_START, TRACE_GLOBAL_MAX); + if (bit < 0) return; - trace_recursion_set(TRACE_GLOBAL_BIT); - op = rcu_dereference_raw(ftrace_global_list); /*see above*/ - while (op != &ftrace_list_end) { + do_for_each_ftrace_op(op, ftrace_global_list) { op->func(ip, parent_ip, op, regs); - op = rcu_dereference_raw(op->next); /*see above*/ - }; - trace_recursion_clear(TRACE_GLOBAL_BIT); + } while_for_each_ftrace_op(op); + + trace_clear_recursion(bit); } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, @@ -221,10 +233,24 @@ static void update_global_ops(void) * registered callers. */ if (ftrace_global_list == &ftrace_list_end || - ftrace_global_list->next == &ftrace_list_end) + ftrace_global_list->next == &ftrace_list_end) { func = ftrace_global_list->func; - else + /* + * As we are calling the function directly. + * If it does not have recursion protection, + * the function_trace_op needs to be updated + * accordingly. + */ + if (ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) + global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; + else + global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE; + } else { func = ftrace_global_list_func; + /* The list has its own recursion protection. */ + global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE; + } + /* If we filter on pids, update to use the pid function */ if (!list_empty(&ftrace_pids)) { @@ -337,7 +363,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) return -EINVAL; -#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS /* * If the ftrace_ops specifies SAVE_REGS, then it only can be used * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. @@ -4090,14 +4116,11 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, */ preempt_disable_notrace(); trace_recursion_set(TRACE_CONTROL_BIT); - op = rcu_dereference_raw(ftrace_control_list); - while (op != &ftrace_list_end) { + do_for_each_ftrace_op(op, ftrace_control_list) { if (!ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) op->func(ip, parent_ip, op, regs); - - op = rcu_dereference_raw(op->next); - }; + } while_for_each_ftrace_op(op); trace_recursion_clear(TRACE_CONTROL_BIT); preempt_enable_notrace(); } @@ -4112,27 +4135,26 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { struct ftrace_ops *op; + int bit; if (function_trace_stop) return; - if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) + bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + if (bit < 0) return; - trace_recursion_set(TRACE_INTERNAL_BIT); /* * Some of the ops may be dynamically allocated, * they must be freed after a synchronize_sched(). */ preempt_disable_notrace(); - op = rcu_dereference_raw(ftrace_ops_list); - while (op != &ftrace_list_end) { + do_for_each_ftrace_op(op, ftrace_ops_list) { if (ftrace_ops_test(op, ip)) op->func(ip, parent_ip, op, regs); - op = rcu_dereference_raw(op->next); - }; + } while_for_each_ftrace_op(op); preempt_enable_notrace(); - trace_recursion_clear(TRACE_INTERNAL_BIT); + trace_clear_recursion(bit); } /* @@ -4143,8 +4165,8 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, * Archs are to support both the regs and ftrace_ops at the same time. * If they support ftrace_ops, it is assumed they support regs. * If call backs want to use regs, they must either check for regs - * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS. - * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved. + * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS. + * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved. * An architecture can pass partial regs with ftrace_ops and still * set the ARCH_SUPPORT_FTARCE_OPS. */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index ce8514f..7244acd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3,8 +3,10 @@ * * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> */ +#include <linux/ftrace_event.h> #include <linux/ring_buffer.h> #include <linux/trace_clock.h> +#include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/debugfs.h> #include <linux/uaccess.h> @@ -21,7 +23,6 @@ #include <linux/fs.h> #include <asm/local.h> -#include "trace.h" static void update_pages_handler(struct work_struct *work); @@ -2432,41 +2433,76 @@ rb_reserve_next_event(struct ring_buffer *buffer, #ifdef CONFIG_TRACING -#define TRACE_RECURSIVE_DEPTH 16 +/* + * The lock and unlock are done within a preempt disable section. + * The current_context per_cpu variable can only be modified + * by the current task between lock and unlock. But it can + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. + * + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. + * + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. + */ +static DEFINE_PER_CPU(unsigned int, current_context); -/* Keep this code out of the fast path cache */ -static noinline void trace_recursive_fail(void) +static __always_inline int trace_recursive_lock(void) { - /* Disable all tracing before we do anything else */ - tracing_off_permanent(); - - printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:" - "HC[%lu]:SC[%lu]:NMI[%lu]\n", - trace_recursion_buffer(), - hardirq_count() >> HARDIRQ_SHIFT, - softirq_count() >> SOFTIRQ_SHIFT, - in_nmi()); - - WARN_ON_ONCE(1); -} + unsigned int val = this_cpu_read(current_context); + int bit; -static inline int trace_recursive_lock(void) -{ - trace_recursion_inc(); + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; - if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH)) - return 0; + if (unlikely(val & (1 << bit))) + return 1; - trace_recursive_fail(); + val |= (1 << bit); + this_cpu_write(current_context, val); - return -1; + return 0; } -static inline void trace_recursive_unlock(void) +static __always_inline void trace_recursive_unlock(void) { - WARN_ON_ONCE(!trace_recursion_buffer()); + unsigned int val = this_cpu_read(current_context); - trace_recursion_dec(); + val--; + val &= this_cpu_read(current_context); + this_cpu_write(current_context, val); } #else @@ -3067,6 +3103,24 @@ ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu); /** + * ring_buffer_read_events_cpu - get the number of events successfully read + * @buffer: The ring buffer + * @cpu: The per CPU buffer to get the number of events read + */ +unsigned long +ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + cpu_buffer = buffer->buffers[cpu]; + return cpu_buffer->read; +} +EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu); + +/** * ring_buffer_entries - get the number of entries in a buffer * @buffer: The ring buffer * @@ -3425,7 +3479,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) /* check for end of page padding */ if ((iter->head >= rb_page_size(iter->head_page)) && (iter->head_page != cpu_buffer->commit_page)) - rb_advance_iter(iter); + rb_inc_iter(iter); } static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3c13e46..c2e2c23 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -39,6 +39,7 @@ #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> +#include <linux/sched/rt.h> #include "trace.h" #include "trace_output.h" @@ -249,7 +250,7 @@ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; static struct tracer *trace_types __read_mostly; /* current_trace points to the tracer that is currently active */ -static struct tracer *current_trace __read_mostly; +static struct tracer *current_trace __read_mostly = &nop_trace; /* * trace_types_lock is used to protect the trace_types list. @@ -709,10 +710,13 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); - if (!current_trace->use_max_tr) { - WARN_ON_ONCE(1); + + if (!current_trace->allocated_snapshot) { + /* Only the nop tracer should hit this when disabling */ + WARN_ON_ONCE(current_trace != &nop_trace); return; } + arch_spin_lock(&ftrace_max_lock); tr->buffer = max_tr.buffer; @@ -739,10 +743,8 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); - if (!current_trace->use_max_tr) { - WARN_ON_ONCE(1); + if (WARN_ON_ONCE(!current_trace->allocated_snapshot)) return; - } arch_spin_lock(&ftrace_max_lock); @@ -862,10 +864,13 @@ int register_tracer(struct tracer *type) current_trace = type; - /* If we expanded the buffers, make sure the max is expanded too */ - if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, trace_buf_size, - RING_BUFFER_ALL_CPUS); + if (type->use_max_tr) { + /* If we expanded the buffers, make sure the max is expanded too */ + if (ring_buffer_expanded) + ring_buffer_resize(max_tr.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); + type->allocated_snapshot = true; + } /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); @@ -881,10 +886,14 @@ int register_tracer(struct tracer *type) /* Only reset on passing, to avoid touching corrupted buffers */ tracing_reset_online_cpus(tr); - /* Shrink the max buffer again */ - if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, 1, - RING_BUFFER_ALL_CPUS); + if (type->use_max_tr) { + type->allocated_snapshot = false; + + /* Shrink the max buffer again */ + if (ring_buffer_expanded) + ring_buffer_resize(max_tr.buffer, 1, + RING_BUFFER_ALL_CPUS); + } printk(KERN_CONT "PASSED\n"); } @@ -922,6 +931,9 @@ void tracing_reset(struct trace_array *tr, int cpu) { struct ring_buffer *buffer = tr->buffer; + if (!buffer) + return; + ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ @@ -936,6 +948,9 @@ void tracing_reset_online_cpus(struct trace_array *tr) struct ring_buffer *buffer = tr->buffer; int cpu; + if (!buffer) + return; + ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ @@ -1167,7 +1182,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; - entry->padding = 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -1335,7 +1349,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, */ preempt_disable_notrace(); - use_stack = ++__get_cpu_var(ftrace_stack_reserve); + use_stack = __this_cpu_inc_return(ftrace_stack_reserve); /* * We don't need any atomic variables, just a barrier. * If an interrupt comes in, we don't care, because it would @@ -1389,7 +1403,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, out: /* Again, don't let gcc optimize things here */ barrier(); - __get_cpu_var(ftrace_stack_reserve)--; + __this_cpu_dec(ftrace_stack_reserve); preempt_enable_notrace(); } @@ -1517,7 +1531,6 @@ static struct trace_buffer_struct *trace_percpu_nmi_buffer; static char *get_trace_buf(void) { struct trace_buffer_struct *percpu_buffer; - struct trace_buffer_struct *buffer; /* * If we have allocated per cpu buffers, then we do not @@ -1535,9 +1548,7 @@ static char *get_trace_buf(void) if (!percpu_buffer) return NULL; - buffer = per_cpu_ptr(percpu_buffer, smp_processor_id()); - - return buffer->buffer; + return this_cpu_ptr(&percpu_buffer->buffer[0]); } static int alloc_percpu_trace_buffer(void) @@ -1942,21 +1953,27 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; - static struct tracer *old_tracer; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; int cpu; - /* copy the tracer to avoid using a global lock all around */ + /* + * copy the tracer to avoid using a global lock all around. + * iter->trace is a copy of current_trace, the pointer to the + * name may be used instead of a strcmp(), as iter->trace->name + * will point to the same string as current_trace->name. + */ mutex_lock(&trace_types_lock); - if (unlikely(old_tracer != current_trace && current_trace)) { - old_tracer = current_trace; + if (unlikely(current_trace && iter->trace->name != current_trace->name)) *iter->trace = *current_trace; - } mutex_unlock(&trace_types_lock); - atomic_inc(&trace_record_cmdline_disabled); + if (iter->snapshot && iter->trace->use_max_tr) + return ERR_PTR(-EBUSY); + + if (!iter->snapshot) + atomic_inc(&trace_record_cmdline_disabled); if (*pos != iter->pos) { iter->ent = NULL; @@ -1995,7 +2012,11 @@ static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; - atomic_dec(&trace_record_cmdline_disabled); + if (iter->snapshot && iter->trace->use_max_tr) + return; + + if (!iter->snapshot) + atomic_dec(&trace_record_cmdline_disabled); trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } @@ -2080,8 +2101,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) unsigned long total; const char *name = "preemption"; - if (type) - name = type->name; + name = type->name; get_total_entries(tr, &total, &entries); @@ -2430,7 +2450,7 @@ static const struct seq_operations tracer_seq_ops = { }; static struct trace_iterator * -__tracing_open(struct inode *inode, struct file *file) +__tracing_open(struct inode *inode, struct file *file, bool snapshot) { long cpu_file = (long) inode->i_private; struct trace_iterator *iter; @@ -2457,16 +2477,16 @@ __tracing_open(struct inode *inode, struct file *file) if (!iter->trace) goto fail; - if (current_trace) - *iter->trace = *current_trace; + *iter->trace = *current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; - if (current_trace && current_trace->print_max) + if (current_trace->print_max || snapshot) iter->tr = &max_tr; else iter->tr = &global_trace; + iter->snapshot = snapshot; iter->pos = -1; mutex_init(&iter->mutex); iter->cpu_file = cpu_file; @@ -2483,8 +2503,9 @@ __tracing_open(struct inode *inode, struct file *file) if (trace_clocks[trace_clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - /* stop the trace while dumping */ - tracing_stop(); + /* stop the trace while dumping if we are not opening "snapshot" */ + if (!iter->snapshot) + tracing_stop(); if (iter->cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) { @@ -2547,8 +2568,9 @@ static int tracing_release(struct inode *inode, struct file *file) if (iter->trace && iter->trace->close) iter->trace->close(iter); - /* reenable tracing if it was previously enabled */ - tracing_start(); + if (!iter->snapshot) + /* reenable tracing if it was previously enabled */ + tracing_start(); mutex_unlock(&trace_types_lock); mutex_destroy(&iter->mutex); @@ -2576,7 +2598,7 @@ static int tracing_open(struct inode *inode, struct file *file) } if (file->f_mode & FMODE_READ) { - iter = __tracing_open(inode, file); + iter = __tracing_open(inode, file, false); if (IS_ERR(iter)) ret = PTR_ERR(iter); else if (trace_flags & TRACE_ITER_LATENCY_FMT) @@ -3014,10 +3036,7 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, int r; mutex_lock(&trace_types_lock); - if (current_trace) - r = sprintf(buf, "%s\n", current_trace->name); - else - r = sprintf(buf, "\n"); + r = sprintf(buf, "%s\n", current_trace->name); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); @@ -3183,6 +3202,7 @@ static int tracing_set_tracer(const char *buf) static struct trace_option_dentry *topts; struct trace_array *tr = &global_trace; struct tracer *t; + bool had_max_tr; int ret = 0; mutex_lock(&trace_types_lock); @@ -3207,9 +3227,21 @@ static int tracing_set_tracer(const char *buf) goto out; trace_branch_disable(); - if (current_trace && current_trace->reset) + if (current_trace->reset) current_trace->reset(tr); - if (current_trace && current_trace->use_max_tr) { + + had_max_tr = current_trace->allocated_snapshot; + current_trace = &nop_trace; + + if (had_max_tr && !t->use_max_tr) { + /* + * We need to make sure that the update_max_tr sees that + * current_trace changed to nop_trace to keep it from + * swapping the buffers after we resize it. + * The update_max_tr is called from interrupts disabled + * so a synchronized_sched() is sufficient. + */ + synchronize_sched(); /* * We don't free the ring buffer. instead, resize it because * The max_tr ring buffer has some state (e.g. ring->clock) and @@ -3217,18 +3249,19 @@ static int tracing_set_tracer(const char *buf) */ ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&max_tr, 1); + tracing_reset_online_cpus(&max_tr); + current_trace->allocated_snapshot = false; } destroy_trace_option_files(topts); - current_trace = &nop_trace; - topts = create_trace_option_files(t); - if (t->use_max_tr) { + if (t->use_max_tr && !had_max_tr) { /* we need to make per cpu buffer sizes equivalent */ ret = resize_buffer_duplicate_size(&max_tr, &global_trace, RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; + t->allocated_snapshot = true; } if (t->init) { @@ -3336,8 +3369,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) ret = -ENOMEM; goto fail; } - if (current_trace) - *iter->trace = *current_trace; + *iter->trace = *current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; @@ -3477,7 +3509,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; - static struct tracer *old_tracer; ssize_t sret; /* return any leftover data */ @@ -3489,10 +3520,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(old_tracer != current_trace && current_trace)) { - old_tracer = current_trace; + if (unlikely(iter->trace->name != current_trace->name)) *iter->trace = *current_trace; - } mutex_unlock(&trace_types_lock); /* @@ -3648,7 +3677,6 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; - static struct tracer *old_tracer; ssize_t ret; size_t rem; unsigned int i; @@ -3658,10 +3686,8 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, /* copy the tracer to avoid using a global lock all around */ mutex_lock(&trace_types_lock); - if (unlikely(old_tracer != current_trace && current_trace)) { - old_tracer = current_trace; + if (unlikely(iter->trace->name != current_trace->name)) *iter->trace = *current_trace; - } mutex_unlock(&trace_types_lock); mutex_lock(&iter->mutex); @@ -4037,8 +4063,7 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, * Reset the buffer so that it doesn't have incomparable timestamps. */ tracing_reset_online_cpus(&global_trace); - if (max_tr.buffer) - tracing_reset_online_cpus(&max_tr); + tracing_reset_online_cpus(&max_tr); mutex_unlock(&trace_types_lock); @@ -4054,6 +4079,87 @@ static int tracing_clock_open(struct inode *inode, struct file *file) return single_open(file, tracing_clock_show, NULL); } +#ifdef CONFIG_TRACER_SNAPSHOT +static int tracing_snapshot_open(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter; + int ret = 0; + + if (file->f_mode & FMODE_READ) { + iter = __tracing_open(inode, file, true); + if (IS_ERR(iter)) + ret = PTR_ERR(iter); + } + return ret; +} + +static ssize_t +tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = tracing_update_buffers(); + if (ret < 0) + return ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + mutex_lock(&trace_types_lock); + + if (current_trace->use_max_tr) { + ret = -EBUSY; + goto out; + } + + switch (val) { + case 0: + if (current_trace->allocated_snapshot) { + /* free spare buffer */ + ring_buffer_resize(max_tr.buffer, 1, + RING_BUFFER_ALL_CPUS); + set_buffer_entries(&max_tr, 1); + tracing_reset_online_cpus(&max_tr); + current_trace->allocated_snapshot = false; + } + break; + case 1: + if (!current_trace->allocated_snapshot) { + /* allocate spare buffer */ + ret = resize_buffer_duplicate_size(&max_tr, + &global_trace, RING_BUFFER_ALL_CPUS); + if (ret < 0) + break; + current_trace->allocated_snapshot = true; + } + + local_irq_disable(); + /* Now, we're going to swap */ + update_max_tr(&global_trace, current, smp_processor_id()); + local_irq_enable(); + break; + default: + if (current_trace->allocated_snapshot) + tracing_reset_online_cpus(&max_tr); + else + ret = -EINVAL; + break; + } + + if (ret >= 0) { + *ppos += cnt; + ret = cnt; + } +out: + mutex_unlock(&trace_types_lock); + return ret; +} +#endif /* CONFIG_TRACER_SNAPSHOT */ + + static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, @@ -4110,6 +4216,16 @@ static const struct file_operations trace_clock_fops = { .write = tracing_clock_write, }; +#ifdef CONFIG_TRACER_SNAPSHOT +static const struct file_operations snapshot_fops = { + .open = tracing_snapshot_open, + .read = seq_read, + .write = tracing_snapshot_write, + .llseek = tracing_seek, + .release = tracing_release, +}; +#endif /* CONFIG_TRACER_SNAPSHOT */ + struct ftrace_buffer_info { struct trace_array *tr; void *spare; @@ -4414,6 +4530,9 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_dropped_events_cpu(tr->buffer, cpu); trace_seq_printf(s, "dropped events: %ld\n", cnt); + cnt = ring_buffer_read_events_cpu(tr->buffer, cpu); + trace_seq_printf(s, "read events: %ld\n", cnt); + count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); kfree(s); @@ -4490,7 +4609,7 @@ struct dentry *tracing_init_dentry(void) static struct dentry *d_percpu; -struct dentry *tracing_dentry_percpu(void) +static struct dentry *tracing_dentry_percpu(void) { static int once; struct dentry *d_tracer; @@ -4906,6 +5025,11 @@ static __init int tracer_init_debugfs(void) &ftrace_update_tot_cnt, &tracing_dyn_info_fops); #endif +#ifdef CONFIG_TRACER_SNAPSHOT + trace_create_file("snapshot", 0644, d_tracer, + (void *) TRACE_PIPE_ALL_CPU, &snapshot_fops); +#endif + create_trace_options_dir(); for_each_tracing_cpu(cpu) @@ -5014,6 +5138,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (disable_tracing) ftrace_kill(); + /* Simulate the iterator */ trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { @@ -5025,10 +5150,6 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) /* don't look at user memory in panic mode */ trace_flags &= ~TRACE_ITER_SYM_USEROBJ; - /* Simulate the iterator */ - iter.tr = &global_trace; - iter.trace = current_trace; - switch (oops_dump_mode) { case DUMP_ALL: iter.cpu_file = TRACE_PIPE_ALL_CPU; @@ -5173,7 +5294,7 @@ __init static int tracer_alloc_buffers(void) init_irq_work(&trace_work_wakeup, trace_wake_up); register_tracer(&nop_trace); - current_trace = &nop_trace; + /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index c75d798..57d7e53 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -287,20 +287,62 @@ struct tracer { struct tracer_flags *flags; bool print_max; bool use_max_tr; + bool allocated_snapshot; }; /* Only current can touch trace_recursion */ -#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0) -#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0) -/* Ring buffer has the 10 LSB bits to count */ -#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff) - -/* for function tracing recursion */ -#define TRACE_INTERNAL_BIT (1<<11) -#define TRACE_GLOBAL_BIT (1<<12) -#define TRACE_CONTROL_BIT (1<<13) +/* + * For function tracing recursion: + * The order of these bits are important. + * + * When function tracing occurs, the following steps are made: + * If arch does not support a ftrace feature: + * call internal function (uses INTERNAL bits) which calls... + * If callback is registered to the "global" list, the list + * function is called and recursion checks the GLOBAL bits. + * then this function calls... + * The function callback, which can use the FTRACE bits to + * check for recursion. + * + * Now if the arch does not suppport a feature, and it calls + * the global list function which calls the ftrace callback + * all three of these steps will do a recursion protection. + * There's no reason to do one if the previous caller already + * did. The recursion that we are protecting against will + * go through the same steps again. + * + * To prevent the multiple recursion checks, if a recursion + * bit is set that is higher than the MAX bit of the current + * check, then we know that the check was made by the previous + * caller, and we can skip the current check. + */ +enum { + TRACE_BUFFER_BIT, + TRACE_BUFFER_NMI_BIT, + TRACE_BUFFER_IRQ_BIT, + TRACE_BUFFER_SIRQ_BIT, + + /* Start of function recursion bits */ + TRACE_FTRACE_BIT, + TRACE_FTRACE_NMI_BIT, + TRACE_FTRACE_IRQ_BIT, + TRACE_FTRACE_SIRQ_BIT, + + /* GLOBAL_BITs must be greater than FTRACE_BITs */ + TRACE_GLOBAL_BIT, + TRACE_GLOBAL_NMI_BIT, + TRACE_GLOBAL_IRQ_BIT, + TRACE_GLOBAL_SIRQ_BIT, + + /* INTERNAL_BITs must be greater than GLOBAL_BITs */ + TRACE_INTERNAL_BIT, + TRACE_INTERNAL_NMI_BIT, + TRACE_INTERNAL_IRQ_BIT, + TRACE_INTERNAL_SIRQ_BIT, + + TRACE_CONTROL_BIT, /* * Abuse of the trace_recursion. @@ -309,11 +351,77 @@ struct tracer { * was called in irq context but we have irq tracing off. Since this * can only be modified by current, we can reuse trace_recursion. */ -#define TRACE_IRQ_BIT (1<<13) + TRACE_IRQ_BIT, +}; + +#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) +#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) +#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) + +#define TRACE_CONTEXT_BITS 4 + +#define TRACE_FTRACE_START TRACE_FTRACE_BIT +#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_GLOBAL_START TRACE_GLOBAL_BIT +#define TRACE_GLOBAL_MAX ((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_LIST_START TRACE_INTERNAL_BIT +#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) + +#define TRACE_CONTEXT_MASK TRACE_LIST_MAX + +static __always_inline int trace_get_context_bit(void) +{ + int bit; -#define trace_recursion_set(bit) do { (current)->trace_recursion |= (bit); } while (0) -#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(bit); } while (0) -#define trace_recursion_test(bit) ((current)->trace_recursion & (bit)) + if (in_interrupt()) { + if (in_nmi()) + bit = 0; + + else if (in_irq()) + bit = 1; + else + bit = 2; + } else + bit = 3; + + return bit; +} + +static __always_inline int trace_test_and_set_recursion(int start, int max) +{ + unsigned int val = current->trace_recursion; + int bit; + + /* A previous recursion check was made */ + if ((val & TRACE_CONTEXT_MASK) > max) + return 0; + + bit = trace_get_context_bit() + start; + if (unlikely(val & (1 << bit))) + return -1; + + val |= 1 << bit; + current->trace_recursion = val; + barrier(); + + return bit; +} + +static __always_inline void trace_clear_recursion(int bit) +{ + unsigned int val = current->trace_recursion; + + if (!bit) + return; + + bit = 1 << bit; + val &= ~bit; + + barrier(); + current->trace_recursion = val; +} #define TRACE_PIPE_ALL_CPU -1 diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 3947835..aa8f5f4 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -21,8 +21,6 @@ #include <linux/ktime.h> #include <linux/trace_clock.h> -#include "trace.h" - /* * trace_clock_local(): the simplest and least coherent tracing clock. * @@ -44,6 +42,7 @@ u64 notrace trace_clock_local(void) return clock; } +EXPORT_SYMBOL_GPL(trace_clock_local); /* * trace_clock(): 'between' trace clock. Not completely serialized, @@ -86,7 +85,7 @@ u64 notrace trace_clock_global(void) local_irq_save(flags); this_cpu = raw_smp_processor_id(); - now = cpu_clock(this_cpu); + now = sched_clock_cpu(this_cpu); /* * If in an NMI context then dont risk lockups and return the * cpu_clock() time: diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 880073d..57e9b28 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,7 +116,6 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); - __common_field(int, padding); return ret; } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 8e3ad80..6011525 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -47,34 +47,6 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(tr); } -static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) -{ - struct trace_array *tr = func_trace; - struct trace_array_cpu *data; - unsigned long flags; - long disabled; - int cpu; - int pc; - - if (unlikely(!ftrace_function_enabled)) - return; - - pc = preempt_count(); - preempt_disable_notrace(); - local_save_flags(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - - if (likely(disabled == 1)) - trace_function(tr, ip, parent_ip, flags, pc); - - atomic_dec(&data->disabled); - preempt_enable_notrace(); -} - /* Our option */ enum { TRACE_FUNC_OPT_STACK = 0x1, @@ -85,34 +57,34 @@ static struct tracer_flags func_flags; static void function_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) - { struct trace_array *tr = func_trace; struct trace_array_cpu *data; unsigned long flags; - long disabled; + int bit; int cpu; int pc; if (unlikely(!ftrace_function_enabled)) return; - /* - * Need to use raw, since this must be called before the - * recursive protection is performed. - */ - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); + pc = preempt_count(); + preempt_disable_notrace(); - if (likely(disabled == 1)) { - pc = preempt_count(); + bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); + if (bit < 0) + goto out; + + cpu = smp_processor_id(); + data = tr->data[cpu]; + if (!atomic_read(&data->disabled)) { + local_save_flags(flags); trace_function(tr, ip, parent_ip, flags, pc); } + trace_clear_recursion(bit); - atomic_dec(&data->disabled); - local_irq_restore(flags); + out: + preempt_enable_notrace(); } static void @@ -185,11 +157,6 @@ static void tracing_start_function_trace(void) { ftrace_function_enabled = 0; - if (trace_flags & TRACE_ITER_PREEMPTONLY) - trace_ops.func = function_trace_call_preempt_only; - else - trace_ops.func = function_trace_call; - if (func_flags.val & TRACE_FUNC_OPT_STACK) register_ftrace_function(&trace_stack_ops); else diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 4edb4b7..39ada66 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -47,6 +47,8 @@ struct fgraph_data { #define TRACE_GRAPH_PRINT_ABS_TIME 0x20 #define TRACE_GRAPH_PRINT_IRQS 0x40 +static unsigned int max_depth; + static struct tracer_opt trace_opts[] = { /* Display overruns? (for self-debug purpose) */ { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) }, @@ -189,10 +191,16 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); - ftrace_graph_return(&trace); barrier(); current->curr_ret_stack--; + /* + * The trace should run after decrementing the ret counter + * in case an interrupt were to come in. We don't want to + * lose the interrupt if max_depth is set. + */ + ftrace_graph_return(&trace); + if (unlikely(!ret)) { ftrace_graph_stop(); WARN_ON(1); @@ -250,8 +258,9 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return 0; /* trace it when it is-nested-in or is a function enabled. */ - if (!(trace->depth || ftrace_graph_addr(trace->func)) || - ftrace_graph_ignore_irqs()) + if ((!(trace->depth || ftrace_graph_addr(trace->func)) || + ftrace_graph_ignore_irqs()) || + (max_depth && trace->depth >= max_depth)) return 0; local_irq_save(flags); @@ -1457,6 +1466,59 @@ static struct tracer graph_trace __read_mostly = { #endif }; + +static ssize_t +graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + max_depth = val; + + *ppos += cnt; + + return cnt; +} + +static ssize_t +graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/ + int n; + + n = sprintf(buf, "%d\n", max_depth); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static const struct file_operations graph_depth_fops = { + .open = tracing_open_generic, + .write = graph_depth_write, + .read = graph_depth_read, + .llseek = generic_file_llseek, +}; + +static __init int init_graph_debugfs(void) +{ + struct dentry *d_tracer; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + trace_create_file("max_graph_depth", 0644, d_tracer, + NULL, &graph_depth_fops); + + return 0; +} +fs_initcall(init_graph_debugfs); + static __init int init_graph_trace(void) { max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 9337086..5c7e09d 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -66,7 +66,6 @@ #define TP_FLAG_TRACE 1 #define TP_FLAG_PROFILE 2 #define TP_FLAG_REGISTERED 4 -#define TP_FLAG_UPROBE 8 /* data_rloc: data relative location, compatible with u32 */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 9fe45fc..75aa97f 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -15,8 +15,8 @@ #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/ftrace.h> +#include <linux/sched/rt.h> #include <trace/events/sched.h> - #include "trace.h" static struct trace_array *wakeup_trace; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 4762316..51c819c 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -415,7 +415,8 @@ static void trace_selftest_test_recursion_func(unsigned long ip, * The ftrace infrastructure should provide the recursion * protection. If not, this will crash the kernel! */ - trace_selftest_recursion_cnt++; + if (trace_selftest_recursion_cnt++ > 10) + return; DYN_FTRACE_TEST_NAME(); } @@ -452,7 +453,6 @@ trace_selftest_function_recursion(void) char *func_name; int len; int ret; - int cnt; /* The previous test PASSED */ pr_cont("PASSED\n"); @@ -510,19 +510,10 @@ trace_selftest_function_recursion(void) unregister_ftrace_function(&test_recsafe_probe); - /* - * If arch supports all ftrace features, and no other task - * was on the list, we should be fine. - */ - if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC) - cnt = 2; /* Should have recursed */ - else - cnt = 1; - ret = -1; - if (trace_selftest_recursion_cnt != cnt) { - pr_cont("*callback not called expected %d times (%d)* ", - cnt, trace_selftest_recursion_cnt); + if (trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called expected 2 times (%d)* ", + trace_selftest_recursion_cnt); goto out; } @@ -568,7 +559,7 @@ trace_selftest_function_regs(void) int ret; int supported = 0; -#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS supported = 1; #endif diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 7609dd6..5329e13e 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -77,7 +77,7 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr) return syscalls_metadata[nr]; } -enum print_line_t +static enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags, struct trace_event *event) { @@ -130,7 +130,7 @@ end: return TRACE_TYPE_HANDLED; } -enum print_line_t +static enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags, struct trace_event *event) { @@ -270,7 +270,7 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call) return ret; } -void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) +static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) { struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; @@ -305,7 +305,7 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) +static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) { struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; @@ -337,7 +337,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) trace_current_buffer_unlock_commit(buffer, event, 0, 0); } -int reg_event_syscall_enter(struct ftrace_event_call *call) +static int reg_event_syscall_enter(struct ftrace_event_call *call) { int ret = 0; int num; @@ -356,7 +356,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call) return ret; } -void unreg_event_syscall_enter(struct ftrace_event_call *call) +static void unreg_event_syscall_enter(struct ftrace_event_call *call) { int num; @@ -371,7 +371,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call) mutex_unlock(&syscall_trace_lock); } -int reg_event_syscall_exit(struct ftrace_event_call *call) +static int reg_event_syscall_exit(struct ftrace_event_call *call) { int ret = 0; int num; @@ -390,7 +390,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call) return ret; } -void unreg_event_syscall_exit(struct ftrace_event_call *call) +static void unreg_event_syscall_exit(struct ftrace_event_call *call) { int num; @@ -459,7 +459,7 @@ unsigned long __init __weak arch_syscall_addr(int nr) return (unsigned long)sys_call_table[nr]; } -int __init init_ftrace_syscalls(void) +static int __init init_ftrace_syscalls(void) { struct syscall_metadata *meta; unsigned long addr; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index c86e6d4..8dad2a9 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -28,20 +28,21 @@ #define UPROBE_EVENT_SYSTEM "uprobes" +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + /* * uprobe event core functions */ -struct trace_uprobe; -struct uprobe_trace_consumer { - struct uprobe_consumer cons; - struct trace_uprobe *tu; -}; - struct trace_uprobe { struct list_head list; struct ftrace_event_class class; struct ftrace_event_call call; - struct uprobe_trace_consumer *consumer; + struct trace_uprobe_filter filter; + struct uprobe_consumer consumer; struct inode *inode; char *filename; unsigned long offset; @@ -64,6 +65,18 @@ static LIST_HEAD(uprobe_list); static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); +static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) +{ + rwlock_init(&filter->rwlock); + filter->nr_systemwide = 0; + INIT_LIST_HEAD(&filter->perf_events); +} + +static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) +{ + return !filter->nr_systemwide && list_empty(&filter->perf_events); +} + /* * Allocate new trace_uprobe and initialize it (including uprobes). */ @@ -92,6 +105,8 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs) goto error; INIT_LIST_HEAD(&tu->list); + tu->consumer.handler = uprobe_dispatcher; + init_trace_uprobe_filter(&tu->filter); return tu; error: @@ -253,12 +268,18 @@ static int create_trace_uprobe(int argc, char **argv) if (ret) goto fail_address_parse; + inode = igrab(path.dentry->d_inode); + path_put(&path); + + if (!inode || !S_ISREG(inode->i_mode)) { + ret = -EINVAL; + goto fail_address_parse; + } + ret = kstrtoul(arg, 0, &offset); if (ret) goto fail_address_parse; - inode = igrab(path.dentry->d_inode); - argc -= 2; argv += 2; @@ -356,7 +377,7 @@ fail_address_parse: if (inode) iput(inode); - pr_info("Failed to parse address.\n"); + pr_info("Failed to parse address or file.\n"); return ret; } @@ -465,7 +486,7 @@ static const struct file_operations uprobe_profile_ops = { }; /* uprobe handler */ -static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) { struct uprobe_trace_entry_head *entry; struct ring_buffer_event *event; @@ -475,8 +496,6 @@ static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) unsigned long irq_flags; struct ftrace_event_call *call = &tu->call; - tu->nhit++; - local_save_flags(irq_flags); pc = preempt_count(); @@ -485,16 +504,18 @@ static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs) event = trace_current_buffer_lock_reserve(&buffer, call->event.type, size, irq_flags, pc); if (!event) - return; + return 0; entry = ring_buffer_event_data(event); - entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + entry->ip = instruction_pointer(task_pt_regs(current)); data = (u8 *)&entry[1]; for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); if (!filter_current_check_discard(buffer, call, entry, event)) trace_buffer_unlock_commit(buffer, event, irq_flags, pc); + + return 0; } /* Event entry printers */ @@ -533,42 +554,43 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -static int probe_event_enable(struct trace_uprobe *tu, int flag) +static inline bool is_trace_uprobe_enabled(struct trace_uprobe *tu) { - struct uprobe_trace_consumer *utc; - int ret = 0; + return tu->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE); +} - if (!tu->inode || tu->consumer) - return -EINTR; +typedef bool (*filter_func_t)(struct uprobe_consumer *self, + enum uprobe_filter_ctx ctx, + struct mm_struct *mm); - utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL); - if (!utc) +static int +probe_event_enable(struct trace_uprobe *tu, int flag, filter_func_t filter) +{ + int ret = 0; + + if (is_trace_uprobe_enabled(tu)) return -EINTR; - utc->cons.handler = uprobe_dispatcher; - utc->cons.filter = NULL; - ret = uprobe_register(tu->inode, tu->offset, &utc->cons); - if (ret) { - kfree(utc); - return ret; - } + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); tu->flags |= flag; - utc->tu = tu; - tu->consumer = utc; + tu->consumer.filter = filter; + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + if (ret) + tu->flags &= ~flag; - return 0; + return ret; } static void probe_event_disable(struct trace_uprobe *tu, int flag) { - if (!tu->inode || !tu->consumer) + if (!is_trace_uprobe_enabled(tu)) return; - uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons); + WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->flags &= ~flag; - kfree(tu->consumer); - tu->consumer = NULL; } static int uprobe_event_define_fields(struct ftrace_event_call *event_call) @@ -642,8 +664,96 @@ static int set_print_fmt(struct trace_uprobe *tu) } #ifdef CONFIG_PERF_EVENTS +static bool +__uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) +{ + struct perf_event *event; + + if (filter->nr_systemwide) + return true; + + list_for_each_entry(event, &filter->perf_events, hw.tp_list) { + if (event->hw.tp_target->mm == mm) + return true; + } + + return false; +} + +static inline bool +uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +{ + return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm); +} + +static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + + write_lock(&tu->filter.rwlock); + if (event->hw.tp_target) { + /* + * event->parent != NULL means copy_process(), we can avoid + * uprobe_apply(). current->mm must be probed and we can rely + * on dup_mmap() which preserves the already installed bp's. + * + * attr.enable_on_exec means that exec/mmap will install the + * breakpoints we need. + */ + done = tu->filter.nr_systemwide || + event->parent || event->attr.enable_on_exec || + uprobe_filter_event(tu, event); + list_add(&event->hw.tp_list, &tu->filter.perf_events); + } else { + done = tu->filter.nr_systemwide; + tu->filter.nr_systemwide++; + } + write_unlock(&tu->filter.rwlock); + + if (!done) + uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + + return 0; +} + +static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +{ + bool done; + + write_lock(&tu->filter.rwlock); + if (event->hw.tp_target) { + list_del(&event->hw.tp_list); + done = tu->filter.nr_systemwide || + (event->hw.tp_target->flags & PF_EXITING) || + uprobe_filter_event(tu, event); + } else { + tu->filter.nr_systemwide--; + done = tu->filter.nr_systemwide; + } + write_unlock(&tu->filter.rwlock); + + if (!done) + uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + + return 0; +} + +static bool uprobe_perf_filter(struct uprobe_consumer *uc, + enum uprobe_filter_ctx ctx, struct mm_struct *mm) +{ + struct trace_uprobe *tu; + int ret; + + tu = container_of(uc, struct trace_uprobe, consumer); + read_lock(&tu->filter.rwlock); + ret = __uprobe_perf_filter(&tu->filter, mm); + read_unlock(&tu->filter.rwlock); + + return ret; +} + /* uprobe profile handler */ -static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) +static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) { struct ftrace_event_call *call = &tu->call; struct uprobe_trace_entry_head *entry; @@ -652,11 +762,14 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) int size, __size, i; int rctx; + if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) + return UPROBE_HANDLER_REMOVE; + __size = sizeof(*entry) + tu->size; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) - return; + return 0; preempt_disable(); @@ -664,7 +777,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) if (!entry) goto out; - entry->ip = uprobe_get_swbp_addr(task_pt_regs(current)); + entry->ip = instruction_pointer(task_pt_regs(current)); data = (u8 *)&entry[1]; for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); @@ -674,6 +787,7 @@ static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs) out: preempt_enable(); + return 0; } #endif /* CONFIG_PERF_EVENTS */ @@ -684,7 +798,7 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, TP_FLAG_TRACE); + return probe_event_enable(tu, TP_FLAG_TRACE, NULL); case TRACE_REG_UNREGISTER: probe_event_disable(tu, TP_FLAG_TRACE); @@ -692,11 +806,18 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, TP_FLAG_PROFILE); + return probe_event_enable(tu, TP_FLAG_PROFILE, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: probe_event_disable(tu, TP_FLAG_PROFILE); return 0; + + case TRACE_REG_PERF_OPEN: + return uprobe_perf_open(tu, data); + + case TRACE_REG_PERF_CLOSE: + return uprobe_perf_close(tu, data); + #endif default: return 0; @@ -706,22 +827,20 @@ int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { - struct uprobe_trace_consumer *utc; struct trace_uprobe *tu; + int ret = 0; - utc = container_of(con, struct uprobe_trace_consumer, cons); - tu = utc->tu; - if (!tu || tu->consumer != utc) - return 0; + tu = container_of(con, struct trace_uprobe, consumer); + tu->nhit++; if (tu->flags & TP_FLAG_TRACE) - uprobe_trace_func(tu, regs); + ret |= uprobe_trace_func(tu, regs); #ifdef CONFIG_PERF_EVENTS if (tu->flags & TP_FLAG_PROFILE) - uprobe_perf_func(tu, regs); + ret |= uprobe_perf_func(tu, regs); #endif - return 0; + return ret; } static struct trace_event_functions uprobe_funcs = { diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 625df0b..a1dd9a1 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -32,6 +32,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, { const struct cred *tcred; struct timespec uptime, ts; + cputime_t utime, stime, utimescaled, stimescaled; u64 ac_etime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); @@ -65,10 +66,15 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_ppid = pid_alive(tsk) ? task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0; rcu_read_unlock(); - stats->ac_utime = cputime_to_usecs(tsk->utime); - stats->ac_stime = cputime_to_usecs(tsk->stime); - stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled); - stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled); + + task_cputime(tsk, &utime, &stime); + stats->ac_utime = cputime_to_usecs(utime); + stats->ac_stime = cputime_to_usecs(stime); + + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + stats->ac_utimescaled = cputime_to_usecs(utimescaled); + stats->ac_stimescaled = cputime_to_usecs(stimescaled); + stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; @@ -115,11 +121,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) #undef KB #undef MB -/** - * acct_update_integrals - update mm integral fields in task_struct - * @tsk: task_struct for accounting - */ -void acct_update_integrals(struct task_struct *tsk) +static void __acct_update_integrals(struct task_struct *tsk, + cputime_t utime, cputime_t stime) { if (likely(tsk->mm)) { cputime_t time, dtime; @@ -128,7 +131,7 @@ void acct_update_integrals(struct task_struct *tsk) u64 delta; local_irq_save(flags); - time = tsk->stime + tsk->utime; + time = stime + utime; dtime = time - tsk->acct_timexpd; jiffies_to_timeval(cputime_to_jiffies(dtime), &value); delta = value.tv_sec; @@ -145,6 +148,27 @@ void acct_update_integrals(struct task_struct *tsk) } /** + * acct_update_integrals - update mm integral fields in task_struct + * @tsk: task_struct for accounting + */ +void acct_update_integrals(struct task_struct *tsk) +{ + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); + __acct_update_integrals(tsk, utime, stime); +} + +/** + * acct_account_cputime - update mm integral after cputime update + * @tsk: task_struct for accounting + */ +void acct_account_cputime(struct task_struct *tsk) +{ + __acct_update_integrals(tsk, tsk->utime, tsk->stime); +} + +/** * acct_clear_integrals - clear the mm integral fields in task_struct * @tsk: task_struct whose accounting fields are cleared */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 75a2ab3..2768942 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -23,6 +23,7 @@ #include <linux/module.h> #include <linux/sysctl.h> #include <linux/smpboot.h> +#include <linux/sched/rt.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> diff --git a/kernel/workqueue.c b/kernel/workqueue.c index fbc6576..f4feaca 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -41,32 +41,31 @@ #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> +#include <linux/hashtable.h> -#include "workqueue_sched.h" +#include "workqueue_internal.h" enum { /* - * global_cwq flags + * worker_pool flags * - * A bound gcwq is either associated or disassociated with its CPU. + * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may - * be executing on any CPU. The gcwq behaves as an unbound one. + * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED can be flipped only while holding - * assoc_mutex of all pools on the gcwq to avoid changing binding - * state while create_worker() is in progress. + * assoc_mutex to avoid changing binding state while + * create_worker() is in progress. */ - GCWQ_DISASSOCIATED = 1 << 0, /* cpu can't serve workers */ - GCWQ_FREEZING = 1 << 1, /* freeze in progress */ - - /* pool flags */ POOL_MANAGE_WORKERS = 1 << 0, /* need to manage workers */ POOL_MANAGING_WORKERS = 1 << 1, /* managing workers */ + POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ + POOL_FREEZING = 1 << 3, /* freeze in progress */ /* worker flags */ WORKER_STARTED = 1 << 0, /* started */ @@ -79,11 +78,9 @@ enum { WORKER_NOT_RUNNING = WORKER_PREP | WORKER_UNBOUND | WORKER_CPU_INTENSIVE, - NR_WORKER_POOLS = 2, /* # worker pools per gcwq */ + NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ - BUSY_WORKER_HASH_SIZE = 1 << BUSY_WORKER_HASH_ORDER, - BUSY_WORKER_HASH_MASK = BUSY_WORKER_HASH_SIZE - 1, MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ @@ -111,48 +108,24 @@ enum { * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * - * L: gcwq->lock protected. Access with gcwq->lock held. + * L: pool->lock protected. Access with pool->lock held. * - * X: During normal operation, modification requires gcwq->lock and - * should be done only from local cpu. Either disabling preemption - * on local cpu or grabbing gcwq->lock is enough for read access. - * If GCWQ_DISASSOCIATED is set, it's identical to L. + * X: During normal operation, modification requires pool->lock and should + * be done only from local cpu. Either disabling preemption on local + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. * * F: wq->flush_mutex protected. * * W: workqueue_lock protected. */ -struct global_cwq; -struct worker_pool; - -/* - * The poor guys doing the actual heavy lifting. All on-duty workers - * are either serving the manager role, on idle list or on busy hash. - */ -struct worker { - /* on idle list while idle, on busy hash table while busy */ - union { - struct list_head entry; /* L: while idle */ - struct hlist_node hentry; /* L: while busy */ - }; - - struct work_struct *current_work; /* L: work being processed */ - struct cpu_workqueue_struct *current_cwq; /* L: current_work's cwq */ - struct list_head scheduled; /* L: scheduled works */ - struct task_struct *task; /* I: worker task */ - struct worker_pool *pool; /* I: the associated pool */ - /* 64 bytes boundary on 64bit, 32 on 32bit */ - unsigned long last_active; /* L: last active timestamp */ - unsigned int flags; /* X: flags */ - int id; /* I: worker id */ - - /* for rebinding worker to CPU */ - struct work_struct rebind_work; /* L: for busy worker */ -}; +/* struct worker is defined in workqueue_internal.h */ struct worker_pool { - struct global_cwq *gcwq; /* I: the owning gcwq */ + spinlock_t lock; /* the pool lock */ + unsigned int cpu; /* I: the associated cpu */ + int id; /* I: pool ID */ unsigned int flags; /* X: flags */ struct list_head worklist; /* L: list of pending works */ @@ -165,34 +138,28 @@ struct worker_pool { struct timer_list idle_timer; /* L: worker idle timeout */ struct timer_list mayday_timer; /* L: SOS timer for workers */ - struct mutex assoc_mutex; /* protect GCWQ_DISASSOCIATED */ - struct ida worker_ida; /* L: for worker IDs */ -}; - -/* - * Global per-cpu workqueue. There's one and only one for each cpu - * and all works are queued and processed here regardless of their - * target workqueues. - */ -struct global_cwq { - spinlock_t lock; /* the gcwq lock */ - unsigned int cpu; /* I: the associated cpu */ - unsigned int flags; /* L: GCWQ_* flags */ - - /* workers are chained either in busy_hash or pool idle_list */ - struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE]; + /* workers are chained either in busy_hash or idle_list */ + DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ - struct worker_pool pools[NR_WORKER_POOLS]; - /* normal and highpri pools */ + struct mutex assoc_mutex; /* protect POOL_DISASSOCIATED */ + struct ida worker_ida; /* L: for worker IDs */ + + /* + * The current concurrency level. As it's likely to be accessed + * from other CPUs during try_to_wake_up(), put it in a separate + * cacheline. + */ + atomic_t nr_running ____cacheline_aligned_in_smp; } ____cacheline_aligned_in_smp; /* - * The per-CPU workqueue. The lower WORK_STRUCT_FLAG_BITS of - * work_struct->data are used for flags and thus cwqs need to be - * aligned at two's power of the number of flag bits. + * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS + * of work_struct->data are used for flags and the remaining high bits + * point to the pwq; thus, pwqs need to be aligned at two's power of the + * number of flag bits. */ -struct cpu_workqueue_struct { +struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ @@ -241,16 +208,16 @@ typedef unsigned long mayday_mask_t; struct workqueue_struct { unsigned int flags; /* W: WQ_* flags */ union { - struct cpu_workqueue_struct __percpu *pcpu; - struct cpu_workqueue_struct *single; + struct pool_workqueue __percpu *pcpu; + struct pool_workqueue *single; unsigned long v; - } cpu_wq; /* I: cwq's */ + } pool_wq; /* I: pwq's */ struct list_head list; /* W: list of all workqueues */ struct mutex flush_mutex; /* protects wq flushing */ int work_color; /* F: current work color */ int flush_color; /* F: current flush color */ - atomic_t nr_cwqs_to_flush; /* flush in progress */ + atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* F: first flusher */ struct list_head flusher_queue; /* F: flush waiters */ struct list_head flusher_overflow; /* F: flush overflow list */ @@ -259,7 +226,7 @@ struct workqueue_struct { struct worker *rescuer; /* I: rescue worker */ int nr_drainers; /* W: drain in progress */ - int saved_max_active; /* W: saved cwq max_active */ + int saved_max_active; /* W: saved pwq max_active */ #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -280,16 +247,15 @@ EXPORT_SYMBOL_GPL(system_freezable_wq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> -#define for_each_worker_pool(pool, gcwq) \ - for ((pool) = &(gcwq)->pools[0]; \ - (pool) < &(gcwq)->pools[NR_WORKER_POOLS]; (pool)++) +#define for_each_std_worker_pool(pool, cpu) \ + for ((pool) = &std_worker_pools(cpu)[0]; \ + (pool) < &std_worker_pools(cpu)[NR_STD_WORKER_POOLS]; (pool)++) -#define for_each_busy_worker(worker, i, pos, gcwq) \ - for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \ - hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry) +#define for_each_busy_worker(worker, i, pos, pool) \ + hash_for_each(pool->busy_hash, i, pos, worker, hentry) -static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask, - unsigned int sw) +static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, + unsigned int sw) { if (cpu < nr_cpu_ids) { if (sw & 1) { @@ -300,42 +266,42 @@ static inline int __next_gcwq_cpu(int cpu, const struct cpumask *mask, if (sw & 2) return WORK_CPU_UNBOUND; } - return WORK_CPU_NONE; + return WORK_CPU_END; } -static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, - struct workqueue_struct *wq) +static inline int __next_pwq_cpu(int cpu, const struct cpumask *mask, + struct workqueue_struct *wq) { - return __next_gcwq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2); + return __next_wq_cpu(cpu, mask, !(wq->flags & WQ_UNBOUND) ? 1 : 2); } /* * CPU iterators * - * An extra gcwq is defined for an invalid cpu number + * An extra cpu number is defined using an invalid cpu number * (WORK_CPU_UNBOUND) to host workqueues which are not bound to any - * specific CPU. The following iterators are similar to - * for_each_*_cpu() iterators but also considers the unbound gcwq. + * specific CPU. The following iterators are similar to for_each_*_cpu() + * iterators but also considers the unbound CPU. * - * for_each_gcwq_cpu() : possible CPUs + WORK_CPU_UNBOUND - * for_each_online_gcwq_cpu() : online CPUs + WORK_CPU_UNBOUND - * for_each_cwq_cpu() : possible CPUs for bound workqueues, + * for_each_wq_cpu() : possible CPUs + WORK_CPU_UNBOUND + * for_each_online_wq_cpu() : online CPUs + WORK_CPU_UNBOUND + * for_each_pwq_cpu() : possible CPUs for bound workqueues, * WORK_CPU_UNBOUND for unbound workqueues */ -#define for_each_gcwq_cpu(cpu) \ - for ((cpu) = __next_gcwq_cpu(-1, cpu_possible_mask, 3); \ - (cpu) < WORK_CPU_NONE; \ - (cpu) = __next_gcwq_cpu((cpu), cpu_possible_mask, 3)) +#define for_each_wq_cpu(cpu) \ + for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, 3); \ + (cpu) < WORK_CPU_END; \ + (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, 3)) -#define for_each_online_gcwq_cpu(cpu) \ - for ((cpu) = __next_gcwq_cpu(-1, cpu_online_mask, 3); \ - (cpu) < WORK_CPU_NONE; \ - (cpu) = __next_gcwq_cpu((cpu), cpu_online_mask, 3)) +#define for_each_online_wq_cpu(cpu) \ + for ((cpu) = __next_wq_cpu(-1, cpu_online_mask, 3); \ + (cpu) < WORK_CPU_END; \ + (cpu) = __next_wq_cpu((cpu), cpu_online_mask, 3)) -#define for_each_cwq_cpu(cpu, wq) \ - for ((cpu) = __next_wq_cpu(-1, cpu_possible_mask, (wq)); \ - (cpu) < WORK_CPU_NONE; \ - (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq))) +#define for_each_pwq_cpu(cpu, wq) \ + for ((cpu) = __next_pwq_cpu(-1, cpu_possible_mask, (wq)); \ + (cpu) < WORK_CPU_END; \ + (cpu) = __next_pwq_cpu((cpu), cpu_possible_mask, (wq))) #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -459,57 +425,69 @@ static LIST_HEAD(workqueues); static bool workqueue_freezing; /* W: have wqs started freezing? */ /* - * The almighty global cpu workqueues. nr_running is the only field - * which is expected to be used frequently by other cpus via - * try_to_wake_up(). Put it in a separate cacheline. + * The CPU and unbound standard worker pools. The unbound ones have + * POOL_DISASSOCIATED set, and their workers have WORKER_UNBOUND set. */ -static DEFINE_PER_CPU(struct global_cwq, global_cwq); -static DEFINE_PER_CPU_SHARED_ALIGNED(atomic_t, pool_nr_running[NR_WORKER_POOLS]); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + cpu_std_worker_pools); +static struct worker_pool unbound_std_worker_pools[NR_STD_WORKER_POOLS]; -/* - * Global cpu workqueue and nr_running counter for unbound gcwq. The - * gcwq is always online, has GCWQ_DISASSOCIATED set, and all its - * workers have WORKER_UNBOUND set. - */ -static struct global_cwq unbound_global_cwq; -static atomic_t unbound_pool_nr_running[NR_WORKER_POOLS] = { - [0 ... NR_WORKER_POOLS - 1] = ATOMIC_INIT(0), /* always 0 */ -}; +/* idr of all pools */ +static DEFINE_MUTEX(worker_pool_idr_mutex); +static DEFINE_IDR(worker_pool_idr); static int worker_thread(void *__worker); -static int worker_pool_pri(struct worker_pool *pool) +static struct worker_pool *std_worker_pools(int cpu) { - return pool - pool->gcwq->pools; + if (cpu != WORK_CPU_UNBOUND) + return per_cpu(cpu_std_worker_pools, cpu); + else + return unbound_std_worker_pools; } -static struct global_cwq *get_gcwq(unsigned int cpu) +static int std_worker_pool_pri(struct worker_pool *pool) { - if (cpu != WORK_CPU_UNBOUND) - return &per_cpu(global_cwq, cpu); - else - return &unbound_global_cwq; + return pool - std_worker_pools(pool->cpu); } -static atomic_t *get_pool_nr_running(struct worker_pool *pool) +/* allocate ID and assign it to @pool */ +static int worker_pool_assign_id(struct worker_pool *pool) { - int cpu = pool->gcwq->cpu; - int idx = worker_pool_pri(pool); + int ret; - if (cpu != WORK_CPU_UNBOUND) - return &per_cpu(pool_nr_running, cpu)[idx]; - else - return &unbound_pool_nr_running[idx]; + mutex_lock(&worker_pool_idr_mutex); + idr_pre_get(&worker_pool_idr, GFP_KERNEL); + ret = idr_get_new(&worker_pool_idr, pool, &pool->id); + mutex_unlock(&worker_pool_idr_mutex); + + return ret; } -static struct cpu_workqueue_struct *get_cwq(unsigned int cpu, - struct workqueue_struct *wq) +/* + * Lookup worker_pool by id. The idr currently is built during boot and + * never modified. Don't worry about locking for now. + */ +static struct worker_pool *worker_pool_by_id(int pool_id) +{ + return idr_find(&worker_pool_idr, pool_id); +} + +static struct worker_pool *get_std_worker_pool(int cpu, bool highpri) +{ + struct worker_pool *pools = std_worker_pools(cpu); + + return &pools[highpri]; +} + +static struct pool_workqueue *get_pwq(unsigned int cpu, + struct workqueue_struct *wq) { if (!(wq->flags & WQ_UNBOUND)) { if (likely(cpu < nr_cpu_ids)) - return per_cpu_ptr(wq->cpu_wq.pcpu, cpu); + return per_cpu_ptr(wq->pool_wq.pcpu, cpu); } else if (likely(cpu == WORK_CPU_UNBOUND)) - return wq->cpu_wq.single; + return wq->pool_wq.single; return NULL; } @@ -530,19 +508,19 @@ static int work_next_color(int color) } /* - * While queued, %WORK_STRUCT_CWQ is set and non flag bits of a work's data - * contain the pointer to the queued cwq. Once execution starts, the flag - * is cleared and the high bits contain OFFQ flags and CPU number. + * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data + * contain the pointer to the queued pwq. Once execution starts, the flag + * is cleared and the high bits contain OFFQ flags and pool ID. * - * set_work_cwq(), set_work_cpu_and_clear_pending(), mark_work_canceling() - * and clear_work_data() can be used to set the cwq, cpu or clear + * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() + * and clear_work_data() can be used to set the pwq, pool or clear * work->data. These functions should only be called while the work is * owned - ie. while the PENDING bit is set. * - * get_work_[g]cwq() can be used to obtain the gcwq or cwq corresponding to - * a work. gcwq is available once the work has been queued anywhere after - * initialization until it is sync canceled. cwq is available only while - * the work item is queued. + * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq + * corresponding to a work. Pool is available once the work has been + * queued anywhere after initialization until it is sync canceled. pwq is + * available only while the work item is queued. * * %WORK_OFFQ_CANCELING is used to mark a work item which is being * canceled. While being canceled, a work item may have its PENDING set @@ -556,16 +534,22 @@ static inline void set_work_data(struct work_struct *work, unsigned long data, atomic_long_set(&work->data, data | flags | work_static(work)); } -static void set_work_cwq(struct work_struct *work, - struct cpu_workqueue_struct *cwq, +static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long extra_flags) { - set_work_data(work, (unsigned long)cwq, - WORK_STRUCT_PENDING | WORK_STRUCT_CWQ | extra_flags); + set_work_data(work, (unsigned long)pwq, + WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); } -static void set_work_cpu_and_clear_pending(struct work_struct *work, - unsigned int cpu) +static void set_work_pool_and_keep_pending(struct work_struct *work, + int pool_id) +{ + set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, + WORK_STRUCT_PENDING); +} + +static void set_work_pool_and_clear_pending(struct work_struct *work, + int pool_id) { /* * The following wmb is paired with the implied mb in @@ -574,67 +558,92 @@ static void set_work_cpu_and_clear_pending(struct work_struct *work, * owner. */ smp_wmb(); - set_work_data(work, (unsigned long)cpu << WORK_OFFQ_CPU_SHIFT, 0); + set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); } static void clear_work_data(struct work_struct *work) { - smp_wmb(); /* see set_work_cpu_and_clear_pending() */ - set_work_data(work, WORK_STRUCT_NO_CPU, 0); + smp_wmb(); /* see set_work_pool_and_clear_pending() */ + set_work_data(work, WORK_STRUCT_NO_POOL, 0); } -static struct cpu_workqueue_struct *get_work_cwq(struct work_struct *work) +static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); - if (data & WORK_STRUCT_CWQ) + if (data & WORK_STRUCT_PWQ) return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); else return NULL; } -static struct global_cwq *get_work_gcwq(struct work_struct *work) +/** + * get_work_pool - return the worker_pool a given work was associated with + * @work: the work item of interest + * + * Return the worker_pool @work was last associated with. %NULL if none. + */ +static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); - unsigned int cpu; + struct worker_pool *pool; + int pool_id; - if (data & WORK_STRUCT_CWQ) - return ((struct cpu_workqueue_struct *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool->gcwq; + if (data & WORK_STRUCT_PWQ) + return ((struct pool_workqueue *) + (data & WORK_STRUCT_WQ_DATA_MASK))->pool; - cpu = data >> WORK_OFFQ_CPU_SHIFT; - if (cpu == WORK_CPU_NONE) + pool_id = data >> WORK_OFFQ_POOL_SHIFT; + if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; - BUG_ON(cpu >= nr_cpu_ids && cpu != WORK_CPU_UNBOUND); - return get_gcwq(cpu); + pool = worker_pool_by_id(pool_id); + WARN_ON_ONCE(!pool); + return pool; +} + +/** + * get_work_pool_id - return the worker pool ID a given work is associated with + * @work: the work item of interest + * + * Return the worker_pool ID @work was last associated with. + * %WORK_OFFQ_POOL_NONE if none. + */ +static int get_work_pool_id(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + + if (data & WORK_STRUCT_PWQ) + return ((struct pool_workqueue *) + (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + + return data >> WORK_OFFQ_POOL_SHIFT; } static void mark_work_canceling(struct work_struct *work) { - struct global_cwq *gcwq = get_work_gcwq(work); - unsigned long cpu = gcwq ? gcwq->cpu : WORK_CPU_NONE; + unsigned long pool_id = get_work_pool_id(work); - set_work_data(work, (cpu << WORK_OFFQ_CPU_SHIFT) | WORK_OFFQ_CANCELING, - WORK_STRUCT_PENDING); + pool_id <<= WORK_OFFQ_POOL_SHIFT; + set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); } static bool work_is_canceling(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); - return !(data & WORK_STRUCT_CWQ) && (data & WORK_OFFQ_CANCELING); + return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that - * they're being called with gcwq->lock held. + * they're being called with pool->lock held. */ static bool __need_more_worker(struct worker_pool *pool) { - return !atomic_read(get_pool_nr_running(pool)); + return !atomic_read(&pool->nr_running); } /* @@ -642,7 +651,7 @@ static bool __need_more_worker(struct worker_pool *pool) * running workers. * * Note that, because unbound workers never contribute to nr_running, this - * function will always return %true for unbound gcwq as long as the + * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) @@ -659,9 +668,8 @@ static bool may_start_working(struct worker_pool *pool) /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { - atomic_t *nr_running = get_pool_nr_running(pool); - - return !list_empty(&pool->worklist) && atomic_read(nr_running) <= 1; + return !list_empty(&pool->worklist) && + atomic_read(&pool->nr_running) <= 1; } /* Do we need a new worker? Called from manager. */ @@ -714,7 +722,7 @@ static struct worker *first_worker(struct worker_pool *pool) * Wake up the first idle worker of @pool. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void wake_up_worker(struct worker_pool *pool) { @@ -740,8 +748,8 @@ void wq_worker_waking_up(struct task_struct *task, unsigned int cpu) struct worker *worker = kthread_data(task); if (!(worker->flags & WORKER_NOT_RUNNING)) { - WARN_ON_ONCE(worker->pool->gcwq->cpu != cpu); - atomic_inc(get_pool_nr_running(worker->pool)); + WARN_ON_ONCE(worker->pool->cpu != cpu); + atomic_inc(&worker->pool->nr_running); } } @@ -764,12 +772,18 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, unsigned int cpu) { struct worker *worker = kthread_data(task), *to_wakeup = NULL; - struct worker_pool *pool = worker->pool; - atomic_t *nr_running = get_pool_nr_running(pool); + struct worker_pool *pool; + /* + * Rescuers, which may not have all the fields set up like normal + * workers, also reach here, let's not access anything before + * checking NOT_RUNNING. + */ if (worker->flags & WORKER_NOT_RUNNING) return NULL; + pool = worker->pool; + /* this can only happen on the local cpu */ BUG_ON(cpu != raw_smp_processor_id()); @@ -781,10 +795,11 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, * NOT_RUNNING is clear. This means that we're bound to and * running on the local cpu w/ rq lock held and preemption * disabled, which in turn means that none else could be - * manipulating idle_list, so dereferencing idle_list without gcwq + * manipulating idle_list, so dereferencing idle_list without pool * lock is safe. */ - if (atomic_dec_and_test(nr_running) && !list_empty(&pool->worklist)) + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) to_wakeup = first_worker(pool); return to_wakeup ? to_wakeup->task : NULL; } @@ -800,7 +815,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, * woken up. * * CONTEXT: - * spin_lock_irq(gcwq->lock) + * spin_lock_irq(pool->lock) */ static inline void worker_set_flags(struct worker *worker, unsigned int flags, bool wakeup) @@ -816,14 +831,12 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags, */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { - atomic_t *nr_running = get_pool_nr_running(pool); - if (wakeup) { - if (atomic_dec_and_test(nr_running) && + if (atomic_dec_and_test(&pool->nr_running) && !list_empty(&pool->worklist)) wake_up_worker(pool); } else - atomic_dec(nr_running); + atomic_dec(&pool->nr_running); } worker->flags |= flags; @@ -837,7 +850,7 @@ static inline void worker_set_flags(struct worker *worker, unsigned int flags, * Clear @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: - * spin_lock_irq(gcwq->lock) + * spin_lock_irq(pool->lock) */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { @@ -855,87 +868,56 @@ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(get_pool_nr_running(pool)); + atomic_inc(&pool->nr_running); } /** - * busy_worker_head - return the busy hash head for a work - * @gcwq: gcwq of interest - * @work: work to be hashed - * - * Return hash head of @gcwq for @work. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - * - * RETURNS: - * Pointer to the hash head. - */ -static struct hlist_head *busy_worker_head(struct global_cwq *gcwq, - struct work_struct *work) -{ - const int base_shift = ilog2(sizeof(struct work_struct)); - unsigned long v = (unsigned long)work; - - /* simple shift and fold hash, do we need something better? */ - v >>= base_shift; - v += v >> BUSY_WORKER_HASH_ORDER; - v &= BUSY_WORKER_HASH_MASK; - - return &gcwq->busy_hash[v]; -} - -/** - * __find_worker_executing_work - find worker which is executing a work - * @gcwq: gcwq of interest - * @bwh: hash head as returned by busy_worker_head() + * find_worker_executing_work - find worker which is executing a work + * @pool: pool of interest * @work: work to find worker for * - * Find a worker which is executing @work on @gcwq. @bwh should be - * the hash head obtained by calling busy_worker_head() with the same - * work. + * Find a worker which is executing @work on @pool by searching + * @pool->busy_hash which is keyed by the address of @work. For a worker + * to match, its current execution should match the address of @work and + * its work function. This is to avoid unwanted dependency between + * unrelated work executions through a work item being recycled while still + * being executed. + * + * This is a bit tricky. A work item may be freed once its execution + * starts and nothing prevents the freed area from being recycled for + * another work item. If the same work item address ends up being reused + * before the original execution finishes, workqueue will identify the + * recycled work item as currently executing and make it wait until the + * current execution finishes, introducing an unwanted dependency. + * + * This function checks the work item address, work function and workqueue + * to avoid false positives. Note that this isn't complete as one may + * construct a work function which can introduce dependency onto itself + * through a recycled work item. Well, if somebody wants to shoot oneself + * in the foot that badly, there's only so much we can do, and if such + * deadlock actually occurs, it should be easy to locate the culprit work + * function. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). * * RETURNS: * Pointer to worker which is executing @work if found, NULL * otherwise. */ -static struct worker *__find_worker_executing_work(struct global_cwq *gcwq, - struct hlist_head *bwh, - struct work_struct *work) +static struct worker *find_worker_executing_work(struct worker_pool *pool, + struct work_struct *work) { struct worker *worker; struct hlist_node *tmp; - hlist_for_each_entry(worker, tmp, bwh, hentry) - if (worker->current_work == work) + hash_for_each_possible(pool->busy_hash, worker, tmp, hentry, + (unsigned long)work) + if (worker->current_work == work && + worker->current_func == work->func) return worker; - return NULL; -} -/** - * find_worker_executing_work - find worker which is executing a work - * @gcwq: gcwq of interest - * @work: work to find worker for - * - * Find a worker which is executing @work on @gcwq. This function is - * identical to __find_worker_executing_work() except that this - * function calculates @bwh itself. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - * - * RETURNS: - * Pointer to worker which is executing @work if found, NULL - * otherwise. - */ -static struct worker *find_worker_executing_work(struct global_cwq *gcwq, - struct work_struct *work) -{ - return __find_worker_executing_work(gcwq, busy_worker_head(gcwq, work), - work); + return NULL; } /** @@ -953,7 +935,7 @@ static struct worker *find_worker_executing_work(struct global_cwq *gcwq, * nested inside outer list_for_each_entry_safe(). * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) @@ -979,67 +961,67 @@ static void move_linked_works(struct work_struct *work, struct list_head *head, *nextp = n; } -static void cwq_activate_delayed_work(struct work_struct *work) +static void pwq_activate_delayed_work(struct work_struct *work) { - struct cpu_workqueue_struct *cwq = get_work_cwq(work); + struct pool_workqueue *pwq = get_work_pwq(work); trace_workqueue_activate_work(work); - move_linked_works(work, &cwq->pool->worklist, NULL); + move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); - cwq->nr_active++; + pwq->nr_active++; } -static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) +static void pwq_activate_first_delayed(struct pool_workqueue *pwq) { - struct work_struct *work = list_first_entry(&cwq->delayed_works, + struct work_struct *work = list_first_entry(&pwq->delayed_works, struct work_struct, entry); - cwq_activate_delayed_work(work); + pwq_activate_delayed_work(work); } /** - * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight - * @cwq: cwq of interest + * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight + * @pwq: pwq of interest * @color: color of work which left the queue * * A work either has completed or is removed from pending queue, - * decrement nr_in_flight of its cwq and handle workqueue flushing. + * decrement nr_in_flight of its pwq and handle workqueue flushing. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, int color) { /* ignore uncolored works */ if (color == WORK_NO_COLOR) return; - cwq->nr_in_flight[color]--; + pwq->nr_in_flight[color]--; - cwq->nr_active--; - if (!list_empty(&cwq->delayed_works)) { + pwq->nr_active--; + if (!list_empty(&pwq->delayed_works)) { /* one down, submit a delayed one */ - if (cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + if (pwq->nr_active < pwq->max_active) + pwq_activate_first_delayed(pwq); } /* is flush in progress and are we at the flushing tip? */ - if (likely(cwq->flush_color != color)) + if (likely(pwq->flush_color != color)) return; /* are there still in-flight works? */ - if (cwq->nr_in_flight[color]) + if (pwq->nr_in_flight[color]) return; - /* this cwq is done, clear flush_color */ - cwq->flush_color = -1; + /* this pwq is done, clear flush_color */ + pwq->flush_color = -1; /* - * If this was the last cwq, wake up the first flusher. It + * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ - if (atomic_dec_and_test(&cwq->wq->nr_cwqs_to_flush)) - complete(&cwq->wq->first_flusher->done); + if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) + complete(&pwq->wq->first_flusher->done); } /** @@ -1070,7 +1052,8 @@ static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) static int try_to_grab_pending(struct work_struct *work, bool is_dwork, unsigned long *flags) { - struct global_cwq *gcwq; + struct worker_pool *pool; + struct pool_workqueue *pwq; local_irq_save(*flags); @@ -1095,41 +1078,43 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ - gcwq = get_work_gcwq(work); - if (!gcwq) + pool = get_work_pool(work); + if (!pool) goto fail; - spin_lock(&gcwq->lock); - if (!list_empty(&work->entry)) { + spin_lock(&pool->lock); + /* + * work->data is guaranteed to point to pwq only while the work + * item is queued on pwq->wq, and both updating work->data to point + * to pwq on queueing and to pool on dequeueing are done under + * pwq->pool->lock. This in turn guarantees that, if work->data + * points to pwq which is associated with a locked pool, the work + * item is currently queued on that pool. + */ + pwq = get_work_pwq(work); + if (pwq && pwq->pool == pool) { + debug_work_deactivate(work); + /* - * This work is queued, but perhaps we locked the wrong gcwq. - * In that case we must see the new value after rmb(), see - * insert_work()->wmb(). + * A delayed work item cannot be grabbed directly because + * it might have linked NO_COLOR work items which, if left + * on the delayed_list, will confuse pwq->nr_active + * management later on and cause stall. Make sure the work + * item is activated before grabbing. */ - smp_rmb(); - if (gcwq == get_work_gcwq(work)) { - debug_work_deactivate(work); + if (*work_data_bits(work) & WORK_STRUCT_DELAYED) + pwq_activate_delayed_work(work); - /* - * A delayed work item cannot be grabbed directly - * because it might have linked NO_COLOR work items - * which, if left on the delayed_list, will confuse - * cwq->nr_active management later on and cause - * stall. Make sure the work item is activated - * before grabbing. - */ - if (*work_data_bits(work) & WORK_STRUCT_DELAYED) - cwq_activate_delayed_work(work); + list_del_init(&work->entry); + pwq_dec_nr_in_flight(get_work_pwq(work), get_work_color(work)); - list_del_init(&work->entry); - cwq_dec_nr_in_flight(get_work_cwq(work), - get_work_color(work)); + /* work->data points to pwq iff queued, point to pool */ + set_work_pool_and_keep_pending(work, pool->id); - spin_unlock(&gcwq->lock); - return 1; - } + spin_unlock(&pool->lock); + return 1; } - spin_unlock(&gcwq->lock); + spin_unlock(&pool->lock); fail: local_irq_restore(*flags); if (work_is_canceling(work)) @@ -1139,33 +1124,25 @@ fail: } /** - * insert_work - insert a work into gcwq - * @cwq: cwq @work belongs to + * insert_work - insert a work into a pool + * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * - * Insert @work which belongs to @cwq into @gcwq after @head. - * @extra_flags is or'd to work_struct flags. + * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to + * work_struct flags. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void insert_work(struct cpu_workqueue_struct *cwq, - struct work_struct *work, struct list_head *head, - unsigned int extra_flags) +static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, + struct list_head *head, unsigned int extra_flags) { - struct worker_pool *pool = cwq->pool; + struct worker_pool *pool = pwq->pool; /* we own @work, set data and link */ - set_work_cwq(work, cwq, extra_flags); - - /* - * Ensure that we get the right work->data if we see the - * result of list_add() below, see try_to_grab_pending(). - */ - smp_wmb(); - + set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); /* @@ -1181,41 +1158,24 @@ static void insert_work(struct cpu_workqueue_struct *cwq, /* * Test whether @work is being queued from another work executing on the - * same workqueue. This is rather expensive and should only be used from - * cold paths. + * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { - unsigned long flags; - unsigned int cpu; - - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); - struct worker *worker; - struct hlist_node *pos; - int i; + struct worker *worker; - spin_lock_irqsave(&gcwq->lock, flags); - for_each_busy_worker(worker, i, pos, gcwq) { - if (worker->task != current) - continue; - spin_unlock_irqrestore(&gcwq->lock, flags); - /* - * I'm @worker, no locking necessary. See if @work - * is headed to the same workqueue. - */ - return worker->current_cwq->wq == wq; - } - spin_unlock_irqrestore(&gcwq->lock, flags); - } - return false; + worker = current_wq_worker(); + /* + * Return %true iff I'm a worker execuing a work item on @wq. If + * I'm @worker, it's safe to dereference it without locking. + */ + return worker && worker->current_pwq->wq == wq; } static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct work_struct *work) { - struct global_cwq *gcwq; - struct cpu_workqueue_struct *cwq; + struct pool_workqueue *pwq; struct list_head *worklist; unsigned int work_flags; unsigned int req_cpu = cpu; @@ -1235,9 +1195,9 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, WARN_ON_ONCE(!is_chained_work(wq))) return; - /* determine gcwq to use */ + /* determine the pwq to use */ if (!(wq->flags & WQ_UNBOUND)) { - struct global_cwq *last_gcwq; + struct worker_pool *last_pool; if (cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); @@ -1248,55 +1208,54 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, * work needs to be queued on that cpu to guarantee * non-reentrancy. */ - gcwq = get_gcwq(cpu); - last_gcwq = get_work_gcwq(work); + pwq = get_pwq(cpu, wq); + last_pool = get_work_pool(work); - if (last_gcwq && last_gcwq != gcwq) { + if (last_pool && last_pool != pwq->pool) { struct worker *worker; - spin_lock(&last_gcwq->lock); + spin_lock(&last_pool->lock); - worker = find_worker_executing_work(last_gcwq, work); + worker = find_worker_executing_work(last_pool, work); - if (worker && worker->current_cwq->wq == wq) - gcwq = last_gcwq; - else { + if (worker && worker->current_pwq->wq == wq) { + pwq = get_pwq(last_pool->cpu, wq); + } else { /* meh... not running there, queue here */ - spin_unlock(&last_gcwq->lock); - spin_lock(&gcwq->lock); + spin_unlock(&last_pool->lock); + spin_lock(&pwq->pool->lock); } } else { - spin_lock(&gcwq->lock); + spin_lock(&pwq->pool->lock); } } else { - gcwq = get_gcwq(WORK_CPU_UNBOUND); - spin_lock(&gcwq->lock); + pwq = get_pwq(WORK_CPU_UNBOUND, wq); + spin_lock(&pwq->pool->lock); } - /* gcwq determined, get cwq and queue */ - cwq = get_cwq(gcwq->cpu, wq); - trace_workqueue_queue_work(req_cpu, cwq, work); + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) { - spin_unlock(&gcwq->lock); + spin_unlock(&pwq->pool->lock); return; } - cwq->nr_in_flight[cwq->work_color]++; - work_flags = work_color_to_flags(cwq->work_color); + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); - if (likely(cwq->nr_active < cwq->max_active)) { + if (likely(pwq->nr_active < pwq->max_active)) { trace_workqueue_activate_work(work); - cwq->nr_active++; - worklist = &cwq->pool->worklist; + pwq->nr_active++; + worklist = &pwq->pool->worklist; } else { work_flags |= WORK_STRUCT_DELAYED; - worklist = &cwq->delayed_works; + worklist = &pwq->delayed_works; } - insert_work(cwq, work, worklist, work_flags); + insert_work(pwq, work, worklist, work_flags); - spin_unlock(&gcwq->lock); + spin_unlock(&pwq->pool->lock); } /** @@ -1347,19 +1306,17 @@ EXPORT_SYMBOL_GPL(queue_work); void delayed_work_timer_fn(unsigned long __data) { struct delayed_work *dwork = (struct delayed_work *)__data; - struct cpu_workqueue_struct *cwq = get_work_cwq(&dwork->work); /* should have been called from irqsafe timer with irq already off */ - __queue_work(dwork->cpu, cwq->wq, &dwork->work); + __queue_work(dwork->cpu, dwork->wq, &dwork->work); } -EXPORT_SYMBOL_GPL(delayed_work_timer_fn); +EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; - unsigned int lcpu; WARN_ON_ONCE(timer->function != delayed_work_timer_fn || timer->data != (unsigned long)dwork); @@ -1379,30 +1336,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); - /* - * This stores cwq for the moment, for the timer_fn. Note that the - * work's gcwq is preserved to allow reentrance detection for - * delayed works. - */ - if (!(wq->flags & WQ_UNBOUND)) { - struct global_cwq *gcwq = get_work_gcwq(work); - - /* - * If we cannot get the last gcwq from @work directly, - * select the last CPU such that it avoids unnecessarily - * triggering non-reentrancy check in __queue_work(). - */ - lcpu = cpu; - if (gcwq) - lcpu = gcwq->cpu; - if (lcpu == WORK_CPU_UNBOUND) - lcpu = raw_smp_processor_id(); - } else { - lcpu = WORK_CPU_UNBOUND; - } - - set_work_cwq(work, get_cwq(lcpu, wq), 0); - + dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; @@ -1519,12 +1453,11 @@ EXPORT_SYMBOL_GPL(mod_delayed_work); * necessary. * * LOCKING: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; BUG_ON(worker->flags & WORKER_IDLE); BUG_ON(!list_empty(&worker->entry) && @@ -1542,14 +1475,14 @@ static void worker_enter_idle(struct worker *worker) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* - * Sanity check nr_running. Because gcwq_unbind_fn() releases - * gcwq->lock between setting %WORKER_UNBOUND and zapping + * Sanity check nr_running. Because wq_unbind_fn() releases + * pool->lock between setting %WORKER_UNBOUND and zapping * nr_running, the warning may trigger spuriously. Check iff * unbind is not in progress. */ - WARN_ON_ONCE(!(gcwq->flags & GCWQ_DISASSOCIATED) && + WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && pool->nr_workers == pool->nr_idle && - atomic_read(get_pool_nr_running(pool))); + atomic_read(&pool->nr_running)); } /** @@ -1559,7 +1492,7 @@ static void worker_enter_idle(struct worker *worker) * @worker is leaving idle state. Update stats. * * LOCKING: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { @@ -1572,7 +1505,7 @@ static void worker_leave_idle(struct worker *worker) } /** - * worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock gcwq + * worker_maybe_bind_and_lock - bind worker to its cpu if possible and lock pool * @worker: self * * Works which are scheduled while the cpu is online must at least be @@ -1584,27 +1517,27 @@ static void worker_leave_idle(struct worker *worker) * themselves to the target cpu and may race with cpu going down or * coming online. kthread_bind() can't be used because it may put the * worker to already dead cpu and set_cpus_allowed_ptr() can't be used - * verbatim as it's best effort and blocking and gcwq may be + * verbatim as it's best effort and blocking and pool may be * [dis]associated in the meantime. * - * This function tries set_cpus_allowed() and locks gcwq and verifies the - * binding against %GCWQ_DISASSOCIATED which is set during + * This function tries set_cpus_allowed() and locks pool and verifies the + * binding against %POOL_DISASSOCIATED which is set during * %CPU_DOWN_PREPARE and cleared during %CPU_ONLINE, so if the worker * enters idle state or fetches works without dropping lock, it can * guarantee the scheduling requirement described in the first paragraph. * * CONTEXT: - * Might sleep. Called without any lock but returns with gcwq->lock + * Might sleep. Called without any lock but returns with pool->lock * held. * * RETURNS: - * %true if the associated gcwq is online (@worker is successfully + * %true if the associated pool is online (@worker is successfully * bound), %false if offline. */ static bool worker_maybe_bind_and_lock(struct worker *worker) -__acquires(&gcwq->lock) +__acquires(&pool->lock) { - struct global_cwq *gcwq = worker->pool->gcwq; + struct worker_pool *pool = worker->pool; struct task_struct *task = worker->task; while (true) { @@ -1612,19 +1545,19 @@ __acquires(&gcwq->lock) * The following call may fail, succeed or succeed * without actually migrating the task to the cpu if * it races with cpu hotunplug operation. Verify - * against GCWQ_DISASSOCIATED. + * against POOL_DISASSOCIATED. */ - if (!(gcwq->flags & GCWQ_DISASSOCIATED)) - set_cpus_allowed_ptr(task, get_cpu_mask(gcwq->cpu)); + if (!(pool->flags & POOL_DISASSOCIATED)) + set_cpus_allowed_ptr(task, get_cpu_mask(pool->cpu)); - spin_lock_irq(&gcwq->lock); - if (gcwq->flags & GCWQ_DISASSOCIATED) + spin_lock_irq(&pool->lock); + if (pool->flags & POOL_DISASSOCIATED) return false; - if (task_cpu(task) == gcwq->cpu && + if (task_cpu(task) == pool->cpu && cpumask_equal(¤t->cpus_allowed, - get_cpu_mask(gcwq->cpu))) + get_cpu_mask(pool->cpu))) return true; - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); /* * We've raced with CPU hot[un]plug. Give it a breather @@ -1643,15 +1576,13 @@ __acquires(&gcwq->lock) */ static void idle_worker_rebind(struct worker *worker) { - struct global_cwq *gcwq = worker->pool->gcwq; - /* CPU may go down again inbetween, clear UNBOUND only on success */ if (worker_maybe_bind_and_lock(worker)) worker_clr_flags(worker, WORKER_UNBOUND); /* rebind complete, become available again */ list_add(&worker->entry, &worker->pool->idle_list); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&worker->pool->lock); } /* @@ -1663,19 +1594,18 @@ static void idle_worker_rebind(struct worker *worker) static void busy_worker_rebind_fn(struct work_struct *work) { struct worker *worker = container_of(work, struct worker, rebind_work); - struct global_cwq *gcwq = worker->pool->gcwq; if (worker_maybe_bind_and_lock(worker)) worker_clr_flags(worker, WORKER_UNBOUND); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&worker->pool->lock); } /** - * rebind_workers - rebind all workers of a gcwq to the associated CPU - * @gcwq: gcwq of interest + * rebind_workers - rebind all workers of a pool to the associated CPU + * @pool: pool of interest * - * @gcwq->cpu is coming online. Rebind all workers to the CPU. Rebinding + * @pool->cpu is coming online. Rebind all workers to the CPU. Rebinding * is different for idle and busy ones. * * Idle ones will be removed from the idle_list and woken up. They will @@ -1693,38 +1623,32 @@ static void busy_worker_rebind_fn(struct work_struct *work) * including the manager will not appear on @idle_list until rebind is * complete, making local wake-ups safe. */ -static void rebind_workers(struct global_cwq *gcwq) +static void rebind_workers(struct worker_pool *pool) { - struct worker_pool *pool; struct worker *worker, *n; struct hlist_node *pos; int i; - lockdep_assert_held(&gcwq->lock); - - for_each_worker_pool(pool, gcwq) - lockdep_assert_held(&pool->assoc_mutex); + lockdep_assert_held(&pool->assoc_mutex); + lockdep_assert_held(&pool->lock); /* dequeue and kick idle ones */ - for_each_worker_pool(pool, gcwq) { - list_for_each_entry_safe(worker, n, &pool->idle_list, entry) { - /* - * idle workers should be off @pool->idle_list - * until rebind is complete to avoid receiving - * premature local wake-ups. - */ - list_del_init(&worker->entry); + list_for_each_entry_safe(worker, n, &pool->idle_list, entry) { + /* + * idle workers should be off @pool->idle_list until rebind + * is complete to avoid receiving premature local wake-ups. + */ + list_del_init(&worker->entry); - /* - * worker_thread() will see the above dequeuing - * and call idle_worker_rebind(). - */ - wake_up_process(worker->task); - } + /* + * worker_thread() will see the above dequeuing and call + * idle_worker_rebind(). + */ + wake_up_process(worker->task); } /* rebind busy workers */ - for_each_busy_worker(worker, i, pos, gcwq) { + for_each_busy_worker(worker, i, pos, pool) { struct work_struct *rebind_work = &worker->rebind_work; struct workqueue_struct *wq; @@ -1736,16 +1660,16 @@ static void rebind_workers(struct global_cwq *gcwq) /* * wq doesn't really matter but let's keep @worker->pool - * and @cwq->pool consistent for sanity. + * and @pwq->pool consistent for sanity. */ - if (worker_pool_pri(worker->pool)) + if (std_worker_pool_pri(worker->pool)) wq = system_highpri_wq; else wq = system_wq; - insert_work(get_cwq(gcwq->cpu, wq), rebind_work, - worker->scheduled.next, - work_color_to_flags(WORK_NO_COLOR)); + insert_work(get_pwq(pool->cpu, wq), rebind_work, + worker->scheduled.next, + work_color_to_flags(WORK_NO_COLOR)); } } @@ -1780,19 +1704,18 @@ static struct worker *alloc_worker(void) */ static struct worker *create_worker(struct worker_pool *pool) { - struct global_cwq *gcwq = pool->gcwq; - const char *pri = worker_pool_pri(pool) ? "H" : ""; + const char *pri = std_worker_pool_pri(pool) ? "H" : ""; struct worker *worker = NULL; int id = -1; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); while (ida_get_new(&pool->worker_ida, &id)) { - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); if (!ida_pre_get(&pool->worker_ida, GFP_KERNEL)) goto fail; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); worker = alloc_worker(); if (!worker) @@ -1801,30 +1724,30 @@ static struct worker *create_worker(struct worker_pool *pool) worker->pool = pool; worker->id = id; - if (gcwq->cpu != WORK_CPU_UNBOUND) + if (pool->cpu != WORK_CPU_UNBOUND) worker->task = kthread_create_on_node(worker_thread, - worker, cpu_to_node(gcwq->cpu), - "kworker/%u:%d%s", gcwq->cpu, id, pri); + worker, cpu_to_node(pool->cpu), + "kworker/%u:%d%s", pool->cpu, id, pri); else worker->task = kthread_create(worker_thread, worker, "kworker/u:%d%s", id, pri); if (IS_ERR(worker->task)) goto fail; - if (worker_pool_pri(pool)) + if (std_worker_pool_pri(pool)) set_user_nice(worker->task, HIGHPRI_NICE_LEVEL); /* * Determine CPU binding of the new worker depending on - * %GCWQ_DISASSOCIATED. The caller is responsible for ensuring the + * %POOL_DISASSOCIATED. The caller is responsible for ensuring the * flag remains stable across this function. See the comments * above the flag definition for details. * * As an unbound worker may later become a regular one if CPU comes * online, make sure every worker has %PF_THREAD_BOUND set. */ - if (!(gcwq->flags & GCWQ_DISASSOCIATED)) { - kthread_bind(worker->task, gcwq->cpu); + if (!(pool->flags & POOL_DISASSOCIATED)) { + kthread_bind(worker->task, pool->cpu); } else { worker->task->flags |= PF_THREAD_BOUND; worker->flags |= WORKER_UNBOUND; @@ -1833,9 +1756,9 @@ static struct worker *create_worker(struct worker_pool *pool) return worker; fail: if (id >= 0) { - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); ida_remove(&pool->worker_ida, id); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } kfree(worker); return NULL; @@ -1845,10 +1768,10 @@ fail: * start_worker - start a newly created worker * @worker: worker to start * - * Make the gcwq aware of @worker and start it. + * Make the pool aware of @worker and start it. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ static void start_worker(struct worker *worker) { @@ -1862,15 +1785,14 @@ static void start_worker(struct worker *worker) * destroy_worker - destroy a workqueue worker * @worker: worker to be destroyed * - * Destroy @worker and adjust @gcwq stats accordingly. + * Destroy @worker and adjust @pool stats accordingly. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which is released and regrabbed. + * spin_lock_irq(pool->lock) which is released and regrabbed. */ static void destroy_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; int id = worker->id; /* sanity check frenzy */ @@ -1885,21 +1807,20 @@ static void destroy_worker(struct worker *worker) list_del_init(&worker->entry); worker->flags |= WORKER_DIE; - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); kthread_stop(worker->task); kfree(worker); - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); ida_remove(&pool->worker_ida, id); } static void idle_worker_timeout(unsigned long __pool) { struct worker_pool *pool = (void *)__pool; - struct global_cwq *gcwq = pool->gcwq; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; @@ -1918,20 +1839,20 @@ static void idle_worker_timeout(unsigned long __pool) } } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } static bool send_mayday(struct work_struct *work) { - struct cpu_workqueue_struct *cwq = get_work_cwq(work); - struct workqueue_struct *wq = cwq->wq; + struct pool_workqueue *pwq = get_work_pwq(work); + struct workqueue_struct *wq = pwq->wq; unsigned int cpu; if (!(wq->flags & WQ_RESCUER)) return false; /* mayday mayday mayday */ - cpu = cwq->pool->gcwq->cpu; + cpu = pwq->pool->cpu; /* WORK_CPU_UNBOUND can't be set in cpumask, use cpu 0 instead */ if (cpu == WORK_CPU_UNBOUND) cpu = 0; @@ -1940,13 +1861,12 @@ static bool send_mayday(struct work_struct *work) return true; } -static void gcwq_mayday_timeout(unsigned long __pool) +static void pool_mayday_timeout(unsigned long __pool) { struct worker_pool *pool = (void *)__pool; - struct global_cwq *gcwq = pool->gcwq; struct work_struct *work; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (need_to_create_worker(pool)) { /* @@ -1959,7 +1879,7 @@ static void gcwq_mayday_timeout(unsigned long __pool) send_mayday(work); } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } @@ -1978,24 +1898,22 @@ static void gcwq_mayday_timeout(unsigned long __pool) * may_start_working() true. * * LOCKING: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. * * RETURNS: - * false if no action was taken and gcwq->lock stayed locked, true + * false if no action was taken and pool->lock stayed locked, true * otherwise. */ static bool maybe_create_worker(struct worker_pool *pool) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) +__releases(&pool->lock) +__acquires(&pool->lock) { - struct global_cwq *gcwq = pool->gcwq; - if (!need_to_create_worker(pool)) return false; restart: - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); @@ -2006,7 +1924,7 @@ restart: worker = create_worker(pool); if (worker) { del_timer_sync(&pool->mayday_timer); - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); start_worker(worker); BUG_ON(need_to_create_worker(pool)); return true; @@ -2023,7 +1941,7 @@ restart: } del_timer_sync(&pool->mayday_timer); - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (need_to_create_worker(pool)) goto restart; return true; @@ -2037,11 +1955,11 @@ restart: * IDLE_WORKER_TIMEOUT. * * LOCKING: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Called only from manager. * * RETURNS: - * false if no action was taken and gcwq->lock stayed locked, true + * false if no action was taken and pool->lock stayed locked, true * otherwise. */ static bool maybe_destroy_workers(struct worker_pool *pool) @@ -2071,21 +1989,21 @@ static bool maybe_destroy_workers(struct worker_pool *pool) * manage_workers - manage worker pool * @worker: self * - * Assume the manager role and manage gcwq worker pool @worker belongs + * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per - * gcwq. The exclusion is handled automatically by this function. + * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * RETURNS: - * false if no action was taken and gcwq->lock stayed locked, true if - * some action was taken. + * spin_lock_irq(pool->lock) which may be released and regrabbed + * multiple times. Does GFP_KERNEL allocations. */ static bool manage_workers(struct worker *worker) { @@ -2107,20 +2025,20 @@ static bool manage_workers(struct worker *worker) * manager against CPU hotplug. * * assoc_mutex would always be free unless CPU hotplug is in - * progress. trylock first without dropping @gcwq->lock. + * progress. trylock first without dropping @pool->lock. */ if (unlikely(!mutex_trylock(&pool->assoc_mutex))) { - spin_unlock_irq(&pool->gcwq->lock); + spin_unlock_irq(&pool->lock); mutex_lock(&pool->assoc_mutex); /* * CPU hotplug could have happened while we were waiting * for assoc_mutex. Hotplug itself can't handle us * because manager isn't either on idle or busy list, and - * @gcwq's state and ours could have deviated. + * @pool's state and ours could have deviated. * * As hotplug is now excluded via assoc_mutex, we can * simply try to bind. It will succeed or fail depending - * on @gcwq's current state. Try it and adjust + * on @pool's current state. Try it and adjust * %WORKER_UNBOUND accordingly. */ if (worker_maybe_bind_and_lock(worker)) @@ -2157,18 +2075,15 @@ static bool manage_workers(struct worker *worker) * call this function to process a work. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which is released and regrabbed. + * spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) -__releases(&gcwq->lock) -__acquires(&gcwq->lock) +__releases(&pool->lock) +__acquires(&pool->lock) { - struct cpu_workqueue_struct *cwq = get_work_cwq(work); + struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; - struct hlist_head *bwh = busy_worker_head(gcwq, work); - bool cpu_intensive = cwq->wq->flags & WQ_CPU_INTENSIVE; - work_func_t f = work->func; + bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE; int work_color; struct worker *collision; #ifdef CONFIG_LOCKDEP @@ -2186,11 +2101,11 @@ __acquires(&gcwq->lock) /* * Ensure we're on the correct CPU. DISASSOCIATED test is * necessary to avoid spurious warnings from rescuers servicing the - * unbound or a disassociated gcwq. + * unbound or a disassociated pool. */ WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) && - !(gcwq->flags & GCWQ_DISASSOCIATED) && - raw_smp_processor_id() != gcwq->cpu); + !(pool->flags & POOL_DISASSOCIATED) && + raw_smp_processor_id() != pool->cpu); /* * A single work shouldn't be executed concurrently by @@ -2198,7 +2113,7 @@ __acquires(&gcwq->lock) * already processing the work. If so, defer the work to the * currently executing one. */ - collision = __find_worker_executing_work(gcwq, bwh, work); + collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, NULL); return; @@ -2206,9 +2121,10 @@ __acquires(&gcwq->lock) /* claim and dequeue */ debug_work_deactivate(work); - hlist_add_head(&worker->hentry, bwh); + hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; - worker->current_cwq = cwq; + worker->current_func = work->func; + worker->current_pwq = pwq; work_color = get_work_color(work); list_del_init(&work->entry); @@ -2221,53 +2137,55 @@ __acquires(&gcwq->lock) worker_set_flags(worker, WORKER_CPU_INTENSIVE, true); /* - * Unbound gcwq isn't concurrency managed and work items should be + * Unbound pool isn't concurrency managed and work items should be * executed ASAP. Wake up another worker if necessary. */ if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) wake_up_worker(pool); /* - * Record the last CPU and clear PENDING which should be the last - * update to @work. Also, do this inside @gcwq->lock so that + * Record the last pool and clear PENDING which should be the last + * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ - set_work_cpu_and_clear_pending(work, gcwq->cpu); + set_work_pool_and_clear_pending(work, pool->id); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); - lock_map_acquire_read(&cwq->wq->lockdep_map); + lock_map_acquire_read(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); trace_workqueue_execute_start(work); - f(work); + worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work); lock_map_release(&lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" " last function: %pf\n", - current->comm, preempt_count(), task_pid_nr(current), f); + current->comm, preempt_count(), task_pid_nr(current), + worker->current_func); debug_show_held_locks(current); dump_stack(); } - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); /* clear cpu intensive status */ if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* we're done with it, release */ - hlist_del_init(&worker->hentry); + hash_del(&worker->hentry); worker->current_work = NULL; - worker->current_cwq = NULL; - cwq_dec_nr_in_flight(cwq, work_color); + worker->current_func = NULL; + worker->current_pwq = NULL; + pwq_dec_nr_in_flight(pwq, work_color); } /** @@ -2279,7 +2197,7 @@ __acquires(&gcwq->lock) * fetches a work from the top and executes it. * * CONTEXT: - * spin_lock_irq(gcwq->lock) which may be released and regrabbed + * spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) @@ -2295,8 +2213,8 @@ static void process_scheduled_works(struct worker *worker) * worker_thread - the worker thread function * @__worker: self * - * The gcwq worker thread function. There's a single dynamic pool of - * these per each cpu. These workers process all works regardless of + * The worker thread function. There are NR_CPU_WORKER_POOLS dynamic pools + * of these per each cpu. These workers process all works regardless of * their specific target workqueue. The only exception is works which * belong to workqueues with a rescuer which will be explained in * rescuer_thread(). @@ -2305,16 +2223,15 @@ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; - struct global_cwq *gcwq = pool->gcwq; /* tell the scheduler that this is a workqueue worker */ worker->task->flags |= PF_WQ_WORKER; woke_up: - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); /* we are off idle list if destruction or rebind is requested */ if (unlikely(list_empty(&worker->entry))) { - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); /* if DIE is set, destruction is requested */ if (worker->flags & WORKER_DIE) { @@ -2373,52 +2290,59 @@ sleep: goto recheck; /* - * gcwq->lock is held and there's no work to process and no - * need to manage, sleep. Workers are woken up only while - * holding gcwq->lock or from local cpu, so setting the - * current state before releasing gcwq->lock is enough to - * prevent losing any event. + * pool->lock is held and there's no work to process and no need to + * manage, sleep. Workers are woken up only while holding + * pool->lock or from local cpu, so setting the current state + * before releasing pool->lock is enough to prevent losing any + * event. */ worker_enter_idle(worker); __set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function - * @__wq: the associated workqueue + * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_RESCUER set. * - * Regular work processing on a gcwq may block trying to create a new + * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * - * When such condition is possible, the gcwq summons rescuers of all - * workqueues which have works queued on the gcwq and let them process + * When such condition is possible, the pool summons rescuers of all + * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. */ -static int rescuer_thread(void *__wq) +static int rescuer_thread(void *__rescuer) { - struct workqueue_struct *wq = __wq; - struct worker *rescuer = wq->rescuer; + struct worker *rescuer = __rescuer; + struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; bool is_unbound = wq->flags & WQ_UNBOUND; unsigned int cpu; set_user_nice(current, RESCUER_NICE_LEVEL); + + /* + * Mark rescuer as worker too. As WORKER_PREP is never cleared, it + * doesn't participate in concurrency management. + */ + rescuer->task->flags |= PF_WQ_WORKER; repeat: set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); + rescuer->task->flags &= ~PF_WQ_WORKER; return 0; } @@ -2428,9 +2352,8 @@ repeat: */ for_each_mayday_cpu(cpu, wq->mayday_mask) { unsigned int tcpu = is_unbound ? WORK_CPU_UNBOUND : cpu; - struct cpu_workqueue_struct *cwq = get_cwq(tcpu, wq); - struct worker_pool *pool = cwq->pool; - struct global_cwq *gcwq = pool->gcwq; + struct pool_workqueue *pwq = get_pwq(tcpu, wq); + struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); @@ -2446,22 +2369,24 @@ repeat: */ BUG_ON(!list_empty(&rescuer->scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) - if (get_work_cwq(work) == cwq) + if (get_work_pwq(work) == pwq) move_linked_works(work, scheduled, &n); process_scheduled_works(rescuer); /* - * Leave this gcwq. If keep_working() is %true, notify a + * Leave this pool. If keep_working() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ if (keep_working(pool)) wake_up_worker(pool); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } + /* rescuers should never participate in concurrency management */ + WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } @@ -2479,7 +2404,7 @@ static void wq_barrier_func(struct work_struct *work) /** * insert_wq_barrier - insert a barrier work - * @cwq: cwq to insert barrier into + * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing @@ -2496,12 +2421,12 @@ static void wq_barrier_func(struct work_struct *work) * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified - * underneath us, so we can't reliably determine cwq from @target. + * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, +static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { @@ -2509,7 +2434,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, unsigned int linked = 0; /* - * debugobject calls are safe here even with gcwq->lock locked + * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. @@ -2534,23 +2459,23 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, } debug_work_activate(&barr->work); - insert_work(cwq, &barr->work, head, + insert_work(pwq, &barr->work, head, work_color_to_flags(WORK_NO_COLOR) | linked); } /** - * flush_workqueue_prep_cwqs - prepare cwqs for workqueue flushing + * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * - * Prepare cwqs for workqueue flushing. + * Prepare pwqs for workqueue flushing. * - * If @flush_color is non-negative, flush_color on all cwqs should be - * -1. If no cwq has in-flight commands at the specified color, all - * cwq->flush_color's stay at -1 and %false is returned. If any cwq - * has in flight commands, its cwq->flush_color is set to - * @flush_color, @wq->nr_cwqs_to_flush is updated accordingly, cwq + * If @flush_color is non-negative, flush_color on all pwqs should be + * -1. If no pwq has in-flight commands at the specified color, all + * pwq->flush_color's stay at -1 and %false is returned. If any pwq + * has in flight commands, its pwq->flush_color is set to + * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to @@ -2558,7 +2483,7 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * @flush_color is negative, no flush color update is done and %false * is returned. * - * If @work_color is non-negative, all cwqs should have the same + * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * @@ -2569,42 +2494,42 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq, * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ -static bool flush_workqueue_prep_cwqs(struct workqueue_struct *wq, +static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; unsigned int cpu; if (flush_color >= 0) { - BUG_ON(atomic_read(&wq->nr_cwqs_to_flush)); - atomic_set(&wq->nr_cwqs_to_flush, 1); + BUG_ON(atomic_read(&wq->nr_pwqs_to_flush)); + atomic_set(&wq->nr_pwqs_to_flush, 1); } - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - struct global_cwq *gcwq = cwq->pool->gcwq; + for_each_pwq_cpu(cpu, wq) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); + struct worker_pool *pool = pwq->pool; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (flush_color >= 0) { - BUG_ON(cwq->flush_color != -1); + BUG_ON(pwq->flush_color != -1); - if (cwq->nr_in_flight[flush_color]) { - cwq->flush_color = flush_color; - atomic_inc(&wq->nr_cwqs_to_flush); + if (pwq->nr_in_flight[flush_color]) { + pwq->flush_color = flush_color; + atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { - BUG_ON(work_color != work_next_color(cwq->work_color)); - cwq->work_color = work_color; + BUG_ON(work_color != work_next_color(pwq->work_color)); + pwq->work_color = work_color; } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } - if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_cwqs_to_flush)) + if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; @@ -2655,7 +2580,7 @@ void flush_workqueue(struct workqueue_struct *wq) wq->first_flusher = &this_flusher; - if (!flush_workqueue_prep_cwqs(wq, wq->flush_color, + if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; @@ -2666,7 +2591,7 @@ void flush_workqueue(struct workqueue_struct *wq) /* wait in queue */ BUG_ON(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); - flush_workqueue_prep_cwqs(wq, -1, wq->work_color); + flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* @@ -2733,7 +2658,7 @@ void flush_workqueue(struct workqueue_struct *wq) list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); - flush_workqueue_prep_cwqs(wq, -1, wq->work_color); + flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { @@ -2743,7 +2668,7 @@ void flush_workqueue(struct workqueue_struct *wq) /* * Need to flush more colors. Make the next flusher - * the new first flusher and arm cwqs. + * the new first flusher and arm pwqs. */ BUG_ON(wq->flush_color == wq->work_color); BUG_ON(wq->flush_color != next->flush_color); @@ -2751,7 +2676,7 @@ void flush_workqueue(struct workqueue_struct *wq) list_del_init(&next->list); wq->first_flusher = next; - if (flush_workqueue_prep_cwqs(wq, wq->flush_color, -1)) + if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* @@ -2794,13 +2719,13 @@ void drain_workqueue(struct workqueue_struct *wq) reflush: flush_workqueue(wq); - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + for_each_pwq_cpu(cpu, wq) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); bool drained; - spin_lock_irq(&cwq->pool->gcwq->lock); - drained = !cwq->nr_active && list_empty(&cwq->delayed_works); - spin_unlock_irq(&cwq->pool->gcwq->lock); + spin_lock_irq(&pwq->pool->lock); + drained = !pwq->nr_active && list_empty(&pwq->delayed_works); + spin_unlock_irq(&pwq->pool->lock); if (drained) continue; @@ -2822,34 +2747,29 @@ EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) { struct worker *worker = NULL; - struct global_cwq *gcwq; - struct cpu_workqueue_struct *cwq; + struct worker_pool *pool; + struct pool_workqueue *pwq; might_sleep(); - gcwq = get_work_gcwq(work); - if (!gcwq) + pool = get_work_pool(work); + if (!pool) return false; - spin_lock_irq(&gcwq->lock); - if (!list_empty(&work->entry)) { - /* - * See the comment near try_to_grab_pending()->smp_rmb(). - * If it was re-queued to a different gcwq under us, we - * are not going to wait. - */ - smp_rmb(); - cwq = get_work_cwq(work); - if (unlikely(!cwq || gcwq != cwq->pool->gcwq)) + spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { + if (unlikely(pwq->pool != pool)) goto already_gone; } else { - worker = find_worker_executing_work(gcwq, work); + worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; - cwq = worker->current_cwq; + pwq = worker->current_pwq; } - insert_wq_barrier(cwq, barr, work, worker); - spin_unlock_irq(&gcwq->lock); + insert_wq_barrier(pwq, barr, work, worker); + spin_unlock_irq(&pool->lock); /* * If @max_active is 1 or rescuer is in use, flushing another work @@ -2857,15 +2777,15 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) * flusher is not running on the same workqueue by verifying write * access. */ - if (cwq->wq->saved_max_active == 1 || cwq->wq->flags & WQ_RESCUER) - lock_map_acquire(&cwq->wq->lockdep_map); + if (pwq->wq->saved_max_active == 1 || pwq->wq->flags & WQ_RESCUER) + lock_map_acquire(&pwq->wq->lockdep_map); else - lock_map_acquire_read(&cwq->wq->lockdep_map); - lock_map_release(&cwq->wq->lockdep_map); + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); return true; already_gone: - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); return false; } @@ -2961,8 +2881,7 @@ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) - __queue_work(dwork->cpu, - get_work_cwq(&dwork->work)->wq, &dwork->work); + __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } @@ -2992,7 +2911,8 @@ bool cancel_delayed_work(struct delayed_work *dwork) if (unlikely(ret < 0)) return false; - set_work_cpu_and_clear_pending(&dwork->work, work_cpu(&dwork->work)); + set_work_pool_and_clear_pending(&dwork->work, + get_work_pool_id(&dwork->work)); local_irq_restore(flags); return ret; } @@ -3171,46 +3091,46 @@ int keventd_up(void) return system_wq != NULL; } -static int alloc_cwqs(struct workqueue_struct *wq) +static int alloc_pwqs(struct workqueue_struct *wq) { /* - * cwqs are forced aligned according to WORK_STRUCT_FLAG_BITS. + * pwqs are forced aligned according to WORK_STRUCT_FLAG_BITS. * Make sure that the alignment isn't lower than that of * unsigned long long. */ - const size_t size = sizeof(struct cpu_workqueue_struct); + const size_t size = sizeof(struct pool_workqueue); const size_t align = max_t(size_t, 1 << WORK_STRUCT_FLAG_BITS, __alignof__(unsigned long long)); if (!(wq->flags & WQ_UNBOUND)) - wq->cpu_wq.pcpu = __alloc_percpu(size, align); + wq->pool_wq.pcpu = __alloc_percpu(size, align); else { void *ptr; /* - * Allocate enough room to align cwq and put an extra + * Allocate enough room to align pwq and put an extra * pointer at the end pointing back to the originally * allocated pointer which will be used for free. */ ptr = kzalloc(size + align + sizeof(void *), GFP_KERNEL); if (ptr) { - wq->cpu_wq.single = PTR_ALIGN(ptr, align); - *(void **)(wq->cpu_wq.single + 1) = ptr; + wq->pool_wq.single = PTR_ALIGN(ptr, align); + *(void **)(wq->pool_wq.single + 1) = ptr; } } /* just in case, make sure it's actually aligned */ - BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); - return wq->cpu_wq.v ? 0 : -ENOMEM; + BUG_ON(!IS_ALIGNED(wq->pool_wq.v, align)); + return wq->pool_wq.v ? 0 : -ENOMEM; } -static void free_cwqs(struct workqueue_struct *wq) +static void free_pwqs(struct workqueue_struct *wq) { if (!(wq->flags & WQ_UNBOUND)) - free_percpu(wq->cpu_wq.pcpu); - else if (wq->cpu_wq.single) { - /* the pointer to free is stored right after the cwq */ - kfree(*(void **)(wq->cpu_wq.single + 1)); + free_percpu(wq->pool_wq.pcpu); + else if (wq->pool_wq.single) { + /* the pointer to free is stored right after the pwq */ + kfree(*(void **)(wq->pool_wq.single + 1)); } } @@ -3264,27 +3184,25 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, wq->flags = flags; wq->saved_max_active = max_active; mutex_init(&wq->flush_mutex); - atomic_set(&wq->nr_cwqs_to_flush, 0); + atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); INIT_LIST_HEAD(&wq->list); - if (alloc_cwqs(wq) < 0) + if (alloc_pwqs(wq) < 0) goto err; - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - struct global_cwq *gcwq = get_gcwq(cpu); - int pool_idx = (bool)(flags & WQ_HIGHPRI); - - BUG_ON((unsigned long)cwq & WORK_STRUCT_FLAG_MASK); - cwq->pool = &gcwq->pools[pool_idx]; - cwq->wq = wq; - cwq->flush_color = -1; - cwq->max_active = max_active; - INIT_LIST_HEAD(&cwq->delayed_works); + for_each_pwq_cpu(cpu, wq) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); + + BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); + pwq->pool = get_std_worker_pool(cpu, flags & WQ_HIGHPRI); + pwq->wq = wq; + pwq->flush_color = -1; + pwq->max_active = max_active; + INIT_LIST_HEAD(&pwq->delayed_works); } if (flags & WQ_RESCUER) { @@ -3297,7 +3215,8 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, if (!rescuer) goto err; - rescuer->task = kthread_create(rescuer_thread, wq, "%s", + rescuer->rescue_wq = wq; + rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name); if (IS_ERR(rescuer->task)) goto err; @@ -3314,8 +3233,8 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, spin_lock(&workqueue_lock); if (workqueue_freezing && wq->flags & WQ_FREEZABLE) - for_each_cwq_cpu(cpu, wq) - get_cwq(cpu, wq)->max_active = 0; + for_each_pwq_cpu(cpu, wq) + get_pwq(cpu, wq)->max_active = 0; list_add(&wq->list, &workqueues); @@ -3324,7 +3243,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt, return wq; err: if (wq) { - free_cwqs(wq); + free_pwqs(wq); free_mayday_mask(wq->mayday_mask); kfree(wq->rescuer); kfree(wq); @@ -3355,14 +3274,14 @@ void destroy_workqueue(struct workqueue_struct *wq) spin_unlock(&workqueue_lock); /* sanity check */ - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + for_each_pwq_cpu(cpu, wq) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); int i; for (i = 0; i < WORK_NR_COLORS; i++) - BUG_ON(cwq->nr_in_flight[i]); - BUG_ON(cwq->nr_active); - BUG_ON(!list_empty(&cwq->delayed_works)); + BUG_ON(pwq->nr_in_flight[i]); + BUG_ON(pwq->nr_active); + BUG_ON(!list_empty(&pwq->delayed_works)); } if (wq->flags & WQ_RESCUER) { @@ -3371,29 +3290,29 @@ void destroy_workqueue(struct workqueue_struct *wq) kfree(wq->rescuer); } - free_cwqs(wq); + free_pwqs(wq); kfree(wq); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** - * cwq_set_max_active - adjust max_active of a cwq - * @cwq: target cpu_workqueue_struct + * pwq_set_max_active - adjust max_active of a pwq + * @pwq: target pool_workqueue * @max_active: new max_active value. * - * Set @cwq->max_active to @max_active and activate delayed works if + * Set @pwq->max_active to @max_active and activate delayed works if * increased. * * CONTEXT: - * spin_lock_irq(gcwq->lock). + * spin_lock_irq(pool->lock). */ -static void cwq_set_max_active(struct cpu_workqueue_struct *cwq, int max_active) +static void pwq_set_max_active(struct pool_workqueue *pwq, int max_active) { - cwq->max_active = max_active; + pwq->max_active = max_active; - while (!list_empty(&cwq->delayed_works) && - cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + while (!list_empty(&pwq->delayed_works) && + pwq->nr_active < pwq->max_active) + pwq_activate_first_delayed(pwq); } /** @@ -3416,16 +3335,17 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) wq->saved_max_active = max_active; - for_each_cwq_cpu(cpu, wq) { - struct global_cwq *gcwq = get_gcwq(cpu); + for_each_pwq_cpu(cpu, wq) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); + struct worker_pool *pool = pwq->pool; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); if (!(wq->flags & WQ_FREEZABLE) || - !(gcwq->flags & GCWQ_FREEZING)) - cwq_set_max_active(get_cwq(gcwq->cpu, wq), max_active); + !(pool->flags & POOL_FREEZING)) + pwq_set_max_active(pwq, max_active); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } spin_unlock(&workqueue_lock); @@ -3446,57 +3366,38 @@ EXPORT_SYMBOL_GPL(workqueue_set_max_active); */ bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + struct pool_workqueue *pwq = get_pwq(cpu, wq); - return !list_empty(&cwq->delayed_works); + return !list_empty(&pwq->delayed_works); } EXPORT_SYMBOL_GPL(workqueue_congested); /** - * work_cpu - return the last known associated cpu for @work - * @work: the work of interest - * - * RETURNS: - * CPU number if @work was ever queued. WORK_CPU_NONE otherwise. - */ -unsigned int work_cpu(struct work_struct *work) -{ - struct global_cwq *gcwq = get_work_gcwq(work); - - return gcwq ? gcwq->cpu : WORK_CPU_NONE; -} -EXPORT_SYMBOL_GPL(work_cpu); - -/** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. - * Especially for reentrant wqs, the pending state might hide the - * running state. * * RETURNS: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { - struct global_cwq *gcwq = get_work_gcwq(work); + struct worker_pool *pool = get_work_pool(work); unsigned long flags; unsigned int ret = 0; - if (!gcwq) - return 0; - - spin_lock_irqsave(&gcwq->lock, flags); - if (work_pending(work)) ret |= WORK_BUSY_PENDING; - if (find_worker_executing_work(gcwq, work)) - ret |= WORK_BUSY_RUNNING; - spin_unlock_irqrestore(&gcwq->lock, flags); + if (pool) { + spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; + spin_unlock_irqrestore(&pool->lock, flags); + } return ret; } @@ -3506,65 +3407,49 @@ EXPORT_SYMBOL_GPL(work_busy); * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there - * are a lot of assumptions on strong associations among work, cwq and - * gcwq which make migrating pending and scheduled works very + * are a lot of assumptions on strong associations among work, pwq and + * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, - * gcwqs serve mix of short, long and very long running works making + * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * - * This is solved by allowing a gcwq to be disassociated from the CPU + * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ -/* claim manager positions of all pools */ -static void gcwq_claim_assoc_and_lock(struct global_cwq *gcwq) +static void wq_unbind_fn(struct work_struct *work) { - struct worker_pool *pool; - - for_each_worker_pool(pool, gcwq) - mutex_lock_nested(&pool->assoc_mutex, pool - gcwq->pools); - spin_lock_irq(&gcwq->lock); -} - -/* release manager positions */ -static void gcwq_release_assoc_and_unlock(struct global_cwq *gcwq) -{ - struct worker_pool *pool; - - spin_unlock_irq(&gcwq->lock); - for_each_worker_pool(pool, gcwq) - mutex_unlock(&pool->assoc_mutex); -} - -static void gcwq_unbind_fn(struct work_struct *work) -{ - struct global_cwq *gcwq = get_gcwq(smp_processor_id()); + int cpu = smp_processor_id(); struct worker_pool *pool; struct worker *worker; struct hlist_node *pos; int i; - BUG_ON(gcwq->cpu != smp_processor_id()); + for_each_std_worker_pool(pool, cpu) { + BUG_ON(cpu != smp_processor_id()); - gcwq_claim_assoc_and_lock(gcwq); + mutex_lock(&pool->assoc_mutex); + spin_lock_irq(&pool->lock); - /* - * We've claimed all manager positions. Make all workers unbound - * and set DISASSOCIATED. Before this, all workers except for the - * ones which are still executing works from before the last CPU - * down must be on the cpu. After this, they may become diasporas. - */ - for_each_worker_pool(pool, gcwq) + /* + * We've claimed all manager positions. Make all workers + * unbound and set DISASSOCIATED. Before this, all workers + * except for the ones which are still executing works from + * before the last CPU down must be on the cpu. After + * this, they may become diasporas. + */ list_for_each_entry(worker, &pool->idle_list, entry) worker->flags |= WORKER_UNBOUND; - for_each_busy_worker(worker, i, pos, gcwq) - worker->flags |= WORKER_UNBOUND; + for_each_busy_worker(worker, i, pos, pool) + worker->flags |= WORKER_UNBOUND; - gcwq->flags |= GCWQ_DISASSOCIATED; + pool->flags |= POOL_DISASSOCIATED; - gcwq_release_assoc_and_unlock(gcwq); + spin_unlock_irq(&pool->lock); + mutex_unlock(&pool->assoc_mutex); + } /* * Call schedule() so that we cross rq->lock and thus can guarantee @@ -3576,16 +3461,16 @@ static void gcwq_unbind_fn(struct work_struct *work) /* * Sched callbacks are disabled now. Zap nr_running. After this, * nr_running stays zero and need_more_worker() and keep_working() - * are always true as long as the worklist is not empty. @gcwq now - * behaves as unbound (in terms of concurrency management) gcwq - * which is served by workers tied to the CPU. + * are always true as long as the worklist is not empty. Pools on + * @cpu now behave as unbound (in terms of concurrency management) + * pools which are served by workers tied to the CPU. * * On return from this function, the current worker would trigger * unbound chain execution of pending work items if other workers * didn't already. */ - for_each_worker_pool(pool, gcwq) - atomic_set(get_pool_nr_running(pool), 0); + for_each_std_worker_pool(pool, cpu) + atomic_set(&pool->nr_running, 0); } /* @@ -3597,12 +3482,11 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; - struct global_cwq *gcwq = get_gcwq(cpu); struct worker_pool *pool; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - for_each_worker_pool(pool, gcwq) { + for_each_std_worker_pool(pool, cpu) { struct worker *worker; if (pool->nr_workers) @@ -3612,18 +3496,24 @@ static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, if (!worker) return NOTIFY_BAD; - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); start_worker(worker); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } break; case CPU_DOWN_FAILED: case CPU_ONLINE: - gcwq_claim_assoc_and_lock(gcwq); - gcwq->flags &= ~GCWQ_DISASSOCIATED; - rebind_workers(gcwq); - gcwq_release_assoc_and_unlock(gcwq); + for_each_std_worker_pool(pool, cpu) { + mutex_lock(&pool->assoc_mutex); + spin_lock_irq(&pool->lock); + + pool->flags &= ~POOL_DISASSOCIATED; + rebind_workers(pool); + + spin_unlock_irq(&pool->lock); + mutex_unlock(&pool->assoc_mutex); + } break; } return NOTIFY_OK; @@ -3643,7 +3533,7 @@ static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb, switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: /* unbinding should happen on the local CPU */ - INIT_WORK_ONSTACK(&unbind_work, gcwq_unbind_fn); + INIT_WORK_ONSTACK(&unbind_work, wq_unbind_fn); queue_work_on(cpu, system_highpri_wq, &unbind_work); flush_work(&unbind_work); break; @@ -3696,10 +3586,10 @@ EXPORT_SYMBOL_GPL(work_on_cpu); * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their frozen_works list instead of - * gcwq->worklist. + * pool->worklist. * * CONTEXT: - * Grabs and releases workqueue_lock and gcwq->lock's. + * Grabs and releases workqueue_lock and pool->lock's. */ void freeze_workqueues_begin(void) { @@ -3710,23 +3600,26 @@ void freeze_workqueues_begin(void) BUG_ON(workqueue_freezing); workqueue_freezing = true; - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); + for_each_wq_cpu(cpu) { + struct worker_pool *pool; struct workqueue_struct *wq; - spin_lock_irq(&gcwq->lock); + for_each_std_worker_pool(pool, cpu) { + spin_lock_irq(&pool->lock); - BUG_ON(gcwq->flags & GCWQ_FREEZING); - gcwq->flags |= GCWQ_FREEZING; + WARN_ON_ONCE(pool->flags & POOL_FREEZING); + pool->flags |= POOL_FREEZING; - list_for_each_entry(wq, &workqueues, list) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + list_for_each_entry(wq, &workqueues, list) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); - if (cwq && wq->flags & WQ_FREEZABLE) - cwq->max_active = 0; - } + if (pwq && pwq->pool == pool && + (wq->flags & WQ_FREEZABLE)) + pwq->max_active = 0; + } - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); + } } spin_unlock(&workqueue_lock); @@ -3754,20 +3647,20 @@ bool freeze_workqueues_busy(void) BUG_ON(!workqueue_freezing); - for_each_gcwq_cpu(cpu) { + for_each_wq_cpu(cpu) { struct workqueue_struct *wq; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ list_for_each_entry(wq, &workqueues, list) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + struct pool_workqueue *pwq = get_pwq(cpu, wq); - if (!cwq || !(wq->flags & WQ_FREEZABLE)) + if (!pwq || !(wq->flags & WQ_FREEZABLE)) continue; - BUG_ON(cwq->nr_active < 0); - if (cwq->nr_active) { + BUG_ON(pwq->nr_active < 0); + if (pwq->nr_active) { busy = true; goto out_unlock; } @@ -3782,10 +3675,10 @@ out_unlock: * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected - * frozen works are transferred to their respective gcwq worklists. + * frozen works are transferred to their respective pool worklists. * * CONTEXT: - * Grabs and releases workqueue_lock and gcwq->lock's. + * Grabs and releases workqueue_lock and pool->lock's. */ void thaw_workqueues(void) { @@ -3796,30 +3689,31 @@ void thaw_workqueues(void) if (!workqueue_freezing) goto out_unlock; - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); + for_each_wq_cpu(cpu) { struct worker_pool *pool; struct workqueue_struct *wq; - spin_lock_irq(&gcwq->lock); + for_each_std_worker_pool(pool, cpu) { + spin_lock_irq(&pool->lock); - BUG_ON(!(gcwq->flags & GCWQ_FREEZING)); - gcwq->flags &= ~GCWQ_FREEZING; + WARN_ON_ONCE(!(pool->flags & POOL_FREEZING)); + pool->flags &= ~POOL_FREEZING; - list_for_each_entry(wq, &workqueues, list) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + list_for_each_entry(wq, &workqueues, list) { + struct pool_workqueue *pwq = get_pwq(cpu, wq); - if (!cwq || !(wq->flags & WQ_FREEZABLE)) - continue; + if (!pwq || pwq->pool != pool || + !(wq->flags & WQ_FREEZABLE)) + continue; - /* restore max_active and repopulate worklist */ - cwq_set_max_active(cwq, wq->saved_max_active); - } + /* restore max_active and repopulate worklist */ + pwq_set_max_active(pwq, wq->saved_max_active); + } - for_each_worker_pool(pool, gcwq) wake_up_worker(pool); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); + } } workqueue_freezing = false; @@ -3831,60 +3725,56 @@ out_unlock: static int __init init_workqueues(void) { unsigned int cpu; - int i; - /* make sure we have enough bits for OFFQ CPU number */ - BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_CPU_SHIFT)) < - WORK_CPU_LAST); + /* make sure we have enough bits for OFFQ pool ID */ + BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) < + WORK_CPU_END * NR_STD_WORKER_POOLS); cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); - /* initialize gcwqs */ - for_each_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); + /* initialize CPU pools */ + for_each_wq_cpu(cpu) { struct worker_pool *pool; - spin_lock_init(&gcwq->lock); - gcwq->cpu = cpu; - gcwq->flags |= GCWQ_DISASSOCIATED; - - for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) - INIT_HLIST_HEAD(&gcwq->busy_hash[i]); - - for_each_worker_pool(pool, gcwq) { - pool->gcwq = gcwq; + for_each_std_worker_pool(pool, cpu) { + spin_lock_init(&pool->lock); + pool->cpu = cpu; + pool->flags |= POOL_DISASSOCIATED; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); + hash_init(pool->busy_hash); init_timer_deferrable(&pool->idle_timer); pool->idle_timer.function = idle_worker_timeout; pool->idle_timer.data = (unsigned long)pool; - setup_timer(&pool->mayday_timer, gcwq_mayday_timeout, + setup_timer(&pool->mayday_timer, pool_mayday_timeout, (unsigned long)pool); mutex_init(&pool->assoc_mutex); ida_init(&pool->worker_ida); + + /* alloc pool ID */ + BUG_ON(worker_pool_assign_id(pool)); } } /* create the initial worker */ - for_each_online_gcwq_cpu(cpu) { - struct global_cwq *gcwq = get_gcwq(cpu); + for_each_online_wq_cpu(cpu) { struct worker_pool *pool; - if (cpu != WORK_CPU_UNBOUND) - gcwq->flags &= ~GCWQ_DISASSOCIATED; - - for_each_worker_pool(pool, gcwq) { + for_each_std_worker_pool(pool, cpu) { struct worker *worker; + if (cpu != WORK_CPU_UNBOUND) + pool->flags &= ~POOL_DISASSOCIATED; + worker = create_worker(pool); BUG_ON(!worker); - spin_lock_irq(&gcwq->lock); + spin_lock_irq(&pool->lock); start_worker(worker); - spin_unlock_irq(&gcwq->lock); + spin_unlock_irq(&pool->lock); } } diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h new file mode 100644 index 0000000..0765026 --- /dev/null +++ b/kernel/workqueue_internal.h @@ -0,0 +1,65 @@ +/* + * kernel/workqueue_internal.h + * + * Workqueue internal header file. Only to be included by workqueue and + * core kernel subsystems. + */ +#ifndef _KERNEL_WORKQUEUE_INTERNAL_H +#define _KERNEL_WORKQUEUE_INTERNAL_H + +#include <linux/workqueue.h> +#include <linux/kthread.h> + +struct worker_pool; + +/* + * The poor guys doing the actual heavy lifting. All on-duty workers are + * either serving the manager role, on idle list or on busy hash. For + * details on the locking annotation (L, I, X...), refer to workqueue.c. + * + * Only to be used in workqueue and async. + */ +struct worker { + /* on idle list while idle, on busy hash table while busy */ + union { + struct list_head entry; /* L: while idle */ + struct hlist_node hentry; /* L: while busy */ + }; + + struct work_struct *current_work; /* L: work being processed */ + work_func_t current_func; /* L: current_work's fn */ + struct pool_workqueue *current_pwq; /* L: current_work's pwq */ + struct list_head scheduled; /* L: scheduled works */ + struct task_struct *task; /* I: worker task */ + struct worker_pool *pool; /* I: the associated pool */ + /* 64 bytes boundary on 64bit, 32 on 32bit */ + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ + + /* for rebinding worker to CPU */ + struct work_struct rebind_work; /* L: for busy worker */ + + /* used only by rescuers to point to the target workqueue */ + struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ +}; + +/** + * current_wq_worker - return struct worker if %current is a workqueue worker + */ +static inline struct worker *current_wq_worker(void) +{ + if (current->flags & PF_WQ_WORKER) + return kthread_data(current); + return NULL; +} + +/* + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched.c and workqueue.c. + */ +void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); +struct task_struct *wq_worker_sleeping(struct task_struct *task, + unsigned int cpu); + +#endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h deleted file mode 100644 index 2d10fc9..0000000 --- a/kernel/workqueue_sched.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * kernel/workqueue_sched.h - * - * Scheduler hooks for concurrency managed workqueue. Only to be - * included from sched.c and workqueue.c. - */ -void wq_worker_waking_up(struct task_struct *task, unsigned int cpu); -struct task_struct *wq_worker_sleeping(struct task_struct *task, - unsigned int cpu); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 67604e5..a1714c8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -605,61 +605,6 @@ config PROVE_LOCKING For more details, see Documentation/lockdep-design.txt. -config PROVE_RCU - bool "RCU debugging: prove RCU correctness" - depends on PROVE_LOCKING - default n - help - This feature enables lockdep extensions that check for correct - use of RCU APIs. This is currently under development. Say Y - if you want to debug RCU usage or help work on the PROVE_RCU - feature. - - Say N if you are unsure. - -config PROVE_RCU_REPEATEDLY - bool "RCU debugging: don't disable PROVE_RCU on first splat" - depends on PROVE_RCU - default n - help - By itself, PROVE_RCU will disable checking upon issuing the - first warning (or "splat"). This feature prevents such - disabling, allowing multiple RCU-lockdep warnings to be printed - on a single reboot. - - Say Y to allow multiple RCU-lockdep warnings per boot. - - Say N if you are unsure. - -config PROVE_RCU_DELAY - bool "RCU debugging: preemptible RCU race provocation" - depends on DEBUG_KERNEL && PREEMPT_RCU - default n - help - There is a class of races that involve an unlikely preemption - of __rcu_read_unlock() just after ->rcu_read_lock_nesting has - been set to INT_MIN. This feature inserts a delay at that - point to increase the probability of these races. - - Say Y to increase probability of preemption of __rcu_read_unlock(). - - Say N if you are unsure. - -config SPARSE_RCU_POINTER - bool "RCU debugging: sparse-based checks for pointer usage" - default n - help - This feature enables the __rcu sparse annotation for - RCU-protected pointers. This annotation will cause sparse - to flag any non-RCU used of annotated pointers. This can be - helpful when debugging RCU usage. Please note that this feature - is not intended to enforce code cleanliness; it is instead merely - a debugging aid. - - Say Y to make sparse flag questionable use of RCU-protected pointers - - Say N if you are unsure. - config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT @@ -937,6 +882,63 @@ config BOOT_PRINTK_DELAY BOOT_PRINTK_DELAY also may cause LOCKUP_DETECTOR to detect what it believes to be lockup conditions. +menu "RCU Debugging" + +config PROVE_RCU + bool "RCU debugging: prove RCU correctness" + depends on PROVE_LOCKING + default n + help + This feature enables lockdep extensions that check for correct + use of RCU APIs. This is currently under development. Say Y + if you want to debug RCU usage or help work on the PROVE_RCU + feature. + + Say N if you are unsure. + +config PROVE_RCU_REPEATEDLY + bool "RCU debugging: don't disable PROVE_RCU on first splat" + depends on PROVE_RCU + default n + help + By itself, PROVE_RCU will disable checking upon issuing the + first warning (or "splat"). This feature prevents such + disabling, allowing multiple RCU-lockdep warnings to be printed + on a single reboot. + + Say Y to allow multiple RCU-lockdep warnings per boot. + + Say N if you are unsure. + +config PROVE_RCU_DELAY + bool "RCU debugging: preemptible RCU race provocation" + depends on DEBUG_KERNEL && PREEMPT_RCU + default n + help + There is a class of races that involve an unlikely preemption + of __rcu_read_unlock() just after ->rcu_read_lock_nesting has + been set to INT_MIN. This feature inserts a delay at that + point to increase the probability of these races. + + Say Y to increase probability of preemption of __rcu_read_unlock(). + + Say N if you are unsure. + +config SPARSE_RCU_POINTER + bool "RCU debugging: sparse-based checks for pointer usage" + default n + help + This feature enables the __rcu sparse annotation for + RCU-protected pointers. This annotation will cause sparse + to flag any non-RCU used of annotated pointers. This can be + helpful when debugging RCU usage. Please note that this feature + is not intended to enforce code cleanliness; it is instead merely + a debugging aid. + + Say Y to make sparse flag questionable use of RCU-protected pointers + + Say N if you are unsure. + config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL @@ -970,7 +972,7 @@ config RCU_TORTURE_TEST_RUNNABLE config RCU_CPU_STALL_TIMEOUT int "RCU CPU stall timeout in seconds" - depends on TREE_RCU || TREE_PREEMPT_RCU + depends on RCU_STALL_COMMON range 3 300 default 21 help @@ -1008,6 +1010,7 @@ config RCU_CPU_STALL_INFO config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL + select TRACE_CLOCK help This option provides tracing in RCU which presents stats in debugfs for debugging RCU implementation. @@ -1015,6 +1018,8 @@ config RCU_TRACE Say Y here if you want to enable RCU tracing Say N if you are unsure. +endmenu # "RCU Debugging" + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL diff --git a/lib/digsig.c b/lib/digsig.c index 8c0e629..dc2be7e 100644 --- a/lib/digsig.c +++ b/lib/digsig.c @@ -162,6 +162,8 @@ static int digsig_verify_rsa(struct key *key, memset(out1, 0, head); memcpy(out1 + head, p, l); + kfree(p); + err = pkcs_1_v1_5_decode_emsa(out1, len, mblen, out2, &len); if (err) goto err; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6001ee6..b5783d8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1257,6 +1257,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, if (flags & FOLL_WRITE && !pmd_write(*pmd)) goto out; + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) + return ERR_PTR(-EFAULT); + page = pmd_page(*pmd); VM_BUG_ON(!PageHead(page)); if (flags & FOLL_TOUCH) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4f3ea0b..546db81 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3033,6 +3033,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (!huge_pte_none(huge_ptep_get(ptep))) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(pte_modify(pte, newprot)); + pte = arch_make_huge_pte(pte, vma, NULL, 0); set_huge_pte_at(mm, address, ptep, pte); pages++; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09255ec..fbb60b1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3030,7 +3030,9 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; - } + } else + s->memcg_params->is_root_cache = true; + return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index c387786..2fd8b4a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -160,8 +160,10 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE - if (PageHuge(new)) + if (PageHuge(new)) { pte = pte_mkhuge(pte); + pte = arch_make_huge_pte(pte, vma, new, 0); + } #endif flush_cache_page(vma, addr, pte_pfn(pte)); set_pte_at(mm, addr, ptep, pte); @@ -517,11 +517,11 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) static int do_mlockall(int flags) { struct vm_area_struct * vma, * prev = NULL; - unsigned int def_flags = 0; if (flags & MCL_FUTURE) - def_flags = VM_LOCKED; - current->mm->def_flags = def_flags; + current->mm->def_flags |= VM_LOCKED; + else + current->mm->def_flags &= ~VM_LOCKED; if (flags == MCL_FUTURE) goto out; @@ -32,6 +32,7 @@ #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/rbtree_augmented.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -2943,7 +2944,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * vma in this mm is backed by the same anon_vma or address_space. * * We can take all the locks in random order because the VM code - * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never + * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never * takes more than one of them in a row. Secondly we're protected * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. * diff --git a/mm/mremap.c b/mm/mremap.c index e1031e1..f9766f4 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mmu_notifier.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -29,6 +29,7 @@ #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/tlb.h> diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0713bfb..66a0024 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -35,6 +35,7 @@ #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> +#include <linux/sched/rt.h> #include <trace/events/writeback.h> /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df2022f..d1107ad 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -58,6 +58,7 @@ #include <linux/prefetch.h> #include <linux/migrate.h> #include <linux/page-debug-flags.h> +#include <linux/sched/rt.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -773,6 +774,10 @@ void __init init_cma_reserved_pageblock(struct page *page) set_pageblock_migratetype(page, MIGRATE_CMA); __free_pages(page, pageblock_order); totalram_pages += pageblock_nr_pages; +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages += pageblock_nr_pages; +#endif } #endif @@ -4416,10 +4421,11 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, * round what is now in bits to nearest long in bits, then return it in * bytes. */ -static unsigned long __init usemap_size(unsigned long zonesize) +static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) { unsigned long usemapsize; + zonesize += zone_start_pfn & (pageblock_nr_pages-1); usemapsize = roundup(zonesize, pageblock_nr_pages); usemapsize = usemapsize >> pageblock_order; usemapsize *= NR_PAGEBLOCK_BITS; @@ -4429,17 +4435,19 @@ static unsigned long __init usemap_size(unsigned long zonesize) } static void __init setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) + struct zone *zone, + unsigned long zone_start_pfn, + unsigned long zonesize) { - unsigned long usemapsize = usemap_size(zonesize); + unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); zone->pageblock_flags = NULL; if (usemapsize) zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, usemapsize); } #else -static inline void setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) {} +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, + unsigned long zone_start_pfn, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE @@ -4590,7 +4598,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, continue; set_pageblock_order(); - setup_usemap(pgdat, zone, size); + setup_usemap(pgdat, zone, zone_start_pfn, size); ret = init_currently_empty_zone(zone, zone_start_pfn, size, MEMMAP_EARLY); BUG_ON(ret); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 8e1d89d..5539215 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -440,7 +440,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, /* this is an hash collision with the temporary selected node. Choose * the one with the lowest address */ - if ((tmp_max == max) && + if ((tmp_max == max) && max_orig_node && (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0)) goto out; @@ -738,6 +738,7 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, struct arphdr *arphdr; struct ethhdr *ethhdr; __be32 ip_src, ip_dst; + uint8_t *hw_src, *hw_dst; uint16_t type = 0; /* pull the ethernet header */ @@ -777,9 +778,23 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, ip_src = batadv_arp_ip_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); if (ipv4_is_loopback(ip_src) || ipv4_is_multicast(ip_src) || - ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst)) + ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst) || + ipv4_is_zeronet(ip_src) || ipv4_is_lbcast(ip_src) || + ipv4_is_zeronet(ip_dst) || ipv4_is_lbcast(ip_dst)) goto out; + hw_src = batadv_arp_hw_src(skb, hdr_size); + if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src)) + goto out; + + /* we don't care about the destination MAC address in ARP requests */ + if (arphdr->ar_op != htons(ARPOP_REQUEST)) { + hw_dst = batadv_arp_hw_dst(skb, hdr_size); + if (is_zero_ether_addr(hw_dst) || + is_multicast_ether_addr(hw_dst)) + goto out; + } + type = ntohs(arphdr->ar_op); out: return type; @@ -1012,6 +1027,8 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, */ ret = !batadv_is_my_client(bat_priv, hw_dst); out: + if (ret) + kfree_skb(skb); /* if ret == false -> packet has to be delivered to the interface */ return ret; } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 25bfce0..4925a02 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -249,12 +249,12 @@ static void hci_conn_disconnect(struct hci_conn *conn) __u8 reason = hci_proto_disconn_ind(conn); switch (conn->type) { - case ACL_LINK: - hci_acl_disconn(conn, reason); - break; case AMP_LINK: hci_amp_disconn(conn, reason); break; + default: + hci_acl_disconn(conn, reason); + break; } } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 596660d..0f78e34 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2810,14 +2810,6 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF); - hci_dev_lock(hdev); - if (test_bit(HCI_MGMT, &hdev->dev_flags) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, &conn->dst, conn->type, - conn->dst_type, 0, NULL, 0, - conn->dev_class); - hci_dev_unlock(hdev); - /* Send to upper protocol */ l2cap_recv_acldata(conn, skb, flags); return; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 705078a..81b4448 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2688,7 +2688,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (ev->opcode != HCI_OP_NOP) del_timer(&hdev->cmd_timer); - if (ev->ncmd) { + if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) queue_work(hdev->workqueue, &hdev->cmd_work); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index b2bcbe2..a7352ff 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -931,7 +931,7 @@ static int hidp_setup_hid(struct hidp_session *session, hid->version = req->version; hid->country = req->country; - strncpy(hid->name, req->name, 128); + strncpy(hid->name, req->name, sizeof(req->name) - 1); snprintf(hid->phys, sizeof(hid->phys), "%pMR", &bt_sk(session->ctrl_sock->sk)->src); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 2c78208..22e6583 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3727,6 +3727,17 @@ sendresp: static int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) { + struct hci_dev *hdev = conn->hcon->hdev; + struct hci_conn *hcon = conn->hcon; + + hci_dev_lock(hdev); + if (test_bit(HCI_MGMT, &hdev->dev_flags) && + !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) + mgmt_device_connected(hdev, &hcon->dst, hcon->type, + hcon->dst_type, 0, NULL, 0, + hcon->dev_class); + hci_dev_unlock(hdev); + l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0); return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 531a93d..57f250c 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -352,7 +352,7 @@ static void __sco_sock_close(struct sock *sk) case BT_CONNECTED: case BT_CONFIG: - if (sco_pi(sk)->conn) { + if (sco_pi(sk)->conn->hcon) { sk->sk_state = BT_DISCONN; sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); hci_conn_put(sco_pi(sk)->conn->hcon); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 68a9587..5abefb1 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -859,6 +859,19 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(code)); + /* + * The SMP context must be initialized for all other PDUs except + * pairing and security requests. If we get any other PDU when + * not initialized simply disconnect (done if this function + * returns an error). + */ + if (code != SMP_CMD_PAIRING_REQ && code != SMP_CMD_SECURITY_REQ && + !conn->smp_chan) { + BT_ERR("Unexpected SMP command 0x%02x. Disconnecting.", code); + kfree_skb(skb); + return -ENOTSUPP; + } + switch (code) { case SMP_CMD_PAIRING_REQ: reason = smp_cmd_pairing_req(conn, skb); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 7f884e3..8660ea3 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -16,6 +16,7 @@ #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> @@ -40,6 +41,7 @@ static void br_send_bpdu(struct net_bridge_port *p, skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); memcpy(__skb_put(skb, length), data, length); diff --git a/net/core/datagram.c b/net/core/datagram.c index 0337e2b..368f9c3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -187,7 +187,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, skb_queue_walk(queue, skb) { *peeked = skb->peeked; if (flags & MSG_PEEK) { - if (*off >= skb->len) { + if (*off >= skb->len && skb->len) { *off -= skb->len; continue; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b29dacf..e6e1cbe 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1781,10 +1781,13 @@ static ssize_t pktgen_thread_write(struct file *file, return -EFAULT; i += len; mutex_lock(&pktgen_thread_lock); - pktgen_add_device(t, f); + ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c31d9e8..4425148 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -186,8 +186,6 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, struct fastopen_queue *fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; - BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk)); - tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; diff --git a/net/core/scm.c b/net/core/scm.c index 57fb1ee..905dcc6 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -35,6 +35,7 @@ #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> +#include <net/cls_cgroup.h> /* @@ -302,8 +303,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } /* Bump the usage count and install the file. */ sock = sock_from_file(fp[i], &err); - if (sock) + if (sock) { sock_update_netprioidx(sock->sk, current); + sock_update_classid(sock->sk, current); + } fd_install(new_fd, get_file(fp[i])); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ab989b..32443eb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -683,7 +683,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->network_header = old->network_header; new->mac_header = old->mac_header; new->inner_transport_header = old->inner_transport_header; - new->inner_network_header = old->inner_transport_header; + new->inner_network_header = old->inner_network_header; skb_dst_copy(new, old); new->rxhash = old->rxhash; new->ooo_okay = old->ooo_okay; @@ -1649,7 +1649,7 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); @@ -1682,14 +1682,14 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd, static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, bool linear, + bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { - page = linear_to_page(page, len, &offset, skb, sk); + page = linear_to_page(page, len, &offset, sk); if (!page) return true; } @@ -1706,23 +1706,9 @@ static bool spd_fill_page(struct splice_pipe_desc *spd, return false; } -static inline void __segment_seek(struct page **page, unsigned int *poff, - unsigned int *plen, unsigned int off) -{ - unsigned long n; - - *poff += off; - n = *poff / PAGE_SIZE; - if (n) - *page = nth_page(*page, n); - - *poff = *poff % PAGE_SIZE; - *plen -= off; -} - static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, + unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) @@ -1737,23 +1723,19 @@ static bool __splice_segment(struct page *page, unsigned int poff, } /* ignore any bits we already processed */ - if (*off) { - __segment_seek(&page, &poff, &plen, *off); - *off = 0; - } + poff += *off; + plen -= *off; + *off = 0; do { unsigned int flen = min(*len, plen); - /* the linear region may spread across several pages */ - flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) return true; - - __segment_seek(&page, &poff, &plen, flen); + poff += flen; + plen -= flen; *len -= flen; - } while (*len && plen); return false; @@ -1777,7 +1759,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, + offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; @@ -1790,7 +1772,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, false, sk, pipe)) + offset, len, spd, false, sk, pipe)) return true; } diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a0d8392..a69b4e4 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -269,7 +269,11 @@ static void ah_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -381,7 +385,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr; @@ -413,9 +420,12 @@ static void ah4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9547a273..ded146b 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -928,24 +928,25 @@ static void parp_redo(struct sk_buff *skb) static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct arphdr *arp; + const struct arphdr *arp; + + if (dev->flags & IFF_NOARP || + skb->pkt_type == PACKET_OTHERHOST || + skb->pkt_type == PACKET_LOOPBACK) + goto freeskb; + + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ if (!pskb_may_pull(skb, arp_hdr_len(dev))) goto freeskb; arp = arp_hdr(skb); - if (arp->ar_hln != dev->addr_len || - dev->flags & IFF_NOARP || - skb->pkt_type == PACKET_OTHERHOST || - skb->pkt_type == PACKET_LOOPBACK || - arp->ar_pln != 4) + if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) goto freeskb; - skb = skb_share_check(skb, GFP_ATOMIC); - if (skb == NULL) - goto out_of_mem; - memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 424fafb..b28e863 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -85,3 +85,28 @@ out: return err; } EXPORT_SYMBOL(ip4_datagram_connect); + +void ip4_datagram_release_cb(struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; + struct flowi4 fl4; + struct rtable *rt; + + if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) + return; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_protocol, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + if (!IS_ERR(rt)) + __sk_dst_set(sk, &rt->dst); + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b61e9de..3b4f0cd 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -346,7 +346,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr[1]; @@ -499,9 +502,12 @@ static void esp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 303012a..e81b1ca 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -963,8 +963,12 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev ptr--; } if (tunnel->parms.o_flags&GRE_CSUM) { + int offset = skb_transport_offset(skb); + *ptr = 0; - *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, + skb->len - offset, + 0)); } } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index d3ab47e..9a46dae 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -47,9 +47,12 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8f3d054..6f9c072 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -738,6 +738,7 @@ struct proto ping_prot = { .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = ping_v4_hash, .unhash = ping_v4_unhash, .get_port = ping_v4_get_port, diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 73d1e4d..6f08991 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -894,6 +894,7 @@ struct proto raw_prot = { .recvmsg = raw_recvmsg, .bind = raw_bind, .backlog_rcv = raw_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw_sock), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 844a9ef..a0fcc47 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -912,6 +912,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct dst_entry *dst = &rt->dst; struct fib_result res; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + if (dst->dev->mtu < mtu) return; @@ -962,7 +965,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; @@ -975,6 +978,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) ip_rt_put(rt); } } + +void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; + struct dst_entry *dst; + bool new = false; + + bh_lock_sock(sk); + rt = (struct rtable *) __sk_dst_get(sk); + + if (sock_owned_by_user(sk) || !rt) { + __ipv4_sk_update_pmtu(skb, sk, mtu); + goto out; + } + + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + + if (!__sk_dst_check(sk, 0)) { + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); + + dst = dst_check(&rt->dst, 0); + if (!dst) { + if (new) + dst_release(&rt->dst); + + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + if (new) + __sk_dst_set(sk, &rt->dst); + +out: + bh_unlock_sock(sk); +} EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, @@ -1120,7 +1170,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu && rt_is_output_route(rt)) + if (mtu) return mtu; mtu = dst->dev->mtu; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 291f2ed..cdf2e70 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -310,6 +310,12 @@ void tcp_slow_start(struct tcp_sock *tp) { int cnt; /* increase in packets */ unsigned int delta = 0; + u32 snd_cwnd = tp->snd_cwnd; + + if (unlikely(!snd_cwnd)) { + pr_err_once("snd_cwnd is nul, please report this bug.\n"); + snd_cwnd = 1U; + } /* RFC3465: ABC Slow start * Increase only after a full MSS of bytes is acked @@ -324,7 +330,7 @@ void tcp_slow_start(struct tcp_sock *tp) if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh) cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */ else - cnt = tp->snd_cwnd; /* exponential increase */ + cnt = snd_cwnd; /* exponential increase */ /* RFC3465: ABC * We MAY increase by 2 if discovered delayed ack @@ -334,11 +340,11 @@ void tcp_slow_start(struct tcp_sock *tp) tp->bytes_acked = 0; tp->snd_cwnd_cnt += cnt; - while (tp->snd_cwnd_cnt >= tp->snd_cwnd) { - tp->snd_cwnd_cnt -= tp->snd_cwnd; + while (tp->snd_cwnd_cnt >= snd_cwnd) { + tp->snd_cwnd_cnt -= snd_cwnd; delta++; } - tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp); + tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_slow_start); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 18f97ca..ad70a96 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3504,6 +3504,11 @@ static bool tcp_process_frto(struct sock *sk, int flag) } } else { if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { + if (!tcp_packets_in_flight(tp)) { + tcp_enter_frto_loss(sk, 2, flag); + return true; + } + /* Prevent sending of new data. */ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)); @@ -5649,8 +5654,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, * the remote receives only the retransmitted (regular) SYNs: either * the original SYN-data or the corresponding SYN-ACK is lost. */ - syn_drop = (cookie->len <= 0 && data && - inet_csk(sk)->icsk_retransmits); + syn_drop = (cookie->len <= 0 && data && tp->total_retrans); tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 54139fa..eadb693 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -369,11 +369,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk) && - type != ICMP_DEST_UNREACH && - code != ICMP_FRAG_NEEDED) - NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out; @@ -497,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -1501,8 +1501,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * clogging syn queue with openreqs with exponentially increasing * timeout. */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) @@ -1667,6 +1669,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 79c8dbe..1f4d405 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1952,6 +1952,7 @@ struct proto udp_prot = { .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 420e563..1b5d8cb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1660,6 +1660,7 @@ static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) if (dev->addr_len != IEEE802154_ADDR_LEN) return -1; memcpy(eui, dev->dev_addr, 8); + eui[0] ^= 2; return 0; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index ecc35b9..3842331 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -472,7 +472,10 @@ static void ah6_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); __skb_pull(skb, ah_hlen + hdr_len); - skb_set_transport_header(skb, -hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -593,9 +596,13 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); - skb->transport_header = skb->network_header; __skb_pull(skb, ah_hlen + hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); + err = nexthdr; out_free: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 8edf260..7a778b9 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -380,7 +380,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { @@ -468,7 +468,8 @@ out: } -int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) +int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_skb_parm *opt = IP6CB(skb); @@ -597,11 +598,12 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } return 0; } +EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); -int datagram_send_ctl(struct net *net, struct sock *sk, - struct msghdr *msg, struct flowi6 *fl6, - struct ipv6_txoptions *opt, - int *hlimit, int *tclass, int *dontfrag) +int ip6_datagram_send_ctl(struct net *net, struct sock *sk, + struct msghdr *msg, struct flowi6 *fl6, + struct ipv6_txoptions *opt, + int *hlimit, int *tclass, int *dontfrag) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -871,4 +873,4 @@ int datagram_send_ctl(struct net *net, struct sock *sk, exit_f: return err; } -EXPORT_SYMBOL_GPL(datagram_send_ctl); +EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 282f372..40ffd72 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -300,7 +300,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); err = nexthdr[1]; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index b4a9fd5..fff5bdd 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -81,10 +81,22 @@ static inline struct sock *icmpv6_sk(struct net *net) return net->ipv6.icmp_sk[smp_processor_id()]; } +static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct net *net = dev_net(skb->dev); + + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, 0, 0); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); +} + static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, + .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 29124b7..d6de4b4 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -365,8 +365,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, msg.msg_control = (void*)(fl->opt+1); memset(&flowi6, 0, sizeof(flowi6)); - err = datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, &junk, - &junk, &junk); + err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, + &junk, &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c727e47..131dd09 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -960,7 +960,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, int ret; if (!ip6_tnl_xmit_ctl(t)) - return -1; + goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5552d13..0c7c03d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1213,10 +1213,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; - exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; - dst_exthdrlen = rt->dst.header_len; + dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 26dcdec..8fd154e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1710,6 +1710,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -EINVAL; if (get_user(v, (u32 __user *)optval)) return -EFAULT; + /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (v != RT_TABLE_DEFAULT && v >= 100000000) + return -EINVAL; if (sk == mrt->mroute6_sk) return -EBUSY; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ee94d31..d1e2e8e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -476,8 +476,8 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, &junk, - &junk); + retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, + &junk, &junk); if (retv) goto done; update: @@ -1002,7 +1002,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, release_sock(sk); if (skb) { - int err = datagram_recv_ctl(sk, &msg, skb); + int err = ip6_datagram_recv_ctl(sk, &msg, skb); kfree_skb(skb); if (err) return err; diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index 7302b0b..83acc14 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> +#include <net/ipv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6t_NPT.h> @@ -18,11 +19,20 @@ static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) { struct ip6t_npt_tginfo *npt = par->targinfo; __wsum src_sum = 0, dst_sum = 0; + struct in6_addr pfx; unsigned int i; if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) return -EINVAL; + /* Ensure that LSB of prefix is zero */ + ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6)) + return -EINVAL; + ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6)) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) { src_sum = csum_add(src_sum, (__force __wsum)npt->src_pfx.in6.s6_addr16[i]); @@ -30,7 +40,7 @@ static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) (__force __wsum)npt->dst_pfx.in6.s6_addr16[i]); } - npt->adjustment = (__force __sum16) csum_sub(src_sum, dst_sum); + npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum)); return 0; } @@ -51,7 +61,7 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, idx = i / 32; addr->s6_addr32[idx] &= mask; - addr->s6_addr32[idx] |= npt->dst_pfx.in6.s6_addr32[idx]; + addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx]; } if (pfx_len <= 48) @@ -66,8 +76,8 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, return false; } - sum = (__force __sum16) csum_add((__force __wsum)addr->s6_addr16[idx], - npt->adjustment); + sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]), + csum_unfold(npt->adjustment))); if (sum == CSUM_MANGLED_0) sum = 0; *(__force __sum16 *)&addr->s6_addr16[idx] = sum; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 6cd29b1..70fa814 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -507,7 +507,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) @@ -822,8 +822,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e229a3b..363d8b7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -928,7 +928,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!rt->n && !(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_LOCAL))) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 93825dd..4f435371 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -423,6 +423,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -958,8 +959,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop; } - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) @@ -1108,6 +1111,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index dfaa29b..fb08329 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -443,7 +443,7 @@ try_again: ip_cmsg_recv(msg, skb); } else { if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); } err = copied; @@ -1153,8 +1153,8 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 1a9f372..2ac884d 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -168,6 +168,51 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } +/* Lookup the tunnel socket, possibly involving the fs code if the socket is + * owned by userspace. A struct sock returned from this function must be + * released using l2tp_tunnel_sock_put once you're done with it. + */ +struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) +{ + int err = 0; + struct socket *sock = NULL; + struct sock *sk = NULL; + + if (!tunnel) + goto out; + + if (tunnel->fd >= 0) { + /* Socket is owned by userspace, who might be in the process + * of closing it. Look the socket up using the fd to ensure + * consistency. + */ + sock = sockfd_lookup(tunnel->fd, &err); + if (sock) + sk = sock->sk; + } else { + /* Socket is owned by kernelspace */ + sk = tunnel->sock; + } + +out: + return sk; +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup); + +/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ +void l2tp_tunnel_sock_put(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + if (tunnel) { + if (tunnel->fd >= 0) { + /* Socket is owned by userspace */ + sockfd_put(sk->sk_socket); + } + sock_put(sk); + } +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); + /* Lookup a session by id in the global session list */ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id) @@ -1123,8 +1168,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len struct udphdr *uh; struct inet_sock *inet; __wsum csum; - int old_headroom; - int new_headroom; int headroom; int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; int udp_len; @@ -1136,16 +1179,12 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len */ headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + hdr_len; - old_headroom = skb_headroom(skb); if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } - new_headroom = skb_headroom(skb); skb_orphan(skb); - skb->truesize += new_headroom - old_headroom; - /* Setup L2TP header */ session->build_header(session, __skb_push(skb, hdr_len)); @@ -1607,6 +1646,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; tunnel->sock = sk; + tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; @@ -1642,24 +1682,32 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); */ int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { - int err = 0; - struct socket *sock = tunnel->sock ? tunnel->sock->sk_socket : NULL; + int err = -EBADF; + struct socket *sock = NULL; + struct sock *sk = NULL; + + sk = l2tp_tunnel_sock_lookup(tunnel); + if (!sk) + goto out; + + sock = sk->sk_socket; + BUG_ON(!sock); /* Force the tunnel socket to close. This will eventually * cause the tunnel to be deleted via the normal socket close * mechanisms when userspace closes the tunnel socket. */ - if (sock != NULL) { - err = inet_shutdown(sock, 2); + err = inet_shutdown(sock, 2); - /* If the tunnel's socket was created by the kernel, - * close the socket here since the socket was not - * created by userspace. - */ - if (sock->file == NULL) - err = inet_release(sock); - } + /* If the tunnel's socket was created by the kernel, + * close the socket here since the socket was not + * created by userspace. + */ + if (sock->file == NULL) + err = inet_release(sock); + l2tp_tunnel_sock_put(sk); +out: return err; } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 56d583e..e62204c 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -188,7 +188,8 @@ struct l2tp_tunnel { int (*recv_payload_hook)(struct sk_buff *skb); void (*old_sk_destruct)(struct sock *); struct sock *sock; /* Parent socket */ - int fd; + int fd; /* Parent fd, if tunnel socket + * was created by userspace */ uint8_t priv[0]; /* private data */ }; @@ -228,6 +229,8 @@ out: return tunnel; } +extern struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel); +extern void l2tp_tunnel_sock_put(struct sock *sk); extern struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth); extern struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9275471..8ee4a86 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -554,8 +554,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -646,7 +646,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { - struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name; size_t copied = 0; int err = -EOPNOTSUPP; @@ -688,8 +688,8 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, lsa->l2tp_scope_id = IP6CB(skb)->iif; } - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + if (np->rxopt.all) + ip6_datagram_recv_ctl(sk, msg, skb); if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 286366e..716605c 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -388,8 +388,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel; struct pppol2tp_session *ps; - int old_headroom; - int new_headroom; int uhlen, headroom; if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) @@ -408,7 +406,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (tunnel == NULL) goto abort_put_sess; - old_headroom = skb_headroom(skb); uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; headroom = NET_SKB_PAD + sizeof(struct iphdr) + /* IP header */ @@ -418,9 +415,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (skb_cow_head(skb, headroom)) goto abort_put_sess_tun; - new_headroom = skb_headroom(skb); - skb->truesize += new_headroom - old_headroom; - /* Setup PPP header */ __skb_push(skb, sizeof(ppph)); skb->data[0] = ppph[0]; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 47e0aca..0479c64 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -164,7 +164,17 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, sta = sta_info_get(sdata, mac_addr); else sta = sta_info_get_bss(sdata, mac_addr); - if (!sta) { + /* + * The ASSOC test makes sure the driver is ready to + * receive the key. When wpa_supplicant has roamed + * using FT, it attempts to set the key before + * association has completed, this rejects that attempt + * so it will set the key again after assocation. + * + * TODO: accept the key if we have a station entry and + * add it to the device after the station. + */ + if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) { ieee80211_key_free(sdata->local, key); err = -ENOENT; goto out_unlock; @@ -1994,7 +2004,8 @@ static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(rate)); + memcpy(sdata->vif.bss_conf.mcast_rate, rate, + sizeof(int) * IEEE80211_NUM_BANDS); return 0; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8563b9a..2ed065c 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1358,10 +1358,8 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata); void ieee80211_sched_scan_stopped_work(struct work_struct *work); /* off-channel helpers */ -void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, - bool offchannel_ps_enable); -void ieee80211_offchannel_return(struct ieee80211_local *local, - bool offchannel_ps_disable); +void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local); +void ieee80211_offchannel_return(struct ieee80211_local *local); void ieee80211_roc_setup(struct ieee80211_local *local); void ieee80211_start_next_roc(struct ieee80211_local *local); void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 47aeee2..2659e42 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -215,6 +215,7 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata, skb->priority = 7; info->control.vif = &sdata->vif; + info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING; ieee80211_set_qos_hdr(sdata, skb); } @@ -246,11 +247,13 @@ int mesh_path_error_tx(u8 ttl, u8 *target, __le32 target_sn, return -EAGAIN; skb = dev_alloc_skb(local->tx_headroom + + IEEE80211_ENCRYPT_HEADROOM + + IEEE80211_ENCRYPT_TAILROOM + hdr_len + 2 + 15 /* PERR IE */); if (!skb) return -1; - skb_reserve(skb, local->tx_headroom); + skb_reserve(skb, local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM); mgmt = (struct ieee80211_mgmt *) skb_put(skb, hdr_len); memset(mgmt, 0, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a355292..5107248 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3400,6 +3400,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = 0; +out: while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, IEEE80211_CHAN_DISABLED)) { if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) { @@ -3408,14 +3409,13 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, goto out; } - ret = chandef_downgrade(chandef); + ret |= chandef_downgrade(chandef); } if (chandef->width != vht_chandef.width) sdata_info(sdata, - "local regulatory prevented using AP HT/VHT configuration, downgraded\n"); + "capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n"); -out: WARN_ON_ONCE(!cfg80211_chandef_valid(chandef)); return ret; } @@ -3529,8 +3529,11 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, */ ret = ieee80211_vif_use_channel(sdata, &chandef, IEEE80211_CHANCTX_SHARED); - while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) + while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) { ifmgd->flags |= chandef_downgrade(&chandef); + ret = ieee80211_vif_use_channel(sdata, &chandef, + IEEE80211_CHANCTX_SHARED); + } return ret; } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index a5379ae..a3ad4c3 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -102,8 +102,7 @@ static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata) ieee80211_sta_reset_conn_monitor(sdata); } -void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, - bool offchannel_ps_enable) +void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; @@ -134,8 +133,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { netif_tx_stop_all_queues(sdata->dev); - if (offchannel_ps_enable && - (sdata->vif.type == NL80211_IFTYPE_STATION) && + if (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.associated) ieee80211_offchannel_ps_enable(sdata); } @@ -143,8 +141,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local, mutex_unlock(&local->iflist_mtx); } -void ieee80211_offchannel_return(struct ieee80211_local *local, - bool offchannel_ps_disable) +void ieee80211_offchannel_return(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; @@ -163,11 +160,9 @@ void ieee80211_offchannel_return(struct ieee80211_local *local, continue; /* Tell AP we're back */ - if (offchannel_ps_disable && - sdata->vif.type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.associated) - ieee80211_offchannel_ps_disable(sdata); - } + if (sdata->vif.type == NL80211_IFTYPE_STATION && + sdata->u.mgd.associated) + ieee80211_offchannel_ps_disable(sdata); if (sdata->vif.type != NL80211_IFTYPE_MONITOR) { /* @@ -385,7 +380,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) local->tmp_channel = NULL; ieee80211_hw_config(local, 0); - ieee80211_offchannel_return(local, true); + ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d59fc68..bf82e69 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -292,7 +292,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted, if (!was_hw_scan) { ieee80211_configure_filter(local); drv_sw_scan_complete(local); - ieee80211_offchannel_return(local, true); + ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); @@ -341,7 +341,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local) local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; - ieee80211_offchannel_stop_vifs(local, true); + ieee80211_offchannel_stop_vifs(local); ieee80211_configure_filter(local); @@ -678,12 +678,8 @@ static void ieee80211_scan_state_suspend(struct ieee80211_local *local, local->scan_channel = NULL; ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - /* - * Re-enable vifs and beaconing. Leave PS - * in off-channel state..will put that back - * on-channel at the end of scanning. - */ - ieee80211_offchannel_return(local, false); + /* disable PS */ + ieee80211_offchannel_return(local); *next_delay = HZ / 5; /* afterwards, resume scan & go to next channel */ @@ -693,8 +689,7 @@ static void ieee80211_scan_state_suspend(struct ieee80211_local *local, static void ieee80211_scan_state_resume(struct ieee80211_local *local, unsigned long *next_delay) { - /* PS already is in off-channel mode */ - ieee80211_offchannel_stop_vifs(local, false); + ieee80211_offchannel_stop_vifs(local); if (local->ops->flush) { drv_flush(local, false); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index e9eadc4..467c1d1 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1673,10 +1673,13 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, chanctx_conf = rcu_dereference(tmp_sdata->vif.chanctx_conf); } - if (!chanctx_conf) - goto fail_rcu; - chan = chanctx_conf->def.chan; + if (chanctx_conf) + chan = chanctx_conf->def.chan; + else if (!local->use_chanctx) + chan = local->_oper_channel; + else + goto fail_rcu; /* * Frame injection is not allowed if beaconing is not allowed diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 746048b..ae8ec6f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -61,14 +61,27 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, return 1; } +static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, + unsigned int sctphoff) +{ + __u32 crc32; + struct sk_buff *iter; + + crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff); + skb_walk_frags(skb, iter) + crc32 = sctp_update_cksum((u8 *) iter->data, + skb_headlen(iter), crc32); + sctph->checksum = sctp_end_cksum(crc32); + + skb->ip_summed = CHECKSUM_UNNECESSARY; +} + static int sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { sctp_sctphdr_t *sctph; unsigned int sctphoff = iph->len; - struct sk_buff *iter; - __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -92,13 +105,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, sctph = (void *) skb_network_header(skb) + sctphoff; sctph->source = cp->vport; - /* Calculate the checksum */ - crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), - crc32); - crc32 = sctp_end_cksum(crc32); - sctph->checksum = crc32; + sctp_nat_csum(skb, sctph, sctphoff); return 1; } @@ -109,8 +116,6 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { sctp_sctphdr_t *sctph; unsigned int sctphoff = iph->len; - struct sk_buff *iter; - __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -134,13 +139,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, sctph = (void *) skb_network_header(skb) + sctphoff; sctph->dest = cp->dport; - /* Calculate the checksum */ - crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), - crc32); - crc32 = sctp_end_cksum(crc32); - sctph->checksum = crc32; + sctp_nat_csum(skb, sctph, sctphoff); return 1; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index effa10c..44fd10c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1795,6 +1795,8 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) GFP_KERNEL); if (!tinfo->buf) goto outtinfo; + } else { + tinfo->buf = NULL; } tinfo->id = id; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 016d95e..e4a0c4f 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1376,11 +1376,12 @@ void nf_conntrack_cleanup(struct net *net) synchronize_net(); nf_conntrack_proto_fini(net); nf_conntrack_cleanup_net(net); +} - if (net_eq(net, &init_net)) { - RCU_INIT_POINTER(nf_ct_destroy, NULL); - nf_conntrack_cleanup_init_net(); - } +void nf_conntrack_cleanup_end(void) +{ + RCU_INIT_POINTER(nf_ct_destroy, NULL); + nf_conntrack_cleanup_init_net(); } void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 363285d..e7185c6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -575,6 +575,7 @@ static int __init nf_conntrack_standalone_init(void) static void __exit nf_conntrack_standalone_fini(void) { unregister_pernet_subsys(&nf_conntrack_net_ops); + nf_conntrack_cleanup_end(); } module_init(nf_conntrack_standalone_init); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8d987c3..7b3a9e5 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -345,19 +345,27 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); -static char *textify_hooks(char *buf, size_t size, unsigned int mask) +static char * +textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { - static const char *const names[] = { + static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; - unsigned int i; + static const char *const arp_names[] = { + "INPUT", "FORWARD", "OUTPUT", + }; + const char *const *names; + unsigned int i, max; char *p = buf; bool np = false; int res; + names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; + max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : + ARRAY_SIZE(inetbr_names); *p = '\0'; - for (i = 0; i < ARRAY_SIZE(names); ++i) { + for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); @@ -402,8 +410,10 @@ int xt_check_match(struct xt_mtchk_param *par, pr_err("%s_tables: %s match: used from hooks %s, but only " "valid from %s\n", xt_prefix[par->family], par->match->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->match->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->match->hooks, + par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { @@ -575,8 +585,10 @@ int xt_check_target(struct xt_tgchk_param *par, pr_err("%s_tables: %s target: used from hooks %s, but only " "usable from %s\n", xt_prefix[par->family], par->target->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->target->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->target->hooks, + par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 2a08430..bde009e 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -109,7 +109,7 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) struct xt_ct_target_info *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; + int ret = -EOPNOTSUPP; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -247,7 +247,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) struct xt_ct_target_info_v1 *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; + int ret = -EOPNOTSUPP; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index a9327e2..670cbc3 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -35,10 +35,11 @@ /* Must be called with rcu_read_lock. */ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) { - if (unlikely(!vport)) { - kfree_skb(skb); - return; - } + if (unlikely(!vport)) + goto error; + + if (unlikely(skb_warn_if_lro(skb))) + goto error; /* Make our own copy of the packet. Otherwise we will mangle the * packet for anyone who came before us (e.g. tcpdump via AF_PACKET). @@ -50,6 +51,10 @@ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) skb_push(skb, ETH_HLEN); ovs_vport_receive(vport, skb); + return; + +error: + kfree_skb(skb); } /* Called with rcu_read_lock and bottom-halves disabled. */ @@ -169,9 +174,6 @@ static int netdev_send(struct vport *vport, struct sk_buff *skb) goto error; } - if (unlikely(skb_warn_if_lro(skb))) - goto error; - skb->dev = netdev_vport->dev; len = skb->len; dev_queue_xmit(skb); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e639645..c111bd0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2361,13 +2361,15 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); - memset(&req_u, 0, sizeof(req_u)); - - if (po->rx_ring.pg_vec) + if (po->rx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); + } - if (po->tx_ring.pg_vec) + if (po->tx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); + } fanout_release(sk); diff --git a/net/rfkill/input.c b/net/rfkill/input.c index c9d931e..b85107b 100644 --- a/net/rfkill/input.c +++ b/net/rfkill/input.c @@ -148,11 +148,9 @@ static unsigned long rfkill_ratelimit(const unsigned long last) static void rfkill_schedule_ratelimited(void) { - if (delayed_work_pending(&rfkill_op_work)) - return; - schedule_delayed_work(&rfkill_op_work, - rfkill_ratelimit(rfkill_last_scheduled)); - rfkill_last_scheduled = jiffies; + if (schedule_delayed_work(&rfkill_op_work, + rfkill_ratelimit(rfkill_last_scheduled))) + rfkill_last_scheduled = jiffies; } static void rfkill_schedule_global_op(enum rfkill_sched_op op) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 51561ea..79e8ed4 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1135,9 +1135,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, memset(&opt, 0, sizeof(opt)); opt.rate.rate = cl->rate.rate_bps >> 3; - opt.buffer = cl->buffer; + opt.buffer = PSCHED_NS2TICKS(cl->buffer); opt.ceil.rate = cl->ceil.rate_bps >> 3; - opt.cbuffer = cl->cbuffer; + opt.cbuffer = PSCHED_NS2TICKS(cl->cbuffer); opt.quantum = cl->quantum; opt.prio = cl->prio; opt.level = cl->level; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 298c0dd..3d2acc7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -438,18 +438,18 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (q->rate) { struct sk_buff_head *list = &sch->q; - delay += packet_len_2_sched_time(skb->len, q); - if (!skb_queue_empty(list)) { /* - * Last packet in queue is reference point (now). - * First packet in queue is already in flight, - * calculate this time bonus and substract + * Last packet in queue is reference point (now), + * calculate this time bonus and subtract * from delay. */ - delay -= now - netem_skb_cb(skb_peek(list))->time_to_send; + delay -= netem_skb_cb(skb_peek_tail(list))->time_to_send - now; + delay = max_t(psched_tdiff_t, 0, delay); now = netem_skb_cb(skb_peek_tail(list))->time_to_send; } + + delay += packet_len_2_sched_time(skb->len, q); } cb->time_to_send = now + delay; diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index 7521d94..cf48528 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -3,8 +3,8 @@ # menuconfig IP_SCTP - tristate "The SCTP Protocol (EXPERIMENTAL)" - depends on INET && EXPERIMENTAL + tristate "The SCTP Protocol" + depends on INET depends on IPV6 || IPV6=n select CRYPTO select CRYPTO_HMAC diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 159b9bc..d8420ae 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -71,7 +71,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key) return; if (atomic_dec_and_test(&key->refcnt)) { - kfree(key); + kzfree(key); SCTP_DBG_OBJCNT_DEC(keys); } } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 17a001b..1a9c5fb 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -249,6 +249,8 @@ void sctp_endpoint_free(struct sctp_endpoint *ep) /* Final destructor for endpoint. */ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) { + int i; + SCTP_ASSERT(ep->base.dead, "Endpoint is not dead", return); /* Free up the HMAC transform. */ @@ -271,6 +273,9 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) sctp_inq_free(&ep->base.inqueue); sctp_bind_addr_free(&ep->base.bind_addr); + for (i = 0; i < SCTP_HOW_MANY_SECRETS; ++i) + memset(&ep->secret_key[i], 0, SCTP_SECRET_SIZE); + /* Remove and free the port */ if (sctp_sk(ep->base.sk)->bind_hash) sctp_put_port(ep->base.sk); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index f3f0f4d..391a245 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -326,9 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid && laddr->state != SCTP_ADDR_SRC) + if (!laddr->valid) continue; - if ((laddr->a.sa.sa_family == AF_INET6) && + if ((laddr->state == SCTP_ADDR_SRC) && + (laddr->a.sa.sa_family == AF_INET6) && (scope <= sctp_scope(&laddr->a))) { bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); if (!baddr || (matchlen < bmatchlen)) { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 379c81d..9bcdbd0 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -224,7 +224,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) /* Free the outqueue structure and any related pending chunks. */ -void sctp_outq_teardown(struct sctp_outq *q) +static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; @@ -277,8 +277,6 @@ void sctp_outq_teardown(struct sctp_outq *q) sctp_chunk_free(chunk); } - q->error = 0; - /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); @@ -286,11 +284,17 @@ void sctp_outq_teardown(struct sctp_outq *q) } } +void sctp_outq_teardown(struct sctp_outq *q) +{ + __sctp_outq_teardown(q); + sctp_outq_init(q->asoc, q); +} + /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ - sctp_outq_teardown(q); + __sctp_outq_teardown(q); /* If we were kmalloc()'d, free the memory. */ if (q->malloced) diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 618ec7e..5131fcf 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1779,8 +1779,10 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return SCTP_DISPOSITION_CONSUME; nomem_ev: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e65758..cedd9bf 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3390,7 +3390,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey); out: - kfree(authkey); + kzfree(authkey); return ret; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 043889a..bf3c6e8 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -366,7 +366,11 @@ int sctp_sysctl_net_register(struct net *net) void sctp_sysctl_net_unregister(struct net *net) { + struct ctl_table *table; + + table = net->sctp.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->sctp.sysctl_header); + kfree(table); } static struct ctl_table_header * sctp_sysctl_header; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index bfa3171..fb20f25 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -98,9 +98,25 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task) list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list); } +static void rpc_rotate_queue_owner(struct rpc_wait_queue *queue) +{ + struct list_head *q = &queue->tasks[queue->priority]; + struct rpc_task *task; + + if (!list_empty(q)) { + task = list_first_entry(q, struct rpc_task, u.tk_wait.list); + if (task->tk_owner == queue->owner) + list_move_tail(&task->u.tk_wait.list, q); + } +} + static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority) { - queue->priority = priority; + if (queue->priority != priority) { + /* Fairness: rotate the list when changing priority */ + rpc_rotate_queue_owner(queue); + queue->priority = priority; + } } static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 0a148c9..0f679df 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -465,7 +465,7 @@ static int svc_udp_get_dest_address4(struct svc_rqst *rqstp, } /* - * See net/ipv6/datagram.c : datagram_recv_ctl + * See net/ipv6/datagram.c : ip6_datagram_recv_ctl */ static int svc_udp_get_dest_address6(struct svc_rqst *rqstp, struct cmsghdr *cmh) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 01592d7..45f1618 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1358,7 +1358,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, &iwe, IW_EV_UINT_LEN); } - buf = kmalloc(30, GFP_ATOMIC); + buf = kmalloc(31, GFP_ATOMIC); if (buf) { memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVCUSTOM; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 41eabc4..07c5857 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2656,7 +2656,7 @@ static void xfrm_policy_fini(struct net *net) WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); htab = &net->xfrm.policy_bydst[dir]; - sz = (htab->hmask + 1); + sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(htab->table)); xfrm_hash_free(htab->table, sz); } diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 765f6fe..35754cc 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -242,11 +242,13 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) u32 diff; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; u32 seq = ntohl(net_seq); - u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window; + u32 pos; if (!replay_esn->replay_window) return; + pos = (replay_esn->seq - 1) % replay_esn->replay_window; + if (seq > replay_esn->seq) { diff = seq - replay_esn->seq; diff --git a/samples/Kconfig b/samples/Kconfig index 7b6792a..6181c2c 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -5,12 +5,6 @@ menuconfig SAMPLES if SAMPLES -config SAMPLE_TRACEPOINTS - tristate "Build tracepoints examples -- loadable modules only" - depends on TRACEPOINTS && m - help - This build tracepoints example modules. - config SAMPLE_TRACE_EVENTS tristate "Build trace_events examples -- loadable modules only" depends on EVENT_TRACING && m diff --git a/samples/Makefile b/samples/Makefile index 5ef08bb..1a60c62 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -1,4 +1,4 @@ # Makefile for Linux samples code -obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ tracepoints/ trace_events/ \ +obj-$(CONFIG_SAMPLES) += kobject/ kprobes/ trace_events/ \ hw_breakpoint/ kfifo/ kdb/ hidraw/ rpmsg/ seccomp/ diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile index bbbd276..7203e66 100644 --- a/samples/seccomp/Makefile +++ b/samples/seccomp/Makefile @@ -19,6 +19,7 @@ bpf-direct-objs := bpf-direct.o # Try to match the kernel target. ifndef CONFIG_64BIT +ifndef CROSS_COMPILE # s390 has -m31 flag to build 31 bit binaries ifndef CONFIG_S390 @@ -35,6 +36,7 @@ HOSTLOADLIBES_bpf-direct += $(MFLAG) HOSTLOADLIBES_bpf-fancy += $(MFLAG) HOSTLOADLIBES_dropper += $(MFLAG) endif +endif # Tell kbuild to always build the programs always := $(hostprogs-y) diff --git a/samples/tracepoints/Makefile b/samples/tracepoints/Makefile deleted file mode 100644 index 36479ad..0000000 --- a/samples/tracepoints/Makefile +++ /dev/null @@ -1,6 +0,0 @@ -# builds the tracepoint example kernel modules; -# then to use one (as root): insmod <module_name.ko> - -obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-sample.o -obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-probe-sample.o -obj-$(CONFIG_SAMPLE_TRACEPOINTS) += tracepoint-probe-sample2.o diff --git a/samples/tracepoints/tp-samples-trace.h b/samples/tracepoints/tp-samples-trace.h deleted file mode 100644 index 4d46be9..0000000 --- a/samples/tracepoints/tp-samples-trace.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _TP_SAMPLES_TRACE_H -#define _TP_SAMPLES_TRACE_H - -#include <linux/proc_fs.h> /* for struct inode and struct file */ -#include <linux/tracepoint.h> - -DECLARE_TRACE(subsys_event, - TP_PROTO(struct inode *inode, struct file *file), - TP_ARGS(inode, file)); -DECLARE_TRACE_NOARGS(subsys_eventb); -#endif diff --git a/samples/tracepoints/tracepoint-probe-sample.c b/samples/tracepoints/tracepoint-probe-sample.c deleted file mode 100644 index 744c0b9..0000000 --- a/samples/tracepoints/tracepoint-probe-sample.c +++ /dev/null @@ -1,57 +0,0 @@ -/* - * tracepoint-probe-sample.c - * - * sample tracepoint probes. - */ - -#include <linux/module.h> -#include <linux/file.h> -#include <linux/dcache.h> -#include "tp-samples-trace.h" - -/* - * Here the caller only guarantees locking for struct file and struct inode. - * Locking must therefore be done in the probe to use the dentry. - */ -static void probe_subsys_event(void *ignore, - struct inode *inode, struct file *file) -{ - path_get(&file->f_path); - dget(file->f_path.dentry); - printk(KERN_INFO "Event is encountered with filename %s\n", - file->f_path.dentry->d_name.name); - dput(file->f_path.dentry); - path_put(&file->f_path); -} - -static void probe_subsys_eventb(void *ignore) -{ - printk(KERN_INFO "Event B is encountered\n"); -} - -static int __init tp_sample_trace_init(void) -{ - int ret; - - ret = register_trace_subsys_event(probe_subsys_event, NULL); - WARN_ON(ret); - ret = register_trace_subsys_eventb(probe_subsys_eventb, NULL); - WARN_ON(ret); - - return 0; -} - -module_init(tp_sample_trace_init); - -static void __exit tp_sample_trace_exit(void) -{ - unregister_trace_subsys_eventb(probe_subsys_eventb, NULL); - unregister_trace_subsys_event(probe_subsys_event, NULL); - tracepoint_synchronize_unregister(); -} - -module_exit(tp_sample_trace_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Mathieu Desnoyers"); -MODULE_DESCRIPTION("Tracepoint Probes Samples"); diff --git a/samples/tracepoints/tracepoint-probe-sample2.c b/samples/tracepoints/tracepoint-probe-sample2.c deleted file mode 100644 index 9fcf990..0000000 --- a/samples/tracepoints/tracepoint-probe-sample2.c +++ /dev/null @@ -1,44 +0,0 @@ -/* - * tracepoint-probe-sample2.c - * - * 2nd sample tracepoint probes. - */ - -#include <linux/module.h> -#include <linux/fs.h> -#include "tp-samples-trace.h" - -/* - * Here the caller only guarantees locking for struct file and struct inode. - * Locking must therefore be done in the probe to use the dentry. - */ -static void probe_subsys_event(void *ignore, - struct inode *inode, struct file *file) -{ - printk(KERN_INFO "Event is encountered with inode number %lu\n", - inode->i_ino); -} - -static int __init tp_sample_trace_init(void) -{ - int ret; - - ret = register_trace_subsys_event(probe_subsys_event, NULL); - WARN_ON(ret); - - return 0; -} - -module_init(tp_sample_trace_init); - -static void __exit tp_sample_trace_exit(void) -{ - unregister_trace_subsys_event(probe_subsys_event, NULL); - tracepoint_synchronize_unregister(); -} - -module_exit(tp_sample_trace_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Mathieu Desnoyers"); -MODULE_DESCRIPTION("Tracepoint Probes Samples"); diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c deleted file mode 100644 index f4d89e0..0000000 --- a/samples/tracepoints/tracepoint-sample.c +++ /dev/null @@ -1,57 +0,0 @@ -/* tracepoint-sample.c - * - * Executes a tracepoint when /proc/tracepoint-sample is opened. - * - * (C) Copyright 2007 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> - * - * This file is released under the GPLv2. - * See the file COPYING for more details. - */ - -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/proc_fs.h> -#include "tp-samples-trace.h" - -DEFINE_TRACE(subsys_event); -DEFINE_TRACE(subsys_eventb); - -struct proc_dir_entry *pentry_sample; - -static int my_open(struct inode *inode, struct file *file) -{ - int i; - - trace_subsys_event(inode, file); - for (i = 0; i < 10; i++) - trace_subsys_eventb(); - return -EPERM; -} - -static const struct file_operations mark_ops = { - .open = my_open, - .llseek = noop_llseek, -}; - -static int __init sample_init(void) -{ - printk(KERN_ALERT "sample init\n"); - pentry_sample = proc_create("tracepoint-sample", 0444, NULL, - &mark_ops); - if (!pentry_sample) - return -EPERM; - return 0; -} - -static void __exit sample_exit(void) -{ - printk(KERN_ALERT "sample exit\n"); - remove_proc_entry("tracepoint-sample", NULL); -} - -module_init(sample_init) -module_exit(sample_exit) - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Mathieu Desnoyers"); -MODULE_DESCRIPTION("Tracepoint sample"); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4d2c7df..2bb08a9 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -230,12 +230,12 @@ our $Inline = qr{inline|__always_inline|noinline}; our $Member = qr{->$Ident|\.$Ident|\[[^]]*\]}; our $Lval = qr{$Ident(?:$Member)*}; -our $Float_hex = qr{(?i:0x[0-9a-f]+p-?[0-9]+[fl]?)}; -our $Float_dec = qr{(?i:((?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?))}; -our $Float_int = qr{(?i:[0-9]+e-?[0-9]+[fl]?)}; +our $Float_hex = qr{(?i)0x[0-9a-f]+p-?[0-9]+[fl]?}; +our $Float_dec = qr{(?i)(?:[0-9]+\.[0-9]*|[0-9]*\.[0-9]+)(?:e-?[0-9]+)?[fl]?}; +our $Float_int = qr{(?i)[0-9]+e-?[0-9]+[fl]?}; our $Float = qr{$Float_hex|$Float_dec|$Float_int}; -our $Constant = qr{(?:$Float|(?i:(?:0x[0-9a-f]+|[0-9]+)[ul]*))}; -our $Assignment = qr{(?:\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=)}; +our $Constant = qr{$Float|(?i)(?:0x[0-9a-f]+|[0-9]+)[ul]*}; +our $Assignment = qr{\*\=|/=|%=|\+=|-=|<<=|>>=|&=|\^=|\|=|=}; our $Compare = qr{<=|>=|==|!=|<|>}; our $Operators = qr{ <=|>=|==|!=| diff --git a/security/capability.c b/security/capability.c index 0fe5a02..5797750 100644 --- a/security/capability.c +++ b/security/capability.c @@ -709,16 +709,31 @@ static void cap_req_classify_flow(const struct request_sock *req, { } +static int cap_tun_dev_alloc_security(void **security) +{ + return 0; +} + +static void cap_tun_dev_free_security(void *security) +{ +} + static int cap_tun_dev_create(void) { return 0; } -static void cap_tun_dev_post_create(struct sock *sk) +static int cap_tun_dev_attach_queue(void *security) +{ + return 0; +} + +static int cap_tun_dev_attach(struct sock *sk, void *security) { + return 0; } -static int cap_tun_dev_attach(struct sock *sk) +static int cap_tun_dev_open(void *security) { return 0; } @@ -1050,8 +1065,11 @@ void __init security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, secmark_refcount_inc); set_to_cap_if_null(ops, secmark_refcount_dec); set_to_cap_if_null(ops, req_classify_flow); + set_to_cap_if_null(ops, tun_dev_alloc_security); + set_to_cap_if_null(ops, tun_dev_free_security); set_to_cap_if_null(ops, tun_dev_create); - set_to_cap_if_null(ops, tun_dev_post_create); + set_to_cap_if_null(ops, tun_dev_open); + set_to_cap_if_null(ops, tun_dev_attach_queue); set_to_cap_if_null(ops, tun_dev_attach); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/security/security.c b/security/security.c index daa97f4..7b88c6a 100644 --- a/security/security.c +++ b/security/security.c @@ -1254,24 +1254,42 @@ void security_secmark_refcount_dec(void) } EXPORT_SYMBOL(security_secmark_refcount_dec); +int security_tun_dev_alloc_security(void **security) +{ + return security_ops->tun_dev_alloc_security(security); +} +EXPORT_SYMBOL(security_tun_dev_alloc_security); + +void security_tun_dev_free_security(void *security) +{ + security_ops->tun_dev_free_security(security); +} +EXPORT_SYMBOL(security_tun_dev_free_security); + int security_tun_dev_create(void) { return security_ops->tun_dev_create(); } EXPORT_SYMBOL(security_tun_dev_create); -void security_tun_dev_post_create(struct sock *sk) +int security_tun_dev_attach_queue(void *security) { - return security_ops->tun_dev_post_create(sk); + return security_ops->tun_dev_attach_queue(security); } -EXPORT_SYMBOL(security_tun_dev_post_create); +EXPORT_SYMBOL(security_tun_dev_attach_queue); -int security_tun_dev_attach(struct sock *sk) +int security_tun_dev_attach(struct sock *sk, void *security) { - return security_ops->tun_dev_attach(sk); + return security_ops->tun_dev_attach(sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); +int security_tun_dev_open(void *security) +{ + return security_ops->tun_dev_open(security); +} +EXPORT_SYMBOL(security_tun_dev_open); + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 61a5336..ef26e96 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4399,6 +4399,24 @@ static void selinux_req_classify_flow(const struct request_sock *req, fl->flowi_secid = req->secid; } +static int selinux_tun_dev_alloc_security(void **security) +{ + struct tun_security_struct *tunsec; + + tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL); + if (!tunsec) + return -ENOMEM; + tunsec->sid = current_sid(); + + *security = tunsec; + return 0; +} + +static void selinux_tun_dev_free_security(void *security) +{ + kfree(security); +} + static int selinux_tun_dev_create(void) { u32 sid = current_sid(); @@ -4414,8 +4432,17 @@ static int selinux_tun_dev_create(void) NULL); } -static void selinux_tun_dev_post_create(struct sock *sk) +static int selinux_tun_dev_attach_queue(void *security) { + struct tun_security_struct *tunsec = security; + + return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, + TUN_SOCKET__ATTACH_QUEUE, NULL); +} + +static int selinux_tun_dev_attach(struct sock *sk, void *security) +{ + struct tun_security_struct *tunsec = security; struct sk_security_struct *sksec = sk->sk_security; /* we don't currently perform any NetLabel based labeling here and it @@ -4425,20 +4452,19 @@ static void selinux_tun_dev_post_create(struct sock *sk) * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ - /* see the comments in selinux_tun_dev_create() about why we don't use - * the sockcreate SID here */ - - sksec->sid = current_sid(); + sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; + + return 0; } -static int selinux_tun_dev_attach(struct sock *sk) +static int selinux_tun_dev_open(void *security) { - struct sk_security_struct *sksec = sk->sk_security; + struct tun_security_struct *tunsec = security; u32 sid = current_sid(); int err; - err = avc_has_perm(sid, sksec->sid, SECCLASS_TUN_SOCKET, + err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; @@ -4446,8 +4472,7 @@ static int selinux_tun_dev_attach(struct sock *sk) TUN_SOCKET__RELABELTO, NULL); if (err) return err; - - sksec->sid = sid; + tunsec->sid = sid; return 0; } @@ -5642,9 +5667,12 @@ static struct security_operations selinux_ops = { .secmark_refcount_inc = selinux_secmark_refcount_inc, .secmark_refcount_dec = selinux_secmark_refcount_dec, .req_classify_flow = selinux_req_classify_flow, + .tun_dev_alloc_security = selinux_tun_dev_alloc_security, + .tun_dev_free_security = selinux_tun_dev_free_security, .tun_dev_create = selinux_tun_dev_create, - .tun_dev_post_create = selinux_tun_dev_post_create, + .tun_dev_attach_queue = selinux_tun_dev_attach_queue, .tun_dev_attach = selinux_tun_dev_attach, + .tun_dev_open = selinux_tun_dev_open, #ifdef CONFIG_SECURITY_NETWORK_XFRM .xfrm_policy_alloc_security = selinux_xfrm_policy_alloc, diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index df2de54..14d04e6 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -150,6 +150,6 @@ struct security_class_mapping secclass_map[] = { NULL } }, { "kernel_service", { "use_as_override", "create_files_as", NULL } }, { "tun_socket", - { COMMON_SOCK_PERMS, NULL } }, + { COMMON_SOCK_PERMS, "attach_queue", NULL } }, { NULL } }; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 26c7eee..aa47bca 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -110,6 +110,10 @@ struct sk_security_struct { u16 sclass; /* sock security class */ }; +struct tun_security_struct { + u32 sid; /* SID for the tun device sockets */ +}; + struct key_security_struct { u32 sid; /* SID of key */ }; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 0b6aeba..c78286f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -656,29 +656,43 @@ static char *driver_short_names[] = { #define get_azx_dev(substream) (substream->runtime->private_data) #ifdef CONFIG_X86 -static void __mark_pages_wc(struct azx *chip, void *addr, size_t size, bool on) +static void __mark_pages_wc(struct azx *chip, struct snd_dma_buffer *dmab, bool on) { + int pages; + if (azx_snoop(chip)) return; - if (addr && size) { - int pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (!dmab || !dmab->area || !dmab->bytes) + return; + +#ifdef CONFIG_SND_DMA_SGBUF + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG) { + struct snd_sg_buf *sgbuf = dmab->private_data; if (on) - set_memory_wc((unsigned long)addr, pages); + set_pages_array_wc(sgbuf->page_table, sgbuf->pages); else - set_memory_wb((unsigned long)addr, pages); + set_pages_array_wb(sgbuf->page_table, sgbuf->pages); + return; } +#endif + + pages = (dmab->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (on) + set_memory_wc((unsigned long)dmab->area, pages); + else + set_memory_wb((unsigned long)dmab->area, pages); } static inline void mark_pages_wc(struct azx *chip, struct snd_dma_buffer *buf, bool on) { - __mark_pages_wc(chip, buf->area, buf->bytes, on); + __mark_pages_wc(chip, buf, on); } static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev, - struct snd_pcm_runtime *runtime, bool on) + struct snd_pcm_substream *substream, bool on) { if (azx_dev->wc_marked != on) { - __mark_pages_wc(chip, runtime->dma_area, runtime->dma_bytes, on); + __mark_pages_wc(chip, snd_pcm_get_dma_buf(substream), on); azx_dev->wc_marked = on; } } @@ -689,7 +703,7 @@ static inline void mark_pages_wc(struct azx *chip, struct snd_dma_buffer *buf, { } static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev, - struct snd_pcm_runtime *runtime, bool on) + struct snd_pcm_substream *substream, bool on) { } #endif @@ -1968,11 +1982,10 @@ static int azx_pcm_hw_params(struct snd_pcm_substream *substream, { struct azx_pcm *apcm = snd_pcm_substream_chip(substream); struct azx *chip = apcm->chip; - struct snd_pcm_runtime *runtime = substream->runtime; struct azx_dev *azx_dev = get_azx_dev(substream); int ret; - mark_runtime_wc(chip, azx_dev, runtime, false); + mark_runtime_wc(chip, azx_dev, substream, false); azx_dev->bufsize = 0; azx_dev->period_bytes = 0; azx_dev->format_val = 0; @@ -1980,7 +1993,7 @@ static int azx_pcm_hw_params(struct snd_pcm_substream *substream, params_buffer_bytes(hw_params)); if (ret < 0) return ret; - mark_runtime_wc(chip, azx_dev, runtime, true); + mark_runtime_wc(chip, azx_dev, substream, true); return ret; } @@ -1989,7 +2002,6 @@ static int azx_pcm_hw_free(struct snd_pcm_substream *substream) struct azx_pcm *apcm = snd_pcm_substream_chip(substream); struct azx_dev *azx_dev = get_azx_dev(substream); struct azx *chip = apcm->chip; - struct snd_pcm_runtime *runtime = substream->runtime; struct hda_pcm_stream *hinfo = apcm->hinfo[substream->stream]; /* reset BDL address */ @@ -2002,7 +2014,7 @@ static int azx_pcm_hw_free(struct snd_pcm_substream *substream) snd_hda_codec_cleanup(apcm->codec, hinfo, substream); - mark_runtime_wc(chip, azx_dev, runtime, false); + mark_runtime_wc(chip, azx_dev, substream, false); return snd_pcm_lib_free_pages(substream); } @@ -3613,13 +3625,12 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = { /* 5 Series/3400 */ { PCI_DEVICE(0x8086, 0x3b56), .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH }, - /* SCH */ + /* Poulsbo */ { PCI_DEVICE(0x8086, 0x811b), - .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP | - AZX_DCAPS_BUFSIZE | AZX_DCAPS_POSFIX_LPIB }, /* Poulsbo */ + .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM }, + /* Oaktrail */ { PCI_DEVICE(0x8086, 0x080a), - .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP | - AZX_DCAPS_BUFSIZE | AZX_DCAPS_POSFIX_LPIB }, /* Oaktrail */ + .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM }, /* ICH */ { PCI_DEVICE(0x8086, 0x2668), .driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC | diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cf38861..5faaad2 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4694,6 +4694,7 @@ static const struct snd_pci_quirk alc880_fixup_tbl[] = { SND_PCI_QUIRK(0x1584, 0x9077, "Uniwill P53", ALC880_FIXUP_VOL_KNOB), SND_PCI_QUIRK(0x161f, 0x203d, "W810", ALC880_FIXUP_W810), SND_PCI_QUIRK(0x161f, 0x205d, "Medion Rim 2150", ALC880_FIXUP_MEDION_RIM), + SND_PCI_QUIRK(0x1631, 0xe011, "PB 13201056", ALC880_FIXUP_6ST), SND_PCI_QUIRK(0x1734, 0x107c, "FSC F1734", ALC880_FIXUP_F1734), SND_PCI_QUIRK(0x1734, 0x1094, "FSC Amilo M1451G", ALC880_FIXUP_FUJITSU), SND_PCI_QUIRK(0x1734, 0x10ac, "FSC AMILO Xi 1526", ALC880_FIXUP_F1734), @@ -5708,6 +5709,7 @@ static const struct alc_model_fixup alc268_fixup_models[] = { }; static const struct snd_pci_quirk alc268_fixup_tbl[] = { + SND_PCI_QUIRK(0x1025, 0x015b, "Acer AOA 150 (ZG5)", ALC268_FIXUP_INV_DMIC), /* below is codec SSID since multiple Toshiba laptops have the * same PCI SSID 1179:ff00 */ diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index 1d8bb59..ef62c43 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -685,7 +685,7 @@ static int arizona_hw_params(struct snd_pcm_substream *substream, } sr_val = i; - lrclk = snd_soc_params_to_bclk(params) / params_rate(params); + lrclk = rates[bclk] / params_rate(params); arizona_aif_dbg(dai, "BCLK %dHz LRCLK %dHz\n", rates[bclk], rates[bclk] / lrclk); @@ -1082,6 +1082,9 @@ int arizona_init_fll(struct arizona *arizona, int id, int base, int lock_irq, id, ret); } + regmap_update_bits(arizona->regmap, fll->base + 1, + ARIZONA_FLL1_FREERUN, 0); + return 0; } EXPORT_SYMBOL_GPL(arizona_init_fll); diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c index e6cefe1..d8c65f5 100644 --- a/sound/soc/codecs/wm2200.c +++ b/sound/soc/codecs/wm2200.c @@ -1019,8 +1019,6 @@ static const char *wm2200_mixer_texts[] = { "EQR", "LHPF1", "LHPF2", - "LHPF3", - "LHPF4", "DSP1.1", "DSP1.2", "DSP1.3", @@ -1053,7 +1051,6 @@ static int wm2200_mixer_values[] = { 0x25, 0x50, /* EQ */ 0x51, - 0x52, 0x60, /* LHPF1 */ 0x61, /* LHPF2 */ 0x68, /* DSP1 */ diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index 7a9048d..988e817 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -896,8 +896,7 @@ static const unsigned int wm5102_aec_loopback_values[] = { static const struct soc_enum wm5102_aec_loopback = SOC_VALUE_ENUM_SINGLE(ARIZONA_DAC_AEC_CONTROL_1, - ARIZONA_AEC_LOOPBACK_SRC_SHIFT, - ARIZONA_AEC_LOOPBACK_SRC_MASK, + ARIZONA_AEC_LOOPBACK_SRC_SHIFT, 0xf, ARRAY_SIZE(wm5102_aec_loopback_texts), wm5102_aec_loopback_texts, wm5102_aec_loopback_values); @@ -1153,6 +1152,8 @@ SND_SOC_DAPM_OUTPUT("SPKOUTRN"), SND_SOC_DAPM_OUTPUT("SPKOUTRP"), SND_SOC_DAPM_OUTPUT("SPKDAT1L"), SND_SOC_DAPM_OUTPUT("SPKDAT1R"), + +SND_SOC_DAPM_OUTPUT("MICSUPP"), }; #define ARIZONA_MIXER_INPUT_ROUTES(name) \ @@ -1365,6 +1366,8 @@ static const struct snd_soc_dapm_route wm5102_dapm_routes[] = { { "AEC Loopback", "SPKDAT1R", "OUT5R" }, { "SPKDAT1L", NULL, "OUT5L" }, { "SPKDAT1R", NULL, "OUT5R" }, + + { "MICSUPP", NULL, "SYSCLK" }, }; static int wm5102_set_fll(struct snd_soc_codec *codec, int fll_id, int source, diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index ae80c8c..0320a32 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -344,8 +344,7 @@ static const unsigned int wm5110_aec_loopback_values[] = { static const struct soc_enum wm5110_aec_loopback = SOC_VALUE_ENUM_SINGLE(ARIZONA_DAC_AEC_CONTROL_1, - ARIZONA_AEC_LOOPBACK_SRC_SHIFT, - ARIZONA_AEC_LOOPBACK_SRC_MASK, + ARIZONA_AEC_LOOPBACK_SRC_SHIFT, 0xf, ARRAY_SIZE(wm5110_aec_loopback_texts), wm5110_aec_loopback_texts, wm5110_aec_loopback_values); @@ -625,6 +624,8 @@ SND_SOC_DAPM_OUTPUT("SPKDAT1L"), SND_SOC_DAPM_OUTPUT("SPKDAT1R"), SND_SOC_DAPM_OUTPUT("SPKDAT2L"), SND_SOC_DAPM_OUTPUT("SPKDAT2R"), + +SND_SOC_DAPM_OUTPUT("MICSUPP"), }; #define ARIZONA_MIXER_INPUT_ROUTES(name) \ @@ -833,6 +834,8 @@ static const struct snd_soc_dapm_route wm5110_dapm_routes[] = { { "SPKDAT2L", NULL, "OUT6L" }, { "SPKDAT2R", NULL, "OUT6R" }, + + { "MICSUPP", NULL, "SYSCLK" }, }; static int wm5110_set_fll(struct snd_soc_codec *codec, int fll_id, int source, diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 7b198c3..b6b6548 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -324,7 +324,7 @@ static int wm_adsp_load(struct wm_adsp *dsp) if (reg) { buf = kmemdup(region->data, le32_to_cpu(region->len), - GFP_KERNEL); + GFP_KERNEL | GFP_DMA); if (!buf) { adsp_err(dsp, "Out of memory\n"); return -ENOMEM; @@ -396,7 +396,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) hdr = (void*)&firmware->data[0]; if (memcmp(hdr->magic, "WMDR", 4) != 0) { adsp_err(dsp, "%s: invalid magic\n", file); - return -EINVAL; + goto out_fw; } adsp_dbg(dsp, "%s: v%d.%d.%d\n", file, @@ -439,7 +439,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) if (reg) { buf = kmemdup(blk->data, le32_to_cpu(blk->len), - GFP_KERNEL); + GFP_KERNEL | GFP_DMA); if (!buf) { adsp_err(dsp, "Out of memory\n"); return -ENOMEM; diff --git a/sound/soc/fsl/imx-pcm-dma.c b/sound/soc/fsl/imx-pcm-dma.c index bf363d8..500f8ce 100644 --- a/sound/soc/fsl/imx-pcm-dma.c +++ b/sound/soc/fsl/imx-pcm-dma.c @@ -154,26 +154,7 @@ static struct snd_soc_platform_driver imx_soc_platform_mx2 = { .pcm_free = imx_pcm_free, }; -static int imx_soc_platform_probe(struct platform_device *pdev) +int imx_pcm_dma_init(struct platform_device *pdev) { return snd_soc_register_platform(&pdev->dev, &imx_soc_platform_mx2); } - -static int imx_soc_platform_remove(struct platform_device *pdev) -{ - snd_soc_unregister_platform(&pdev->dev); - return 0; -} - -static struct platform_driver imx_pcm_driver = { - .driver = { - .name = "imx-pcm-audio", - .owner = THIS_MODULE, - }, - .probe = imx_soc_platform_probe, - .remove = imx_soc_platform_remove, -}; - -module_platform_driver(imx_pcm_driver); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:imx-pcm-audio"); diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c index 5ec362a..920f945 100644 --- a/sound/soc/fsl/imx-pcm-fiq.c +++ b/sound/soc/fsl/imx-pcm-fiq.c @@ -281,7 +281,7 @@ static struct snd_soc_platform_driver imx_soc_platform_fiq = { .pcm_free = imx_pcm_fiq_free, }; -static int imx_soc_platform_probe(struct platform_device *pdev) +int imx_pcm_fiq_init(struct platform_device *pdev) { struct imx_ssi *ssi = platform_get_drvdata(pdev); int ret; @@ -314,23 +314,3 @@ failed_register: return ret; } - -static int imx_soc_platform_remove(struct platform_device *pdev) -{ - snd_soc_unregister_platform(&pdev->dev); - return 0; -} - -static struct platform_driver imx_pcm_driver = { - .driver = { - .name = "imx-fiq-pcm-audio", - .owner = THIS_MODULE, - }, - - .probe = imx_soc_platform_probe, - .remove = imx_soc_platform_remove, -}; - -module_platform_driver(imx_pcm_driver); - -MODULE_LICENSE("GPL"); diff --git a/sound/soc/fsl/imx-pcm.c b/sound/soc/fsl/imx-pcm.c index d5cd9ef..0d0625b 100644 --- a/sound/soc/fsl/imx-pcm.c +++ b/sound/soc/fsl/imx-pcm.c @@ -104,6 +104,38 @@ void imx_pcm_free(struct snd_pcm *pcm) } EXPORT_SYMBOL_GPL(imx_pcm_free); +static int imx_pcm_probe(struct platform_device *pdev) +{ + if (strcmp(pdev->id_entry->name, "imx-fiq-pcm-audio") == 0) + return imx_pcm_fiq_init(pdev); + + return imx_pcm_dma_init(pdev); +} + +static int imx_pcm_remove(struct platform_device *pdev) +{ + snd_soc_unregister_platform(&pdev->dev); + return 0; +} + +static struct platform_device_id imx_pcm_devtype[] = { + { .name = "imx-pcm-audio", }, + { .name = "imx-fiq-pcm-audio", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, imx_pcm_devtype); + +static struct platform_driver imx_pcm_driver = { + .driver = { + .name = "imx-pcm", + .owner = THIS_MODULE, + }, + .id_table = imx_pcm_devtype, + .probe = imx_pcm_probe, + .remove = imx_pcm_remove, +}; +module_platform_driver(imx_pcm_driver); + MODULE_DESCRIPTION("Freescale i.MX PCM driver"); MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/fsl/imx-pcm.h b/sound/soc/fsl/imx-pcm.h index 83c0ed7..5ae13a1 100644 --- a/sound/soc/fsl/imx-pcm.h +++ b/sound/soc/fsl/imx-pcm.h @@ -30,4 +30,22 @@ int snd_imx_pcm_mmap(struct snd_pcm_substream *substream, int imx_pcm_new(struct snd_soc_pcm_runtime *rtd); void imx_pcm_free(struct snd_pcm *pcm); +#ifdef CONFIG_SND_SOC_IMX_PCM_DMA +int imx_pcm_dma_init(struct platform_device *pdev); +#else +static inline int imx_pcm_dma_init(struct platform_device *pdev) +{ + return -ENODEV; +} +#endif + +#ifdef CONFIG_SND_SOC_IMX_PCM_FIQ +int imx_pcm_fiq_init(struct platform_device *pdev); +#else +static inline int imx_pcm_fiq_init(struct platform_device *pdev) +{ + return -ENODEV; +} +#endif + #endif /* _IMX_PCM_H */ diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 1e36bc8..258acad 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1023,7 +1023,7 @@ int dapm_regulator_event(struct snd_soc_dapm_widget *w, if (SND_SOC_DAPM_EVENT_ON(event)) { if (w->invert & SND_SOC_DAPM_REGULATOR_BYPASS) { - ret = regulator_allow_bypass(w->regulator, true); + ret = regulator_allow_bypass(w->regulator, false); if (ret != 0) dev_warn(w->dapm->dev, "ASoC: Failed to bypass %s: %d\n", @@ -1033,7 +1033,7 @@ int dapm_regulator_event(struct snd_soc_dapm_widget *w, return regulator_enable(w->regulator); } else { if (w->invert & SND_SOC_DAPM_REGULATOR_BYPASS) { - ret = regulator_allow_bypass(w->regulator, false); + ret = regulator_allow_bypass(w->regulator, true); if (ret != 0) dev_warn(w->dapm->dev, "ASoC: Failed to unbypass %s: %d\n", @@ -3039,6 +3039,14 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm, w->name, ret); return NULL; } + + if (w->invert & SND_SOC_DAPM_REGULATOR_BYPASS) { + ret = regulator_allow_bypass(w->regulator, true); + if (ret != 0) + dev_warn(w->dapm->dev, + "ASoC: Failed to unbypass %s: %d\n", + w->name, ret); + } break; case snd_soc_dapm_clock_supply: #ifdef CONFIG_CLKDEV_LOOKUP diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index ed4d89c..e90daf8 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1331,16 +1331,23 @@ static int parse_audio_feature_unit(struct mixer_build *state, int unitid, void } channels = (hdr->bLength - 7) / csize - 1; bmaControls = hdr->bmaControls; + if (hdr->bLength < 7 + csize) { + snd_printk(KERN_ERR "usbaudio: unit %u: " + "invalid UAC_FEATURE_UNIT descriptor\n", + unitid); + return -EINVAL; + } } else { struct uac2_feature_unit_descriptor *ftr = _ftr; csize = 4; channels = (hdr->bLength - 6) / 4 - 1; bmaControls = ftr->bmaControls; - } - - if (hdr->bLength < 7 || !csize || hdr->bLength < 7 + csize) { - snd_printk(KERN_ERR "usbaudio: unit %u: invalid UAC_FEATURE_UNIT descriptor\n", unitid); - return -EINVAL; + if (hdr->bLength < 6 + csize) { + snd_printk(KERN_ERR "usbaudio: unit %u: " + "invalid UAC_FEATURE_UNIT descriptor\n", + unitid); + return -EINVAL; + } } /* parse the source unit */ diff --git a/tools/Makefile b/tools/Makefile index 1f9a529..fa36565 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -3,6 +3,7 @@ include scripts/Makefile.include help: @echo 'Possible targets:' @echo '' + @echo ' cgroup - cgroup tools' @echo ' cpupower - a tool for all things x86 CPU power' @echo ' firewire - the userspace part of nosy, an IEEE-1394 traffic sniffer' @echo ' lguest - a minimal 32-bit x86 hypervisor' @@ -15,7 +16,7 @@ help: @echo ' x86_energy_perf_policy - Intel energy policy tool' @echo '' @echo 'You can do:' - @echo ' $$ make -C tools/<tool>_install' + @echo ' $$ make -C tools/ <tool>_install' @echo '' @echo ' from the kernel command line to build and install one of' @echo ' the tools above' @@ -33,7 +34,7 @@ help: cpupower: FORCE $(call descend,power/$@) -firewire lguest perf usb virtio vm: FORCE +cgroup firewire lguest perf usb virtio vm: FORCE $(call descend,$@) selftests: FORCE @@ -45,7 +46,7 @@ turbostat x86_energy_perf_policy: FORCE cpupower_install: $(call descend,power/$(@:_install=),install) -firewire_install lguest_install perf_install usb_install virtio_install vm_install: +cgroup_install firewire_install lguest_install perf_install usb_install virtio_install vm_install: $(call descend,$(@:_install=),install) selftests_install: @@ -54,14 +55,14 @@ selftests_install: turbostat_install x86_energy_perf_policy_install: $(call descend,power/x86/$(@:_install=),install) -install: cpupower_install firewire_install lguest_install perf_install \ - selftests_install turbostat_install usb_install virtio_install \ - vm_install x86_energy_perf_policy_install +install: cgroup_install cpupower_install firewire_install lguest_install \ + perf_install selftests_install turbostat_install usb_install \ + virtio_install vm_install x86_energy_perf_policy_install cpupower_clean: $(call descend,power/cpupower,clean) -firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean: +cgroup_clean firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean: $(call descend,$(@:_clean=),clean) selftests_clean: @@ -70,8 +71,8 @@ selftests_clean: turbostat_clean x86_energy_perf_policy_clean: $(call descend,power/x86/$(@:_clean=),clean) -clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \ - turbostat_clean usb_clean virtio_clean vm_clean \ - x86_energy_perf_policy_clean +clean: cgroup_clean cpupower_clean firewire_clean lguest_clean perf_clean \ + selftests_clean turbostat_clean usb_clean virtio_clean \ + vm_clean x86_energy_perf_policy_clean .PHONY: FORCE diff --git a/tools/cgroup/.gitignore b/tools/cgroup/.gitignore new file mode 100644 index 0000000..633cd9b --- /dev/null +++ b/tools/cgroup/.gitignore @@ -0,0 +1 @@ +cgroup_event_listener diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile new file mode 100644 index 0000000..b428619 --- /dev/null +++ b/tools/cgroup/Makefile @@ -0,0 +1,11 @@ +# Makefile for cgroup tools + +CC = $(CROSS_COMPILE)gcc +CFLAGS = -Wall -Wextra + +all: cgroup_event_listener +%: %.c + $(CC) $(CFLAGS) -o $@ $^ + +clean: + $(RM) cgroup_event_listener diff --git a/Documentation/cgroups/cgroup_event_listener.c b/tools/cgroup/cgroup_event_listener.c index 3e082f9..4eb5507 100644 --- a/Documentation/cgroups/cgroup_event_listener.c +++ b/tools/cgroup/cgroup_event_listener.c @@ -5,6 +5,7 @@ */ #include <assert.h> +#include <err.h> #include <errno.h> #include <fcntl.h> #include <libgen.h> @@ -15,7 +16,7 @@ #include <sys/eventfd.h> -#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n" +#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>" int main(int argc, char **argv) { @@ -26,49 +27,33 @@ int main(int argc, char **argv) char line[LINE_MAX]; int ret; - if (argc != 3) { - fputs(USAGE_STR, stderr); - return 1; - } + if (argc != 3) + errx(1, "%s", USAGE_STR); cfd = open(argv[1], O_RDONLY); - if (cfd == -1) { - fprintf(stderr, "Cannot open %s: %s\n", argv[1], - strerror(errno)); - goto out; - } + if (cfd == -1) + err(1, "Cannot open %s", argv[1]); ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control", dirname(argv[1])); - if (ret >= PATH_MAX) { - fputs("Path to cgroup.event_control is too long\n", stderr); - goto out; - } + if (ret >= PATH_MAX) + errx(1, "Path to cgroup.event_control is too long"); event_control = open(event_control_path, O_WRONLY); - if (event_control == -1) { - fprintf(stderr, "Cannot open %s: %s\n", event_control_path, - strerror(errno)); - goto out; - } + if (event_control == -1) + err(1, "Cannot open %s", event_control_path); efd = eventfd(0, 0); - if (efd == -1) { - perror("eventfd() failed"); - goto out; - } + if (efd == -1) + err(1, "eventfd() failed"); ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]); - if (ret >= LINE_MAX) { - fputs("Arguments string is too long\n", stderr); - goto out; - } + if (ret >= LINE_MAX) + errx(1, "Arguments string is too long"); ret = write(event_control, line, strlen(line) + 1); - if (ret == -1) { - perror("Cannot write to cgroup.event_control"); - goto out; - } + if (ret == -1) + err(1, "Cannot write to cgroup.event_control"); while (1) { uint64_t result; @@ -77,34 +62,21 @@ int main(int argc, char **argv) if (ret == -1) { if (errno == EINTR) continue; - perror("Cannot read from eventfd"); - break; + err(1, "Cannot read from eventfd"); } assert(ret == sizeof(result)); ret = access(event_control_path, W_OK); if ((ret == -1) && (errno == ENOENT)) { - puts("The cgroup seems to have removed."); - ret = 0; - break; - } - - if (ret == -1) { - perror("cgroup.event_control " - "is not accessible any more"); + puts("The cgroup seems to have removed."); break; } + if (ret == -1) + err(1, "cgroup.event_control is not accessible any more"); + printf("%s %s: crossed\n", argv[1], argv[2]); } -out: - if (efd >= 0) - close(efd); - if (event_control >= 0) - close(event_control); - if (cfd >= 0) - close(cfd); - - return (ret != 0); + return 0; } diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 5a824e3..82b0606 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -13,8 +13,7 @@ * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * License along with this program; if not, see <http://www.gnu.org/licenses> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -1224,6 +1223,34 @@ static int field_is_long(struct format_field *field) return 0; } +static unsigned int type_size(const char *name) +{ + /* This covers all FIELD_IS_STRING types. */ + static struct { + const char *type; + unsigned int size; + } table[] = { + { "u8", 1 }, + { "u16", 2 }, + { "u32", 4 }, + { "u64", 8 }, + { "s8", 1 }, + { "s16", 2 }, + { "s32", 4 }, + { "s64", 8 }, + { "char", 1 }, + { }, + }; + int i; + + for (i = 0; table[i].type; i++) { + if (!strcmp(table[i].type, name)) + return table[i].size; + } + + return 0; +} + static int event_read_fields(struct event_format *event, struct format_field **fields) { struct format_field *field = NULL; @@ -1233,6 +1260,8 @@ static int event_read_fields(struct event_format *event, struct format_field **f int count = 0; do { + unsigned int size_dynamic = 0; + type = read_token(&token); if (type == EVENT_NEWLINE) { free_token(token); @@ -1391,6 +1420,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f field->type = new_type; strcat(field->type, " "); strcat(field->type, field->name); + size_dynamic = type_size(field->name); free_token(field->name); strcat(field->type, brackets); field->name = token; @@ -1463,7 +1493,8 @@ static int event_read_fields(struct event_format *event, struct format_field **f if (read_expect_type(EVENT_ITEM, &token)) goto fail; - /* add signed type */ + if (strtoul(token, NULL, 0)) + field->flags |= FIELD_IS_SIGNED; free_token(token); if (read_expected(EVENT_OP, ";") < 0) @@ -1478,10 +1509,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f if (field->flags & FIELD_IS_ARRAY) { if (field->arraylen) field->elementsize = field->size / field->arraylen; + else if (field->flags & FIELD_IS_DYNAMIC) + field->elementsize = size_dynamic; else if (field->flags & FIELD_IS_STRING) field->elementsize = 1; - else - field->elementsize = event->pevent->long_size; + else if (field->flags & FIELD_IS_LONG) + field->elementsize = event->pevent ? + event->pevent->long_size : + sizeof(long); } else field->elementsize = field->size; @@ -1785,6 +1820,8 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) strcmp(token, "/") == 0 || strcmp(token, "<") == 0 || strcmp(token, ">") == 0 || + strcmp(token, "<=") == 0 || + strcmp(token, ">=") == 0 || strcmp(token, "==") == 0 || strcmp(token, "!=") == 0) { @@ -2481,7 +2518,7 @@ process_dynamic_array(struct event_format *event, struct print_arg *arg, char ** free_token(token); arg = alloc_arg(); - if (!field) { + if (!arg) { do_warning("%s: not enough memory!", __func__); *tok = NULL; return EVENT_ERROR; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 24a4bba..7be7e89 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -13,8 +13,7 @@ * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * License along with this program; if not, see <http://www.gnu.org/licenses> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ diff --git a/tools/lib/traceevent/event-utils.h b/tools/lib/traceevent/event-utils.h index bc07500..e76c9ac 100644 --- a/tools/lib/traceevent/event-utils.h +++ b/tools/lib/traceevent/event-utils.h @@ -13,8 +13,7 @@ * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * License along with this program; if not, see <http://www.gnu.org/licenses> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 5ea4326..2500e75 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -13,8 +13,7 @@ * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * License along with this program; if not, see <http://www.gnu.org/licenses> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c index f023a13..bba701c 100644 --- a/tools/lib/traceevent/parse-utils.c +++ b/tools/lib/traceevent/parse-utils.c @@ -1,3 +1,22 @@ +/* + * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see <http://www.gnu.org/licenses> + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + */ #include <stdio.h> #include <stdlib.h> #include <string.h> diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c index b1ccc92..a57db80 100644 --- a/tools/lib/traceevent/trace-seq.c +++ b/tools/lib/traceevent/trace-seq.c @@ -13,8 +13,7 @@ * GNU Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public - * License along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * License along with this program; if not, see <http://www.gnu.org/licenses> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index ef6d22e..eb30044 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -222,10 +222,14 @@ install-pdf: pdf #install-html: html # '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) +ifneq ($(MAKECMDGOALS),clean) +ifneq ($(MAKECMDGOALS),tags) $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE -include $(OUTPUT)PERF-VERSION-FILE +endif +endif # # Determine "include::" file references in asciidoc files. diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index c8ffd9f..5ad07ef 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -61,11 +61,13 @@ OPTIONS --stdio:: Use the stdio interface. ---tui:: Use the TUI interface Use of --tui requires a tty, if one is not +--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not present, as when piping to other commands, the stdio interface is used. This interfaces starts by centering on the line with more samples, TAB/UNTAB cycles through the lines with more samples. +--gtk:: Use the GTK interface. + -C:: --cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can be provided as a comma-separated list with no space: 0,1. Ranges of @@ -88,6 +90,9 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--skip-missing:: + Skip symbols that cannot be annotated. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index c105770..e9a8349 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -24,6 +24,13 @@ OPTIONS -r:: --remove=:: Remove specified file from the cache. +-M:: +--missing=:: + List missing build ids in the cache for the specified file. +-u:: +--update:: + Update specified file of the cache. It can be used to update kallsyms + kernel dso to vmlinux in order to support annotation. -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index 194f37d..5b3123d 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -22,10 +22,6 @@ specified perf.data files. OPTIONS ------- --M:: ---displacement:: - Show position displacement relative to baseline. - -D:: --dump-raw-trace:: Dump raw trace in ASCII. diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt index 1521734..1ceb370 100644 --- a/tools/perf/Documentation/perf-evlist.txt +++ b/tools/perf/Documentation/perf-evlist.txt @@ -28,6 +28,10 @@ OPTIONS --verbose=:: Show all fields. +-g:: +--group:: + Show event group information. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-list[1], diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index f4d91be..02284a0 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -57,11 +57,44 @@ OPTIONS -s:: --sort=:: - Sort by key(s): pid, comm, dso, symbol, parent, srcline. + Sort histogram entries by given key(s) - multiple keys can be specified + in CSV format. Following sort keys are available: + pid, comm, dso, symbol, parent, cpu, srcline. + + Each key has following meaning: + + - comm: command (name) of the task which can be read via /proc/<pid>/comm + - pid: command and tid of the task + - dso: name of library or module executed at the time of sample + - symbol: name of function executed at the time of sample + - parent: name of function matched to the parent regex filter. Unmatched + entries are displayed as "[other]". + - cpu: cpu number the task ran at the time of sample + - srcline: filename and line number executed at the time of sample. The + DWARF debuggin info must be provided. + + By default, comm, dso and symbol keys are used. + (i.e. --sort comm,dso,symbol) + + If --branch-stack option is used, following sort keys are also + available: + dso_from, dso_to, symbol_from, symbol_to, mispredict. + + - dso_from: name of library or module branched from + - dso_to: name of library or module branched to + - symbol_from: name of function branched from + - symbol_to: name of function branched to + - mispredict: "N" for predicted branch, "Y" for mispredicted branch + + And default sort keys are changed to comm, dso_from, symbol_from, dso_to + and symbol_to, see '--branch-stack'. -p:: --parent=<regex>:: - regex filter to identify parent, see: '--sort parent' + A regex filter to identify parent. The parent is a caller of this + function and searched through the callchain, thus it requires callchain + information recorded. The pattern is in the exteneded regex format and + defaults to "\^sys_|^do_page_fault", see '--sort parent'. -x:: --exclude-other:: @@ -74,7 +107,6 @@ OPTIONS -t:: --field-separator=:: - Use a special separator character and don't pad with spaces, replacing all occurrences of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. @@ -171,6 +203,9 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--group:: + Show event group information together. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-annotate[1] diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index a4027f2..9f1f054 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -336,7 +336,6 @@ scripts listed by the 'perf script -l' command e.g.: ---- root@tropicana:~# perf script -l List of available trace scripts: - workqueue-stats workqueue stats (ins/exe/create/destroy) wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file rw-by-pid system-wide r/w activity @@ -402,7 +401,6 @@ should show a new entry for your script: ---- root@tropicana:~# perf script -l List of available trace scripts: - workqueue-stats workqueue stats (ins/exe/create/destroy) wakeup-latency system-wide min/max/avg wakeup latency rw-by-file <comm> r/w activity for a program, by file rw-by-pid system-wide r/w activity diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index cf0c310..faf4f4f 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -114,6 +114,17 @@ with it. --append may be used here. Examples: perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage +-I msecs:: +--interval-print msecs:: + Print count deltas every N milliseconds (minimum: 100ms) + example: perf stat -I 1000 -e cycles -a sleep 5 + +--aggr-socket:: +Aggregate counts per processor socket for system-wide mode measurements. This +is a useful mode to detect imbalance between sockets. To enable this mode, +use --aggr-socket in addition to -a. (system-wide). The output includes the +socket number and the number of online processors on that socket. This is +useful to gauge the amount of aggregation. EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt index b24ac40..d1d3e5121 100644 --- a/tools/perf/Documentation/perf-test.txt +++ b/tools/perf/Documentation/perf-test.txt @@ -23,6 +23,10 @@ from 'perf test list'. OPTIONS ------- +-s:: +--skip:: + Tests to skip (comma separater numeric list). + -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 5b80d84..a414bc9 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -60,7 +60,7 @@ Default is to monitor all CPUS. -i:: --inherit:: - Child tasks inherit counters, only makes sens with -p option. + Child tasks do not inherit counters. -k <path>:: --vmlinux=<path>:: diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 8ab05e5..a2108ca 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -47,10 +47,11 @@ include config/utilities.mak # backtrace post unwind. # # Define NO_BACKTRACE if you do not want stack backtrace debug feature +# +# Define NO_LIBNUMA if you do not want numa perf benchmark $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) --include $(OUTPUT)PERF-VERSION-FILE uname_M := $(shell uname -m 2>/dev/null || echo not) @@ -148,13 +149,25 @@ RM = rm -f MKDIR = mkdir FIND = find INSTALL = install +FLEX = flex +BISON= bison # sparse is architecture-neutral, which means that we need to tell it # explicitly what architecture to check for. Fix this up for yours.. SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ +ifneq ($(MAKECMDGOALS),clean) +ifneq ($(MAKECMDGOALS),tags) -include config/feature-tests.mak +ifeq ($(call get-executable,$(FLEX)),) + dummy := $(error Error: $(FLEX) is missing on this system, please install it) +endif + +ifeq ($(call get-executable,$(BISON)),) + dummy := $(error Error: $(BISON) is missing on this system, please install it) +endif + ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y) CFLAGS := $(CFLAGS) -fstack-protector-all endif @@ -206,6 +219,8 @@ ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y) EXTLIBS := $(filter-out -lpthread,$(EXTLIBS)) BASIC_CFLAGS += -I. endif +endif # MAKECMDGOALS != tags +endif # MAKECMDGOALS != clean # Guard against environment variables BUILTIN_OBJS = @@ -230,11 +245,19 @@ endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a TE_LIB := -L$(TE_PATH) -ltraceevent +export LIBTRACEEVENT + +# python extension build directories +PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ +PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ +PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/ +export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP + +python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so + PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py -export LIBTRACEEVENT - $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ @@ -269,20 +292,17 @@ endif export PERL_PATH -FLEX = flex -BISON= bison - $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) -t util/parse-events.l > $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c: util/parse-events.y - $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c + $(QUIET_BISON)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $(OUTPUT)util/parse-events-bison.c -p parse_events_ $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c $(QUIET_FLEX)$(FLEX) --header-file=$(OUTPUT)util/pmu-flex.h -t util/pmu.l > $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c: util/pmu.y - $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c + $(QUIET_BISON)$(BISON) -v util/pmu.y -d -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_ $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c @@ -378,8 +398,11 @@ LIB_H += util/rblist.h LIB_H += util/intlist.h LIB_H += util/perf_regs.h LIB_H += util/unwind.h -LIB_H += ui/helpline.h LIB_H += util/vdso.h +LIB_H += ui/helpline.h +LIB_H += ui/progress.h +LIB_H += ui/util.h +LIB_H += ui/ui.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o @@ -453,6 +476,7 @@ LIB_OBJS += $(OUTPUT)util/stat.o LIB_OBJS += $(OUTPUT)ui/setup.o LIB_OBJS += $(OUTPUT)ui/helpline.o LIB_OBJS += $(OUTPUT)ui/progress.o +LIB_OBJS += $(OUTPUT)ui/util.o LIB_OBJS += $(OUTPUT)ui/hist.o LIB_OBJS += $(OUTPUT)ui/stdio/hist.o @@ -471,7 +495,8 @@ LIB_OBJS += $(OUTPUT)tests/rdpmc.o LIB_OBJS += $(OUTPUT)tests/evsel-roundtrip-name.o LIB_OBJS += $(OUTPUT)tests/evsel-tp-sched.o LIB_OBJS += $(OUTPUT)tests/pmu.o -LIB_OBJS += $(OUTPUT)tests/util.o +LIB_OBJS += $(OUTPUT)tests/hists_link.o +LIB_OBJS += $(OUTPUT)tests/python-use.o BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o BUILTIN_OBJS += $(OUTPUT)builtin-bench.o @@ -510,14 +535,13 @@ PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT) # # Platform specific tweaks # +ifneq ($(MAKECMDGOALS),clean) +ifneq ($(MAKECMDGOALS),tags) # We choose to avoid "if .. else if .. else .. endif endif" # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... --include config.mak.autogen --include config.mak - ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 @@ -557,6 +581,11 @@ else endif # SOURCE_LIBELF endif # NO_LIBELF +# There's only x86 (both 32 and 64) support for CFI unwind so far +ifneq ($(ARCH),x86) + NO_LIBUNWIND := 1 +endif + ifndef NO_LIBUNWIND # for linking with debug library, run like: # make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/ @@ -646,7 +675,6 @@ ifndef NO_NEWT LIB_OBJS += $(OUTPUT)ui/browsers/hists.o LIB_OBJS += $(OUTPUT)ui/browsers/map.o LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o - LIB_OBJS += $(OUTPUT)ui/util.o LIB_OBJS += $(OUTPUT)ui/tui/setup.o LIB_OBJS += $(OUTPUT)ui/tui/util.o LIB_OBJS += $(OUTPUT)ui/tui/helpline.o @@ -655,9 +683,6 @@ ifndef NO_NEWT LIB_H += ui/browsers/map.h LIB_H += ui/keysyms.h LIB_H += ui/libslang.h - LIB_H += ui/progress.h - LIB_H += ui/util.h - LIB_H += ui/ui.h endif endif @@ -673,14 +698,12 @@ ifndef NO_GTK2 BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null) EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null) LIB_OBJS += $(OUTPUT)ui/gtk/browser.o + LIB_OBJS += $(OUTPUT)ui/gtk/hists.o LIB_OBJS += $(OUTPUT)ui/gtk/setup.o LIB_OBJS += $(OUTPUT)ui/gtk/util.o LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o LIB_OBJS += $(OUTPUT)ui/gtk/progress.o - # Make sure that it'd be included only once. - ifeq ($(findstring -DNEWT_SUPPORT,$(BASIC_CFLAGS)),) - LIB_OBJS += $(OUTPUT)ui/util.o - endif + LIB_OBJS += $(OUTPUT)ui/gtk/annotate.o endif endif @@ -707,7 +730,7 @@ disable-python = $(eval $(disable-python_code)) define disable-python_code BASIC_CFLAGS += -DNO_LIBPYTHON $(if $(1),$(warning No $(1) was found)) - $(warning Python support won't be built) + $(warning Python support will not be built) endef override PYTHON := \ @@ -715,19 +738,10 @@ override PYTHON := \ ifndef PYTHON $(call disable-python,python interpreter) - python-clean := else PYTHON_WORD := $(call shell-wordify,$(PYTHON)) - # python extension build directories - PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ - PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ - PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/ - export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP - - python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so - ifdef NO_LIBPYTHON $(call disable-python) else @@ -839,10 +853,24 @@ ifndef NO_BACKTRACE endif endif +ifndef NO_LIBNUMA + FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma + ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y) + msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev); + else + BASIC_CFLAGS += -DLIBNUMA_SUPPORT + BUILTIN_OBJS += $(OUTPUT)bench/numa.o + EXTLIBS += -lnuma + endif +endif + ifdef ASCIIDOC8 export ASCIIDOC8 endif +endif # MAKECMDGOALS != tags +endif # MAKECMDGOALS != clean + # Shell quote (do not use $(call) to accommodate ancient setups); ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) @@ -884,7 +912,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \ + $(QUIET_CC)$(CC) -include $(OUTPUT)PERF-VERSION-FILE \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@ @@ -948,7 +976,13 @@ $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ - '-DBINDIR="$(bindir_SQ)"' \ + '-DBINDIR="$(bindir_SQ)"' -DPYTHON='"$(PYTHON_WORD)"' \ + $< + +$(OUTPUT)tests/python-use.o: tests/python-use.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \ + -DPYTHONPATH='"$(OUTPUT)python"' \ + -DPYTHON='"$(PYTHON_WORD)"' \ $< $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS @@ -1099,7 +1133,7 @@ perfexec_instdir = $(prefix)/$(perfexecdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) -install: all try-install-man +install-bin: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' @@ -1120,6 +1154,8 @@ install: all try-install-man $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr' +install: install-bin try-install-man + install-python_ext: $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)' diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 3e975cb..aacef07 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -155,6 +155,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env, if (lookup_path(buf)) goto out; free(buf); + buf = NULL; } if (!strcmp(arch, "arm")) diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 8f89998..a5223e6 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -1,6 +1,7 @@ #ifndef BENCH_H #define BENCH_H +extern int bench_numa(int argc, const char **argv, const char *prefix); extern int bench_sched_messaging(int argc, const char **argv, const char *prefix); extern int bench_sched_pipe(int argc, const char **argv, const char *prefix); extern int bench_mem_memcpy(int argc, const char **argv, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c new file mode 100644 index 0000000..30d1c32 --- /dev/null +++ b/tools/perf/bench/numa.c @@ -0,0 +1,1731 @@ +/* + * numa.c + * + * numa: Simulate NUMA-sensitive workload and measure their NUMA performance + */ + +#include "../perf.h" +#include "../builtin.h" +#include "../util/util.h" +#include "../util/parse-options.h" + +#include "bench.h" + +#include <errno.h> +#include <sched.h> +#include <stdio.h> +#include <assert.h> +#include <malloc.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <sys/time.h> +#include <sys/wait.h> +#include <sys/prctl.h> +#include <sys/types.h> + +#include <numa.h> +#include <numaif.h> + +/* + * Regular printout to the terminal, supressed if -q is specified: + */ +#define tprintf(x...) do { if (g && g->p.show_details >= 0) printf(x); } while (0) + +/* + * Debug printf: + */ +#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0) + +struct thread_data { + int curr_cpu; + cpu_set_t bind_cpumask; + int bind_node; + u8 *process_data; + int process_nr; + int thread_nr; + int task_nr; + unsigned int loops_done; + u64 val; + u64 runtime_ns; + pthread_mutex_t *process_lock; +}; + +/* Parameters set by options: */ + +struct params { + /* Startup synchronization: */ + bool serialize_startup; + + /* Task hierarchy: */ + int nr_proc; + int nr_threads; + + /* Working set sizes: */ + const char *mb_global_str; + const char *mb_proc_str; + const char *mb_proc_locked_str; + const char *mb_thread_str; + + double mb_global; + double mb_proc; + double mb_proc_locked; + double mb_thread; + + /* Access patterns to the working set: */ + bool data_reads; + bool data_writes; + bool data_backwards; + bool data_zero_memset; + bool data_rand_walk; + u32 nr_loops; + u32 nr_secs; + u32 sleep_usecs; + + /* Working set initialization: */ + bool init_zero; + bool init_random; + bool init_cpu0; + + /* Misc options: */ + int show_details; + int run_all; + int thp; + + long bytes_global; + long bytes_process; + long bytes_process_locked; + long bytes_thread; + + int nr_tasks; + bool show_quiet; + + bool show_convergence; + bool measure_convergence; + + int perturb_secs; + int nr_cpus; + int nr_nodes; + + /* Affinity options -C and -N: */ + char *cpu_list_str; + char *node_list_str; +}; + + +/* Global, read-writable area, accessible to all processes and threads: */ + +struct global_info { + u8 *data; + + pthread_mutex_t startup_mutex; + int nr_tasks_started; + + pthread_mutex_t startup_done_mutex; + + pthread_mutex_t start_work_mutex; + int nr_tasks_working; + + pthread_mutex_t stop_work_mutex; + u64 bytes_done; + + struct thread_data *threads; + + /* Convergence latency measurement: */ + bool all_converged; + bool stop_work; + + int print_once; + + struct params p; +}; + +static struct global_info *g = NULL; + +static int parse_cpus_opt(const struct option *opt, const char *arg, int unset); +static int parse_nodes_opt(const struct option *opt, const char *arg, int unset); + +struct params p0; + +static const struct option options[] = { + OPT_INTEGER('p', "nr_proc" , &p0.nr_proc, "number of processes"), + OPT_INTEGER('t', "nr_threads" , &p0.nr_threads, "number of threads per process"), + + OPT_STRING('G', "mb_global" , &p0.mb_global_str, "MB", "global memory (MBs)"), + OPT_STRING('P', "mb_proc" , &p0.mb_proc_str, "MB", "process memory (MBs)"), + OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"), + OPT_STRING('T', "mb_thread" , &p0.mb_thread_str, "MB", "thread memory (MBs)"), + + OPT_UINTEGER('l', "nr_loops" , &p0.nr_loops, "max number of loops to run"), + OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run"), + OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), + + OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), + OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"), + OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"), + OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"), + OPT_BOOLEAN('r', "data_rand_walk", &p0.data_rand_walk, "access the data with random (32bit LFSR) walk"), + + + OPT_BOOLEAN('z', "init_zero" , &p0.init_zero, "bzero the initial allocations"), + OPT_BOOLEAN('I', "init_random" , &p0.init_random, "randomize the contents of the initial allocations"), + OPT_BOOLEAN('0', "init_cpu0" , &p0.init_cpu0, "do the initial allocations on CPU#0"), + OPT_INTEGER('x', "perturb_secs", &p0.perturb_secs, "perturb thread 0/0 every X secs, to test convergence stability"), + + OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"), + OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"), + OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), + OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), + OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), + OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "bzero the initial allocations"), + OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), + + /* Special option string parsing callbacks: */ + OPT_CALLBACK('C', "cpus", NULL, "cpu[,cpu2,...cpuN]", + "bind the first N tasks to these specific cpus (the rest is unbound)", + parse_cpus_opt), + OPT_CALLBACK('M', "memnodes", NULL, "node[,node2,...nodeN]", + "bind the first N tasks to these specific memory nodes (the rest is unbound)", + parse_nodes_opt), + OPT_END() +}; + +static const char * const bench_numa_usage[] = { + "perf bench numa <options>", + NULL +}; + +static const char * const numa_usage[] = { + "perf bench numa mem [<options>]", + NULL +}; + +static cpu_set_t bind_to_cpu(int target_cpu) +{ + cpu_set_t orig_mask, mask; + int ret; + + ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); + BUG_ON(ret); + + CPU_ZERO(&mask); + + if (target_cpu == -1) { + int cpu; + + for (cpu = 0; cpu < g->p.nr_cpus; cpu++) + CPU_SET(cpu, &mask); + } else { + BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); + CPU_SET(target_cpu, &mask); + } + + ret = sched_setaffinity(0, sizeof(mask), &mask); + BUG_ON(ret); + + return orig_mask; +} + +static cpu_set_t bind_to_node(int target_node) +{ + int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes; + cpu_set_t orig_mask, mask; + int cpu; + int ret; + + BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus); + BUG_ON(!cpus_per_node); + + ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); + BUG_ON(ret); + + CPU_ZERO(&mask); + + if (target_node == -1) { + for (cpu = 0; cpu < g->p.nr_cpus; cpu++) + CPU_SET(cpu, &mask); + } else { + int cpu_start = (target_node + 0) * cpus_per_node; + int cpu_stop = (target_node + 1) * cpus_per_node; + + BUG_ON(cpu_stop > g->p.nr_cpus); + + for (cpu = cpu_start; cpu < cpu_stop; cpu++) + CPU_SET(cpu, &mask); + } + + ret = sched_setaffinity(0, sizeof(mask), &mask); + BUG_ON(ret); + + return orig_mask; +} + +static void bind_to_cpumask(cpu_set_t mask) +{ + int ret; + + ret = sched_setaffinity(0, sizeof(mask), &mask); + BUG_ON(ret); +} + +static void mempol_restore(void) +{ + int ret; + + ret = set_mempolicy(MPOL_DEFAULT, NULL, g->p.nr_nodes-1); + + BUG_ON(ret); +} + +static void bind_to_memnode(int node) +{ + unsigned long nodemask; + int ret; + + if (node == -1) + return; + + BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)); + nodemask = 1L << node; + + ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8); + dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret); + + BUG_ON(ret); +} + +#define HPSIZE (2*1024*1024) + +#define set_taskname(fmt...) \ +do { \ + char name[20]; \ + \ + snprintf(name, 20, fmt); \ + prctl(PR_SET_NAME, name); \ +} while (0) + +static u8 *alloc_data(ssize_t bytes0, int map_flags, + int init_zero, int init_cpu0, int thp, int init_random) +{ + cpu_set_t orig_mask; + ssize_t bytes; + u8 *buf; + int ret; + + if (!bytes0) + return NULL; + + /* Allocate and initialize all memory on CPU#0: */ + if (init_cpu0) { + orig_mask = bind_to_node(0); + bind_to_memnode(0); + } + + bytes = bytes0 + HPSIZE; + + buf = (void *)mmap(0, bytes, PROT_READ|PROT_WRITE, MAP_ANON|map_flags, -1, 0); + BUG_ON(buf == (void *)-1); + + if (map_flags == MAP_PRIVATE) { + if (thp > 0) { + ret = madvise(buf, bytes, MADV_HUGEPAGE); + if (ret && !g->print_once) { + g->print_once = 1; + printf("WARNING: Could not enable THP - do: 'echo madvise > /sys/kernel/mm/transparent_hugepage/enabled'\n"); + } + } + if (thp < 0) { + ret = madvise(buf, bytes, MADV_NOHUGEPAGE); + if (ret && !g->print_once) { + g->print_once = 1; + printf("WARNING: Could not disable THP: run a CONFIG_TRANSPARENT_HUGEPAGE kernel?\n"); + } + } + } + + if (init_zero) { + bzero(buf, bytes); + } else { + /* Initialize random contents, different in each word: */ + if (init_random) { + u64 *wbuf = (void *)buf; + long off = rand(); + long i; + + for (i = 0; i < bytes/8; i++) + wbuf[i] = i + off; + } + } + + /* Align to 2MB boundary: */ + buf = (void *)(((unsigned long)buf + HPSIZE-1) & ~(HPSIZE-1)); + + /* Restore affinity: */ + if (init_cpu0) { + bind_to_cpumask(orig_mask); + mempol_restore(); + } + + return buf; +} + +static void free_data(void *data, ssize_t bytes) +{ + int ret; + + if (!data) + return; + + ret = munmap(data, bytes); + BUG_ON(ret); +} + +/* + * Create a shared memory buffer that can be shared between processes, zeroed: + */ +static void * zalloc_shared_data(ssize_t bytes) +{ + return alloc_data(bytes, MAP_SHARED, 1, g->p.init_cpu0, g->p.thp, g->p.init_random); +} + +/* + * Create a shared memory buffer that can be shared between processes: + */ +static void * setup_shared_data(ssize_t bytes) +{ + return alloc_data(bytes, MAP_SHARED, 0, g->p.init_cpu0, g->p.thp, g->p.init_random); +} + +/* + * Allocate process-local memory - this will either be shared between + * threads of this process, or only be accessed by this thread: + */ +static void * setup_private_data(ssize_t bytes) +{ + return alloc_data(bytes, MAP_PRIVATE, 0, g->p.init_cpu0, g->p.thp, g->p.init_random); +} + +/* + * Return a process-shared (global) mutex: + */ +static void init_global_mutex(pthread_mutex_t *mutex) +{ + pthread_mutexattr_t attr; + + pthread_mutexattr_init(&attr); + pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED); + pthread_mutex_init(mutex, &attr); +} + +static int parse_cpu_list(const char *arg) +{ + p0.cpu_list_str = strdup(arg); + + dprintf("got CPU list: {%s}\n", p0.cpu_list_str); + + return 0; +} + +static void parse_setup_cpu_list(void) +{ + struct thread_data *td; + char *str0, *str; + int t; + + if (!g->p.cpu_list_str) + return; + + dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); + + str0 = str = strdup(g->p.cpu_list_str); + t = 0; + + BUG_ON(!str); + + tprintf("# binding tasks to CPUs:\n"); + tprintf("# "); + + while (true) { + int bind_cpu, bind_cpu_0, bind_cpu_1; + char *tok, *tok_end, *tok_step, *tok_len, *tok_mul; + int bind_len; + int step; + int mul; + + tok = strsep(&str, ","); + if (!tok) + break; + + tok_end = strstr(tok, "-"); + + dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end); + if (!tok_end) { + /* Single CPU specified: */ + bind_cpu_0 = bind_cpu_1 = atol(tok); + } else { + /* CPU range specified (for example: "5-11"): */ + bind_cpu_0 = atol(tok); + bind_cpu_1 = atol(tok_end + 1); + } + + step = 1; + tok_step = strstr(tok, "#"); + if (tok_step) { + step = atol(tok_step + 1); + BUG_ON(step <= 0 || step >= g->p.nr_cpus); + } + + /* + * Mask length. + * Eg: "--cpus 8_4-16#4" means: '--cpus 8_4,12_4,16_4', + * where the _4 means the next 4 CPUs are allowed. + */ + bind_len = 1; + tok_len = strstr(tok, "_"); + if (tok_len) { + bind_len = atol(tok_len + 1); + BUG_ON(bind_len <= 0 || bind_len > g->p.nr_cpus); + } + + /* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */ + mul = 1; + tok_mul = strstr(tok, "x"); + if (tok_mul) { + mul = atol(tok_mul + 1); + BUG_ON(mul <= 0); + } + + dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul); + + BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus); + BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus); + BUG_ON(bind_cpu_0 > bind_cpu_1); + + for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + int i; + + for (i = 0; i < mul; i++) { + int cpu; + + if (t >= g->p.nr_tasks) { + printf("\n# NOTE: ignoring bind CPUs starting at CPU#%d\n #", bind_cpu); + goto out; + } + td = g->threads + t; + + if (t) + tprintf(","); + if (bind_len > 1) { + tprintf("%2d/%d", bind_cpu, bind_len); + } else { + tprintf("%2d", bind_cpu); + } + + CPU_ZERO(&td->bind_cpumask); + for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { + BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); + CPU_SET(cpu, &td->bind_cpumask); + } + t++; + } + } + } +out: + + tprintf("\n"); + + if (t < g->p.nr_tasks) + printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t); + + free(str0); +} + +static int parse_cpus_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (!arg) + return -1; + + return parse_cpu_list(arg); +} + +static int parse_node_list(const char *arg) +{ + p0.node_list_str = strdup(arg); + + dprintf("got NODE list: {%s}\n", p0.node_list_str); + + return 0; +} + +static void parse_setup_node_list(void) +{ + struct thread_data *td; + char *str0, *str; + int t; + + if (!g->p.node_list_str) + return; + + dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); + + str0 = str = strdup(g->p.node_list_str); + t = 0; + + BUG_ON(!str); + + tprintf("# binding tasks to NODEs:\n"); + tprintf("# "); + + while (true) { + int bind_node, bind_node_0, bind_node_1; + char *tok, *tok_end, *tok_step, *tok_mul; + int step; + int mul; + + tok = strsep(&str, ","); + if (!tok) + break; + + tok_end = strstr(tok, "-"); + + dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end); + if (!tok_end) { + /* Single NODE specified: */ + bind_node_0 = bind_node_1 = atol(tok); + } else { + /* NODE range specified (for example: "5-11"): */ + bind_node_0 = atol(tok); + bind_node_1 = atol(tok_end + 1); + } + + step = 1; + tok_step = strstr(tok, "#"); + if (tok_step) { + step = atol(tok_step + 1); + BUG_ON(step <= 0 || step >= g->p.nr_nodes); + } + + /* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */ + mul = 1; + tok_mul = strstr(tok, "x"); + if (tok_mul) { + mul = atol(tok_mul + 1); + BUG_ON(mul <= 0); + } + + dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step); + + BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes); + BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes); + BUG_ON(bind_node_0 > bind_node_1); + + for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) { + int i; + + for (i = 0; i < mul; i++) { + if (t >= g->p.nr_tasks) { + printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node); + goto out; + } + td = g->threads + t; + + if (!t) + tprintf(" %2d", bind_node); + else + tprintf(",%2d", bind_node); + + td->bind_node = bind_node; + t++; + } + } + } +out: + + tprintf("\n"); + + if (t < g->p.nr_tasks) + printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t); + + free(str0); +} + +static int parse_nodes_opt(const struct option *opt __maybe_unused, + const char *arg, int unset __maybe_unused) +{ + if (!arg) + return -1; + + return parse_node_list(arg); + + return 0; +} + +#define BIT(x) (1ul << x) + +static inline uint32_t lfsr_32(uint32_t lfsr) +{ + const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); + return (lfsr>>1) ^ ((0x0u - (lfsr & 0x1u)) & taps); +} + +/* + * Make sure there's real data dependency to RAM (when read + * accesses are enabled), so the compiler, the CPU and the + * kernel (KSM, zero page, etc.) cannot optimize away RAM + * accesses: + */ +static inline u64 access_data(u64 *data __attribute__((unused)), u64 val) +{ + if (g->p.data_reads) + val += *data; + if (g->p.data_writes) + *data = val + 1; + return val; +} + +/* + * The worker process does two types of work, a forwards going + * loop and a backwards going loop. + * + * We do this so that on multiprocessor systems we do not create + * a 'train' of processing, with highly synchronized processes, + * skewing the whole benchmark. + */ +static u64 do_work(u8 *__data, long bytes, int nr, int nr_max, int loop, u64 val) +{ + long words = bytes/sizeof(u64); + u64 *data = (void *)__data; + long chunk_0, chunk_1; + u64 *d0, *d, *d1; + long off; + long i; + + BUG_ON(!data && words); + BUG_ON(data && !words); + + if (!data) + return val; + + /* Very simple memset() work variant: */ + if (g->p.data_zero_memset && !g->p.data_rand_walk) { + bzero(data, bytes); + return val; + } + + /* Spread out by PID/TID nr and by loop nr: */ + chunk_0 = words/nr_max; + chunk_1 = words/g->p.nr_loops; + off = nr*chunk_0 + loop*chunk_1; + + while (off >= words) + off -= words; + + if (g->p.data_rand_walk) { + u32 lfsr = nr + loop + val; + int j; + + for (i = 0; i < words/1024; i++) { + long start, end; + + lfsr = lfsr_32(lfsr); + + start = lfsr % words; + end = min(start + 1024, words-1); + + if (g->p.data_zero_memset) { + bzero(data + start, (end-start) * sizeof(u64)); + } else { + for (j = start; j < end; j++) + val = access_data(data + j, val); + } + } + } else if (!g->p.data_backwards || (nr + loop) & 1) { + + d0 = data + off; + d = data + off + 1; + d1 = data + words; + + /* Process data forwards: */ + for (;;) { + if (unlikely(d >= d1)) + d = data; + if (unlikely(d == d0)) + break; + + val = access_data(d, val); + + d++; + } + } else { + /* Process data backwards: */ + + d0 = data + off; + d = data + off - 1; + d1 = data + words; + + /* Process data forwards: */ + for (;;) { + if (unlikely(d < data)) + d = data + words-1; + if (unlikely(d == d0)) + break; + + val = access_data(d, val); + + d--; + } + } + + return val; +} + +static void update_curr_cpu(int task_nr, unsigned long bytes_worked) +{ + unsigned int cpu; + + cpu = sched_getcpu(); + + g->threads[task_nr].curr_cpu = cpu; + prctl(0, bytes_worked); +} + +#define MAX_NR_NODES 64 + +/* + * Count the number of nodes a process's threads + * are spread out on. + * + * A count of 1 means that the process is compressed + * to a single node. A count of g->p.nr_nodes means it's + * spread out on the whole system. + */ +static int count_process_nodes(int process_nr) +{ + char node_present[MAX_NR_NODES] = { 0, }; + int nodes; + int n, t; + + for (t = 0; t < g->p.nr_threads; t++) { + struct thread_data *td; + int task_nr; + int node; + + task_nr = process_nr*g->p.nr_threads + t; + td = g->threads + task_nr; + + node = numa_node_of_cpu(td->curr_cpu); + node_present[node] = 1; + } + + nodes = 0; + + for (n = 0; n < MAX_NR_NODES; n++) + nodes += node_present[n]; + + return nodes; +} + +/* + * Count the number of distinct process-threads a node contains. + * + * A count of 1 means that the node contains only a single + * process. If all nodes on the system contain at most one + * process then we are well-converged. + */ +static int count_node_processes(int node) +{ + int processes = 0; + int t, p; + + for (p = 0; p < g->p.nr_proc; p++) { + for (t = 0; t < g->p.nr_threads; t++) { + struct thread_data *td; + int task_nr; + int n; + + task_nr = p*g->p.nr_threads + t; + td = g->threads + task_nr; + + n = numa_node_of_cpu(td->curr_cpu); + if (n == node) { + processes++; + break; + } + } + } + + return processes; +} + +static void calc_convergence_compression(int *strong) +{ + unsigned int nodes_min, nodes_max; + int p; + + nodes_min = -1; + nodes_max = 0; + + for (p = 0; p < g->p.nr_proc; p++) { + unsigned int nodes = count_process_nodes(p); + + nodes_min = min(nodes, nodes_min); + nodes_max = max(nodes, nodes_max); + } + + /* Strong convergence: all threads compress on a single node: */ + if (nodes_min == 1 && nodes_max == 1) { + *strong = 1; + } else { + *strong = 0; + tprintf(" {%d-%d}", nodes_min, nodes_max); + } +} + +static void calc_convergence(double runtime_ns_max, double *convergence) +{ + unsigned int loops_done_min, loops_done_max; + int process_groups; + int nodes[MAX_NR_NODES]; + int distance; + int nr_min; + int nr_max; + int strong; + int sum; + int nr; + int node; + int cpu; + int t; + + if (!g->p.show_convergence && !g->p.measure_convergence) + return; + + for (node = 0; node < g->p.nr_nodes; node++) + nodes[node] = 0; + + loops_done_min = -1; + loops_done_max = 0; + + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + unsigned int loops_done; + + cpu = td->curr_cpu; + + /* Not all threads have written it yet: */ + if (cpu < 0) + continue; + + node = numa_node_of_cpu(cpu); + + nodes[node]++; + + loops_done = td->loops_done; + loops_done_min = min(loops_done, loops_done_min); + loops_done_max = max(loops_done, loops_done_max); + } + + nr_max = 0; + nr_min = g->p.nr_tasks; + sum = 0; + + for (node = 0; node < g->p.nr_nodes; node++) { + nr = nodes[node]; + nr_min = min(nr, nr_min); + nr_max = max(nr, nr_max); + sum += nr; + } + BUG_ON(nr_min > nr_max); + + BUG_ON(sum > g->p.nr_tasks); + + if (0 && (sum < g->p.nr_tasks)) + return; + + /* + * Count the number of distinct process groups present + * on nodes - when we are converged this will decrease + * to g->p.nr_proc: + */ + process_groups = 0; + + for (node = 0; node < g->p.nr_nodes; node++) { + int processes = count_node_processes(node); + + nr = nodes[node]; + tprintf(" %2d/%-2d", nr, processes); + + process_groups += processes; + } + + distance = nr_max - nr_min; + + tprintf(" [%2d/%-2d]", distance, process_groups); + + tprintf(" l:%3d-%-3d (%3d)", + loops_done_min, loops_done_max, loops_done_max-loops_done_min); + + if (loops_done_min && loops_done_max) { + double skew = 1.0 - (double)loops_done_min/loops_done_max; + + tprintf(" [%4.1f%%]", skew * 100.0); + } + + calc_convergence_compression(&strong); + + if (strong && process_groups == g->p.nr_proc) { + if (!*convergence) { + *convergence = runtime_ns_max; + tprintf(" (%6.1fs converged)\n", *convergence/1e9); + if (g->p.measure_convergence) { + g->all_converged = true; + g->stop_work = true; + } + } + } else { + if (*convergence) { + tprintf(" (%6.1fs de-converged)", runtime_ns_max/1e9); + *convergence = 0; + } + tprintf("\n"); + } +} + +static void show_summary(double runtime_ns_max, int l, double *convergence) +{ + tprintf("\r # %5.1f%% [%.1f mins]", + (double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max/1e9 / 60.0); + + calc_convergence(runtime_ns_max, convergence); + + if (g->p.show_details >= 0) + fflush(stdout); +} + +static void *worker_thread(void *__tdata) +{ + struct thread_data *td = __tdata; + struct timeval start0, start, stop, diff; + int process_nr = td->process_nr; + int thread_nr = td->thread_nr; + unsigned long last_perturbance; + int task_nr = td->task_nr; + int details = g->p.show_details; + int first_task, last_task; + double convergence = 0; + u64 val = td->val; + double runtime_ns_max; + u8 *global_data; + u8 *process_data; + u8 *thread_data; + u64 bytes_done; + long work_done; + u32 l; + + bind_to_cpumask(td->bind_cpumask); + bind_to_memnode(td->bind_node); + + set_taskname("thread %d/%d", process_nr, thread_nr); + + global_data = g->data; + process_data = td->process_data; + thread_data = setup_private_data(g->p.bytes_thread); + + bytes_done = 0; + + last_task = 0; + if (process_nr == g->p.nr_proc-1 && thread_nr == g->p.nr_threads-1) + last_task = 1; + + first_task = 0; + if (process_nr == 0 && thread_nr == 0) + first_task = 1; + + if (details >= 2) { + printf("# thread %2d / %2d global mem: %p, process mem: %p, thread mem: %p\n", + process_nr, thread_nr, global_data, process_data, thread_data); + } + + if (g->p.serialize_startup) { + pthread_mutex_lock(&g->startup_mutex); + g->nr_tasks_started++; + pthread_mutex_unlock(&g->startup_mutex); + + /* Here we will wait for the main process to start us all at once: */ + pthread_mutex_lock(&g->start_work_mutex); + g->nr_tasks_working++; + + /* Last one wake the main process: */ + if (g->nr_tasks_working == g->p.nr_tasks) + pthread_mutex_unlock(&g->startup_done_mutex); + + pthread_mutex_unlock(&g->start_work_mutex); + } + + gettimeofday(&start0, NULL); + + start = stop = start0; + last_perturbance = start.tv_sec; + + for (l = 0; l < g->p.nr_loops; l++) { + start = stop; + + if (g->stop_work) + break; + + val += do_work(global_data, g->p.bytes_global, process_nr, g->p.nr_proc, l, val); + val += do_work(process_data, g->p.bytes_process, thread_nr, g->p.nr_threads, l, val); + val += do_work(thread_data, g->p.bytes_thread, 0, 1, l, val); + + if (g->p.sleep_usecs) { + pthread_mutex_lock(td->process_lock); + usleep(g->p.sleep_usecs); + pthread_mutex_unlock(td->process_lock); + } + /* + * Amount of work to be done under a process-global lock: + */ + if (g->p.bytes_process_locked) { + pthread_mutex_lock(td->process_lock); + val += do_work(process_data, g->p.bytes_process_locked, thread_nr, g->p.nr_threads, l, val); + pthread_mutex_unlock(td->process_lock); + } + + work_done = g->p.bytes_global + g->p.bytes_process + + g->p.bytes_process_locked + g->p.bytes_thread; + + update_curr_cpu(task_nr, work_done); + bytes_done += work_done; + + if (details < 0 && !g->p.perturb_secs && !g->p.measure_convergence && !g->p.nr_secs) + continue; + + td->loops_done = l; + + gettimeofday(&stop, NULL); + + /* Check whether our max runtime timed out: */ + if (g->p.nr_secs) { + timersub(&stop, &start0, &diff); + if (diff.tv_sec >= g->p.nr_secs) { + g->stop_work = true; + break; + } + } + + /* Update the summary at most once per second: */ + if (start.tv_sec == stop.tv_sec) + continue; + + /* + * Perturb the first task's equilibrium every g->p.perturb_secs seconds, + * by migrating to CPU#0: + */ + if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { + cpu_set_t orig_mask; + int target_cpu; + int this_cpu; + + last_perturbance = stop.tv_sec; + + /* + * Depending on where we are running, move into + * the other half of the system, to create some + * real disturbance: + */ + this_cpu = g->threads[task_nr].curr_cpu; + if (this_cpu < g->p.nr_cpus/2) + target_cpu = g->p.nr_cpus-1; + else + target_cpu = 0; + + orig_mask = bind_to_cpu(target_cpu); + + /* Here we are running on the target CPU already */ + if (details >= 1) + printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); + + bind_to_cpumask(orig_mask); + } + + if (details >= 3) { + timersub(&stop, &start, &diff); + runtime_ns_max = diff.tv_sec * 1000000000; + runtime_ns_max += diff.tv_usec * 1000; + + if (details >= 0) { + printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n", + process_nr, thread_nr, runtime_ns_max / bytes_done, val); + } + fflush(stdout); + } + if (!last_task) + continue; + + timersub(&stop, &start0, &diff); + runtime_ns_max = diff.tv_sec * 1000000000ULL; + runtime_ns_max += diff.tv_usec * 1000ULL; + + show_summary(runtime_ns_max, l, &convergence); + } + + gettimeofday(&stop, NULL); + timersub(&stop, &start0, &diff); + td->runtime_ns = diff.tv_sec * 1000000000ULL; + td->runtime_ns += diff.tv_usec * 1000ULL; + + free_data(thread_data, g->p.bytes_thread); + + pthread_mutex_lock(&g->stop_work_mutex); + g->bytes_done += bytes_done; + pthread_mutex_unlock(&g->stop_work_mutex); + + return NULL; +} + +/* + * A worker process starts a couple of threads: + */ +static void worker_process(int process_nr) +{ + pthread_mutex_t process_lock; + struct thread_data *td; + pthread_t *pthreads; + u8 *process_data; + int task_nr; + int ret; + int t; + + pthread_mutex_init(&process_lock, NULL); + set_taskname("process %d", process_nr); + + /* + * Pick up the memory policy and the CPU binding of our first thread, + * so that we initialize memory accordingly: + */ + task_nr = process_nr*g->p.nr_threads; + td = g->threads + task_nr; + + bind_to_memnode(td->bind_node); + bind_to_cpumask(td->bind_cpumask); + + pthreads = zalloc(g->p.nr_threads * sizeof(pthread_t)); + process_data = setup_private_data(g->p.bytes_process); + + if (g->p.show_details >= 3) { + printf(" # process %2d global mem: %p, process mem: %p\n", + process_nr, g->data, process_data); + } + + for (t = 0; t < g->p.nr_threads; t++) { + task_nr = process_nr*g->p.nr_threads + t; + td = g->threads + task_nr; + + td->process_data = process_data; + td->process_nr = process_nr; + td->thread_nr = t; + td->task_nr = task_nr; + td->val = rand(); + td->curr_cpu = -1; + td->process_lock = &process_lock; + + ret = pthread_create(pthreads + t, NULL, worker_thread, td); + BUG_ON(ret); + } + + for (t = 0; t < g->p.nr_threads; t++) { + ret = pthread_join(pthreads[t], NULL); + BUG_ON(ret); + } + + free_data(process_data, g->p.bytes_process); + free(pthreads); +} + +static void print_summary(void) +{ + if (g->p.show_details < 0) + return; + + printf("\n ###\n"); + printf(" # %d %s will execute (on %d nodes, %d CPUs):\n", + g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus); + printf(" # %5dx %5ldMB global shared mem operations\n", + g->p.nr_loops, g->p.bytes_global/1024/1024); + printf(" # %5dx %5ldMB process shared mem operations\n", + g->p.nr_loops, g->p.bytes_process/1024/1024); + printf(" # %5dx %5ldMB thread local mem operations\n", + g->p.nr_loops, g->p.bytes_thread/1024/1024); + + printf(" ###\n"); + + printf("\n ###\n"); fflush(stdout); +} + +static void init_thread_data(void) +{ + ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + g->threads = zalloc_shared_data(size); + + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + int cpu; + + /* Allow all nodes by default: */ + td->bind_node = -1; + + /* Allow all CPUs by default: */ + CPU_ZERO(&td->bind_cpumask); + for (cpu = 0; cpu < g->p.nr_cpus; cpu++) + CPU_SET(cpu, &td->bind_cpumask); + } +} + +static void deinit_thread_data(void) +{ + ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + + free_data(g->threads, size); +} + +static int init(void) +{ + g = (void *)alloc_data(sizeof(*g), MAP_SHARED, 1, 0, 0 /* THP */, 0); + + /* Copy over options: */ + g->p = p0; + + g->p.nr_cpus = numa_num_configured_cpus(); + + g->p.nr_nodes = numa_max_node() + 1; + + /* char array in count_process_nodes(): */ + BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0); + + if (g->p.show_quiet && !g->p.show_details) + g->p.show_details = -1; + + /* Some memory should be specified: */ + if (!g->p.mb_global_str && !g->p.mb_proc_str && !g->p.mb_thread_str) + return -1; + + if (g->p.mb_global_str) { + g->p.mb_global = atof(g->p.mb_global_str); + BUG_ON(g->p.mb_global < 0); + } + + if (g->p.mb_proc_str) { + g->p.mb_proc = atof(g->p.mb_proc_str); + BUG_ON(g->p.mb_proc < 0); + } + + if (g->p.mb_proc_locked_str) { + g->p.mb_proc_locked = atof(g->p.mb_proc_locked_str); + BUG_ON(g->p.mb_proc_locked < 0); + BUG_ON(g->p.mb_proc_locked > g->p.mb_proc); + } + + if (g->p.mb_thread_str) { + g->p.mb_thread = atof(g->p.mb_thread_str); + BUG_ON(g->p.mb_thread < 0); + } + + BUG_ON(g->p.nr_threads <= 0); + BUG_ON(g->p.nr_proc <= 0); + + g->p.nr_tasks = g->p.nr_proc*g->p.nr_threads; + + g->p.bytes_global = g->p.mb_global *1024L*1024L; + g->p.bytes_process = g->p.mb_proc *1024L*1024L; + g->p.bytes_process_locked = g->p.mb_proc_locked *1024L*1024L; + g->p.bytes_thread = g->p.mb_thread *1024L*1024L; + + g->data = setup_shared_data(g->p.bytes_global); + + /* Startup serialization: */ + init_global_mutex(&g->start_work_mutex); + init_global_mutex(&g->startup_mutex); + init_global_mutex(&g->startup_done_mutex); + init_global_mutex(&g->stop_work_mutex); + + init_thread_data(); + + tprintf("#\n"); + parse_setup_cpu_list(); + parse_setup_node_list(); + tprintf("#\n"); + + print_summary(); + + return 0; +} + +static void deinit(void) +{ + free_data(g->data, g->p.bytes_global); + g->data = NULL; + + deinit_thread_data(); + + free_data(g, sizeof(*g)); + g = NULL; +} + +/* + * Print a short or long result, depending on the verbosity setting: + */ +static void print_res(const char *name, double val, + const char *txt_unit, const char *txt_short, const char *txt_long) +{ + if (!name) + name = "main,"; + + if (g->p.show_quiet) + printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short); + else + printf(" %14.3f %s\n", val, txt_long); +} + +static int __bench_numa(const char *name) +{ + struct timeval start, stop, diff; + u64 runtime_ns_min, runtime_ns_sum; + pid_t *pids, pid, wpid; + double delta_runtime; + double runtime_avg; + double runtime_sec_max; + double runtime_sec_min; + int wait_stat; + double bytes; + int i, t; + + if (init()) + return -1; + + pids = zalloc(g->p.nr_proc * sizeof(*pids)); + pid = -1; + + /* All threads try to acquire it, this way we can wait for them to start up: */ + pthread_mutex_lock(&g->start_work_mutex); + + if (g->p.serialize_startup) { + tprintf(" #\n"); + tprintf(" # Startup synchronization: ..."); fflush(stdout); + } + + gettimeofday(&start, NULL); + + for (i = 0; i < g->p.nr_proc; i++) { + pid = fork(); + dprintf(" # process %2d: PID %d\n", i, pid); + + BUG_ON(pid < 0); + if (!pid) { + /* Child process: */ + worker_process(i); + + exit(0); + } + pids[i] = pid; + + } + /* Wait for all the threads to start up: */ + while (g->nr_tasks_started != g->p.nr_tasks) + usleep(1000); + + BUG_ON(g->nr_tasks_started != g->p.nr_tasks); + + if (g->p.serialize_startup) { + double startup_sec; + + pthread_mutex_lock(&g->startup_done_mutex); + + /* This will start all threads: */ + pthread_mutex_unlock(&g->start_work_mutex); + + /* This mutex is locked - the last started thread will wake us: */ + pthread_mutex_lock(&g->startup_done_mutex); + + gettimeofday(&stop, NULL); + + timersub(&stop, &start, &diff); + + startup_sec = diff.tv_sec * 1000000000.0; + startup_sec += diff.tv_usec * 1000.0; + startup_sec /= 1e9; + + tprintf(" threads initialized in %.6f seconds.\n", startup_sec); + tprintf(" #\n"); + + start = stop; + pthread_mutex_unlock(&g->startup_done_mutex); + } else { + gettimeofday(&start, NULL); + } + + /* Parent process: */ + + + for (i = 0; i < g->p.nr_proc; i++) { + wpid = waitpid(pids[i], &wait_stat, 0); + BUG_ON(wpid < 0); + BUG_ON(!WIFEXITED(wait_stat)); + + } + + runtime_ns_sum = 0; + runtime_ns_min = -1LL; + + for (t = 0; t < g->p.nr_tasks; t++) { + u64 thread_runtime_ns = g->threads[t].runtime_ns; + + runtime_ns_sum += thread_runtime_ns; + runtime_ns_min = min(thread_runtime_ns, runtime_ns_min); + } + + gettimeofday(&stop, NULL); + timersub(&stop, &start, &diff); + + BUG_ON(bench_format != BENCH_FORMAT_DEFAULT); + + tprintf("\n ###\n"); + tprintf("\n"); + + runtime_sec_max = diff.tv_sec * 1000000000.0; + runtime_sec_max += diff.tv_usec * 1000.0; + runtime_sec_max /= 1e9; + + runtime_sec_min = runtime_ns_min/1e9; + + bytes = g->bytes_done; + runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / 1e9; + + if (g->p.measure_convergence) { + print_res(name, runtime_sec_max, + "secs,", "NUMA-convergence-latency", "secs latency to NUMA-converge"); + } + + print_res(name, runtime_sec_max, + "secs,", "runtime-max/thread", "secs slowest (max) thread-runtime"); + + print_res(name, runtime_sec_min, + "secs,", "runtime-min/thread", "secs fastest (min) thread-runtime"); + + print_res(name, runtime_avg, + "secs,", "runtime-avg/thread", "secs average thread-runtime"); + + delta_runtime = (runtime_sec_max - runtime_sec_min)/2.0; + print_res(name, delta_runtime / runtime_sec_max * 100.0, + "%,", "spread-runtime/thread", "% difference between max/avg runtime"); + + print_res(name, bytes / g->p.nr_tasks / 1e9, + "GB,", "data/thread", "GB data processed, per thread"); + + print_res(name, bytes / 1e9, + "GB,", "data-total", "GB data processed, total"); + + print_res(name, runtime_sec_max * 1e9 / (bytes / g->p.nr_tasks), + "nsecs,", "runtime/byte/thread","nsecs/byte/thread runtime"); + + print_res(name, bytes / g->p.nr_tasks / 1e9 / runtime_sec_max, + "GB/sec,", "thread-speed", "GB/sec/thread speed"); + + print_res(name, bytes / runtime_sec_max / 1e9, + "GB/sec,", "total-speed", "GB/sec total speed"); + + free(pids); + + deinit(); + + return 0; +} + +#define MAX_ARGS 50 + +static int command_size(const char **argv) +{ + int size = 0; + + while (*argv) { + size++; + argv++; + } + + BUG_ON(size >= MAX_ARGS); + + return size; +} + +static void init_params(struct params *p, const char *name, int argc, const char **argv) +{ + int i; + + printf("\n # Running %s \"perf bench numa", name); + + for (i = 0; i < argc; i++) + printf(" %s", argv[i]); + + printf("\"\n"); + + memset(p, 0, sizeof(*p)); + + /* Initialize nonzero defaults: */ + + p->serialize_startup = 1; + p->data_reads = true; + p->data_writes = true; + p->data_backwards = true; + p->data_rand_walk = true; + p->nr_loops = -1; + p->init_random = true; +} + +static int run_bench_numa(const char *name, const char **argv) +{ + int argc = command_size(argv); + + init_params(&p0, name, argc, argv); + argc = parse_options(argc, argv, options, bench_numa_usage, 0); + if (argc) + goto err; + + if (__bench_numa(name)) + goto err; + + return 0; + +err: + usage_with_options(numa_usage, options); + return -1; +} + +#define OPT_BW_RAM "-s", "20", "-zZq", "--thp", " 1", "--no-data_rand_walk" +#define OPT_BW_RAM_NOTHP OPT_BW_RAM, "--thp", "-1" + +#define OPT_CONV "-s", "100", "-zZ0qcm", "--thp", " 1" +#define OPT_CONV_NOTHP OPT_CONV, "--thp", "-1" + +#define OPT_BW "-s", "20", "-zZ0q", "--thp", " 1" +#define OPT_BW_NOTHP OPT_BW, "--thp", "-1" + +/* + * The built-in test-suite executed by "perf bench numa -a". + * + * (A minimum of 4 nodes and 16 GB of RAM is recommended.) + */ +static const char *tests[][MAX_ARGS] = { + /* Basic single-stream NUMA bandwidth measurements: */ + { "RAM-bw-local,", "mem", "-p", "1", "-t", "1", "-P", "1024", + "-C" , "0", "-M", "0", OPT_BW_RAM }, + { "RAM-bw-local-NOTHP,", + "mem", "-p", "1", "-t", "1", "-P", "1024", + "-C" , "0", "-M", "0", OPT_BW_RAM_NOTHP }, + { "RAM-bw-remote,", "mem", "-p", "1", "-t", "1", "-P", "1024", + "-C" , "0", "-M", "1", OPT_BW_RAM }, + + /* 2-stream NUMA bandwidth measurements: */ + { "RAM-bw-local-2x,", "mem", "-p", "2", "-t", "1", "-P", "1024", + "-C", "0,2", "-M", "0x2", OPT_BW_RAM }, + { "RAM-bw-remote-2x,", "mem", "-p", "2", "-t", "1", "-P", "1024", + "-C", "0,2", "-M", "1x2", OPT_BW_RAM }, + + /* Cross-stream NUMA bandwidth measurement: */ + { "RAM-bw-cross,", "mem", "-p", "2", "-t", "1", "-P", "1024", + "-C", "0,8", "-M", "1,0", OPT_BW_RAM }, + + /* Convergence latency measurements: */ + { " 1x3-convergence,", "mem", "-p", "1", "-t", "3", "-P", "512", OPT_CONV }, + { " 1x4-convergence,", "mem", "-p", "1", "-t", "4", "-P", "512", OPT_CONV }, + { " 1x6-convergence,", "mem", "-p", "1", "-t", "6", "-P", "1020", OPT_CONV }, + { " 2x3-convergence,", "mem", "-p", "3", "-t", "3", "-P", "1020", OPT_CONV }, + { " 3x3-convergence,", "mem", "-p", "3", "-t", "3", "-P", "1020", OPT_CONV }, + { " 4x4-convergence,", "mem", "-p", "4", "-t", "4", "-P", "512", OPT_CONV }, + { " 4x4-convergence-NOTHP,", + "mem", "-p", "4", "-t", "4", "-P", "512", OPT_CONV_NOTHP }, + { " 4x6-convergence,", "mem", "-p", "4", "-t", "6", "-P", "1020", OPT_CONV }, + { " 4x8-convergence,", "mem", "-p", "4", "-t", "8", "-P", "512", OPT_CONV }, + { " 8x4-convergence,", "mem", "-p", "8", "-t", "4", "-P", "512", OPT_CONV }, + { " 8x4-convergence-NOTHP,", + "mem", "-p", "8", "-t", "4", "-P", "512", OPT_CONV_NOTHP }, + { " 3x1-convergence,", "mem", "-p", "3", "-t", "1", "-P", "512", OPT_CONV }, + { " 4x1-convergence,", "mem", "-p", "4", "-t", "1", "-P", "512", OPT_CONV }, + { " 8x1-convergence,", "mem", "-p", "8", "-t", "1", "-P", "512", OPT_CONV }, + { "16x1-convergence,", "mem", "-p", "16", "-t", "1", "-P", "256", OPT_CONV }, + { "32x1-convergence,", "mem", "-p", "32", "-t", "1", "-P", "128", OPT_CONV }, + + /* Various NUMA process/thread layout bandwidth measurements: */ + { " 2x1-bw-process,", "mem", "-p", "2", "-t", "1", "-P", "1024", OPT_BW }, + { " 3x1-bw-process,", "mem", "-p", "3", "-t", "1", "-P", "1024", OPT_BW }, + { " 4x1-bw-process,", "mem", "-p", "4", "-t", "1", "-P", "1024", OPT_BW }, + { " 8x1-bw-process,", "mem", "-p", "8", "-t", "1", "-P", " 512", OPT_BW }, + { " 8x1-bw-process-NOTHP,", + "mem", "-p", "8", "-t", "1", "-P", " 512", OPT_BW_NOTHP }, + { "16x1-bw-process,", "mem", "-p", "16", "-t", "1", "-P", "256", OPT_BW }, + + { " 4x1-bw-thread,", "mem", "-p", "1", "-t", "4", "-T", "256", OPT_BW }, + { " 8x1-bw-thread,", "mem", "-p", "1", "-t", "8", "-T", "256", OPT_BW }, + { "16x1-bw-thread,", "mem", "-p", "1", "-t", "16", "-T", "128", OPT_BW }, + { "32x1-bw-thread,", "mem", "-p", "1", "-t", "32", "-T", "64", OPT_BW }, + + { " 2x3-bw-thread,", "mem", "-p", "2", "-t", "3", "-P", "512", OPT_BW }, + { " 4x4-bw-thread,", "mem", "-p", "4", "-t", "4", "-P", "512", OPT_BW }, + { " 4x6-bw-thread,", "mem", "-p", "4", "-t", "6", "-P", "512", OPT_BW }, + { " 4x8-bw-thread,", "mem", "-p", "4", "-t", "8", "-P", "512", OPT_BW }, + { " 4x8-bw-thread-NOTHP,", + "mem", "-p", "4", "-t", "8", "-P", "512", OPT_BW_NOTHP }, + { " 3x3-bw-thread,", "mem", "-p", "3", "-t", "3", "-P", "512", OPT_BW }, + { " 5x5-bw-thread,", "mem", "-p", "5", "-t", "5", "-P", "512", OPT_BW }, + + { "2x16-bw-thread,", "mem", "-p", "2", "-t", "16", "-P", "512", OPT_BW }, + { "1x32-bw-thread,", "mem", "-p", "1", "-t", "32", "-P", "2048", OPT_BW }, + + { "numa02-bw,", "mem", "-p", "1", "-t", "32", "-T", "32", OPT_BW }, + { "numa02-bw-NOTHP,", "mem", "-p", "1", "-t", "32", "-T", "32", OPT_BW_NOTHP }, + { "numa01-bw-thread,", "mem", "-p", "2", "-t", "16", "-T", "192", OPT_BW }, + { "numa01-bw-thread-NOTHP,", + "mem", "-p", "2", "-t", "16", "-T", "192", OPT_BW_NOTHP }, +}; + +static int bench_all(void) +{ + int nr = ARRAY_SIZE(tests); + int ret; + int i; + + ret = system("echo ' #'; echo ' # Running test on: '$(uname -a); echo ' #'"); + BUG_ON(ret < 0); + + for (i = 0; i < nr; i++) { + if (run_bench_numa(tests[i][0], tests[i] + 1)) + return -1; + } + + printf("\n"); + + return 0; +} + +int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused) +{ + init_params(&p0, "main,", argc, argv); + argc = parse_options(argc, argv, options, bench_numa_usage, 0); + if (argc) + goto err; + + if (p0.run_all) + return bench_all(); + + if (__bench_numa(NULL)) + goto err; + + return 0; + +err: + usage_with_options(numa_usage, options); + return -1; +} diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index dc870cf..2e6961e 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -34,9 +34,10 @@ struct perf_annotate { struct perf_tool tool; - bool force, use_tui, use_stdio; + bool force, use_tui, use_stdio, use_gtk; bool full_paths; bool print_line; + bool skip_missing; const char *sym_hist_filter; const char *cpu_list; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); @@ -138,9 +139,22 @@ find_next: continue; } - if (use_browser > 0) { + if (use_browser == 2) { + int ret; + + ret = hist_entry__gtk_annotate(he, evidx, NULL); + if (!ret || !ann->skip_missing) + return; + + /* skip missing symbols */ + nd = rb_next(nd); + } else if (use_browser == 1) { key = hist_entry__tui_annotate(he, evidx, NULL); switch (key) { + case -1: + if (!ann->skip_missing) + return; + /* fall through */ case K_RIGHT: next = rb_next(nd); break; @@ -224,6 +238,10 @@ static int __cmd_annotate(struct perf_annotate *ann) ui__error("The %s file has no samples!\n", session->filename); goto out_delete; } + + if (use_browser == 2) + perf_gtk__show_annotations(); + out_delete: /* * Speed up the exit process, for large files this can @@ -270,6 +288,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"), OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"), OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, @@ -280,6 +299,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) "print matching source lines (may be slow)"), OPT_BOOLEAN('P', "full-paths", &annotate.full_paths, "Don't shorten the displayed pathnames"), + OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing, + "Skip symbols that cannot be annotated"), OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), @@ -300,6 +321,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) use_browser = 0; else if (annotate.use_tui) use_browser = 1; + else if (annotate.use_gtk) + use_browser = 2; setup_browser(true); @@ -309,7 +332,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) if (symbol__init() < 0) return -1; - setup_sorting(annotate_usage, options); + if (setup_sorting() < 0) + usage_with_options(annotate_usage, options); if (argc) { /* diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index cae9a5f..77298bf 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -35,6 +35,18 @@ struct bench_suite { /* sentinel: easy for help */ #define suite_all { "all", "Test all benchmark suites", NULL } +#ifdef LIBNUMA_SUPPORT +static struct bench_suite numa_suites[] = { + { "mem", + "Benchmark for NUMA workloads", + bench_numa }, + suite_all, + { NULL, + NULL, + NULL } +}; +#endif + static struct bench_suite sched_suites[] = { { "messaging", "Benchmark for scheduler and IPC mechanisms", @@ -68,6 +80,11 @@ struct bench_subsys { }; static struct bench_subsys subsystems[] = { +#ifdef LIBNUMA_SUPPORT + { "numa", + "NUMA scheduling and MM behavior", + numa_suites }, +#endif { "sched", "scheduler and IPC mechanism", sched_suites }, @@ -159,6 +176,7 @@ static void all_suite(struct bench_subsys *subsys) /* FROM HERE */ printf("# Running %s/%s benchmark...\n", subsys->name, suites[i].name); + fflush(stdout); argv[1] = suites[i].name; suites[i].fn(1, argv, NULL); @@ -225,6 +243,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) printf("# Running %s/%s benchmark...\n", subsystems[i].name, subsystems[i].suites[j].name); + fflush(stdout); status = subsystems[i].suites[j].fn(argc - 1, argv + 1, prefix); goto end; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index fae8b25..c96c8fa 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -14,6 +14,7 @@ #include "util/parse-options.h" #include "util/strlist.h" #include "util/build-id.h" +#include "util/session.h" #include "util/symbol.h" static int build_id_cache__add_file(const char *filename, const char *debugdir) @@ -58,19 +59,89 @@ static int build_id_cache__remove_file(const char *filename, return err; } +static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) +{ + char filename[PATH_MAX]; + u8 build_id[BUILD_ID_SIZE]; + + if (dso__build_id_filename(dso, filename, sizeof(filename)) && + filename__read_build_id(filename, build_id, + sizeof(build_id)) != sizeof(build_id)) { + if (errno == ENOENT) + return false; + + pr_warning("Problems with %s file, consider removing it from the cache\n", + filename); + } else if (memcmp(dso->build_id, build_id, sizeof(dso->build_id))) { + pr_warning("Problems with %s file, consider removing it from the cache\n", + filename); + } + + return true; +} + +static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp) +{ + struct perf_session *session = perf_session__new(filename, O_RDONLY, + force, false, NULL); + if (session == NULL) + return -1; + + perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0); + perf_session__delete(session); + + return 0; +} + +static int build_id_cache__update_file(const char *filename, + const char *debugdir) +{ + u8 build_id[BUILD_ID_SIZE]; + char sbuild_id[BUILD_ID_SIZE * 2 + 1]; + + int err; + + if (filename__read_build_id(filename, &build_id, sizeof(build_id)) < 0) { + pr_debug("Couldn't read a build-id in %s\n", filename); + return -1; + } + + build_id__sprintf(build_id, sizeof(build_id), sbuild_id); + err = build_id_cache__remove_s(sbuild_id, debugdir); + if (!err) { + err = build_id_cache__add_s(sbuild_id, debugdir, filename, + false, false); + } + if (verbose) + pr_info("Updating %s %s: %s\n", sbuild_id, filename, + err ? "FAIL" : "Ok"); + + return err; +} + int cmd_buildid_cache(int argc, const char **argv, const char *prefix __maybe_unused) { struct strlist *list; struct str_node *pos; + int ret = 0; + bool force = false; char debugdir[PATH_MAX]; char const *add_name_list_str = NULL, - *remove_name_list_str = NULL; + *remove_name_list_str = NULL, + *missing_filename = NULL, + *update_name_list_str = NULL; + const struct option buildid_cache_options[] = { OPT_STRING('a', "add", &add_name_list_str, "file list", "file(s) to add"), OPT_STRING('r', "remove", &remove_name_list_str, "file list", "file(s) to remove"), + OPT_STRING('M', "missing", &missing_filename, "file", + "to find missing build ids in the cache"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), + OPT_STRING('u', "update", &update_name_list_str, "file list", + "file(s) to update"), OPT_INCR('v', "verbose", &verbose, "be more verbose"), OPT_END() }; @@ -125,5 +196,26 @@ int cmd_buildid_cache(int argc, const char **argv, } } - return 0; + if (missing_filename) + ret = build_id_cache__fprintf_missing(missing_filename, force, stdout); + + if (update_name_list_str) { + list = strlist__new(true, update_name_list_str); + if (list) { + strlist__for_each(pos, list) + if (build_id_cache__update_file(pos->s, debugdir)) { + if (errno == ENOENT) { + pr_debug("%s wasn't in the cache\n", + pos->s); + continue; + } + pr_warning("Couldn't update %s: %s\n", + pos->s, strerror(errno)); + } + + strlist__delete(list); + } + } + + return ret; } diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index a82d99f..e74366a 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -44,23 +44,26 @@ static int filename__fprintf_build_id(const char *name, FILE *fp) return fprintf(fp, "%s\n", sbuild_id); } +static bool dso__skip_buildid(struct dso *dso, int with_hits) +{ + return with_hits && !dso->hit; +} + static int perf_session__list_build_ids(bool force, bool with_hits) { struct perf_session *session; symbol__elf_init(); - - session = perf_session__new(input_name, O_RDONLY, force, false, - &build_id__mark_dso_hit_ops); - if (session == NULL) - return -1; - /* * See if this is an ELF file first: */ - if (filename__fprintf_build_id(session->filename, stdout)) + if (filename__fprintf_build_id(input_name, stdout)) goto out; + session = perf_session__new(input_name, O_RDONLY, force, false, + &build_id__mark_dso_hit_ops); + if (session == NULL) + return -1; /* * in pipe-mode, the only way to get the buildids is to parse * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID @@ -68,9 +71,9 @@ static int perf_session__list_build_ids(bool force, bool with_hits) if (with_hits || session->fd_pipe) perf_session__process_events(session, &build_id__mark_dso_hit_ops); - perf_session__fprintf_dsos_buildid(session, stdout, with_hits); -out: + perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits); perf_session__delete(session); +out: return 0; } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 93b852f..d207a97 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -23,7 +23,6 @@ static char const *input_old = "perf.data.old", *input_new = "perf.data"; static char diff__default_sort_order[] = "dso,symbol"; static bool force; -static bool show_displacement; static bool show_period; static bool show_formula; static bool show_baseline_only; @@ -146,58 +145,47 @@ static int setup_compute(const struct option *opt, const char *str, return -EINVAL; } -static double get_period_percent(struct hist_entry *he, u64 period) +double perf_diff__period_percent(struct hist_entry *he, u64 period) { u64 total = he->hists->stats.total_period; return (period * 100.0) / total; } -double perf_diff__compute_delta(struct hist_entry *he) +double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair) { - struct hist_entry *pair = hist_entry__next_pair(he); - double new_percent = get_period_percent(he, he->stat.period); - double old_percent = pair ? get_period_percent(pair, pair->stat.period) : 0.0; + double new_percent = perf_diff__period_percent(he, he->stat.period); + double old_percent = perf_diff__period_percent(pair, pair->stat.period); he->diff.period_ratio_delta = new_percent - old_percent; he->diff.computed = true; return he->diff.period_ratio_delta; } -double perf_diff__compute_ratio(struct hist_entry *he) +double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair) { - struct hist_entry *pair = hist_entry__next_pair(he); double new_period = he->stat.period; - double old_period = pair ? pair->stat.period : 0; + double old_period = pair->stat.period; he->diff.computed = true; - he->diff.period_ratio = pair ? (new_period / old_period) : 0; + he->diff.period_ratio = new_period / old_period; return he->diff.period_ratio; } -s64 perf_diff__compute_wdiff(struct hist_entry *he) +s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair) { - struct hist_entry *pair = hist_entry__next_pair(he); u64 new_period = he->stat.period; - u64 old_period = pair ? pair->stat.period : 0; + u64 old_period = pair->stat.period; he->diff.computed = true; - - if (!pair) - he->diff.wdiff = 0; - else - he->diff.wdiff = new_period * compute_wdiff_w2 - - old_period * compute_wdiff_w1; + he->diff.wdiff = new_period * compute_wdiff_w2 - + old_period * compute_wdiff_w1; return he->diff.wdiff; } -static int formula_delta(struct hist_entry *he, char *buf, size_t size) +static int formula_delta(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) { - struct hist_entry *pair = hist_entry__next_pair(he); - - if (!pair) - return -1; - return scnprintf(buf, size, "(%" PRIu64 " * 100 / %" PRIu64 ") - " "(%" PRIu64 " * 100 / %" PRIu64 ")", @@ -205,41 +193,36 @@ static int formula_delta(struct hist_entry *he, char *buf, size_t size) pair->stat.period, pair->hists->stats.total_period); } -static int formula_ratio(struct hist_entry *he, char *buf, size_t size) +static int formula_ratio(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) { - struct hist_entry *pair = hist_entry__next_pair(he); double new_period = he->stat.period; - double old_period = pair ? pair->stat.period : 0; - - if (!pair) - return -1; + double old_period = pair->stat.period; return scnprintf(buf, size, "%.0F / %.0F", new_period, old_period); } -static int formula_wdiff(struct hist_entry *he, char *buf, size_t size) +static int formula_wdiff(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) { - struct hist_entry *pair = hist_entry__next_pair(he); u64 new_period = he->stat.period; - u64 old_period = pair ? pair->stat.period : 0; - - if (!pair) - return -1; + u64 old_period = pair->stat.period; return scnprintf(buf, size, "(%" PRIu64 " * " "%" PRId64 ") - (%" PRIu64 " * " "%" PRId64 ")", new_period, compute_wdiff_w2, old_period, compute_wdiff_w1); } -int perf_diff__formula(char *buf, size_t size, struct hist_entry *he) +int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size) { switch (compute) { case COMPUTE_DELTA: - return formula_delta(he, buf, size); + return formula_delta(he, pair, buf, size); case COMPUTE_RATIO: - return formula_ratio(he, buf, size); + return formula_ratio(he, pair, buf, size); case COMPUTE_WEIGHTED_DIFF: - return formula_wdiff(he, buf, size); + return formula_wdiff(he, pair, buf, size); default: BUG_ON(1); } @@ -292,48 +275,6 @@ static struct perf_tool tool = { .ordering_requires_timestamps = true, }; -static void insert_hist_entry_by_name(struct rb_root *root, - struct hist_entry *he) -{ - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct hist_entry *iter; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hist_entry, rb_node); - if (hist_entry__cmp(he, iter) < 0) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, root); -} - -static void hists__name_resort(struct hists *self, bool sort) -{ - unsigned long position = 1; - struct rb_root tmp = RB_ROOT; - struct rb_node *next = rb_first(&self->entries); - - while (next != NULL) { - struct hist_entry *n = rb_entry(next, struct hist_entry, rb_node); - - next = rb_next(&n->rb_node); - n->position = position++; - - if (sort) { - rb_erase(&n->rb_node, &self->entries); - insert_hist_entry_by_name(&tmp, n); - } - } - - if (sort) - self->entries = tmp; -} - static struct perf_evsel *evsel_match(struct perf_evsel *evsel, struct perf_evlist *evlist) { @@ -346,34 +287,34 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel, return NULL; } -static void perf_evlist__resort_hists(struct perf_evlist *evlist, bool name) +static void perf_evlist__collapse_resort(struct perf_evlist *evlist) { struct perf_evsel *evsel; list_for_each_entry(evsel, &evlist->entries, node) { struct hists *hists = &evsel->hists; - hists__output_resort(hists); - - /* - * The hists__name_resort only sets possition - * if name is false. - */ - if (name || ((!name) && show_displacement)) - hists__name_resort(hists, name); + hists__collapse_resort(hists); } } static void hists__baseline_only(struct hists *hists) { - struct rb_node *next = rb_first(&hists->entries); + struct rb_root *root; + struct rb_node *next; + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + next = rb_first(root); while (next != NULL) { - struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in); - next = rb_next(&he->rb_node); + next = rb_next(&he->rb_node_in); if (!hist_entry__next_pair(he)) { - rb_erase(&he->rb_node, &hists->entries); + rb_erase(&he->rb_node_in, root); hist_entry__free(he); } } @@ -385,18 +326,21 @@ static void hists__precompute(struct hists *hists) while (next != NULL) { struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + struct hist_entry *pair = hist_entry__next_pair(he); next = rb_next(&he->rb_node); + if (!pair) + continue; switch (compute) { case COMPUTE_DELTA: - perf_diff__compute_delta(he); + perf_diff__compute_delta(he, pair); break; case COMPUTE_RATIO: - perf_diff__compute_ratio(he); + perf_diff__compute_ratio(he, pair); break; case COMPUTE_WEIGHTED_DIFF: - perf_diff__compute_wdiff(he); + perf_diff__compute_wdiff(he, pair); break; default: BUG_ON(1); @@ -470,19 +414,30 @@ static void insert_hist_entry_by_compute(struct rb_root *root, static void hists__compute_resort(struct hists *hists) { - struct rb_root tmp = RB_ROOT; - struct rb_node *next = rb_first(&hists->entries); + struct rb_root *root; + struct rb_node *next; + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + hists->entries = RB_ROOT; + next = rb_first(root); + + hists->nr_entries = 0; + hists->stats.total_period = 0; + hists__reset_col_len(hists); while (next != NULL) { - struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node); + struct hist_entry *he; - next = rb_next(&he->rb_node); + he = rb_entry(next, struct hist_entry, rb_node_in); + next = rb_next(&he->rb_node_in); - rb_erase(&he->rb_node, &hists->entries); - insert_hist_entry_by_compute(&tmp, he, compute); + insert_hist_entry_by_compute(&hists->entries, he, compute); + hists__inc_nr_entries(hists, he); } - - hists->entries = tmp; } static void hists__process(struct hists *old, struct hists *new) @@ -497,6 +452,8 @@ static void hists__process(struct hists *old, struct hists *new) if (sort_compute) { hists__precompute(new); hists__compute_resort(new); + } else { + hists__output_resort(new); } hists__fprintf(new, true, 0, 0, stdout); @@ -528,8 +485,8 @@ static int __cmd_diff(void) evlist_old = older->evlist; evlist_new = newer->evlist; - perf_evlist__resort_hists(evlist_old, true); - perf_evlist__resort_hists(evlist_new, false); + perf_evlist__collapse_resort(evlist_old); + perf_evlist__collapse_resort(evlist_new); list_for_each_entry(evsel, &evlist_new->entries, node) { struct perf_evsel *evsel_old; @@ -562,8 +519,6 @@ static const char * const diff_usage[] = { static const struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('M', "displacement", &show_displacement, - "Show position displacement relative to baseline"), OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, "Show only items with match in baseline"), OPT_CALLBACK('c', "compute", &compute, @@ -597,40 +552,32 @@ static const struct option options[] = { static void ui_init(void) { - perf_hpp__init(); - - /* No overhead column. */ - perf_hpp__column_enable(PERF_HPP__OVERHEAD, false); - /* - * Display baseline/delta/ratio/displacement/ + * Display baseline/delta/ratio * formula/periods columns. */ - perf_hpp__column_enable(PERF_HPP__BASELINE, true); + perf_hpp__column_enable(PERF_HPP__BASELINE); switch (compute) { case COMPUTE_DELTA: - perf_hpp__column_enable(PERF_HPP__DELTA, true); + perf_hpp__column_enable(PERF_HPP__DELTA); break; case COMPUTE_RATIO: - perf_hpp__column_enable(PERF_HPP__RATIO, true); + perf_hpp__column_enable(PERF_HPP__RATIO); break; case COMPUTE_WEIGHTED_DIFF: - perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF, true); + perf_hpp__column_enable(PERF_HPP__WEIGHTED_DIFF); break; default: BUG_ON(1); }; - if (show_displacement) - perf_hpp__column_enable(PERF_HPP__DISPL, true); - if (show_formula) - perf_hpp__column_enable(PERF_HPP__FORMULA, true); + perf_hpp__column_enable(PERF_HPP__FORMULA); if (show_period) { - perf_hpp__column_enable(PERF_HPP__PERIOD, true); - perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE, true); + perf_hpp__column_enable(PERF_HPP__PERIOD); + perf_hpp__column_enable(PERF_HPP__PERIOD_BASELINE); } } @@ -658,7 +605,9 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) ui_init(); - setup_sorting(diff_usage, options); + if (setup_sorting() < 0) + usage_with_options(diff_usage, options); + setup_pager(); sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", NULL); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index c20f1dc..05bd9df 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -15,39 +15,6 @@ #include "util/parse-options.h" #include "util/session.h" -struct perf_attr_details { - bool freq; - bool verbose; -}; - -static int comma_printf(bool *first, const char *fmt, ...) -{ - va_list args; - int ret = 0; - - if (!*first) { - ret += printf(","); - } else { - ret += printf(":"); - *first = false; - } - - va_start(args, fmt); - ret += vprintf(fmt, args); - va_end(args); - return ret; -} - -static int __if_print(bool *first, const char *field, u64 value) -{ - if (value == 0) - return 0; - - return comma_printf(first, " %s: %" PRIu64, field, value); -} - -#define if_print(field) __if_print(&first, #field, pos->attr.field) - static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { struct perf_session *session; @@ -57,52 +24,8 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details if (session == NULL) return -ENOMEM; - list_for_each_entry(pos, &session->evlist->entries, node) { - bool first = true; - - printf("%s", perf_evsel__name(pos)); - - if (details->verbose || details->freq) { - comma_printf(&first, " sample_freq=%" PRIu64, - (u64)pos->attr.sample_freq); - } - - if (details->verbose) { - if_print(type); - if_print(config); - if_print(config1); - if_print(config2); - if_print(size); - if_print(sample_type); - if_print(read_format); - if_print(disabled); - if_print(inherit); - if_print(pinned); - if_print(exclusive); - if_print(exclude_user); - if_print(exclude_kernel); - if_print(exclude_hv); - if_print(exclude_idle); - if_print(mmap); - if_print(comm); - if_print(freq); - if_print(inherit_stat); - if_print(enable_on_exec); - if_print(task); - if_print(watermark); - if_print(precise_ip); - if_print(mmap_data); - if_print(sample_id_all); - if_print(exclude_host); - if_print(exclude_guest); - if_print(__reserved_1); - if_print(wakeup_events); - if_print(bp_type); - if_print(branch_sample_type); - } - - putchar('\n'); - } + list_for_each_entry(pos, &session->evlist->entries, node) + perf_evsel__fprintf(pos, details, stdout); perf_session__delete(session); return 0; @@ -116,6 +39,8 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('F', "freq", &details.freq, "Show the sample frequency"), OPT_BOOLEAN('v', "verbose", &details.verbose, "Show all event attr details"), + OPT_BOOLEAN('g', "group", &details.event_group, + "Show event group information"), OPT_END() }; const char * const evlist_usage[] = { @@ -127,5 +52,10 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(evlist_usage, options); + if (details.event_group && (details.verbose || details.freq)) { + pr_err("--group option is not compatible with other options\n"); + usage_with_options(evlist_usage, options); + } + return __cmd_evlist(input_name, &details); } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 0b4b796..46878da 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -17,6 +17,7 @@ #include "util/debug.h" #include <linux/rbtree.h> +#include <linux/string.h> struct alloc_stat; typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *); @@ -340,7 +341,7 @@ static void __print_result(struct rb_root *root, struct perf_session *session, int n_lines, int is_caller) { struct rb_node *next; - struct machine *machine; + struct machine *machine = &session->machines.host; printf("%.102s\n", graph_dotted_line); printf(" %-34s |", is_caller ? "Callsite": "Alloc Ptr"); @@ -349,11 +350,6 @@ static void __print_result(struct rb_root *root, struct perf_session *session, next = rb_first(root); - machine = perf_session__find_host_machine(session); - if (!machine) { - pr_err("__print_result: couldn't find kernel information\n"); - return; - } while (next && n_lines--) { struct alloc_stat *data = rb_entry(next, struct alloc_stat, node); @@ -614,8 +610,7 @@ static struct sort_dimension *avail_sorts[] = { &pingpong_sort_dimension, }; -#define NUM_AVAIL_SORTS \ - (int)(sizeof(avail_sorts) / sizeof(struct sort_dimension *)) +#define NUM_AVAIL_SORTS ((int)ARRAY_SIZE(avail_sorts)) static int sort_dimension__add(const char *tok, struct list_head *list) { @@ -624,12 +619,11 @@ static int sort_dimension__add(const char *tok, struct list_head *list) for (i = 0; i < NUM_AVAIL_SORTS; i++) { if (!strcmp(avail_sorts[i]->name, tok)) { - sort = malloc(sizeof(*sort)); + sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i])); if (!sort) { - pr_err("%s: malloc failed\n", __func__); + pr_err("%s: memdup failed\n", __func__); return -1; } - memcpy(sort, avail_sorts[i], sizeof(*sort)); list_add_tail(&sort->list, list); return 0; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index ca3f80e..37a769d 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -973,8 +973,7 @@ __cmd_buildid_list(const char *file_name, int argc, const char **argv) int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) { - const char *file_name; - + const char *file_name = NULL; const struct option kvm_options[] = { OPT_STRING('i', "input", &file_name, "file", "Input file name"), diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f3151d3..774c907 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -224,130 +224,28 @@ static bool perf_evlist__equal(struct perf_evlist *evlist, static int perf_record__open(struct perf_record *rec) { + char msg[512]; struct perf_evsel *pos; struct perf_evlist *evlist = rec->evlist; struct perf_session *session = rec->session; struct perf_record_opts *opts = &rec->opts; int rc = 0; - /* - * Set the evsel leader links before we configure attributes, - * since some might depend on this info. - */ - if (opts->group) - perf_evlist__set_leader(evlist); - - perf_evlist__config_attrs(evlist, opts); + perf_evlist__config(evlist, opts); list_for_each_entry(pos, &evlist->entries, node) { - struct perf_event_attr *attr = &pos->attr; - /* - * Check if parse_single_tracepoint_event has already asked for - * PERF_SAMPLE_TIME. - * - * XXX this is kludgy but short term fix for problems introduced by - * eac23d1c that broke 'perf script' by having different sample_types - * when using multiple tracepoint events when we use a perf binary - * that tries to use sample_id_all on an older kernel. - * - * We need to move counter creation to perf_session, support - * different sample_types, etc. - */ - bool time_needed = attr->sample_type & PERF_SAMPLE_TIME; - -fallback_missing_features: - if (opts->exclude_guest_missing) - attr->exclude_guest = attr->exclude_host = 0; -retry_sample_id: - attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) { - int err = errno; - - if (err == EPERM || err == EACCES) { - ui__error_paranoid(); - rc = -err; - goto out; - } else if (err == ENODEV && opts->target.cpu_list) { - pr_err("No such device - did you specify" - " an out-of-range profile CPU?\n"); - rc = -err; - goto out; - } else if (err == EINVAL) { - if (!opts->exclude_guest_missing && - (attr->exclude_guest || attr->exclude_host)) { - pr_debug("Old kernel, cannot exclude " - "guest or host samples.\n"); - opts->exclude_guest_missing = true; - goto fallback_missing_features; - } else if (!opts->sample_id_all_missing) { - /* - * Old kernel, no attr->sample_id_type_all field - */ - opts->sample_id_all_missing = true; - if (!opts->sample_time && !opts->raw_samples && !time_needed) - attr->sample_type &= ~PERF_SAMPLE_TIME; - - goto retry_sample_id; - } - } - - /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support. - * - * PPC returns ENXIO until 2.6.37 (behavior changed - * with commit b0a873e). - */ - if ((err == ENOENT || err == ENXIO) - && attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { - + if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) { if (verbose) - ui__warning("The cycles event is not supported, " - "trying to fall back to cpu-clock-ticks\n"); - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - if (pos->name) { - free(pos->name); - pos->name = NULL; - } + ui__warning("%s\n", msg); goto try_again; } - if (err == ENOENT) { - ui__error("The %s event is not supported.\n", - perf_evsel__name(pos)); - rc = -err; - goto out; - } else if ((err == EOPNOTSUPP) && (attr->precise_ip)) { - ui__error("\'precise\' request may not be supported. " - "Try removing 'p' modifier\n"); - rc = -err; - goto out; - } - - printf("\n"); - error("sys_perf_event_open() syscall returned with %d " - "(%s) for event %s. /bin/dmesg may provide " - "additional information.\n", - err, strerror(err), perf_evsel__name(pos)); - -#if defined(__i386__) || defined(__x86_64__) - if (attr->type == PERF_TYPE_HARDWARE && - err == EOPNOTSUPP) { - pr_err("No hardware sampling interrupt available." - " No APIC? If so then you can boot the kernel" - " with the \"lapic\" boot parameter to" - " force-enable it.\n"); - rc = -err; - goto out; - } -#endif - - pr_err("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - rc = -err; + rc = -errno; + perf_evsel__open_strerror(pos, &opts->target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); goto out; } } @@ -430,10 +328,6 @@ static void perf_event__synthesize_guest_os(struct machine *machine, void *data) { int err; struct perf_tool *tool = data; - - if (machine__is_host(machine)) - return; - /* *As for guest kernel when processing subcommand record&report, *we arrange module mmap prior to guest kernel mmap and trigger @@ -592,6 +486,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) goto out_delete_session; } + if (!evsel_list->nr_groups) + perf_header__clear_feat(&session->header, HEADER_GROUP_DESC); + /* * perf_session__delete(session) will be called at perf_record__exit() */ @@ -618,12 +515,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) rec->post_processing_offset = lseek(output, 0, SEEK_CUR); - machine = perf_session__find_host_machine(session); - if (!machine) { - pr_err("Couldn't find native kernel information.\n"); - err = -1; - goto out_delete_session; - } + machine = &session->machines.host; if (opts->pipe_output) { err = perf_event__synthesize_attrs(tool, session, @@ -676,9 +568,10 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" "Check /proc/modules permission or run as root.\n"); - if (perf_guest) - perf_session__process_machines(session, tool, - perf_event__synthesize_guest_os); + if (perf_guest) { + machines__process_guests(&session->machines, + perf_event__synthesize_guest_os, tool); + } if (!opts->target.system_wide) err = perf_event__synthesize_thread_map(tool, evsel_list->threads, @@ -875,11 +768,10 @@ static int get_stack_size(char *str, unsigned long *_size) } #endif /* LIBUNWIND_SUPPORT */ -static int -parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, - int unset) +int record_parse_callchain_opt(const struct option *opt, + const char *arg, int unset) { - struct perf_record *rec = (struct perf_record *)opt->value; + struct perf_record_opts *opts = opt->value; char *tok, *name, *saveptr = NULL; char *buf; int ret = -1; @@ -905,7 +797,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, /* Framepointer style */ if (!strncmp(name, "fp", sizeof("fp"))) { if (!strtok_r(NULL, ",", &saveptr)) { - rec->opts.call_graph = CALLCHAIN_FP; + opts->call_graph = CALLCHAIN_FP; ret = 0; } else pr_err("callchain: No more arguments " @@ -918,20 +810,20 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, const unsigned long default_stack_dump_size = 8192; ret = 0; - rec->opts.call_graph = CALLCHAIN_DWARF; - rec->opts.stack_dump_size = default_stack_dump_size; + opts->call_graph = CALLCHAIN_DWARF; + opts->stack_dump_size = default_stack_dump_size; tok = strtok_r(NULL, ",", &saveptr); if (tok) { unsigned long size = 0; ret = get_stack_size(tok, &size); - rec->opts.stack_dump_size = size; + opts->stack_dump_size = size; } if (!ret) pr_debug("callchain: stack dump size %d\n", - rec->opts.stack_dump_size); + opts->stack_dump_size); #endif /* LIBUNWIND_SUPPORT */ } else { pr_err("callchain: Unknown -g option " @@ -944,7 +836,7 @@ parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg, free(buf); if (!ret) - pr_debug("callchain: type %d\n", rec->opts.call_graph); + pr_debug("callchain: type %d\n", opts->call_graph); return ret; } @@ -982,9 +874,9 @@ static struct perf_record record = { #define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " #ifdef LIBUNWIND_SUPPORT -static const char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; #else -static const char callchain_help[] = CALLCHAIN_HELP "[fp]"; +const char record_callchain_help[] = CALLCHAIN_HELP "[fp]"; #endif /* @@ -1028,9 +920,9 @@ const struct option record_options[] = { "number of mmap data pages"), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]", - callchain_help, &parse_callchain_opt, - "fp"), + OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts, + "mode[,dump_size]", record_callchain_help, + &record_parse_callchain_opt, "fp"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index fc25100..96b5a7f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -8,6 +8,7 @@ #include "builtin.h" #include "util/util.h" +#include "util/cache.h" #include "util/annotate.h" #include "util/color.h" @@ -54,6 +55,16 @@ struct perf_report { DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; +static int perf_report_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "report.group")) { + symbol_conf.event_group = perf_config_bool(var, value); + return 0; + } + + return perf_default_config(var, value, cb); +} + static int perf_report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al, struct perf_sample *sample, @@ -299,6 +310,21 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, char unit; unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = self->stats.total_period; + struct perf_evsel *evsel = hists_to_evsel(self); + char buf[512]; + size_t size = sizeof(buf); + + if (symbol_conf.event_group && evsel->nr_members > 1) { + struct perf_evsel *pos; + + perf_evsel__group_desc(evsel, buf, size); + evname = buf; + + for_each_group_member(pos, evsel) { + nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos->hists.stats.total_period; + } + } nr_samples = convert_unit(nr_samples, &unit); ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit); @@ -319,6 +345,10 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, struct hists *hists = &pos->hists; const char *evname = perf_evsel__name(pos); + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) + continue; + hists__fprintf_nr_sample_events(hists, evname, stdout); hists__fprintf(hists, true, 0, 0, stdout); fprintf(stdout, "\n\n"); @@ -372,7 +402,7 @@ static int __cmd_report(struct perf_report *rep) if (ret) goto out_delete; - kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION]; + kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION]; kernel_kmap = map__kmap(kernel_map); if (kernel_map == NULL || (kernel_map->dso->hit && @@ -416,8 +446,16 @@ static int __cmd_report(struct perf_report *rep) hists->symbol_filter_str = rep->symbol_filter_str; hists__collapse_resort(hists); - hists__output_resort(hists); nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE]; + + /* Non-group events are considered as leader */ + if (symbol_conf.event_group && + !perf_evsel__is_group_leader(pos)) { + struct hists *leader_hists = &pos->leader->hists; + + hists__match(leader_hists, hists); + hists__link(leader_hists, hists); + } } if (nr_samples == 0) { @@ -425,11 +463,22 @@ static int __cmd_report(struct perf_report *rep) goto out_delete; } + list_for_each_entry(pos, &session->evlist->entries, node) + hists__output_resort(&pos->hists); + if (use_browser > 0) { if (use_browser == 1) { - perf_evlist__tui_browse_hists(session->evlist, help, - NULL, - &session->header.env); + ret = perf_evlist__tui_browse_hists(session->evlist, + help, + NULL, + &session->header.env); + /* + * Usually "ret" is the last pressed key, and we only + * care if the key notifies us to switch data file. + */ + if (ret != K_SWITCH_INPUT_DATA) + ret = 0; + } else if (use_browser == 2) { perf_evlist__gtk_browse_hists(session->evlist, help, NULL); @@ -595,8 +644,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "stdio", &report.use_stdio, "Use the stdio interface"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent, dso_to," - " dso_from, symbol_to, symbol_from, mispredict"), + "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline," + " dso_to, dso_from, symbol_to, symbol_from, mispredict"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -638,6 +687,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), + OPT_BOOLEAN(0, "group", &symbol_conf.event_group, + "Show event group information together"), OPT_CALLBACK_NOOPT('b', "branch-stack", &sort__branch_mode, "", "use branch records for histogram filling", parse_branch_mode), OPT_STRING(0, "objdump", &objdump_path, "path", @@ -645,6 +696,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_END() }; + perf_config(perf_report_config, NULL); + argc = parse_options(argc, argv, options, report_usage, 0); if (report.use_stdio) @@ -663,6 +716,16 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) else input_name = "perf.data"; } + + if (strcmp(input_name, "-") != 0) + setup_browser(true); + else { + use_browser = 0; + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + perf_hpp__init(); + } + +repeat: session = perf_session__new(input_name, O_RDONLY, report.force, false, &report.tool); if (session == NULL) @@ -688,14 +751,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) } - if (strcmp(input_name, "-") != 0) - setup_browser(true); - else { - use_browser = 0; - perf_hpp__init(); - } - - setup_sorting(report_usage, options); + if (setup_sorting() < 0) + usage_with_options(report_usage, options); /* * Only in the newt browser we are doing integrated annotation, @@ -763,6 +820,12 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) } ret = __cmd_report(&report); + if (ret == K_SWITCH_INPUT_DATA) { + perf_session__delete(session); + goto repeat; + } else + ret = 0; + error: perf_session__delete(session); return ret; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index cc28b85..1382294 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1475,9 +1475,9 @@ static int perf_sched__read_events(struct perf_sched *sched, bool destroy, goto out_delete; } - sched->nr_events = session->hists.stats.nr_events[0]; - sched->nr_lost_events = session->hists.stats.total_lost; - sched->nr_lost_chunks = session->hists.stats.nr_events[PERF_RECORD_LOST]; + sched->nr_events = session->stats.nr_events[0]; + sched->nr_lost_events = session->stats.total_lost; + sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST]; } if (destroy) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b363e7b..92d4658f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -692,7 +692,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { char *tok; - int i, imax = sizeof(all_output_options) / sizeof(struct output_option); + int i, imax = ARRAY_SIZE(all_output_options); int j; int rc = 0; char *str = strdup(arg); @@ -909,18 +909,6 @@ static const char *ends_with(const char *str, const char *suffix) return NULL; } -static char *ltrim(char *str) -{ - int len = strlen(str); - - while (len && isspace(*str)) { - len--; - str++; - } - - return str; -} - static int read_script_info(struct script_desc *desc, const char *filename) { char line[BUFSIZ], *p; @@ -1487,7 +1475,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - perf_session__fprintf_info(session, stdout, show_full_info); + if (!script_name && !generate_script_lang) + perf_session__fprintf_info(session, stdout, show_full_info); if (!no_callchain) symbol_conf.use_callchain = true; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index c247fac..9984876 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -65,6 +65,11 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" +static void print_stat(int argc, const char **argv); +static void print_counter_aggr(struct perf_evsel *counter, char *prefix); +static void print_counter(struct perf_evsel *counter, char *prefix); +static void print_aggr_socket(char *prefix); + static struct perf_evlist *evsel_list; static struct perf_target target = { @@ -75,6 +80,7 @@ static int run_count = 1; static bool no_inherit = false; static bool scale = true; static bool no_aggr = false; +static bool aggr_socket = false; static pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; @@ -87,6 +93,9 @@ static FILE *output = NULL; static const char *pre_cmd = NULL; static const char *post_cmd = NULL; static bool sync_run = false; +static unsigned int interval = 0; +static struct timespec ref_time; +static struct cpu_map *sock_map; static volatile int done = 0; @@ -94,6 +103,28 @@ struct perf_stat { struct stats res_stats[3]; }; +static inline void diff_timespec(struct timespec *r, struct timespec *a, + struct timespec *b) +{ + r->tv_sec = a->tv_sec - b->tv_sec; + if (a->tv_nsec < b->tv_nsec) { + r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec; + r->tv_sec--; + } else { + r->tv_nsec = a->tv_nsec - b->tv_nsec ; + } +} + +static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +{ + return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; +} + +static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +{ + return perf_evsel__cpus(evsel)->nr; +} + static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) { evsel->priv = zalloc(sizeof(struct perf_stat)); @@ -106,14 +137,27 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) evsel->priv = NULL; } -static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel) { - return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; + void *addr; + size_t sz; + + sz = sizeof(*evsel->counts) + + (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values)); + + addr = zalloc(sz); + if (!addr) + return -ENOMEM; + + evsel->prev_raw_counts = addr; + + return 0; } -static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) { - return perf_evsel__cpus(evsel)->nr; + free(evsel->prev_raw_counts); + evsel->prev_raw_counts = NULL; } static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; @@ -132,8 +176,6 @@ static struct stats walltime_nsecs_stats; static int create_perf_stat_counter(struct perf_evsel *evsel) { struct perf_event_attr *attr = &evsel->attr; - bool exclude_guest_missing = false; - int ret; if (scale) attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | @@ -141,38 +183,16 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) attr->inherit = !no_inherit; -retry: - if (exclude_guest_missing) - evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; - - if (perf_target__has_cpu(&target)) { - ret = perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); - if (ret) - goto check_ret; - return 0; - } + if (perf_target__has_cpu(&target)) + return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); if (!perf_target__has_task(&target) && - !perf_evsel__is_group_member(evsel)) { + perf_evsel__is_group_leader(evsel)) { attr->disabled = 1; attr->enable_on_exec = 1; } - ret = perf_evsel__open_per_thread(evsel, evsel_list->threads); - if (!ret) - return 0; - /* fall through */ -check_ret: - if (ret && errno == EINVAL) { - if (!exclude_guest_missing && - (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { - pr_debug("Old kernel, cannot exclude " - "guest or host samples.\n"); - exclude_guest_missing = true; - goto retry; - } - } - return ret; + return perf_evsel__open_per_thread(evsel, evsel_list->threads); } /* @@ -269,15 +289,79 @@ static int read_counter(struct perf_evsel *counter) return 0; } +static void print_interval(void) +{ + static int num_print_interval; + struct perf_evsel *counter; + struct perf_stat *ps; + struct timespec ts, rs; + char prefix[64]; + + if (no_aggr) { + list_for_each_entry(counter, &evsel_list->entries, node) { + ps = counter->priv; + memset(ps->res_stats, 0, sizeof(ps->res_stats)); + read_counter(counter); + } + } else { + list_for_each_entry(counter, &evsel_list->entries, node) { + ps = counter->priv; + memset(ps->res_stats, 0, sizeof(ps->res_stats)); + read_counter_aggr(counter); + } + } + clock_gettime(CLOCK_MONOTONIC, &ts); + diff_timespec(&rs, &ts, &ref_time); + sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep); + + if (num_print_interval == 0 && !csv_output) { + if (aggr_socket) + fprintf(output, "# time socket cpus counts events\n"); + else if (no_aggr) + fprintf(output, "# time CPU counts events\n"); + else + fprintf(output, "# time counts events\n"); + } + + if (++num_print_interval == 25) + num_print_interval = 0; + + if (aggr_socket) + print_aggr_socket(prefix); + else if (no_aggr) { + list_for_each_entry(counter, &evsel_list->entries, node) + print_counter(counter, prefix); + } else { + list_for_each_entry(counter, &evsel_list->entries, node) + print_counter_aggr(counter, prefix); + } +} + static int __run_perf_stat(int argc __maybe_unused, const char **argv) { + char msg[512]; unsigned long long t0, t1; struct perf_evsel *counter; + struct timespec ts; int status = 0; int child_ready_pipe[2], go_pipe[2]; const bool forks = (argc > 0); char buf; + if (interval) { + ts.tv_sec = interval / 1000; + ts.tv_nsec = (interval % 1000) * 1000000; + } else { + ts.tv_sec = 1; + ts.tv_nsec = 0; + } + + if (aggr_socket + && cpu_map__build_socket_map(evsel_list->cpus, &sock_map)) { + perror("cannot build socket map"); + return -1; + } + if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) { perror("failed to create pipes"); return -1; @@ -348,20 +432,13 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv) continue; } - if (errno == EPERM || errno == EACCES) { - error("You may not have permission to collect %sstats.\n" - "\t Consider tweaking" - " /proc/sys/kernel/perf_event_paranoid or running as root.", - target.system_wide ? "system-wide " : ""); - } else { - error("open_counter returned with %d (%s). " - "/bin/dmesg may provide additional information.\n", - errno, strerror(errno)); - } + perf_evsel__open_strerror(counter, &target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); + if (child_pid != -1) kill(child_pid, SIGTERM); - pr_err("Not all events could be opened.\n"); return -1; } counter->supported = true; @@ -377,14 +454,25 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv) * Enable counters and exec the command: */ t0 = rdclock(); + clock_gettime(CLOCK_MONOTONIC, &ref_time); if (forks) { close(go_pipe[1]); + if (interval) { + while (!waitpid(child_pid, &status, WNOHANG)) { + nanosleep(&ts, NULL); + print_interval(); + } + } wait(&status); if (WIFSIGNALED(status)) psignal(WTERMSIG(status), argv[0]); } else { - while(!done) sleep(1); + while (!done) { + nanosleep(&ts, NULL); + if (interval) + print_interval(); + } } t1 = rdclock(); @@ -454,13 +542,21 @@ static void print_noise(struct perf_evsel *evsel, double avg) print_noise_pct(stddev_stats(&ps->res_stats[0]), avg); } -static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) +static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { double msecs = avg / 1e6; char cpustr[16] = { '\0', }; const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s"; - if (no_aggr) + if (aggr_socket) + sprintf(cpustr, "S%*d%s%*d%s", + csv_output ? 0 : -5, + cpu, + csv_sep, + csv_output ? 0 : 4, + nr, + csv_sep); + else if (no_aggr) sprintf(cpustr, "CPU%*d%s", csv_output ? 0 : -4, perf_evsel__cpus(evsel)->map[cpu], csv_sep); @@ -470,7 +566,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); - if (csv_output) + if (csv_output || interval) return; if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) @@ -659,7 +755,7 @@ static void print_ll_cache_misses(int cpu, fprintf(output, " of all LL-cache hits "); } -static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) +static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg) { double total, ratio = 0.0; char cpustr[16] = { '\0', }; @@ -672,7 +768,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) else fmt = "%s%18.0f%s%-25s"; - if (no_aggr) + if (aggr_socket) + sprintf(cpustr, "S%*d%s%*d%s", + csv_output ? 0 : -5, + cpu, + csv_sep, + csv_output ? 0 : 4, + nr, + csv_sep); + else if (no_aggr) sprintf(cpustr, "CPU%*d%s", csv_output ? 0 : -4, perf_evsel__cpus(evsel)->map[cpu], csv_sep); @@ -684,12 +788,11 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); - if (csv_output) + if (csv_output || interval) return; if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { total = avg_stats(&runtime_cycles_stats[cpu]); - if (total) ratio = avg / total; @@ -779,16 +882,83 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) } } +static void print_aggr_socket(char *prefix) +{ + struct perf_evsel *counter; + u64 ena, run, val; + int cpu, s, s2, sock, nr; + + if (!sock_map) + return; + + for (s = 0; s < sock_map->nr; s++) { + sock = cpu_map__socket(sock_map, s); + list_for_each_entry(counter, &evsel_list->entries, node) { + val = ena = run = 0; + nr = 0; + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + s2 = cpu_map__get_socket(evsel_list->cpus, cpu); + if (s2 != sock) + continue; + val += counter->counts->cpu[cpu].val; + ena += counter->counts->cpu[cpu].ena; + run += counter->counts->cpu[cpu].run; + nr++; + } + if (prefix) + fprintf(output, "%s", prefix); + + if (run == 0 || ena == 0) { + fprintf(output, "S%*d%s%*d%s%*s%s%*s", + csv_output ? 0 : -5, + s, + csv_sep, + csv_output ? 0 : 4, + nr, + csv_sep, + csv_output ? 0 : 18, + counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, + csv_sep, + csv_output ? 0 : -24, + perf_evsel__name(counter)); + if (counter->cgrp) + fprintf(output, "%s%s", + csv_sep, counter->cgrp->name); + + fputc('\n', output); + continue; + } + + if (nsec_counter(counter)) + nsec_printout(sock, nr, counter, val); + else + abs_printout(sock, nr, counter, val); + + if (!csv_output) { + print_noise(counter, 1.0); + + if (run != ena) + fprintf(output, " (%.2f%%)", + 100.0 * run / ena); + } + fputc('\n', output); + } + } +} + /* * Print out the results of a single counter: * aggregated counts in system-wide mode */ -static void print_counter_aggr(struct perf_evsel *counter) +static void print_counter_aggr(struct perf_evsel *counter, char *prefix) { struct perf_stat *ps = counter->priv; double avg = avg_stats(&ps->res_stats[0]); int scaled = counter->counts->scaled; + if (prefix) + fprintf(output, "%s", prefix); + if (scaled == -1) { fprintf(output, "%*s%s%*s", csv_output ? 0 : 18, @@ -805,9 +975,9 @@ static void print_counter_aggr(struct perf_evsel *counter) } if (nsec_counter(counter)) - nsec_printout(-1, counter, avg); + nsec_printout(-1, 0, counter, avg); else - abs_printout(-1, counter, avg); + abs_printout(-1, 0, counter, avg); print_noise(counter, avg); @@ -831,7 +1001,7 @@ static void print_counter_aggr(struct perf_evsel *counter) * Print out the results of a single counter: * does not use aggregated count in system-wide */ -static void print_counter(struct perf_evsel *counter) +static void print_counter(struct perf_evsel *counter, char *prefix) { u64 ena, run, val; int cpu; @@ -840,6 +1010,10 @@ static void print_counter(struct perf_evsel *counter) val = counter->counts->cpu[cpu].val; ena = counter->counts->cpu[cpu].ena; run = counter->counts->cpu[cpu].run; + + if (prefix) + fprintf(output, "%s", prefix); + if (run == 0 || ena == 0) { fprintf(output, "CPU%*d%s%*s%s%*s", csv_output ? 0 : -4, @@ -859,9 +1033,9 @@ static void print_counter(struct perf_evsel *counter) } if (nsec_counter(counter)) - nsec_printout(cpu, counter, val); + nsec_printout(cpu, 0, counter, val); else - abs_printout(cpu, counter, val); + abs_printout(cpu, 0, counter, val); if (!csv_output) { print_noise(counter, 1.0); @@ -899,12 +1073,14 @@ static void print_stat(int argc, const char **argv) fprintf(output, ":\n\n"); } - if (no_aggr) { + if (aggr_socket) + print_aggr_socket(NULL); + else if (no_aggr) { list_for_each_entry(counter, &evsel_list->entries, node) - print_counter(counter); + print_counter(counter, NULL); } else { list_for_each_entry(counter, &evsel_list->entries, node) - print_counter_aggr(counter); + print_counter_aggr(counter, NULL); } if (!csv_output) { @@ -925,7 +1101,7 @@ static volatile int signr = -1; static void skip_signal(int signo) { - if(child_pid == -1) + if ((child_pid == -1) || interval) done = 1; signr = signo; @@ -1145,6 +1321,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "command to run prior to the measured command"), OPT_STRING(0, "post", &post_cmd, "command", "command to run after to the measured command"), + OPT_UINTEGER('I', "interval-print", &interval, + "print counts at regular interval in ms (>= 100)"), + OPT_BOOLEAN(0, "aggr-socket", &aggr_socket, "aggregate counts per processor socket"), OPT_END() }; const char * const stat_usage[] = { @@ -1231,6 +1410,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(stat_usage, options); } + if (aggr_socket) { + if (!perf_target__has_cpu(&target)) { + fprintf(stderr, "--aggr-socket only available in system-wide mode (-a)\n"); + usage_with_options(stat_usage, options); + } + no_aggr = true; + } + if (add_default_attributes()) goto out; @@ -1245,12 +1432,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(stat_usage, options); return -1; } + if (interval && interval < 100) { + pr_err("print interval must be >= 100ms\n"); + usage_with_options(stat_usage, options); + return -1; + } list_for_each_entry(pos, &evsel_list->entries, node) { if (perf_evsel__alloc_stat_priv(pos) < 0 || perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0) goto out_free_fd; } + if (interval) { + list_for_each_entry(pos, &evsel_list->entries, node) { + if (perf_evsel__alloc_prev_raw_counts(pos) < 0) + goto out_free_fd; + } + } /* * We dont want to block the signals - that would cause @@ -1260,6 +1458,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) */ atexit(sig_atexit); signal(SIGINT, skip_signal); + signal(SIGCHLD, skip_signal); signal(SIGALRM, skip_signal); signal(SIGABRT, skip_signal); @@ -1272,11 +1471,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) status = run_perf_stat(argc, argv); } - if (status != -1) + if (status != -1 && !interval) print_stat(argc, argv); out_free_fd: - list_for_each_entry(pos, &evsel_list->entries, node) + list_for_each_entry(pos, &evsel_list->entries, node) { perf_evsel__free_stat_priv(pos); + perf_evsel__free_counts(pos); + perf_evsel__free_prev_raw_counts(pos); + } perf_evlist__delete_maps(evsel_list); out: perf_evlist__delete(evsel_list); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c9ff395..72f6eb7 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -68,27 +68,7 @@ #include <linux/unistd.h> #include <linux/types.h> -void get_term_dimensions(struct winsize *ws) -{ - char *s = getenv("LINES"); - - if (s != NULL) { - ws->ws_row = atoi(s); - s = getenv("COLUMNS"); - if (s != NULL) { - ws->ws_col = atoi(s); - if (ws->ws_row && ws->ws_col) - return; - } - } -#ifdef TIOCGWINSZ - if (ioctl(1, TIOCGWINSZ, ws) == 0 && - ws->ws_row && ws->ws_col) - return; -#endif - ws->ws_row = 25; - ws->ws_col = 80; -} +static volatile int done; static void perf_top__update_print_entries(struct perf_top *top) { @@ -453,8 +433,10 @@ static int perf_top__key_mapped(struct perf_top *top, int c) return 0; } -static void perf_top__handle_keypress(struct perf_top *top, int c) +static bool perf_top__handle_keypress(struct perf_top *top, int c) { + bool ret = true; + if (!perf_top__key_mapped(top, c)) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; struct termios tc, save; @@ -475,7 +457,7 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) tcsetattr(0, TCSAFLUSH, &save); if (!perf_top__key_mapped(top, c)) - return; + return ret; } switch (c) { @@ -537,7 +519,8 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) printf("exiting.\n"); if (top->dump_symtab) perf_session__fprintf_dsos(top->session, stderr); - exit(0); + ret = false; + break; case 's': perf_top__prompt_symbol(top, "Enter details symbol"); break; @@ -560,6 +543,8 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) default: break; } + + return ret; } static void perf_top__sort_new_samples(void *arg) @@ -596,13 +581,12 @@ static void *display_thread_tui(void *arg) * via --uid. */ list_for_each_entry(pos, &top->evlist->entries, node) - pos->hists.uid_filter_str = top->target.uid_str; + pos->hists.uid_filter_str = top->record_opts.target.uid_str; perf_evlist__tui_browse_hists(top->evlist, help, &hbt, &top->session->header.env); - exit_browser(0); - exit(0); + done = 1; return NULL; } @@ -626,7 +610,7 @@ repeat: /* trash return*/ getc(stdin); - while (1) { + while (!done) { perf_top__print_sym_table(top); /* * Either timeout expired or we got an EINTR due to SIGWINCH, @@ -640,15 +624,14 @@ repeat: continue; /* Fall trhu */ default: - goto process_hotkey; + c = getc(stdin); + tcsetattr(0, TCSAFLUSH, &save); + + if (perf_top__handle_keypress(top, c)) + goto repeat; + done = 1; } } -process_hotkey: - c = getc(stdin); - tcsetattr(0, TCSAFLUSH, &save); - - perf_top__handle_keypress(top, c); - goto repeat; return NULL; } @@ -716,7 +699,7 @@ static void perf_event__process_sample(struct perf_tool *tool, static struct intlist *seen; if (!seen) - seen = intlist__new(); + seen = intlist__new(NULL); if (!intlist__has_entry(seen, event->ip.pid)) { pr_err("Can't find guest [%d]'s kernel information\n", @@ -727,8 +710,8 @@ static void perf_event__process_sample(struct perf_tool *tool, } if (!machine) { - pr_err("%u unprocessable samples recorded.", - top->session->hists.stats.nr_unprocessable_samples++); + pr_err("%u unprocessable samples recorded.\r", + top->session->stats.nr_unprocessable_samples++); return; } @@ -847,13 +830,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) ++top->us_samples; if (top->hide_user_symbols) continue; - machine = perf_session__find_host_machine(session); + machine = &session->machines.host; break; case PERF_RECORD_MISC_KERNEL: ++top->kernel_samples; if (top->hide_kernel_symbols) continue; - machine = perf_session__find_host_machine(session); + machine = &session->machines.host; break; case PERF_RECORD_MISC_GUEST_KERNEL: ++top->guest_kernel_samples; @@ -878,7 +861,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) hists__inc_nr_events(&evsel->hists, event->header.type); machine__process_event(machine, event); } else - ++session->hists.stats.nr_unknown_events; + ++session->stats.nr_unknown_events; } } @@ -890,123 +873,42 @@ static void perf_top__mmap_read(struct perf_top *top) perf_top__mmap_read_idx(top, i); } -static void perf_top__start_counters(struct perf_top *top) +static int perf_top__start_counters(struct perf_top *top) { + char msg[512]; struct perf_evsel *counter; struct perf_evlist *evlist = top->evlist; + struct perf_record_opts *opts = &top->record_opts; - if (top->group) - perf_evlist__set_leader(evlist); + perf_evlist__config(evlist, opts); list_for_each_entry(counter, &evlist->entries, node) { - struct perf_event_attr *attr = &counter->attr; - - attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; - - if (top->freq) { - attr->sample_type |= PERF_SAMPLE_PERIOD; - attr->freq = 1; - attr->sample_freq = top->freq; - } - - if (evlist->nr_entries > 1) { - attr->sample_type |= PERF_SAMPLE_ID; - attr->read_format |= PERF_FORMAT_ID; - } - - if (perf_target__has_cpu(&top->target)) - attr->sample_type |= PERF_SAMPLE_CPU; - - if (symbol_conf.use_callchain) - attr->sample_type |= PERF_SAMPLE_CALLCHAIN; - - attr->mmap = 1; - attr->comm = 1; - attr->inherit = top->inherit; -fallback_missing_features: - if (top->exclude_guest_missing) - attr->exclude_guest = attr->exclude_host = 0; -retry_sample_id: - attr->sample_id_all = top->sample_id_all_missing ? 0 : 1; try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { - int err = errno; - - if (err == EPERM || err == EACCES) { - ui__error_paranoid(); - goto out_err; - } else if (err == EINVAL) { - if (!top->exclude_guest_missing && - (attr->exclude_guest || attr->exclude_host)) { - pr_debug("Old kernel, cannot exclude " - "guest or host samples.\n"); - top->exclude_guest_missing = true; - goto fallback_missing_features; - } else if (!top->sample_id_all_missing) { - /* - * Old kernel, no attr->sample_id_type_all field - */ - top->sample_id_all_missing = true; - goto retry_sample_id; - } - } - /* - * If it's cycles then fall back to hrtimer - * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: - */ - if ((err == ENOENT || err == ENXIO) && - (attr->type == PERF_TYPE_HARDWARE) && - (attr->config == PERF_COUNT_HW_CPU_CYCLES)) { - + if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { if (verbose) - ui__warning("Cycles event not supported,\n" - "trying to fall back to cpu-clock-ticks\n"); - - attr->type = PERF_TYPE_SOFTWARE; - attr->config = PERF_COUNT_SW_CPU_CLOCK; - if (counter->name) { - free(counter->name); - counter->name = NULL; - } + ui__warning("%s\n", msg); goto try_again; } - if (err == ENOENT) { - ui__error("The %s event is not supported.\n", - perf_evsel__name(counter)); - goto out_err; - } else if (err == EMFILE) { - ui__error("Too many events are opened.\n" - "Try again after reducing the number of events\n"); - goto out_err; - } else if ((err == EOPNOTSUPP) && (attr->precise_ip)) { - ui__error("\'precise\' request may not be supported. " - "Try removing 'p' modifier\n"); - goto out_err; - } - - ui__error("The sys_perf_event_open() syscall " - "returned with %d (%s). /bin/dmesg " - "may provide additional information.\n" - "No CONFIG_PERF_EVENTS=y kernel support " - "configured?\n", err, strerror(err)); + perf_evsel__open_strerror(counter, &opts->target, + errno, msg, sizeof(msg)); + ui__error("%s\n", msg); goto out_err; } } - if (perf_evlist__mmap(evlist, top->mmap_pages, false) < 0) { + if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) { ui__error("Failed to mmap with %d (%s)\n", errno, strerror(errno)); goto out_err; } - return; + return 0; out_err: - exit_browser(0); - exit(0); + return -1; } static int perf_top__setup_sample_type(struct perf_top *top) @@ -1016,7 +918,7 @@ static int perf_top__setup_sample_type(struct perf_top *top) ui__error("Selected -g but \"sym\" not present in --sort/-s."); return -EINVAL; } - } else if (!top->dont_use_callchains && callchain_param.mode != CHAIN_NONE) { + } else if (callchain_param.mode != CHAIN_NONE) { if (callchain_register_param(&callchain_param) < 0) { ui__error("Can't register callchain params.\n"); return -EINVAL; @@ -1028,6 +930,7 @@ static int perf_top__setup_sample_type(struct perf_top *top) static int __cmd_top(struct perf_top *top) { + struct perf_record_opts *opts = &top->record_opts; pthread_t thread; int ret; /* @@ -1042,26 +945,42 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; - if (perf_target__has_task(&top->target)) + if (perf_target__has_task(&opts->target)) perf_event__synthesize_thread_map(&top->tool, top->evlist->threads, perf_event__process, - &top->session->host_machine); + &top->session->machines.host); else perf_event__synthesize_threads(&top->tool, perf_event__process, - &top->session->host_machine); - perf_top__start_counters(top); + &top->session->machines.host); + + ret = perf_top__start_counters(top); + if (ret) + goto out_delete; + top->session->evlist = top->evlist; perf_session__set_id_hdr_size(top->session); + /* + * When perf is starting the traced process, all the events (apart from + * group members) have enable_on_exec=1 set, so don't spoil it by + * prematurely enabling them. + * + * XXX 'top' still doesn't start workloads like record, trace, but should, + * so leave the check here. + */ + if (!perf_target__none(&opts->target)) + perf_evlist__enable(top->evlist); + /* Wait for a minimal set of events before starting the snapshot */ poll(top->evlist->pollfd, top->evlist->nr_fds, 100); perf_top__mmap_read(top); + ret = -1; if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui : display_thread), top)) { ui__error("Could not create display thread.\n"); - exit(-1); + goto out_delete; } if (top->realtime_prio) { @@ -1070,11 +989,11 @@ static int __cmd_top(struct perf_top *top) param.sched_priority = top->realtime_prio; if (sched_setscheduler(0, SCHED_FIFO, ¶m)) { ui__error("Could not set realtime priority.\n"); - exit(-1); + goto out_delete; } } - while (1) { + while (!done) { u64 hits = top->samples; perf_top__mmap_read(top); @@ -1083,126 +1002,67 @@ static int __cmd_top(struct perf_top *top) ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100); } + ret = 0; out_delete: perf_session__delete(top->session); top->session = NULL; - return 0; + return ret; } static int parse_callchain_opt(const struct option *opt, const char *arg, int unset) { - struct perf_top *top = (struct perf_top *)opt->value; - char *tok, *tok2; - char *endptr; - /* * --no-call-graph */ - if (unset) { - top->dont_use_callchains = true; + if (unset) return 0; - } symbol_conf.use_callchain = true; - if (!arg) - return 0; - - tok = strtok((char *)arg, ","); - if (!tok) - return -1; - - /* get the output mode */ - if (!strncmp(tok, "graph", strlen(arg))) - callchain_param.mode = CHAIN_GRAPH_ABS; - - else if (!strncmp(tok, "flat", strlen(arg))) - callchain_param.mode = CHAIN_FLAT; - - else if (!strncmp(tok, "fractal", strlen(arg))) - callchain_param.mode = CHAIN_GRAPH_REL; - - else if (!strncmp(tok, "none", strlen(arg))) { - callchain_param.mode = CHAIN_NONE; - symbol_conf.use_callchain = false; - - return 0; - } else - return -1; - - /* get the min percentage */ - tok = strtok(NULL, ","); - if (!tok) - goto setup; - - callchain_param.min_percent = strtod(tok, &endptr); - if (tok == endptr) - return -1; - - /* get the print limit */ - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - - if (tok2[0] != 'c') { - callchain_param.print_limit = strtod(tok2, &endptr); - tok2 = strtok(NULL, ","); - if (!tok2) - goto setup; - } - - /* get the call chain order */ - if (!strcmp(tok2, "caller")) - callchain_param.order = ORDER_CALLER; - else if (!strcmp(tok2, "callee")) - callchain_param.order = ORDER_CALLEE; - else - return -1; -setup: - if (callchain_register_param(&callchain_param) < 0) { - fprintf(stderr, "Can't register callchain params\n"); - return -1; - } - return 0; + return record_parse_callchain_opt(opt, arg, unset); } int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) { - struct perf_evsel *pos; int status; char errbuf[BUFSIZ]; struct perf_top top = { .count_filter = 5, .delay_secs = 2, - .freq = 4000, /* 4 KHz */ - .mmap_pages = 128, - .sym_pcnt_filter = 5, - .target = { - .uses_mmap = true, + .record_opts = { + .mmap_pages = UINT_MAX, + .user_freq = UINT_MAX, + .user_interval = ULLONG_MAX, + .freq = 4000, /* 4 KHz */ + .target = { + .uses_mmap = true, + }, }, + .sym_pcnt_filter = 5, }; - char callchain_default_opt[] = "fractal,0.5,callee"; + struct perf_record_opts *opts = &top.record_opts; + struct perf_target *target = &opts->target; const struct option options[] = { OPT_CALLBACK('e', "event", &top.evlist, "event", "event selector. use 'perf list' to list available events", parse_events_option), - OPT_INTEGER('c', "count", &top.default_interval, - "event period to sample"), - OPT_STRING('p', "pid", &top.target.pid, "pid", + OPT_U64('c', "count", &opts->user_interval, "event period to sample"), + OPT_STRING('p', "pid", &target->pid, "pid", "profile events on existing process id"), - OPT_STRING('t', "tid", &top.target.tid, "tid", + OPT_STRING('t', "tid", &target->tid, "tid", "profile events on existing thread id"), - OPT_BOOLEAN('a', "all-cpus", &top.target.system_wide, + OPT_BOOLEAN('a', "all-cpus", &target->system_wide, "system-wide collection from all CPUs"), - OPT_STRING('C', "cpu", &top.target.cpu_list, "cpu", + OPT_STRING('C', "cpu", &target->cpu_list, "cpu", "list of cpus to monitor"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols, "hide kernel symbols"), - OPT_UINTEGER('m', "mmap-pages", &top.mmap_pages, "number of mmap data pages"), + OPT_UINTEGER('m', "mmap-pages", &opts->mmap_pages, + "number of mmap data pages"), OPT_INTEGER('r', "realtime", &top.realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_INTEGER('d', "delay", &top.delay_secs, @@ -1211,16 +1071,14 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "dump the symbol table used for profiling"), OPT_INTEGER('f', "count-filter", &top.count_filter, "only display functions with more events than this"), - OPT_BOOLEAN('g', "group", &top.group, + OPT_BOOLEAN('g', "group", &opts->group, "put the counters into a counter group"), - OPT_BOOLEAN('i', "inherit", &top.inherit, - "child tasks inherit counters"), + OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit, + "child tasks do not inherit counters"), OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name", "symbol to annotate"), - OPT_BOOLEAN('z', "zero", &top.zero, - "zero history across updates"), - OPT_INTEGER('F', "freq", &top.freq, - "profile at this frequency"), + OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"), + OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"), OPT_INTEGER('E', "entries", &top.print_entries, "display this many functions"), OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols, @@ -1233,10 +1091,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "sort by key(s): pid, comm, dso, symbol, parent"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), - OPT_CALLBACK_DEFAULT('G', "call-graph", &top, "output_type,min_percent, call_order", - "Display callchains using output_type (graph, flat, fractal, or none), min percent threshold and callchain order. " - "Default: fractal,0.5,callee", &parse_callchain_opt, - callchain_default_opt), + OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, + "mode[,dump_size]", record_callchain_help, + &parse_callchain_opt, "fp"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", @@ -1251,7 +1108,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING('u', "uid", &top.target.uid_str, "user", "user to profile"), + OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_END() }; const char * const top_usage[] = { @@ -1272,7 +1129,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (sort_order == default_sort_order) sort_order = "dso,symbol"; - setup_sorting(top_usage, options); + if (setup_sorting() < 0) + usage_with_options(top_usage, options); if (top.use_stdio) use_browser = 0; @@ -1281,33 +1139,33 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) setup_browser(false); - status = perf_target__validate(&top.target); + status = perf_target__validate(target); if (status) { - perf_target__strerror(&top.target, status, errbuf, BUFSIZ); + perf_target__strerror(target, status, errbuf, BUFSIZ); ui__warning("%s", errbuf); } - status = perf_target__parse_uid(&top.target); + status = perf_target__parse_uid(target); if (status) { int saved_errno = errno; - perf_target__strerror(&top.target, status, errbuf, BUFSIZ); + perf_target__strerror(target, status, errbuf, BUFSIZ); ui__error("%s", errbuf); status = -saved_errno; goto out_delete_evlist; } - if (perf_target__none(&top.target)) - top.target.system_wide = true; + if (perf_target__none(target)) + target->system_wide = true; - if (perf_evlist__create_maps(top.evlist, &top.target) < 0) + if (perf_evlist__create_maps(top.evlist, target) < 0) usage_with_options(top_usage, options); if (!top.evlist->nr_entries && perf_evlist__add_default(top.evlist) < 0) { ui__error("Not enough memory for event selector list\n"); - return -ENOMEM; + goto out_delete_maps; } symbol_conf.nr_events = top.evlist->nr_entries; @@ -1315,24 +1173,22 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.delay_secs < 1) top.delay_secs = 1; + if (opts->user_interval != ULLONG_MAX) + opts->default_interval = opts->user_interval; + if (opts->user_freq != UINT_MAX) + opts->freq = opts->user_freq; + /* * User specified count overrides default frequency. */ - if (top.default_interval) - top.freq = 0; - else if (top.freq) { - top.default_interval = top.freq; + if (opts->default_interval) + opts->freq = 0; + else if (opts->freq) { + opts->default_interval = opts->freq; } else { ui__error("frequency and count are zero, aborting\n"); - exit(EXIT_FAILURE); - } - - list_for_each_entry(pos, &top.evlist->entries, node) { - /* - * Fill in the ones not specifically initialized via -c: - */ - if (!pos->attr.sample_period) - pos->attr.sample_period = top.default_interval; + status = -EINVAL; + goto out_delete_maps; } top.sym_evsel = perf_evlist__first(top.evlist); @@ -1365,6 +1221,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) status = __cmd_top(&top); +out_delete_maps: + perf_evlist__delete_maps(top.evlist); out_delete_evlist: perf_evlist__delete(top.evlist); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 7932ffa..d222d7f 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -455,7 +455,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_delete_evlist; } - perf_evlist__config_attrs(evlist, &trace->opts); + perf_evlist__config(evlist, &trace->opts); signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index f5ac774..b4eabb4 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -225,3 +225,14 @@ int main(void) return on_exit(NULL, NULL); } endef + +define SOURCE_LIBNUMA +#include <numa.h> +#include <numaif.h> + +int main(void) +{ + numa_available(); + return 0; +} +endef
\ No newline at end of file diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak index e541312..8ef3bd3 100644 --- a/tools/perf/config/utilities.mak +++ b/tools/perf/config/utilities.mak @@ -13,7 +13,7 @@ newline := $(newline) # what should replace a newline when escaping # newlines; the default is a bizarre string. # -nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n) +nl-escape = $(if $(1),$(1),m822df3020w6a44id34bt574ctac44eb9f4n) # escape-nl # @@ -173,9 +173,9 @@ _ge-abspath = $(if $(is-executable),$(1)) # Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default) # define get-executable-or-default -$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2))) +$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2),$(1))) endef -_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2))) +_ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2))) _gea_warn = $(warning The path '$(1)' is not executable.) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 0f661fb..095b882 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -328,14 +328,23 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) if (S_ISFIFO(st.st_mode) || S_ISSOCK(st.st_mode)) return 0; + status = 1; /* Check for ENOSPC and EIO errors.. */ - if (fflush(stdout)) - die("write failure on standard output: %s", strerror(errno)); - if (ferror(stdout)) - die("unknown write failure on standard output"); - if (fclose(stdout)) - die("close failed on standard output: %s", strerror(errno)); - return 0; + if (fflush(stdout)) { + fprintf(stderr, "write failure on standard output: %s", strerror(errno)); + goto out; + } + if (ferror(stdout)) { + fprintf(stderr, "unknown write failure on standard output"); + goto out; + } + if (fclose(stdout)) { + fprintf(stderr, "close failed on standard output: %s", strerror(errno)); + goto out; + } + status = 0; +out: + return status; } static void handle_internal_command(int argc, const char **argv) @@ -467,7 +476,8 @@ int main(int argc, const char **argv) cmd += 5; argv[0] = cmd; handle_internal_command(argc, argv); - die("cannot handle %s internally", cmd); + fprintf(stderr, "cannot handle %s internally", cmd); + goto out; } /* Look for flags.. */ @@ -485,7 +495,7 @@ int main(int argc, const char **argv) printf("\n usage: %s\n\n", perf_usage_string); list_common_cmds_help(); printf("\n %s\n\n", perf_more_info_string); - exit(1); + goto out; } cmd = argv[0]; @@ -517,7 +527,7 @@ int main(int argc, const char **argv) fprintf(stderr, "Expansion of alias '%s' failed; " "'%s' is not a perf-command\n", cmd, argv[0]); - exit(1); + goto out; } if (!done_help) { cmd = argv[0] = help_unknown_cmd(cmd); @@ -528,6 +538,6 @@ int main(int argc, const char **argv) fprintf(stderr, "Failed to run command '%s': %s\n", cmd, strerror(errno)); - +out: return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 2c340e7..c2206c8 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -1,10 +1,6 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H -struct winsize; - -void get_term_dimensions(struct winsize *ws); - #include <asm/unistd.h> #if defined(__i386__) @@ -107,32 +103,6 @@ void get_term_dimensions(struct winsize *ws); #include "util/types.h" #include <stdbool.h> -struct perf_mmap { - void *base; - int mask; - unsigned int prev; -}; - -static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) -{ - struct perf_event_mmap_page *pc = mm->base; - int head = pc->data_head; - rmb(); - return head; -} - -static inline void perf_mmap__write_tail(struct perf_mmap *md, - unsigned long tail) -{ - struct perf_event_mmap_page *pc = md->base; - - /* - * ensure all reads are done before we write the tail out. - */ - /* mb(); */ - pc->data_tail = tail; -} - /* * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all * counters in the current task. @@ -237,8 +207,6 @@ struct perf_record_opts { bool raw_samples; bool sample_address; bool sample_time; - bool sample_id_all_missing; - bool exclude_guest_missing; bool period; unsigned int freq; unsigned int mmap_pages; diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record deleted file mode 100644 index 8edda90..0000000 --- a/tools/perf/scripts/perl/bin/workqueue-stats-record +++ /dev/null @@ -1,2 +0,0 @@ -#!/bin/bash -perf record -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@ diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report deleted file mode 100644 index 6d91411..0000000 --- a/tools/perf/scripts/perl/bin/workqueue-stats-report +++ /dev/null @@ -1,3 +0,0 @@ -#!/bin/bash -# description: workqueue stats (ins/exe/create/destroy) -perf script $@ -s "$PERF_EXEC_PATH"/scripts/perl/workqueue-stats.pl diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl index 4bb3ecd..8b20787 100644 --- a/tools/perf/scripts/perl/rwtop.pl +++ b/tools/perf/scripts/perl/rwtop.pl @@ -17,6 +17,7 @@ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; use lib "./Perf-Trace-Util/lib"; use Perf::Trace::Core; use Perf::Trace::Util; +use POSIX qw/SIGALRM SA_RESTART/; my $default_interval = 3; my $nlines = 20; @@ -90,7 +91,10 @@ sub syscalls::sys_enter_write sub trace_begin { - $SIG{ALRM} = \&set_print_pending; + my $sa = POSIX::SigAction->new(\&set_print_pending); + $sa->flags(SA_RESTART); + $sa->safe(1); + POSIX::sigaction(SIGALRM, $sa) or die "Can't set SIGALRM handler: $!\n"; alarm 1; } diff --git a/tools/perf/scripts/perl/workqueue-stats.pl b/tools/perf/scripts/perl/workqueue-stats.pl deleted file mode 100644 index a8eaff5..0000000 --- a/tools/perf/scripts/perl/workqueue-stats.pl +++ /dev/null @@ -1,129 +0,0 @@ -#!/usr/bin/perl -w -# (c) 2009, Tom Zanussi <tzanussi@gmail.com> -# Licensed under the terms of the GNU GPL License version 2 - -# Displays workqueue stats -# -# Usage: -# -# perf record -c 1 -f -a -R -e workqueue:workqueue_creation -e -# workqueue:workqueue_destruction -e workqueue:workqueue_execution -# -e workqueue:workqueue_insertion -# -# perf script -p -s tools/perf/scripts/perl/workqueue-stats.pl - -use 5.010000; -use strict; -use warnings; - -use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib"; -use lib "./Perf-Trace-Util/lib"; -use Perf::Trace::Core; -use Perf::Trace::Util; - -my @cpus; - -sub workqueue::workqueue_destruction -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid) = @_; - - $cpus[$common_cpu]{$thread_pid}{destroyed}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub workqueue::workqueue_creation -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid, $cpu) = @_; - - $cpus[$common_cpu]{$thread_pid}{created}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub workqueue::workqueue_execution -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid, $func) = @_; - - $cpus[$common_cpu]{$thread_pid}{executed}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub workqueue::workqueue_insertion -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm, - $thread_comm, $thread_pid, $func) = @_; - - $cpus[$common_cpu]{$thread_pid}{inserted}++; - $cpus[$common_cpu]{$thread_pid}{comm} = $thread_comm; -} - -sub trace_end -{ - print "workqueue work stats:\n\n"; - my $cpu = 0; - printf("%3s %6s %6s\t%-20s\n", "cpu", "ins", "exec", "name"); - printf("%3s %6s %6s\t%-20s\n", "---", "---", "----", "----"); - foreach my $pidhash (@cpus) { - while ((my $pid, my $wqhash) = each %$pidhash) { - my $ins = $$wqhash{'inserted'} || 0; - my $exe = $$wqhash{'executed'} || 0; - my $comm = $$wqhash{'comm'} || ""; - if ($ins || $exe) { - printf("%3u %6u %6u\t%-20s\n", $cpu, $ins, $exe, $comm); - } - } - $cpu++; - } - - $cpu = 0; - print "\nworkqueue lifecycle stats:\n\n"; - printf("%3s %6s %6s\t%-20s\n", "cpu", "created", "destroyed", "name"); - printf("%3s %6s %6s\t%-20s\n", "---", "-------", "---------", "----"); - foreach my $pidhash (@cpus) { - while ((my $pid, my $wqhash) = each %$pidhash) { - my $created = $$wqhash{'created'} || 0; - my $destroyed = $$wqhash{'destroyed'} || 0; - my $comm = $$wqhash{'comm'} || ""; - if ($created || $destroyed) { - printf("%3u %6u %6u\t%-20s\n", $cpu, $created, $destroyed, - $comm); - } - } - $cpu++; - } - - print_unhandled(); -} - -my %unhandled; - -sub print_unhandled -{ - if ((scalar keys %unhandled) == 0) { - return; - } - - print "\nunhandled events:\n\n"; - - printf("%-40s %10s\n", "event", "count"); - printf("%-40s %10s\n", "----------------------------------------", - "-----------"); - - foreach my $event_name (keys %unhandled) { - printf("%-40s %10d\n", $event_name, $unhandled{$event_name}); - } -} - -sub trace_unhandled -{ - my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs, - $common_pid, $common_comm) = @_; - - $unhandled{$event_name}++; -} diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 25638a9..bdcceb8 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -19,6 +19,11 @@ * permissions. All the event text files are stored there. */ +/* + * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select + * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu. + */ +#define __SANE_USERSPACE_TYPES__ #include <stdlib.h> #include <stdio.h> #include <inttypes.h> @@ -33,8 +38,6 @@ extern int verbose; -bool test_attr__enabled; - static char *dir; void test_attr__init(void) @@ -146,7 +149,7 @@ static int run_dir(const char *d, const char *perf) { char cmd[3*PATH_MAX]; - snprintf(cmd, 3*PATH_MAX, "python %s/attr.py -d %s/attr/ -p %s %s", + snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %s", d, d, perf, verbose ? "-v" : ""); return system(cmd); diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index e702b82..2f629ca 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -68,7 +68,7 @@ class Event(dict): self[key] = val def __init__(self, name, data, base): - log.info(" Event %s" % name); + log.debug(" Event %s" % name); self.name = name; self.group = '' self.add(base) @@ -97,6 +97,14 @@ class Event(dict): return False return True + def diff(self, other): + for t in Event.terms: + if not self.has_key(t) or not other.has_key(t): + continue + if not self.compare_data(self[t], other[t]): + log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) + + # Test file description needs to have following sections: # [config] # - just single instance in file @@ -113,7 +121,7 @@ class Test(object): parser = ConfigParser.SafeConfigParser() parser.read(path) - log.warning("running '%s'" % path) + log.debug("running '%s'" % path) self.path = path self.test_dir = options.test_dir @@ -128,7 +136,7 @@ class Test(object): self.expect = {} self.result = {} - log.info(" loading expected events"); + log.debug(" loading expected events"); self.load_events(path, self.expect) def is_event(self, name): @@ -164,7 +172,7 @@ class Test(object): self.perf, self.command, tempdir, self.args) ret = os.WEXITSTATUS(os.system(cmd)) - log.info(" running '%s' ret %d " % (cmd, ret)) + log.warning(" running '%s' ret %d " % (cmd, ret)) if ret != int(self.ret): raise Unsup(self) @@ -172,7 +180,7 @@ class Test(object): def compare(self, expect, result): match = {} - log.info(" compare"); + log.debug(" compare"); # For each expected event find all matching # events in result. Fail if there's not any. @@ -187,10 +195,11 @@ class Test(object): else: log.debug(" ->FAIL"); - log.info(" match: [%s] matches %s" % (exp_name, str(exp_list))) + log.debug(" match: [%s] matches %s" % (exp_name, str(exp_list))) # we did not any matching event - fail if (not exp_list): + exp_event.diff(res_event) raise Fail(self, 'match failure'); match[exp_name] = exp_list @@ -208,10 +217,10 @@ class Test(object): if res_group not in match[group]: raise Fail(self, 'group failure') - log.info(" group: [%s] matches group leader %s" % + log.debug(" group: [%s] matches group leader %s" % (exp_name, str(match[group]))) - log.info(" matched") + log.debug(" matched") def resolve_groups(self, events): for name, event in events.items(): @@ -233,7 +242,7 @@ class Test(object): self.run_cmd(tempdir); # load events expectation for the test - log.info(" loading result events"); + log.debug(" loading result events"); for f in glob.glob(tempdir + '/event*'): self.load_events(f, self.result); diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index f1485d8..5bc3880 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -7,7 +7,7 @@ size=96 config=0 sample_period=4000 sample_type=263 -read_format=7 +read_format=0 disabled=1 inherit=1 pinned=0 diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group index a6599e9..57739ca 100644 --- a/tools/perf/tests/attr/test-record-group +++ b/tools/perf/tests/attr/test-record-group @@ -6,12 +6,14 @@ args = --group -e cycles,instructions kill >/dev/null 2>&1 fd=1 group_fd=-1 sample_type=327 +read_format=4 [event-2:base-record] fd=2 group_fd=1 config=1 sample_type=327 +read_format=4 mmap=0 comm=0 enable_on_exec=0 diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 index 5a8359d..c5548d0 100644 --- a/tools/perf/tests/attr/test-record-group1 +++ b/tools/perf/tests/attr/test-record-group1 @@ -1,11 +1,12 @@ [config] command = record -args = -e '{cycles,instructions}' kill >/tmp/krava 2>&1 +args = -e '{cycles,instructions}' kill >/dev/null 2>&1 [event-1:base-record] fd=1 group_fd=-1 sample_type=327 +read_format=4 [event-2:base-record] fd=2 @@ -13,6 +14,7 @@ group_fd=1 type=0 config=1 sample_type=327 +read_format=4 mmap=0 comm=0 enable_on_exec=0 diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 186f675..acb98e0 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -4,6 +4,7 @@ * Builtin regression testing command: ever growing number of sanity tests */ #include "builtin.h" +#include "intlist.h" #include "tests.h" #include "debug.h" #include "color.h" @@ -69,6 +70,14 @@ static struct test { .func = test__attr, }, { + .desc = "Test matching and linking mutliple hists", + .func = test__hists_link, + }, + { + .desc = "Try 'use perf' in python, checking link problems", + .func = test__python_use, + }, + { .func = NULL, }, }; @@ -97,7 +106,7 @@ static bool perf_test__matches(int curr, int argc, const char *argv[]) return false; } -static int __cmd_test(int argc, const char *argv[]) +static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { int i = 0; int width = 0; @@ -118,13 +127,28 @@ static int __cmd_test(int argc, const char *argv[]) continue; pr_info("%2d: %-*s:", i, width, tests[curr].desc); + + if (intlist__find(skiplist, i)) { + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); + continue; + } + pr_debug("\n--- start ---\n"); err = tests[curr].func(); pr_debug("---- end ----\n%s:", tests[curr].desc); - if (err) - color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n"); - else + + switch (err) { + case TEST_OK: pr_info(" Ok\n"); + break; + case TEST_SKIP: + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); + break; + case TEST_FAIL: + default: + color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n"); + break; + } } return 0; @@ -152,11 +176,14 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", NULL, }; + const char *skip = NULL; const struct option test_options[] = { + OPT_STRING('s', "skip", &skip, "tests", "tests to skip"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_END() }; + struct intlist *skiplist = NULL; argc = parse_options(argc, argv, test_options, test_usage, 0); if (argc >= 1 && !strcmp(argv[0], "list")) @@ -169,5 +196,8 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) if (symbol__init() < 0) return -1; - return __cmd_test(argc, argv); + if (skip != NULL) + skiplist = intlist__new(skip); + + return __cmd_test(argc, argv, skiplist); } diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index e61fc82..0fd99a9 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -22,7 +22,7 @@ static int perf_evsel__roundtrip_cache_name_test(void) for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { __perf_evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name)); - err = parse_events(evlist, name, 0); + err = parse_events(evlist, name); if (err) ret = err; } @@ -70,7 +70,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names) return -ENOMEM; for (i = 0; i < nr_names; ++i) { - err = parse_events(evlist, names[i], 0); + err = parse_events(evlist, names[i]); if (err) { pr_debug("failed to parse event '%s', err %d\n", names[i], err); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c new file mode 100644 index 0000000..1be64a6 --- /dev/null +++ b/tools/perf/tests/hists_link.c @@ -0,0 +1,500 @@ +#include "perf.h" +#include "tests.h" +#include "debug.h" +#include "symbol.h" +#include "sort.h" +#include "evsel.h" +#include "evlist.h" +#include "machine.h" +#include "thread.h" +#include "parse-events.h" + +static struct { + u32 pid; + const char *comm; +} fake_threads[] = { + { 100, "perf" }, + { 200, "perf" }, + { 300, "bash" }, +}; + +static struct { + u32 pid; + u64 start; + const char *filename; +} fake_mmap_info[] = { + { 100, 0x40000, "perf" }, + { 100, 0x50000, "libc" }, + { 100, 0xf0000, "[kernel]" }, + { 200, 0x40000, "perf" }, + { 200, 0x50000, "libc" }, + { 200, 0xf0000, "[kernel]" }, + { 300, 0x40000, "bash" }, + { 300, 0x50000, "libc" }, + { 300, 0xf0000, "[kernel]" }, +}; + +struct fake_sym { + u64 start; + u64 length; + const char *name; +}; + +static struct fake_sym perf_syms[] = { + { 700, 100, "main" }, + { 800, 100, "run_command" }, + { 900, 100, "cmd_record" }, +}; + +static struct fake_sym bash_syms[] = { + { 700, 100, "main" }, + { 800, 100, "xmalloc" }, + { 900, 100, "xfree" }, +}; + +static struct fake_sym libc_syms[] = { + { 700, 100, "malloc" }, + { 800, 100, "free" }, + { 900, 100, "realloc" }, +}; + +static struct fake_sym kernel_syms[] = { + { 700, 100, "schedule" }, + { 800, 100, "page_fault" }, + { 900, 100, "sys_perf_event_open" }, +}; + +static struct { + const char *dso_name; + struct fake_sym *syms; + size_t nr_syms; +} fake_symbols[] = { + { "perf", perf_syms, ARRAY_SIZE(perf_syms) }, + { "bash", bash_syms, ARRAY_SIZE(bash_syms) }, + { "libc", libc_syms, ARRAY_SIZE(libc_syms) }, + { "[kernel]", kernel_syms, ARRAY_SIZE(kernel_syms) }, +}; + +static struct machine *setup_fake_machine(struct machines *machines) +{ + struct machine *machine = machines__find(machines, HOST_KERNEL_ID); + size_t i; + + if (machine == NULL) { + pr_debug("Not enough memory for machine setup\n"); + return NULL; + } + + for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { + struct thread *thread; + + thread = machine__findnew_thread(machine, fake_threads[i].pid); + if (thread == NULL) + goto out; + + thread__set_comm(thread, fake_threads[i].comm); + } + + for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) { + union perf_event fake_mmap_event = { + .mmap = { + .header = { .misc = PERF_RECORD_MISC_USER, }, + .pid = fake_mmap_info[i].pid, + .start = fake_mmap_info[i].start, + .len = 0x1000ULL, + .pgoff = 0ULL, + }, + }; + + strcpy(fake_mmap_event.mmap.filename, + fake_mmap_info[i].filename); + + machine__process_mmap_event(machine, &fake_mmap_event); + } + + for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) { + size_t k; + struct dso *dso; + + dso = __dsos__findnew(&machine->user_dsos, + fake_symbols[i].dso_name); + if (dso == NULL) + goto out; + + /* emulate dso__load() */ + dso__set_loaded(dso, MAP__FUNCTION); + + for (k = 0; k < fake_symbols[i].nr_syms; k++) { + struct symbol *sym; + struct fake_sym *fsym = &fake_symbols[i].syms[k]; + + sym = symbol__new(fsym->start, fsym->length, + STB_GLOBAL, fsym->name); + if (sym == NULL) + goto out; + + symbols__insert(&dso->symbols[MAP__FUNCTION], sym); + } + } + + return machine; + +out: + pr_debug("Not enough memory for machine setup\n"); + machine__delete_threads(machine); + machine__delete(machine); + return NULL; +} + +struct sample { + u32 pid; + u64 ip; + struct thread *thread; + struct map *map; + struct symbol *sym; +}; + +static struct sample fake_common_samples[] = { + /* perf [kernel] schedule() */ + { .pid = 100, .ip = 0xf0000 + 700, }, + /* perf [perf] main() */ + { .pid = 200, .ip = 0x40000 + 700, }, + /* perf [perf] cmd_record() */ + { .pid = 200, .ip = 0x40000 + 900, }, + /* bash [bash] xmalloc() */ + { .pid = 300, .ip = 0x40000 + 800, }, + /* bash [libc] malloc() */ + { .pid = 300, .ip = 0x50000 + 700, }, +}; + +static struct sample fake_samples[][5] = { + { + /* perf [perf] run_command() */ + { .pid = 100, .ip = 0x40000 + 800, }, + /* perf [libc] malloc() */ + { .pid = 100, .ip = 0x50000 + 700, }, + /* perf [kernel] page_fault() */ + { .pid = 100, .ip = 0xf0000 + 800, }, + /* perf [kernel] sys_perf_event_open() */ + { .pid = 200, .ip = 0xf0000 + 900, }, + /* bash [libc] free() */ + { .pid = 300, .ip = 0x50000 + 800, }, + }, + { + /* perf [libc] free() */ + { .pid = 200, .ip = 0x50000 + 800, }, + /* bash [libc] malloc() */ + { .pid = 300, .ip = 0x50000 + 700, }, /* will be merged */ + /* bash [bash] xfee() */ + { .pid = 300, .ip = 0x40000 + 900, }, + /* bash [libc] realloc() */ + { .pid = 300, .ip = 0x50000 + 900, }, + /* bash [kernel] page_fault() */ + { .pid = 300, .ip = 0xf0000 + 800, }, + }, +}; + +static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) +{ + struct perf_evsel *evsel; + struct addr_location al; + struct hist_entry *he; + struct perf_sample sample = { .cpu = 0, }; + size_t i = 0, k; + + /* + * each evsel will have 10 samples - 5 common and 5 distinct. + * However the second evsel also has a collapsed entry for + * "bash [libc] malloc" so total 9 entries will be in the tree. + */ + list_for_each_entry(evsel, &evlist->entries, node) { + for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) { + const union perf_event event = { + .ip = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + .pid = fake_common_samples[k].pid, + .ip = fake_common_samples[k].ip, + }, + }; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample, 0) < 0) + goto out; + + he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + if (he == NULL) + goto out; + + fake_common_samples[k].thread = al.thread; + fake_common_samples[k].map = al.map; + fake_common_samples[k].sym = al.sym; + } + + for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) { + const union perf_event event = { + .ip = { + .header = { + .misc = PERF_RECORD_MISC_USER, + }, + .pid = fake_samples[i][k].pid, + .ip = fake_samples[i][k].ip, + }, + }; + + if (perf_event__preprocess_sample(&event, machine, &al, + &sample, 0) < 0) + goto out; + + he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + if (he == NULL) + goto out; + + fake_samples[i][k].thread = al.thread; + fake_samples[i][k].map = al.map; + fake_samples[i][k].sym = al.sym; + } + i++; + } + + return 0; + +out: + pr_debug("Not enough memory for adding a hist entry\n"); + return -1; +} + +static int find_sample(struct sample *samples, size_t nr_samples, + struct thread *t, struct map *m, struct symbol *s) +{ + while (nr_samples--) { + if (samples->thread == t && samples->map == m && + samples->sym == s) + return 1; + samples++; + } + return 0; +} + +static int __validate_match(struct hists *hists) +{ + size_t count = 0; + struct rb_root *root; + struct rb_node *node; + + /* + * Only entries from fake_common_samples should have a pair. + */ + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + if (hist_entry__has_pairs(he)) { + if (find_sample(fake_common_samples, + ARRAY_SIZE(fake_common_samples), + he->thread, he->ms.map, he->ms.sym)) { + count++; + } else { + pr_debug("Can't find the matched entry\n"); + return -1; + } + } + + node = rb_next(node); + } + + if (count != ARRAY_SIZE(fake_common_samples)) { + pr_debug("Invalid count for matched entries: %zd of %zd\n", + count, ARRAY_SIZE(fake_common_samples)); + return -1; + } + + return 0; +} + +static int validate_match(struct hists *leader, struct hists *other) +{ + return __validate_match(leader) || __validate_match(other); +} + +static int __validate_link(struct hists *hists, int idx) +{ + size_t count = 0; + size_t count_pair = 0; + size_t count_dummy = 0; + struct rb_root *root; + struct rb_node *node; + + /* + * Leader hists (idx = 0) will have dummy entries from other, + * and some entries will have no pair. However every entry + * in other hists should have (dummy) pair. + */ + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + if (hist_entry__has_pairs(he)) { + if (!find_sample(fake_common_samples, + ARRAY_SIZE(fake_common_samples), + he->thread, he->ms.map, he->ms.sym) && + !find_sample(fake_samples[idx], + ARRAY_SIZE(fake_samples[idx]), + he->thread, he->ms.map, he->ms.sym)) { + count_dummy++; + } + count_pair++; + } else if (idx) { + pr_debug("A entry from the other hists should have pair\n"); + return -1; + } + + count++; + node = rb_next(node); + } + + /* + * Note that we have a entry collapsed in the other (idx = 1) hists. + */ + if (idx == 0) { + if (count_dummy != ARRAY_SIZE(fake_samples[1]) - 1) { + pr_debug("Invalid count of dummy entries: %zd of %zd\n", + count_dummy, ARRAY_SIZE(fake_samples[1]) - 1); + return -1; + } + if (count != count_pair + ARRAY_SIZE(fake_samples[0])) { + pr_debug("Invalid count of total leader entries: %zd of %zd\n", + count, count_pair + ARRAY_SIZE(fake_samples[0])); + return -1; + } + } else { + if (count != count_pair) { + pr_debug("Invalid count of total other entries: %zd of %zd\n", + count, count_pair); + return -1; + } + if (count_dummy > 0) { + pr_debug("Other hists should not have dummy entries: %zd\n", + count_dummy); + return -1; + } + } + + return 0; +} + +static int validate_link(struct hists *leader, struct hists *other) +{ + return __validate_link(leader, 0) || __validate_link(other, 1); +} + +static void print_hists(struct hists *hists) +{ + int i = 0; + struct rb_root *root; + struct rb_node *node; + + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + pr_info("----- %s --------\n", __func__); + node = rb_first(root); + while (node) { + struct hist_entry *he; + + he = rb_entry(node, struct hist_entry, rb_node_in); + + pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n", + i, he->thread->comm, he->ms.map->dso->short_name, + he->ms.sym->name, he->stat.period); + + i++; + node = rb_next(node); + } +} + +int test__hists_link(void) +{ + int err = -1; + struct machines machines; + struct machine *machine = NULL; + struct perf_evsel *evsel, *first; + struct perf_evlist *evlist = perf_evlist__new(NULL, NULL); + + if (evlist == NULL) + return -ENOMEM; + + err = parse_events(evlist, "cpu-clock"); + if (err) + goto out; + err = parse_events(evlist, "task-clock"); + if (err) + goto out; + + /* default sort order (comm,dso,sym) will be used */ + if (setup_sorting() < 0) + goto out; + + machines__init(&machines); + + /* setup threads/dso/map/symbols also */ + machine = setup_fake_machine(&machines); + if (!machine) + goto out; + + if (verbose > 1) + machine__fprintf(machine, stderr); + + /* process sample events */ + err = add_hist_entries(evlist, machine); + if (err < 0) + goto out; + + list_for_each_entry(evsel, &evlist->entries, node) { + hists__collapse_resort(&evsel->hists); + + if (verbose > 2) + print_hists(&evsel->hists); + } + + first = perf_evlist__first(evlist); + evsel = perf_evlist__last(evlist); + + /* match common entries */ + hists__match(&first->hists, &evsel->hists); + err = validate_match(&first->hists, &evsel->hists); + if (err) + goto out; + + /* link common and/or dummy entries */ + hists__link(&first->hists, &evsel->hists); + err = validate_link(&first->hists, &evsel->hists); + if (err) + goto out; + + err = 0; + +out: + /* tear down everything */ + perf_evlist__delete(evlist); + machines__exit(&machines); + + return err; +} diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index e174681..cdd5075 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -22,36 +22,16 @@ int test__basic_mmap(void) struct thread_map *threads; struct cpu_map *cpus; struct perf_evlist *evlist; - struct perf_event_attr attr = { - .type = PERF_TYPE_TRACEPOINT, - .read_format = PERF_FORMAT_ID, - .sample_type = PERF_SAMPLE_ID, - .watermark = 0, - }; cpu_set_t cpu_set; const char *syscall_names[] = { "getsid", "getppid", "getpgrp", "getpgid", }; pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp, (void*)getpgid }; #define nsyscalls ARRAY_SIZE(syscall_names) - int ids[nsyscalls]; unsigned int nr_events[nsyscalls], expected_nr_events[nsyscalls], i, j; struct perf_evsel *evsels[nsyscalls], *evsel; - for (i = 0; i < nsyscalls; ++i) { - char name[64]; - - snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]); - ids[i] = trace_event__id(name); - if (ids[i] < 0) { - pr_debug("Is debugfs mounted on /sys/kernel/debug?\n"); - return -1; - } - nr_events[i] = 0; - expected_nr_events[i] = random() % 257; - } - threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { pr_debug("thread_map__new\n"); @@ -79,18 +59,19 @@ int test__basic_mmap(void) goto out_free_cpus; } - /* anonymous union fields, can't be initialized above */ - attr.wakeup_events = 1; - attr.sample_period = 1; - for (i = 0; i < nsyscalls; ++i) { - attr.config = ids[i]; - evsels[i] = perf_evsel__new(&attr, i); + char name[64]; + + snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]); + evsels[i] = perf_evsel__newtp("syscalls", name, i); if (evsels[i] == NULL) { pr_debug("perf_evsel__new\n"); goto out_free_evlist; } + evsels[i]->attr.wakeup_events = 1; + perf_evsel__set_sample_id(evsels[i]); + perf_evlist__add(evlist, evsels[i]); if (perf_evsel__open(evsels[i], cpus, threads) < 0) { @@ -99,6 +80,9 @@ int test__basic_mmap(void) strerror(errno)); goto out_close_fd; } + + nr_events[i] = 0; + expected_nr_events[i] = 1 + rand() % 127; } if (perf_evlist__mmap(evlist, 128, true) < 0) { @@ -128,6 +112,7 @@ int test__basic_mmap(void) goto out_munmap; } + err = -1; evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { pr_debug("event with id %" PRIu64 @@ -137,16 +122,17 @@ int test__basic_mmap(void) nr_events[evsel->idx]++; } + err = 0; list_for_each_entry(evsel, &evlist->entries, node) { if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { pr_debug("expected %d %s events, got %d\n", expected_nr_events[evsel->idx], perf_evsel__name(evsel), nr_events[evsel->idx]); + err = -1; goto out_munmap; } } - err = 0; out_munmap: perf_evlist__munmap(evlist); out_close_fd: diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c index 31072ab..b0657a9 100644 --- a/tools/perf/tests/open-syscall-all-cpus.c +++ b/tools/perf/tests/open-syscall-all-cpus.c @@ -7,20 +7,12 @@ int test__open_syscall_event_on_all_cpus(void) { int err = -1, fd, cpu; - struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *evsel; - struct perf_event_attr attr; unsigned int nr_open_calls = 111, i; cpu_set_t cpu_set; - int id = trace_event__id("sys_enter_open"); + struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); - if (id < 0) { - pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); - return -1; - } - - threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { pr_debug("thread_map__new\n"); return -1; @@ -32,15 +24,11 @@ int test__open_syscall_event_on_all_cpus(void) goto out_thread_map_delete; } - CPU_ZERO(&cpu_set); - memset(&attr, 0, sizeof(attr)); - attr.type = PERF_TYPE_TRACEPOINT; - attr.config = id; - evsel = perf_evsel__new(&attr, 0); + evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); if (evsel == NULL) { - pr_debug("perf_evsel__new\n"); + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); goto out_thread_map_delete; } @@ -110,6 +98,7 @@ int test__open_syscall_event_on_all_cpus(void) } } + perf_evsel__free_counts(evsel); out_close_fd: perf_evsel__close_fd(evsel, 1, threads->nr); out_evsel_delete: diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c index 98be8b5..befc067 100644 --- a/tools/perf/tests/open-syscall.c +++ b/tools/perf/tests/open-syscall.c @@ -6,29 +6,18 @@ int test__open_syscall_event(void) { int err = -1, fd; - struct thread_map *threads; struct perf_evsel *evsel; - struct perf_event_attr attr; unsigned int nr_open_calls = 111, i; - int id = trace_event__id("sys_enter_open"); + struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX); - if (id < 0) { - pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); - return -1; - } - - threads = thread_map__new(-1, getpid(), UINT_MAX); if (threads == NULL) { pr_debug("thread_map__new\n"); return -1; } - memset(&attr, 0, sizeof(attr)); - attr.type = PERF_TYPE_TRACEPOINT; - attr.config = id; - evsel = perf_evsel__new(&attr, 0); + evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0); if (evsel == NULL) { - pr_debug("perf_evsel__new\n"); + pr_debug("is debugfs mounted on /sys/kernel/debug?\n"); goto out_thread_map_delete; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 32ee478..c5636f3 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -3,6 +3,7 @@ #include "evsel.h" #include "evlist.h" #include "sysfs.h" +#include "debugfs.h" #include "tests.h" #include <linux/hw_breakpoint.h> @@ -22,6 +23,7 @@ static int test__checkevent_tracepoint(struct perf_evlist *evlist) struct perf_evsel *evsel = perf_evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type); TEST_ASSERT_VAL("wrong sample_type", PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type); @@ -34,6 +36,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist) struct perf_evsel *evsel; TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1); + TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups); list_for_each_entry(evsel, &evlist->entries, node) { TEST_ASSERT_VAL("wrong type", @@ -463,10 +466,10 @@ static int test__checkevent_pmu_events(struct perf_evlist *evlist) static int test__checkterms_simple(struct list_head *terms) { - struct parse_events__term *term; + struct parse_events_term *term; /* config=10 */ - term = list_entry(terms->next, struct parse_events__term, list); + term = list_entry(terms->next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG); TEST_ASSERT_VAL("wrong type val", @@ -475,7 +478,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong config", !term->config); /* config1 */ - term = list_entry(term->list.next, struct parse_events__term, list); + term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1); TEST_ASSERT_VAL("wrong type val", @@ -484,7 +487,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong config", !term->config); /* config2=3 */ - term = list_entry(term->list.next, struct parse_events__term, list); + term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2); TEST_ASSERT_VAL("wrong type val", @@ -493,7 +496,7 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong config", !term->config); /* umask=1*/ - term = list_entry(term->list.next, struct parse_events__term, list); + term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_USER); TEST_ASSERT_VAL("wrong type val", @@ -509,6 +512,7 @@ static int test__group1(struct perf_evlist *evlist) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* instructions:k */ evsel = leader = perf_evlist__first(evlist); @@ -521,7 +525,9 @@ static int test__group1(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cycles:upp */ evsel = perf_evsel__next(evsel); @@ -536,6 +542,7 @@ static int test__group1(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } @@ -545,6 +552,7 @@ static int test__group2(struct perf_evlist *evlist) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* faults + :ku modifier */ evsel = leader = perf_evlist__first(evlist); @@ -557,7 +565,9 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* cache-references + :u modifier */ evsel = perf_evsel__next(evsel); @@ -567,10 +577,11 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles:k */ evsel = perf_evsel__next(evsel); @@ -583,7 +594,7 @@ static int test__group2(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); return 0; } @@ -593,6 +604,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* group1 syscalls:sys_enter_open:H */ evsel = leader = perf_evlist__first(evlist); @@ -606,9 +618,11 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong group name", !strcmp(leader->group_name, "group1")); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* group1 cycles:kppp */ evsel = perf_evsel__next(evsel); @@ -624,6 +638,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* group2 cycles + G modifier */ evsel = leader = perf_evsel__next(evsel); @@ -636,9 +651,11 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); TEST_ASSERT_VAL("wrong group name", !strcmp(leader->group_name, "group2")); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* group2 1:3 + G modifier */ evsel = perf_evsel__next(evsel); @@ -651,6 +668,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* instructions:u */ evsel = perf_evsel__next(evsel); @@ -663,7 +681,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); return 0; } @@ -673,6 +691,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); /* cycles:u + p */ evsel = leader = perf_evlist__first(evlist); @@ -687,7 +706,9 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* instructions:kp + p */ evsel = perf_evsel__next(evsel); @@ -702,6 +723,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } @@ -711,6 +733,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) struct perf_evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups); /* cycles + G */ evsel = leader = perf_evlist__first(evlist); @@ -724,7 +747,9 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* instructions + G */ evsel = perf_evsel__next(evsel); @@ -738,6 +763,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles:G */ evsel = leader = perf_evsel__next(evsel); @@ -751,7 +777,9 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong group name", !evsel->group_name); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); /* instructions:G */ evsel = perf_evsel__next(evsel); @@ -765,6 +793,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); /* cycles */ evsel = perf_evsel__next(evsel); @@ -777,18 +806,235 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); - TEST_ASSERT_VAL("wrong leader", !perf_evsel__is_group_member(evsel)); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + + return 0; +} + +static int test__group_gh1(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles + :H group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:G + :H group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + + return 0; +} + +static int test__group_gh2(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles + :G group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:H + :G group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + + return 0; +} + +static int test__group_gh3(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles:G + :u group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:H + :u group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); + + return 0; +} + +static int test__group_gh4(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel, *leader; + + TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->nr_groups); + + /* cycles:G + :uG group modifier */ + evsel = leader = perf_evlist__first(evlist); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); + TEST_ASSERT_VAL("wrong leader", perf_evsel__is_group_leader(evsel)); + TEST_ASSERT_VAL("wrong nr_members", evsel->nr_members == 2); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 0); + + /* cache-misses:H + :uG group modifier */ + evsel = perf_evsel__next(evsel); + TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", + PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); + TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host); + TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong leader", evsel->leader == leader); + TEST_ASSERT_VAL("wrong group_idx", perf_evsel__group_idx(evsel) == 1); return 0; } -struct test__event_st { +static int count_tracepoints(void) +{ + char events_path[PATH_MAX]; + struct dirent *events_ent; + DIR *events_dir; + int cnt = 0; + + scnprintf(events_path, PATH_MAX, "%s/tracing/events", + debugfs_find_mountpoint()); + + events_dir = opendir(events_path); + + TEST_ASSERT_VAL("Can't open events dir", events_dir); + + while ((events_ent = readdir(events_dir))) { + char sys_path[PATH_MAX]; + struct dirent *sys_ent; + DIR *sys_dir; + + if (!strcmp(events_ent->d_name, ".") + || !strcmp(events_ent->d_name, "..") + || !strcmp(events_ent->d_name, "enable") + || !strcmp(events_ent->d_name, "header_event") + || !strcmp(events_ent->d_name, "header_page")) + continue; + + scnprintf(sys_path, PATH_MAX, "%s/%s", + events_path, events_ent->d_name); + + sys_dir = opendir(sys_path); + TEST_ASSERT_VAL("Can't open sys dir", sys_dir); + + while ((sys_ent = readdir(sys_dir))) { + if (!strcmp(sys_ent->d_name, ".") + || !strcmp(sys_ent->d_name, "..") + || !strcmp(sys_ent->d_name, "enable") + || !strcmp(sys_ent->d_name, "filter")) + continue; + + cnt++; + } + + closedir(sys_dir); + } + + closedir(events_dir); + return cnt; +} + +static int test__all_tracepoints(struct perf_evlist *evlist) +{ + TEST_ASSERT_VAL("wrong events count", + count_tracepoints() == evlist->nr_entries); + + return test__checkevent_tracepoint_multi(evlist); +} + +struct evlist_test { const char *name; __u32 type; int (*check)(struct perf_evlist *evlist); }; -static struct test__event_st test__events[] = { +static struct evlist_test test__events[] = { [0] = { .name = "syscalls:sys_enter_open", .check = test__checkevent_tracepoint, @@ -921,9 +1167,29 @@ static struct test__event_st test__events[] = { .name = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles", .check = test__group5, }, + [33] = { + .name = "*:*", + .check = test__all_tracepoints, + }, + [34] = { + .name = "{cycles,cache-misses:G}:H", + .check = test__group_gh1, + }, + [35] = { + .name = "{cycles,cache-misses:H}:G", + .check = test__group_gh2, + }, + [36] = { + .name = "{cycles:G,cache-misses:H}:u", + .check = test__group_gh3, + }, + [37] = { + .name = "{cycles:G,cache-misses:H}:uG", + .check = test__group_gh4, + }, }; -static struct test__event_st test__events_pmu[] = { +static struct evlist_test test__events_pmu[] = { [0] = { .name = "cpu/config=10,config1,config2=3,period=1000/u", .check = test__checkevent_pmu, @@ -934,20 +1200,20 @@ static struct test__event_st test__events_pmu[] = { }, }; -struct test__term { +struct terms_test { const char *str; __u32 type; int (*check)(struct list_head *terms); }; -static struct test__term test__terms[] = { +static struct terms_test test__terms[] = { [0] = { .str = "config=10,config1,config2=3,umask=1", .check = test__checkterms_simple, }, }; -static int test_event(struct test__event_st *e) +static int test_event(struct evlist_test *e) { struct perf_evlist *evlist; int ret; @@ -956,7 +1222,7 @@ static int test_event(struct test__event_st *e) if (evlist == NULL) return -ENOMEM; - ret = parse_events(evlist, e->name, 0); + ret = parse_events(evlist, e->name); if (ret) { pr_debug("failed to parse event '%s', err %d\n", e->name, ret); @@ -969,13 +1235,13 @@ static int test_event(struct test__event_st *e) return ret; } -static int test_events(struct test__event_st *events, unsigned cnt) +static int test_events(struct evlist_test *events, unsigned cnt) { int ret1, ret2 = 0; unsigned i; for (i = 0; i < cnt; i++) { - struct test__event_st *e = &events[i]; + struct evlist_test *e = &events[i]; pr_debug("running test %d '%s'\n", i, e->name); ret1 = test_event(e); @@ -986,7 +1252,7 @@ static int test_events(struct test__event_st *events, unsigned cnt) return ret2; } -static int test_term(struct test__term *t) +static int test_term(struct terms_test *t) { struct list_head *terms; int ret; @@ -1010,13 +1276,13 @@ static int test_term(struct test__term *t) return ret; } -static int test_terms(struct test__term *terms, unsigned cnt) +static int test_terms(struct terms_test *terms, unsigned cnt) { int ret = 0; unsigned i; for (i = 0; i < cnt; i++) { - struct test__term *t = &terms[i]; + struct terms_test *t = &terms[i]; pr_debug("running test %d '%s'\n", i, t->str); ret = test_term(t); @@ -1067,7 +1333,7 @@ static int test_pmu_events(void) while (!ret && (ent = readdir(dir))) { #define MAX_NAME 100 - struct test__event_st e; + struct evlist_test e; char name[MAX_NAME]; if (!strcmp(ent->d_name, ".") || diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 70e0d44..1e8e512 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -96,22 +96,22 @@ int test__PERF_RECORD(void) err = perf_evlist__prepare_workload(evlist, &opts, argv); if (err < 0) { pr_debug("Couldn't run the workload!\n"); - goto out_delete_evlist; + goto out_delete_maps; } /* * Config the evsels, setting attr->comm on the first one, etc. */ evsel = perf_evlist__first(evlist); - evsel->attr.sample_type |= PERF_SAMPLE_CPU; - evsel->attr.sample_type |= PERF_SAMPLE_TID; - evsel->attr.sample_type |= PERF_SAMPLE_TIME; - perf_evlist__config_attrs(evlist, &opts); + perf_evsel__set_sample_bit(evsel, CPU); + perf_evsel__set_sample_bit(evsel, TID); + perf_evsel__set_sample_bit(evsel, TIME); + perf_evlist__config(evlist, &opts); err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); if (err < 0) { pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_delete_maps; } cpu = err; @@ -121,7 +121,7 @@ int test__PERF_RECORD(void) */ if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) { pr_debug("sched_setaffinity: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_delete_maps; } /* @@ -131,7 +131,7 @@ int test__PERF_RECORD(void) err = perf_evlist__open(evlist); if (err < 0) { pr_debug("perf_evlist__open: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_delete_maps; } /* @@ -142,7 +142,7 @@ int test__PERF_RECORD(void) err = perf_evlist__mmap(evlist, opts.mmap_pages, false); if (err < 0) { pr_debug("perf_evlist__mmap: %s\n", strerror(errno)); - goto out_delete_evlist; + goto out_delete_maps; } /* @@ -305,6 +305,8 @@ found_exit: } out_err: perf_evlist__munmap(evlist); +out_delete_maps: + perf_evlist__delete_maps(evlist); out_delete_evlist: perf_evlist__delete(evlist); out: diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index a5f3798..12b322f 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -19,10 +19,8 @@ static struct test_format { { "krava23", "config2:28-29,38\n", }, }; -#define TEST_FORMATS_CNT (sizeof(test_formats) / sizeof(struct test_format)) - /* Simulated users input. */ -static struct parse_events__term test_terms[] = { +static struct parse_events_term test_terms[] = { { .config = (char *) "krava01", .val.num = 15, @@ -78,7 +76,6 @@ static struct parse_events__term test_terms[] = { .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, }; -#define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term)) /* * Prepare format directory data, exported by kernel @@ -93,7 +90,7 @@ static char *test_format_dir_get(void) if (!mkdtemp(dir)) return NULL; - for (i = 0; i < TEST_FORMATS_CNT; i++) { + for (i = 0; i < ARRAY_SIZE(test_formats); i++) { static char name[PATH_MAX]; struct test_format *format = &test_formats[i]; FILE *file; @@ -130,14 +127,12 @@ static struct list_head *test_terms_list(void) static LIST_HEAD(terms); unsigned int i; - for (i = 0; i < TERMS_CNT; i++) + for (i = 0; i < ARRAY_SIZE(test_terms); i++) list_add_tail(&test_terms[i].list, &terms); return &terms; } -#undef TERMS_CNT - int test__pmu(void) { char *format = test_format_dir_get(); diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c new file mode 100644 index 0000000..7760277 --- /dev/null +++ b/tools/perf/tests/python-use.c @@ -0,0 +1,23 @@ +/* + * Just test if we can load the python binding. + */ + +#include <stdio.h> +#include <stdlib.h> +#include "tests.h" + +extern int verbose; + +int test__python_use(void) +{ + char *cmd; + int ret; + + if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s", + PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0) + return -1; + + ret = system(cmd) ? -1 : 0; + free(cmd); + return ret; +} diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index fc121ed..5de0be1 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -1,6 +1,12 @@ #ifndef TESTS_H #define TESTS_H +enum { + TEST_OK = 0, + TEST_FAIL = -1, + TEST_SKIP = -2, +}; + /* Tests */ int test__vmlinux_matches_kallsyms(void); int test__open_syscall_event(void); @@ -15,8 +21,7 @@ int test__pmu(void); int test__attr(void); int test__dso_data(void); int test__parse_events(void); - -/* Util */ -int trace_event__id(const char *evname); +int test__hists_link(void); +int test__python_use(void); #endif /* TESTS_H */ diff --git a/tools/perf/tests/util.c b/tools/perf/tests/util.c deleted file mode 100644 index 748f2e8..0000000 --- a/tools/perf/tests/util.c +++ /dev/null @@ -1,30 +0,0 @@ -#include <stdio.h> -#include <unistd.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include "tests.h" -#include "debugfs.h" - -int trace_event__id(const char *evname) -{ - char *filename; - int err = -1, fd; - - if (asprintf(&filename, - "%s/syscalls/%s/id", - tracing_events_path, evname) < 0) - return -1; - - fd = open(filename, O_RDONLY); - if (fd >= 0) { - char id[16]; - if (read(fd, id, sizeof(id)) > 0) - err = atoi(id); - close(fd); - } - - free(filename); - return err; -} diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 0d1cdbe..7b4c4d2 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -44,7 +44,7 @@ int test__vmlinux_matches_kallsyms(void) */ if (machine__create_kernel_maps(&kallsyms) < 0) { pr_debug("machine__create_kernel_maps "); - return -1; + goto out; } /* @@ -101,7 +101,8 @@ int test__vmlinux_matches_kallsyms(void) */ if (machine__load_vmlinux_path(&vmlinux, type, vmlinux_matches_kallsyms_filter) <= 0) { - pr_debug("machine__load_vmlinux_path "); + pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n"); + err = TEST_SKIP; goto out; } @@ -226,5 +227,7 @@ detour: map__fprintf(pos, stderr); } out: + machine__exit(&kallsyms); + machine__exit(&vmlinux); return err; } diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 4aeb7d5..809ea46 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -273,6 +273,8 @@ void ui_browser__hide(struct ui_browser *browser __maybe_unused) { pthread_mutex_lock(&ui__lock); ui_helpline__pop(); + free(browser->helpline); + browser->helpline = NULL; pthread_mutex_unlock(&ui__lock); } @@ -471,7 +473,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser) return row; } -static struct ui_browser__colorset { +static struct ui_browser_colorset { const char *name, *fg, *bg; int colorset; } ui_browser__colorsets[] = { @@ -706,7 +708,7 @@ void ui_browser__init(void) perf_config(ui_browser__color_config, NULL); while (ui_browser__colorsets[i].name) { - struct ui_browser__colorset *c = &ui_browser__colorsets[i++]; + struct ui_browser_colorset *c = &ui_browser__colorsets[i++]; sltt_set_color(c->colorset, c->name, c->fg, c->bg); } diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 5dab3ca..7dca155 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -182,6 +182,16 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int ab->selection = dl; } +static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym) +{ + if (!dl || !dl->ins || !ins__is_jump(dl->ins) + || !disasm_line__has_offset(dl) + || dl->ops.target.offset >= symbol__size(sym)) + return false; + + return true; +} + static void annotate_browser__draw_current_jump(struct ui_browser *browser) { struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); @@ -195,8 +205,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) if (strstr(sym->name, "@plt")) return; - if (!cursor || !cursor->ins || !ins__is_jump(cursor->ins) || - !disasm_line__has_offset(cursor)) + if (!disasm_line__is_valid_jump(cursor, sym)) return; target = ab->offsets[cursor->ops.target.offset]; @@ -788,17 +797,9 @@ static void annotate_browser__mark_jump_targets(struct annotate_browser *browser struct disasm_line *dl = browser->offsets[offset], *dlt; struct browser_disasm_line *bdlt; - if (!dl || !dl->ins || !ins__is_jump(dl->ins) || - !disasm_line__has_offset(dl)) + if (!disasm_line__is_valid_jump(dl, sym)) continue; - if (dl->ops.target.offset >= size) { - ui__error("jump to after symbol!\n" - "size: %zx, jump target: %" PRIx64, - size, dl->ops.target.offset); - continue; - } - dlt = browser->offsets[dl->ops.target.offset]; /* * FIXME: Oops, no jump target? Buggy disassembler? Or do we @@ -921,11 +922,11 @@ out_free_offsets: #define ANNOTATE_CFG(n) \ { .name = #n, .value = &annotate_browser__opts.n, } - + /* * Keep the entries sorted, they are bsearch'ed */ -static struct annotate__config { +static struct annotate_config { const char *name; bool *value; } annotate__configs[] = { @@ -939,7 +940,7 @@ static struct annotate__config { static int annotate_config__cmp(const void *name, const void *cfgp) { - const struct annotate__config *cfg = cfgp; + const struct annotate_config *cfg = cfgp; return strcmp(name, cfg->name); } @@ -947,7 +948,7 @@ static int annotate_config__cmp(const void *name, const void *cfgp) static int annotate__config(const char *var, const char *value, void *data __maybe_unused) { - struct annotate__config *cfg; + struct annotate_config *cfg; const char *name; if (prefixcmp(var, "annotate.") != 0) @@ -955,7 +956,7 @@ static int annotate__config(const char *var, const char *value, name = var + 9; cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs), - sizeof(struct annotate__config), annotate_config__cmp); + sizeof(struct annotate_config), annotate_config__cmp); if (cfg == NULL) return -1; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index ccc4bd1..aa22704 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -567,26 +567,128 @@ static int hist_browser__show_callchain(struct hist_browser *browser, return row - first_row; } -#define HPP__COLOR_FN(_name, _field) \ -static int hist_browser__hpp_color_ ## _name(struct perf_hpp *hpp, \ - struct hist_entry *he) \ +struct hpp_arg { + struct ui_browser *b; + char folded_sign; + bool current_entry; +}; + +static int __hpp__color_callchain(struct hpp_arg *arg) +{ + if (!symbol_conf.use_callchain) + return 0; + + slsmg_printf("%c ", arg->folded_sign); + return 2; +} + +static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, + u64 (*get_field)(struct hist_entry *), + int (*callchain_cb)(struct hpp_arg *)) +{ + int ret = 0; + double percent = 0.0; + struct hists *hists = he->hists; + struct hpp_arg *arg = hpp->ptr; + + if (hists->stats.total_period) + percent = 100.0 * get_field(he) / hists->stats.total_period; + + ui_browser__set_percent_color(arg->b, percent, arg->current_entry); + + if (callchain_cb) + ret += callchain_cb(arg); + + ret += scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); + slsmg_printf("%s", hpp->buf); + + if (symbol_conf.event_group) { + int prev_idx, idx_delta; + struct perf_evsel *evsel = hists_to_evsel(hists); + struct hist_entry *pair; + int nr_members = evsel->nr_members; + + if (nr_members <= 1) + goto out; + + prev_idx = perf_evsel__group_idx(evsel); + + list_for_each_entry(pair, &he->pairs.head, pairs.node) { + u64 period = get_field(pair); + u64 total = pair->hists->stats.total_period; + + if (!total) + continue; + + evsel = hists_to_evsel(pair->hists); + idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members in the middle which + * have no sample + */ + ui_browser__set_percent_color(arg->b, 0.0, + arg->current_entry); + ret += scnprintf(hpp->buf, hpp->size, + " %6.2f%%", 0.0); + slsmg_printf("%s", hpp->buf); + } + + percent = 100.0 * period / total; + ui_browser__set_percent_color(arg->b, percent, + arg->current_entry); + ret += scnprintf(hpp->buf, hpp->size, + " %6.2f%%", percent); + slsmg_printf("%s", hpp->buf); + + prev_idx = perf_evsel__group_idx(evsel); + } + + idx_delta = nr_members - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members at last which have no sample + */ + ui_browser__set_percent_color(arg->b, 0.0, + arg->current_entry); + ret += scnprintf(hpp->buf, hpp->size, + " %6.2f%%", 0.0); + slsmg_printf("%s", hpp->buf); + } + } +out: + if (!arg->current_entry || !arg->b->navkeypressed) + ui_browser__set_color(arg->b, HE_COLORSET_NORMAL); + + return ret; +} + +#define __HPP_COLOR_PERCENT_FN(_type, _field, _cb) \ +static u64 __hpp_get_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp, \ + struct hist_entry *he) \ { \ - struct hists *hists = he->hists; \ - double percent = 100.0 * he->stat._field / hists->stats.total_period; \ - *(double *)hpp->ptr = percent; \ - return scnprintf(hpp->buf, hpp->size, "%6.2f%%", percent); \ + return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb); \ } -HPP__COLOR_FN(overhead, period) -HPP__COLOR_FN(overhead_sys, period_sys) -HPP__COLOR_FN(overhead_us, period_us) -HPP__COLOR_FN(overhead_guest_sys, period_guest_sys) -HPP__COLOR_FN(overhead_guest_us, period_guest_us) +__HPP_COLOR_PERCENT_FN(overhead, period, __hpp__color_callchain) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys, NULL) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us, NULL) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys, NULL) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL) -#undef HPP__COLOR_FN +#undef __HPP_COLOR_PERCENT_FN void hist_browser__init_hpp(void) { + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + perf_hpp__init(); perf_hpp__format[PERF_HPP__OVERHEAD].color = @@ -606,13 +708,13 @@ static int hist_browser__show_entry(struct hist_browser *browser, unsigned short row) { char s[256]; - double percent; - int i, printed = 0; + int printed = 0; int width = browser->b.width; char folded_sign = ' '; bool current_entry = ui_browser__is_current_entry(&browser->b, row); off_t row_offset = entry->row_offset; bool first = true; + struct perf_hpp_fmt *fmt; if (current_entry) { browser->he_selection = entry; @@ -625,41 +727,30 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (row_offset == 0) { + struct hpp_arg arg = { + .b = &browser->b, + .folded_sign = folded_sign, + .current_entry = current_entry, + }; struct perf_hpp hpp = { .buf = s, .size = sizeof(s), + .ptr = &arg, }; ui_browser__gotorc(&browser->b, row, 0); - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - + perf_hpp__for_each_format(fmt) { if (!first) { slsmg_printf(" "); width -= 2; } first = false; - if (perf_hpp__format[i].color) { - hpp.ptr = &percent; - /* It will set percent for us. See HPP__COLOR_FN above. */ - width -= perf_hpp__format[i].color(&hpp, entry); - - ui_browser__set_percent_color(&browser->b, percent, current_entry); - - if (i == PERF_HPP__OVERHEAD && symbol_conf.use_callchain) { - slsmg_printf("%c ", folded_sign); - width -= 2; - } - - slsmg_printf("%s", s); - - if (!current_entry || !browser->b.navkeypressed) - ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL); + if (fmt->color) { + width -= fmt->color(&hpp, entry); } else { - width -= perf_hpp__format[i].entry(&hpp, entry); + width -= fmt->entry(&hpp, entry); slsmg_printf("%s", s); } } @@ -1098,6 +1189,21 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size, const struct thread *thread = hists->thread_filter; unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; u64 nr_events = hists->stats.total_period; + struct perf_evsel *evsel = hists_to_evsel(hists); + char buf[512]; + size_t buflen = sizeof(buf); + + if (symbol_conf.event_group && evsel->nr_members > 1) { + struct perf_evsel *pos; + + perf_evsel__group_desc(evsel, buf, buflen); + ev_name = buf; + + for_each_group_member(pos, evsel) { + nr_samples += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + nr_events += pos->hists.stats.total_period; + } + } nr_samples = convert_unit(nr_samples, &unit); printed = scnprintf(bf, size, @@ -1135,6 +1241,96 @@ static inline bool is_report_browser(void *timer) return timer == NULL; } +/* + * Only runtime switching of perf data file will make "input_name" point + * to a malloced buffer. So add "is_input_name_malloced" flag to decide + * whether we need to call free() for current "input_name" during the switch. + */ +static bool is_input_name_malloced = false; + +static int switch_data_file(void) +{ + char *pwd, *options[32], *abs_path[32], *tmp; + DIR *pwd_dir; + int nr_options = 0, choice = -1, ret = -1; + struct dirent *dent; + + pwd = getenv("PWD"); + if (!pwd) + return ret; + + pwd_dir = opendir(pwd); + if (!pwd_dir) + return ret; + + memset(options, 0, sizeof(options)); + memset(options, 0, sizeof(abs_path)); + + while ((dent = readdir(pwd_dir))) { + char path[PATH_MAX]; + u64 magic; + char *name = dent->d_name; + FILE *file; + + if (!(dent->d_type == DT_REG)) + continue; + + snprintf(path, sizeof(path), "%s/%s", pwd, name); + + file = fopen(path, "r"); + if (!file) + continue; + + if (fread(&magic, 1, 8, file) < 8) + goto close_file_and_continue; + + if (is_perf_magic(magic)) { + options[nr_options] = strdup(name); + if (!options[nr_options]) + goto close_file_and_continue; + + abs_path[nr_options] = strdup(path); + if (!abs_path[nr_options]) { + free(options[nr_options]); + ui__warning("Can't search all data files due to memory shortage.\n"); + fclose(file); + break; + } + + nr_options++; + } + +close_file_and_continue: + fclose(file); + if (nr_options >= 32) { + ui__warning("Too many perf data files in PWD!\n" + "Only the first 32 files will be listed.\n"); + break; + } + } + closedir(pwd_dir); + + if (nr_options) { + choice = ui__popup_menu(nr_options, options); + if (choice < nr_options && choice >= 0) { + tmp = strdup(abs_path[choice]); + if (tmp) { + if (is_input_name_malloced) + free((void *)input_name); + input_name = tmp; + is_input_name_malloced = true; + ret = 0; + } else + ui__warning("Data switch failed due to memory shortage!\n"); + } + } + + free_popup_options(options, nr_options); + free_popup_options(abs_path, nr_options); + return ret; +} + + static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, const char *helpline, const char *ev_name, bool left_exits, @@ -1169,7 +1365,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, int choice = 0, annotate = -2, zoom_dso = -2, zoom_thread = -2, annotate_f = -2, annotate_t = -2, browse_map = -2; - int scripts_comm = -2, scripts_symbol = -2, scripts_all = -2; + int scripts_comm = -2, scripts_symbol = -2, + scripts_all = -2, switch_data = -2; nr_options = 0; @@ -1226,6 +1423,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (is_report_browser(hbt)) goto do_scripts; continue; + case 's': + if (is_report_browser(hbt)) + goto do_data_switch; + continue; case K_F1: case 'h': case '?': @@ -1245,6 +1446,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "d Zoom into current DSO\n" "t Zoom into current Thread\n" "r Run available scripts('perf report' only)\n" + "s Switch to another data file in PWD ('perf report' only)\n" "P Print histograms to perf.hist.N\n" "V Verbose (DSO names in callchains, etc)\n" "/ Filter symbol by name"); @@ -1352,6 +1554,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, if (asprintf(&options[nr_options], "Run scripts for all samples") > 0) scripts_all = nr_options++; + if (is_report_browser(hbt) && asprintf(&options[nr_options], + "Switch to another data file in PWD") > 0) + switch_data = nr_options++; add_exit_option: options[nr_options++] = (char *)"Exit"; retry_popup_menu: @@ -1462,6 +1667,16 @@ do_scripts: script_browse(script_opt); } + /* Switch to another data file */ + else if (choice == switch_data) { +do_data_switch: + if (!switch_data_file()) { + key = K_SWITCH_INPUT_DATA; + break; + } else + ui__warning("Won't switch the data files due to\n" + "no valid data file get selected!\n"); + } } out_free_stack: pstack__delete(fstack); @@ -1494,6 +1709,16 @@ static void perf_evsel_menu__write(struct ui_browser *browser, ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : HE_COLORSET_NORMAL); + if (symbol_conf.event_group && evsel->nr_members > 1) { + struct perf_evsel *pos; + + ev_name = perf_evsel__group_name(evsel); + + for_each_group_member(pos, evsel) { + nr_events += pos->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + } + } + nr_events = convert_unit(nr_events, &unit); printed = scnprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events, unit, unit == ' ' ? "" : " ", ev_name); @@ -1578,6 +1803,7 @@ browse_hists: "Do you really want to exit?")) continue; /* Fall thru */ + case K_SWITCH_INPUT_DATA: case 'q': case CTRL('c'): goto out; @@ -1604,8 +1830,19 @@ out: return key; } +static bool filter_group_entries(struct ui_browser *self __maybe_unused, + void *entry) +{ + struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); + + if (symbol_conf.event_group && !perf_evsel__is_group_leader(evsel)) + return true; + + return false; +} + static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, - const char *help, + int nr_entries, const char *help, struct hist_browser_timer *hbt, struct perf_session_env *env) { @@ -1616,7 +1853,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, .refresh = ui_browser__list_head_refresh, .seek = ui_browser__list_head_seek, .write = perf_evsel_menu__write, - .nr_entries = evlist->nr_entries, + .filter = filter_group_entries, + .nr_entries = nr_entries, .priv = evlist, }, .env = env, @@ -1632,20 +1870,37 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, menu.b.width = line_len; } - return perf_evsel_menu__run(&menu, evlist->nr_entries, help, hbt); + return perf_evsel_menu__run(&menu, nr_entries, help, hbt); } int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct hist_browser_timer *hbt, struct perf_session_env *env) { - if (evlist->nr_entries == 1) { + int nr_entries = evlist->nr_entries; + +single_entry: + if (nr_entries == 1) { struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); const char *ev_name = perf_evsel__name(first); - return perf_evsel__hists_browse(first, evlist->nr_entries, help, + + return perf_evsel__hists_browse(first, nr_entries, help, ev_name, false, hbt, env); } - return __perf_evlist__tui_browse_hists(evlist, help, hbt, env); + if (symbol_conf.event_group) { + struct perf_evsel *pos; + + nr_entries = 0; + list_for_each_entry(pos, &evlist->entries, node) + if (perf_evsel__is_group_leader(pos)) + nr_entries++; + + if (nr_entries == 1) + goto single_entry; + } + + return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, + hbt, env); } diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c new file mode 100644 index 0000000..7d8dc58 --- /dev/null +++ b/tools/perf/ui/gtk/annotate.c @@ -0,0 +1,229 @@ +#include "gtk.h" +#include "util/debug.h" +#include "util/annotate.h" +#include "ui/helpline.h" + + +enum { + ANN_COL__PERCENT, + ANN_COL__OFFSET, + ANN_COL__LINE, + + MAX_ANN_COLS +}; + +static const char *const col_names[] = { + "Overhead", + "Offset", + "Line" +}; + +static int perf_gtk__get_percent(char *buf, size_t size, struct symbol *sym, + struct disasm_line *dl, int evidx) +{ + struct sym_hist *symhist; + double percent = 0.0; + const char *markup; + int ret = 0; + + strcpy(buf, ""); + + if (dl->offset == (s64) -1) + return 0; + + symhist = annotation__histogram(symbol__annotation(sym), evidx); + if (!symhist->addr[dl->offset]) + return 0; + + percent = 100.0 * symhist->addr[dl->offset] / symhist->sum; + + markup = perf_gtk__get_percent_color(percent); + if (markup) + ret += scnprintf(buf, size, "%s", markup); + ret += scnprintf(buf + ret, size - ret, "%6.2f%%", percent); + if (markup) + ret += scnprintf(buf + ret, size - ret, "</span>"); + + return ret; +} + +static int perf_gtk__get_offset(char *buf, size_t size, struct symbol *sym, + struct map *map, struct disasm_line *dl) +{ + u64 start = map__rip_2objdump(map, sym->start); + + strcpy(buf, ""); + + if (dl->offset == (s64) -1) + return 0; + + return scnprintf(buf, size, "%"PRIx64, start + dl->offset); +} + +static int perf_gtk__get_line(char *buf, size_t size, struct disasm_line *dl) +{ + int ret = 0; + char *line = g_markup_escape_text(dl->line, -1); + const char *markup = "<span fgcolor='gray'>"; + + strcpy(buf, ""); + + if (!line) + return 0; + + if (dl->offset != (s64) -1) + markup = NULL; + + if (markup) + ret += scnprintf(buf, size, "%s", markup); + ret += scnprintf(buf + ret, size - ret, "%s", line); + if (markup) + ret += scnprintf(buf + ret, size - ret, "</span>"); + + g_free(line); + return ret; +} + +static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym, + struct map *map, int evidx, + struct hist_browser_timer *hbt __maybe_unused) +{ + struct disasm_line *pos, *n; + struct annotation *notes; + GType col_types[MAX_ANN_COLS]; + GtkCellRenderer *renderer; + GtkListStore *store; + GtkWidget *view; + int i; + char s[512]; + + notes = symbol__annotation(sym); + + for (i = 0; i < MAX_ANN_COLS; i++) { + col_types[i] = G_TYPE_STRING; + } + store = gtk_list_store_newv(MAX_ANN_COLS, col_types); + + view = gtk_tree_view_new(); + renderer = gtk_cell_renderer_text_new(); + + for (i = 0; i < MAX_ANN_COLS; i++) { + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, col_names[i], renderer, "markup", + i, NULL); + } + + gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); + g_object_unref(GTK_TREE_MODEL(store)); + + list_for_each_entry(pos, ¬es->src->source, node) { + GtkTreeIter iter; + + gtk_list_store_append(store, &iter); + + if (perf_gtk__get_percent(s, sizeof(s), sym, pos, evidx)) + gtk_list_store_set(store, &iter, ANN_COL__PERCENT, s, -1); + if (perf_gtk__get_offset(s, sizeof(s), sym, map, pos)) + gtk_list_store_set(store, &iter, ANN_COL__OFFSET, s, -1); + if (perf_gtk__get_line(s, sizeof(s), pos)) + gtk_list_store_set(store, &iter, ANN_COL__LINE, s, -1); + } + + gtk_container_add(GTK_CONTAINER(window), view); + + list_for_each_entry_safe(pos, n, ¬es->src->source, node) { + list_del(&pos->node); + disasm_line__free(pos); + } + + return 0; +} + +int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx, + struct hist_browser_timer *hbt) +{ + GtkWidget *window; + GtkWidget *notebook; + GtkWidget *scrolled_window; + GtkWidget *tab_label; + + if (map->dso->annotate_warned) + return -1; + + if (symbol__annotate(sym, map, 0) < 0) { + ui__error("%s", ui_helpline__current); + return -1; + } + + if (perf_gtk__is_active_context(pgctx)) { + window = pgctx->main_window; + notebook = pgctx->notebook; + } else { + GtkWidget *vbox; + GtkWidget *infobar; + GtkWidget *statbar; + + signal(SIGSEGV, perf_gtk__signal); + signal(SIGFPE, perf_gtk__signal); + signal(SIGINT, perf_gtk__signal); + signal(SIGQUIT, perf_gtk__signal); + signal(SIGTERM, perf_gtk__signal); + + window = gtk_window_new(GTK_WINDOW_TOPLEVEL); + gtk_window_set_title(GTK_WINDOW(window), "perf annotate"); + + g_signal_connect(window, "delete_event", gtk_main_quit, NULL); + + pgctx = perf_gtk__activate_context(window); + if (!pgctx) + return -1; + + vbox = gtk_vbox_new(FALSE, 0); + notebook = gtk_notebook_new(); + pgctx->notebook = notebook; + + gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); + + infobar = perf_gtk__setup_info_bar(); + if (infobar) { + gtk_box_pack_start(GTK_BOX(vbox), infobar, + FALSE, FALSE, 0); + } + + statbar = perf_gtk__setup_statusbar(); + gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); + + gtk_container_add(GTK_CONTAINER(window), vbox); + } + + scrolled_window = gtk_scrolled_window_new(NULL, NULL); + tab_label = gtk_label_new(sym->name); + + gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window), + GTK_POLICY_AUTOMATIC, + GTK_POLICY_AUTOMATIC); + + gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, + tab_label); + + perf_gtk__annotate_symbol(scrolled_window, sym, map, evidx, hbt); + return 0; +} + +void perf_gtk__show_annotations(void) +{ + GtkWidget *window; + + if (!perf_gtk__is_active_context(pgctx)) + return; + + window = pgctx->main_window; + gtk_widget_show_all(window); + + perf_gtk__resize_window(window); + gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); + + gtk_main(); + + perf_gtk__deactivate_context(&pgctx); +} diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 253b621..c95012c 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -8,15 +8,13 @@ #include <signal.h> -#define MAX_COLUMNS 32 - -static void perf_gtk__signal(int sig) +void perf_gtk__signal(int sig) { perf_gtk__exit(false); psignal(sig, "perf"); } -static void perf_gtk__resize_window(GtkWidget *window) +void perf_gtk__resize_window(GtkWidget *window) { GdkRectangle rect; GdkScreen *screen; @@ -36,7 +34,7 @@ static void perf_gtk__resize_window(GtkWidget *window) gtk_window_resize(GTK_WINDOW(window), width, height); } -static const char *perf_gtk__get_percent_color(double percent) +const char *perf_gtk__get_percent_color(double percent) { if (percent >= MIN_RED) return "<span fgcolor='red'>"; @@ -45,155 +43,8 @@ static const char *perf_gtk__get_percent_color(double percent) return NULL; } -#define HPP__COLOR_FN(_name, _field) \ -static int perf_gtk__hpp_color_ ## _name(struct perf_hpp *hpp, \ - struct hist_entry *he) \ -{ \ - struct hists *hists = he->hists; \ - double percent = 100.0 * he->stat._field / hists->stats.total_period; \ - const char *markup; \ - int ret = 0; \ - \ - markup = perf_gtk__get_percent_color(percent); \ - if (markup) \ - ret += scnprintf(hpp->buf, hpp->size, "%s", markup); \ - ret += scnprintf(hpp->buf + ret, hpp->size - ret, "%6.2f%%", percent); \ - if (markup) \ - ret += scnprintf(hpp->buf + ret, hpp->size - ret, "</span>"); \ - \ - return ret; \ -} - -HPP__COLOR_FN(overhead, period) -HPP__COLOR_FN(overhead_sys, period_sys) -HPP__COLOR_FN(overhead_us, period_us) -HPP__COLOR_FN(overhead_guest_sys, period_guest_sys) -HPP__COLOR_FN(overhead_guest_us, period_guest_us) - -#undef HPP__COLOR_FN - -void perf_gtk__init_hpp(void) -{ - perf_hpp__init(); - - perf_hpp__format[PERF_HPP__OVERHEAD].color = - perf_gtk__hpp_color_overhead; - perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = - perf_gtk__hpp_color_overhead_sys; - perf_hpp__format[PERF_HPP__OVERHEAD_US].color = - perf_gtk__hpp_color_overhead_us; - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color = - perf_gtk__hpp_color_overhead_guest_sys; - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color = - perf_gtk__hpp_color_overhead_guest_us; -} - -static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) -{ - GType col_types[MAX_COLUMNS]; - GtkCellRenderer *renderer; - struct sort_entry *se; - GtkListStore *store; - struct rb_node *nd; - GtkWidget *view; - int i, col_idx; - int nr_cols; - char s[512]; - - struct perf_hpp hpp = { - .buf = s, - .size = sizeof(s), - }; - - nr_cols = 0; - - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - - col_types[nr_cols++] = G_TYPE_STRING; - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - col_types[nr_cols++] = G_TYPE_STRING; - } - - store = gtk_list_store_newv(nr_cols, col_types); - - view = gtk_tree_view_new(); - - renderer = gtk_cell_renderer_text_new(); - - col_idx = 0; - - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - - perf_hpp__format[i].header(&hpp); - - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, s, - renderer, "markup", - col_idx++, NULL); - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), - -1, se->se_header, - renderer, "text", - col_idx++, NULL); - } - - gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); - - g_object_unref(GTK_TREE_MODEL(store)); - - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - GtkTreeIter iter; - - if (h->filtered) - continue; - - gtk_list_store_append(store, &iter); - - col_idx = 0; - - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - - if (perf_hpp__format[i].color) - perf_hpp__format[i].color(&hpp, h); - else - perf_hpp__format[i].entry(&hpp, h); - - gtk_list_store_set(store, &iter, col_idx++, s, -1); - } - - list_for_each_entry(se, &hist_entry__sort_list, list) { - if (se->elide) - continue; - - se->se_snprintf(h, s, ARRAY_SIZE(s), - hists__col_len(hists, se->se_width_idx)); - - gtk_list_store_set(store, &iter, col_idx++, s, -1); - } - } - - gtk_container_add(GTK_CONTAINER(window), view); -} - #ifdef HAVE_GTK_INFO_BAR -static GtkWidget *perf_gtk__setup_info_bar(void) +GtkWidget *perf_gtk__setup_info_bar(void) { GtkWidget *info_bar; GtkWidget *label; @@ -220,7 +71,7 @@ static GtkWidget *perf_gtk__setup_info_bar(void) } #endif -static GtkWidget *perf_gtk__setup_statusbar(void) +GtkWidget *perf_gtk__setup_statusbar(void) { GtkWidget *stbar; unsigned ctxid; @@ -234,79 +85,3 @@ static GtkWidget *perf_gtk__setup_statusbar(void) return stbar; } - -int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, - const char *help, - struct hist_browser_timer *hbt __maybe_unused) -{ - struct perf_evsel *pos; - GtkWidget *vbox; - GtkWidget *notebook; - GtkWidget *info_bar; - GtkWidget *statbar; - GtkWidget *window; - - signal(SIGSEGV, perf_gtk__signal); - signal(SIGFPE, perf_gtk__signal); - signal(SIGINT, perf_gtk__signal); - signal(SIGQUIT, perf_gtk__signal); - signal(SIGTERM, perf_gtk__signal); - - window = gtk_window_new(GTK_WINDOW_TOPLEVEL); - - gtk_window_set_title(GTK_WINDOW(window), "perf report"); - - g_signal_connect(window, "delete_event", gtk_main_quit, NULL); - - pgctx = perf_gtk__activate_context(window); - if (!pgctx) - return -1; - - vbox = gtk_vbox_new(FALSE, 0); - - notebook = gtk_notebook_new(); - - list_for_each_entry(pos, &evlist->entries, node) { - struct hists *hists = &pos->hists; - const char *evname = perf_evsel__name(pos); - GtkWidget *scrolled_window; - GtkWidget *tab_label; - - scrolled_window = gtk_scrolled_window_new(NULL, NULL); - - gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window), - GTK_POLICY_AUTOMATIC, - GTK_POLICY_AUTOMATIC); - - perf_gtk__show_hists(scrolled_window, hists); - - tab_label = gtk_label_new(evname); - - gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); - } - - gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); - - info_bar = perf_gtk__setup_info_bar(); - if (info_bar) - gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0); - - statbar = perf_gtk__setup_statusbar(); - gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); - - gtk_container_add(GTK_CONTAINER(window), vbox); - - gtk_widget_show_all(window); - - perf_gtk__resize_window(window); - - gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); - - ui_helpline__push(help); - - gtk_main(); - - perf_gtk__deactivate_context(&pgctx); - - return 0; -} diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 856320e..3d96785 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -10,6 +10,7 @@ struct perf_gtk_context { GtkWidget *main_window; + GtkWidget *notebook; #ifdef HAVE_GTK_INFO_BAR GtkWidget *info_bar; @@ -33,7 +34,14 @@ void perf_gtk__init_helpline(void); void perf_gtk__init_progress(void); void perf_gtk__init_hpp(void); -#ifndef HAVE_GTK_INFO_BAR +void perf_gtk__signal(int sig); +void perf_gtk__resize_window(GtkWidget *window); +const char *perf_gtk__get_percent_color(double percent); +GtkWidget *perf_gtk__setup_statusbar(void); + +#ifdef HAVE_GTK_INFO_BAR +GtkWidget *perf_gtk__setup_info_bar(void); +#else static inline GtkWidget *perf_gtk__setup_info_bar(void) { return NULL; diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c index 5db4432..3388cbd 100644 --- a/tools/perf/ui/gtk/helpline.c +++ b/tools/perf/ui/gtk/helpline.c @@ -24,17 +24,7 @@ static void gtk_helpline_push(const char *msg) pgctx->statbar_ctx_id, msg); } -static struct ui_helpline gtk_helpline_fns = { - .pop = gtk_helpline_pop, - .push = gtk_helpline_push, -}; - -void perf_gtk__init_helpline(void) -{ - helpline_fns = >k_helpline_fns; -} - -int perf_gtk__show_helpline(const char *fmt, va_list ap) +static int gtk_helpline_show(const char *fmt, va_list ap) { int ret; char *ptr; @@ -54,3 +44,14 @@ int perf_gtk__show_helpline(const char *fmt, va_list ap) return ret; } + +static struct ui_helpline gtk_helpline_fns = { + .pop = gtk_helpline_pop, + .push = gtk_helpline_push, + .show = gtk_helpline_show, +}; + +void perf_gtk__init_helpline(void) +{ + helpline_fns = >k_helpline_fns; +} diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c new file mode 100644 index 0000000..1e764a8 --- /dev/null +++ b/tools/perf/ui/gtk/hists.c @@ -0,0 +1,312 @@ +#include "../evlist.h" +#include "../cache.h" +#include "../evsel.h" +#include "../sort.h" +#include "../hist.h" +#include "../helpline.h" +#include "gtk.h" + +#define MAX_COLUMNS 32 + +static int __percent_color_snprintf(char *buf, size_t size, double percent) +{ + int ret = 0; + const char *markup; + + markup = perf_gtk__get_percent_color(percent); + if (markup) + ret += scnprintf(buf, size, markup); + + ret += scnprintf(buf + ret, size - ret, " %6.2f%%", percent); + + if (markup) + ret += scnprintf(buf + ret, size - ret, "</span>"); + + return ret; +} + + +static int __hpp__color_fmt(struct perf_hpp *hpp, struct hist_entry *he, + u64 (*get_field)(struct hist_entry *)) +{ + int ret; + double percent = 0.0; + struct hists *hists = he->hists; + + if (hists->stats.total_period) + percent = 100.0 * get_field(he) / hists->stats.total_period; + + ret = __percent_color_snprintf(hpp->buf, hpp->size, percent); + + if (symbol_conf.event_group) { + int prev_idx, idx_delta; + struct perf_evsel *evsel = hists_to_evsel(hists); + struct hist_entry *pair; + int nr_members = evsel->nr_members; + + if (nr_members <= 1) + return ret; + + prev_idx = perf_evsel__group_idx(evsel); + + list_for_each_entry(pair, &he->pairs.head, pairs.node) { + u64 period = get_field(pair); + u64 total = pair->hists->stats.total_period; + + evsel = hists_to_evsel(pair->hists); + idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members in the middle which + * have no sample + */ + ret += __percent_color_snprintf(hpp->buf + ret, + hpp->size - ret, + 0.0); + } + + percent = 100.0 * period / total; + ret += __percent_color_snprintf(hpp->buf + ret, + hpp->size - ret, + percent); + + prev_idx = perf_evsel__group_idx(evsel); + } + + idx_delta = nr_members - prev_idx - 1; + + while (idx_delta--) { + /* + * zero-fill group members at last which have no sample + */ + ret += __percent_color_snprintf(hpp->buf + ret, + hpp->size - ret, + 0.0); + } + } + return ret; +} + +#define __HPP_COLOR_PERCENT_FN(_type, _field) \ +static u64 he_get_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp, \ + struct hist_entry *he) \ +{ \ + return __hpp__color_fmt(hpp, he, he_get_##_field); \ +} + +__HPP_COLOR_PERCENT_FN(overhead, period) +__HPP_COLOR_PERCENT_FN(overhead_sys, period_sys) +__HPP_COLOR_PERCENT_FN(overhead_us, period_us) +__HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys) +__HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us) + +#undef __HPP_COLOR_PERCENT_FN + + +void perf_gtk__init_hpp(void) +{ + perf_hpp__column_enable(PERF_HPP__OVERHEAD); + + perf_hpp__init(); + + perf_hpp__format[PERF_HPP__OVERHEAD].color = + perf_gtk__hpp_color_overhead; + perf_hpp__format[PERF_HPP__OVERHEAD_SYS].color = + perf_gtk__hpp_color_overhead_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_US].color = + perf_gtk__hpp_color_overhead_us; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].color = + perf_gtk__hpp_color_overhead_guest_sys; + perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color = + perf_gtk__hpp_color_overhead_guest_us; +} + +static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) +{ + struct perf_hpp_fmt *fmt; + GType col_types[MAX_COLUMNS]; + GtkCellRenderer *renderer; + struct sort_entry *se; + GtkListStore *store; + struct rb_node *nd; + GtkWidget *view; + int col_idx; + int nr_cols; + char s[512]; + + struct perf_hpp hpp = { + .buf = s, + .size = sizeof(s), + .ptr = hists_to_evsel(hists), + }; + + nr_cols = 0; + + perf_hpp__for_each_format(fmt) + col_types[nr_cols++] = G_TYPE_STRING; + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + col_types[nr_cols++] = G_TYPE_STRING; + } + + store = gtk_list_store_newv(nr_cols, col_types); + + view = gtk_tree_view_new(); + + renderer = gtk_cell_renderer_text_new(); + + col_idx = 0; + + perf_hpp__for_each_format(fmt) { + fmt->header(&hpp); + + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, ltrim(s), + renderer, "markup", + col_idx++, NULL); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view), + -1, se->se_header, + renderer, "text", + col_idx++, NULL); + } + + gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store)); + + g_object_unref(GTK_TREE_MODEL(store)); + + for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + GtkTreeIter iter; + + if (h->filtered) + continue; + + gtk_list_store_append(store, &iter); + + col_idx = 0; + + perf_hpp__for_each_format(fmt) { + if (fmt->color) + fmt->color(&hpp, h); + else + fmt->entry(&hpp, h); + + gtk_list_store_set(store, &iter, col_idx++, s, -1); + } + + list_for_each_entry(se, &hist_entry__sort_list, list) { + if (se->elide) + continue; + + se->se_snprintf(h, s, ARRAY_SIZE(s), + hists__col_len(hists, se->se_width_idx)); + + gtk_list_store_set(store, &iter, col_idx++, s, -1); + } + } + + gtk_container_add(GTK_CONTAINER(window), view); +} + +int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, + const char *help, + struct hist_browser_timer *hbt __maybe_unused) +{ + struct perf_evsel *pos; + GtkWidget *vbox; + GtkWidget *notebook; + GtkWidget *info_bar; + GtkWidget *statbar; + GtkWidget *window; + + signal(SIGSEGV, perf_gtk__signal); + signal(SIGFPE, perf_gtk__signal); + signal(SIGINT, perf_gtk__signal); + signal(SIGQUIT, perf_gtk__signal); + signal(SIGTERM, perf_gtk__signal); + + window = gtk_window_new(GTK_WINDOW_TOPLEVEL); + + gtk_window_set_title(GTK_WINDOW(window), "perf report"); + + g_signal_connect(window, "delete_event", gtk_main_quit, NULL); + + pgctx = perf_gtk__activate_context(window); + if (!pgctx) + return -1; + + vbox = gtk_vbox_new(FALSE, 0); + + notebook = gtk_notebook_new(); + + gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); + + info_bar = perf_gtk__setup_info_bar(); + if (info_bar) + gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0); + + statbar = perf_gtk__setup_statusbar(); + gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); + + gtk_container_add(GTK_CONTAINER(window), vbox); + + list_for_each_entry(pos, &evlist->entries, node) { + struct hists *hists = &pos->hists; + const char *evname = perf_evsel__name(pos); + GtkWidget *scrolled_window; + GtkWidget *tab_label; + char buf[512]; + size_t size = sizeof(buf); + + if (symbol_conf.event_group) { + if (!perf_evsel__is_group_leader(pos)) + continue; + + if (pos->nr_members > 1) { + perf_evsel__group_desc(pos, buf, size); + evname = buf; + } + } + + scrolled_window = gtk_scrolled_window_new(NULL, NULL); + + gtk_scrolled_window_set_policy(GTK_SCROLLED_WINDOW(scrolled_window), + GTK_POLICY_AUTOMATIC, + GTK_POLICY_AUTOMATIC); + + perf_gtk__show_hists(scrolled_window, hists); + + tab_label = gtk_label_new(evname); + + gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); + } + + gtk_widget_show_all(window); + + perf_gtk__resize_window(window); + + gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); + + ui_helpline__push(help); + + gtk_main(); + + perf_gtk__deactivate_context(&pgctx); + + return 0; +} diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c index a49bcf3..700fb3c 100644 --- a/tools/perf/ui/helpline.c +++ b/tools/perf/ui/helpline.c @@ -16,9 +16,16 @@ static void nop_helpline__push(const char *msg __maybe_unused) { } +static int nop_helpline__show(const char *fmt __maybe_unused, + va_list ap __maybe_unused) +{ + return 0; +} + static struct ui_helpline default_helpline_fns = { .pop = nop_helpline__pop, .push = nop_helpline__push, + .show = nop_helpline__show, }; struct ui_helpline *helpline_fns = &default_helpline_fns; @@ -59,3 +66,8 @@ void ui_helpline__puts(const char *msg) ui_helpline__pop(); ui_helpline__push(msg); } + +int ui_helpline__vshow(const char *fmt, va_list ap) +{ + return helpline_fns->show(fmt, ap); +} diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h index baa28a4..46181f4 100644 --- a/tools/perf/ui/helpline.h +++ b/tools/perf/ui/helpline.h @@ -9,6 +9,7 @@ struct ui_helpline { void (*pop)(void); void (*push)(const char *msg); + int (*show)(const char *fmt, va_list ap); }; extern struct ui_helpline *helpline_fns; @@ -20,28 +21,9 @@ void ui_helpline__push(const char *msg); void ui_helpline__vpush(const char *fmt, va_list ap); void ui_helpline__fpush(const char *fmt, ...); void ui_helpline__puts(const char *msg); +int ui_helpline__vshow(const char *fmt, va_list ap); extern char ui_helpline__current[512]; - -#ifdef NEWT_SUPPORT extern char ui_helpline__last_msg[]; -int ui_helpline__show_help(const char *format, va_list ap); -#else -static inline int ui_helpline__show_help(const char *format __maybe_unused, - va_list ap __maybe_unused) -{ - return 0; -} -#endif /* NEWT_SUPPORT */ - -#ifdef GTK2_SUPPORT -int perf_gtk__show_helpline(const char *format, va_list ap); -#else -static inline int perf_gtk__show_helpline(const char *format __maybe_unused, - va_list ap __maybe_unused) -{ - return 0; -} -#endif /* GTK2_SUPPORT */ #endif /* _PERF_UI_HELPLINE_H_ */ diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index aa84130..d671e63 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -3,151 +3,163 @@ #include "../util/hist.h" #include "../util/util.h" #include "../util/sort.h" - +#include "../util/evsel.h" /* hist period print (hpp) functions */ -static int hpp__header_overhead(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "Overhead"); -} - -static int hpp__width_overhead(struct perf_hpp *hpp __maybe_unused) -{ - return 8; -} - -static int hpp__color_overhead(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period / hists->stats.total_period; - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); -} +typedef int (*hpp_snprint_fn)(char *buf, size_t size, const char *fmt, ...); -static int hpp__entry_overhead(struct perf_hpp *hpp, struct hist_entry *he) +static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he, + u64 (*get_field)(struct hist_entry *), + const char *fmt, hpp_snprint_fn print_fn, + bool fmt_percent) { + int ret; struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%"; - - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} -static int hpp__header_overhead_sys(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "sys"); -} + if (fmt_percent) { + double percent = 0.0; -static int hpp__width_overhead_sys(struct perf_hpp *hpp __maybe_unused) -{ - return 7; -} + if (hists->stats.total_period) + percent = 100.0 * get_field(he) / + hists->stats.total_period; -static int hpp__color_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_sys / hists->stats.total_period; + ret = print_fn(hpp->buf, hpp->size, fmt, percent); + } else + ret = print_fn(hpp->buf, hpp->size, fmt, get_field(he)); - return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); -} + if (symbol_conf.event_group) { + int prev_idx, idx_delta; + struct perf_evsel *evsel = hists_to_evsel(hists); + struct hist_entry *pair; + int nr_members = evsel->nr_members; -static int hpp__entry_overhead_sys(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_sys / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; + if (nr_members <= 1) + return ret; - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} + prev_idx = perf_evsel__group_idx(evsel); -static int hpp__header_overhead_us(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; + list_for_each_entry(pair, &he->pairs.head, pairs.node) { + u64 period = get_field(pair); + u64 total = pair->hists->stats.total_period; - return scnprintf(hpp->buf, hpp->size, fmt, "user"); -} + if (!total) + continue; -static int hpp__width_overhead_us(struct perf_hpp *hpp __maybe_unused) -{ - return 7; -} + evsel = hists_to_evsel(pair->hists); + idx_delta = perf_evsel__group_idx(evsel) - prev_idx - 1; -static int hpp__color_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_us / hists->stats.total_period; + while (idx_delta--) { + /* + * zero-fill group members in the middle which + * have no sample + */ + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, 0); + } - return percent_color_snprintf(hpp->buf, hpp->size, "%6.2f%%", percent); -} + if (fmt_percent) + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, 100.0 * period / total); + else + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, period); -static int hpp__entry_overhead_us(struct perf_hpp *hpp, struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_us / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : "%6.2f%%"; - - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} - -static int hpp__header_overhead_guest_sys(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "guest sys"); -} - -static int hpp__width_overhead_guest_sys(struct perf_hpp *hpp __maybe_unused) -{ - return 9; -} - -static int hpp__color_overhead_guest_sys(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period; - - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); -} - -static int hpp__entry_overhead_guest_sys(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_sys / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; - - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} - -static int hpp__header_overhead_guest_us(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "guest usr"); -} + prev_idx = perf_evsel__group_idx(evsel); + } -static int hpp__width_overhead_guest_us(struct perf_hpp *hpp __maybe_unused) -{ - return 9; -} + idx_delta = nr_members - prev_idx - 1; -static int hpp__color_overhead_guest_us(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period; - - return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%% ", percent); + while (idx_delta--) { + /* + * zero-fill group members at last which have no sample + */ + ret += print_fn(hpp->buf + ret, hpp->size - ret, + fmt, 0); + } + } + return ret; } -static int hpp__entry_overhead_guest_us(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hists *hists = he->hists; - double percent = 100.0 * he->stat.period_guest_us / hists->stats.total_period; - const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%% "; +#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +static int hpp__header_##_type(struct perf_hpp *hpp) \ +{ \ + int len = _min_width; \ + \ + if (symbol_conf.event_group) { \ + struct perf_evsel *evsel = hpp->ptr; \ + \ + len = max(len, evsel->nr_members * _unit_width); \ + } \ + return scnprintf(hpp->buf, hpp->size, "%*s", len, _str); \ +} + +#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused) \ +{ \ + int len = _min_width; \ + \ + if (symbol_conf.event_group) { \ + struct perf_evsel *evsel = hpp->ptr; \ + \ + len = max(len, evsel->nr_members * _unit_width); \ + } \ + return len; \ +} + +#define __HPP_COLOR_PERCENT_FN(_type, _field) \ +static u64 he_get_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ + (hpp_snprint_fn)percent_color_snprintf, true); \ +} + +#define __HPP_ENTRY_PERCENT_FN(_type, _field) \ +static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ + return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ + scnprintf, true); \ +} + +#define __HPP_ENTRY_RAW_FN(_type, _field) \ +static u64 he_get_raw_##_field(struct hist_entry *he) \ +{ \ + return he->stat._field; \ +} \ + \ +static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ +{ \ + const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64; \ + return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ +} + +#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width) \ +__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +__HPP_COLOR_PERCENT_FN(_type, _field) \ +__HPP_ENTRY_PERCENT_FN(_type, _field) + +#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width) \ +__HPP_HEADER_FN(_type, _str, _min_width, _unit_width) \ +__HPP_WIDTH_FN(_type, _min_width, _unit_width) \ +__HPP_ENTRY_RAW_FN(_type, _field) + + +HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8) +HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8) +HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8) +HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8) +HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8) + +HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12) +HPP_RAW_FNS(period, "Period", period, 12, 12) - return scnprintf(hpp->buf, hpp->size, fmt, percent); -} static int hpp__header_baseline(struct perf_hpp *hpp) { @@ -179,7 +191,7 @@ static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he) { double percent = baseline_percent(he); - if (hist_entry__has_pairs(he)) + if (hist_entry__has_pairs(he) || symbol_conf.field_sep) return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent); else return scnprintf(hpp->buf, hpp->size, " "); @@ -196,44 +208,6 @@ static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he) return scnprintf(hpp->buf, hpp->size, " "); } -static int hpp__header_samples(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%11s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Samples"); -} - -static int hpp__width_samples(struct perf_hpp *hpp __maybe_unused) -{ - return 11; -} - -static int hpp__entry_samples(struct perf_hpp *hpp, struct hist_entry *he) -{ - const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%11" PRIu64; - - return scnprintf(hpp->buf, hpp->size, fmt, he->stat.nr_events); -} - -static int hpp__header_period(struct perf_hpp *hpp) -{ - const char *fmt = symbol_conf.field_sep ? "%s" : "%12s"; - - return scnprintf(hpp->buf, hpp->size, fmt, "Period"); -} - -static int hpp__width_period(struct perf_hpp *hpp __maybe_unused) -{ - return 12; -} - -static int hpp__entry_period(struct perf_hpp *hpp, struct hist_entry *he) -{ - const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64; - - return scnprintf(hpp->buf, hpp->size, fmt, he->stat.period); -} - static int hpp__header_period_baseline(struct perf_hpp *hpp) { const char *fmt = symbol_conf.field_sep ? "%s" : "%12s"; @@ -254,6 +228,7 @@ static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *h return scnprintf(hpp->buf, hpp->size, fmt, period); } + static int hpp__header_delta(struct perf_hpp *hpp) { const char *fmt = symbol_conf.field_sep ? "%s" : "%7s"; @@ -268,14 +243,18 @@ static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused) static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he) { + struct hist_entry *pair = hist_entry__next_pair(he); const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s"; char buf[32] = " "; - double diff; + double diff = 0.0; - if (he->diff.computed) - diff = he->diff.period_ratio_delta; - else - diff = perf_diff__compute_delta(he); + if (pair) { + if (he->diff.computed) + diff = he->diff.period_ratio_delta; + else + diff = perf_diff__compute_delta(he, pair); + } else + diff = perf_diff__period_percent(he, he->stat.period); if (fabs(diff) >= 0.01) scnprintf(buf, sizeof(buf), "%+4.2F%%", diff); @@ -297,14 +276,17 @@ static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused) static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he) { + struct hist_entry *pair = hist_entry__next_pair(he); const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; char buf[32] = " "; - double ratio; + double ratio = 0.0; - if (he->diff.computed) - ratio = he->diff.period_ratio; - else - ratio = perf_diff__compute_ratio(he); + if (pair) { + if (he->diff.computed) + ratio = he->diff.period_ratio; + else + ratio = perf_diff__compute_ratio(he, pair); + } if (ratio > 0.0) scnprintf(buf, sizeof(buf), "%+14.6F", ratio); @@ -326,14 +308,17 @@ static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused) static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he) { + struct hist_entry *pair = hist_entry__next_pair(he); const char *fmt = symbol_conf.field_sep ? "%s" : "%14s"; char buf[32] = " "; - s64 wdiff; + s64 wdiff = 0; - if (he->diff.computed) - wdiff = he->diff.wdiff; - else - wdiff = perf_diff__compute_wdiff(he); + if (pair) { + if (he->diff.computed) + wdiff = he->diff.wdiff; + else + wdiff = perf_diff__compute_wdiff(he, pair); + } if (wdiff != 0) scnprintf(buf, sizeof(buf), "%14ld", wdiff); @@ -341,30 +326,6 @@ static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he) return scnprintf(hpp->buf, hpp->size, fmt, buf); } -static int hpp__header_displ(struct perf_hpp *hpp) -{ - return scnprintf(hpp->buf, hpp->size, "Displ."); -} - -static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused) -{ - return 6; -} - -static int hpp__entry_displ(struct perf_hpp *hpp, - struct hist_entry *he) -{ - struct hist_entry *pair = hist_entry__next_pair(he); - long displacement = pair ? pair->position - he->position : 0; - const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s"; - char buf[32] = " "; - - if (displacement) - scnprintf(buf, sizeof(buf), "%+4ld", displacement); - - return scnprintf(hpp->buf, hpp->size, fmt, buf); -} - static int hpp__header_formula(struct perf_hpp *hpp) { const char *fmt = symbol_conf.field_sep ? "%s" : "%70s"; @@ -379,67 +340,91 @@ static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused) static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he) { + struct hist_entry *pair = hist_entry__next_pair(he); const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s"; char buf[96] = " "; - perf_diff__formula(buf, sizeof(buf), he); + if (pair) + perf_diff__formula(he, pair, buf, sizeof(buf)); + return scnprintf(hpp->buf, hpp->size, fmt, buf); } -#define HPP__COLOR_PRINT_FNS(_name) \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .color = hpp__color_ ## _name, \ - .entry = hpp__entry_ ## _name +#define HPP__COLOR_PRINT_FNS(_name) \ + { \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .color = hpp__color_ ## _name, \ + .entry = hpp__entry_ ## _name \ + } -#define HPP__PRINT_FNS(_name) \ - .header = hpp__header_ ## _name, \ - .width = hpp__width_ ## _name, \ - .entry = hpp__entry_ ## _name +#define HPP__PRINT_FNS(_name) \ + { \ + .header = hpp__header_ ## _name, \ + .width = hpp__width_ ## _name, \ + .entry = hpp__entry_ ## _name \ + } struct perf_hpp_fmt perf_hpp__format[] = { - { .cond = false, HPP__COLOR_PRINT_FNS(baseline) }, - { .cond = true, HPP__COLOR_PRINT_FNS(overhead) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_sys) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_us) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_sys) }, - { .cond = false, HPP__COLOR_PRINT_FNS(overhead_guest_us) }, - { .cond = false, HPP__PRINT_FNS(samples) }, - { .cond = false, HPP__PRINT_FNS(period) }, - { .cond = false, HPP__PRINT_FNS(period_baseline) }, - { .cond = false, HPP__PRINT_FNS(delta) }, - { .cond = false, HPP__PRINT_FNS(ratio) }, - { .cond = false, HPP__PRINT_FNS(wdiff) }, - { .cond = false, HPP__PRINT_FNS(displ) }, - { .cond = false, HPP__PRINT_FNS(formula) } + HPP__COLOR_PRINT_FNS(baseline), + HPP__COLOR_PRINT_FNS(overhead), + HPP__COLOR_PRINT_FNS(overhead_sys), + HPP__COLOR_PRINT_FNS(overhead_us), + HPP__COLOR_PRINT_FNS(overhead_guest_sys), + HPP__COLOR_PRINT_FNS(overhead_guest_us), + HPP__PRINT_FNS(samples), + HPP__PRINT_FNS(period), + HPP__PRINT_FNS(period_baseline), + HPP__PRINT_FNS(delta), + HPP__PRINT_FNS(ratio), + HPP__PRINT_FNS(wdiff), + HPP__PRINT_FNS(formula) }; +LIST_HEAD(perf_hpp__list); + + #undef HPP__COLOR_PRINT_FNS #undef HPP__PRINT_FNS +#undef HPP_PERCENT_FNS +#undef HPP_RAW_FNS + +#undef __HPP_HEADER_FN +#undef __HPP_WIDTH_FN +#undef __HPP_COLOR_PERCENT_FN +#undef __HPP_ENTRY_PERCENT_FN +#undef __HPP_ENTRY_RAW_FN + + void perf_hpp__init(void) { if (symbol_conf.show_cpu_utilization) { - perf_hpp__format[PERF_HPP__OVERHEAD_SYS].cond = true; - perf_hpp__format[PERF_HPP__OVERHEAD_US].cond = true; + perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS); + perf_hpp__column_enable(PERF_HPP__OVERHEAD_US); if (perf_guest) { - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_SYS].cond = true; - perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].cond = true; + perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_SYS); + perf_hpp__column_enable(PERF_HPP__OVERHEAD_GUEST_US); } } if (symbol_conf.show_nr_samples) - perf_hpp__format[PERF_HPP__SAMPLES].cond = true; + perf_hpp__column_enable(PERF_HPP__SAMPLES); if (symbol_conf.show_total_period) - perf_hpp__format[PERF_HPP__PERIOD].cond = true; + perf_hpp__column_enable(PERF_HPP__PERIOD); +} + +void perf_hpp__column_register(struct perf_hpp_fmt *format) +{ + list_add_tail(&format->list, &perf_hpp__list); } -void perf_hpp__column_enable(unsigned col, bool enable) +void perf_hpp__column_enable(unsigned col) { BUG_ON(col >= PERF_HPP__MAX_INDEX); - perf_hpp__format[col].cond = enable; + perf_hpp__column_register(&perf_hpp__format[col]); } static inline void advance_hpp(struct perf_hpp *hpp, int inc) @@ -452,27 +437,29 @@ int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, bool color) { const char *sep = symbol_conf.field_sep; + struct perf_hpp_fmt *fmt; char *start = hpp->buf; - int i, ret; + int ret; bool first = true; if (symbol_conf.exclude_other && !he->parent) return 0; - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; - + perf_hpp__for_each_format(fmt) { + /* + * If there's no field_sep, we still need + * to display initial ' '. + */ if (!sep || !first) { ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " "); advance_hpp(hpp, ret); + } else first = false; - } - if (color && perf_hpp__format[i].color) - ret = perf_hpp__format[i].color(hpp, he); + if (color && fmt->color) + ret = fmt->color(hpp, he); else - ret = perf_hpp__format[i].entry(hpp, he); + ret = fmt->entry(hpp, he); advance_hpp(hpp, ret); } @@ -504,16 +491,18 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size, */ unsigned int hists__sort_list_width(struct hists *hists) { + struct perf_hpp_fmt *fmt; struct sort_entry *se; - int i, ret = 0; + int i = 0, ret = 0; + struct perf_hpp dummy_hpp = { + .ptr = hists_to_evsel(hists), + }; - for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { - if (!perf_hpp__format[i].cond) - continue; + perf_hpp__for_each_format(fmt) { if (i) ret += 2; - ret += perf_hpp__format[i].width(NULL); + ret += fmt->width(&dummy_hpp); } list_for_each_entry(se, &hist_entry__sort_list, list) diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h index 809eca5..65092d5 100644 --- a/tools/perf/ui/keysyms.h +++ b/tools/perf/ui/keysyms.h @@ -23,5 +23,6 @@ #define K_TIMER -1 #define K_ERROR -2 #define K_RESIZE -3 +#define K_SWITCH_INPUT_DATA -4 #endif /* _PERF_KEYSYMS_H_ */ diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index ebb4cc1..ae6a789 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -8,7 +8,7 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void setup_browser(bool fallback_to_pager) { - if (!isatty(1) || dump_trace) + if (use_browser < 2 && (!isatty(1) || dump_trace)) use_browser = 0; /* default to TUI */ @@ -30,6 +30,7 @@ void setup_browser(bool fallback_to_pager) if (fallback_to_pager) setup_pager(); + perf_hpp__column_enable(PERF_HPP__OVERHEAD); perf_hpp__init(); break; } diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index f0ee204..ff1f60c 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -3,6 +3,7 @@ #include "../../util/util.h" #include "../../util/hist.h" #include "../../util/sort.h" +#include "../../util/evsel.h" static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) @@ -335,17 +336,19 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, FILE *fp) { + struct perf_hpp_fmt *fmt; struct sort_entry *se; struct rb_node *nd; size_t ret = 0; unsigned int width; const char *sep = symbol_conf.field_sep; const char *col_width = symbol_conf.col_width_list_str; - int idx, nr_rows = 0; + int nr_rows = 0; char bf[96]; struct perf_hpp dummy_hpp = { .buf = bf, .size = sizeof(bf), + .ptr = hists_to_evsel(hists), }; bool first = true; @@ -355,16 +358,14 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, goto print_entries; fprintf(fp, "# "); - for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { - if (!perf_hpp__format[idx].cond) - continue; + perf_hpp__for_each_format(fmt) { if (!first) fprintf(fp, "%s", sep ?: " "); else first = false; - perf_hpp__format[idx].header(&dummy_hpp); + fmt->header(&dummy_hpp); fprintf(fp, "%s", bf); } @@ -400,18 +401,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, first = true; fprintf(fp, "# "); - for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) { - unsigned int i; - if (!perf_hpp__format[idx].cond) - continue; + perf_hpp__for_each_format(fmt) { + unsigned int i; if (!first) fprintf(fp, "%s", sep ?: " "); else first = false; - width = perf_hpp__format[idx].width(&dummy_hpp); + width = fmt->width(&dummy_hpp); for (i = 0; i < width; i++) fprintf(fp, "."); } @@ -462,7 +461,7 @@ out: return ret; } -size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp) { int i; size_t ret = 0; @@ -470,7 +469,7 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { const char *name; - if (hists->stats.nr_events[i] == 0) + if (stats->nr_events[i] == 0) continue; name = perf_event__name(i); @@ -478,7 +477,7 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp) continue; ret += fprintf(fp, "%16s events: %10d\n", name, - hists->stats.nr_events[i]); + stats->nr_events[i]); } return ret; diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index 2884d2f..1c8b9af 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -8,6 +8,8 @@ #include "../ui.h" #include "../libslang.h" +char ui_helpline__last_msg[1024]; + static void tui_helpline__pop(void) { } @@ -23,20 +25,7 @@ static void tui_helpline__push(const char *msg) strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0'; } -struct ui_helpline tui_helpline_fns = { - .pop = tui_helpline__pop, - .push = tui_helpline__push, -}; - -void ui_helpline__init(void) -{ - helpline_fns = &tui_helpline_fns; - ui_helpline__puts(" "); -} - -char ui_helpline__last_msg[1024]; - -int ui_helpline__show_help(const char *format, va_list ap) +static int tui_helpline__show(const char *format, va_list ap) { int ret; static int backlog; @@ -55,3 +44,15 @@ int ui_helpline__show_help(const char *format, va_list ap) return ret; } + +struct ui_helpline tui_helpline_fns = { + .pop = tui_helpline__pop, + .push = tui_helpline__push, + .show = tui_helpline__show, +}; + +void ui_helpline__init(void) +{ + helpline_fns = &tui_helpline_fns; + ui_helpline__puts(" "); +} diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c index 4f98977..e3e0a96 100644 --- a/tools/perf/ui/util.c +++ b/tools/perf/ui/util.c @@ -52,7 +52,6 @@ int ui__warning(const char *format, ...) return ret; } - /** * perf_error__register - Register error logging functions * @eops: The pointer to error logging function struct diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN index 6aa34e5..055fef3 100755 --- a/tools/perf/util/PERF-VERSION-GEN +++ b/tools/perf/util/PERF-VERSION-GEN @@ -26,13 +26,13 @@ VN=$(expr "$VN" : v*'\(.*\)') if test -r $GVF then - VC=$(sed -e 's/^PERF_VERSION = //' <$GVF) + VC=$(sed -e 's/^#define PERF_VERSION "\(.*\)"/\1/' <$GVF) else VC=unset fi test "$VN" = "$VC" || { echo >&2 "PERF_VERSION = $VN" - echo "PERF_VERSION = $VN" >$GVF + echo "#define PERF_VERSION \"$VN\"" >$GVF } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 07aaeea..d33fe93 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -809,7 +809,7 @@ fallback: pr_err("Can't annotate %s:\n\n" "No vmlinux file%s\nwas found in the path.\n\n" "Please use:\n\n" - " perf buildid-cache -av vmlinux\n\n" + " perf buildid-cache -vu vmlinux\n\n" "or:\n\n" " --vmlinux vmlinux\n", sym->name, build_id_msg ?: ""); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 8eec943..c422440 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -6,6 +6,7 @@ #include "types.h" #include "symbol.h" #include "hist.h" +#include "sort.h" #include <linux/list.h> #include <linux/rbtree.h> #include <pthread.h> @@ -154,6 +155,29 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused, } #endif +#ifdef GTK2_SUPPORT +int symbol__gtk_annotate(struct symbol *sym, struct map *map, int evidx, + struct hist_browser_timer *hbt); + +static inline int hist_entry__gtk_annotate(struct hist_entry *he, int evidx, + struct hist_browser_timer *hbt) +{ + return symbol__gtk_annotate(he->ms.sym, he->ms.map, evidx, hbt); +} + +void perf_gtk__show_annotations(void); +#else +static inline int hist_entry__gtk_annotate(struct hist_entry *he __maybe_unused, + int evidx __maybe_unused, + struct hist_browser_timer *hbt + __maybe_unused) +{ + return 0; +} + +static inline void perf_gtk__show_annotations(void) {} +#endif + extern const char *disassembler_style; #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index d3b3f5d..42b6a63 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -444,7 +444,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, struct callchain_cursor_node *node = *cursor->last; if (!node) { - node = calloc(sizeof(*node), 1); + node = calloc(1, sizeof(*node)); if (!node) return -ENOMEM; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index eb34057..3ee9f67 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -143,4 +143,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) cursor->curr = cursor->curr->next; cursor->pos++; } + +struct option; + +int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 2b32ffa..f817046 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -1,4 +1,5 @@ #include "util.h" +#include "sysfs.h" #include "../perf.h" #include "cpumap.h" #include <assert.h> @@ -201,3 +202,56 @@ void cpu_map__delete(struct cpu_map *map) { free(map); } + +int cpu_map__get_socket(struct cpu_map *map, int idx) +{ + FILE *fp; + const char *mnt; + char path[PATH_MAX]; + int cpu, ret; + + if (idx > map->nr) + return -1; + + cpu = map->map[idx]; + + mnt = sysfs_find_mountpoint(); + if (!mnt) + return -1; + + sprintf(path, + "%s/devices/system/cpu/cpu%d/topology/physical_package_id", + mnt, cpu); + + fp = fopen(path, "r"); + if (!fp) + return -1; + ret = fscanf(fp, "%d", &cpu); + fclose(fp); + return ret == 1 ? cpu : -1; +} + +int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp) +{ + struct cpu_map *sock; + int nr = cpus->nr; + int cpu, s1, s2; + + sock = calloc(1, sizeof(*sock) + nr * sizeof(int)); + if (!sock) + return -1; + + for (cpu = 0; cpu < nr; cpu++) { + s1 = cpu_map__get_socket(cpus, cpu); + for (s2 = 0; s2 < sock->nr; s2++) { + if (s1 == sock->map[s2]) + break; + } + if (s2 == sock->nr) { + sock->map[sock->nr] = s1; + sock->nr++; + } + } + *sockp = sock; + return 0; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 2f68a3b..161b007 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -14,6 +14,15 @@ struct cpu_map *cpu_map__dummy_new(void); void cpu_map__delete(struct cpu_map *map); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); +int cpu_map__get_socket(struct cpu_map *map, int idx); +int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); + +static inline int cpu_map__socket(struct cpu_map *sock, int s) +{ + if (!sock || s > sock->nr || s < 0) + return 0; + return sock->map[s]; +} static inline int cpu_map__nr(const struct cpu_map *map) { diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 03f830b..399e74c 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -23,10 +23,8 @@ int eprintf(int level, const char *fmt, ...) if (verbose >= level) { va_start(args, fmt); - if (use_browser == 1) - ret = ui_helpline__show_help(fmt, args); - else if (use_browser == 2) - ret = perf_gtk__show_helpline(fmt, args); + if (use_browser >= 1) + ui_helpline__vshow(fmt, args); else ret = vfprintf(stderr, fmt, args); va_end(args); @@ -49,28 +47,6 @@ int dump_printf(const char *fmt, ...) return ret; } -#if !defined(NEWT_SUPPORT) && !defined(GTK2_SUPPORT) -int ui__warning(const char *format, ...) -{ - va_list args; - - va_start(args, format); - vfprintf(stderr, format, args); - va_end(args); - return 0; -} -#endif - -int ui__error_paranoid(void) -{ - return ui__error("Permission error - are you root?\n" - "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" - " -1 - Not paranoid at all\n" - " 0 - Disallow raw tracepoint access for unpriv\n" - " 1 - Disallow cpu events for unpriv\n" - " 2 - Disallow kernel profiling for unpriv\n"); -} - void trace_event(union perf_event *event) { unsigned char *raw_event = (void *)event; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 83e8d23..efbd988 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -5,6 +5,8 @@ #include <stdbool.h> #include "event.h" #include "../ui/helpline.h" +#include "../ui/progress.h" +#include "../ui/util.h" extern int verbose; extern bool quiet, dump_trace; @@ -12,39 +14,7 @@ extern bool quiet, dump_trace; int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); -struct ui_progress; -struct perf_error_ops; - -#if defined(NEWT_SUPPORT) || defined(GTK2_SUPPORT) - -#include "../ui/progress.h" int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -#include "../ui/util.h" - -#else - -static inline void ui_progress__update(u64 curr __maybe_unused, - u64 total __maybe_unused, - const char *title __maybe_unused) {} -static inline void ui_progress__finish(void) {} - -#define ui__error(format, arg...) ui__warning(format, ##arg) - -static inline int -perf_error__register(struct perf_error_ops *eops __maybe_unused) -{ - return 0; -} - -static inline int -perf_error__unregister(struct perf_error_ops *eops __maybe_unused) -{ - return 0; -} - -#endif /* NEWT_SUPPORT || GTK2_SUPPORT */ - int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); -int ui__error_paranoid(void); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d6d9a46..6f7d5a9 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -539,13 +539,13 @@ struct dso *__dsos__findnew(struct list_head *head, const char *name) } size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, - bool with_hits) + bool (skip)(struct dso *dso, int parm), int parm) { struct dso *pos; size_t ret = 0; list_for_each_entry(pos, head, node) { - if (with_hits && !pos->hit) + if (skip && skip(pos, parm)) continue; ret += dso__fprintf_buildid(pos, fp); ret += fprintf(fp, " %s\n", pos->long_name); @@ -583,7 +583,7 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp) if (dso->short_name != dso->long_name) ret += fprintf(fp, "%s, ", dso->long_name); ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type], - dso->loaded ? "" : "NOT "); + dso__loaded(dso, type) ? "" : "NOT "); ret += dso__fprintf_buildid(dso, fp); ret += fprintf(fp, ")\n"); for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) { diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index e032769..450199a 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -138,7 +138,7 @@ struct dso *__dsos__findnew(struct list_head *head, const char *name); bool __dsos__read_build_ids(struct list_head *head, bool with_hits); size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp, - bool with_hits); + bool (skip)(struct dso *dso, int parm), int parm); size_t __dsos__fprintf(struct list_head *head, FILE *fp); size_t dso__fprintf_buildid(struct dso *dso, FILE *fp); diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 3cf2c3e..5cd13d7 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -476,8 +476,10 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, } } - if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) + if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) { + free(event); return -ENOENT; + } map = machine->vmlinux_maps[MAP__FUNCTION]; size = snprintf(event->mmap.filename, sizeof(event->mmap.filename), diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 7052934..bc4ad79 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -49,10 +49,16 @@ struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, return evlist; } -void perf_evlist__config_attrs(struct perf_evlist *evlist, - struct perf_record_opts *opts) +void perf_evlist__config(struct perf_evlist *evlist, + struct perf_record_opts *opts) { struct perf_evsel *evsel; + /* + * Set the evsel leader links before we configure attributes, + * since some might depend on this info. + */ + if (opts->group) + perf_evlist__set_leader(evlist); if (evlist->cpus->map[0] < 0) opts->no_inherit = true; @@ -61,7 +67,7 @@ void perf_evlist__config_attrs(struct perf_evlist *evlist, perf_evsel__config(evsel, opts); if (evlist->nr_entries > 1) - evsel->attr.sample_type |= PERF_SAMPLE_ID; + perf_evsel__set_sample_id(evsel); } } @@ -111,18 +117,21 @@ void __perf_evlist__set_leader(struct list_head *list) struct perf_evsel *evsel, *leader; leader = list_entry(list->next, struct perf_evsel, node); - leader->leader = NULL; + evsel = list_entry(list->prev, struct perf_evsel, node); + + leader->nr_members = evsel->idx - leader->idx + 1; list_for_each_entry(evsel, list, node) { - if (evsel != leader) - evsel->leader = leader; + evsel->leader = leader; } } void perf_evlist__set_leader(struct perf_evlist *evlist) { - if (evlist->nr_entries) + if (evlist->nr_entries) { + evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; __perf_evlist__set_leader(&evlist->entries); + } } int perf_evlist__add_default(struct perf_evlist *evlist) @@ -222,7 +231,7 @@ void perf_evlist__disable(struct perf_evlist *evlist) for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { list_for_each_entry(pos, &evlist->entries, node) { - if (perf_evsel__is_group_member(pos)) + if (!perf_evsel__is_group_leader(pos)) continue; for (thread = 0; thread < evlist->threads->nr; thread++) ioctl(FD(pos, cpu, thread), @@ -238,7 +247,7 @@ void perf_evlist__enable(struct perf_evlist *evlist) for (cpu = 0; cpu < cpu_map__nr(evlist->cpus); cpu++) { list_for_each_entry(pos, &evlist->entries, node) { - if (perf_evsel__is_group_member(pos)) + if (!perf_evsel__is_group_leader(pos)) continue; for (thread = 0; thread < evlist->threads->nr; thread++) ioctl(FD(pos, cpu, thread), @@ -366,7 +375,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) if ((old & md->mask) + size != ((old + size) & md->mask)) { unsigned int offset = old; unsigned int len = min(sizeof(*event), size), cpy; - void *dst = &evlist->event_copy; + void *dst = &md->event_copy; do { cpy = min(md->mask + 1 - (offset & md->mask), len); @@ -376,7 +385,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) len -= cpy; } while (len); - event = &evlist->event_copy; + event = &md->event_copy; } old += size; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 56003f7..2dd07bd 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -17,10 +17,18 @@ struct perf_record_opts; #define PERF_EVLIST__HLIST_BITS 8 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) +struct perf_mmap { + void *base; + int mask; + unsigned int prev; + union perf_event event_copy; +}; + struct perf_evlist { struct list_head entries; struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; int nr_entries; + int nr_groups; int nr_fds; int nr_mmaps; int mmap_len; @@ -29,7 +37,6 @@ struct perf_evlist { pid_t pid; } workload; bool overwrite; - union perf_event event_copy; struct perf_mmap *mmap; struct pollfd *pollfd; struct thread_map *threads; @@ -76,8 +83,8 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); int perf_evlist__open(struct perf_evlist *evlist); -void perf_evlist__config_attrs(struct perf_evlist *evlist, - struct perf_record_opts *opts); +void perf_evlist__config(struct perf_evlist *evlist, + struct perf_record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_record_opts *opts, @@ -135,4 +142,25 @@ static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) } size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp); + +static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) +{ + struct perf_event_mmap_page *pc = mm->base; + int head = pc->data_head; + rmb(); + return head; +} + +static inline void perf_mmap__write_tail(struct perf_mmap *md, + unsigned long tail) +{ + struct perf_event_mmap_page *pc = md->base; + + /* + * ensure all reads are done before we write the tail out. + */ + /* mb(); */ + pc->data_tail = tail; +} + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1b16dd1..9c82f98f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -22,6 +22,11 @@ #include <linux/perf_event.h> #include "perf_regs.h" +static struct { + bool sample_id_all; + bool exclude_guest; +} perf_missing_features; + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) static int __perf_evsel__sample_size(u64 sample_type) @@ -50,11 +55,36 @@ void hists__init(struct hists *hists) pthread_mutex_init(&hists->lock, NULL); } +void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit) +{ + if (!(evsel->attr.sample_type & bit)) { + evsel->attr.sample_type |= bit; + evsel->sample_size += sizeof(u64); + } +} + +void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit) +{ + if (evsel->attr.sample_type & bit) { + evsel->attr.sample_type &= ~bit; + evsel->sample_size -= sizeof(u64); + } +} + +void perf_evsel__set_sample_id(struct perf_evsel *evsel) +{ + perf_evsel__set_sample_bit(evsel, ID); + evsel->attr.read_format |= PERF_FORMAT_ID; +} + void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { evsel->idx = idx; evsel->attr = *attr; + evsel->leader = evsel; INIT_LIST_HEAD(&evsel->node); hists__init(&evsel->hists); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); @@ -404,6 +434,31 @@ const char *perf_evsel__name(struct perf_evsel *evsel) return evsel->name ?: "unknown"; } +const char *perf_evsel__group_name(struct perf_evsel *evsel) +{ + return evsel->group_name ?: "anon group"; +} + +int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) +{ + int ret; + struct perf_evsel *pos; + const char *group_name = perf_evsel__group_name(evsel); + + ret = scnprintf(buf, size, "%s", group_name); + + ret += scnprintf(buf + ret, size - ret, " { %s", + perf_evsel__name(evsel)); + + for_each_group_member(pos, evsel) + ret += scnprintf(buf + ret, size - ret, ", %s", + perf_evsel__name(pos)); + + ret += scnprintf(buf + ret, size - ret, " }"); + + return ret; +} + /* * The enable_on_exec/disabled value strategy: * @@ -438,13 +493,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_event_attr *attr = &evsel->attr; int track = !evsel->idx; /* only the first counter needs these */ - attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1; + attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; attr->inherit = !opts->no_inherit; - attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | - PERF_FORMAT_TOTAL_TIME_RUNNING | - PERF_FORMAT_ID; - attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID; + perf_evsel__set_sample_bit(evsel, IP); + perf_evsel__set_sample_bit(evsel, TID); /* * We default some events to a 1 default interval. But keep @@ -453,7 +506,7 @@ void perf_evsel__config(struct perf_evsel *evsel, if (!attr->sample_period || (opts->user_freq != UINT_MAX && opts->user_interval != ULLONG_MAX)) { if (opts->freq) { - attr->sample_type |= PERF_SAMPLE_PERIOD; + perf_evsel__set_sample_bit(evsel, PERIOD); attr->freq = 1; attr->sample_freq = opts->freq; } else { @@ -468,16 +521,16 @@ void perf_evsel__config(struct perf_evsel *evsel, attr->inherit_stat = 1; if (opts->sample_address) { - attr->sample_type |= PERF_SAMPLE_ADDR; + perf_evsel__set_sample_bit(evsel, ADDR); attr->mmap_data = track; } if (opts->call_graph) { - attr->sample_type |= PERF_SAMPLE_CALLCHAIN; + perf_evsel__set_sample_bit(evsel, CALLCHAIN); if (opts->call_graph == CALLCHAIN_DWARF) { - attr->sample_type |= PERF_SAMPLE_REGS_USER | - PERF_SAMPLE_STACK_USER; + perf_evsel__set_sample_bit(evsel, REGS_USER); + perf_evsel__set_sample_bit(evsel, STACK_USER); attr->sample_regs_user = PERF_REGS_MASK; attr->sample_stack_user = opts->stack_dump_size; attr->exclude_callchain_user = 1; @@ -485,20 +538,20 @@ void perf_evsel__config(struct perf_evsel *evsel, } if (perf_target__has_cpu(&opts->target)) - attr->sample_type |= PERF_SAMPLE_CPU; + perf_evsel__set_sample_bit(evsel, CPU); if (opts->period) - attr->sample_type |= PERF_SAMPLE_PERIOD; + perf_evsel__set_sample_bit(evsel, PERIOD); - if (!opts->sample_id_all_missing && + if (!perf_missing_features.sample_id_all && (opts->sample_time || !opts->no_inherit || perf_target__has_cpu(&opts->target))) - attr->sample_type |= PERF_SAMPLE_TIME; + perf_evsel__set_sample_bit(evsel, TIME); if (opts->raw_samples) { - attr->sample_type |= PERF_SAMPLE_TIME; - attr->sample_type |= PERF_SAMPLE_RAW; - attr->sample_type |= PERF_SAMPLE_CPU; + perf_evsel__set_sample_bit(evsel, TIME); + perf_evsel__set_sample_bit(evsel, RAW); + perf_evsel__set_sample_bit(evsel, CPU); } if (opts->no_delay) { @@ -506,7 +559,7 @@ void perf_evsel__config(struct perf_evsel *evsel, attr->wakeup_events = 1; } if (opts->branch_stack) { - attr->sample_type |= PERF_SAMPLE_BRANCH_STACK; + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } @@ -519,14 +572,14 @@ void perf_evsel__config(struct perf_evsel *evsel, * Disabling only independent events or group leaders, * keeping group members enabled. */ - if (!perf_evsel__is_group_member(evsel)) + if (perf_evsel__is_group_leader(evsel)) attr->disabled = 1; /* * Setting enable_on_exec for independent events and * group leaders for traced executed by perf. */ - if (perf_target__none(&opts->target) && !perf_evsel__is_group_member(evsel)) + if (perf_target__none(&opts->target) && perf_evsel__is_group_leader(evsel)) attr->enable_on_exec = 1; } @@ -612,6 +665,11 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) } } +void perf_evsel__free_counts(struct perf_evsel *evsel) +{ + free(evsel->counts); +} + void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); @@ -631,6 +689,28 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } +static inline void compute_deltas(struct perf_evsel *evsel, + int cpu, + struct perf_counts_values *count) +{ + struct perf_counts_values tmp; + + if (!evsel->prev_raw_counts) + return; + + if (cpu == -1) { + tmp = evsel->prev_raw_counts->aggr; + evsel->prev_raw_counts->aggr = *count; + } else { + tmp = evsel->prev_raw_counts->cpu[cpu]; + evsel->prev_raw_counts->cpu[cpu] = *count; + } + + count->val = count->val - tmp.val; + count->ena = count->ena - tmp.ena; + count->run = count->run - tmp.run; +} + int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale) { @@ -646,6 +726,8 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) return -errno; + compute_deltas(evsel, cpu, &count); + if (scale) { if (count.run == 0) count.val = 0; @@ -684,6 +766,8 @@ int __perf_evsel__read(struct perf_evsel *evsel, } } + compute_deltas(evsel, -1, aggr); + evsel->counts->scaled = 0; if (scale) { if (aggr->run == 0) { @@ -707,7 +791,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) struct perf_evsel *leader = evsel->leader; int fd; - if (!perf_evsel__is_group_member(evsel)) + if (perf_evsel__is_group_leader(evsel)) return -1; /* @@ -738,6 +822,13 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, pid = evsel->cgrp->fd; } +fallback_missing_features: + if (perf_missing_features.exclude_guest) + evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; +retry_sample_id: + if (perf_missing_features.sample_id_all) + evsel->attr.sample_id_all = 0; + for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < threads->nr; thread++) { @@ -754,13 +845,26 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, group_fd, flags); if (FD(evsel, cpu, thread) < 0) { err = -errno; - goto out_close; + goto try_fallback; } } } return 0; +try_fallback: + if (err != -EINVAL || cpu > 0 || thread > 0) + goto out_close; + + if (!perf_missing_features.exclude_guest && + (evsel->attr.exclude_guest || evsel->attr.exclude_host)) { + perf_missing_features.exclude_guest = true; + goto fallback_missing_features; + } else if (!perf_missing_features.sample_id_all) { + perf_missing_features.sample_id_all = true; + goto retry_sample_id; + } + out_close: do { while (--thread >= 0) { @@ -1205,3 +1309,225 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } + +static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (!*first) { + ret += fprintf(fp, ","); + } else { + ret += fprintf(fp, ":"); + *first = false; + } + + va_start(args, fmt); + ret += vfprintf(fp, fmt, args); + va_end(args); + return ret; +} + +static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value) +{ + if (value == 0) + return 0; + + return comma_fprintf(fp, first, " %s: %" PRIu64, field, value); +} + +#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field) + +struct bit_names { + int bit; + const char *name; +}; + +static int bits__fprintf(FILE *fp, const char *field, u64 value, + struct bit_names *bits, bool *first) +{ + int i = 0, printed = comma_fprintf(fp, first, " %s: ", field); + bool first_bit = true; + + do { + if (value & bits[i].bit) { + printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); + + return printed; +} + +static int sample_type__fprintf(FILE *fp, bool *first, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), + bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), + bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + { .name = NULL, } + }; +#undef bit_name + return bits__fprintf(fp, "sample_type", value, bits, first); +} + +static int read_format__fprintf(FILE *fp, bool *first, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + return bits__fprintf(fp, "read_format", value, bits, first); +} + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp) +{ + bool first = true; + int printed = 0; + + if (details->event_group) { + struct perf_evsel *pos; + + if (!perf_evsel__is_group_leader(evsel)) + return 0; + + if (evsel->nr_members > 1) + printed += fprintf(fp, "%s{", evsel->group_name ?: ""); + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + for_each_group_member(pos, evsel) + printed += fprintf(fp, ",%s", perf_evsel__name(pos)); + + if (evsel->nr_members > 1) + printed += fprintf(fp, "}"); + goto out; + } + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + + if (details->verbose || details->freq) { + printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, + (u64)evsel->attr.sample_freq); + } + + if (details->verbose) { + if_print(type); + if_print(config); + if_print(config1); + if_print(config2); + if_print(size); + printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type); + if (evsel->attr.read_format) + printed += read_format__fprintf(fp, &first, evsel->attr.read_format); + if_print(disabled); + if_print(inherit); + if_print(pinned); + if_print(exclusive); + if_print(exclude_user); + if_print(exclude_kernel); + if_print(exclude_hv); + if_print(exclude_idle); + if_print(mmap); + if_print(comm); + if_print(freq); + if_print(inherit_stat); + if_print(enable_on_exec); + if_print(task); + if_print(watermark); + if_print(precise_ip); + if_print(mmap_data); + if_print(sample_id_all); + if_print(exclude_host); + if_print(exclude_guest); + if_print(__reserved_1); + if_print(wakeup_events); + if_print(bp_type); + if_print(branch_sample_type); + } +out: + fputc('\n', fp); + return ++printed; +} + +bool perf_evsel__fallback(struct perf_evsel *evsel, int err, + char *msg, size_t msgsize) +{ + if ((err == ENOENT || err == ENXIO) && + evsel->attr.type == PERF_TYPE_HARDWARE && + evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) { + /* + * If it's cycles then fall back to hrtimer based + * cpu-clock-tick sw counter, which is always available even if + * no PMU support. + * + * PPC returns ENXIO until 2.6.37 (behavior changed with commit + * b0a873e). + */ + scnprintf(msg, msgsize, "%s", +"The cycles event is not supported, trying to fall back to cpu-clock-ticks"); + + evsel->attr.type = PERF_TYPE_SOFTWARE; + evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK; + + free(evsel->name); + evsel->name = NULL; + return true; + } + + return false; +} + +int perf_evsel__open_strerror(struct perf_evsel *evsel, + struct perf_target *target, + int err, char *msg, size_t size) +{ + switch (err) { + case EPERM: + case EACCES: + return scnprintf(msg, size, "%s", + "You may not have permission to collect %sstats.\n" + "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n" + " -1 - Not paranoid at all\n" + " 0 - Disallow raw tracepoint access for unpriv\n" + " 1 - Disallow cpu events for unpriv\n" + " 2 - Disallow kernel profiling for unpriv", + target->system_wide ? "system-wide " : ""); + case ENOENT: + return scnprintf(msg, size, "The %s event is not supported.", + perf_evsel__name(evsel)); + case EMFILE: + return scnprintf(msg, size, "%s", + "Too many events are opened.\n" + "Try again after reducing the number of events."); + case ENODEV: + if (target->cpu_list) + return scnprintf(msg, size, "%s", + "No such device - did you specify an out-of-range profile CPU?\n"); + break; + case EOPNOTSUPP: + if (evsel->attr.precise_ip) + return scnprintf(msg, size, "%s", + "\'precise\' request may not be supported. Try removing 'p' modifier."); +#if defined(__i386__) || defined(__x86_64__) + if (evsel->attr.type == PERF_TYPE_HARDWARE) + return scnprintf(msg, size, "%s", + "No hardware sampling interrupt available.\n" + "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); +#endif + break; + default: + break; + } + + return scnprintf(msg, size, + "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n" + "/bin/dmesg may provide additional information.\n" + "No CONFIG_PERF_EVENTS=y kernel support configured?\n", + err, strerror(err), perf_evsel__name(evsel)); +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 3d2b801..52021c3 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -53,6 +53,7 @@ struct perf_evsel { struct xyarray *sample_id; u64 *id; struct perf_counts *counts; + struct perf_counts *prev_raw_counts; int idx; u32 ids; struct hists hists; @@ -73,10 +74,13 @@ struct perf_evsel { bool needs_swap; /* parse modifier helper */ int exclude_GH; + int nr_members; struct perf_evsel *leader; char *group_name; }; +#define hists_to_evsel(h) container_of(h, struct perf_evsel, hists) + struct cpu_map; struct thread_map; struct perf_evlist; @@ -110,14 +114,30 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX]; int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *perf_evsel__name(struct perf_evsel *evsel); +const char *perf_evsel__group_name(struct perf_evsel *evsel); +int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__free_fd(struct perf_evsel *evsel); void perf_evsel__free_id(struct perf_evsel *evsel); +void perf_evsel__free_counts(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit); +void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel, + enum perf_event_sample_format bit); + +#define perf_evsel__set_sample_bit(evsel, bit) \ + __perf_evsel__set_sample_bit(evsel, PERF_SAMPLE_##bit) + +#define perf_evsel__reset_sample_bit(evsel, bit) \ + __perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit) + +void perf_evsel__set_sample_id(struct perf_evsel *evsel); + int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); @@ -226,8 +246,34 @@ static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel) return list_entry(evsel->node.next, struct perf_evsel, node); } -static inline bool perf_evsel__is_group_member(const struct perf_evsel *evsel) +static inline bool perf_evsel__is_group_leader(const struct perf_evsel *evsel) +{ + return evsel->leader == evsel; +} + +struct perf_attr_details { + bool freq; + bool verbose; + bool event_group; +}; + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp); + +bool perf_evsel__fallback(struct perf_evsel *evsel, int err, + char *msg, size_t msgsize); +int perf_evsel__open_strerror(struct perf_evsel *evsel, + struct perf_target *target, + int err, char *msg, size_t size); + +static inline int perf_evsel__group_idx(struct perf_evsel *evsel) { - return evsel->leader != NULL; + return evsel->idx - evsel->leader->idx; } + +#define for_each_group_member(_evsel, _leader) \ +for ((_evsel) = list_entry((_leader)->node.next, struct perf_evsel, node); \ + (_evsel) && (_evsel)->leader == (_leader); \ + (_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node)) + #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b7da463..f4bfd79 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -148,7 +148,7 @@ static char *do_read_string(int fd, struct perf_header *ph) u32 len; char *buf; - sz = read(fd, &len, sizeof(len)); + sz = readn(fd, &len, sizeof(len)); if (sz < (ssize_t)sizeof(len)) return NULL; @@ -159,7 +159,7 @@ static char *do_read_string(int fd, struct perf_header *ph) if (!buf) return NULL; - ret = read(fd, buf, len); + ret = readn(fd, buf, len); if (ret == (ssize_t)len) { /* * strings are padded by zeroes @@ -287,12 +287,12 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd) struct perf_session *session = container_of(header, struct perf_session, header); struct rb_node *nd; - int err = machine__write_buildid_table(&session->host_machine, fd); + int err = machine__write_buildid_table(&session->machines.host, fd); if (err) return err; - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); err = machine__write_buildid_table(pos, fd); if (err) @@ -313,7 +313,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, if (is_kallsyms) { if (symbol_conf.kptr_restrict) { pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n"); - return 0; + err = 0; + goto out_free; } realname = (char *) name; } else @@ -448,9 +449,9 @@ static int perf_session__cache_build_ids(struct perf_session *session) if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->host_machine, debugdir); + ret = machine__cache_build_ids(&session->machines.host, debugdir); - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__cache_build_ids(pos, debugdir); } @@ -467,9 +468,9 @@ static bool machine__read_build_ids(struct machine *machine, bool with_hits) static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) { struct rb_node *nd; - bool ret = machine__read_build_ids(&session->host_machine, with_hits); + bool ret = machine__read_build_ids(&session->machines.host, with_hits); - for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__read_build_ids(pos, with_hits); } @@ -954,6 +955,7 @@ static int write_topo_node(int fd, int node) } fclose(fp); + fp = NULL; ret = do_write(fd, &mem_total, sizeof(u64)); if (ret) @@ -980,7 +982,8 @@ static int write_topo_node(int fd, int node) ret = do_write_string(fd, buf); done: free(buf); - fclose(fp); + if (fp) + fclose(fp); return ret; } @@ -1051,16 +1054,25 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, struct perf_pmu *pmu = NULL; off_t offset = lseek(fd, 0, SEEK_CUR); __u32 pmu_num = 0; + int ret; /* write real pmu_num later */ - do_write(fd, &pmu_num, sizeof(pmu_num)); + ret = do_write(fd, &pmu_num, sizeof(pmu_num)); + if (ret < 0) + return ret; while ((pmu = perf_pmu__scan(pmu))) { if (!pmu->name) continue; pmu_num++; - do_write(fd, &pmu->type, sizeof(pmu->type)); - do_write_string(fd, pmu->name); + + ret = do_write(fd, &pmu->type, sizeof(pmu->type)); + if (ret < 0) + return ret; + + ret = do_write_string(fd, pmu->name); + if (ret < 0) + return ret; } if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) { @@ -1073,6 +1085,52 @@ static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused, } /* + * File format: + * + * struct group_descs { + * u32 nr_groups; + * struct group_desc { + * char name[]; + * u32 leader_idx; + * u32 nr_members; + * }[nr_groups]; + * }; + */ +static int write_group_desc(int fd, struct perf_header *h __maybe_unused, + struct perf_evlist *evlist) +{ + u32 nr_groups = evlist->nr_groups; + struct perf_evsel *evsel; + int ret; + + ret = do_write(fd, &nr_groups, sizeof(nr_groups)); + if (ret < 0) + return ret; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (perf_evsel__is_group_leader(evsel) && + evsel->nr_members > 1) { + const char *name = evsel->group_name ?: "{anon_group}"; + u32 leader_idx = evsel->idx; + u32 nr_members = evsel->nr_members; + + ret = do_write_string(fd, name); + if (ret < 0) + return ret; + + ret = do_write(fd, &leader_idx, sizeof(leader_idx)); + if (ret < 0) + return ret; + + ret = do_write(fd, &nr_members, sizeof(nr_members)); + if (ret < 0) + return ret; + } + } + return 0; +} + +/* * default get_cpuid(): nothing gets recorded * actual implementation must be in arch/$(ARCH)/util/header.c */ @@ -1209,14 +1267,14 @@ read_event_desc(struct perf_header *ph, int fd) size_t msz; /* number of events */ - ret = read(fd, &nre, sizeof(nre)); + ret = readn(fd, &nre, sizeof(nre)); if (ret != (ssize_t)sizeof(nre)) goto error; if (ph->needs_swap) nre = bswap_32(nre); - ret = read(fd, &sz, sizeof(sz)); + ret = readn(fd, &sz, sizeof(sz)); if (ret != (ssize_t)sizeof(sz)) goto error; @@ -1244,7 +1302,7 @@ read_event_desc(struct perf_header *ph, int fd) * must read entire on-file attr struct to * sync up with layout. */ - ret = read(fd, buf, sz); + ret = readn(fd, buf, sz); if (ret != (ssize_t)sz) goto error; @@ -1253,7 +1311,7 @@ read_event_desc(struct perf_header *ph, int fd) memcpy(&evsel->attr, buf, msz); - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != (ssize_t)sizeof(nr)) goto error; @@ -1274,7 +1332,7 @@ read_event_desc(struct perf_header *ph, int fd) evsel->id = id; for (j = 0 ; j < nr; j++) { - ret = read(fd, id, sizeof(*id)); + ret = readn(fd, id, sizeof(*id)); if (ret != (ssize_t)sizeof(*id)) goto error; if (ph->needs_swap) @@ -1435,6 +1493,31 @@ error: fprintf(fp, "# pmu mappings: unable to read\n"); } +static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, + FILE *fp) +{ + struct perf_session *session; + struct perf_evsel *evsel; + u32 nr = 0; + + session = container_of(ph, struct perf_session, header); + + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (perf_evsel__is_group_leader(evsel) && + evsel->nr_members > 1) { + fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", + perf_evsel__name(evsel)); + + nr = evsel->nr_members - 1; + } else if (nr) { + fprintf(fp, ",%s", perf_evsel__name(evsel)); + + if (--nr == 0) + fprintf(fp, "}\n"); + } + } +} + static int __event_process_build_id(struct build_id_event *bev, char *filename, struct perf_session *session) @@ -1506,14 +1589,14 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header, while (offset < limit) { ssize_t len; - if (read(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) + if (readn(input, &old_bev, sizeof(old_bev)) != sizeof(old_bev)) return -1; if (header->needs_swap) perf_event_header__bswap(&old_bev.header); len = old_bev.header.size - sizeof(old_bev); - if (read(input, filename, len) != len) + if (readn(input, filename, len) != len) return -1; bev.header = old_bev.header; @@ -1548,14 +1631,14 @@ static int perf_header__read_build_ids(struct perf_header *header, while (offset < limit) { ssize_t len; - if (read(input, &bev, sizeof(bev)) != sizeof(bev)) + if (readn(input, &bev, sizeof(bev)) != sizeof(bev)) goto out; if (header->needs_swap) perf_event_header__bswap(&bev.header); len = bev.header.size - sizeof(bev); - if (read(input, filename, len) != len) + if (readn(input, filename, len) != len) goto out; /* * The a1645ce1 changeset: @@ -1641,7 +1724,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, size_t ret; u32 nr; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1650,7 +1733,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused, ph->env.nr_cpus_online = nr; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1684,7 +1767,7 @@ static int process_total_mem(struct perf_file_section *section __maybe_unused, uint64_t mem; size_t ret; - ret = read(fd, &mem, sizeof(mem)); + ret = readn(fd, &mem, sizeof(mem)); if (ret != sizeof(mem)) return -1; @@ -1756,7 +1839,7 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused, u32 nr, i; struct strbuf sb; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1792,7 +1875,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused char *str; struct strbuf sb; - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1813,7 +1896,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused } ph->env.sibling_cores = strbuf_detach(&sb, NULL); - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) return -1; @@ -1850,7 +1933,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse struct strbuf sb; /* nr nodes */ - ret = read(fd, &nr, sizeof(nr)); + ret = readn(fd, &nr, sizeof(nr)); if (ret != sizeof(nr)) goto error; @@ -1862,15 +1945,15 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse for (i = 0; i < nr; i++) { /* node number */ - ret = read(fd, &node, sizeof(node)); + ret = readn(fd, &node, sizeof(node)); if (ret != sizeof(node)) goto error; - ret = read(fd, &mem_total, sizeof(u64)); + ret = readn(fd, &mem_total, sizeof(u64)); if (ret != sizeof(u64)) goto error; - ret = read(fd, &mem_free, sizeof(u64)); + ret = readn(fd, &mem_free, sizeof(u64)); if (ret != sizeof(u64)) goto error; @@ -1909,7 +1992,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused u32 type; struct strbuf sb; - ret = read(fd, &pmu_num, sizeof(pmu_num)); + ret = readn(fd, &pmu_num, sizeof(pmu_num)); if (ret != sizeof(pmu_num)) return -1; @@ -1925,7 +2008,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused strbuf_init(&sb, 128); while (pmu_num) { - if (read(fd, &type, sizeof(type)) != sizeof(type)) + if (readn(fd, &type, sizeof(type)) != sizeof(type)) goto error; if (ph->needs_swap) type = bswap_32(type); @@ -1949,6 +2032,98 @@ error: return -1; } +static int process_group_desc(struct perf_file_section *section __maybe_unused, + struct perf_header *ph, int fd, + void *data __maybe_unused) +{ + size_t ret = -1; + u32 i, nr, nr_groups; + struct perf_session *session; + struct perf_evsel *evsel, *leader = NULL; + struct group_desc { + char *name; + u32 leader_idx; + u32 nr_members; + } *desc; + + if (readn(fd, &nr_groups, sizeof(nr_groups)) != sizeof(nr_groups)) + return -1; + + if (ph->needs_swap) + nr_groups = bswap_32(nr_groups); + + ph->env.nr_groups = nr_groups; + if (!nr_groups) { + pr_debug("group desc not available\n"); + return 0; + } + + desc = calloc(nr_groups, sizeof(*desc)); + if (!desc) + return -1; + + for (i = 0; i < nr_groups; i++) { + desc[i].name = do_read_string(fd, ph); + if (!desc[i].name) + goto out_free; + + if (readn(fd, &desc[i].leader_idx, sizeof(u32)) != sizeof(u32)) + goto out_free; + + if (readn(fd, &desc[i].nr_members, sizeof(u32)) != sizeof(u32)) + goto out_free; + + if (ph->needs_swap) { + desc[i].leader_idx = bswap_32(desc[i].leader_idx); + desc[i].nr_members = bswap_32(desc[i].nr_members); + } + } + + /* + * Rebuild group relationship based on the group_desc + */ + session = container_of(ph, struct perf_session, header); + session->evlist->nr_groups = nr_groups; + + i = nr = 0; + list_for_each_entry(evsel, &session->evlist->entries, node) { + if (evsel->idx == (int) desc[i].leader_idx) { + evsel->leader = evsel; + /* {anon_group} is a dummy name */ + if (strcmp(desc[i].name, "{anon_group}")) + evsel->group_name = desc[i].name; + evsel->nr_members = desc[i].nr_members; + + if (i >= nr_groups || nr > 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + leader = evsel; + nr = evsel->nr_members - 1; + i++; + } else if (nr) { + /* This is a group member */ + evsel->leader = leader; + + nr--; + } + } + + if (i != nr_groups || nr != 0) { + pr_debug("invalid group desc\n"); + goto out_free; + } + + ret = 0; +out_free: + while ((int) --i >= 0) + free(desc[i].name); + free(desc); + + return ret; +} + struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); @@ -1988,6 +2163,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology), FEAT_OPA(HEADER_BRANCH_STACK, branch_stack), FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), + FEAT_OPP(HEADER_GROUP_DESC, group_desc), }; struct header_print_data { @@ -2077,7 +2253,7 @@ static int perf_header__adds_write(struct perf_header *header, if (!nr_sections) return 0; - feat_sec = p = calloc(sizeof(*feat_sec), nr_sections); + feat_sec = p = calloc(nr_sections, sizeof(*feat_sec)); if (feat_sec == NULL) return -ENOMEM; @@ -2249,7 +2425,7 @@ int perf_header__process_sections(struct perf_header *header, int fd, if (!nr_sections) return 0; - feat_sec = sec = calloc(sizeof(*feat_sec), nr_sections); + feat_sec = sec = calloc(nr_sections, sizeof(*feat_sec)); if (!feat_sec) return -1; @@ -2912,16 +3088,22 @@ int perf_event__process_tracing_data(union perf_event *event, session->repipe); padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read; - if (read(session->fd, buf, padding) < 0) - die("reading input file"); + if (readn(session->fd, buf, padding) < 0) { + pr_err("%s: reading input file", __func__); + return -1; + } if (session->repipe) { int retw = write(STDOUT_FILENO, buf, padding); - if (retw <= 0 || retw != padding) - die("repiping tracing data padding"); + if (retw <= 0 || retw != padding) { + pr_err("%s: repiping tracing data padding", __func__); + return -1; + } } - if (size_read + padding != size) - die("tracing data size mismatch"); + if (size_read + padding != size) { + pr_err("%s: tracing data size mismatch", __func__); + return -1; + } perf_evlist__prepare_tracepoint_events(session->evlist, session->pevent); diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 20f0344..c9fc55c 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -29,6 +29,7 @@ enum { HEADER_NUMA_TOPOLOGY, HEADER_BRANCH_STACK, HEADER_PMU_MAPPINGS, + HEADER_GROUP_DESC, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -79,6 +80,7 @@ struct perf_session_env { char *numa_nodes; int nr_pmu_mappings; char *pmu_mappings; + int nr_groups; }; struct perf_header { diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index cb17e2a..f855941 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -4,6 +4,7 @@ #include "hist.h" #include "session.h" #include "sort.h" +#include "evsel.h" #include <math.h> static bool hists__filter_entry_by_dso(struct hists *hists, @@ -82,6 +83,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_DSO, len); } + if (h->parent) + hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen); + if (h->branch_info) { int symlen; /* @@ -242,6 +246,14 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (he->ms.map) he->ms.map->referenced = true; + + if (he->branch_info) { + if (he->branch_info->from.map) + he->branch_info->from.map->referenced = true; + if (he->branch_info->to.map) + he->branch_info->to.map->referenced = true; + } + if (symbol_conf.use_callchain) callchain_init(he->callchain); @@ -251,7 +263,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) return he; } -static void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) +void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h) { if (!h->filtered) { hists__calc_col_len(hists, h); @@ -285,7 +297,13 @@ static struct hist_entry *add_hist_entry(struct hists *hists, parent = *p; he = rb_entry(parent, struct hist_entry, rb_node_in); - cmp = hist_entry__cmp(entry, he); + /* + * Make sure that it receives arguments in a same order as + * hist_entry__collapse() so that we can use an appropriate + * function when searching an entry regardless which sort + * keys were used. + */ + cmp = hist_entry__cmp(he, entry); if (!cmp) { he_stat__add_period(&he->stat, period); @@ -523,6 +541,62 @@ void hists__collapse_resort_threaded(struct hists *hists) * reverse the map, sort on period. */ +static int period_cmp(u64 period_a, u64 period_b) +{ + if (period_a > period_b) + return 1; + if (period_a < period_b) + return -1; + return 0; +} + +static int hist_entry__sort_on_period(struct hist_entry *a, + struct hist_entry *b) +{ + int ret; + int i, nr_members; + struct perf_evsel *evsel; + struct hist_entry *pair; + u64 *periods_a, *periods_b; + + ret = period_cmp(a->stat.period, b->stat.period); + if (ret || !symbol_conf.event_group) + return ret; + + evsel = hists_to_evsel(a->hists); + nr_members = evsel->nr_members; + if (nr_members <= 1) + return ret; + + periods_a = zalloc(sizeof(periods_a) * nr_members); + periods_b = zalloc(sizeof(periods_b) * nr_members); + + if (!periods_a || !periods_b) + goto out; + + list_for_each_entry(pair, &a->pairs.head, pairs.node) { + evsel = hists_to_evsel(pair->hists); + periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period; + } + + list_for_each_entry(pair, &b->pairs.head, pairs.node) { + evsel = hists_to_evsel(pair->hists); + periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period; + } + + for (i = 1; i < nr_members; i++) { + ret = period_cmp(periods_a[i], periods_b[i]); + if (ret) + break; + } + +out: + free(periods_a); + free(periods_b); + + return ret; +} + static void __hists__insert_output_entry(struct rb_root *entries, struct hist_entry *he, u64 min_callchain_hits) @@ -539,7 +613,7 @@ static void __hists__insert_output_entry(struct rb_root *entries, parent = *p; iter = rb_entry(parent, struct hist_entry, rb_node); - if (he->stat.period > iter->stat.period) + if (hist_entry__sort_on_period(he, iter) > 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -711,25 +785,38 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) return symbol__annotate(he->ms.sym, he->ms.map, privsize); } +void events_stats__inc(struct events_stats *stats, u32 type) +{ + ++stats->nr_events[0]; + ++stats->nr_events[type]; +} + void hists__inc_nr_events(struct hists *hists, u32 type) { - ++hists->stats.nr_events[0]; - ++hists->stats.nr_events[type]; + events_stats__inc(&hists->stats, type); } static struct hist_entry *hists__add_dummy_entry(struct hists *hists, struct hist_entry *pair) { - struct rb_node **p = &hists->entries.rb_node; + struct rb_root *root; + struct rb_node **p; struct rb_node *parent = NULL; struct hist_entry *he; int cmp; + if (sort__need_collapse) + root = &hists->entries_collapsed; + else + root = hists->entries_in; + + p = &root->rb_node; + while (*p != NULL) { parent = *p; - he = rb_entry(parent, struct hist_entry, rb_node); + he = rb_entry(parent, struct hist_entry, rb_node_in); - cmp = hist_entry__cmp(pair, he); + cmp = hist_entry__collapse(he, pair); if (!cmp) goto out; @@ -744,8 +831,8 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists, if (he) { memset(&he->stat, 0, sizeof(he->stat)); he->hists = hists; - rb_link_node(&he->rb_node, parent, p); - rb_insert_color(&he->rb_node, &hists->entries); + rb_link_node(&he->rb_node_in, parent, p); + rb_insert_color(&he->rb_node_in, root); hists__inc_nr_entries(hists, he); } out: @@ -755,11 +842,16 @@ out: static struct hist_entry *hists__find_entry(struct hists *hists, struct hist_entry *he) { - struct rb_node *n = hists->entries.rb_node; + struct rb_node *n; + + if (sort__need_collapse) + n = hists->entries_collapsed.rb_node; + else + n = hists->entries_in->rb_node; while (n) { - struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node); - int64_t cmp = hist_entry__cmp(he, iter); + struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node_in); + int64_t cmp = hist_entry__collapse(iter, he); if (cmp < 0) n = n->rb_left; @@ -777,15 +869,21 @@ static struct hist_entry *hists__find_entry(struct hists *hists, */ void hists__match(struct hists *leader, struct hists *other) { + struct rb_root *root; struct rb_node *nd; struct hist_entry *pos, *pair; - for (nd = rb_first(&leader->entries); nd; nd = rb_next(nd)) { - pos = rb_entry(nd, struct hist_entry, rb_node); + if (sort__need_collapse) + root = &leader->entries_collapsed; + else + root = leader->entries_in; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); pair = hists__find_entry(other, pos); if (pair) - hist__entry_add_pair(pos, pair); + hist_entry__add_pair(pair, pos); } } @@ -796,17 +894,23 @@ void hists__match(struct hists *leader, struct hists *other) */ int hists__link(struct hists *leader, struct hists *other) { + struct rb_root *root; struct rb_node *nd; struct hist_entry *pos, *pair; - for (nd = rb_first(&other->entries); nd; nd = rb_next(nd)) { - pos = rb_entry(nd, struct hist_entry, rb_node); + if (sort__need_collapse) + root = &other->entries_collapsed; + else + root = other->entries_in; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct hist_entry, rb_node_in); if (!hist_entry__has_pairs(pos)) { pair = hists__add_dummy_entry(leader, pos); if (pair == NULL) return -1; - hist__entry_add_pair(pair, pos); + hist_entry__add_pair(pos, pair); } } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 8b091a5..3862468 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -96,8 +96,10 @@ void hists__decay_entries_threaded(struct hists *hists, bool zap_user, bool zap_kernel); void hists__output_recalc_col_len(struct hists *hists, int max_rows); +void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h); void hists__inc_nr_events(struct hists *self, u32 type); -size_t hists__fprintf_nr_events(struct hists *self, FILE *fp); +void events_stats__inc(struct events_stats *stats, u32 type); +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *self, bool show_header, int max_rows, int max_cols, FILE *fp); @@ -126,13 +128,19 @@ struct perf_hpp { }; struct perf_hpp_fmt { - bool cond; int (*header)(struct perf_hpp *hpp); int (*width)(struct perf_hpp *hpp); int (*color)(struct perf_hpp *hpp, struct hist_entry *he); int (*entry)(struct perf_hpp *hpp, struct hist_entry *he); + + struct list_head list; }; +extern struct list_head perf_hpp__list; + +#define perf_hpp__for_each_format(format) \ + list_for_each_entry(format, &perf_hpp__list, list) + extern struct perf_hpp_fmt perf_hpp__format[]; enum { @@ -148,14 +156,14 @@ enum { PERF_HPP__DELTA, PERF_HPP__RATIO, PERF_HPP__WEIGHTED_DIFF, - PERF_HPP__DISPL, PERF_HPP__FORMULA, PERF_HPP__MAX_INDEX }; void perf_hpp__init(void); -void perf_hpp__column_enable(unsigned col, bool enable); +void perf_hpp__column_register(struct perf_hpp_fmt *format); +void perf_hpp__column_enable(unsigned col); int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he, bool color); @@ -219,8 +227,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused, unsigned int hists__sort_list_width(struct hists *self); -double perf_diff__compute_delta(struct hist_entry *he); -double perf_diff__compute_ratio(struct hist_entry *he); -s64 perf_diff__compute_wdiff(struct hist_entry *he); -int perf_diff__formula(char *buf, size_t size, struct hist_entry *he); +double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair); +double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair); +s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair); +int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, + char *buf, size_t size); +double perf_diff__period_percent(struct hist_entry *he, u64 period); #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index a55d8cf..45cf10a 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -14,6 +14,7 @@ #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) #define for_each_set_bit(bit, addr, size) \ for ((bit) = find_first_bit((addr), (size)); \ diff --git a/tools/perf/util/intlist.c b/tools/perf/util/intlist.c index 9d07400..11a8d86 100644 --- a/tools/perf/util/intlist.c +++ b/tools/perf/util/intlist.c @@ -59,16 +59,40 @@ void intlist__remove(struct intlist *ilist, struct int_node *node) struct int_node *intlist__find(struct intlist *ilist, int i) { - struct int_node *node = NULL; - struct rb_node *rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); + struct int_node *node; + struct rb_node *rb_node; + if (ilist == NULL) + return NULL; + + node = NULL; + rb_node = rblist__find(&ilist->rblist, (void *)((long)i)); if (rb_node) node = container_of(rb_node, struct int_node, rb_node); return node; } -struct intlist *intlist__new(void) +static int intlist__parse_list(struct intlist *ilist, const char *s) +{ + char *sep; + int err; + + do { + long value = strtol(s, &sep, 10); + err = -EINVAL; + if (*sep != ',' && *sep != '\0') + break; + err = intlist__add(ilist, value); + if (err) + break; + s = sep + 1; + } while (*sep != '\0'); + + return err; +} + +struct intlist *intlist__new(const char *slist) { struct intlist *ilist = malloc(sizeof(*ilist)); @@ -77,9 +101,15 @@ struct intlist *intlist__new(void) ilist->rblist.node_cmp = intlist__node_cmp; ilist->rblist.node_new = intlist__node_new; ilist->rblist.node_delete = intlist__node_delete; + + if (slist && intlist__parse_list(ilist, slist)) + goto out_delete; } return ilist; +out_delete: + intlist__delete(ilist); + return NULL; } void intlist__delete(struct intlist *ilist) diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index 6d63ab9..62351da 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -15,7 +15,7 @@ struct intlist { struct rblist rblist; }; -struct intlist *intlist__new(void); +struct intlist *intlist__new(const char *slist); void intlist__delete(struct intlist *ilist); void intlist__remove(struct intlist *ilist, struct int_node *in); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1f09d05..efdb38e 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1,10 +1,15 @@ +#include "callchain.h" #include "debug.h" #include "event.h" +#include "evsel.h" +#include "hist.h" #include "machine.h" #include "map.h" +#include "sort.h" #include "strlist.h" #include "thread.h" #include <stdbool.h> +#include "unwind.h" int machine__init(struct machine *machine, const char *root_dir, pid_t pid) { @@ -48,6 +53,29 @@ static void dsos__delete(struct list_head *dsos) } } +void machine__delete_dead_threads(struct machine *machine) +{ + struct thread *n, *t; + + list_for_each_entry_safe(t, n, &machine->dead_threads, node) { + list_del(&t->node); + thread__delete(t); + } +} + +void machine__delete_threads(struct machine *machine) +{ + struct rb_node *nd = rb_first(&machine->threads); + + while (nd) { + struct thread *t = rb_entry(nd, struct thread, rb_node); + + rb_erase(&t->rb_node, &machine->threads); + nd = rb_next(nd); + thread__delete(t); + } +} + void machine__exit(struct machine *machine) { map_groups__exit(&machine->kmaps); @@ -63,10 +91,22 @@ void machine__delete(struct machine *machine) free(machine); } -struct machine *machines__add(struct rb_root *machines, pid_t pid, +void machines__init(struct machines *machines) +{ + machine__init(&machines->host, "", HOST_KERNEL_ID); + machines->guests = RB_ROOT; +} + +void machines__exit(struct machines *machines) +{ + machine__exit(&machines->host); + /* XXX exit guest */ +} + +struct machine *machines__add(struct machines *machines, pid_t pid, const char *root_dir) { - struct rb_node **p = &machines->rb_node; + struct rb_node **p = &machines->guests.rb_node; struct rb_node *parent = NULL; struct machine *pos, *machine = malloc(sizeof(*machine)); @@ -88,18 +128,21 @@ struct machine *machines__add(struct rb_root *machines, pid_t pid, } rb_link_node(&machine->rb_node, parent, p); - rb_insert_color(&machine->rb_node, machines); + rb_insert_color(&machine->rb_node, &machines->guests); return machine; } -struct machine *machines__find(struct rb_root *machines, pid_t pid) +struct machine *machines__find(struct machines *machines, pid_t pid) { - struct rb_node **p = &machines->rb_node; + struct rb_node **p = &machines->guests.rb_node; struct rb_node *parent = NULL; struct machine *machine; struct machine *default_machine = NULL; + if (pid == HOST_KERNEL_ID) + return &machines->host; + while (*p != NULL) { parent = *p; machine = rb_entry(parent, struct machine, rb_node); @@ -116,7 +159,7 @@ struct machine *machines__find(struct rb_root *machines, pid_t pid) return default_machine; } -struct machine *machines__findnew(struct rb_root *machines, pid_t pid) +struct machine *machines__findnew(struct machines *machines, pid_t pid) { char path[PATH_MAX]; const char *root_dir = ""; @@ -150,12 +193,12 @@ out: return machine; } -void machines__process(struct rb_root *machines, - machine__process_t process, void *data) +void machines__process_guests(struct machines *machines, + machine__process_t process, void *data) { struct rb_node *nd; - for (nd = rb_first(machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); process(pos, data); } @@ -175,12 +218,14 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size) return bf; } -void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size) +void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size) { struct rb_node *node; struct machine *machine; - for (node = rb_first(machines); node; node = rb_next(node)) { + machines->host.id_hdr_size = id_hdr_size; + + for (node = rb_first(&machines->guests); node; node = rb_next(node)) { machine = rb_entry(node, struct machine, rb_node); machine->id_hdr_size = id_hdr_size; } @@ -264,6 +309,537 @@ int machine__process_lost_event(struct machine *machine __maybe_unused, return 0; } +struct map *machine__new_module(struct machine *machine, u64 start, + const char *filename) +{ + struct map *map; + struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); + + if (dso == NULL) + return NULL; + + map = map__new2(start, dso, MAP__FUNCTION); + if (map == NULL) + return NULL; + + if (machine__is_host(machine)) + dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; + else + dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; + map_groups__insert(&machine->kmaps, map); + return map; +} + +size_t machines__fprintf_dsos(struct machines *machines, FILE *fp) +{ + struct rb_node *nd; + size_t ret = __dsos__fprintf(&machines->host.kernel_dsos, fp) + + __dsos__fprintf(&machines->host.user_dsos, fp); + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret += __dsos__fprintf(&pos->kernel_dsos, fp); + ret += __dsos__fprintf(&pos->user_dsos, fp); + } + + return ret; +} + +size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, skip, parm) + + __dsos__fprintf_buildid(&machine->user_dsos, fp, skip, parm); +} + +size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm) +{ + struct rb_node *nd; + size_t ret = machine__fprintf_dsos_buildid(&machines->host, fp, skip, parm); + + for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); + ret += machine__fprintf_dsos_buildid(pos, fp, skip, parm); + } + return ret; +} + +size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) +{ + int i; + size_t printed = 0; + struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso; + + if (kdso->has_build_id) { + char filename[PATH_MAX]; + if (dso__build_id_filename(kdso, filename, sizeof(filename))) + printed += fprintf(fp, "[0] %s\n", filename); + } + + for (i = 0; i < vmlinux_path__nr_entries; ++i) + printed += fprintf(fp, "[%d] %s\n", + i + kdso->has_build_id, vmlinux_path[i]); + + return printed; +} + +size_t machine__fprintf(struct machine *machine, FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + + for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { + struct thread *pos = rb_entry(nd, struct thread, rb_node); + + ret += thread__fprintf(pos, fp); + } + + return ret; +} + +static struct dso *machine__get_kernel(struct machine *machine) +{ + const char *vmlinux_name = NULL; + struct dso *kernel; + + if (machine__is_host(machine)) { + vmlinux_name = symbol_conf.vmlinux_name; + if (!vmlinux_name) + vmlinux_name = "[kernel.kallsyms]"; + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[kernel]", + DSO_TYPE_KERNEL); + } else { + char bf[PATH_MAX]; + + if (machine__is_default_guest(machine)) + vmlinux_name = symbol_conf.default_guest_vmlinux_name; + if (!vmlinux_name) + vmlinux_name = machine__mmap_name(machine, bf, + sizeof(bf)); + + kernel = dso__kernel_findnew(machine, vmlinux_name, + "[guest.kernel]", + DSO_TYPE_GUEST_KERNEL); + } + + if (kernel != NULL && (!kernel->has_build_id)) + dso__read_running_kernel_build_id(kernel, machine); + + return kernel; +} + +struct process_args { + u64 start; +}; + +static int symbol__in_kernel(void *arg, const char *name, + char type __maybe_unused, u64 start) +{ + struct process_args *args = arg; + + if (strchr(name, '[')) + return 0; + + args->start = start; + return 1; +} + +/* Figure out the start address of kernel map from /proc/kallsyms */ +static u64 machine__get_kernel_start_addr(struct machine *machine) +{ + const char *filename; + char path[PATH_MAX]; + struct process_args args; + + if (machine__is_host(machine)) { + filename = "/proc/kallsyms"; + } else { + if (machine__is_default_guest(machine)) + filename = (char *)symbol_conf.default_guest_kallsyms; + else { + sprintf(path, "%s/proc/kallsyms", machine->root_dir); + filename = path; + } + } + + if (symbol__restricted_filename(filename, "/proc/kallsyms")) + return 0; + + if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0) + return 0; + + return args.start; +} + +int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) +{ + enum map_type type; + u64 start = machine__get_kernel_start_addr(machine); + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + machine->vmlinux_maps[type] = map__new2(start, kernel, type); + if (machine->vmlinux_maps[type] == NULL) + return -1; + + machine->vmlinux_maps[type]->map_ip = + machine->vmlinux_maps[type]->unmap_ip = + identity__map_ip; + kmap = map__kmap(machine->vmlinux_maps[type]); + kmap->kmaps = &machine->kmaps; + map_groups__insert(&machine->kmaps, + machine->vmlinux_maps[type]); + } + + return 0; +} + +void machine__destroy_kernel_maps(struct machine *machine) +{ + enum map_type type; + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + if (machine->vmlinux_maps[type] == NULL) + continue; + + kmap = map__kmap(machine->vmlinux_maps[type]); + map_groups__remove(&machine->kmaps, + machine->vmlinux_maps[type]); + if (kmap->ref_reloc_sym) { + /* + * ref_reloc_sym is shared among all maps, so free just + * on one of them. + */ + if (type == MAP__FUNCTION) { + free((char *)kmap->ref_reloc_sym->name); + kmap->ref_reloc_sym->name = NULL; + free(kmap->ref_reloc_sym); + } + kmap->ref_reloc_sym = NULL; + } + + map__delete(machine->vmlinux_maps[type]); + machine->vmlinux_maps[type] = NULL; + } +} + +int machines__create_guest_kernel_maps(struct machines *machines) +{ + int ret = 0; + struct dirent **namelist = NULL; + int i, items = 0; + char path[PATH_MAX]; + pid_t pid; + char *endp; + + if (symbol_conf.default_guest_vmlinux_name || + symbol_conf.default_guest_modules || + symbol_conf.default_guest_kallsyms) { + machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID); + } + + if (symbol_conf.guestmount) { + items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); + if (items <= 0) + return -ENOENT; + for (i = 0; i < items; i++) { + if (!isdigit(namelist[i]->d_name[0])) { + /* Filter out . and .. */ + continue; + } + pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10); + if ((*endp != '\0') || + (endp == namelist[i]->d_name) || + (errno == ERANGE)) { + pr_debug("invalid directory (%s). Skipping.\n", + namelist[i]->d_name); + continue; + } + sprintf(path, "%s/%s/proc/kallsyms", + symbol_conf.guestmount, + namelist[i]->d_name); + ret = access(path, R_OK); + if (ret) { + pr_debug("Can't access file %s\n", path); + goto failure; + } + machines__create_kernel_maps(machines, pid); + } +failure: + free(namelist); + } + + return ret; +} + +void machines__destroy_kernel_maps(struct machines *machines) +{ + struct rb_node *next = rb_first(&machines->guests); + + machine__destroy_kernel_maps(&machines->host); + + while (next) { + struct machine *pos = rb_entry(next, struct machine, rb_node); + + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, &machines->guests); + machine__delete(pos); + } +} + +int machines__create_kernel_maps(struct machines *machines, pid_t pid) +{ + struct machine *machine = machines__findnew(machines, pid); + + if (machine == NULL) + return -1; + + return machine__create_kernel_maps(machine); +} + +int machine__load_kallsyms(struct machine *machine, const char *filename, + enum map_type type, symbol_filter_t filter) +{ + struct map *map = machine->vmlinux_maps[type]; + int ret = dso__load_kallsyms(map->dso, filename, map, filter); + + if (ret > 0) { + dso__set_loaded(map->dso, type); + /* + * Since /proc/kallsyms will have multiple sessions for the + * kernel, with modules between them, fixup the end of all + * sections. + */ + __map_groups__fixup_end(&machine->kmaps, type); + } + + return ret; +} + +int machine__load_vmlinux_path(struct machine *machine, enum map_type type, + symbol_filter_t filter) +{ + struct map *map = machine->vmlinux_maps[type]; + int ret = dso__load_vmlinux_path(map->dso, map, filter); + + if (ret > 0) { + dso__set_loaded(map->dso, type); + map__reloc_vmlinux(map); + } + + return ret; +} + +static void map_groups__fixup_end(struct map_groups *mg) +{ + int i; + for (i = 0; i < MAP__NR_TYPES; ++i) + __map_groups__fixup_end(mg, i); +} + +static char *get_kernel_version(const char *root_dir) +{ + char version[PATH_MAX]; + FILE *file; + char *name, *tmp; + const char *prefix = "Linux version "; + + sprintf(version, "%s/proc/version", root_dir); + file = fopen(version, "r"); + if (!file) + return NULL; + + version[0] = '\0'; + tmp = fgets(version, sizeof(version), file); + fclose(file); + + name = strstr(version, prefix); + if (!name) + return NULL; + name += strlen(prefix); + tmp = strchr(name, ' '); + if (tmp) + *tmp = '\0'; + + return strdup(name); +} + +static int map_groups__set_modules_path_dir(struct map_groups *mg, + const char *dir_name) +{ + struct dirent *dent; + DIR *dir = opendir(dir_name); + int ret = 0; + + if (!dir) { + pr_debug("%s: cannot open %s dir\n", __func__, dir_name); + return -1; + } + + while ((dent = readdir(dir)) != NULL) { + char path[PATH_MAX]; + struct stat st; + + /*sshfs might return bad dent->d_type, so we have to stat*/ + snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); + if (stat(path, &st)) + continue; + + if (S_ISDIR(st.st_mode)) { + if (!strcmp(dent->d_name, ".") || + !strcmp(dent->d_name, "..")) + continue; + + ret = map_groups__set_modules_path_dir(mg, path); + if (ret < 0) + goto out; + } else { + char *dot = strrchr(dent->d_name, '.'), + dso_name[PATH_MAX]; + struct map *map; + char *long_name; + + if (dot == NULL || strcmp(dot, ".ko")) + continue; + snprintf(dso_name, sizeof(dso_name), "[%.*s]", + (int)(dot - dent->d_name), dent->d_name); + + strxfrchar(dso_name, '-', '_'); + map = map_groups__find_by_name(mg, MAP__FUNCTION, + dso_name); + if (map == NULL) + continue; + + long_name = strdup(path); + if (long_name == NULL) { + ret = -1; + goto out; + } + dso__set_long_name(map->dso, long_name); + map->dso->lname_alloc = 1; + dso__kernel_module_get_build_id(map->dso, ""); + } + } + +out: + closedir(dir); + return ret; +} + +static int machine__set_modules_path(struct machine *machine) +{ + char *version; + char modules_path[PATH_MAX]; + + version = get_kernel_version(machine->root_dir); + if (!version) + return -1; + + snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", + machine->root_dir, version); + free(version); + + return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); +} + +static int machine__create_modules(struct machine *machine) +{ + char *line = NULL; + size_t n; + FILE *file; + struct map *map; + const char *modules; + char path[PATH_MAX]; + + if (machine__is_default_guest(machine)) + modules = symbol_conf.default_guest_modules; + else { + sprintf(path, "%s/proc/modules", machine->root_dir); + modules = path; + } + + if (symbol__restricted_filename(path, "/proc/modules")) + return -1; + + file = fopen(modules, "r"); + if (file == NULL) + return -1; + + while (!feof(file)) { + char name[PATH_MAX]; + u64 start; + char *sep; + int line_len; + + line_len = getline(&line, &n, file); + if (line_len < 0) + break; + + if (!line) + goto out_failure; + + line[--line_len] = '\0'; /* \n */ + + sep = strrchr(line, 'x'); + if (sep == NULL) + continue; + + hex2u64(sep + 1, &start); + + sep = strchr(line, ' '); + if (sep == NULL) + continue; + + *sep = '\0'; + + snprintf(name, sizeof(name), "[%s]", line); + map = machine__new_module(machine, start, name); + if (map == NULL) + goto out_delete_line; + dso__kernel_module_get_build_id(map->dso, machine->root_dir); + } + + free(line); + fclose(file); + + return machine__set_modules_path(machine); + +out_delete_line: + free(line); +out_failure: + return -1; +} + +int machine__create_kernel_maps(struct machine *machine) +{ + struct dso *kernel = machine__get_kernel(machine); + + if (kernel == NULL || + __machine__create_kernel_maps(machine, kernel) < 0) + return -1; + + if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { + if (machine__is_host(machine)) + pr_debug("Problems creating module maps, " + "continuing anyway...\n"); + else + pr_debug("Problems creating module maps for guest %d, " + "continuing anyway...\n", machine->pid); + } + + /* + * Now that we have all the maps created, just set the ->end of them: + */ + map_groups__fixup_end(&machine->kmaps); + return 0; +} + static void machine__set_kernel_mmap_len(struct machine *machine, union perf_event *event) { @@ -462,3 +1038,189 @@ int machine__process_event(struct machine *machine, union perf_event *event) return ret; } + +void machine__remove_thread(struct machine *machine, struct thread *th) +{ + machine->last_match = NULL; + rb_erase(&th->rb_node, &machine->threads); + /* + * We may have references to this thread, for instance in some hist_entry + * instances, so just move them to a separate list. + */ + list_add_tail(&th->node, &machine->dead_threads); +} + +static bool symbol__match_parent_regex(struct symbol *sym) +{ + if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) + return 1; + + return 0; +} + +static const u8 cpumodes[] = { + PERF_RECORD_MISC_USER, + PERF_RECORD_MISC_KERNEL, + PERF_RECORD_MISC_GUEST_USER, + PERF_RECORD_MISC_GUEST_KERNEL +}; +#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) + +static void ip__resolve_ams(struct machine *machine, struct thread *thread, + struct addr_map_symbol *ams, + u64 ip) +{ + struct addr_location al; + size_t i; + u8 m; + + memset(&al, 0, sizeof(al)); + + for (i = 0; i < NCPUMODES; i++) { + m = cpumodes[i]; + /* + * We cannot use the header.misc hint to determine whether a + * branch stack address is user, kernel, guest, hypervisor. + * Branches may straddle the kernel/user/hypervisor boundaries. + * Thus, we have to try consecutively until we find a match + * or else, the symbol is unknown + */ + thread__find_addr_location(thread, machine, m, MAP__FUNCTION, + ip, &al, NULL); + if (al.sym) + goto found; + } +found: + ams->addr = ip; + ams->al_addr = al.addr; + ams->sym = al.sym; + ams->map = al.map; +} + +struct branch_info *machine__resolve_bstack(struct machine *machine, + struct thread *thr, + struct branch_stack *bs) +{ + struct branch_info *bi; + unsigned int i; + + bi = calloc(bs->nr, sizeof(struct branch_info)); + if (!bi) + return NULL; + + for (i = 0; i < bs->nr; i++) { + ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to); + ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from); + bi[i].flags = bs->entries[i].flags; + } + return bi; +} + +static int machine__resolve_callchain_sample(struct machine *machine, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) + +{ + u8 cpumode = PERF_RECORD_MISC_USER; + unsigned int i; + int err; + + callchain_cursor_reset(&callchain_cursor); + + if (chain->nr > PERF_MAX_STACK_DEPTH) { + pr_warning("corrupted callchain. skipping...\n"); + return 0; + } + + for (i = 0; i < chain->nr; i++) { + u64 ip; + struct addr_location al; + + if (callchain_param.order == ORDER_CALLEE) + ip = chain->ips[i]; + else + ip = chain->ips[chain->nr - i - 1]; + + if (ip >= PERF_CONTEXT_MAX) { + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; + break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; + break; + default: + pr_debug("invalid callchain context: " + "%"PRId64"\n", (s64) ip); + /* + * It seems the callchain is corrupted. + * Discard all. + */ + callchain_cursor_reset(&callchain_cursor); + return 0; + } + continue; + } + + al.filtered = false; + thread__find_addr_location(thread, machine, cpumode, + MAP__FUNCTION, ip, &al, NULL); + if (al.sym != NULL) { + if (sort__has_parent && !*parent && + symbol__match_parent_regex(al.sym)) + *parent = al.sym; + if (!symbol_conf.use_callchain) + break; + } + + err = callchain_cursor_append(&callchain_cursor, + ip, al.map, al.sym); + if (err) + return err; + } + + return 0; +} + +static int unwind_entry(struct unwind_entry *entry, void *arg) +{ + struct callchain_cursor *cursor = arg; + return callchain_cursor_append(cursor, entry->ip, + entry->map, entry->sym); +} + +int machine__resolve_callchain(struct machine *machine, + struct perf_evsel *evsel, + struct thread *thread, + struct perf_sample *sample, + struct symbol **parent) + +{ + int ret; + + callchain_cursor_reset(&callchain_cursor); + + ret = machine__resolve_callchain_sample(machine, thread, + sample->callchain, parent); + if (ret) + return ret; + + /* Can we do dwarf post unwind? */ + if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && + (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) + return 0; + + /* Bail out if nothing was captured. */ + if ((!sample->user_regs.regs) || + (!sample->user_stack.size)) + return 0; + + return unwind__get_entries(unwind_entry, &callchain_cursor, machine, + thread, evsel->attr.sample_regs_user, + sample); + +} diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index b7cde74..5ac5892 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -47,23 +47,32 @@ int machine__process_event(struct machine *machine, union perf_event *event); typedef void (*machine__process_t)(struct machine *machine, void *data); -void machines__process(struct rb_root *machines, - machine__process_t process, void *data); +struct machines { + struct machine host; + struct rb_root guests; +}; + +void machines__init(struct machines *machines); +void machines__exit(struct machines *machines); -struct machine *machines__add(struct rb_root *machines, pid_t pid, +void machines__process_guests(struct machines *machines, + machine__process_t process, void *data); + +struct machine *machines__add(struct machines *machines, pid_t pid, const char *root_dir); -struct machine *machines__find_host(struct rb_root *machines); -struct machine *machines__find(struct rb_root *machines, pid_t pid); -struct machine *machines__findnew(struct rb_root *machines, pid_t pid); +struct machine *machines__find_host(struct machines *machines); +struct machine *machines__find(struct machines *machines, pid_t pid); +struct machine *machines__findnew(struct machines *machines, pid_t pid); -void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size); +void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size); char *machine__mmap_name(struct machine *machine, char *bf, size_t size); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); +void machine__delete_dead_threads(struct machine *machine); +void machine__delete_threads(struct machine *machine); void machine__delete(struct machine *machine); - struct branch_info *machine__resolve_bstack(struct machine *machine, struct thread *thread, struct branch_stack *bs); @@ -129,19 +138,19 @@ int machine__load_kallsyms(struct machine *machine, const char *filename, int machine__load_vmlinux_path(struct machine *machine, enum map_type type, symbol_filter_t filter); -size_t machine__fprintf_dsos_buildid(struct machine *machine, - FILE *fp, bool with_hits); -size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp); -size_t machines__fprintf_dsos_buildid(struct rb_root *machines, - FILE *fp, bool with_hits); +size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); +size_t machines__fprintf_dsos(struct machines *machines, FILE *fp); +size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp, + bool (skip)(struct dso *dso, int parm), int parm); void machine__destroy_kernel_maps(struct machine *machine); int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel); int machine__create_kernel_maps(struct machine *machine); -int machines__create_kernel_maps(struct rb_root *machines, pid_t pid); -int machines__create_guest_kernel_maps(struct rb_root *machines); -void machines__destroy_guest_kernel_maps(struct rb_root *machines); +int machines__create_kernel_maps(struct machines *machines, pid_t pid); +int machines__create_guest_kernel_maps(struct machines *machines); +void machines__destroy_kernel_maps(struct machines *machines); size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 0328d45..6fcb9de 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -11,6 +11,7 @@ #include "strlist.h" #include "vdso.h" #include "build-id.h" +#include <linux/string.h> const char *map_type__name[MAP__NR_TYPES] = { [MAP__FUNCTION] = "Functions", @@ -19,7 +20,8 @@ const char *map_type__name[MAP__NR_TYPES] = { static inline int is_anon_memory(const char *filename) { - return strcmp(filename, "//anon") == 0; + return !strcmp(filename, "//anon") || + !strcmp(filename, "/anon_hugepage (deleted)"); } static inline int is_no_dso_memory(const char *filename) @@ -28,29 +30,29 @@ static inline int is_no_dso_memory(const char *filename) !strcmp(filename, "[heap]"); } -void map__init(struct map *self, enum map_type type, +void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { - self->type = type; - self->start = start; - self->end = end; - self->pgoff = pgoff; - self->dso = dso; - self->map_ip = map__map_ip; - self->unmap_ip = map__unmap_ip; - RB_CLEAR_NODE(&self->rb_node); - self->groups = NULL; - self->referenced = false; - self->erange_warned = false; + map->type = type; + map->start = start; + map->end = end; + map->pgoff = pgoff; + map->dso = dso; + map->map_ip = map__map_ip; + map->unmap_ip = map__unmap_ip; + RB_CLEAR_NODE(&map->rb_node); + map->groups = NULL; + map->referenced = false; + map->erange_warned = false; } struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, enum map_type type) { - struct map *self = malloc(sizeof(*self)); + struct map *map = malloc(sizeof(*map)); - if (self != NULL) { + if (map != NULL) { char newfilename[PATH_MAX]; struct dso *dso; int anon, no_dso, vdso; @@ -73,10 +75,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, if (dso == NULL) goto out_delete; - map__init(self, type, start, start + len, pgoff, dso); + map__init(map, type, start, start + len, pgoff, dso); if (anon || no_dso) { - self->map_ip = self->unmap_ip = identity__map_ip; + map->map_ip = map->unmap_ip = identity__map_ip; /* * Set memory without DSO as loaded. All map__find_* @@ -84,12 +86,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, * unnecessary map__load warning. */ if (no_dso) - dso__set_loaded(dso, self->type); + dso__set_loaded(dso, map->type); } } - return self; + return map; out_delete: - free(self); + free(map); return NULL; } @@ -112,48 +114,48 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type) return map; } -void map__delete(struct map *self) +void map__delete(struct map *map) { - free(self); + free(map); } -void map__fixup_start(struct map *self) +void map__fixup_start(struct map *map) { - struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_root *symbols = &map->dso->symbols[map->type]; struct rb_node *nd = rb_first(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - self->start = sym->start; + map->start = sym->start; } } -void map__fixup_end(struct map *self) +void map__fixup_end(struct map *map) { - struct rb_root *symbols = &self->dso->symbols[self->type]; + struct rb_root *symbols = &map->dso->symbols[map->type]; struct rb_node *nd = rb_last(symbols); if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - self->end = sym->end; + map->end = sym->end; } } #define DSO__DELETED "(deleted)" -int map__load(struct map *self, symbol_filter_t filter) +int map__load(struct map *map, symbol_filter_t filter) { - const char *name = self->dso->long_name; + const char *name = map->dso->long_name; int nr; - if (dso__loaded(self->dso, self->type)) + if (dso__loaded(map->dso, map->type)) return 0; - nr = dso__load(self->dso, self, filter); + nr = dso__load(map->dso, map, filter); if (nr < 0) { - if (self->dso->has_build_id) { + if (map->dso->has_build_id) { char sbuild_id[BUILD_ID_SIZE * 2 + 1]; - build_id__sprintf(self->dso->build_id, - sizeof(self->dso->build_id), + build_id__sprintf(map->dso->build_id, + sizeof(map->dso->build_id), sbuild_id); pr_warning("%s with build id %s not found", name, sbuild_id); @@ -183,43 +185,36 @@ int map__load(struct map *self, symbol_filter_t filter) * Only applies to the kernel, as its symtabs aren't relative like the * module ones. */ - if (self->dso->kernel) - map__reloc_vmlinux(self); + if (map->dso->kernel) + map__reloc_vmlinux(map); return 0; } -struct symbol *map__find_symbol(struct map *self, u64 addr, +struct symbol *map__find_symbol(struct map *map, u64 addr, symbol_filter_t filter) { - if (map__load(self, filter) < 0) + if (map__load(map, filter) < 0) return NULL; - return dso__find_symbol(self->dso, self->type, addr); + return dso__find_symbol(map->dso, map->type, addr); } -struct symbol *map__find_symbol_by_name(struct map *self, const char *name, +struct symbol *map__find_symbol_by_name(struct map *map, const char *name, symbol_filter_t filter) { - if (map__load(self, filter) < 0) + if (map__load(map, filter) < 0) return NULL; - if (!dso__sorted_by_name(self->dso, self->type)) - dso__sort_by_name(self->dso, self->type); + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); - return dso__find_symbol_by_name(self->dso, self->type, name); + return dso__find_symbol_by_name(map->dso, map->type, name); } -struct map *map__clone(struct map *self) +struct map *map__clone(struct map *map) { - struct map *map = malloc(sizeof(*self)); - - if (!map) - return NULL; - - memcpy(map, self, sizeof(*self)); - - return map; + return memdup(map, sizeof(*map)); } int map__overlap(struct map *l, struct map *r) @@ -236,10 +231,10 @@ int map__overlap(struct map *l, struct map *r) return 0; } -size_t map__fprintf(struct map *self, FILE *fp) +size_t map__fprintf(struct map *map, FILE *fp) { return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", - self->start, self->end, self->pgoff, self->dso->name); + map->start, map->end, map->pgoff, map->dso->name); } size_t map__fprintf_dsoname(struct map *map, FILE *fp) @@ -527,9 +522,9 @@ static u64 map__reloc_unmap_ip(struct map *map, u64 ip) return ip - (s64)map->pgoff; } -void map__reloc_vmlinux(struct map *self) +void map__reloc_vmlinux(struct map *map) { - struct kmap *kmap = map__kmap(self); + struct kmap *kmap = map__kmap(map); s64 reloc; if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr) @@ -541,9 +536,9 @@ void map__reloc_vmlinux(struct map *self) if (!reloc) return; - self->map_ip = map__reloc_map_ip; - self->unmap_ip = map__reloc_unmap_ip; - self->pgoff = reloc; + map->map_ip = map__reloc_map_ip; + map->unmap_ip = map__reloc_unmap_ip; + map->pgoff = reloc; } void maps__insert(struct rb_root *maps, struct map *map) @@ -566,9 +561,9 @@ void maps__insert(struct rb_root *maps, struct map *map) rb_insert_color(&map->rb_node, maps); } -void maps__remove(struct rb_root *self, struct map *map) +void maps__remove(struct rb_root *maps, struct map *map) { - rb_erase(&map->rb_node, self); + rb_erase(&map->rb_node, maps); } struct map *maps__find(struct rb_root *maps, u64 ip) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index bcb39e2..a887f2c 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -57,9 +57,9 @@ struct map_groups { struct machine *machine; }; -static inline struct kmap *map__kmap(struct map *self) +static inline struct kmap *map__kmap(struct map *map) { - return (struct kmap *)(self + 1); + return (struct kmap *)(map + 1); } static inline u64 map__map_ip(struct map *map, u64 ip) @@ -85,27 +85,27 @@ struct symbol; typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym); -void map__init(struct map *self, enum map_type type, +void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, enum map_type type); struct map *map__new2(u64 start, struct dso *dso, enum map_type type); -void map__delete(struct map *self); -struct map *map__clone(struct map *self); +void map__delete(struct map *map); +struct map *map__clone(struct map *map); int map__overlap(struct map *l, struct map *r); -size_t map__fprintf(struct map *self, FILE *fp); +size_t map__fprintf(struct map *map, FILE *fp); size_t map__fprintf_dsoname(struct map *map, FILE *fp); -int map__load(struct map *self, symbol_filter_t filter); -struct symbol *map__find_symbol(struct map *self, +int map__load(struct map *map, symbol_filter_t filter); +struct symbol *map__find_symbol(struct map *map, u64 addr, symbol_filter_t filter); -struct symbol *map__find_symbol_by_name(struct map *self, const char *name, +struct symbol *map__find_symbol_by_name(struct map *map, const char *name, symbol_filter_t filter); -void map__fixup_start(struct map *self); -void map__fixup_end(struct map *self); +void map__fixup_start(struct map *map); +void map__fixup_end(struct map *map); -void map__reloc_vmlinux(struct map *self); +void map__reloc_vmlinux(struct map *map); size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type, int verbose, FILE *fp); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 2d8d53be..c84f48c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -380,8 +380,8 @@ static int add_tracepoint(struct list_head **listp, int *idx, return 0; } -static int add_tracepoint_multi(struct list_head **list, int *idx, - char *sys_name, char *evt_name) +static int add_tracepoint_multi_event(struct list_head **list, int *idx, + char *sys_name, char *evt_name) { char evt_path[MAXPATHLEN]; struct dirent *evt_ent; @@ -408,6 +408,47 @@ static int add_tracepoint_multi(struct list_head **list, int *idx, ret = add_tracepoint(list, idx, sys_name, evt_ent->d_name); } + closedir(evt_dir); + return ret; +} + +static int add_tracepoint_event(struct list_head **list, int *idx, + char *sys_name, char *evt_name) +{ + return strpbrk(evt_name, "*?") ? + add_tracepoint_multi_event(list, idx, sys_name, evt_name) : + add_tracepoint(list, idx, sys_name, evt_name); +} + +static int add_tracepoint_multi_sys(struct list_head **list, int *idx, + char *sys_name, char *evt_name) +{ + struct dirent *events_ent; + DIR *events_dir; + int ret = 0; + + events_dir = opendir(tracing_events_path); + if (!events_dir) { + perror("Can't open event dir"); + return -1; + } + + while (!ret && (events_ent = readdir(events_dir))) { + if (!strcmp(events_ent->d_name, ".") + || !strcmp(events_ent->d_name, "..") + || !strcmp(events_ent->d_name, "enable") + || !strcmp(events_ent->d_name, "header_event") + || !strcmp(events_ent->d_name, "header_page")) + continue; + + if (!strglobmatch(events_ent->d_name, sys_name)) + continue; + + ret = add_tracepoint_event(list, idx, events_ent->d_name, + evt_name); + } + + closedir(events_dir); return ret; } @@ -420,9 +461,10 @@ int parse_events_add_tracepoint(struct list_head **list, int *idx, if (ret) return ret; - return strpbrk(event, "*?") ? - add_tracepoint_multi(list, idx, sys, event) : - add_tracepoint(list, idx, sys, event); + if (strpbrk(sys, "*?")) + return add_tracepoint_multi_sys(list, idx, sys, event); + else + return add_tracepoint_event(list, idx, sys, event); } static int @@ -492,7 +534,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, } static int config_term(struct perf_event_attr *attr, - struct parse_events__term *term) + struct parse_events_term *term) { #define CHECK_TYPE_VAL(type) \ do { \ @@ -537,7 +579,7 @@ do { \ static int config_attr(struct perf_event_attr *attr, struct list_head *head, int fail) { - struct parse_events__term *term; + struct parse_events_term *term; list_for_each_entry(term, head, list) if (config_term(attr, term) && fail) @@ -563,14 +605,14 @@ int parse_events_add_numeric(struct list_head **list, int *idx, return add_event(list, idx, &attr, NULL); } -static int parse_events__is_name_term(struct parse_events__term *term) +static int parse_events__is_name_term(struct parse_events_term *term) { return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; } static char *pmu_event_name(struct list_head *head_terms) { - struct parse_events__term *term; + struct parse_events_term *term; list_for_each_entry(term, head_terms, list) if (parse_events__is_name_term(term)) @@ -657,14 +699,6 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; - /* - * We are here for group and 'GH' was not set as event - * modifier and whatever event/group modifier override - * default 'GH' setup. - */ - if (evsel && !exclude_GH) - eH = eG = 0; - memset(mod, 0, sizeof(*mod)); while (*str) { @@ -814,7 +848,7 @@ static int parse_events__scanner(const char *str, void *data, int start_token) */ int parse_events_terms(struct list_head *terms, const char *str) { - struct parse_events_data__terms data = { + struct parse_events_terms data = { .terms = NULL, }; int ret; @@ -830,10 +864,9 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } -int parse_events(struct perf_evlist *evlist, const char *str, - int unset __maybe_unused) +int parse_events(struct perf_evlist *evlist, const char *str) { - struct parse_events_data__events data = { + struct parse_events_evlist data = { .list = LIST_HEAD_INIT(data.list), .idx = evlist->nr_entries, }; @@ -843,6 +876,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, if (!ret) { int entries = data.idx - evlist->nr_entries; perf_evlist__splice_list_tail(evlist, &data.list, entries); + evlist->nr_groups += data.nr_groups; return 0; } @@ -858,7 +892,7 @@ int parse_events_option(const struct option *opt, const char *str, int unset __maybe_unused) { struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; - int ret = parse_events(evlist, str, unset); + int ret = parse_events(evlist, str); if (ret) { fprintf(stderr, "invalid or unsupported event: '%s'\n", str); @@ -1121,16 +1155,16 @@ void print_events(const char *event_glob, bool name_only) print_tracepoint_events(NULL, NULL, name_only); } -int parse_events__is_hardcoded_term(struct parse_events__term *term) +int parse_events__is_hardcoded_term(struct parse_events_term *term) { return term->type_term != PARSE_EVENTS__TERM_TYPE_USER; } -static int new_term(struct parse_events__term **_term, int type_val, +static int new_term(struct parse_events_term **_term, int type_val, int type_term, char *config, char *str, u64 num) { - struct parse_events__term *term; + struct parse_events_term *term; term = zalloc(sizeof(*term)); if (!term) @@ -1156,21 +1190,21 @@ static int new_term(struct parse_events__term **_term, int type_val, return 0; } -int parse_events__term_num(struct parse_events__term **term, +int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num) { return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, config, NULL, num); } -int parse_events__term_str(struct parse_events__term **term, +int parse_events_term__str(struct parse_events_term **term, int type_term, char *config, char *str) { return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term, config, str, 0); } -int parse_events__term_sym_hw(struct parse_events__term **term, +int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx) { struct event_symbol *sym; @@ -1188,8 +1222,8 @@ int parse_events__term_sym_hw(struct parse_events__term **term, (char *) "event", (char *) sym->symbol, 0); } -int parse_events__term_clone(struct parse_events__term **new, - struct parse_events__term *term) +int parse_events_term__clone(struct parse_events_term **new, + struct parse_events_term *term) { return new_term(new, term->type_val, term->type_term, term->config, term->val.str, term->val.num); @@ -1197,7 +1231,7 @@ int parse_events__term_clone(struct parse_events__term **new, void parse_events__free_terms(struct list_head *terms) { - struct parse_events__term *term, *h; + struct parse_events_term *term, *h; list_for_each_entry_safe(term, h, terms, list) free(term); diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index b7af80b..8a48593 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -29,8 +29,7 @@ const char *event_type(int type); extern int parse_events_option(const struct option *opt, const char *str, int unset); -extern int parse_events(struct perf_evlist *evlist, const char *str, - int unset); +extern int parse_events(struct perf_evlist *evlist, const char *str); extern int parse_events_terms(struct list_head *terms, const char *str); extern int parse_filter(const struct option *opt, const char *str, int unset); @@ -51,7 +50,7 @@ enum { PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, }; -struct parse_events__term { +struct parse_events_term { char *config; union { char *str; @@ -62,24 +61,25 @@ struct parse_events__term { struct list_head list; }; -struct parse_events_data__events { +struct parse_events_evlist { struct list_head list; int idx; + int nr_groups; }; -struct parse_events_data__terms { +struct parse_events_terms { struct list_head *terms; }; -int parse_events__is_hardcoded_term(struct parse_events__term *term); -int parse_events__term_num(struct parse_events__term **_term, +int parse_events__is_hardcoded_term(struct parse_events_term *term); +int parse_events_term__num(struct parse_events_term **_term, int type_term, char *config, u64 num); -int parse_events__term_str(struct parse_events__term **_term, +int parse_events_term__str(struct parse_events_term **_term, int type_term, char *config, char *str); -int parse_events__term_sym_hw(struct parse_events__term **term, +int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx); -int parse_events__term_clone(struct parse_events__term **new, - struct parse_events__term *term); +int parse_events_term__clone(struct parse_events_term **new, + struct parse_events_term *term); void parse_events__free_terms(struct list_head *terms); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 0f9914a..afc44c1 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,5 +1,4 @@ %pure-parser -%name-prefix "parse_events_" %parse-param {void *_data} %parse-param {void *scanner} %lex-param {void* scanner} @@ -23,6 +22,14 @@ do { \ YYABORT; \ } while (0) +static inc_group_count(struct list_head *list, + struct parse_events_evlist *data) +{ + /* Count groups only have more than 1 members */ + if (!list_is_last(list->next, list)) + data->nr_groups++; +} + %} %token PE_START_EVENTS PE_START_TERMS @@ -68,7 +75,7 @@ do { \ char *str; u64 num; struct list_head *head; - struct parse_events__term *term; + struct parse_events_term *term; } %% @@ -79,7 +86,7 @@ PE_START_TERMS start_terms start_events: groups { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; parse_events_update_lists($1, &data->list); } @@ -123,6 +130,7 @@ PE_NAME '{' events '}' { struct list_head *list = $3; + inc_group_count(list, _data); parse_events__set_leader($1, list); $$ = list; } @@ -131,6 +139,7 @@ PE_NAME '{' events '}' { struct list_head *list = $2; + inc_group_count(list, _data); parse_events__set_leader(NULL, list); $$ = list; } @@ -186,7 +195,7 @@ event_def: event_pmu | event_pmu: PE_NAME '/' event_config '/' { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3)); @@ -202,7 +211,7 @@ PE_VALUE_SYM_SW event_legacy_symbol: value_sym '/' event_config '/' { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; @@ -215,7 +224,7 @@ value_sym '/' event_config '/' | value_sym sep_slash_dc { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; @@ -228,7 +237,7 @@ value_sym sep_slash_dc event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5)); @@ -237,7 +246,7 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL)); @@ -246,7 +255,7 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT | PE_NAME_CACHE_TYPE { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL)); @@ -256,7 +265,7 @@ PE_NAME_CACHE_TYPE event_legacy_mem: PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, @@ -266,7 +275,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc | PE_PREFIX_MEM PE_VALUE sep_dc { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, @@ -277,7 +286,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc event_legacy_tracepoint: PE_NAME ':' PE_NAME { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3)); @@ -287,7 +296,7 @@ PE_NAME ':' PE_NAME event_legacy_numeric: PE_VALUE ':' PE_VALUE { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL)); @@ -297,7 +306,7 @@ PE_VALUE ':' PE_VALUE event_legacy_raw: PE_RAW { - struct parse_events_data__events *data = _data; + struct parse_events_evlist *data = _data; struct list_head *list = NULL; ABORT_ON(parse_events_add_numeric(&list, &data->idx, @@ -307,7 +316,7 @@ PE_RAW start_terms: event_config { - struct parse_events_data__terms *data = _data; + struct parse_events_terms *data = _data; data->terms = $1; } @@ -315,7 +324,7 @@ event_config: event_config ',' event_term { struct list_head *head = $1; - struct parse_events__term *term = $3; + struct parse_events_term *term = $3; ABORT_ON(!head); list_add_tail(&term->list, head); @@ -325,7 +334,7 @@ event_config ',' event_term event_term { struct list_head *head = malloc(sizeof(*head)); - struct parse_events__term *term = $1; + struct parse_events_term *term = $1; ABORT_ON(!head); INIT_LIST_HEAD(head); @@ -336,70 +345,70 @@ event_term event_term: PE_NAME '=' PE_NAME { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_str(&term, PARSE_EVENTS__TERM_TYPE_USER, + ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3)); $$ = term; } | PE_NAME '=' PE_VALUE { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER, + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3)); $$ = term; } | PE_NAME '=' PE_VALUE_SYM_HW { - struct parse_events__term *term; + struct parse_events_term *term; int config = $3 & 255; - ABORT_ON(parse_events__term_sym_hw(&term, $1, config)); + ABORT_ON(parse_events_term__sym_hw(&term, $1, config)); $$ = term; } | PE_NAME { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER, + ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, 1)); $$ = term; } | PE_VALUE_SYM_HW { - struct parse_events__term *term; + struct parse_events_term *term; int config = $1 & 255; - ABORT_ON(parse_events__term_sym_hw(&term, NULL, config)); + ABORT_ON(parse_events_term__sym_hw(&term, NULL, config)); $$ = term; } | PE_TERM '=' PE_NAME { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_str(&term, (int)$1, NULL, $3)); + ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3)); $$ = term; } | PE_TERM '=' PE_VALUE { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, $3)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3)); $$ = term; } | PE_TERM { - struct parse_events__term *term; + struct parse_events_term *term; - ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, 1)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1)); $$ = term; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 9bdc60c..4c6f9c4 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1,4 +1,3 @@ - #include <linux/list.h> #include <sys/types.h> #include <sys/stat.h> @@ -11,6 +10,19 @@ #include "parse-events.h" #include "cpumap.h" +struct perf_pmu_alias { + char *name; + struct list_head terms; + struct list_head list; +}; + +struct perf_pmu_format { + char *name; + int value; + DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); + struct list_head list; +}; + #define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/" int perf_pmu_parse(struct list_head *list, char *name); @@ -85,7 +97,7 @@ static int pmu_format(char *name, struct list_head *format) static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file) { - struct perf_pmu__alias *alias; + struct perf_pmu_alias *alias; char buf[256]; int ret; @@ -172,15 +184,15 @@ static int pmu_aliases(char *name, struct list_head *head) return 0; } -static int pmu_alias_terms(struct perf_pmu__alias *alias, +static int pmu_alias_terms(struct perf_pmu_alias *alias, struct list_head *terms) { - struct parse_events__term *term, *clone; + struct parse_events_term *term, *clone; LIST_HEAD(list); int ret; list_for_each_entry(term, &alias->terms, list) { - ret = parse_events__term_clone(&clone, term); + ret = parse_events_term__clone(&clone, term); if (ret) { parse_events__free_terms(&list); return ret; @@ -360,10 +372,10 @@ struct perf_pmu *perf_pmu__find(char *name) return pmu_lookup(name); } -static struct perf_pmu__format* +static struct perf_pmu_format * pmu_find_format(struct list_head *formats, char *name) { - struct perf_pmu__format *format; + struct perf_pmu_format *format; list_for_each_entry(format, formats, list) if (!strcmp(format->name, name)) @@ -403,9 +415,9 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value) */ static int pmu_config_term(struct list_head *formats, struct perf_event_attr *attr, - struct parse_events__term *term) + struct parse_events_term *term) { - struct perf_pmu__format *format; + struct perf_pmu_format *format; __u64 *vp; /* @@ -450,7 +462,7 @@ int perf_pmu__config_terms(struct list_head *formats, struct perf_event_attr *attr, struct list_head *head_terms) { - struct parse_events__term *term; + struct parse_events_term *term; list_for_each_entry(term, head_terms, list) if (pmu_config_term(formats, attr, term)) @@ -471,10 +483,10 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, return perf_pmu__config_terms(&pmu->format, attr, head_terms); } -static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu, - struct parse_events__term *term) +static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu, + struct parse_events_term *term) { - struct perf_pmu__alias *alias; + struct perf_pmu_alias *alias; char *name; if (parse_events__is_hardcoded_term(term)) @@ -507,8 +519,8 @@ static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu, */ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms) { - struct parse_events__term *term, *h; - struct perf_pmu__alias *alias; + struct parse_events_term *term, *h; + struct perf_pmu_alias *alias; int ret; list_for_each_entry_safe(term, h, head_terms, list) { @@ -527,7 +539,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms) int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits) { - struct perf_pmu__format *format; + struct perf_pmu_format *format; format = zalloc(sizeof(*format)); if (!format) @@ -548,7 +560,7 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to) if (!to) to = from; - memset(bits, 0, BITS_TO_LONGS(PERF_PMU_FORMAT_BITS)); + memset(bits, 0, BITS_TO_BYTES(PERF_PMU_FORMAT_BITS)); for (b = from; b <= to; b++) set_bit(b, bits); } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a313ed7..32fe55b 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -12,19 +12,6 @@ enum { #define PERF_PMU_FORMAT_BITS 64 -struct perf_pmu__format { - char *name; - int value; - DECLARE_BITMAP(bits, PERF_PMU_FORMAT_BITS); - struct list_head list; -}; - -struct perf_pmu__alias { - char *name; - struct list_head terms; - struct list_head list; -}; - struct perf_pmu { char *name; __u32 type; @@ -42,7 +29,7 @@ int perf_pmu__config_terms(struct list_head *formats, struct list_head *head_terms); int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, - struct list_head *head_terms); + struct list_head *head_terms); int perf_pmu_wrap(void); void perf_pmu_error(struct list_head *list, char *name, char const *msg); diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index ec89804..bfd7e85 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -1,5 +1,4 @@ -%name-prefix "perf_pmu_" %parse-param {struct list_head *format} %parse-param {char *name} diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1daf5c1..be03293 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -413,12 +413,12 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(vr_die), dwarf_diename(&type)); return -EINVAL; } + if (die_get_real_type(&type, &type) == NULL) { + pr_warning("Failed to get a type" + " information.\n"); + return -ENOENT; + } if (ret == DW_TAG_pointer_type) { - if (die_get_real_type(&type, &type) == NULL) { - pr_warning("Failed to get a type" - " information.\n"); - return -ENOENT; - } while (*ref_ptr) ref_ptr = &(*ref_ptr)->next; /* Add new reference with offset +0 */ diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index c40c2d3..64536a9 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -18,4 +18,5 @@ util/cgroup.c util/debugfs.c util/rblist.c util/strlist.c +util/sysfs.c ../../lib/rbtree.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index a2657fd..925e0c3 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -1045,3 +1045,12 @@ error: if (PyErr_Occurred()) PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); } + +/* + * Dummy, to avoid dragging all the test_attr infrastructure in the python + * binding. + */ +void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu, + int fd, int group_fd, unsigned long flags) +{ +} diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index f80605e..eacec85 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -292,6 +292,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, ns = nsecs - s * NSECS_PER_SEC; scripting_context->event_data = data; + scripting_context->pevent = evsel->tp_format->pevent; ENTER; SAVETMPS; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 14683df..e87aa5d 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -265,6 +265,7 @@ static void python_process_tracepoint(union perf_event *perf_event ns = nsecs - s * NSECS_PER_SEC; scripting_context->event_data = data; + scripting_context->pevent = evsel->tp_format->pevent; context = PyCObject_FromVoidPtr(scripting_context, NULL); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ce6f511..bd85280b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -16,7 +16,6 @@ #include "cpumap.h" #include "event-parse.h" #include "perf_regs.h" -#include "unwind.h" #include "vdso.h" static int perf_session__open(struct perf_session *self, bool force) @@ -87,13 +86,12 @@ void perf_session__set_id_hdr_size(struct perf_session *session) { u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist); - session->host_machine.id_hdr_size = id_hdr_size; machines__set_id_hdr_size(&session->machines, id_hdr_size); } int perf_session__create_kernel_maps(struct perf_session *self) { - int ret = machine__create_kernel_maps(&self->host_machine); + int ret = machine__create_kernel_maps(&self->machines.host); if (ret >= 0) ret = machines__create_guest_kernel_maps(&self->machines); @@ -102,8 +100,7 @@ int perf_session__create_kernel_maps(struct perf_session *self) static void perf_session__destroy_kernel_maps(struct perf_session *self) { - machine__destroy_kernel_maps(&self->host_machine); - machines__destroy_guest_kernel_maps(&self->machines); + machines__destroy_kernel_maps(&self->machines); } struct perf_session *perf_session__new(const char *filename, int mode, @@ -128,22 +125,11 @@ struct perf_session *perf_session__new(const char *filename, int mode, goto out; memcpy(self->filename, filename, len); - /* - * On 64bit we can mmap the data file in one go. No need for tiny mmap - * slices. On 32bit we use 32MB. - */ -#if BITS_PER_LONG == 64 - self->mmap_window = ULLONG_MAX; -#else - self->mmap_window = 32 * 1024 * 1024ULL; -#endif - self->machines = RB_ROOT; self->repipe = repipe; INIT_LIST_HEAD(&self->ordered_samples.samples); INIT_LIST_HEAD(&self->ordered_samples.sample_cache); INIT_LIST_HEAD(&self->ordered_samples.to_free); - machine__init(&self->host_machine, "", HOST_KERNEL_ID); - hists__init(&self->hists); + machines__init(&self->machines); if (mode == O_RDONLY) { if (perf_session__open(self, force) < 0) @@ -171,37 +157,30 @@ out_delete: return NULL; } -static void machine__delete_dead_threads(struct machine *machine) -{ - struct thread *n, *t; - - list_for_each_entry_safe(t, n, &machine->dead_threads, node) { - list_del(&t->node); - thread__delete(t); - } -} - static void perf_session__delete_dead_threads(struct perf_session *session) { - machine__delete_dead_threads(&session->host_machine); + machine__delete_dead_threads(&session->machines.host); } -static void machine__delete_threads(struct machine *self) +static void perf_session__delete_threads(struct perf_session *session) { - struct rb_node *nd = rb_first(&self->threads); - - while (nd) { - struct thread *t = rb_entry(nd, struct thread, rb_node); - - rb_erase(&t->rb_node, &self->threads); - nd = rb_next(nd); - thread__delete(t); - } + machine__delete_threads(&session->machines.host); } -static void perf_session__delete_threads(struct perf_session *session) +static void perf_session_env__delete(struct perf_session_env *env) { - machine__delete_threads(&session->host_machine); + free(env->hostname); + free(env->os_release); + free(env->version); + free(env->arch); + free(env->cpu_desc); + free(env->cpuid); + + free(env->cmdline); + free(env->sibling_cores); + free(env->sibling_threads); + free(env->numa_nodes); + free(env->pmu_mappings); } void perf_session__delete(struct perf_session *self) @@ -209,198 +188,13 @@ void perf_session__delete(struct perf_session *self) perf_session__destroy_kernel_maps(self); perf_session__delete_dead_threads(self); perf_session__delete_threads(self); - machine__exit(&self->host_machine); + perf_session_env__delete(&self->header.env); + machines__exit(&self->machines); close(self->fd); free(self); vdso__exit(); } -void machine__remove_thread(struct machine *self, struct thread *th) -{ - self->last_match = NULL; - rb_erase(&th->rb_node, &self->threads); - /* - * We may have references to this thread, for instance in some hist_entry - * instances, so just move them to a separate list. - */ - list_add_tail(&th->node, &self->dead_threads); -} - -static bool symbol__match_parent_regex(struct symbol *sym) -{ - if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0)) - return 1; - - return 0; -} - -static const u8 cpumodes[] = { - PERF_RECORD_MISC_USER, - PERF_RECORD_MISC_KERNEL, - PERF_RECORD_MISC_GUEST_USER, - PERF_RECORD_MISC_GUEST_KERNEL -}; -#define NCPUMODES (sizeof(cpumodes)/sizeof(u8)) - -static void ip__resolve_ams(struct machine *self, struct thread *thread, - struct addr_map_symbol *ams, - u64 ip) -{ - struct addr_location al; - size_t i; - u8 m; - - memset(&al, 0, sizeof(al)); - - for (i = 0; i < NCPUMODES; i++) { - m = cpumodes[i]; - /* - * We cannot use the header.misc hint to determine whether a - * branch stack address is user, kernel, guest, hypervisor. - * Branches may straddle the kernel/user/hypervisor boundaries. - * Thus, we have to try consecutively until we find a match - * or else, the symbol is unknown - */ - thread__find_addr_location(thread, self, m, MAP__FUNCTION, - ip, &al, NULL); - if (al.sym) - goto found; - } -found: - ams->addr = ip; - ams->al_addr = al.addr; - ams->sym = al.sym; - ams->map = al.map; -} - -struct branch_info *machine__resolve_bstack(struct machine *self, - struct thread *thr, - struct branch_stack *bs) -{ - struct branch_info *bi; - unsigned int i; - - bi = calloc(bs->nr, sizeof(struct branch_info)); - if (!bi) - return NULL; - - for (i = 0; i < bs->nr; i++) { - ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to); - ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from); - bi[i].flags = bs->entries[i].flags; - } - return bi; -} - -static int machine__resolve_callchain_sample(struct machine *machine, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) - -{ - u8 cpumode = PERF_RECORD_MISC_USER; - unsigned int i; - int err; - - callchain_cursor_reset(&callchain_cursor); - - if (chain->nr > PERF_MAX_STACK_DEPTH) { - pr_warning("corrupted callchain. skipping...\n"); - return 0; - } - - for (i = 0; i < chain->nr; i++) { - u64 ip; - struct addr_location al; - - if (callchain_param.order == ORDER_CALLEE) - ip = chain->ips[i]; - else - ip = chain->ips[chain->nr - i - 1]; - - if (ip >= PERF_CONTEXT_MAX) { - switch (ip) { - case PERF_CONTEXT_HV: - cpumode = PERF_RECORD_MISC_HYPERVISOR; - break; - case PERF_CONTEXT_KERNEL: - cpumode = PERF_RECORD_MISC_KERNEL; - break; - case PERF_CONTEXT_USER: - cpumode = PERF_RECORD_MISC_USER; - break; - default: - pr_debug("invalid callchain context: " - "%"PRId64"\n", (s64) ip); - /* - * It seems the callchain is corrupted. - * Discard all. - */ - callchain_cursor_reset(&callchain_cursor); - return 0; - } - continue; - } - - al.filtered = false; - thread__find_addr_location(thread, machine, cpumode, - MAP__FUNCTION, ip, &al, NULL); - if (al.sym != NULL) { - if (sort__has_parent && !*parent && - symbol__match_parent_regex(al.sym)) - *parent = al.sym; - if (!symbol_conf.use_callchain) - break; - } - - err = callchain_cursor_append(&callchain_cursor, - ip, al.map, al.sym); - if (err) - return err; - } - - return 0; -} - -static int unwind_entry(struct unwind_entry *entry, void *arg) -{ - struct callchain_cursor *cursor = arg; - return callchain_cursor_append(cursor, entry->ip, - entry->map, entry->sym); -} - -int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, - struct thread *thread, - struct perf_sample *sample, - struct symbol **parent) - -{ - int ret; - - callchain_cursor_reset(&callchain_cursor); - - ret = machine__resolve_callchain_sample(machine, thread, - sample->callchain, parent); - if (ret) - return ret; - - /* Can we do dwarf post unwind? */ - if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) && - (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER))) - return 0; - - /* Bail out if nothing was captured. */ - if ((!sample->user_regs.regs) || - (!sample->user_stack.size)) - return 0; - - return unwind__get_entries(unwind_entry, &callchain_cursor, machine, - thread, evsel->attr.sample_regs_user, - sample); - -} - static int process_event_synth_tracing_data_stub(union perf_event *event __maybe_unused, struct perf_session *session @@ -1027,7 +821,7 @@ static struct machine * return perf_session__findnew_machine(session, pid); } - return perf_session__find_host_machine(session); + return &session->machines.host; } static int perf_session_deliver_event(struct perf_session *session, @@ -1065,11 +859,11 @@ static int perf_session_deliver_event(struct perf_session *session, case PERF_RECORD_SAMPLE: dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->hists.stats.nr_unknown_id; + ++session->stats.nr_unknown_id; return 0; } if (machine == NULL) { - ++session->hists.stats.nr_unprocessable_samples; + ++session->stats.nr_unprocessable_samples; return 0; } return tool->sample(tool, event, sample, evsel, machine); @@ -1083,7 +877,7 @@ static int perf_session_deliver_event(struct perf_session *session, return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: if (tool->lost == perf_event__process_lost) - session->hists.stats.total_lost += event->lost.lost; + session->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_READ: return tool->read(tool, event, sample, evsel, machine); @@ -1092,7 +886,7 @@ static int perf_session_deliver_event(struct perf_session *session, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); default: - ++session->hists.stats.nr_unknown_events; + ++session->stats.nr_unknown_events; return -1; } } @@ -1106,8 +900,8 @@ static int perf_session__preprocess_sample(struct perf_session *session, if (!ip_callchain__valid(sample->callchain, event)) { pr_debug("call-chain problem with event, skipping it.\n"); - ++session->hists.stats.nr_invalid_chains; - session->hists.stats.total_invalid_chains += sample->period; + ++session->stats.nr_invalid_chains; + session->stats.total_invalid_chains += sample->period; return -EINVAL; } return 0; @@ -1165,7 +959,7 @@ static int perf_session__process_event(struct perf_session *session, if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - hists__inc_nr_events(&session->hists, event->header.type); + events_stats__inc(&session->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) return perf_session__process_user_event(session, event, tool, file_offset); @@ -1201,7 +995,7 @@ void perf_event_header__bswap(struct perf_event_header *self) struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->host_machine, pid); + return machine__findnew_thread(&session->machines.host, pid); } static struct thread *perf_session__register_idle_thread(struct perf_session *self) @@ -1220,39 +1014,39 @@ static void perf_session__warn_about_errors(const struct perf_session *session, const struct perf_tool *tool) { if (tool->lost == perf_event__process_lost && - session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) { + session->stats.nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", - session->hists.stats.nr_events[0], - session->hists.stats.nr_events[PERF_RECORD_LOST]); + session->stats.nr_events[0], + session->stats.nr_events[PERF_RECORD_LOST]); } - if (session->hists.stats.nr_unknown_events != 0) { + if (session->stats.nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " "file generated by a more recent tool?\n\n" "If that is not the case, consider " "reporting to linux-kernel@vger.kernel.org.\n\n", - session->hists.stats.nr_unknown_events); + session->stats.nr_unknown_events); } - if (session->hists.stats.nr_unknown_id != 0) { + if (session->stats.nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->hists.stats.nr_unknown_id); + session->stats.nr_unknown_id); } - if (session->hists.stats.nr_invalid_chains != 0) { + if (session->stats.nr_invalid_chains != 0) { ui__warning("Found invalid callchains!\n\n" "%u out of %u events were discarded for this reason.\n\n" "Consider reporting to linux-kernel@vger.kernel.org.\n\n", - session->hists.stats.nr_invalid_chains, - session->hists.stats.nr_events[PERF_RECORD_SAMPLE]); + session->stats.nr_invalid_chains, + session->stats.nr_events[PERF_RECORD_SAMPLE]); } - if (session->hists.stats.nr_unprocessable_samples != 0) { + if (session->stats.nr_unprocessable_samples != 0) { ui__warning("%u unprocessable samples recorded.\n" "Do you have a KVM guest running and not using 'perf kvm'?\n", - session->hists.stats.nr_unprocessable_samples); + session->stats.nr_unprocessable_samples); } } @@ -1369,6 +1163,18 @@ fetch_mmaped_event(struct perf_session *session, return event; } +/* + * On 64bit we can mmap the data file in one go. No need for tiny mmap + * slices. On 32bit we use 32MB. + */ +#if BITS_PER_LONG == 64 +#define MMAP_SIZE ULLONG_MAX +#define NUM_MMAPS 1 +#else +#define MMAP_SIZE (32 * 1024 * 1024ULL) +#define NUM_MMAPS 128 +#endif + int __perf_session__process_events(struct perf_session *session, u64 data_offset, u64 data_size, u64 file_size, struct perf_tool *tool) @@ -1376,7 +1182,7 @@ int __perf_session__process_events(struct perf_session *session, u64 head, page_offset, file_offset, file_pos, progress_next; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; - char *buf, *mmaps[8]; + char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; uint32_t size; @@ -1391,7 +1197,7 @@ int __perf_session__process_events(struct perf_session *session, progress_next = file_size / 16; - mmap_size = session->mmap_window; + mmap_size = MMAP_SIZE; if (mmap_size > file_size) mmap_size = file_size; @@ -1526,16 +1332,13 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp) { - return __dsos__fprintf(&self->host_machine.kernel_dsos, fp) + - __dsos__fprintf(&self->host_machine.user_dsos, fp) + - machines__fprintf_dsos(&self->machines, fp); + return machines__fprintf_dsos(&self->machines, fp); } size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, - bool with_hits) + bool (skip)(struct dso *dso, int parm), int parm) { - size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits); - return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits); + return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm); } size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) @@ -1543,11 +1346,11 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) struct perf_evsel *pos; size_t ret = fprintf(fp, "Aggregated stats:\n"); - ret += hists__fprintf_nr_events(&session->hists, fp); + ret += events_stats__fprintf(&session->stats, fp); list_for_each_entry(pos, &session->evlist->entries, node) { ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); - ret += hists__fprintf_nr_events(&pos->hists, fp); + ret += events_stats__fprintf(&pos->hists.stats, fp); } return ret; @@ -1559,7 +1362,7 @@ size_t perf_session__fprintf(struct perf_session *session, FILE *fp) * FIXME: Here we have to actually print all the machines in this * session, not just the host... */ - return machine__fprintf(&session->host_machine, fp); + return machine__fprintf(&session->machines.host, fp); } void perf_session__remove_thread(struct perf_session *session, @@ -1568,10 +1371,10 @@ void perf_session__remove_thread(struct perf_session *session, /* * FIXME: This one makes no sense, we need to remove the thread from * the machine it belongs to, perf_session can have many machines, so - * doing it always on ->host_machine is wrong. Fix when auditing all + * doing it always on ->machines.host is wrong. Fix when auditing all * the 'perf kvm' code. */ - machine__remove_thread(&session->host_machine, th); + machine__remove_thread(&session->machines.host, th); } struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index cea133a..b5c0847 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -30,16 +30,10 @@ struct ordered_samples { struct perf_session { struct perf_header header; unsigned long size; - unsigned long mmap_window; - struct machine host_machine; - struct rb_root machines; + struct machines machines; struct perf_evlist *evlist; struct pevent *pevent; - /* - * FIXME: Need to split this up further, we need global - * stats + per event stats. - */ - struct hists hists; + struct events_stats stats; int fd; bool fd_pipe; bool repipe; @@ -54,7 +48,7 @@ struct perf_tool; struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe, struct perf_tool *tool); -void perf_session__delete(struct perf_session *self); +void perf_session__delete(struct perf_session *session); void perf_event_header__bswap(struct perf_event_header *self); @@ -81,43 +75,24 @@ void perf_session__set_id_hdr_size(struct perf_session *session); void perf_session__remove_thread(struct perf_session *self, struct thread *th); static inline -struct machine *perf_session__find_host_machine(struct perf_session *self) -{ - return &self->host_machine; -} - -static inline struct machine *perf_session__find_machine(struct perf_session *self, pid_t pid) { - if (pid == HOST_KERNEL_ID) - return &self->host_machine; return machines__find(&self->machines, pid); } static inline struct machine *perf_session__findnew_machine(struct perf_session *self, pid_t pid) { - if (pid == HOST_KERNEL_ID) - return &self->host_machine; return machines__findnew(&self->machines, pid); } -static inline -void perf_session__process_machines(struct perf_session *self, - struct perf_tool *tool, - machine__process_t process) -{ - process(&self->host_machine, tool); - return machines__process(&self->machines, process, tool); -} - struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); size_t perf_session__fprintf(struct perf_session *self, FILE *fp); size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp); -size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, - FILE *fp, bool with_hits); +size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, + bool (fn)(struct dso *dso, int parm), int parm); size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cfd1c0f..d41926c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -60,7 +60,7 @@ sort__thread_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%*s:%5d", width, + return repsep_snprintf(bf, size, "%*s:%5d", width - 6, self->thread->comm ?: "", self->thread->pid); } @@ -97,6 +97,16 @@ static int hist_entry__comm_snprintf(struct hist_entry *self, char *bf, return repsep_snprintf(bf, size, "%*s", width, self->thread->comm); } +struct sort_entry sort_comm = { + .se_header = "Command", + .se_cmp = sort__comm_cmp, + .se_collapse = sort__comm_collapse, + .se_snprintf = hist_entry__comm_snprintf, + .se_width_idx = HISTC_COMM, +}; + +/* --sort dso */ + static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) { struct dso *dso_l = map_l ? map_l->dso : NULL; @@ -117,40 +127,12 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) return strcmp(dso_name_l, dso_name_r); } -struct sort_entry sort_comm = { - .se_header = "Command", - .se_cmp = sort__comm_cmp, - .se_collapse = sort__comm_collapse, - .se_snprintf = hist_entry__comm_snprintf, - .se_width_idx = HISTC_COMM, -}; - -/* --sort dso */ - static int64_t sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) { return _sort__dso_cmp(left->ms.map, right->ms.map); } - -static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r, - u64 ip_l, u64 ip_r) -{ - if (!sym_l || !sym_r) - return cmp_null(sym_l, sym_r); - - if (sym_l == sym_r) - return 0; - - if (sym_l) - ip_l = sym_l->start; - if (sym_r) - ip_r = sym_r->start; - - return (int64_t)(ip_r - ip_l); -} - static int _hist_entry__dso_snprintf(struct map *map, char *bf, size_t size, unsigned int width) { @@ -169,9 +151,43 @@ static int hist_entry__dso_snprintf(struct hist_entry *self, char *bf, return _hist_entry__dso_snprintf(self->ms.map, bf, size, width); } +struct sort_entry sort_dso = { + .se_header = "Shared Object", + .se_cmp = sort__dso_cmp, + .se_snprintf = hist_entry__dso_snprintf, + .se_width_idx = HISTC_DSO, +}; + +/* --sort symbol */ + +static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r) +{ + u64 ip_l, ip_r; + + if (!sym_l || !sym_r) + return cmp_null(sym_l, sym_r); + + if (sym_l == sym_r) + return 0; + + ip_l = sym_l->start; + ip_r = sym_r->start; + + return (int64_t)(ip_r - ip_l); +} + +static int64_t +sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->ms.sym && !right->ms.sym) + return right->level - left->level; + + return _sort__sym_cmp(left->ms.sym, right->ms.sym); +} + static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, u64 ip, char level, char *bf, size_t size, - unsigned int width __maybe_unused) + unsigned int width) { size_t ret = 0; @@ -197,43 +213,13 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, return ret; } - -struct sort_entry sort_dso = { - .se_header = "Shared Object", - .se_cmp = sort__dso_cmp, - .se_snprintf = hist_entry__dso_snprintf, - .se_width_idx = HISTC_DSO, -}; - static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { return _hist_entry__sym_snprintf(self->ms.map, self->ms.sym, self->ip, self->level, bf, size, width); } -/* --sort symbol */ -static int64_t -sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) -{ - u64 ip_l, ip_r; - - if (!left->ms.sym && !right->ms.sym) - return right->level - left->level; - - if (!left->ms.sym || !right->ms.sym) - return cmp_null(left->ms.sym, right->ms.sym); - - if (left->ms.sym == right->ms.sym) - return 0; - - ip_l = left->ms.sym->start; - ip_r = right->ms.sym->start; - - return _sort__sym_cmp(left->ms.sym, right->ms.sym, ip_l, ip_r); -} - struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, @@ -253,7 +239,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width __maybe_unused) { - FILE *fp; + FILE *fp = NULL; char cmd[PATH_MAX + 2], *path = self->srcline, *nl; size_t line_len; @@ -274,7 +260,6 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, if (getline(&path, &line_len, fp) < 0 || !line_len) goto out_ip; - fclose(fp); self->srcline = strdup(path); if (self->srcline == NULL) goto out_ip; @@ -284,8 +269,12 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, *nl = '\0'; path = self->srcline; out_path: + if (fp) + pclose(fp); return repsep_snprintf(bf, size, "%s", path); out_ip: + if (fp) + pclose(fp); return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip); } @@ -335,7 +324,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*d", width, self->cpu); + return repsep_snprintf(bf, size, "%*d", width, self->cpu); } struct sort_entry sort_cpu = { @@ -345,6 +334,8 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +/* sort keys for branch stacks */ + static int64_t sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -359,13 +350,6 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *self, char *bf, bf, size, width); } -struct sort_entry sort_dso_from = { - .se_header = "Source Shared Object", - .se_cmp = sort__dso_from_cmp, - .se_snprintf = hist_entry__dso_from_snprintf, - .se_width_idx = HISTC_DSO_FROM, -}; - static int64_t sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right) { @@ -389,8 +373,7 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) if (!from_l->sym && !from_r->sym) return right->level - left->level; - return _sort__sym_cmp(from_l->sym, from_r->sym, from_l->addr, - from_r->addr); + return _sort__sym_cmp(from_l->sym, from_r->sym); } static int64_t @@ -402,12 +385,11 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right) if (!to_l->sym && !to_r->sym) return right->level - left->level; - return _sort__sym_cmp(to_l->sym, to_r->sym, to_l->addr, to_r->addr); + return _sort__sym_cmp(to_l->sym, to_r->sym); } static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { struct addr_map_symbol *from = &self->branch_info->from; return _hist_entry__sym_snprintf(from->map, from->sym, from->addr, @@ -416,8 +398,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *self, char *bf, } static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, - size_t size, - unsigned int width __maybe_unused) + size_t size, unsigned int width) { struct addr_map_symbol *to = &self->branch_info->to; return _hist_entry__sym_snprintf(to->map, to->sym, to->addr, @@ -425,6 +406,13 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *self, char *bf, } +struct sort_entry sort_dso_from = { + .se_header = "Source Shared Object", + .se_cmp = sort__dso_from_cmp, + .se_snprintf = hist_entry__dso_from_snprintf, + .se_width_idx = HISTC_DSO_FROM, +}; + struct sort_entry sort_dso_to = { .se_header = "Target Shared Object", .se_cmp = sort__dso_to_cmp, @@ -484,30 +472,40 @@ struct sort_dimension { #define DIM(d, n, func) [d] = { .name = n, .entry = &(func) } -static struct sort_dimension sort_dimensions[] = { +static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PID, "pid", sort_thread), DIM(SORT_COMM, "comm", sort_comm), DIM(SORT_DSO, "dso", sort_dso), - DIM(SORT_DSO_FROM, "dso_from", sort_dso_from), - DIM(SORT_DSO_TO, "dso_to", sort_dso_to), DIM(SORT_SYM, "symbol", sort_sym), - DIM(SORT_SYM_TO, "symbol_from", sort_sym_from), - DIM(SORT_SYM_FROM, "symbol_to", sort_sym_to), DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), - DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), DIM(SORT_SRCLINE, "srcline", sort_srcline), }; +#undef DIM + +#define DIM(d, n, func) [d - __SORT_BRANCH_STACK] = { .name = n, .entry = &(func) } + +static struct sort_dimension bstack_sort_dimensions[] = { + DIM(SORT_DSO_FROM, "dso_from", sort_dso_from), + DIM(SORT_DSO_TO, "dso_to", sort_dso_to), + DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from), + DIM(SORT_SYM_TO, "symbol_to", sort_sym_to), + DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), +}; + +#undef DIM + int sort_dimension__add(const char *tok) { unsigned int i; - for (i = 0; i < ARRAY_SIZE(sort_dimensions); i++) { - struct sort_dimension *sd = &sort_dimensions[i]; + for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { + struct sort_dimension *sd = &common_sort_dimensions[i]; if (strncasecmp(tok, sd->name, strlen(tok))) continue; + if (sd->entry == &sort_parent) { int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); if (ret) { @@ -518,9 +516,7 @@ int sort_dimension__add(const char *tok) return -EINVAL; } sort__has_parent = 1; - } else if (sd->entry == &sort_sym || - sd->entry == &sort_sym_from || - sd->entry == &sort_sym_to) { + } else if (sd->entry == &sort_sym) { sort__has_sym = 1; } @@ -530,52 +526,69 @@ int sort_dimension__add(const char *tok) if (sd->entry->se_collapse) sort__need_collapse = 1; - if (list_empty(&hist_entry__sort_list)) { - if (!strcmp(sd->name, "pid")) - sort__first_dimension = SORT_PID; - else if (!strcmp(sd->name, "comm")) - sort__first_dimension = SORT_COMM; - else if (!strcmp(sd->name, "dso")) - sort__first_dimension = SORT_DSO; - else if (!strcmp(sd->name, "symbol")) - sort__first_dimension = SORT_SYM; - else if (!strcmp(sd->name, "parent")) - sort__first_dimension = SORT_PARENT; - else if (!strcmp(sd->name, "cpu")) - sort__first_dimension = SORT_CPU; - else if (!strcmp(sd->name, "symbol_from")) - sort__first_dimension = SORT_SYM_FROM; - else if (!strcmp(sd->name, "symbol_to")) - sort__first_dimension = SORT_SYM_TO; - else if (!strcmp(sd->name, "dso_from")) - sort__first_dimension = SORT_DSO_FROM; - else if (!strcmp(sd->name, "dso_to")) - sort__first_dimension = SORT_DSO_TO; - else if (!strcmp(sd->name, "mispredict")) - sort__first_dimension = SORT_MISPREDICT; - } + if (list_empty(&hist_entry__sort_list)) + sort__first_dimension = i; list_add_tail(&sd->entry->list, &hist_entry__sort_list); sd->taken = 1; return 0; } + + for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) { + struct sort_dimension *sd = &bstack_sort_dimensions[i]; + + if (strncasecmp(tok, sd->name, strlen(tok))) + continue; + + if (sort__branch_mode != 1) + return -EINVAL; + + if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to) + sort__has_sym = 1; + + if (sd->taken) + return 0; + + if (sd->entry->se_collapse) + sort__need_collapse = 1; + + if (list_empty(&hist_entry__sort_list)) + sort__first_dimension = i + __SORT_BRANCH_STACK; + + list_add_tail(&sd->entry->list, &hist_entry__sort_list); + sd->taken = 1; + + return 0; + } + return -ESRCH; } -void setup_sorting(const char * const usagestr[], const struct option *opts) +int setup_sorting(void) { char *tmp, *tok, *str = strdup(sort_order); + int ret = 0; + + if (str == NULL) { + error("Not enough memory to setup sort keys"); + return -ENOMEM; + } for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - if (sort_dimension__add(tok) < 0) { + ret = sort_dimension__add(tok); + if (ret == -EINVAL) { + error("Invalid --sort key: `%s'", tok); + break; + } else if (ret == -ESRCH) { error("Unknown --sort key: `%s'", tok); - usage_with_options(usagestr, opts); + break; } } free(str); + return ret; } void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index b4e8c3b..b13e56f 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -55,9 +55,6 @@ struct he_stat { struct hist_entry_diff { bool computed; - /* PERF_HPP__DISPL */ - int displacement; - /* PERF_HPP__DELTA */ double period_ratio_delta; @@ -118,25 +115,29 @@ static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he) return NULL; } -static inline void hist__entry_add_pair(struct hist_entry *he, +static inline void hist_entry__add_pair(struct hist_entry *he, struct hist_entry *pair) { list_add_tail(&he->pairs.head, &pair->pairs.node); } enum sort_type { + /* common sort keys */ SORT_PID, SORT_COMM, SORT_DSO, SORT_SYM, SORT_PARENT, SORT_CPU, - SORT_DSO_FROM, + SORT_SRCLINE, + + /* branch stack specific sort keys */ + __SORT_BRANCH_STACK, + SORT_DSO_FROM = __SORT_BRANCH_STACK, SORT_DSO_TO, SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, - SORT_SRCLINE, }; /* @@ -159,7 +160,7 @@ struct sort_entry { extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -void setup_sorting(const char * const usagestr[], const struct option *opts); +int setup_sorting(void); extern int sort_dimension__add(const char *); void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, const char *list_name, FILE *fp); diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 346707d..29c7b2c 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -332,6 +332,24 @@ char *strxfrchar(char *s, char from, char to) } /** + * ltrim - Removes leading whitespace from @s. + * @s: The string to be stripped. + * + * Return pointer to the first non-whitespace character in @s. + */ +char *ltrim(char *s) +{ + int len = strlen(s); + + while (len && isspace(*s)) { + len--; + s++; + } + + return s; +} + +/** * rtrim - Removes trailing whitespace from @s. * @s: The string to be stripped. * diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 155d8b7..55433aa 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -35,11 +35,11 @@ out_delete: return NULL; } -static void str_node__delete(struct str_node *self, bool dupstr) +static void str_node__delete(struct str_node *snode, bool dupstr) { if (dupstr) - free((void *)self->s); - free(self); + free((void *)snode->s); + free(snode); } static @@ -59,12 +59,12 @@ static int strlist__node_cmp(struct rb_node *rb_node, const void *entry) return strcmp(snode->s, str); } -int strlist__add(struct strlist *self, const char *new_entry) +int strlist__add(struct strlist *slist, const char *new_entry) { - return rblist__add_node(&self->rblist, new_entry); + return rblist__add_node(&slist->rblist, new_entry); } -int strlist__load(struct strlist *self, const char *filename) +int strlist__load(struct strlist *slist, const char *filename) { char entry[1024]; int err; @@ -80,7 +80,7 @@ int strlist__load(struct strlist *self, const char *filename) continue; entry[len - 1] = '\0'; - err = strlist__add(self, entry); + err = strlist__add(slist, entry); if (err != 0) goto out; } @@ -107,56 +107,56 @@ struct str_node *strlist__find(struct strlist *slist, const char *entry) return snode; } -static int strlist__parse_list_entry(struct strlist *self, const char *s) +static int strlist__parse_list_entry(struct strlist *slist, const char *s) { if (strncmp(s, "file://", 7) == 0) - return strlist__load(self, s + 7); + return strlist__load(slist, s + 7); - return strlist__add(self, s); + return strlist__add(slist, s); } -int strlist__parse_list(struct strlist *self, const char *s) +int strlist__parse_list(struct strlist *slist, const char *s) { char *sep; int err; while ((sep = strchr(s, ',')) != NULL) { *sep = '\0'; - err = strlist__parse_list_entry(self, s); + err = strlist__parse_list_entry(slist, s); *sep = ','; if (err != 0) return err; s = sep + 1; } - return *s ? strlist__parse_list_entry(self, s) : 0; + return *s ? strlist__parse_list_entry(slist, s) : 0; } -struct strlist *strlist__new(bool dupstr, const char *slist) +struct strlist *strlist__new(bool dupstr, const char *list) { - struct strlist *self = malloc(sizeof(*self)); + struct strlist *slist = malloc(sizeof(*slist)); - if (self != NULL) { - rblist__init(&self->rblist); - self->rblist.node_cmp = strlist__node_cmp; - self->rblist.node_new = strlist__node_new; - self->rblist.node_delete = strlist__node_delete; + if (slist != NULL) { + rblist__init(&slist->rblist); + slist->rblist.node_cmp = strlist__node_cmp; + slist->rblist.node_new = strlist__node_new; + slist->rblist.node_delete = strlist__node_delete; - self->dupstr = dupstr; - if (slist && strlist__parse_list(self, slist) != 0) + slist->dupstr = dupstr; + if (slist && strlist__parse_list(slist, list) != 0) goto out_error; } - return self; + return slist; out_error: - free(self); + free(slist); return NULL; } -void strlist__delete(struct strlist *self) +void strlist__delete(struct strlist *slist) { - if (self != NULL) - rblist__delete(&self->rblist); + if (slist != NULL) + rblist__delete(&slist->rblist); } struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx) diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index dd9f922..5c7f870 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -17,34 +17,34 @@ struct strlist { }; struct strlist *strlist__new(bool dupstr, const char *slist); -void strlist__delete(struct strlist *self); +void strlist__delete(struct strlist *slist); -void strlist__remove(struct strlist *self, struct str_node *sn); -int strlist__load(struct strlist *self, const char *filename); -int strlist__add(struct strlist *self, const char *str); +void strlist__remove(struct strlist *slist, struct str_node *sn); +int strlist__load(struct strlist *slist, const char *filename); +int strlist__add(struct strlist *slist, const char *str); -struct str_node *strlist__entry(const struct strlist *self, unsigned int idx); -struct str_node *strlist__find(struct strlist *self, const char *entry); +struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx); +struct str_node *strlist__find(struct strlist *slist, const char *entry); -static inline bool strlist__has_entry(struct strlist *self, const char *entry) +static inline bool strlist__has_entry(struct strlist *slist, const char *entry) { - return strlist__find(self, entry) != NULL; + return strlist__find(slist, entry) != NULL; } -static inline bool strlist__empty(const struct strlist *self) +static inline bool strlist__empty(const struct strlist *slist) { - return rblist__empty(&self->rblist); + return rblist__empty(&slist->rblist); } -static inline unsigned int strlist__nr_entries(const struct strlist *self) +static inline unsigned int strlist__nr_entries(const struct strlist *slist) { - return rblist__nr_entries(&self->rblist); + return rblist__nr_entries(&slist->rblist); } /* For strlist iteration */ -static inline struct str_node *strlist__first(struct strlist *self) +static inline struct str_node *strlist__first(struct strlist *slist) { - struct rb_node *rn = rb_first(&self->rblist.entries); + struct rb_node *rn = rb_first(&slist->rblist.entries); return rn ? rb_entry(rn, struct str_node, rb_node) : NULL; } static inline struct str_node *strlist__next(struct str_node *sn) @@ -59,21 +59,21 @@ static inline struct str_node *strlist__next(struct str_node *sn) /** * strlist_for_each - iterate over a strlist * @pos: the &struct str_node to use as a loop cursor. - * @self: the &struct strlist for loop. + * @slist: the &struct strlist for loop. */ -#define strlist__for_each(pos, self) \ - for (pos = strlist__first(self); pos; pos = strlist__next(pos)) +#define strlist__for_each(pos, slist) \ + for (pos = strlist__first(slist); pos; pos = strlist__next(pos)) /** * strlist_for_each_safe - iterate over a strlist safe against removal of * str_node * @pos: the &struct str_node to use as a loop cursor. * @n: another &struct str_node to use as temporary storage. - * @self: the &struct strlist for loop. + * @slist: the &struct strlist for loop. */ -#define strlist__for_each_safe(pos, n, self) \ - for (pos = strlist__first(self), n = strlist__next(pos); pos;\ +#define strlist__for_each_safe(pos, n, slist) \ + for (pos = strlist__first(slist), n = strlist__next(pos); pos;\ pos = n, n = strlist__next(n)) -int strlist__parse_list(struct strlist *self, const char *s); +int strlist__parse_list(struct strlist *slist, const char *s); #endif /* __PERF_STRLIST_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index db0cc92..54efcb5 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1,6 +1,3 @@ -#include <libelf.h> -#include <gelf.h> -#include <elf.h> #include <fcntl.h> #include <stdio.h> #include <errno.h> @@ -718,6 +715,17 @@ int dso__load_sym(struct dso *dso, struct map *map, sym.st_value); used_opd = true; } + /* + * When loading symbols in a data mapping, ABS symbols (which + * has a value of SHN_ABS in its st_shndx) failed at + * elf_getscn(). And it marks the loading as a failure so + * already loaded symbols cannot be fixed up. + * + * I'm not sure what should be done. Just ignore them for now. + * - Namhyung Kim + */ + if (sym.st_shndx == SHN_ABS) + continue; sec = elf_getscn(runtime_ss->elf, sym.st_shndx); if (!sec) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 259f8f2..a7390cd 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,6 +1,5 @@ #include "symbol.h" -#include <elf.h> #include <stdio.h> #include <fcntl.h> #include <string.h> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 295f8d4..e6432d8 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -28,8 +28,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map, symbol_filter_t filter); -static int vmlinux_path__nr_entries; -static char **vmlinux_path; +int vmlinux_path__nr_entries; +char **vmlinux_path; struct symbol_conf symbol_conf = { .exclude_other = true, @@ -202,13 +202,6 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) curr->end = ~0ULL; } -static void map_groups__fixup_end(struct map_groups *mg) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(mg, i); -} - struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name) { size_t namelen = strlen(name) + 1; @@ -652,8 +645,8 @@ discard_symbol: rb_erase(&pos->rb_node, root); return count + moved; } -static bool symbol__restricted_filename(const char *filename, - const char *restricted_filename) +bool symbol__restricted_filename(const char *filename, + const char *restricted_filename) { bool restricted = false; @@ -775,10 +768,6 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) else machine = NULL; - name = malloc(PATH_MAX); - if (!name) - return -1; - dso->adjust_symbols = 0; if (strncmp(dso->name, "/tmp/perf-", 10) == 0) { @@ -802,6 +791,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (machine) root_dir = machine->root_dir; + name = malloc(PATH_MAX); + if (!name) + return -1; + /* Iterate over candidate debug images. * Keep track of "interesting" ones (those which have a symtab, dynsym, * and/or opd section) for processing. @@ -887,200 +880,6 @@ struct map *map_groups__find_by_name(struct map_groups *mg, return NULL; } -static int map_groups__set_modules_path_dir(struct map_groups *mg, - const char *dir_name) -{ - struct dirent *dent; - DIR *dir = opendir(dir_name); - int ret = 0; - - if (!dir) { - pr_debug("%s: cannot open %s dir\n", __func__, dir_name); - return -1; - } - - while ((dent = readdir(dir)) != NULL) { - char path[PATH_MAX]; - struct stat st; - - /*sshfs might return bad dent->d_type, so we have to stat*/ - snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name); - if (stat(path, &st)) - continue; - - if (S_ISDIR(st.st_mode)) { - if (!strcmp(dent->d_name, ".") || - !strcmp(dent->d_name, "..")) - continue; - - ret = map_groups__set_modules_path_dir(mg, path); - if (ret < 0) - goto out; - } else { - char *dot = strrchr(dent->d_name, '.'), - dso_name[PATH_MAX]; - struct map *map; - char *long_name; - - if (dot == NULL || strcmp(dot, ".ko")) - continue; - snprintf(dso_name, sizeof(dso_name), "[%.*s]", - (int)(dot - dent->d_name), dent->d_name); - - strxfrchar(dso_name, '-', '_'); - map = map_groups__find_by_name(mg, MAP__FUNCTION, - dso_name); - if (map == NULL) - continue; - - long_name = strdup(path); - if (long_name == NULL) { - ret = -1; - goto out; - } - dso__set_long_name(map->dso, long_name); - map->dso->lname_alloc = 1; - dso__kernel_module_get_build_id(map->dso, ""); - } - } - -out: - closedir(dir); - return ret; -} - -static char *get_kernel_version(const char *root_dir) -{ - char version[PATH_MAX]; - FILE *file; - char *name, *tmp; - const char *prefix = "Linux version "; - - sprintf(version, "%s/proc/version", root_dir); - file = fopen(version, "r"); - if (!file) - return NULL; - - version[0] = '\0'; - tmp = fgets(version, sizeof(version), file); - fclose(file); - - name = strstr(version, prefix); - if (!name) - return NULL; - name += strlen(prefix); - tmp = strchr(name, ' '); - if (tmp) - *tmp = '\0'; - - return strdup(name); -} - -static int machine__set_modules_path(struct machine *machine) -{ - char *version; - char modules_path[PATH_MAX]; - - version = get_kernel_version(machine->root_dir); - if (!version) - return -1; - - snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel", - machine->root_dir, version); - free(version); - - return map_groups__set_modules_path_dir(&machine->kmaps, modules_path); -} - -struct map *machine__new_module(struct machine *machine, u64 start, - const char *filename) -{ - struct map *map; - struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename); - - if (dso == NULL) - return NULL; - - map = map__new2(start, dso, MAP__FUNCTION); - if (map == NULL) - return NULL; - - if (machine__is_host(machine)) - dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE; - else - dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE; - map_groups__insert(&machine->kmaps, map); - return map; -} - -static int machine__create_modules(struct machine *machine) -{ - char *line = NULL; - size_t n; - FILE *file; - struct map *map; - const char *modules; - char path[PATH_MAX]; - - if (machine__is_default_guest(machine)) - modules = symbol_conf.default_guest_modules; - else { - sprintf(path, "%s/proc/modules", machine->root_dir); - modules = path; - } - - if (symbol__restricted_filename(path, "/proc/modules")) - return -1; - - file = fopen(modules, "r"); - if (file == NULL) - return -1; - - while (!feof(file)) { - char name[PATH_MAX]; - u64 start; - char *sep; - int line_len; - - line_len = getline(&line, &n, file); - if (line_len < 0) - break; - - if (!line) - goto out_failure; - - line[--line_len] = '\0'; /* \n */ - - sep = strrchr(line, 'x'); - if (sep == NULL) - continue; - - hex2u64(sep + 1, &start); - - sep = strchr(line, ' '); - if (sep == NULL) - continue; - - *sep = '\0'; - - snprintf(name, sizeof(name), "[%s]", line); - map = machine__new_module(machine, start, name); - if (map == NULL) - goto out_delete_line; - dso__kernel_module_get_build_id(map->dso, machine->root_dir); - } - - free(line); - fclose(file); - - return machine__set_modules_path(machine); - -out_delete_line: - free(line); -out_failure: - return -1; -} - int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, symbol_filter_t filter) { @@ -1124,8 +923,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, filename = dso__build_id_filename(dso, NULL, 0); if (filename != NULL) { err = dso__load_vmlinux(dso, map, filename, filter); - if (err > 0) + if (err > 0) { + dso->lname_alloc = 1; goto out; + } free(filename); } @@ -1133,6 +934,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map, err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter); if (err > 0) { dso__set_long_name(dso, strdup(vmlinux_path[i])); + dso->lname_alloc = 1; break; } } @@ -1172,6 +974,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map, if (err > 0) { dso__set_long_name(dso, strdup(symbol_conf.vmlinux_name)); + dso->lname_alloc = 1; goto out_fixup; } return err; @@ -1300,195 +1103,6 @@ out_try_fixup: return err; } -size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp) -{ - struct rb_node *nd; - size_t ret = 0; - - for (nd = rb_first(machines); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += __dsos__fprintf(&pos->kernel_dsos, fp); - ret += __dsos__fprintf(&pos->user_dsos, fp); - } - - return ret; -} - -size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp, - bool with_hits) -{ - return __dsos__fprintf_buildid(&machine->kernel_dsos, fp, with_hits) + - __dsos__fprintf_buildid(&machine->user_dsos, fp, with_hits); -} - -size_t machines__fprintf_dsos_buildid(struct rb_root *machines, - FILE *fp, bool with_hits) -{ - struct rb_node *nd; - size_t ret = 0; - - for (nd = rb_first(machines); nd; nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret += machine__fprintf_dsos_buildid(pos, fp, with_hits); - } - return ret; -} - -static struct dso *machine__get_kernel(struct machine *machine) -{ - const char *vmlinux_name = NULL; - struct dso *kernel; - - if (machine__is_host(machine)) { - vmlinux_name = symbol_conf.vmlinux_name; - if (!vmlinux_name) - vmlinux_name = "[kernel.kallsyms]"; - - kernel = dso__kernel_findnew(machine, vmlinux_name, - "[kernel]", - DSO_TYPE_KERNEL); - } else { - char bf[PATH_MAX]; - - if (machine__is_default_guest(machine)) - vmlinux_name = symbol_conf.default_guest_vmlinux_name; - if (!vmlinux_name) - vmlinux_name = machine__mmap_name(machine, bf, - sizeof(bf)); - - kernel = dso__kernel_findnew(machine, vmlinux_name, - "[guest.kernel]", - DSO_TYPE_GUEST_KERNEL); - } - - if (kernel != NULL && (!kernel->has_build_id)) - dso__read_running_kernel_build_id(kernel, machine); - - return kernel; -} - -struct process_args { - u64 start; -}; - -static int symbol__in_kernel(void *arg, const char *name, - char type __maybe_unused, u64 start) -{ - struct process_args *args = arg; - - if (strchr(name, '[')) - return 0; - - args->start = start; - return 1; -} - -/* Figure out the start address of kernel map from /proc/kallsyms */ -static u64 machine__get_kernel_start_addr(struct machine *machine) -{ - const char *filename; - char path[PATH_MAX]; - struct process_args args; - - if (machine__is_host(machine)) { - filename = "/proc/kallsyms"; - } else { - if (machine__is_default_guest(machine)) - filename = (char *)symbol_conf.default_guest_kallsyms; - else { - sprintf(path, "%s/proc/kallsyms", machine->root_dir); - filename = path; - } - } - - if (symbol__restricted_filename(filename, "/proc/kallsyms")) - return 0; - - if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0) - return 0; - - return args.start; -} - -int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) -{ - enum map_type type; - u64 start = machine__get_kernel_start_addr(machine); - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - - machine->vmlinux_maps[type] = map__new2(start, kernel, type); - if (machine->vmlinux_maps[type] == NULL) - return -1; - - machine->vmlinux_maps[type]->map_ip = - machine->vmlinux_maps[type]->unmap_ip = - identity__map_ip; - kmap = map__kmap(machine->vmlinux_maps[type]); - kmap->kmaps = &machine->kmaps; - map_groups__insert(&machine->kmaps, - machine->vmlinux_maps[type]); - } - - return 0; -} - -void machine__destroy_kernel_maps(struct machine *machine) -{ - enum map_type type; - - for (type = 0; type < MAP__NR_TYPES; ++type) { - struct kmap *kmap; - - if (machine->vmlinux_maps[type] == NULL) - continue; - - kmap = map__kmap(machine->vmlinux_maps[type]); - map_groups__remove(&machine->kmaps, - machine->vmlinux_maps[type]); - if (kmap->ref_reloc_sym) { - /* - * ref_reloc_sym is shared among all maps, so free just - * on one of them. - */ - if (type == MAP__FUNCTION) { - free((char *)kmap->ref_reloc_sym->name); - kmap->ref_reloc_sym->name = NULL; - free(kmap->ref_reloc_sym); - } - kmap->ref_reloc_sym = NULL; - } - - map__delete(machine->vmlinux_maps[type]); - machine->vmlinux_maps[type] = NULL; - } -} - -int machine__create_kernel_maps(struct machine *machine) -{ - struct dso *kernel = machine__get_kernel(machine); - - if (kernel == NULL || - __machine__create_kernel_maps(machine, kernel) < 0) - return -1; - - if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { - if (machine__is_host(machine)) - pr_debug("Problems creating module maps, " - "continuing anyway...\n"); - else - pr_debug("Problems creating module maps for guest %d, " - "continuing anyway...\n", machine->pid); - } - - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&machine->kmaps); - return 0; -} - static void vmlinux_path__exit(void) { while (--vmlinux_path__nr_entries >= 0) { @@ -1549,25 +1163,6 @@ out_fail: return -1; } -size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp) -{ - int i; - size_t printed = 0; - struct dso *kdso = machine->vmlinux_maps[MAP__FUNCTION]->dso; - - if (kdso->has_build_id) { - char filename[PATH_MAX]; - if (dso__build_id_filename(kdso, filename, sizeof(filename))) - printed += fprintf(fp, "[0] %s\n", filename); - } - - for (i = 0; i < vmlinux_path__nr_entries; ++i) - printed += fprintf(fp, "[%d] %s\n", - i + kdso->has_build_id, vmlinux_path[i]); - - return printed; -} - static int setup_list(struct strlist **list, const char *list_str, const char *list_name) { @@ -1671,108 +1266,3 @@ void symbol__exit(void) symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; symbol_conf.initialized = false; } - -int machines__create_kernel_maps(struct rb_root *machines, pid_t pid) -{ - struct machine *machine = machines__findnew(machines, pid); - - if (machine == NULL) - return -1; - - return machine__create_kernel_maps(machine); -} - -int machines__create_guest_kernel_maps(struct rb_root *machines) -{ - int ret = 0; - struct dirent **namelist = NULL; - int i, items = 0; - char path[PATH_MAX]; - pid_t pid; - char *endp; - - if (symbol_conf.default_guest_vmlinux_name || - symbol_conf.default_guest_modules || - symbol_conf.default_guest_kallsyms) { - machines__create_kernel_maps(machines, DEFAULT_GUEST_KERNEL_ID); - } - - if (symbol_conf.guestmount) { - items = scandir(symbol_conf.guestmount, &namelist, NULL, NULL); - if (items <= 0) - return -ENOENT; - for (i = 0; i < items; i++) { - if (!isdigit(namelist[i]->d_name[0])) { - /* Filter out . and .. */ - continue; - } - pid = (pid_t)strtol(namelist[i]->d_name, &endp, 10); - if ((*endp != '\0') || - (endp == namelist[i]->d_name) || - (errno == ERANGE)) { - pr_debug("invalid directory (%s). Skipping.\n", - namelist[i]->d_name); - continue; - } - sprintf(path, "%s/%s/proc/kallsyms", - symbol_conf.guestmount, - namelist[i]->d_name); - ret = access(path, R_OK); - if (ret) { - pr_debug("Can't access file %s\n", path); - goto failure; - } - machines__create_kernel_maps(machines, pid); - } -failure: - free(namelist); - } - - return ret; -} - -void machines__destroy_guest_kernel_maps(struct rb_root *machines) -{ - struct rb_node *next = rb_first(machines); - - while (next) { - struct machine *pos = rb_entry(next, struct machine, rb_node); - - next = rb_next(&pos->rb_node); - rb_erase(&pos->rb_node, machines); - machine__delete(pos); - } -} - -int machine__load_kallsyms(struct machine *machine, const char *filename, - enum map_type type, symbol_filter_t filter) -{ - struct map *map = machine->vmlinux_maps[type]; - int ret = dso__load_kallsyms(map->dso, filename, map, filter); - - if (ret > 0) { - dso__set_loaded(map->dso, type); - /* - * Since /proc/kallsyms will have multiple sessions for the - * kernel, with modules between them, fixup the end of all - * sections. - */ - __map_groups__fixup_end(&machine->kmaps, type); - } - - return ret; -} - -int machine__load_vmlinux_path(struct machine *machine, enum map_type type, - symbol_filter_t filter) -{ - struct map *map = machine->vmlinux_maps[type]; - int ret = dso__load_vmlinux_path(map->dso, map, filter); - - if (ret > 0) { - dso__set_loaded(map->dso, type); - map__reloc_vmlinux(map); - } - - return ret; -} diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index de68f98..b62ca37 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -16,8 +16,8 @@ #ifdef LIBELF_SUPPORT #include <libelf.h> #include <gelf.h> -#include <elf.h> #endif +#include <elf.h> #include "dso.h" @@ -96,7 +96,8 @@ struct symbol_conf { initialized, kptr_restrict, annotate_asm_raw, - annotate_src; + annotate_src, + event_group; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -120,6 +121,8 @@ struct symbol_conf { }; extern struct symbol_conf symbol_conf; +extern int vmlinux_path__nr_entries; +extern char **vmlinux_path; static inline void *symbol__priv(struct symbol *sym) { @@ -223,6 +226,8 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym, size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); +bool symbol__restricted_filename(const char *filename, + const char *restricted_filename); int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, symbol_filter_t filter, diff --git a/tools/perf/util/sysfs.c b/tools/perf/util/sysfs.c index 48c6902..f71e9ea 100644 --- a/tools/perf/util/sysfs.c +++ b/tools/perf/util/sysfs.c @@ -8,7 +8,7 @@ static const char * const sysfs_known_mountpoints[] = { }; static int sysfs_found; -char sysfs_mountpoint[PATH_MAX]; +char sysfs_mountpoint[PATH_MAX + 1]; static int sysfs_valid_mountpoint(const char *sysfs) { diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index df59623..632e40e 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -54,10 +54,10 @@ int thread__comm_len(struct thread *self) return self->comm_len; } -static size_t thread__fprintf(struct thread *self, FILE *fp) +size_t thread__fprintf(struct thread *thread, FILE *fp) { - return fprintf(fp, "Thread %d %s\n", self->pid, self->comm) + - map_groups__fprintf(&self->mg, verbose, fp); + return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) + + map_groups__fprintf(&thread->mg, verbose, fp); } void thread__insert_map(struct thread *self, struct map *map) @@ -84,17 +84,3 @@ int thread__fork(struct thread *self, struct thread *parent) return -ENOMEM; return 0; } - -size_t machine__fprintf(struct machine *machine, FILE *fp) -{ - size_t ret = 0; - struct rb_node *nd; - - for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) { - struct thread *pos = rb_entry(nd, struct thread, rb_node); - - ret += thread__fprintf(pos, fp); - } - - return ret; -} diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index f2fa17c..5ad2664 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -30,6 +30,7 @@ int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); void thread__insert_map(struct thread *self, struct map *map); int thread__fork(struct thread *self, struct thread *parent); +size_t thread__fprintf(struct thread *thread, FILE *fp); static inline struct map *thread__find_map(struct thread *self, enum map_type type, u64 addr) diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 884dde9..54d37a4 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -26,6 +26,8 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) float samples_per_sec = top->samples / top->delay_secs; float ksamples_per_sec = top->kernel_samples / top->delay_secs; float esamples_percent = (100.0 * top->exact_samples) / top->samples; + struct perf_record_opts *opts = &top->record_opts; + struct perf_target *target = &opts->target; size_t ret = 0; if (!perf_guest) { @@ -61,31 +63,31 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) struct perf_evsel *first = perf_evlist__first(top->evlist); ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", (uint64_t)first->attr.sample_period, - top->freq ? "Hz" : ""); + opts->freq ? "Hz" : ""); } ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel)); ret += SNPRINTF(bf + ret, size - ret, "], "); - if (top->target.pid) + if (target->pid) ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s", - top->target.pid); - else if (top->target.tid) + target->pid); + else if (target->tid) ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s", - top->target.tid); - else if (top->target.uid_str != NULL) + target->tid); + else if (target->uid_str != NULL) ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", - top->target.uid_str); + target->uid_str); else ret += SNPRINTF(bf + ret, size - ret, " (all"); - if (top->target.cpu_list) + if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", top->evlist->cpus->nr > 1 ? "s" : "", - top->target.cpu_list); + target->cpu_list); else { - if (top->target.tid) + if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index 86ff1b1..7ebf357 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -14,7 +14,7 @@ struct perf_session; struct perf_top { struct perf_tool tool; struct perf_evlist *evlist; - struct perf_target target; + struct perf_record_opts record_opts; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -24,24 +24,16 @@ struct perf_top { u64 exact_samples; u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; - int freq; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; bool sort_has_symbols; - bool dont_use_callchains; bool kptr_restrict_warned; bool vmlinux_warned; - bool inherit; - bool group; - bool sample_id_all_missing; - bool exclude_guest_missing; bool dump_symtab; struct hist_entry *sym_filter_entry; struct perf_evsel *sym_evsel; struct perf_session *session; struct winsize winsize; - unsigned int mmap_pages; - int default_interval; int realtime_prio; int sym_pcnt_filter; const char *sym_filter; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 5906e84..805d1f5 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -12,6 +12,8 @@ */ unsigned int page_size; +bool test_attr__enabled; + bool perf_host = true; bool perf_guest = false; @@ -218,3 +220,25 @@ void dump_stack(void) #else void dump_stack(void) {} #endif + +void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index c233091..09b4c26 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -265,10 +265,14 @@ bool is_power_of_2(unsigned long n) size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); +char *ltrim(char *s); char *rtrim(char *s); void dump_stack(void); extern unsigned int page_size; +struct winsize; +void get_term_dimensions(struct winsize *ws); + #endif diff --git a/tools/vm/.gitignore b/tools/vm/.gitignore new file mode 100644 index 0000000..44f095f --- /dev/null +++ b/tools/vm/.gitignore @@ -0,0 +1,2 @@ +slabinfo +page-types |