diff options
| author | Arnd Bergmann <arnd@arndb.de> | 2012-07-25 12:33:45 (GMT) |
|---|---|---|
| committer | Arnd Bergmann <arnd@arndb.de> | 2012-07-25 12:35:04 (GMT) |
| commit | 8cef081c71dd4e16a01a1e63cedab21eef8b5735 (patch) | |
| tree | b5b0fb5ab09dc60dee5fc8fd8e980359abbd1b1e /arch | |
| parent | 3d55c29fb24286f350f04021bef2dd799e25dd20 (diff) | |
| parent | 9161c3b796a2841a9a7be3d9c9dd121269ce90e8 (diff) | |
| download | linux-8cef081c71dd4e16a01a1e63cedab21eef8b5735.tar.xz | |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into fixes
The merge of the 'clk-for-linus' branch caused an automated
merge failure. Pull that in here so we can fix the problem.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Diffstat (limited to 'arch')
602 files changed, 20624 insertions, 8601 deletions
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 1a62963..9816d5a 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -59,15 +59,13 @@ struct pci_controller *pci_isa_hose; * Quirks. */ -static void __init -quirk_isa_bridge(struct pci_dev *dev) +static void __devinit quirk_isa_bridge(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_ISA << 8; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82378, quirk_isa_bridge); -static void __init -quirk_cypress(struct pci_dev *dev) +static void __devinit quirk_cypress(struct pci_dev *dev) { /* The Notorious Cy82C693 chip. */ @@ -106,8 +104,7 @@ quirk_cypress(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CONTAQ, PCI_DEVICE_ID_CONTAQ_82C693, quirk_cypress); /* Called for each device after PCI setup is done. */ -static void __init -pcibios_fixup_final(struct pci_dev *dev) +static void __devinit pcibios_fixup_final(struct pci_dev *dev) { unsigned int class = dev->class >> 8; @@ -198,12 +195,6 @@ pcibios_init(void) subsys_initcall(pcibios_init); -char * __devinit -pcibios_setup(char *str) -{ - return str; -} - #ifdef ALPHA_RESTORE_SRM_SETUP static struct pdev_srm_saved_conf *srm_saved_configs; @@ -359,7 +350,7 @@ common_init_pci(void) hose, &resources); hose->bus = bus; hose->need_domain_info = need_domain_info; - next_busno = bus->subordinate + 1; + next_busno = bus->busn_res.end + 1; /* Don't allow 8-bit bus number overflow inside the hose - reserve some space for bridges. */ if (next_busno > 224) { diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index c7e6d20..b25c9d3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -273,8 +273,8 @@ config ARCH_INTEGRATOR bool "ARM Ltd. Integrator family" select ARM_AMBA select ARCH_HAS_CPUFREQ - select CLKDEV_LOOKUP - select HAVE_MACH_CLKDEV + select COMMON_CLK + select CLK_VERSATILE select HAVE_TCM select ICST select GENERIC_CLOCKEVENTS @@ -336,6 +336,7 @@ config ARCH_VEXPRESS select ICST select NO_IOPORT select PLAT_VERSATILE + select PLAT_VERSATILE_CLOCK select PLAT_VERSATILE_CLCD select REGULATOR_FIXED_VOLTAGE if REGULATOR help @@ -372,6 +373,7 @@ config ARCH_HIGHBANK select ARM_TIMER_SP804 select CACHE_L2X0 select CLKDEV_LOOKUP + select COMMON_CLK select CPU_V7 select GENERIC_CLOCKEVENTS select HAVE_ARM_SCU @@ -929,7 +931,7 @@ config ARCH_U300 select ARM_VIC select GENERIC_CLOCKEVENTS select CLKDEV_LOOKUP - select HAVE_MACH_CLKDEV + select COMMON_CLK select GENERIC_GPIO select ARCH_REQUIRE_GPIOLIB help diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts index 83e7229..2e1cfa0 100644 --- a/arch/arm/boot/dts/highbank.dts +++ b/arch/arm/boot/dts/highbank.dts @@ -1,5 +1,5 @@ /* - * Copyright 2011 Calxeda, Inc. + * Copyright 2011-2012 Calxeda, Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -24,6 +24,7 @@ compatible = "calxeda,highbank"; #address-cells = <1>; #size-cells = <1>; + clock-ranges; cpus { #address-cells = <1>; @@ -33,24 +34,32 @@ compatible = "arm,cortex-a9"; reg = <0>; next-level-cache = <&L2>; + clocks = <&a9pll>; + clock-names = "cpu"; }; cpu@1 { compatible = "arm,cortex-a9"; reg = <1>; next-level-cache = <&L2>; + clocks = <&a9pll>; + clock-names = "cpu"; }; cpu@2 { compatible = "arm,cortex-a9"; reg = <2>; next-level-cache = <&L2>; + clocks = <&a9pll>; + clock-names = "cpu"; }; cpu@3 { compatible = "arm,cortex-a9"; reg = <3>; next-level-cache = <&L2>; + clocks = <&a9pll>; + clock-names = "cpu"; }; }; @@ -75,12 +84,14 @@ compatible = "arm,cortex-a9-twd-timer"; reg = <0xfff10600 0x20>; interrupts = <1 13 0xf01>; + clocks = <&a9periphclk>; }; watchdog@fff10620 { compatible = "arm,cortex-a9-twd-wdt"; reg = <0xfff10620 0x20>; interrupts = <1 14 0xf01>; + clocks = <&a9periphclk>; }; intc: interrupt-controller@fff11000 { @@ -116,12 +127,15 @@ compatible = "calxeda,hb-sdhci"; reg = <0xffe0e000 0x1000>; interrupts = <0 90 4>; + clocks = <&eclk>; }; ipc@fff20000 { compatible = "arm,pl320", "arm,primecell"; reg = <0xfff20000 0x1000>; interrupts = <0 7 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; gpioe: gpio@fff30000 { @@ -130,6 +144,8 @@ gpio-controller; reg = <0xfff30000 0x1000>; interrupts = <0 14 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; gpiof: gpio@fff31000 { @@ -138,6 +154,8 @@ gpio-controller; reg = <0xfff31000 0x1000>; interrupts = <0 15 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; gpiog: gpio@fff32000 { @@ -146,6 +164,8 @@ gpio-controller; reg = <0xfff32000 0x1000>; interrupts = <0 16 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; gpioh: gpio@fff33000 { @@ -154,24 +174,32 @@ gpio-controller; reg = <0xfff33000 0x1000>; interrupts = <0 17 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; timer { compatible = "arm,sp804", "arm,primecell"; reg = <0xfff34000 0x1000>; interrupts = <0 18 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; rtc@fff35000 { compatible = "arm,pl031", "arm,primecell"; reg = <0xfff35000 0x1000>; interrupts = <0 19 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; serial@fff36000 { compatible = "arm,pl011", "arm,primecell"; reg = <0xfff36000 0x1000>; interrupts = <0 20 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; smic@fff3a000 { @@ -186,12 +214,73 @@ sregs@fff3c000 { compatible = "calxeda,hb-sregs"; reg = <0xfff3c000 0x1000>; + + clocks { + #address-cells = <1>; + #size-cells = <0>; + + osc: oscillator { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <33333000>; + }; + + ddrpll: ddrpll { + #clock-cells = <0>; + compatible = "calxeda,hb-pll-clock"; + clocks = <&osc>; + reg = <0x108>; + }; + + a9pll: a9pll { + #clock-cells = <0>; + compatible = "calxeda,hb-pll-clock"; + clocks = <&osc>; + reg = <0x100>; + }; + + a9periphclk: a9periphclk { + #clock-cells = <0>; + compatible = "calxeda,hb-a9periph-clock"; + clocks = <&a9pll>; + reg = <0x104>; + }; + + a9bclk: a9bclk { + #clock-cells = <0>; + compatible = "calxeda,hb-a9bus-clock"; + clocks = <&a9pll>; + reg = <0x104>; + }; + + emmcpll: emmcpll { + #clock-cells = <0>; + compatible = "calxeda,hb-pll-clock"; + clocks = <&osc>; + reg = <0x10C>; + }; + + eclk: eclk { + #clock-cells = <0>; + compatible = "calxeda,hb-emmc-clock"; + clocks = <&emmcpll>; + reg = <0x114>; + }; + + pclk: pclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <150000000>; + }; + }; }; dma@fff3d000 { compatible = "arm,pl330", "arm,primecell"; reg = <0xfff3d000 0x1000>; interrupts = <0 92 4>; + clocks = <&pclk>; + clock-names = "apb_pclk"; }; ethernet@fff50000 { diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 2555250..2b2f25e 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -253,7 +253,7 @@ static void __devinit pci_fixup_cy82c693(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CONTAQ, PCI_DEVICE_ID_CONTAQ_82C693, pci_fixup_cy82c693); -static void __init pci_fixup_it8152(struct pci_dev *dev) +static void __devinit pci_fixup_it8152(struct pci_dev *dev) { int i; /* fixup for ITE 8152 devices */ @@ -461,7 +461,7 @@ static void __init pcibios_init_hw(struct hw_pci *hw, struct list_head *head) if (!sys->bus) panic("PCI: unable to scan bus!"); - busnr = sys->bus->subordinate + 1; + busnr = sys->bus->busn_res.end + 1; list_add(&sys->node, head); } else { diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig index 2ce1ef0..ab99c3c 100644 --- a/arch/arm/mach-davinci/Kconfig +++ b/arch/arm/mach-davinci/Kconfig @@ -62,7 +62,6 @@ config MACH_DAVINCI_EVM bool "TI DM644x EVM" default ARCH_DAVINCI_DM644x depends on ARCH_DAVINCI_DM644x - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -72,7 +71,6 @@ config MACH_DAVINCI_EVM config MACH_SFFSDR bool "Lyrtech SFFSDR" depends on ARCH_DAVINCI_DM644x - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -106,7 +104,6 @@ config MACH_DAVINCI_DM6467_EVM default ARCH_DAVINCI_DM646x depends on ARCH_DAVINCI_DM646x select MACH_DAVINCI_DM6467TEVM - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -120,7 +117,6 @@ config MACH_DAVINCI_DM365_EVM bool "TI DM365 EVM" default ARCH_DAVINCI_DM365 depends on ARCH_DAVINCI_DM365 - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -132,7 +128,6 @@ config MACH_DAVINCI_DA830_EVM default ARCH_DAVINCI_DA830 depends on ARCH_DAVINCI_DA830 select GPIO_PCF857X - select MISC_DEVICES select EEPROM_AT24 select I2C help @@ -219,7 +214,6 @@ config MACH_TNETV107X config MACH_MITYOMAPL138 bool "Critical Link MityDSP-L138/MityARM-1808 SoM" depends on ARCH_DAVINCI_DA850 - select MISC_DEVICES select EEPROM_AT24 select I2C help diff --git a/arch/arm/mach-highbank/Makefile b/arch/arm/mach-highbank/Makefile index ded4652..3ec8bdd 100644 --- a/arch/arm/mach-highbank/Makefile +++ b/arch/arm/mach-highbank/Makefile @@ -1,4 +1,4 @@ -obj-y := clock.o highbank.o system.o smc.o +obj-y := highbank.o system.o smc.o plus_sec := $(call as-instr,.arch_extension sec,+sec) AFLAGS_smc.o :=-Wa,-march=armv7-a$(plus_sec) diff --git a/arch/arm/mach-highbank/clock.c b/arch/arm/mach-highbank/clock.c deleted file mode 100644 index c25a2ae..0000000 --- a/arch/arm/mach-highbank/clock.c +++ /dev/null @@ -1,62 +0,0 @@ -/* - * Copyright 2011 Calxeda, Inc. - * - * 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/kernel.h> -#include <linux/errno.h> -#include <linux/clk.h> -#include <linux/clkdev.h> - -struct clk { - unsigned long rate; -}; - -int clk_enable(struct clk *clk) -{ - return 0; -} - -void clk_disable(struct clk *clk) -{} - -unsigned long clk_get_rate(struct clk *clk) -{ - return clk->rate; -} - -long clk_round_rate(struct clk *clk, unsigned long rate) -{ - return clk->rate; -} - -int clk_set_rate(struct clk *clk, unsigned long rate) -{ - return 0; -} - -static struct clk eclk = { .rate = 200000000 }; -static struct clk pclk = { .rate = 150000000 }; - -static struct clk_lookup lookups[] = { - { .clk = &pclk, .con_id = "apb_pclk", }, - { .clk = &pclk, .dev_id = "sp804", }, - { .clk = &eclk, .dev_id = "ffe0e000.sdhci", }, - { .clk = &pclk, .dev_id = "fff36000.serial", }, -}; - -void __init highbank_clocks_init(void) -{ - clkdev_add_table(lookups, ARRAY_SIZE(lookups)); -} diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index 8777612..d75b0a7 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -105,6 +105,11 @@ static void __init highbank_init_irq(void) #endif } +static struct clk_lookup lookup = { + .dev_id = "sp804", + .con_id = NULL, +}; + static void __init highbank_timer_init(void) { int irq; @@ -122,6 +127,8 @@ static void __init highbank_timer_init(void) irq = irq_of_parse_and_map(np, 0); highbank_clocks_init(); + lookup.clk = of_clk_get(np, 0); + clkdev_add(&lookup); sp804_clocksource_and_sched_clock_init(timer_base + 0x20, "timer1"); sp804_clockevents_init(timer_base, irq, "timer0"); diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c index eaf6c63..ebf680b 100644 --- a/arch/arm/mach-integrator/core.c +++ b/arch/arm/mach-integrator/core.c @@ -21,7 +21,6 @@ #include <linux/amba/bus.h> #include <linux/amba/serial.h> #include <linux/io.h> -#include <linux/clkdev.h> #include <mach/hardware.h> #include <mach/platform.h> @@ -41,17 +40,17 @@ static struct amba_pl010_data integrator_uart_data; #define KMI0_IRQ { IRQ_KMIINT0 } #define KMI1_IRQ { IRQ_KMIINT1 } -static AMBA_APB_DEVICE(rtc, "mb:15", 0, +static AMBA_APB_DEVICE(rtc, "rtc", 0, INTEGRATOR_RTC_BASE, INTEGRATOR_RTC_IRQ, NULL); -static AMBA_APB_DEVICE(uart0, "mb:16", 0, +static AMBA_APB_DEVICE(uart0, "uart0", 0, INTEGRATOR_UART0_BASE, INTEGRATOR_UART0_IRQ, &integrator_uart_data); -static AMBA_APB_DEVICE(uart1, "mb:17", 0, +static AMBA_APB_DEVICE(uart1, "uart1", 0, INTEGRATOR_UART1_BASE, INTEGRATOR_UART1_IRQ, &integrator_uart_data); -static AMBA_APB_DEVICE(kmi0, "mb:18", 0, KMI0_BASE, KMI0_IRQ, NULL); -static AMBA_APB_DEVICE(kmi1, "mb:19", 0, KMI1_BASE, KMI1_IRQ, NULL); +static AMBA_APB_DEVICE(kmi0, "kmi0", 0, KMI0_BASE, KMI0_IRQ, NULL); +static AMBA_APB_DEVICE(kmi1, "kmi1", 0, KMI1_BASE, KMI1_IRQ, NULL); static struct amba_device *amba_devs[] __initdata = { &rtc_device, @@ -61,50 +60,6 @@ static struct amba_device *amba_devs[] __initdata = { &kmi1_device, }; -/* - * These are fixed clocks. - */ -static struct clk clk24mhz = { - .rate = 24000000, -}; - -static struct clk uartclk = { - .rate = 14745600, -}; - -static struct clk dummy_apb_pclk; - -static struct clk_lookup lookups[] = { - { /* Bus clock */ - .con_id = "apb_pclk", - .clk = &dummy_apb_pclk, - }, { - /* Integrator/AP timer frequency */ - .dev_id = "ap_timer", - .clk = &clk24mhz, - }, { /* UART0 */ - .dev_id = "mb:16", - .clk = &uartclk, - }, { /* UART1 */ - .dev_id = "mb:17", - .clk = &uartclk, - }, { /* KMI0 */ - .dev_id = "mb:18", - .clk = &clk24mhz, - }, { /* KMI1 */ - .dev_id = "mb:19", - .clk = &clk24mhz, - }, { /* MMCI - IntegratorCP */ - .dev_id = "mb:1c", - .clk = &uartclk, - } -}; - -void __init integrator_init_early(void) -{ - clkdev_add_table(lookups, ARRAY_SIZE(lookups)); -} - static int __init integrator_init(void) { int i; diff --git a/arch/arm/mach-integrator/include/mach/clkdev.h b/arch/arm/mach-integrator/include/mach/clkdev.h deleted file mode 100644 index bfe0767..0000000 --- a/arch/arm/mach-integrator/include/mach/clkdev.h +++ /dev/null @@ -1,26 +0,0 @@ -#ifndef __ASM_MACH_CLKDEV_H -#define __ASM_MACH_CLKDEV_H - -#include <linux/module.h> -#include <plat/clock.h> - -struct clk { - unsigned long rate; - const struct clk_ops *ops; - struct module *owner; - const struct icst_params *params; - void __iomem *vcoreg; - void *data; -}; - -static inline int __clk_get(struct clk *clk) -{ - return try_module_get(clk->owner); -} - -static inline void __clk_put(struct clk *clk) -{ - module_put(clk->owner); -} - -#endif diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index c857501..7b1055c 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -33,6 +33,7 @@ #include <linux/io.h> #include <linux/mtd/physmap.h> #include <linux/clk.h> +#include <linux/platform_data/clk-integrator.h> #include <video/vga.h> #include <mach/hardware.h> @@ -174,6 +175,7 @@ static void __init ap_init_irq(void) fpga_irq_init(VA_IC_BASE, "SC", IRQ_PIC_START, -1, INTEGRATOR_SC_VALID_INT, NULL); + integrator_clk_init(false); } #ifdef CONFIG_PM @@ -440,6 +442,10 @@ static void integrator_clockevent_init(unsigned long inrate) 0xffffU); } +void __init ap_init_early(void) +{ +} + /* * Set up timer(s). */ @@ -471,7 +477,7 @@ MACHINE_START(INTEGRATOR, "ARM-Integrator") .reserve = integrator_reserve, .map_io = ap_map_io, .nr_irqs = NR_IRQS_INTEGRATOR_AP, - .init_early = integrator_init_early, + .init_early = ap_init_early, .init_irq = ap_init_irq, .handle_irq = fpga_handle_irq, .timer = &ap_timer, diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c index a56c536..82d5c83 100644 --- a/arch/arm/mach-integrator/integrator_cp.c +++ b/arch/arm/mach-integrator/integrator_cp.c @@ -21,8 +21,8 @@ #include <linux/amba/mmci.h> #include <linux/io.h> #include <linux/gfp.h> -#include <linux/clkdev.h> #include <linux/mtd/physmap.h> +#include <linux/platform_data/clk-integrator.h> #include <mach/hardware.h> #include <mach/platform.h> @@ -171,65 +171,10 @@ static void __init intcp_init_irq(void) fpga_irq_init(INTCP_VA_SIC_BASE, "SIC", IRQ_SIC_START, IRQ_CP_CPPLDINT, sic_mask, NULL); + integrator_clk_init(true); } /* - * Clock handling - */ -#define CM_LOCK (__io_address(INTEGRATOR_HDR_BASE)+INTEGRATOR_HDR_LOCK_OFFSET) -#define CM_AUXOSC (__io_address(INTEGRATOR_HDR_BASE)+0x1c) - -static const struct icst_params cp_auxvco_params = { - .ref = 24000000, - .vco_max = ICST525_VCO_MAX_5V, - .vco_min = ICST525_VCO_MIN, - .vd_min = 8, - .vd_max = 263, - .rd_min = 3, - .rd_max = 65, - .s2div = icst525_s2div, - .idx2s = icst525_idx2s, -}; - -static void cp_auxvco_set(struct clk *clk, struct icst_vco vco) -{ - u32 val; - - val = readl(clk->vcoreg) & ~0x7ffff; - val |= vco.v | (vco.r << 9) | (vco.s << 16); - - writel(0xa05f, CM_LOCK); - writel(val, clk->vcoreg); - writel(0, CM_LOCK); -} - -static const struct clk_ops cp_auxclk_ops = { - .round = icst_clk_round, - .set = icst_clk_set, - .setvco = cp_auxvco_set, -}; - -static struct clk cp_auxclk = { - .ops = &cp_auxclk_ops, - .params = &cp_auxvco_params, - .vcoreg = CM_AUXOSC, -}; - -static struct clk sp804_clk = { - .rate = 1000000, -}; - -static struct clk_lookup cp_lookups[] = { - { /* CLCD */ - .dev_id = "mb:c0", - .clk = &cp_auxclk, - }, { /* SP804 timers */ - .dev_id = "sp804", - .clk = &sp804_clk, - }, -}; - -/* * Flash handling. */ static int intcp_flash_init(struct platform_device *dev) @@ -336,10 +281,10 @@ static struct mmci_platform_data mmc_data = { #define INTEGRATOR_CP_MMC_IRQS { IRQ_CP_MMCIINT0, IRQ_CP_MMCIINT1 } #define INTEGRATOR_CP_AACI_IRQS { IRQ_CP_AACIINT } -static AMBA_APB_DEVICE(mmc, "mb:1c", 0, INTEGRATOR_CP_MMC_BASE, +static AMBA_APB_DEVICE(mmc, "mmci", 0, INTEGRATOR_CP_MMC_BASE, INTEGRATOR_CP_MMC_IRQS, &mmc_data); -static AMBA_APB_DEVICE(aaci, "mb:1d", 0, INTEGRATOR_CP_AACI_BASE, +static AMBA_APB_DEVICE(aaci, "aaci", 0, INTEGRATOR_CP_AACI_BASE, INTEGRATOR_CP_AACI_IRQS, NULL); @@ -393,7 +338,7 @@ static struct clcd_board clcd_data = { .remove = versatile_clcd_remove_dma, }; -static AMBA_AHB_DEVICE(clcd, "mb:c0", 0, INTCP_PA_CLCD_BASE, +static AMBA_AHB_DEVICE(clcd, "clcd", 0, INTCP_PA_CLCD_BASE, { IRQ_CP_CLCDCINT }, &clcd_data); static struct amba_device *amba_devs[] __initdata = { @@ -406,10 +351,6 @@ static struct amba_device *amba_devs[] __initdata = { static void __init intcp_init_early(void) { - clkdev_add_table(cp_lookups, ARRAY_SIZE(cp_lookups)); - - integrator_init_early(); - #ifdef CONFIG_PLAT_VERSATILE_SCHED_CLOCK versatile_sched_clock_init(REFCOUNTER, 24000000); #endif diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c index 519bcd3..e5fa46b 100644 --- a/arch/arm/mach-omap2/board-apollon.c +++ b/arch/arm/mach-omap2/board-apollon.c @@ -311,7 +311,7 @@ static void __init omap_apollon_init(void) /* LCD PWR_EN */ omap_mux_init_signal("mcbsp2_dr.gpio_11", OMAP_PULL_ENA | OMAP_PULL_UP); - /* Use Interal loop-back in MMC/SDIO Module Input Clock selection */ + /* Use Internal loop-back in MMC/SDIO Module Input Clock selection */ v = omap_ctrl_readl(OMAP2_CONTROL_DEVCONF0); v |= (1 << 24); omap_ctrl_writel(v, OMAP2_CONTROL_DEVCONF0); diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c index b627cdc..70f6d1d 100644 --- a/arch/arm/mach-omap2/board-omap4panda.c +++ b/arch/arm/mach-omap2/board-omap4panda.c @@ -106,7 +106,7 @@ static struct platform_device leds_gpio = { static struct omap_abe_twl6040_data panda_abe_audio_data = { /* Audio out */ .has_hs = ABE_TWL6040_LEFT | ABE_TWL6040_RIGHT, - /* HandsFree through expasion connector */ + /* HandsFree through expansion connector */ .has_hf = ABE_TWL6040_LEFT | ABE_TWL6040_RIGHT, /* PandaBoard: FM TX, PandaBoardES: can be connected to audio out */ .has_aux = ABE_TWL6040_LEFT | ABE_TWL6040_RIGHT, diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c index e35a86b..637a1bd 100644 --- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c +++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c @@ -313,7 +313,7 @@ int __cpuinit omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state) scu_pwrst_prepare(cpu, power_state); /* - * CPU never retuns back if targetted power state is OFF mode. + * CPU never retuns back if targeted power state is OFF mode. * CPU ONLINE follows normal CPU ONLINE ptah via * omap_secondary_startup(). */ diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c index e107e39..d033a65 100644 --- a/arch/arm/mach-omap2/sr_device.c +++ b/arch/arm/mach-omap2/sr_device.c @@ -131,7 +131,7 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user) omap_voltage_get_volttable(sr_data->voltdm, &volt_data); if (!volt_data) { - pr_warning("%s: No Voltage table registerd fo VDD%d." + pr_warning("%s: No Voltage table registered fo VDD%d." "Something really wrong\n\n", __func__, i + 1); goto exit; } diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c index 3882f3c..de47f17 100644 --- a/arch/arm/mach-omap2/twl-common.c +++ b/arch/arm/mach-omap2/twl-common.c @@ -96,7 +96,7 @@ void __init omap4_pmic_init(const char *pmic_type, void __init omap_pmic_late_init(void) { - /* Init the OMAP TWL parameters (if PMIC has been registerd) */ + /* Init the OMAP TWL parameters (if PMIC has been registered) */ if (pmic_i2c_board_info.irq) omap3_twl_init(); if (omap4_i2c1_board_info[0].irq) diff --git a/arch/arm/mach-u300/Makefile b/arch/arm/mach-u300/Makefile index fd3a5c3..7e47d37 100644 --- a/arch/arm/mach-u300/Makefile +++ b/arch/arm/mach-u300/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel, U300 machine. # -obj-y := core.o clock.o timer.o +obj-y := core.o timer.o obj-m := obj-n := obj- := diff --git a/arch/arm/mach-u300/clock.c b/arch/arm/mach-u300/clock.c deleted file mode 100644 index 5535dd0..0000000 --- a/arch/arm/mach-u300/clock.c +++ /dev/null @@ -1,1504 +0,0 @@ -/* - * - * arch/arm/mach-u300/clock.c - * - * - * Copyright (C) 2007-2009 ST-Ericsson AB - * License terms: GNU General Public License (GPL) version 2 - * Define clocks in the app platform. - * Author: Linus Walleij <linus.walleij@stericsson.com> - * Author: Jonas Aaberg <jonas.aberg@stericsson.com> - * - */ -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/errno.h> -#include <linux/err.h> -#include <linux/string.h> -#include <linux/clk.h> -#include <linux/mutex.h> -#include <linux/spinlock.h> -#include <linux/debugfs.h> -#include <linux/device.h> -#include <linux/init.h> -#include <linux/timer.h> -#include <linux/io.h> -#include <linux/seq_file.h> -#include <linux/clkdev.h> - -#include <mach/hardware.h> -#include <mach/syscon.h> - -#include "clock.h" - -/* - * TODO: - * - move all handling of the CCR register into this file and create - * a spinlock for the CCR register - * - switch to the clkdevice lookup mechanism that maps clocks to - * device ID:s instead when it becomes available in kernel 2.6.29. - * - implement rate get/set for all clocks that need it. - */ - -/* - * Syscon clock I/O registers lock so clock requests don't collide - * NOTE: this is a local lock only used to lock access to clock and - * reset registers in syscon. - */ -static DEFINE_SPINLOCK(syscon_clkreg_lock); -static DEFINE_SPINLOCK(syscon_resetreg_lock); - -/* - * The clocking hierarchy currently looks like this. - * NOTE: the idea is NOT to show how the clocks are routed on the chip! - * The ideas is to show dependencies, so a clock higher up in the - * hierarchy has to be on in order for another clock to be on. Now, - * both CPU and DMA can actually be on top of the hierarchy, and that - * is not modeled currently. Instead we have the backbone AMBA bus on - * top. This bus cannot be programmed in any way but conceptually it - * needs to be active for the bridges and devices to transport data. - * - * Please be aware that a few clocks are hw controlled, which mean that - * the hw itself can turn on/off or change the rate of the clock when - * needed! - * - * AMBA bus - * | - * +- CPU - * +- FSMC NANDIF NAND Flash interface - * +- SEMI Shared Memory interface - * +- ISP Image Signal Processor (U335 only) - * +- CDS (U335 only) - * +- DMA Direct Memory Access Controller - * +- AAIF APP/ACC Inteface (Mobile Scalable Link, MSL) - * +- APEX - * +- VIDEO_ENC AVE2/3 Video Encoder - * +- XGAM Graphics Accelerator Controller - * +- AHB - * | - * +- ahb:0 AHB Bridge - * | | - * | +- ahb:1 INTCON Interrupt controller - * | +- ahb:3 MSPRO Memory Stick Pro controller - * | +- ahb:4 EMIF External Memory interface - * | - * +- fast:0 FAST bridge - * | | - * | +- fast:1 MMCSD MMC/SD card reader controller - * | +- fast:2 I2S0 PCM I2S channel 0 controller - * | +- fast:3 I2S1 PCM I2S channel 1 controller - * | +- fast:4 I2C0 I2C channel 0 controller - * | +- fast:5 I2C1 I2C channel 1 controller - * | +- fast:6 SPI SPI controller - * | +- fast:7 UART1 Secondary UART (U335 only) - * | - * +- slow:0 SLOW bridge - * | - * +- slow:1 SYSCON (not possible to control) - * +- slow:2 WDOG Watchdog - * +- slow:3 UART0 primary UART - * +- slow:4 TIMER_APP Application timer - used in Linux - * +- slow:5 KEYPAD controller - * +- slow:6 GPIO controller - * +- slow:7 RTC controller - * +- slow:8 BT Bus Tracer (not used currently) - * +- slow:9 EH Event Handler (not used currently) - * +- slow:a TIMER_ACC Access style timer (not used currently) - * +- slow:b PPM (U335 only, what is that?) - */ - -/* - * Reset control functions. We remember if a block has been - * taken out of reset and don't remove the reset assertion again - * and vice versa. Currently we only remove resets so the - * enablement function is defined out. - */ -static void syscon_block_reset_enable(struct clk *clk) -{ - u16 val; - unsigned long iflags; - - /* Not all blocks support resetting */ - if (!clk->res_reg || !clk->res_mask) - return; - spin_lock_irqsave(&syscon_resetreg_lock, iflags); - val = readw(clk->res_reg); - val |= clk->res_mask; - writew(val, clk->res_reg); - spin_unlock_irqrestore(&syscon_resetreg_lock, iflags); - clk->reset = true; -} - -static void syscon_block_reset_disable(struct clk *clk) -{ - u16 val; - unsigned long iflags; - - /* Not all blocks support resetting */ - if (!clk->res_reg || !clk->res_mask) - return; - spin_lock_irqsave(&syscon_resetreg_lock, iflags); - val = readw(clk->res_reg); - val &= ~clk->res_mask; - writew(val, clk->res_reg); - spin_unlock_irqrestore(&syscon_resetreg_lock, iflags); - clk->reset = false; -} - -int __clk_get(struct clk *clk) -{ - u16 val; - - /* The MMC and MSPRO clocks need some special set-up */ - if (!strcmp(clk->name, "MCLK")) { - /* Set default MMC clock divisor to 18.9 MHz */ - writew(0x0054U, U300_SYSCON_VBASE + U300_SYSCON_MMF0R); - val = readw(U300_SYSCON_VBASE + U300_SYSCON_MMCR); - /* Disable the MMC feedback clock */ - val &= ~U300_SYSCON_MMCR_MMC_FB_CLK_SEL_ENABLE; - /* Disable MSPRO frequency */ - val &= ~U300_SYSCON_MMCR_MSPRO_FREQSEL_ENABLE; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_MMCR); - } - if (!strcmp(clk->name, "MSPRO")) { - val = readw(U300_SYSCON_VBASE + U300_SYSCON_MMCR); - /* Disable the MMC feedback clock */ - val &= ~U300_SYSCON_MMCR_MMC_FB_CLK_SEL_ENABLE; - /* Enable MSPRO frequency */ - val |= U300_SYSCON_MMCR_MSPRO_FREQSEL_ENABLE; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_MMCR); - } - return 1; -} -EXPORT_SYMBOL(__clk_get); - -void __clk_put(struct clk *clk) -{ -} -EXPORT_SYMBOL(__clk_put); - -static void syscon_clk_disable(struct clk *clk) -{ - unsigned long iflags; - - /* Don't touch the hardware controlled clocks */ - if (clk->hw_ctrld) - return; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - writew(clk->clk_val, U300_SYSCON_VBASE + U300_SYSCON_SBCDR); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} - -static void syscon_clk_enable(struct clk *clk) -{ - unsigned long iflags; - - /* Don't touch the hardware controlled clocks */ - if (clk->hw_ctrld) - return; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - writew(clk->clk_val, U300_SYSCON_VBASE + U300_SYSCON_SBCER); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} - -static u16 syscon_clk_get_rate(void) -{ - u16 val; - unsigned long iflags; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val &= U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK; - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); - return val; -} - -#ifdef CONFIG_MACH_U300_USE_I2S_AS_MASTER -static void enable_i2s0_vcxo(void) -{ - u16 val; - unsigned long iflags; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - /* Set I2S0 to use the VCXO 26 MHz clock */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val |= U300_SYSCON_CCR_TURN_VCXO_ON; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - val |= U300_SYSCON_CCR_I2S0_USE_VCXO; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CEFR); - val |= U300_SYSCON_CEFR_I2S0_CLK_EN; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CEFR); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} - -static void enable_i2s1_vcxo(void) -{ - u16 val; - unsigned long iflags; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - /* Set I2S1 to use the VCXO 26 MHz clock */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val |= U300_SYSCON_CCR_TURN_VCXO_ON; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - val |= U300_SYSCON_CCR_I2S1_USE_VCXO; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CEFR); - val |= U300_SYSCON_CEFR_I2S1_CLK_EN; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CEFR); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} - -static void disable_i2s0_vcxo(void) -{ - u16 val; - unsigned long iflags; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - /* Disable I2S0 use of the VCXO 26 MHz clock */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val &= ~U300_SYSCON_CCR_I2S0_USE_VCXO; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - /* Deactivate VCXO if no one else is using VCXO */ - if (!(val & U300_SYSCON_CCR_I2S1_USE_VCXO)) - val &= ~U300_SYSCON_CCR_TURN_VCXO_ON; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CEFR); - val &= ~U300_SYSCON_CEFR_I2S0_CLK_EN; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CEFR); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} - -static void disable_i2s1_vcxo(void) -{ - u16 val; - unsigned long iflags; - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - /* Disable I2S1 use of the VCXO 26 MHz clock */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val &= ~U300_SYSCON_CCR_I2S1_USE_VCXO; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - /* Deactivate VCXO if no one else is using VCXO */ - if (!(val & U300_SYSCON_CCR_I2S0_USE_VCXO)) - val &= ~U300_SYSCON_CCR_TURN_VCXO_ON; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CEFR); - val &= ~U300_SYSCON_CEFR_I2S0_CLK_EN; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CEFR); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} -#endif /* CONFIG_MACH_U300_USE_I2S_AS_MASTER */ - - -static void syscon_clk_rate_set_mclk(unsigned long rate) -{ - u16 val; - u32 reg; - unsigned long iflags; - - switch (rate) { - case 18900000: - val = 0x0054; - break; - case 20800000: - val = 0x0044; - break; - case 23100000: - val = 0x0043; - break; - case 26000000: - val = 0x0033; - break; - case 29700000: - val = 0x0032; - break; - case 34700000: - val = 0x0022; - break; - case 41600000: - val = 0x0021; - break; - case 52000000: - val = 0x0011; - break; - case 104000000: - val = 0x0000; - break; - default: - printk(KERN_ERR "Trying to set MCLK to unknown speed! %ld\n", - rate); - return; - } - - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - reg = readw(U300_SYSCON_VBASE + U300_SYSCON_MMF0R) & - ~U300_SYSCON_MMF0R_MASK; - writew(reg | val, U300_SYSCON_VBASE + U300_SYSCON_MMF0R); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} - -void syscon_clk_rate_set_cpuclk(unsigned long rate) -{ - u16 val; - unsigned long iflags; - - switch (rate) { - case 13000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER; - break; - case 52000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE; - break; - case 104000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH; - break; - case 208000000: - val = U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST; - break; - default: - return; - } - spin_lock_irqsave(&syscon_clkreg_lock, iflags); - val |= readw(U300_SYSCON_VBASE + U300_SYSCON_CCR) & - ~U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK ; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - spin_unlock_irqrestore(&syscon_clkreg_lock, iflags); -} -EXPORT_SYMBOL(syscon_clk_rate_set_cpuclk); - -void clk_disable(struct clk *clk) -{ - unsigned long iflags; - - spin_lock_irqsave(&clk->lock, iflags); - if (clk->usecount > 0 && !(--clk->usecount)) { - /* some blocks lack clocking registers and cannot be disabled */ - if (clk->disable) - clk->disable(clk); - if (likely((u32)clk->parent)) - clk_disable(clk->parent); - } -#ifdef CONFIG_MACH_U300_USE_I2S_AS_MASTER - if (unlikely(!strcmp(clk->name, "I2S0"))) - disable_i2s0_vcxo(); - if (unlikely(!strcmp(clk->name, "I2S1"))) - disable_i2s1_vcxo(); -#endif - spin_unlock_irqrestore(&clk->lock, iflags); -} -EXPORT_SYMBOL(clk_disable); - -int clk_enable(struct clk *clk) -{ - int ret = 0; - unsigned long iflags; - - spin_lock_irqsave(&clk->lock, iflags); - if (clk->usecount++ == 0) { - if (likely((u32)clk->parent)) - ret = clk_enable(clk->parent); - - if (unlikely(ret != 0)) - clk->usecount--; - else { - /* remove reset line (we never enable reset again) */ - syscon_block_reset_disable(clk); - /* clocks without enable function are always on */ - if (clk->enable) - clk->enable(clk); -#ifdef CONFIG_MACH_U300_USE_I2S_AS_MASTER - if (unlikely(!strcmp(clk->name, "I2S0"))) - enable_i2s0_vcxo(); - if (unlikely(!strcmp(clk->name, "I2S1"))) - enable_i2s1_vcxo(); -#endif - } - } - spin_unlock_irqrestore(&clk->lock, iflags); - return ret; - -} -EXPORT_SYMBOL(clk_enable); - -/* Returns the clock rate in Hz */ -static unsigned long clk_get_rate_cpuclk(struct clk *clk) -{ - u16 val; - - val = syscon_clk_get_rate(); - - switch (val) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 52000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - return 104000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - return 208000000; - default: - break; - } - return clk->rate; -} - -static unsigned long clk_get_rate_ahb_clk(struct clk *clk) -{ - u16 val; - - val = syscon_clk_get_rate(); - - switch (val) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 6500000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 26000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - return 52000000; - default: - break; - } - return clk->rate; - -} - -static unsigned long clk_get_rate_emif_clk(struct clk *clk) -{ - u16 val; - - val = syscon_clk_get_rate(); - - switch (val) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 52000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - return 104000000; - default: - break; - } - return clk->rate; - -} - -static unsigned long clk_get_rate_xgamclk(struct clk *clk) -{ - u16 val; - - val = syscon_clk_get_rate(); - - switch (val) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 6500000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - return 26000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - return 52000000; - default: - break; - } - - return clk->rate; -} - -static unsigned long clk_get_rate_mclk(struct clk *clk) -{ - u16 val; - - val = syscon_clk_get_rate(); - - switch (val) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - /* - * Here, the 208 MHz PLL gets shut down and the always - * on 13 MHz PLL used for RTC etc kicks into use - * instead. - */ - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - { - /* - * This clock is under program control. The register is - * divided in two nybbles, bit 7-4 gives cycles-1 to count - * high, bit 3-0 gives cycles-1 to count low. Distribute - * these with no more than 1 cycle difference between - * low and high and add low and high to get the actual - * divisor. The base PLL is 208 MHz. Writing 0x00 will - * divide by 1 and 1 so the highest frequency possible - * is 104 MHz. - * - * e.g. 0x54 => - * f = 208 / ((5+1) + (4+1)) = 208 / 11 = 18.9 MHz - */ - u16 val = readw(U300_SYSCON_VBASE + U300_SYSCON_MMF0R) & - U300_SYSCON_MMF0R_MASK; - switch (val) { - case 0x0054: - return 18900000; - case 0x0044: - return 20800000; - case 0x0043: - return 23100000; - case 0x0033: - return 26000000; - case 0x0032: - return 29700000; - case 0x0022: - return 34700000; - case 0x0021: - return 41600000; - case 0x0011: - return 52000000; - case 0x0000: - return 104000000; - default: - break; - } - } - default: - break; - } - - return clk->rate; -} - -static unsigned long clk_get_rate_i2s_i2c_spi(struct clk *clk) -{ - u16 val; - - val = syscon_clk_get_rate(); - - switch (val) { - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW_POWER: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_LOW: - return 13000000; - case U300_SYSCON_CCR_CLKING_PERFORMANCE_INTERMEDIATE: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_HIGH: - case U300_SYSCON_CCR_CLKING_PERFORMANCE_BEST: - return 26000000; - default: - break; - } - - return clk->rate; -} - -unsigned long clk_get_rate(struct clk *clk) -{ - if (clk->get_rate) - return clk->get_rate(clk); - else - return clk->rate; -} -EXPORT_SYMBOL(clk_get_rate); - -static unsigned long clk_round_rate_mclk(struct clk *clk, unsigned long rate) -{ - if (rate <= 18900000) - return 18900000; - if (rate <= 20800000) - return 20800000; - if (rate <= 23100000) - return 23100000; - if (rate <= 26000000) - return 26000000; - if (rate <= 29700000) - return 29700000; - if (rate <= 34700000) - return 34700000; - if (rate <= 41600000) - return 41600000; - if (rate <= 52000000) - return 52000000; - return -EINVAL; -} - -static unsigned long clk_round_rate_cpuclk(struct clk *clk, unsigned long rate) -{ - if (rate <= 13000000) - return 13000000; - if (rate <= 52000000) - return 52000000; - if (rate <= 104000000) - return 104000000; - if (rate <= 208000000) - return 208000000; - return -EINVAL; -} - -/* - * This adjusts a requested rate to the closest exact rate - * a certain clock can provide. For a fixed clock it's - * mostly clk->rate. - */ -long clk_round_rate(struct clk *clk, unsigned long rate) -{ - /* TODO: get appropriate switches for EMIFCLK, AHBCLK and MCLK */ - /* Else default to fixed value */ - - if (clk->round_rate) { - return (long) clk->round_rate(clk, rate); - } else { - printk(KERN_ERR "clock: Failed to round rate of %s\n", - clk->name); - } - return (long) clk->rate; -} -EXPORT_SYMBOL(clk_round_rate); - -static int clk_set_rate_mclk(struct clk *clk, unsigned long rate) -{ - syscon_clk_rate_set_mclk(clk_round_rate(clk, rate)); - return 0; -} - -static int clk_set_rate_cpuclk(struct clk *clk, unsigned long rate) -{ - syscon_clk_rate_set_cpuclk(clk_round_rate(clk, rate)); - return 0; -} - -int clk_set_rate(struct clk *clk, unsigned long rate) -{ - /* TODO: set for EMIFCLK and AHBCLK */ - /* Else assume the clock is fixed and fail */ - if (clk->set_rate) { - return clk->set_rate(clk, rate); - } else { - printk(KERN_ERR "clock: Failed to set %s to %ld hz\n", - clk->name, rate); - return -EINVAL; - } -} -EXPORT_SYMBOL(clk_set_rate); - -/* - * Clock definitions. The clock parents are set to respective - * bridge and the clock framework makes sure that the clocks have - * parents activated and are brought out of reset when in use. - * - * Clocks that have hw_ctrld = true are hw controlled, and the hw - * can by itself turn these clocks on and off. - * So in other words, we don't really have to care about them. - */ - -static struct clk amba_clk = { - .name = "AMBA", - .rate = 52000000, /* this varies! */ - .hw_ctrld = true, - .reset = false, - .lock = __SPIN_LOCK_UNLOCKED(amba_clk.lock), -}; - -/* - * These blocks are connected directly to the AMBA bus - * with no bridge. - */ - -static struct clk cpu_clk = { - .name = "CPU", - .parent = &amba_clk, - .rate = 208000000, /* this varies! */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_CPU_RESET_EN, - .set_rate = clk_set_rate_cpuclk, - .get_rate = clk_get_rate_cpuclk, - .round_rate = clk_round_rate_cpuclk, - .lock = __SPIN_LOCK_UNLOCKED(cpu_clk.lock), -}; - -static struct clk nandif_clk = { - .name = "FSMC", - .parent = &amba_clk, - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_NANDIF_RESET_EN, - .clk_val = U300_SYSCON_SBCER_NANDIF_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(nandif_clk.lock), -}; - -static struct clk semi_clk = { - .name = "SEMI", - .parent = &amba_clk, - .rate = 0, /* FIXME */ - /* It is not possible to reset SEMI */ - .hw_ctrld = false, - .reset = false, - .clk_val = U300_SYSCON_SBCER_SEMI_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(semi_clk.lock), -}; - -#ifdef CONFIG_MACH_U300_BS335 -static struct clk isp_clk = { - .name = "ISP", - .parent = &amba_clk, - .rate = 0, /* FIXME */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_ISP_RESET_EN, - .clk_val = U300_SYSCON_SBCER_ISP_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(isp_clk.lock), -}; - -static struct clk cds_clk = { - .name = "CDS", - .parent = &amba_clk, - .rate = 0, /* FIXME */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_CDS_RESET_EN, - .clk_val = U300_SYSCON_SBCER_CDS_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(cds_clk.lock), -}; -#endif - -static struct clk dma_clk = { - .name = "DMA", - .parent = &amba_clk, - .rate = 52000000, /* this varies! */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_DMAC_RESET_EN, - .clk_val = U300_SYSCON_SBCER_DMAC_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(dma_clk.lock), -}; - -static struct clk aaif_clk = { - .name = "AAIF", - .parent = &amba_clk, - .rate = 52000000, /* this varies! */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_AAIF_RESET_EN, - .clk_val = U300_SYSCON_SBCER_AAIF_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(aaif_clk.lock), -}; - -static struct clk apex_clk = { - .name = "APEX", - .parent = &amba_clk, - .rate = 0, /* FIXME */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_APEX_RESET_EN, - .clk_val = U300_SYSCON_SBCER_APEX_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(apex_clk.lock), -}; - -static struct clk video_enc_clk = { - .name = "VIDEO_ENC", - .parent = &amba_clk, - .rate = 208000000, /* this varies! */ - .hw_ctrld = false, - .reset = false, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - /* This has XGAM in the name but refers to the video encoder */ - .res_mask = U300_SYSCON_RRR_XGAM_VC_SYNC_RESET_EN, - .clk_val = U300_SYSCON_SBCER_VIDEO_ENC_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(video_enc_clk.lock), -}; - -static struct clk xgam_clk = { - .name = "XGAMCLK", - .parent = &amba_clk, - .rate = 52000000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_XGAM_RESET_EN, - .clk_val = U300_SYSCON_SBCER_XGAM_CLK_EN, - .get_rate = clk_get_rate_xgamclk, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(xgam_clk.lock), -}; - -/* This clock is used to activate the video encoder */ -static struct clk ahb_clk = { - .name = "AHB", - .parent = &amba_clk, - .rate = 52000000, /* this varies! */ - .hw_ctrld = false, /* This one is set to false due to HW bug */ - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_AHB_RESET_EN, - .clk_val = U300_SYSCON_SBCER_AHB_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_ahb_clk, - .lock = __SPIN_LOCK_UNLOCKED(ahb_clk.lock), -}; - - -/* - * Clocks on the AHB bridge - */ - -static struct clk ahb_subsys_clk = { - .name = "AHB_SUBSYS", - .parent = &amba_clk, - .rate = 52000000, /* this varies! */ - .hw_ctrld = true, - .reset = false, - .clk_val = U300_SYSCON_SBCER_AHB_SUBSYS_BRIDGE_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_ahb_clk, - .lock = __SPIN_LOCK_UNLOCKED(ahb_subsys_clk.lock), -}; - -static struct clk intcon_clk = { - .name = "INTCON", - .parent = &ahb_subsys_clk, - .rate = 52000000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_INTCON_RESET_EN, - /* INTCON can be reset but not clock-gated */ - .lock = __SPIN_LOCK_UNLOCKED(intcon_clk.lock), - -}; - -static struct clk mspro_clk = { - .name = "MSPRO", - .parent = &ahb_subsys_clk, - .rate = 0, /* FIXME */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_MSPRO_RESET_EN, - .clk_val = U300_SYSCON_SBCER_MSPRO_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(mspro_clk.lock), -}; - -static struct clk emif_clk = { - .name = "EMIF", - .parent = &ahb_subsys_clk, - .rate = 104000000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RRR, - .res_mask = U300_SYSCON_RRR_EMIF_RESET_EN, - .clk_val = U300_SYSCON_SBCER_EMIF_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_emif_clk, - .lock = __SPIN_LOCK_UNLOCKED(emif_clk.lock), -}; - - -/* - * Clocks on the FAST bridge - */ -static struct clk fast_clk = { - .name = "FAST_BRIDGE", - .parent = &amba_clk, - .rate = 13000000, /* this varies! */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_FAST_BRIDGE_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_FAST_BRIDGE_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(fast_clk.lock), -}; - -/* - * The MMCI apb_pclk is hardwired to the same terminal as the - * external MCI clock. Thus this will be referenced twice. - */ -static struct clk mmcsd_clk = { - .name = "MCLK", - .parent = &fast_clk, - .rate = 18900000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_MMC_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_MMC_CLK_EN, - .get_rate = clk_get_rate_mclk, - .set_rate = clk_set_rate_mclk, - .round_rate = clk_round_rate_mclk, - .disable = syscon_clk_disable, - .enable = syscon_clk_enable, - .lock = __SPIN_LOCK_UNLOCKED(mmcsd_clk.lock), -}; - -static struct clk i2s0_clk = { - .name = "i2s0", - .parent = &fast_clk, - .rate = 26000000, /* this varies! */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_PCM_I2S0_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_I2S0_CORE_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_i2s_i2c_spi, - .lock = __SPIN_LOCK_UNLOCKED(i2s0_clk.lock), -}; - -static struct clk i2s1_clk = { - .name = "i2s1", - .parent = &fast_clk, - .rate = 26000000, /* this varies! */ - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_PCM_I2S1_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_I2S1_CORE_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_i2s_i2c_spi, - .lock = __SPIN_LOCK_UNLOCKED(i2s1_clk.lock), -}; - -static struct clk i2c0_clk = { - .name = "I2C0", - .parent = &fast_clk, - .rate = 26000000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_I2C0_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_I2C0_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_i2s_i2c_spi, - .lock = __SPIN_LOCK_UNLOCKED(i2c0_clk.lock), -}; - -static struct clk i2c1_clk = { - .name = "I2C1", - .parent = &fast_clk, - .rate = 26000000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_I2C1_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_I2C1_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_i2s_i2c_spi, - .lock = __SPIN_LOCK_UNLOCKED(i2c1_clk.lock), -}; - -/* - * The SPI apb_pclk is hardwired to the same terminal as the - * external SPI clock. Thus this will be referenced twice. - */ -static struct clk spi_clk = { - .name = "SPI", - .parent = &fast_clk, - .rate = 26000000, /* this varies! */ - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_SPI_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_SPI_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .get_rate = clk_get_rate_i2s_i2c_spi, - .lock = __SPIN_LOCK_UNLOCKED(spi_clk.lock), -}; - -#ifdef CONFIG_MACH_U300_BS335 -static struct clk uart1_pclk = { - .name = "UART1_PCLK", - .parent = &fast_clk, - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RFR, - .res_mask = U300_SYSCON_RFR_UART1_RESET_ENABLE, - .clk_val = U300_SYSCON_SBCER_UART1_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(uart1_pclk.lock), -}; - -/* This one is hardwired to PLL13 */ -static struct clk uart1_clk = { - .name = "UART1_CLK", - .rate = 13000000, - .hw_ctrld = true, - .lock = __SPIN_LOCK_UNLOCKED(uart1_clk.lock), -}; -#endif - - -/* - * Clocks on the SLOW bridge - */ -static struct clk slow_clk = { - .name = "SLOW_BRIDGE", - .parent = &amba_clk, - .rate = 13000000, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_SLOW_BRIDGE_RESET_EN, - .clk_val = U300_SYSCON_SBCER_SLOW_BRIDGE_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(slow_clk.lock), -}; - -/* TODO: implement SYSCON clock? */ - -static struct clk wdog_clk = { - .name = "WDOG", - .parent = &slow_clk, - .hw_ctrld = false, - .rate = 32768, - .reset = false, - /* This is always on, cannot be enabled/disabled or reset */ - .lock = __SPIN_LOCK_UNLOCKED(wdog_clk.lock), -}; - -static struct clk uart0_pclk = { - .name = "UART0_PCLK", - .parent = &slow_clk, - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_UART_RESET_EN, - .clk_val = U300_SYSCON_SBCER_UART_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(uart0_pclk.lock), -}; - -/* This one is hardwired to PLL13 */ -static struct clk uart0_clk = { - .name = "UART0_CLK", - .parent = &slow_clk, - .rate = 13000000, - .hw_ctrld = true, - .lock = __SPIN_LOCK_UNLOCKED(uart0_clk.lock), -}; - -static struct clk keypad_clk = { - .name = "KEYPAD", - .parent = &slow_clk, - .rate = 32768, - .hw_ctrld = false, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_KEYPAD_RESET_EN, - .clk_val = U300_SYSCON_SBCER_KEYPAD_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(keypad_clk.lock), -}; - -static struct clk gpio_clk = { - .name = "GPIO", - .parent = &slow_clk, - .rate = 13000000, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_GPIO_RESET_EN, - .clk_val = U300_SYSCON_SBCER_GPIO_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(gpio_clk.lock), -}; - -static struct clk rtc_clk = { - .name = "RTC", - .parent = &slow_clk, - .rate = 32768, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_RTC_RESET_EN, - /* This clock is always on, cannot be enabled/disabled */ - .lock = __SPIN_LOCK_UNLOCKED(rtc_clk.lock), -}; - -static struct clk bustr_clk = { - .name = "BUSTR", - .parent = &slow_clk, - .rate = 13000000, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_BTR_RESET_EN, - .clk_val = U300_SYSCON_SBCER_BTR_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(bustr_clk.lock), -}; - -static struct clk evhist_clk = { - .name = "EVHIST", - .parent = &slow_clk, - .rate = 13000000, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_EH_RESET_EN, - .clk_val = U300_SYSCON_SBCER_EH_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(evhist_clk.lock), -}; - -static struct clk timer_clk = { - .name = "TIMER", - .parent = &slow_clk, - .rate = 13000000, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_ACC_TMR_RESET_EN, - .clk_val = U300_SYSCON_SBCER_ACC_TMR_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(timer_clk.lock), -}; - -/* - * There is a binary divider in the hardware that divides - * the 13MHz PLL by 13 down to 1 MHz. - */ -static struct clk app_timer_clk = { - .name = "TIMER_APP", - .parent = &slow_clk, - .rate = 1000000, - .hw_ctrld = true, - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_APP_TMR_RESET_EN, - .clk_val = U300_SYSCON_SBCER_APP_TMR_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(app_timer_clk.lock), -}; - -#ifdef CONFIG_MACH_U300_BS335 -static struct clk ppm_clk = { - .name = "PPM", - .parent = &slow_clk, - .rate = 0, /* FIXME */ - .hw_ctrld = true, /* TODO: Look up if it is hw ctrld or not */ - .reset = true, - .res_reg = U300_SYSCON_VBASE + U300_SYSCON_RSR, - .res_mask = U300_SYSCON_RSR_PPM_RESET_EN, - .clk_val = U300_SYSCON_SBCER_PPM_CLK_EN, - .enable = syscon_clk_enable, - .disable = syscon_clk_disable, - .lock = __SPIN_LOCK_UNLOCKED(ppm_clk.lock), -}; -#endif - -#define DEF_LOOKUP(devid, clkref) \ - { \ - .dev_id = devid, \ - .clk = clkref, \ - } - -#define DEF_LOOKUP_CON(devid, conid, clkref) \ - { \ - .dev_id = devid, \ - .con_id = conid, \ - .clk = clkref, \ - } - -/* - * Here we only define clocks that are meaningful to - * look up through clockdevice. - */ -static struct clk_lookup lookups[] = { - /* Connected directly to the AMBA bus */ - DEF_LOOKUP("amba", &amba_clk), - DEF_LOOKUP("cpu", &cpu_clk), - DEF_LOOKUP("fsmc-nand", &nandif_clk), - DEF_LOOKUP("semi", &semi_clk), -#ifdef CONFIG_MACH_U300_BS335 - DEF_LOOKUP("isp", &isp_clk), - DEF_LOOKUP("cds", &cds_clk), -#endif - DEF_LOOKUP("dma", &dma_clk), - DEF_LOOKUP("msl", &aaif_clk), - DEF_LOOKUP("apex", &apex_clk), - DEF_LOOKUP("video_enc", &video_enc_clk), - DEF_LOOKUP("xgam", &xgam_clk), - DEF_LOOKUP("ahb", &ahb_clk), - /* AHB bridge clocks */ - DEF_LOOKUP("ahb_subsys", &ahb_subsys_clk), - DEF_LOOKUP("intcon", &intcon_clk), - DEF_LOOKUP_CON("intcon", "apb_pclk", &intcon_clk), - DEF_LOOKUP("mspro", &mspro_clk), - DEF_LOOKUP("pl172", &emif_clk), - DEF_LOOKUP_CON("pl172", "apb_pclk", &emif_clk), - /* FAST bridge clocks */ - DEF_LOOKUP("fast", &fast_clk), - DEF_LOOKUP("mmci", &mmcsd_clk), - DEF_LOOKUP_CON("mmci", "apb_pclk", &mmcsd_clk), - /* - * The .0 and .1 identifiers on these comes from the platform device - * .id field and are assigned when the platform devices are registered. - */ - DEF_LOOKUP("i2s.0", &i2s0_clk), - DEF_LOOKUP("i2s.1", &i2s1_clk), - DEF_LOOKUP("stu300.0", &i2c0_clk), - DEF_LOOKUP("stu300.1", &i2c1_clk), - DEF_LOOKUP("pl022", &spi_clk), - DEF_LOOKUP_CON("pl022", "apb_pclk", &spi_clk), -#ifdef CONFIG_MACH_U300_BS335 - DEF_LOOKUP("uart1", &uart1_clk), - DEF_LOOKUP_CON("uart1", "apb_pclk", &uart1_pclk), -#endif - /* SLOW bridge clocks */ - DEF_LOOKUP("slow", &slow_clk), - DEF_LOOKUP("coh901327_wdog", &wdog_clk), - DEF_LOOKUP("uart0", &uart0_clk), - DEF_LOOKUP_CON("uart0", "apb_pclk", &uart0_pclk), - DEF_LOOKUP("apptimer", &app_timer_clk), - DEF_LOOKUP("coh901461-keypad", &keypad_clk), - DEF_LOOKUP("u300-gpio", &gpio_clk), - DEF_LOOKUP("rtc-coh901331", &rtc_clk), - DEF_LOOKUP("bustr", &bustr_clk), - DEF_LOOKUP("evhist", &evhist_clk), - DEF_LOOKUP("timer", &timer_clk), -#ifdef CONFIG_MACH_U300_BS335 - DEF_LOOKUP("ppm", &ppm_clk), -#endif -}; - -static void __init clk_register(void) -{ - /* Register the lookups */ - clkdev_add_table(lookups, ARRAY_SIZE(lookups)); -} - -#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_U300_DEBUG)) -/* - * The following makes it possible to view the status (especially - * reference count and reset status) for the clocks in the platform - * by looking into the special file <debugfs>/u300_clocks - */ - -/* A list of all clocks in the platform */ -static struct clk *clks[] = { - /* Top node clock for the AMBA bus */ - &amba_clk, - /* Connected directly to the AMBA bus */ - &cpu_clk, - &nandif_clk, - &semi_clk, -#ifdef CONFIG_MACH_U300_BS335 - &isp_clk, - &cds_clk, -#endif - &dma_clk, - &aaif_clk, - &apex_clk, - &video_enc_clk, - &xgam_clk, - &ahb_clk, - - /* AHB bridge clocks */ - &ahb_subsys_clk, - &intcon_clk, - &mspro_clk, - &emif_clk, - /* FAST bridge clocks */ - &fast_clk, - &mmcsd_clk, - &i2s0_clk, - &i2s1_clk, - &i2c0_clk, - &i2c1_clk, - &spi_clk, -#ifdef CONFIG_MACH_U300_BS335 - &uart1_clk, - &uart1_pclk, -#endif - /* SLOW bridge clocks */ - &slow_clk, - &wdog_clk, - &uart0_clk, - &uart0_pclk, - &app_timer_clk, - &keypad_clk, - &gpio_clk, - &rtc_clk, - &bustr_clk, - &evhist_clk, - &timer_clk, -#ifdef CONFIG_MACH_U300_BS335 - &ppm_clk, -#endif -}; - -static int u300_clocks_show(struct seq_file *s, void *data) -{ - struct clk *clk; - int i; - - seq_printf(s, "CLOCK DEVICE RESET STATE\t" \ - "ACTIVE\tUSERS\tHW CTRL FREQ\n"); - seq_printf(s, "---------------------------------------------" \ - "-----------------------------------------\n"); - for (i = 0; i < ARRAY_SIZE(clks); i++) { - clk = clks[i]; - if (clk != ERR_PTR(-ENOENT)) { - /* Format clock and device name nicely */ - char cdp[33]; - int chars; - - chars = snprintf(&cdp[0], 17, "%s", clk->name); - while (chars < 16) { - cdp[chars] = ' '; - chars++; - } - chars = snprintf(&cdp[16], 17, "%s", clk->dev ? - dev_name(clk->dev) : "N/A"); - while (chars < 16) { - cdp[chars+16] = ' '; - chars++; - } - cdp[32] = '\0'; - if (clk->get_rate || clk->rate != 0) - seq_printf(s, - "%s%s\t%s\t%d\t%s\t%lu Hz\n", - &cdp[0], - clk->reset ? - "ASSERTED" : "RELEASED", - clk->usecount ? "ON" : "OFF", - clk->usecount, - clk->hw_ctrld ? "YES" : "NO ", - clk_get_rate(clk)); - else - seq_printf(s, - "%s%s\t%s\t%d\t%s\t" \ - "(unknown rate)\n", - &cdp[0], - clk->reset ? - "ASSERTED" : "RELEASED", - clk->usecount ? "ON" : "OFF", - clk->usecount, - clk->hw_ctrld ? "YES" : "NO "); - } - } - return 0; -} - -static int u300_clocks_open(struct inode *inode, struct file *file) -{ - return single_open(file, u300_clocks_show, NULL); -} - -static const struct file_operations u300_clocks_operations = { - .open = u300_clocks_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init init_clk_read_debugfs(void) -{ - /* Expose a simple debugfs interface to view all clocks */ - (void) debugfs_create_file("u300_clocks", S_IFREG | S_IRUGO, - NULL, NULL, - &u300_clocks_operations); - return 0; -} -/* - * This needs to come in after the core_initcall() for the - * overall clocks, because debugfs is not available until - * the subsystems come up. - */ -module_init(init_clk_read_debugfs); -#endif - -int __init u300_clock_init(void) -{ - u16 val; - - /* - * FIXME: shall all this powermanagement stuff really live here??? - */ - - /* Set system to run at PLL208, max performance, a known state. */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val &= ~U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - /* Wait for the PLL208 to lock if not locked in yet */ - while (!(readw(U300_SYSCON_VBASE + U300_SYSCON_CSR) & - U300_SYSCON_CSR_PLL208_LOCK_IND)); - - /* Power management enable */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_PMCR); - val |= U300_SYSCON_PMCR_PWR_MGNT_ENABLE; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_PMCR); - - clk_register(); - - /* - * Some of these may be on when we boot the system so make sure they - * are turned OFF. - */ - syscon_block_reset_enable(&timer_clk); - timer_clk.disable(&timer_clk); - - /* - * These shall be turned on by default when we boot the system - * so make sure they are ON. (Adding CPU here is a bit too much.) - * These clocks will be claimed by drivers later. - */ - syscon_block_reset_disable(&semi_clk); - syscon_block_reset_disable(&emif_clk); - clk_enable(&semi_clk); - clk_enable(&emif_clk); - - return 0; -} diff --git a/arch/arm/mach-u300/clock.h b/arch/arm/mach-u300/clock.h deleted file mode 100644 index 4f50ca8..0000000 --- a/arch/arm/mach-u300/clock.h +++ /dev/null @@ -1,50 +0,0 @@ -/* - * arch/arm/mach-u300/include/mach/clock.h - * - * Copyright (C) 2004 - 2005 Nokia corporation - * Written by Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com> - * Based on clocks.h by Tony Lindgren, Gordon McNutt and RidgeRun, Inc - * Copyright (C) 2007-2009 ST-Ericsson AB - * Adopted to ST-Ericsson U300 platforms by - * Jonas Aaberg <jonas.aberg@stericsson.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 __MACH_CLOCK_H -#define __MACH_CLOCK_H - -#include <linux/clk.h> - -struct clk { - struct list_head node; - struct module *owner; - struct device *dev; - const char *name; - struct clk *parent; - - spinlock_t lock; - unsigned long rate; - bool reset; - __u16 clk_val; - __s8 usecount; - void __iomem * res_reg; - __u16 res_mask; - - bool hw_ctrld; - - void (*recalc) (struct clk *); - int (*set_rate) (struct clk *, unsigned long); - unsigned long (*get_rate) (struct clk *); - unsigned long (*round_rate) (struct clk *, unsigned long); - void (*init) (struct clk *); - void (*enable) (struct clk *); - void (*disable) (struct clk *); -}; - -int u300_clock_init(void); - -#endif diff --git a/arch/arm/mach-u300/core.c b/arch/arm/mach-u300/core.c index 3333974..03acf18 100644 --- a/arch/arm/mach-u300/core.c +++ b/arch/arm/mach-u300/core.c @@ -30,6 +30,7 @@ #include <linux/pinctrl/consumer.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/dma-mapping.h> +#include <linux/platform_data/clk-u300.h> #include <asm/types.h> #include <asm/setup.h> @@ -44,7 +45,6 @@ #include <mach/dma_channels.h> #include <mach/gpio-u300.h> -#include "clock.h" #include "spi.h" #include "i2c.h" #include "u300-gpio.h" @@ -1658,12 +1658,20 @@ void __init u300_init_irq(void) int i; /* initialize clocking early, we want to clock the INTCON */ - u300_clock_init(); + u300_clk_init(U300_SYSCON_VBASE); + + /* Bootstrap EMIF and SEMI clocks */ + clk = clk_get_sys("pl172", NULL); + BUG_ON(IS_ERR(clk)); + clk_prepare_enable(clk); + clk = clk_get_sys("semi", NULL); + BUG_ON(IS_ERR(clk)); + clk_prepare_enable(clk); /* Clock the interrupt controller */ clk = clk_get_sys("intcon", NULL); BUG_ON(IS_ERR(clk)); - clk_enable(clk); + clk_prepare_enable(clk); for (i = 0; i < U300_VIC_IRQS_END; i++) set_bit(i, (unsigned long *) &mask[0]); @@ -1811,13 +1819,6 @@ void __init u300_init_devices(void) /* Check what platform we run and print some status information */ u300_init_check_chip(); - /* Set system to run at PLL208, max performance, a known state. */ - val = readw(U300_SYSCON_VBASE + U300_SYSCON_CCR); - val &= ~U300_SYSCON_CCR_CLKING_PERFORMANCE_MASK; - writew(val, U300_SYSCON_VBASE + U300_SYSCON_CCR); - /* Wait for the PLL208 to lock if not locked in yet */ - while (!(readw(U300_SYSCON_VBASE + U300_SYSCON_CSR) & - U300_SYSCON_CSR_PLL208_LOCK_IND)); /* Initialize SPI device with some board specifics */ u300_spi_init(&pl022_device); diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c index bc1c789..56ac06d 100644 --- a/arch/arm/mach-u300/timer.c +++ b/arch/arm/mach-u300/timer.c @@ -354,7 +354,7 @@ static void __init u300_timer_init(void) /* Clock the interrupt controller */ clk = clk_get_sys("apptimer", NULL); BUG_ON(IS_ERR(clk)); - clk_enable(clk); + clk_prepare_enable(clk); rate = clk_get_rate(clk); setup_sched_clock(u300_read_sched_clock, 32, rate); diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index 84461fa..a310222 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -25,6 +25,7 @@ #include <linux/mfd/tc3589x.h> #include <linux/mfd/tps6105x.h> #include <linux/mfd/abx500/ab8500-gpio.h> +#include <linux/mfd/abx500/ab8500-codec.h> #include <linux/leds-lp5521.h> #include <linux/input.h> #include <linux/smsc911x.h> @@ -97,6 +98,18 @@ static struct ab8500_gpio_platform_data ab8500_gpio_pdata = { 0x7A, 0x00, 0x00}, }; +/* ab8500-codec */ +static struct ab8500_codec_platform_data ab8500_codec_pdata = { + .amics = { + .mic1_type = AMIC_TYPE_DIFFERENTIAL, + .mic2_type = AMIC_TYPE_DIFFERENTIAL, + .mic1a_micbias = AMIC_MICBIAS_VAMIC1, + .mic1b_micbias = AMIC_MICBIAS_VAMIC1, + .mic2_micbias = AMIC_MICBIAS_VAMIC2 + }, + .ear_cmv = EAR_CMV_0_95V +}; + static struct gpio_keys_button snowball_key_array[] = { { .gpio = 32, @@ -195,6 +208,7 @@ static struct ab8500_platform_data ab8500_platdata = { .regulator = ab8500_regulators, .num_regulator = ARRAY_SIZE(ab8500_regulators), .gpio = &ab8500_gpio_pdata, + .codec = &ab8500_codec_pdata, }; static struct resource ab8500_resources[] = { diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h index df8155b..08740ee 100644 --- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h +++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h @@ -24,7 +24,7 @@ #ifndef __PLAT_GPIO_CFG_H #define __PLAT_GPIO_CFG_H __FILE__ -#include<linux/types.h> +#include <linux/types.h> typedef unsigned int __bitwise__ samsung_gpio_pull_t; typedef unsigned int __bitwise__ s5p_gpio_drvstr_t; diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index fef96f4..9b76510 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -352,6 +352,11 @@ config MEM_MT48H32M16LFCJ_75 depends on (BFIN526_EZBRD) default y +config MEM_MT47H64M16 + bool + depends on (BFIN609_EZKIT) + default y + source "arch/blackfin/mach-bf518/Kconfig" source "arch/blackfin/mach-bf527/Kconfig" source "arch/blackfin/mach-bf533/Kconfig" @@ -399,8 +404,9 @@ config ROM_BASE hex "Kernel ROM Base" depends on ROMKERNEL default "0x20040040" - range 0x20000000 0x20400000 if !(BF54x || BF561) + range 0x20000000 0x20400000 if !(BF54x || BF561 || BF60x) range 0x20000000 0x30000000 if (BF54x || BF561) + range 0xB0000000 0xC0000000 if (BF60x) help Make sure your ROM base does not include any file-header information that is prepended to the kernel. @@ -1009,6 +1015,12 @@ config HAVE_PWM choice prompt "Uncached DMA region" default DMA_UNCACHED_1M +config DMA_UNCACHED_32M + bool "Enable 32M DMA region" +config DMA_UNCACHED_16M + bool "Enable 16M DMA region" +config DMA_UNCACHED_8M + bool "Enable 8M DMA region" config DMA_UNCACHED_4M bool "Enable 4M DMA region" config DMA_UNCACHED_2M @@ -1038,7 +1050,7 @@ config BFIN_EXTMEM_ICACHEABLE config BFIN_L2_ICACHEABLE bool "Enable ICACHE for L2 SRAM" depends on BFIN_ICACHE - depends on BF54x || BF561 + depends on (BF54x || BF561 || BF60x) && !SMP default n config BFIN_DCACHE diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig index be9526b..f4b0235 100644 --- a/arch/blackfin/configs/BF609-EZKIT_defconfig +++ b/arch/blackfin/configs/BF609-EZKIT_defconfig @@ -90,6 +90,7 @@ CONFIG_INPUT_BFIN_ROTARY=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set CONFIG_BFIN_SIMPLE_TIMER=m +# CONFIG_BFIN_CRC is not set CONFIG_BFIN_LINKPORT=y # CONFIG_DEVKMEM is not set CONFIG_SERIAL_BFIN=y @@ -153,3 +154,4 @@ CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_ARC4=y # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_DEV_BFIN_CRC=y diff --git a/arch/blackfin/include/asm/bfin-global.h b/arch/blackfin/include/asm/bfin-global.h index 608be5e..dc47d79 100644 --- a/arch/blackfin/include/asm/bfin-global.h +++ b/arch/blackfin/include/asm/bfin-global.h @@ -14,7 +14,13 @@ #include <linux/linkage.h> #include <linux/types.h> -#if defined(CONFIG_DMA_UNCACHED_4M) +#if defined(CONFIG_DMA_UNCACHED_32M) +# define DMA_UNCACHED_REGION (32 * 1024 * 1024) +#elif defined(CONFIG_DMA_UNCACHED_16M) +# define DMA_UNCACHED_REGION (16 * 1024 * 1024) +#elif defined(CONFIG_DMA_UNCACHED_8M) +# define DMA_UNCACHED_REGION (8 * 1024 * 1024) +#elif defined(CONFIG_DMA_UNCACHED_4M) # define DMA_UNCACHED_REGION (4 * 1024 * 1024) #elif defined(CONFIG_DMA_UNCACHED_2M) # define DMA_UNCACHED_REGION (2 * 1024 * 1024) diff --git a/arch/blackfin/include/asm/bfin_crc.h b/arch/blackfin/include/asm/bfin_crc.h index 3deb445..75cef4d 100644 --- a/arch/blackfin/include/asm/bfin_crc.h +++ b/arch/blackfin/include/asm/bfin_crc.h @@ -79,20 +79,6 @@ struct crc_register { u32 revid; }; -struct bfin_crc { - struct miscdevice mdev; - struct list_head list; - int irq; - int dma_ch_src; - int dma_ch_dest; - volatile struct crc_register *regs; - struct crc_info *info; - struct mutex mutex; - struct completion c; - unsigned short opmode; - char name[20]; -}; - /* CRC_STATUS Masks */ #define CMPERR 0x00000002 /* Compare error */ #define DCNTEXP 0x00000010 /* datacnt register expired */ diff --git a/arch/blackfin/include/asm/bfin_serial.h b/arch/blackfin/include/asm/bfin_serial.h index 8597158..2d90d62 100644 --- a/arch/blackfin/include/asm/bfin_serial.h +++ b/arch/blackfin/include/asm/bfin_serial.h @@ -282,7 +282,7 @@ struct bfin_uart_regs { #define UART_GET_GCTL(p) UART_GET_CTL(p) #define UART_GET_LCR(p) UART_GET_CTL(p) #define UART_GET_MCR(p) UART_GET_CTL(p) -#if ANOMALY_05001001 +#if ANOMALY_16000030 #define UART_GET_STAT(p) \ ({ \ u32 __ret; \ diff --git a/arch/blackfin/include/asm/bfin_simple_timer.h b/arch/blackfin/include/asm/bfin_simple_timer.h index aadfb1a..b2d5e73 100644 --- a/arch/blackfin/include/asm/bfin_simple_timer.h +++ b/arch/blackfin/include/asm/bfin_simple_timer.h @@ -17,5 +17,11 @@ #define BFIN_SIMPLE_TIMER_START _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 6) #define BFIN_SIMPLE_TIMER_STOP _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 8) #define BFIN_SIMPLE_TIMER_READ _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 10) +#define BFIN_SIMPLE_TIMER_READ_COUNTER _IO(BFIN_SIMPLE_TIMER_IOCTL_MAGIC, 11) + +#define BFIN_SIMPLE_TIMER_MODE_PWM_ONESHOT 0 +#define BFIN_SIMPLE_TIMER_MODE_PWMOUT_CONT 1 +#define BFIN_SIMPLE_TIMER_MODE_WDTH_CAP 2 +#define BFIN_SIMPLE_TIMER_MODE_PWMOUT_CONT_NOIRQ 3 #endif diff --git a/arch/blackfin/include/asm/bfin_twi.h b/arch/blackfin/include/asm/bfin_twi.h index 2f3339a..f4a0727 100644 --- a/arch/blackfin/include/asm/bfin_twi.h +++ b/arch/blackfin/include/asm/bfin_twi.h @@ -66,9 +66,9 @@ struct bfin_twi_iface { #define DEFINE_TWI_REG(reg_name, reg) \ static inline u16 read_##reg_name(struct bfin_twi_iface *iface) \ - { return iface->regs_base->reg; } \ + { return bfin_read16(&iface->regs_base->reg); } \ static inline void write_##reg_name(struct bfin_twi_iface *iface, u16 v) \ - { iface->regs_base->reg = v; } + { bfin_write16(&iface->regs_base->reg, v); } DEFINE_TWI_REG(CLKDIV, clkdiv) DEFINE_TWI_REG(CONTROL, control) @@ -84,7 +84,7 @@ DEFINE_TWI_REG(FIFO_CTL, fifo_ctl) DEFINE_TWI_REG(FIFO_STAT, fifo_stat) DEFINE_TWI_REG(XMT_DATA8, xmt_data8) DEFINE_TWI_REG(XMT_DATA16, xmt_data16) -#if !ANOMALY_05001001 +#if !ANOMALY_16000030 DEFINE_TWI_REG(RCV_DATA8, rcv_data8) DEFINE_TWI_REG(RCV_DATA16, rcv_data16) #else @@ -94,7 +94,7 @@ static inline u16 read_RCV_DATA8(struct bfin_twi_iface *iface) unsigned long flags; flags = hard_local_irq_save(); - ret = iface->regs_base->rcv_data8; + ret = bfin_read16(&iface->regs_base->rcv_data8); hard_local_irq_restore(flags); return ret; @@ -106,7 +106,7 @@ static inline u16 read_RCV_DATA16(struct bfin_twi_iface *iface) unsigned long flags; flags = hard_local_irq_save(); - ret = iface->regs_base->rcv_data16; + ret = bfin_read16(&iface->regs_base->rcv_data16); hard_local_irq_restore(flags); return ret; diff --git a/arch/blackfin/include/asm/context.S b/arch/blackfin/include/asm/context.S index 1f90603..507e7aa 100644 --- a/arch/blackfin/include/asm/context.S +++ b/arch/blackfin/include/asm/context.S @@ -396,3 +396,12 @@ call \func; #endif .endm + +#if defined(CONFIG_BFIN_SCRATCH_REG_RETN) +# define EX_SCRATCH_REG RETN +#elif defined(CONFIG_BFIN_SCRATCH_REG_RETE) +# define EX_SCRATCH_REG RETE +#else +# define EX_SCRATCH_REG CYCLES +#endif + diff --git a/arch/blackfin/include/asm/dpmc.h b/arch/blackfin/include/asm/dpmc.h index e91eae8..2673b11 100644 --- a/arch/blackfin/include/asm/dpmc.h +++ b/arch/blackfin/include/asm/dpmc.h @@ -280,7 +280,7 @@ PM_POP_SYNC(9) #endif -#ifdef EBIU_AMBCTL +#ifdef EBIU_AMGCTL PM_SYS_POP(9, EBIU_AMBCTL1) PM_SYS_POP(8, EBIU_AMBCTL0) PM_SYS_POP16(7, EBIU_AMGCTL) diff --git a/arch/blackfin/include/asm/gpio.h b/arch/blackfin/include/asm/gpio.h index 3d84d96..98d0133 100644 --- a/arch/blackfin/include/asm/gpio.h +++ b/arch/blackfin/include/asm/gpio.h @@ -141,6 +141,8 @@ static inline void bfin_pm_standby_restore(void) void bfin_gpio_pm_hibernate_restore(void); void bfin_gpio_pm_hibernate_suspend(void); +void bfin_pint_suspend(void); +void bfin_pint_resume(void); # if !BFIN_GPIO_PINT int gpio_pm_wakeup_ctrl(unsigned gpio, unsigned ctrl); diff --git a/arch/blackfin/include/asm/irq.h b/arch/blackfin/include/asm/irq.h index 89de539..4ae1144 100644 --- a/arch/blackfin/include/asm/irq.h +++ b/arch/blackfin/include/asm/irq.h @@ -20,6 +20,16 @@ /* SYS_IRQS and NR_IRQS are defined in <mach-bf5xx/irq.h> */ #include <mach/irq.h> +/* + * pm save bfin pint registers + */ +struct bfin_pm_pint_save { + u32 mask_set; + u32 assign; + u32 edge_set; + u32 invert_set; +}; + #if ANOMALY_05000244 && defined(CONFIG_BFIN_ICACHE) # define NOP_PAD_ANOMALY_05000244 "nop; nop;" #else diff --git a/arch/blackfin/include/asm/mem_init.h b/arch/blackfin/include/asm/mem_init.h index 2375799..f019e9b 100644 --- a/arch/blackfin/include/asm/mem_init.h +++ b/arch/blackfin/include/asm/mem_init.h @@ -6,6 +6,9 @@ * Licensed under the GPL-2 or later. */ +#ifndef __MEM_INIT_H__ +#define __MEM_INIT_H__ + #if defined(EBIU_SDGCTL) #if defined(CONFIG_MEM_MT48LC16M16A2TG_75) || \ defined(CONFIG_MEM_MT48LC64M4A2FB_7E) || \ @@ -277,3 +280,212 @@ #else #define PLL_BYPASS 0 #endif + +#ifdef CONFIG_BF60x + +/* DMC status bits */ +#define IDLE 0x1 +#define MEMINITDONE 0x4 +#define SRACK 0x8 +#define PDACK 0x10 +#define DPDACK 0x20 +#define DLLCALDONE 0x2000 +#define PENDREF 0xF0000 +#define PHYRDPHASE 0xF00000 +#define PHYRDPHASE_OFFSET 20 + +/* DMC control bits */ +#define LPDDR 0x2 +#define INIT 0x4 +#define SRREQ 0x8 +#define PDREQ 0x10 +#define DPDREQ 0x20 +#define PREC 0x40 +#define ADDRMODE 0x100 +#define RDTOWR 0xE00 +#define PPREF 0x1000 +#define DLLCAL 0x2000 + +/* DMC DLL control bits */ +#define DLLCALRDCNT 0xFF +#define DATACYC 0xF00 +#define DATACYC_OFFSET 8 + +/* CGU Divisor bits */ +#define CSEL_OFFSET 0 +#define S0SEL_OFFSET 5 +#define SYSSEL_OFFSET 8 +#define S1SEL_OFFSET 13 +#define DSEL_OFFSET 16 +#define OSEL_OFFSET 22 +#define ALGN 0x20000000 +#define UPDT 0x40000000 +#define LOCK 0x80000000 + +/* CGU Status bits */ +#define PLLEN 0x1 +#define PLLBP 0x2 +#define PLOCK 0x4 +#define CLKSALGN 0x8 + +/* CGU Control bits */ +#define MSEL_MASK 0x7F00 +#define DF_MASK 0x1 + +struct ddr_config { + u32 ddr_clk; + u32 dmc_ddrctl; + u32 dmc_ddrcfg; + u32 dmc_ddrtr0; + u32 dmc_ddrtr1; + u32 dmc_ddrtr2; + u32 dmc_ddrmr; + u32 dmc_ddrmr1; +}; + +#if defined(CONFIG_MEM_MT47H64M16) +static struct ddr_config ddr_config_table[] __attribute__((section(".data_l1"))) = { + [0] = { + .ddr_clk = 125, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20705212, + .dmc_ddrtr1 = 0x201003CF, + .dmc_ddrtr2 = 0x00320107, + .dmc_ddrmr = 0x00000422, + .dmc_ddrmr1 = 0x4, + }, + [1] = { + .ddr_clk = 133, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20806313, + .dmc_ddrtr1 = 0x2013040D, + .dmc_ddrtr2 = 0x00320108, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [2] = { + .ddr_clk = 150, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20A07323, + .dmc_ddrtr1 = 0x20160492, + .dmc_ddrtr2 = 0x00320209, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [3] = { + .ddr_clk = 166, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20A07323, + .dmc_ddrtr1 = 0x2016050E, + .dmc_ddrtr2 = 0x00320209, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [4] = { + .ddr_clk = 200, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20a07323, + .dmc_ddrtr1 = 0x2016050f, + .dmc_ddrtr2 = 0x00320509, + .dmc_ddrmr = 0x00000632, + .dmc_ddrmr1 = 0x4, + }, + [5] = { + .ddr_clk = 225, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20E0A424, + .dmc_ddrtr1 = 0x302006DB, + .dmc_ddrtr2 = 0x0032020D, + .dmc_ddrmr = 0x00000842, + .dmc_ddrmr1 = 0x4, + }, + [6] = { + .ddr_clk = 250, + .dmc_ddrctl = 0x00000904, + .dmc_ddrcfg = 0x00000422, + .dmc_ddrtr0 = 0x20E0A424, + .dmc_ddrtr1 = 0x3020079E, + .dmc_ddrtr2 = 0x0032020D, + .dmc_ddrmr = 0x00000842, + .dmc_ddrmr1 = 0x4, + }, +}; +#endif + +static inline void dmc_enter_self_refresh(void) +{ + if (bfin_read_DMC0_STAT() & MEMINITDONE) { + bfin_write_DMC0_CTL(bfin_read_DMC0_CTL() | SRREQ); + while (!(bfin_read_DMC0_STAT() & SRACK)) + continue; + } +} + +static inline void dmc_exit_self_refresh(void) +{ + if (bfin_read_DMC0_STAT() & MEMINITDONE) { + bfin_write_DMC0_CTL(bfin_read_DMC0_CTL() & ~SRREQ); + while (bfin_read_DMC0_STAT() & SRACK) + continue; + } +} + +static inline void init_cgu(u32 cgu_div, u32 cgu_ctl) +{ + dmc_enter_self_refresh(); + + /* Don't set the same value of MSEL and DF to CGU_CTL */ + if ((bfin_read32(CGU0_CTL) & (MSEL_MASK | DF_MASK)) + != cgu_ctl) { + bfin_write32(CGU0_DIV, cgu_div); + bfin_write32(CGU0_CTL, cgu_ctl); + while ((bfin_read32(CGU0_STAT) & (CLKSALGN | PLLBP)) || + !(bfin_read32(CGU0_STAT) & PLOCK)) + continue; + } + + bfin_write32(CGU0_DIV, cgu_div | UPDT); + while (bfin_read32(CGU0_STAT) & CLKSALGN) + continue; + + dmc_exit_self_refresh(); +} + +static inline void init_dmc(u32 dmc_clk) +{ + int i, dlldatacycle, dll_ctl; + + for (i = 0; i < 7; i++) { + if (ddr_config_table[i].ddr_clk == dmc_clk) { + bfin_write_DMC0_CFG(ddr_config_table[i].dmc_ddrcfg); + bfin_write_DMC0_TR0(ddr_config_table[i].dmc_ddrtr0); + bfin_write_DMC0_TR1(ddr_config_table[i].dmc_ddrtr1); + bfin_write_DMC0_TR2(ddr_config_table[i].dmc_ddrtr2); + bfin_write_DMC0_MR(ddr_config_table[i].dmc_ddrmr); + bfin_write_DMC0_EMR1(ddr_config_table[i].dmc_ddrmr1); + bfin_write_DMC0_CTL(ddr_config_table[i].dmc_ddrctl); + break; + } + } + + while (!(bfin_read_DMC0_STAT() & MEMINITDONE)) + continue; + + dlldatacycle = (bfin_read_DMC0_STAT() & PHYRDPHASE) >> PHYRDPHASE_OFFSET; + dll_ctl = bfin_read_DMC0_DLLCTL(); + dll_ctl &= ~DATACYC; + bfin_write_DMC0_DLLCTL(dll_ctl | (dlldatacycle << DATACYC_OFFSET)); + + while (!(bfin_read_DMC0_STAT() & DLLCALDONE)) + continue; +} +#endif + +#endif /*__MEM_INIT_H__*/ + diff --git a/arch/blackfin/include/asm/traps.h b/arch/blackfin/include/asm/traps.h index 70c4e51..cec771b 100644 --- a/arch/blackfin/include/asm/traps.h +++ b/arch/blackfin/include/asm/traps.h @@ -125,5 +125,7 @@ level " for Supervisor use: Supervisor only registers, all MMRs, and Supervisor\n" \ level " only instructions.\n" +extern void double_fault_c(struct pt_regs *fp); + #endif /* __ASSEMBLY__ */ #endif /* _BFIN_TRAPS_H */ diff --git a/arch/blackfin/kernel/bfin_dma.c b/arch/blackfin/kernel/bfin_dma.c index c166939..4a32f2d 100644 --- a/arch/blackfin/kernel/bfin_dma.c +++ b/arch/blackfin/kernel/bfin_dma.c @@ -45,7 +45,7 @@ static int __init blackfin_dma_init(void) atomic_set(&dma_ch[i].chan_status, 0); dma_ch[i].regs = dma_io_base_addr[i]; } -#ifdef CH_MEM_STREAM3_SRC +#if defined(CH_MEM_STREAM3_SRC) && defined(CONFIG_BF60x) /* Mark MEMDMA Channel 3 as requested since we're using it internally */ request_dma(CH_MEM_STREAM3_DEST, "Blackfin dma_memcpy"); request_dma(CH_MEM_STREAM3_SRC, "Blackfin dma_memcpy"); @@ -361,7 +361,7 @@ void __init early_dma_memcpy_done(void) __builtin_bfin_ssync(); } -#ifdef CH_MEM_STREAM3_SRC +#if defined(CH_MEM_STREAM3_SRC) && defined(CONFIG_BF60x) #define bfin_read_MDMA_S_CONFIG bfin_read_MDMA_S3_CONFIG #define bfin_write_MDMA_S_CONFIG bfin_write_MDMA_S3_CONFIG #define bfin_write_MDMA_S_START_ADDR bfin_write_MDMA_S3_START_ADDR diff --git a/arch/blackfin/kernel/cplb-nompu/cplbinit.c b/arch/blackfin/kernel/cplb-nompu/cplbinit.c index 3e366dc..34e96ce 100644 --- a/arch/blackfin/kernel/cplb-nompu/cplbinit.c +++ b/arch/blackfin/kernel/cplb-nompu/cplbinit.c @@ -58,12 +58,20 @@ void __init generate_cplb_tables_cpu(unsigned int cpu) #ifdef CONFIG_ROMKERNEL /* Cover kernel XIP flash area */ +#ifdef CONFIG_BF60x + addr = CONFIG_ROM_BASE & ~(16 * 1024 * 1024 - 1); + d_tbl[i_d].addr = addr; + d_tbl[i_d++].data = SDRAM_DGENERIC | PAGE_SIZE_16MB; + i_tbl[i_i].addr = addr; + i_tbl[i_i++].data = SDRAM_IGENERIC | PAGE_SIZE_16MB; +#else addr = CONFIG_ROM_BASE & ~(4 * 1024 * 1024 - 1); d_tbl[i_d].addr = addr; d_tbl[i_d++].data = SDRAM_DGENERIC | PAGE_SIZE_4MB; i_tbl[i_i].addr = addr; i_tbl[i_i++].data = SDRAM_IGENERIC | PAGE_SIZE_4MB; #endif +#endif /* Cover L1 memory. One 4M area for code and data each is enough. */ if (cpu == 0) { diff --git a/arch/blackfin/kernel/dma-mapping.c b/arch/blackfin/kernel/dma-mapping.c index f0d1118..e7be653 100644 --- a/arch/blackfin/kernel/dma-mapping.c +++ b/arch/blackfin/kernel/dma-mapping.c @@ -122,12 +122,13 @@ void __dma_sync(dma_addr_t addr, size_t size, EXPORT_SYMBOL(__dma_sync); int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +dma_map_sg(struct device *dev, struct scatterlist *sg_list, int nents, enum dma_data_direction direction) { + struct scatterlist *sg; int i; - for (i = 0; i < nents; i++, sg++) { + for_each_sg(sg_list, sg, nents, i) { sg->dma_address = (dma_addr_t) sg_virt(sg); __dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction); } @@ -136,12 +137,13 @@ dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, } EXPORT_SYMBOL(dma_map_sg); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg_list, int nelems, enum dma_data_direction direction) { + struct scatterlist *sg; int i; - for (i = 0; i < nelems; i++, sg++) { + for_each_sg(sg_list, sg, nelems, i) { sg->dma_address = (dma_addr_t) sg_virt(sg); __dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction); } diff --git a/arch/blackfin/mach-bf527/boards/ezkit.c b/arch/blackfin/mach-bf527/boards/ezkit.c index af732eb..fc179ca 100644 --- a/arch/blackfin/mach-bf527/boards/ezkit.c +++ b/arch/blackfin/mach-bf527/boards/ezkit.c @@ -114,9 +114,9 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data musb_plat = { -#if defined(CONFIG_USB_MUSB_OTG) +#if defined(CONFIG_USB_MUSB_HDRC) && defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_OTG, -#elif defined(CONFIG_USB_MUSB_HDRC_HCD) +#elif defined(CONFIG_USB_MUSB_HDRC) .mode = MUSB_HOST, #elif defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_PERIPHERAL, diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c index c9d9473..5ed654a 100644 --- a/arch/blackfin/mach-bf537/boards/stamp.c +++ b/arch/blackfin/mach-bf537/boards/stamp.c @@ -873,7 +873,7 @@ static struct adf702x_platform_data adf7021_platform_data = { }; static inline void adf702x_mac_init(void) { - random_ether_addr(adf7021_platform_data.mac_addr); + eth_random_addr(adf7021_platform_data.mac_addr); } #else static inline void adf702x_mac_init(void) {} diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c index 3bd75ba..c4d07f0 100644 --- a/arch/blackfin/mach-bf548/boards/ezkit.c +++ b/arch/blackfin/mach-bf548/boards/ezkit.c @@ -635,9 +635,9 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data musb_plat = { -#if defined(CONFIG_USB_MUSB_OTG) +#if defined(CONFIG_USB_MUSB_HDRC) && defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_OTG, -#elif defined(CONFIG_USB_MUSB_HDRC_HCD) +#elif defined(CONFIG_USB_MUSB_HDRC) .mode = MUSB_HOST, #elif defined(CONFIG_USB_GADGET_MUSB_HDRC) .mode = MUSB_PERIPHERAL, diff --git a/arch/blackfin/mach-bf548/include/mach/gpio.h b/arch/blackfin/mach-bf548/include/mach/gpio.h index 35c8ced..be9edb2 100644 --- a/arch/blackfin/mach-bf548/include/mach/gpio.h +++ b/arch/blackfin/mach-bf548/include/mach/gpio.h @@ -171,6 +171,8 @@ #define MAX_BLACKFIN_GPIOS 160 #define BFIN_GPIO_PINT 1 +#define NR_PINT_SYS_IRQS 4 +#define NR_PINTS 160 #ifndef __ASSEMBLY__ diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index 8389788..7c36777 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -452,18 +452,21 @@ static struct v4l2_input adv7183_inputs[] = { .name = "Composite", .type = V4L2_INPUT_TYPE_CAMERA, .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, }, { .index = 1, .name = "S-Video", .type = V4L2_INPUT_TYPE_CAMERA, .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, }, { .index = 2, .name = "Component", .type = V4L2_INPUT_TYPE_CAMERA, .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, }, }; diff --git a/arch/blackfin/mach-bf609/Kconfig b/arch/blackfin/mach-bf609/Kconfig index 2cb7272..101b33e 100644 --- a/arch/blackfin/mach-bf609/Kconfig +++ b/arch/blackfin/mach-bf609/Kconfig @@ -51,6 +51,14 @@ config PINT5_ASSIGN endmenu +config SEC_IRQ_PRIORITY_LEVELS + int "SEC interrupt priority levels" + default 7 + range 0 7 + help + Devide the total number of interrupt priority levels into sub-levels. + There is 2 ^ (SEC_IRQ_PRIORITY_LEVELS + 1) different levels. + endmenu endif diff --git a/arch/blackfin/mach-bf609/Makefile b/arch/blackfin/mach-bf609/Makefile index 2a27f81..234fe1b 100644 --- a/arch/blackfin/mach-bf609/Makefile +++ b/arch/blackfin/mach-bf609/Makefile @@ -2,5 +2,5 @@ # arch/blackfin/mach-bf609/Makefile # -obj-y := dma.o clock.o -obj-$(CONFIG_PM) += pm.o hibernate.o +obj-y := dma.o clock.o ints-priority.o +obj-$(CONFIG_PM) += pm.o dpm.o diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c index ac64f47..c2cf1ae 100644 --- a/arch/blackfin/mach-bf609/boards/ezkit.c +++ b/arch/blackfin/mach-bf609/boards/ezkit.c @@ -677,11 +677,28 @@ int bf609_nor_flash_init(struct platform_device *dev) return 0; } +void bf609_nor_flash_exit(struct platform_device *dev) +{ + const unsigned short pins[] = { + P_A3, P_A4, P_A5, P_A6, P_A7, P_A8, P_A9, P_A10, P_A11, P_A12, + P_A13, P_A14, P_A15, P_A16, P_A17, P_A18, P_A19, P_A20, P_A21, + P_A22, P_A23, P_A24, P_A25, P_NORCK, 0, + }; + + peripheral_free_list(pins); + + bfin_write32(SMC_GCTL, 0); +} + static struct physmap_flash_data ezkit_flash_data = { .width = 2, .parts = ezkit_partitions, - .init = bf609_nor_flash_init, + .init = bf609_nor_flash_init, + .exit = bf609_nor_flash_exit, .nr_parts = ARRAY_SIZE(ezkit_partitions), +#ifdef CONFIG_ROMKERNEL + .probe_type = "map_rom", +#endif }; static struct resource ezkit_flash_resource = { @@ -739,7 +756,7 @@ static struct bfin6xx_spi_chip spidev_chip_info = { }; #endif -#if defined(CONFIG_SND_BF6XX_I2S) || defined(CONFIG_SND_BF6XX_I2S_MODULE) +#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) static struct platform_device bfin_i2s_pcm = { .name = "bfin-i2s-pcm-audio", .id = -1, @@ -825,6 +842,12 @@ static struct adau1761_platform_data adau1761_info = { static const unsigned short ppi_req[] = { P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3, P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7, + P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11, + P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15, +#if !defined(CONFIG_VIDEO_VS6624) && !defined(CONFIG_VIDEO_VS6624_MODULE) + P_PPI0_D16, P_PPI0_D17, P_PPI0_D18, P_PPI0_D19, + P_PPI0_D20, P_PPI0_D21, P_PPI0_D22, P_PPI0_D23, +#endif P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2, 0, }; @@ -855,7 +878,7 @@ static struct bcap_route vs6624_routes[] = { }, }; -static const unsigned vs6624_ce_pin = GPIO_PD1; +static const unsigned vs6624_ce_pin = GPIO_PE4; static struct bfin_capture_config bfin_capture_data = { .card_name = "BF609", @@ -871,7 +894,128 @@ static struct bfin_capture_config bfin_capture_data = { .ppi_info = &ppi_info, .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FS1HI_FS2HI | EPPI_CTL_POLC3 | EPPI_CTL_SYNC2 | EPPI_CTL_NON656), - .blank_clocks = 8, + .blank_pixels = 4, +}; +#endif + +#if defined(CONFIG_VIDEO_ADV7842) \ + || defined(CONFIG_VIDEO_ADV7842_MODULE) +#include <media/adv7842.h> + +static struct v4l2_input adv7842_inputs[] = { + { + .index = 0, + .name = "Composite", + .type = V4L2_INPUT_TYPE_CAMERA, + .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, + }, + { + .index = 1, + .name = "S-Video", + .type = V4L2_INPUT_TYPE_CAMERA, + .std = V4L2_STD_ALL, + .capabilities = V4L2_IN_CAP_STD, + }, + { + .index = 2, + .name = "Component", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS, + }, + { + .index = 3, + .name = "VGA", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS, + }, + { + .index = 4, + .name = "HDMI", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_IN_CAP_CUSTOM_TIMINGS, + }, +}; + +static struct bcap_route adv7842_routes[] = { + { + .input = 3, + .output = 0, + .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FLDSEL + | EPPI_CTL_ACTIVE656), + }, + { + .input = 4, + .output = 0, + }, + { + .input = 2, + .output = 0, + }, + { + .input = 1, + .output = 0, + }, + { + .input = 0, + .output = 1, + .ppi_control = (EPPI_CTL_SPLTWRD | PACK_EN | DLEN_16 + | EPPI_CTL_FS1LO_FS2LO | EPPI_CTL_POLC2 + | EPPI_CTL_SYNC2 | EPPI_CTL_NON656), + }, +}; + +static struct adv7842_output_format adv7842_opf[] = { + { + .op_ch_sel = ADV7842_OP_CH_SEL_BRG, + .op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_8, + .op_656_range = 1, + .blank_data = 1, + .insert_av_codes = 1, + }, + { + .op_ch_sel = ADV7842_OP_CH_SEL_RGB, + .op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_16, + .op_656_range = 1, + .blank_data = 1, + }, +}; + +static struct adv7842_platform_data adv7842_data = { + .opf = adv7842_opf, + .num_opf = ARRAY_SIZE(adv7842_opf), + .ain_sel = ADV7842_AIN10_11_12_NC_SYNC_4_1, + .prim_mode = ADV7842_PRIM_MODE_SDP, + .vid_std_select = ADV7842_SDP_VID_STD_CVBS_SD_4x1, + .inp_color_space = ADV7842_INP_COLOR_SPACE_AUTO, + .i2c_sdp_io = 0x40, + .i2c_sdp = 0x41, + .i2c_cp = 0x42, + .i2c_vdp = 0x43, + .i2c_afe = 0x44, + .i2c_hdmi = 0x45, + .i2c_repeater = 0x46, + .i2c_edid = 0x47, + .i2c_infoframe = 0x48, + .i2c_cec = 0x49, + .i2c_avlink = 0x4a, + .i2c_ex = 0x26, +}; + +static struct bfin_capture_config bfin_capture_data = { + .card_name = "BF609", + .inputs = adv7842_inputs, + .num_inputs = ARRAY_SIZE(adv7842_inputs), + .routes = adv7842_routes, + .i2c_adapter_id = 0, + .board_info = { + .type = "adv7842", + .addr = 0x20, + .platform_data = (void *)&adv7842_data, + }, + .ppi_info = &ppi_info, + .ppi_control = (PACK_EN | DLEN_8 | EPPI_CTL_FLDSEL + | EPPI_CTL_ACTIVE656), }; #endif @@ -883,6 +1027,80 @@ static struct platform_device bfin_capture_device = { }; #endif +#if defined(CONFIG_VIDEO_BLACKFIN_DISPLAY) \ + || defined(CONFIG_VIDEO_BLACKFIN_DISPLAY_MODULE) +#include <linux/videodev2.h> +#include <media/blackfin/bfin_display.h> +#include <media/blackfin/ppi.h> + +static const unsigned short ppi_req_disp[] = { + P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3, + P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7, + P_PPI0_D8, P_PPI0_D9, P_PPI0_D10, P_PPI0_D11, + P_PPI0_D12, P_PPI0_D13, P_PPI0_D14, P_PPI0_D15, + P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2, + 0, +}; + +static const struct ppi_info ppi_info = { + .type = PPI_TYPE_EPPI3, + .dma_ch = CH_EPPI0_CH0, + .irq_err = IRQ_EPPI0_STAT, + .base = (void __iomem *)EPPI0_STAT, + .pin_req = ppi_req_disp, +}; + +#if defined(CONFIG_VIDEO_ADV7511) \ + || defined(CONFIG_VIDEO_ADV7511_MODULE) +#include <media/adv7511.h> + +static struct v4l2_output adv7511_outputs[] = { + { + .index = 0, + .name = "HDMI", + .type = V4L2_INPUT_TYPE_CAMERA, + .capabilities = V4L2_OUT_CAP_CUSTOM_TIMINGS, + }, +}; + +static struct disp_route adv7511_routes[] = { + { + .output = 0, + }, +}; + +static struct adv7511_platform_data adv7511_data = { + .edid_addr = 0x7e, + .i2c_ex = 0x25, +}; + +static struct bfin_display_config bfin_display_data = { + .card_name = "BF609", + .outputs = adv7511_outputs, + .num_outputs = ARRAY_SIZE(adv7511_outputs), + .routes = adv7511_routes, + .i2c_adapter_id = 0, + .board_info = { + .type = "adv7511", + .addr = 0x39, + .platform_data = (void *)&adv7511_data, + }, + .ppi_info = &ppi_info, + .ppi_control = (EPPI_CTL_SPLTWRD | PACK_EN | DLEN_16 + | EPPI_CTL_FS1LO_FS2LO | EPPI_CTL_POLC3 + | EPPI_CTL_IFSGEN | EPPI_CTL_SYNC2 + | EPPI_CTL_NON656 | EPPI_CTL_DIR), +}; +#endif + +static struct platform_device bfin_display_device = { + .name = "bfin_display", + .dev = { + .platform_data = &bfin_display_data, + }, +}; +#endif + #if defined(CONFIG_BFIN_CRC) #define BFIN_CRC_NAME "bfin-crc" @@ -947,6 +1165,39 @@ static struct platform_device bfin_crc1_device = { }; #endif +#if defined(CONFIG_CRYPTO_DEV_BFIN_CRC) +#define BFIN_CRYPTO_CRC_NAME "bfin-hmac-crc" +#define BFIN_CRYPTO_CRC_POLY_DATA 0x5c5c5c5c + +static struct resource bfin_crypto_crc_resources[] = { + { + .start = REG_CRC0_CTL, + .end = REG_CRC0_REVID+4, + .flags = IORESOURCE_MEM, + }, + { + .start = IRQ_CRC0_DCNTEXP, + .end = IRQ_CRC0_DCNTEXP, + .flags = IORESOURCE_IRQ, + }, + { + .start = CH_MEM_STREAM0_SRC_CRC0, + .end = CH_MEM_STREAM0_SRC_CRC0, + .flags = IORESOURCE_DMA, + }, +}; + +static struct platform_device bfin_crypto_crc_device = { + .name = BFIN_CRYPTO_CRC_NAME, + .id = 0, + .num_resources = ARRAY_SIZE(bfin_crypto_crc_resources), + .resource = bfin_crypto_crc_resources, + .dev = { + .platform_data = (void *)BFIN_CRYPTO_CRC_POLY_DATA, + }, +}; +#endif + #if defined(CONFIG_TOUCHSCREEN_AD7877) || defined(CONFIG_TOUCHSCREEN_AD7877_MODULE) static const struct ad7877_platform_data bfin_ad7877_ts_info = { .model = 7877, @@ -963,6 +1214,28 @@ static const struct ad7877_platform_data bfin_ad7877_ts_info = { }; #endif +#if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) +#include <linux/input.h> +#include <linux/gpio_keys.h> + +static struct gpio_keys_button bfin_gpio_keys_table[] = { + {BTN_0, GPIO_PB10, 1, "gpio-keys: BTN0"}, + {BTN_1, GPIO_PE1, 1, "gpio-keys: BTN1"}, +}; + +static struct gpio_keys_platform_data bfin_gpio_keys_data = { + .buttons = bfin_gpio_keys_table, + .nbuttons = ARRAY_SIZE(bfin_gpio_keys_table), +}; + +static struct platform_device bfin_device_gpiokeys = { + .name = "gpio-keys", + .dev = { + .platform_data = &bfin_gpio_keys_data, + }, +}; +#endif + static struct spi_board_info bfin_spi_board_info[] __initdata = { #if defined(CONFIG_MTD_M25P80) \ || defined(CONFIG_MTD_M25P80_MODULE) @@ -981,10 +1254,10 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { { .modalias = "ad7877", .platform_data = &bfin_ad7877_ts_info, - .irq = IRQ_PB4, /* old boards (<=Rev 1.3) use IRQ_PJ11 */ + .irq = IRQ_PD9, .max_speed_hz = 12500000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, - .chip_select = 2, + .chip_select = 4, }, #endif #if defined(CONFIG_SPI_SPIDEV) || defined(CONFIG_SPI_SPIDEV_MODULE) @@ -1050,7 +1323,7 @@ static struct resource bfin_spi1_resource[] = { /* SPI controller data */ static struct bfin6xx_spi_master bf60x_spi_master_info0 = { - .num_chipselect = 4, + .num_chipselect = MAX_CTRL_CS + MAX_BLACKFIN_GPIOS, .pin_req = {P_SPI0_SCK, P_SPI0_MISO, P_SPI0_MOSI, 0}, }; @@ -1065,7 +1338,7 @@ static struct platform_device bf60x_spi_master0 = { }; static struct bfin6xx_spi_master bf60x_spi_master_info1 = { - .num_chipselect = 4, + .num_chipselect = MAX_CTRL_CS + MAX_BLACKFIN_GPIOS, .pin_req = {P_SPI1_SCK, P_SPI1_MISO, P_SPI1_MOSI, 0}, }; @@ -1146,6 +1419,11 @@ static struct i2c_board_info __initdata bfin_i2c_board_info0[] = { .platform_data = (void *)&adau1761_info }, #endif +#if defined(CONFIG_SND_SOC_SSM2602) || defined(CONFIG_SND_SOC_SSM2602_MODULE) + { + I2C_BOARD_INFO("ssm2602", 0x1b), + }, +#endif }; static struct i2c_board_info __initdata bfin_i2c_board_info1[] = { @@ -1261,6 +1539,9 @@ static struct platform_device *ezkit_devices[] __initdata = { &bfin_crc0_device, &bfin_crc1_device, #endif +#if defined(CONFIG_CRYPTO_DEV_BFIN_CRC) + &bfin_crypto_crc_device, +#endif #if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE) &bfin_device_gpiokeys, @@ -1269,7 +1550,7 @@ static struct platform_device *ezkit_devices[] __initdata = { #if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE) &ezkit_flash_device, #endif -#if defined(CONFIG_SND_BF6XX_I2S) || defined(CONFIG_SND_BF6XX_I2S_MODULE) +#if defined(CONFIG_SND_BF5XX_I2S) || defined(CONFIG_SND_BF5XX_I2S_MODULE) &bfin_i2s_pcm, #endif #if defined(CONFIG_SND_BF6XX_SOC_I2S) || \ @@ -1284,6 +1565,11 @@ static struct platform_device *ezkit_devices[] __initdata = { || defined(CONFIG_VIDEO_BLACKFIN_CAPTURE_MODULE) &bfin_capture_device, #endif +#if defined(CONFIG_VIDEO_BLACKFIN_DISPLAY) \ + || defined(CONFIG_VIDEO_BLACKFIN_DISPLAY_MODULE) + &bfin_display_device, +#endif + }; static int __init ezkit_init(void) diff --git a/arch/blackfin/mach-bf609/clock.c b/arch/blackfin/mach-bf609/clock.c index 7f8f529..437d56c 100644 --- a/arch/blackfin/mach-bf609/clock.c +++ b/arch/blackfin/mach-bf609/clock.c @@ -97,9 +97,10 @@ int wait_for_pll_align(void) while (i-- && (bfin_read32(CGU0_STAT) & CGU0_STAT_CLKSALGN)); if (bfin_read32(CGU0_STAT) & CGU0_STAT_CLKSALGN) { - printk(KERN_DEBUG "fail to align clk\n"); + printk(KERN_CRIT "fail to align clk\n"); return -1; } + return 0; } diff --git a/arch/blackfin/mach-bf609/dpm.S b/arch/blackfin/mach-bf609/dpm.S new file mode 100644 index 0000000..54d50c6 --- /dev/null +++ b/arch/blackfin/mach-bf609/dpm.S @@ -0,0 +1,157 @@ +#include <linux/linkage.h> +#include <asm/blackfin.h> +#include <asm/dpmc.h> + +#include <asm/context.S> + +#define PM_STACK (COREA_L1_SCRATCH_START + L1_SCRATCH_LENGTH - 12) + +.section .l1.text +ENTRY(_enter_hibernate) + /* switch stack to L1 scratch, prepare for ddr srfr */ + P0.H = HI(PM_STACK); + P0.L = LO(PM_STACK); + SP = P0; + + call _bf609_ddr_sr; + call _bfin_hibernate_syscontrol; + + P0.H = HI(DPM0_RESTORE4); + P0.L = LO(DPM0_RESTORE4); + P1.H = _bf609_pm_data; + P1.L = _bf609_pm_data; + [P0] = P1; + + P0.H = HI(DPM0_CTL); + P0.L = LO(DPM0_CTL); + R3.H = HI(0x00000010); + R3.L = LO(0x00000010); + + bfin_init_pm_bench_cycles; + + [P0] = R3; + + SSYNC; +ENDPROC(_enter_hibernate) + +/* DPM wake up interrupt won't wake up core on bf60x if its core IMASK + * is disabled. This behavior differ from bf5xx serial processor. + */ +ENTRY(_dummy_deepsleep) + [--sp] = SYSCFG; + [--sp] = (R7:0,P5:0); + cli r0; + + /* get wake up interrupt ID */ + P0.l = LO(SEC_SCI_BASE + SEC_CSID); + P0.h = HI(SEC_SCI_BASE + SEC_CSID); + R0 = [P0]; + + /* ACK wake up interrupt in SEC */ + P1.l = LO(SEC_END); + P1.h = HI(SEC_END); + + [P1] = R0; + SSYNC; + + /* restore EVT 11 entry */ + p0.h = hi(EVT11); + p0.l = lo(EVT11); + p1.h = _evt_evt11; + p1.l = _evt_evt11; + + [p0] = p1; + SSYNC; + + (R7:0,P5:0) = [sp++]; + SYSCFG = [sp++]; + RTI; +ENDPROC(_dummy_deepsleep) + +ENTRY(_enter_deepsleep) + LINK 0xC; + [--sp] = (R7:0,P5:0); + + /* Change EVT 11 entry to dummy handler for wake up event */ + p0.h = hi(EVT11); + p0.l = lo(EVT11); + p1.h = _dummy_deepsleep; + p1.l = _dummy_deepsleep; + + [p0] = p1; + + P0.H = HI(PM_STACK); + P0.L = LO(PM_STACK); + + EX_SCRATCH_REG = SP; + SP = P0; + + SSYNC; + + /* should put ddr to self refresh mode before sleep */ + call _bf609_ddr_sr; + + /* Set DPM controller to deep sleep mode */ + P0.H = HI(DPM0_CTL); + P0.L = LO(DPM0_CTL); + R3.H = HI(0x00000008); + R3.L = LO(0x00000008); + [P0] = R3; + CSYNC; + + /* Enable evt 11 in IMASK before idle, otherwise core doesn't wake up. */ + r0.l = 0x800; + r0.h = 0; + sti r0; + SSYNC; + + bfin_init_pm_bench_cycles; + + /* Fall into deep sleep in idle*/ + idle; + SSYNC; + + /* Restore PLL after wake up from deep sleep */ + call _bf609_resume_ccbuf; + + /* turn ddr out of self refresh mode */ + call _bf609_ddr_sr_exit; + + SP = EX_SCRATCH_REG; + + (R7:0,P5:0) = [SP++]; + UNLINK; + RTS; +ENDPROC(_enter_deepsleep) + +.section .text +ENTRY(_bf609_hibernate) + bfin_cpu_reg_save; + bfin_core_mmr_save; + + P0.H = _bf609_pm_data; + P0.L = _bf609_pm_data; + R1.H = 0xDEAD; + R1.L = 0xBEEF; + R2.H = .Lpm_resume_here; + R2.L = .Lpm_resume_here; + [P0++] = R1; + [P0++] = R2; + [P0++] = SP; + + P1.H = _enter_hibernate; + P1.L = _enter_hibernate; + + call (P1); +.Lpm_resume_here: + + bfin_core_mmr_restore; + bfin_cpu_reg_restore; + + [--sp] = RETI; /* Clear Global Interrupt Disable */ + SP += 4; + + RTS; + +ENDPROC(_bf609_hibernate) + diff --git a/arch/blackfin/mach-bf609/hibernate.S b/arch/blackfin/mach-bf609/hibernate.S deleted file mode 100644 index d37a532..0000000 --- a/arch/blackfin/mach-bf609/hibernate.S +++ /dev/null @@ -1,65 +0,0 @@ -#include <linux/linkage.h> -#include <asm/blackfin.h> -#include <asm/dpmc.h> - -#define PM_STACK (COREA_L1_SCRATCH_START + L1_SCRATCH_LENGTH - 12) - -.section .l1.text -ENTRY(_enter_hibernate) - /* switch stack to L1 scratch, prepare for ddr srfr */ - P0.H = HI(PM_STACK); - P0.L = LO(PM_STACK); - SP = P0; - - call _bf609_ddr_sr; - call _bfin_hibernate_syscontrol; - - P0.H = HI(DPM0_RESTORE4); - P0.L = LO(DPM0_RESTORE4); - P1.H = _bf609_pm_data; - P1.L = _bf609_pm_data; - [P0] = P1; - - P0.H = HI(DPM0_CTL); - P0.L = LO(DPM0_CTL); - R3.H = HI(0x00000010); - R3.L = LO(0x00000010); - - bfin_init_pm_bench_cycles; - - [P0] = R3; - - SSYNC; -ENDPROC(_enter_hibernate_mode) - -.section .text -ENTRY(_bf609_hibernate) - bfin_cpu_reg_save; - bfin_core_mmr_save; - - P0.H = _bf609_pm_data; - P0.L = _bf609_pm_data; - R1.H = 0xDEAD; - R1.L = 0xBEEF; - R2.H = .Lpm_resume_here; - R2.L = .Lpm_resume_here; - [P0++] = R1; - [P0++] = R2; - [P0++] = SP; - - P1.H = _enter_hibernate; - P1.L = _enter_hibernate; - - call (P1); -.Lpm_resume_here: - - bfin_core_mmr_restore; - bfin_cpu_reg_restore; - - [--sp] = RETI; /* Clear Global Interrupt Disable */ - SP += 4; - - RTS; - -ENDPROC(_bf609_hibernate) - diff --git a/arch/blackfin/mach-bf609/include/mach/anomaly.h b/arch/blackfin/mach-bf609/include/mach/anomaly.h index bdd39ae..7a07374 100644 --- a/arch/blackfin/mach-bf609/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf609/include/mach/anomaly.h @@ -5,126 +5,99 @@ * and can be replaced with that version at any time * DO NOT EDIT THIS FILE * - * Copyright 2004-2011 Analog Devices Inc. + * Copyright 2004-2012 Analog Devices Inc. * Licensed under the Clear BSD license. */ /* This file should be up to date with: + * - Revision A, 15/06/2012; ADSP-BF609 Blackfin Processor Anomaly List */ #if __SILICON_REVISION__ < 0 -# error will not work on BF506 silicon version +# error will not work on BF609 silicon version #endif #ifndef _MACH_ANOMALY_H_ #define _MACH_ANOMALY_H_ -/* Multi-Issue Instruction with dsp32shiftimm in slot1 and P-reg Store in slot2 Not Supported */ -#define ANOMALY_05000074 (1) -/* DMA_RUN Bit Is Not Valid after a Peripheral Receive Channel DMA Stops */ -#define ANOMALY_05000119 (1) -/* Rx.H Cannot Be Used to Access 16-bit System MMR Registers */ -#define ANOMALY_05000122 (1) -/* False Hardware Error from an Access in the Shadow of a Conditional Branch */ -#define ANOMALY_05000245 (1) -/* Incorrect Timer Pulse Width in Single-Shot PWM_OUT Mode with External Clock */ -#define ANOMALY_05000254 (1) -/* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ -#define ANOMALY_05000265 (1) -/* False Hardware Errors Caused by Fetches at the Boundary of Reserved Memory */ -#define ANOMALY_05000310 (1) -/* PPI Underflow Error Goes Undetected in ITU-R 656 Mode */ -#define ANOMALY_05000366 (1) -/* Speculative Fetches Can Cause Undesired External FIFO Operations */ -#define ANOMALY_05000416 (1) -/* Speculative Fetches of Indirect-Pointer Instructions Can Cause False Hardware Errors */ -#define ANOMALY_05000426 (1) +/* TRU_STAT.ADDRERR and TRU_ERRADDR.ADDR May Not Reflect the Correct Status */ +#define ANOMALY_16000003 (1) +/* The EPPI Data Enable (DEN) Signal is Not Functional */ +#define ANOMALY_16000004 (1) +/* Using L1 Instruction Cache with Parity Enabled is Unreliable */ +#define ANOMALY_16000005 (1) +/* SEQSTAT.SYSNMI Clears Upon Entering the NMI ISR */ +#define ANOMALY_16000006 (1) +/* DDR2 Memory Reads May Fail Intermittently */ +#define ANOMALY_16000007 (1) +/* Instruction Memory Stalls Can Cause IFLUSH to Fail */ +#define ANOMALY_16000008 (1) +/* TestSET Instruction Cannot Be Interrupted */ +#define ANOMALY_16000009 (1) /* IFLUSH Instruction at End of Hardware Loop Causes Infinite Stall */ -#define ANOMALY_05000443 (1) -/* UART IrDA Receiver Fails on Extended Bit Pulses */ -#define ANOMALY_05000447 (1) +#define ANOMALY_16000010 (1) /* False Hardware Error when RETI Points to Invalid Memory */ -#define ANOMALY_05000461 (1) -/* PLL Latches Incorrect Settings During Reset */ -#define ANOMALY_05000469 (1) -/* Incorrect Default MSEL Value in PLL_CTL */ -#define ANOMALY_05000472 (1) -/* Interrupted SPORT Receive Data Register Read Results In Underflow when SLEN > 15 */ -#define ANOMALY_05000473 (1) -/* TESTSET Instruction Cannot Be Interrupted */ -#define ANOMALY_05000477 (1) -/* Reads of ITEST_COMMAND and ITEST_DATA Registers Cause Cache Corruption */ -#define ANOMALY_05000481 (1) -/* IFLUSH sucks at life */ -#define ANOMALY_05000491 (1) -/* Tempopary anomaly ID for data loss in MMR read operation if interrupted */ -#define ANOMALY_05001001 (__SILICON_REVISION__ < 1) +#define ANOMALY_16000011 (1) +/* Speculative Fetches of Indirect-Pointer Instructions Can Cause False Hardware Errors */ +#define ANOMALY_16000012 (1) +/* False Hardware Errors Caused by Fetches at the Boundary of Reserved Memory */ +#define ANOMALY_16000013 (1) +/* False Hardware Error from an Access in the Shadow of a Conditional Branch */ +#define ANOMALY_16000014 (1) +/* Multi-Issue Instruction with dsp32shiftimm in slot1 and P-reg Store in slot2 Not Supported */ +#define ANOMALY_16000015 (1) +/* Speculative Fetches Can Cause Undesired External FIFO Operations */ +#define ANOMALY_16000017 (1) +/* RSI Boot Cleanup Routine Does Not Clear Registers */ +#define ANOMALY_16000018 (1) +/* SPI Master Boot Device Auto-detection Frequency is Set Incorrectly */ +#define ANOMALY_16000019 (1) +/* rom_SysControl() Fails to Set DDR0_CTL.INIT for Wakeup From Hibernate */ +#define ANOMALY_16000020 (1) +/* rom_SysControl() Fails to Save and Restore DDR0_PHYCTL3 for Hibernate/Wakeup Sequence */ +#define ANOMALY_16000021 (1) +/* Boot Code Fails to Enable Parity Fault Detection */ +#define ANOMALY_16000022 (1) +/* USB DMA interrupt status do not show the DMA channel interrupt in the DMA ISR */ +#define ANOMALY_16000027 (1) +/* Interrupted Core Reads of MMRs May Cause Data Loss */ +#define ANOMALY_16000030 (1) /* Anomalies that don't exist on this proc */ -#define ANOMALY_05000099 (0) -#define ANOMALY_05000120 (0) -#define ANOMALY_05000125 (0) -#define ANOMALY_05000149 (0) #define ANOMALY_05000158 (0) -#define ANOMALY_05000171 (0) -#define ANOMALY_05000179 (0) -#define ANOMALY_05000182 (0) -#define ANOMALY_05000183 (0) #define ANOMALY_05000189 (0) #define ANOMALY_05000198 (0) -#define ANOMALY_05000202 (0) -#define ANOMALY_05000215 (0) -#define ANOMALY_05000219 (0) #define ANOMALY_05000220 (0) -#define ANOMALY_05000227 (0) #define ANOMALY_05000230 (0) #define ANOMALY_05000231 (0) -#define ANOMALY_05000233 (0) -#define ANOMALY_05000234 (0) -#define ANOMALY_05000242 (0) #define ANOMALY_05000244 (0) -#define ANOMALY_05000248 (0) -#define ANOMALY_05000250 (0) -#define ANOMALY_05000257 (0) -#define ANOMALY_05000261 (0) #define ANOMALY_05000263 (0) -#define ANOMALY_05000266 (0) #define ANOMALY_05000273 (0) #define ANOMALY_05000274 (0) #define ANOMALY_05000278 (0) #define ANOMALY_05000281 (0) -#define ANOMALY_05000283 (0) -#define ANOMALY_05000285 (0) #define ANOMALY_05000287 (0) -#define ANOMALY_05000301 (0) -#define ANOMALY_05000305 (0) -#define ANOMALY_05000307 (0) #define ANOMALY_05000311 (0) #define ANOMALY_05000312 (0) -#define ANOMALY_05000315 (0) #define ANOMALY_05000323 (0) -#define ANOMALY_05000353 (1) -#define ANOMALY_05000357 (0) -#define ANOMALY_05000362 (1) #define ANOMALY_05000363 (0) -#define ANOMALY_05000364 (0) -#define ANOMALY_05000371 (0) #define ANOMALY_05000380 (0) -#define ANOMALY_05000386 (0) -#define ANOMALY_05000389 (0) -#define ANOMALY_05000400 (0) -#define ANOMALY_05000402 (0) -#define ANOMALY_05000412 (0) -#define ANOMALY_05000432 (0) -#define ANOMALY_05000440 (0) #define ANOMALY_05000448 (0) -#define ANOMALY_05000456 (0) #define ANOMALY_05000450 (0) -#define ANOMALY_05000465 (0) -#define ANOMALY_05000467 (0) -#define ANOMALY_05000474 (0) -#define ANOMALY_05000475 (0) +#define ANOMALY_05000456 (0) #define ANOMALY_05000480 (0) -#define ANOMALY_05000485 (0) +#define ANOMALY_05000481 (1) + +/* Reuse BF5xx anomalies IDs for the same anomaly in BF60x */ +#define ANOMALY_05000491 ANOMALY_16000008 +#define ANOMALY_05000477 ANOMALY_16000009 +#define ANOMALY_05000443 ANOMALY_16000010 +#define ANOMALY_05000461 ANOMALY_16000011 +#define ANOMALY_05000426 ANOMALY_16000012 +#define ANOMALY_05000310 ANOMALY_16000013 +#define ANOMALY_05000245 ANOMALY_16000014 +#define ANOMALY_05000074 ANOMALY_16000015 +#define ANOMALY_05000416 ANOMALY_16000017 + #endif diff --git a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h index 6aac385..f1a6afa 100644 --- a/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h +++ b/arch/blackfin/mach-bf609/include/mach/defBF60x_base.h @@ -2665,7 +2665,6 @@ #define DEVSZ_1G 0x400 /* DMC External Bank Size = 1Gbit */ #define DEVSZ_2G 0x500 /* DMC External Bank Size = 2Gbit */ - /* ========================= L2CTL Registers ========================= */ diff --git a/arch/blackfin/mach-bf609/include/mach/gpio.h b/arch/blackfin/mach-bf609/include/mach/gpio.h index 127586b..c32c8cc 100644 --- a/arch/blackfin/mach-bf609/include/mach/gpio.h +++ b/arch/blackfin/mach-bf609/include/mach/gpio.h @@ -123,6 +123,8 @@ #define BFIN_GPIO_PINT 1 +#define NR_PINT_SYS_IRQS 6 +#define NR_PINTS 112 #ifndef __ASSEMBLY__ diff --git a/arch/blackfin/mach-bf609/include/mach/irq.h b/arch/blackfin/mach-bf609/include/mach/irq.h index 0004552..23e74cd 100644 --- a/arch/blackfin/mach-bf609/include/mach/irq.h +++ b/arch/blackfin/mach-bf609/include/mach/irq.h @@ -293,9 +293,13 @@ #define NR_MACH_IRQS (IRQ_PG15 + 1) +#define SEC_SCTL_PRIO_OFFSET 8 + #ifndef __ASSEMBLY__ #include <linux/types.h> +extern u8 sec_int_priority[]; + /* * bfin pint registers layout */ diff --git a/arch/blackfin/mach-bf609/include/mach/pm.h b/arch/blackfin/mach-bf609/include/mach/pm.h index 036d9bdc8..3ca0fb9 100644 --- a/arch/blackfin/mach-bf609/include/mach/pm.h +++ b/arch/blackfin/mach-bf609/include/mach/pm.h @@ -11,11 +11,14 @@ #include <linux/suspend.h> -int bfin609_pm_enter(suspend_state_t state); -int bf609_pm_prepare(void); -void bf609_pm_finish(void); +extern int bfin609_pm_enter(suspend_state_t state); +extern int bf609_pm_prepare(void); +extern void bf609_pm_finish(void); void bf609_hibernate(void); void bfin_sec_raise_irq(unsigned int sid); void coreb_enable(void); + +int bf609_nor_flash_init(void); +void bf609_nor_flash_exit(void); #endif diff --git a/arch/blackfin/mach-bf609/ints-priority.c b/arch/blackfin/mach-bf609/ints-priority.c new file mode 100644 index 0000000..f68abb9 --- /dev/null +++ b/arch/blackfin/mach-bf609/ints-priority.c @@ -0,0 +1,156 @@ +/* + * Copyright 2007-2008 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + * + * Set up the interrupt priorities + */ + +#include <linux/module.h> +#include <linux/irq.h> +#include <asm/blackfin.h> + +u8 sec_int_priority[] = { + 255, /* IRQ_SEC_ERR */ + 255, /* IRQ_CGU_EVT */ + 254, /* IRQ_WATCH0 */ + 254, /* IRQ_WATCH1 */ + 253, /* IRQ_L2CTL0_ECC_ERR */ + 253, /* IRQ_L2CTL0_ECC_WARN */ + 253, /* IRQ_C0_DBL_FAULT */ + 253, /* IRQ_C1_DBL_FAULT */ + 252, /* IRQ_C0_HW_ERR */ + 252, /* IRQ_C1_HW_ERR */ + 255, /* IRQ_C0_NMI_L1_PARITY_ERR */ + 255, /* IRQ_C1_NMI_L1_PARITY_ERR */ + + 50, /* IRQ_TIMER0 */ + 50, /* IRQ_TIMER1 */ + 50, /* IRQ_TIMER2 */ + 50, /* IRQ_TIMER3 */ + 50, /* IRQ_TIMER4 */ + 50, /* IRQ_TIMER5 */ + 50, /* IRQ_TIMER6 */ + 50, /* IRQ_TIMER7 */ + 50, /* IRQ_TIMER_STAT */ + 0, /* IRQ_PINT0 */ + 0, /* IRQ_PINT1 */ + 0, /* IRQ_PINT2 */ + 0, /* IRQ_PINT3 */ + 0, /* IRQ_PINT4 */ + 0, /* IRQ_PINT5 */ + 0, /* IRQ_CNT */ + 50, /* RQ_PWM0_TRIP */ + 50, /* IRQ_PWM0_SYNC */ + 50, /* IRQ_PWM1_TRIP */ + 50, /* IRQ_PWM1_SYNC */ + 0, /* IRQ_TWI0 */ + 0, /* IRQ_TWI1 */ + 10, /* IRQ_SOFT0 */ + 10, /* IRQ_SOFT1 */ + 10, /* IRQ_SOFT2 */ + 10, /* IRQ_SOFT3 */ + 0, /* IRQ_ACM_EVT_MISS */ + 0, /* IRQ_ACM_EVT_COMPLETE */ + 0, /* IRQ_CAN0_RX */ + 0, /* IRQ_CAN0_TX */ + 0, /* IRQ_CAN0_STAT */ + 100, /* IRQ_SPORT0_TX */ + 100, /* IRQ_SPORT0_TX_STAT */ + 100, /* IRQ_SPORT0_RX */ + 100, /* IRQ_SPORT0_RX_STAT */ + 100, /* IRQ_SPORT1_TX */ + 100, /* IRQ_SPORT1_TX_STAT */ + 100, /* IRQ_SPORT1_RX */ + 100, /* IRQ_SPORT1_RX_STAT */ + 100, /* IRQ_SPORT2_TX */ + 100, /* IRQ_SPORT2_TX_STAT */ + 100, /* IRQ_SPORT2_RX */ + 100, /* IRQ_SPORT2_RX_STAT */ + 0, /* IRQ_SPI0_TX */ + 0, /* IRQ_SPI0_RX */ + 0, /* IRQ_SPI0_STAT */ + 0, /* IRQ_SPI1_TX */ + 0, /* IRQ_SPI1_RX */ + 0, /* IRQ_SPI1_STAT */ + 0, /* IRQ_RSI */ + 0, /* IRQ_RSI_INT0 */ + 0, /* IRQ_RSI_INT1 */ + 0, /* DMA11 Data (SDU) */ + 0, /* DMA12 Data (Reserved) */ + 0, /* Reserved */ + 0, /* Reserved */ + 30, /* IRQ_EMAC0_STAT */ + 0, /* EMAC0 Power (Reserved) */ + 30, /* IRQ_EMAC1_STAT */ + 0, /* EMAC1 Power (Reserved) */ + 0, /* IRQ_LP0 */ + 0, /* IRQ_LP0_STAT */ + 0, /* IRQ_LP1 */ + 0, /* IRQ_LP1_STAT */ + 0, /* IRQ_LP2 */ + 0, /* IRQ_LP2_STAT */ + 0, /* IRQ_LP3 */ + 0, /* IRQ_LP3_STAT */ + 0, /* IRQ_UART0_TX */ + 0, /* IRQ_UART0_RX */ + 0, /* IRQ_UART0_STAT */ + 0, /* IRQ_UART1_TX */ + 0, /* IRQ_UART1_RX */ + 0, /* IRQ_UART1_STAT */ + 0, /* IRQ_MDMA0_SRC_CRC0 */ + 0, /* IRQ_MDMA0_DEST_CRC0 */ + 0, /* IRQ_CRC0_DCNTEXP */ + 0, /* IRQ_CRC0_ERR */ + 0, /* IRQ_MDMA1_SRC_CRC1 */ + 0, /* IRQ_MDMA1_DEST_CRC1 */ + 0, /* IRQ_CRC1_DCNTEXP */ + 0, /* IRQ_CRC1_ERR */ + 0, /* IRQ_MDMA2_SRC */ + 0, /* IRQ_MDMA2_DEST */ + 0, /* IRQ_MDMA3_SRC */ + 0, /* IRQ_MDMA3_DEST */ + 120, /* IRQ_EPPI0_CH0 */ + 120, /* IRQ_EPPI0_CH1 */ + 120, /* IRQ_EPPI0_STAT */ + 120, /* IRQ_EPPI2_CH0 */ + 120, /* IRQ_EPPI2_CH1 */ + 120, /* IRQ_EPPI2_STAT */ + 120, /* IRQ_EPPI1_CH0 */ + 120, /* IRQ_EPPI1_CH1 */ + 120, /* IRQ_EPPI1_STAT */ + 120, /* IRQ_PIXC_CH0 */ + 120, /* IRQ_PIXC_CH1 */ + 120, /* IRQ_PIXC_CH2 */ + 120, /* IRQ_PIXC_STAT */ + 120, /* IRQ_PVP_CPDOB */ + 120, /* IRQ_PVP_CPDOC */ + 120, /* IRQ_PVP_CPSTAT */ + 120, /* IRQ_PVP_CPCI */ + 120, /* IRQ_PVP_STAT0 */ + 120, /* IRQ_PVP_MPDO */ + 120, /* IRQ_PVP_MPDI */ + 120, /* IRQ_PVP_MPSTAT */ + 120, /* IRQ_PVP_MPCI */ + 120, /* IRQ_PVP_CPDOA */ + 120, /* IRQ_PVP_STAT1 */ + 0, /* IRQ_USB_STAT */ + 0, /* IRQ_USB_DMA */ + 0, /* IRQ_TRU_INT0 */ + 0, /* IRQ_TRU_INT1 */ + 0, /* IRQ_TRU_INT2 */ + 0, /* IRQ_TRU_INT3 */ + 0, /* IRQ_DMAC0_ERROR */ + 0, /* IRQ_CGU0_ERROR */ + 0, /* Reserved */ + 0, /* IRQ_DPM */ + 0, /* Reserved */ + 0, /* IRQ_SWU0 */ + 0, /* IRQ_SWU1 */ + 0, /* IRQ_SWU2 */ + 0, /* IRQ_SWU3 */ + 0, /* IRQ_SWU4 */ + 0, /* IRQ_SWU4 */ + 0, /* IRQ_SWU6 */ +}; + diff --git a/arch/blackfin/mach-bf609/pm.c b/arch/blackfin/mach-bf609/pm.c index b76966e..dacafc1 100644 --- a/arch/blackfin/mach-bf609/pm.c +++ b/arch/blackfin/mach-bf609/pm.c @@ -11,13 +11,14 @@ #include <linux/interrupt.h> #include <linux/gpio.h> #include <linux/irq.h> - #include <linux/delay.h> +#include <linux/syscore_ops.h> #include <asm/dpmc.h> #include <asm/pm.h> #include <mach/pm.h> #include <asm/blackfin.h> +#include <asm/mem_init.h> /***********************************************************/ /* */ @@ -132,60 +133,30 @@ void bfin_cpu_suspend(void) } __attribute__((l1_text)) -void bfin_deepsleep(unsigned long mask) +void bf609_ddr_sr(void) { - uint32_t dpm0_ctl; - - bfin_write32(DPM0_WAKE_EN, 0x10); - bfin_write32(DPM0_WAKE_POL, 0x10); - dpm0_ctl = 0x00000008; - bfin_write32(DPM0_CTL, dpm0_ctl); - SSYNC(); - __asm__ __volatile__( \ - ".align 8;" \ - "idle;" \ - : : \ - ); -#ifdef CONFIG_BFIN_PM_WAKEUP_TIME_BENCH - __asm__ __volatile__( - "R0 = 0;" - "CYCLES = R0;" - "CYCLES2 = R0;" - "R0 = SYSCFG;" - "BITSET(R0, 1);" - "SYSCFG = R0;" - : : : "R0" - ); -#endif - + dmc_enter_self_refresh(); } __attribute__((l1_text)) -void bf609_ddr_sr(void) +void bf609_ddr_sr_exit(void) { - uint32_t reg; - - reg = bfin_read_DMC0_CTL(); - reg |= 0x8; - bfin_write_DMC0_CTL(reg); + dmc_exit_self_refresh(); - while (!(bfin_read_DMC0_STAT() & 0x8)) + /* After wake up from deep sleep and exit DDR from self refress mode, + * should wait till CGU PLL is locked. + */ + while (bfin_read32(CGU0_STAT) & CLKSALGN) continue; } __attribute__((l1_text)) -void bf609_ddr_sr_exit(void) +void bf609_resume_ccbuf(void) { - uint32_t reg; - while (!(bfin_read_DMC0_STAT() & 0x1)) - continue; + bfin_write32(DPM0_CCBF_EN, 3); + bfin_write32(DPM0_CTL, 2); - reg = bfin_read_DMC0_CTL(); - reg &= ~0x8; - bfin_write_DMC0_CTL(reg); - - while ((bfin_read_DMC0_STAT() & 0x8)) - continue; + while ((bfin_read32(DPM0_STAT) & 0xf) != 1); } __attribute__((l1_text)) @@ -203,20 +174,25 @@ void bfin_hibernate_syscontrol(void) bfin_write32(DPM0_RESTORE5, bfin_read32(DPM0_RESTORE5) | 4); } -#ifndef CONFIG_BF60x -# define SIC_SYSIRQ(irq) (irq - (IRQ_CORETMR + 1)) -#else -# define SIC_SYSIRQ(irq) ((irq) - IVG15) -#endif -void bfin_hibernate(unsigned long mask) +#define IRQ_SID(irq) ((irq) - IVG15) +asmlinkage void enter_deepsleep(void); + +__attribute__((l1_text)) +void bfin_deepsleep(unsigned long mask, unsigned long pol_mask) { - bfin_write32(DPM0_WAKE_EN, 0x10); - bfin_write32(DPM0_WAKE_POL, 0x10); + bfin_write32(DPM0_WAKE_EN, mask); + bfin_write32(DPM0_WAKE_POL, pol_mask); + SSYNC(); + enter_deepsleep(); +} + +void bfin_hibernate(unsigned long mask, unsigned long pol_mask) +{ + bfin_write32(DPM0_WAKE_EN, mask); + bfin_write32(DPM0_WAKE_POL, pol_mask); bfin_write32(DPM0_PGCNTR, 0x0000FFFF); bfin_write32(DPM0_HIB_DIS, 0xFFFF); - printk(KERN_DEBUG "hibernate: restore %x pgcnt %x\n", bfin_read32(DPM0_RESTORE0), bfin_read32(DPM0_PGCNTR)); - bf609_hibernate(); } @@ -290,10 +266,11 @@ void bf609_cpu_pm_enter(suspend_state_t state) printk(KERN_DEBUG "Unable to get irq wake\n"); if (state == PM_SUSPEND_STANDBY) - bfin_deepsleep(wakeup); + bfin_deepsleep(wakeup, wakeup_pol); else { - bfin_hibernate(wakeup); + bfin_hibernate(wakeup, wakeup_pol); } + } int bf609_cpu_pm_prepare(void) @@ -312,20 +289,36 @@ static struct bfin_cpu_pm_fns bf609_cpu_pm = { .finish = bf609_cpu_pm_finish, }; +#if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE) +static int smc_pm_syscore_suspend(void) +{ + bf609_nor_flash_exit(); + return 0; +} + +static void smc_pm_syscore_resume(void) +{ + bf609_nor_flash_init(); +} + +static struct syscore_ops smc_pm_syscore_ops = { + .suspend = smc_pm_syscore_suspend, + .resume = smc_pm_syscore_resume, +}; +#endif + static irqreturn_t test_isr(int irq, void *dev_id) { printk(KERN_DEBUG "gpio irq %d\n", irq); + if (irq == 231) + bfin_sec_raise_irq(IRQ_SID(IRQ_SOFT1)); return IRQ_HANDLED; } static irqreturn_t dpm0_isr(int irq, void *dev_id) { - uint32_t wake_stat; - - wake_stat = bfin_read32(DPM0_WAKE_STAT); - printk(KERN_DEBUG "enter %s wake stat %08x\n", __func__, wake_stat); - - bfin_write32(DPM0_WAKE_STAT, wake_stat); + bfin_write32(DPM0_WAKE_STAT, bfin_read32(DPM0_WAKE_STAT)); + bfin_write32(CGU0_STAT, bfin_read32(CGU0_STAT)); return IRQ_HANDLED; } @@ -334,7 +327,11 @@ static int __init bf609_init_pm(void) int irq; int error; -#if CONFIG_PM_BFIN_WAKE_PE12 +#if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE) + register_syscore_ops(&smc_pm_syscore_ops); +#endif + +#ifdef CONFIG_PM_BFIN_WAKE_PE12 irq = gpio_to_irq(GPIO_PE12); if (irq < 0) { error = irq; @@ -342,16 +339,19 @@ static int __init bf609_init_pm(void) GPIO_PE12, error); } - error = request_irq(irq, test_isr, IRQF_TRIGGER_RISING | IRQF_NO_SUSPEND, "gpiope12", NULL); + error = request_irq(irq, test_isr, IRQF_TRIGGER_RISING | IRQF_NO_SUSPEND + | IRQF_FORCE_RESUME, "gpiope12", NULL); if(error < 0) printk(KERN_DEBUG "Unable to get irq\n"); #endif - error = request_irq(IRQ_CGU_EVT, dpm0_isr, IRQF_NO_SUSPEND, "cgu0 event", NULL); + error = request_irq(IRQ_CGU_EVT, dpm0_isr, IRQF_NO_SUSPEND | + IRQF_FORCE_RESUME, "cgu0 event", NULL); if(error < 0) printk(KERN_DEBUG "Unable to get irq\n"); - error = request_irq(IRQ_DPM, dpm0_isr, IRQF_NO_SUSPEND, "dpm0 event", NULL); + error = request_irq(IRQ_DPM, dpm0_isr, IRQF_NO_SUSPEND | + IRQF_FORCE_RESUME, "dpm0 event", NULL); if (error < 0) printk(KERN_DEBUG "Unable to get irq\n"); diff --git a/arch/blackfin/mach-common/clocks-init.c b/arch/blackfin/mach-common/clocks-init.c index 7ad2407..2308ce5 100644 --- a/arch/blackfin/mach-common/clocks-init.c +++ b/arch/blackfin/mach-common/clocks-init.c @@ -16,23 +16,14 @@ #include <asm/dpmc.h> #ifdef CONFIG_BF60x -#define CSEL_P 0 -#define S0SEL_P 5 -#define SYSSEL_P 8 -#define S1SEL_P 13 -#define DSEL_P 16 -#define OSEL_P 22 -#define ALGN_P 29 -#define UPDT_P 30 -#define LOCK_P 31 #define CGU_CTL_VAL ((CONFIG_VCO_MULT << 8) | CLKIN_HALF) #define CGU_DIV_VAL \ - ((CONFIG_CCLK_DIV << CSEL_P) | \ - (CONFIG_SCLK_DIV << SYSSEL_P) | \ - (CONFIG_SCLK0_DIV << S0SEL_P) | \ - (CONFIG_SCLK1_DIV << S1SEL_P) | \ - (CONFIG_DCLK_DIV << DSEL_P)) + ((CONFIG_CCLK_DIV << CSEL_OFFSET) | \ + (CONFIG_SCLK_DIV << SYSSEL_OFFSET) | \ + (CONFIG_SCLK0_DIV << S0SEL_OFFSET) | \ + (CONFIG_SCLK1_DIV << S1SEL_OFFSET) | \ + (CONFIG_DCLK_DIV << DSEL_OFFSET)) #define CONFIG_BFIN_DCLK (((CONFIG_CLKIN_HZ * CONFIG_VCO_MULT) / CONFIG_DCLK_DIV) / 1000000) #if ((CONFIG_BFIN_DCLK != 125) && \ @@ -41,89 +32,7 @@ (CONFIG_BFIN_DCLK != 225) && (CONFIG_BFIN_DCLK != 250)) #error "DCLK must be in (125, 133, 150, 166, 200, 225, 250)MHz" #endif -struct ddr_config { - u32 ddr_clk; - u32 dmc_ddrctl; - u32 dmc_ddrcfg; - u32 dmc_ddrtr0; - u32 dmc_ddrtr1; - u32 dmc_ddrtr2; - u32 dmc_ddrmr; - u32 dmc_ddrmr1; -}; -struct ddr_config ddr_config_table[] __attribute__((section(".data_l1"))) = { - [0] = { - .ddr_clk = 125, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20705212, - .dmc_ddrtr1 = 0x201003CF, - .dmc_ddrtr2 = 0x00320107, - .dmc_ddrmr = 0x00000422, - .dmc_ddrmr1 = 0x4, - }, - [1] = { - .ddr_clk = 133, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20806313, - .dmc_ddrtr1 = 0x2013040D, - .dmc_ddrtr2 = 0x00320108, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [2] = { - .ddr_clk = 150, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20A07323, - .dmc_ddrtr1 = 0x20160492, - .dmc_ddrtr2 = 0x00320209, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [3] = { - .ddr_clk = 166, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20A07323, - .dmc_ddrtr1 = 0x2016050E, - .dmc_ddrtr2 = 0x00320209, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [4] = { - .ddr_clk = 200, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20a07323, - .dmc_ddrtr1 = 0x2016050f, - .dmc_ddrtr2 = 0x00320509, - .dmc_ddrmr = 0x00000632, - .dmc_ddrmr1 = 0x4, - }, - [5] = { - .ddr_clk = 225, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20E0A424, - .dmc_ddrtr1 = 0x302006DB, - .dmc_ddrtr2 = 0x0032020D, - .dmc_ddrmr = 0x00000842, - .dmc_ddrmr1 = 0x4, - }, - [6] = { - .ddr_clk = 250, - .dmc_ddrctl = 0x00000904, - .dmc_ddrcfg = 0x00000422, - .dmc_ddrtr0 = 0x20E0A424, - .dmc_ddrtr1 = 0x3020079E, - .dmc_ddrtr2 = 0x0032020D, - .dmc_ddrmr = 0x00000842, - .dmc_ddrmr1 = 0x4, - }, -}; #else #define SDGCTL_WIDTH (1 << 31) /* SDRAM external data path width */ #define PLL_CTL_VAL \ @@ -144,43 +53,9 @@ void init_clocks(void) * in the middle of reprogramming things, and that'll screw us up. * For example, any automatic DMAs left by U-Boot for splash screens. */ - #ifdef CONFIG_BF60x - int i, dlldatacycle, dll_ctl; - bfin_write32(CGU0_DIV, CGU_DIV_VAL); - bfin_write32(CGU0_CTL, CGU_CTL_VAL); - while ((bfin_read32(CGU0_STAT) & 0x8) || !(bfin_read32(CGU0_STAT) & 0x4)) - continue; - - bfin_write32(CGU0_DIV, CGU_DIV_VAL | (1 << UPDT_P)); - while (bfin_read32(CGU0_STAT) & (1 << 3)) - continue; - - for (i = 0; i < 7; i++) { - if (ddr_config_table[i].ddr_clk == CONFIG_BFIN_DCLK) { - bfin_write_DDR0_CFG(ddr_config_table[i].dmc_ddrcfg); - bfin_write_DDR0_TR0(ddr_config_table[i].dmc_ddrtr0); - bfin_write_DDR0_TR1(ddr_config_table[i].dmc_ddrtr1); - bfin_write_DDR0_TR2(ddr_config_table[i].dmc_ddrtr2); - bfin_write_DDR0_MR(ddr_config_table[i].dmc_ddrmr); - bfin_write_DDR0_EMR1(ddr_config_table[i].dmc_ddrmr1); - bfin_write_DDR0_CTL(ddr_config_table[i].dmc_ddrctl); - break; - } - } - - do_sync(); - while (!(bfin_read_DDR0_STAT() & 0x4)) - continue; - - dlldatacycle = (bfin_read_DDR0_STAT() & 0x00f00000) >> 20; - dll_ctl = bfin_read_DDR0_DLLCTL(); - dll_ctl &= 0x0ff; - bfin_write_DDR0_DLLCTL(dll_ctl | (dlldatacycle << 8)); - - do_sync(); - while (!(bfin_read_DDR0_STAT() & 0x2000)) - continue; + init_cgu(CGU_DIV_VAL, CGU_CTL_VAL); + init_dmc(CONFIG_BFIN_DCLK); #else size_t i; for (i = 0; i < MAX_DMA_CHANNELS; ++i) { diff --git a/arch/blackfin/mach-common/cpufreq.c b/arch/blackfin/mach-common/cpufreq.c index 6e87dc1..c854a27 100644 --- a/arch/blackfin/mach-common/cpufreq.c +++ b/arch/blackfin/mach-common/cpufreq.c @@ -64,7 +64,8 @@ static void __init bfin_init_tables(unsigned long cclk, unsigned long sclk) /* Anomaly 273 seems to still exist on non-BF54x w/dcache turned on */ #if ANOMALY_05000273 || ANOMALY_05000274 || \ - (!defined(CONFIG_BF54x) && defined(CONFIG_BFIN_EXTMEM_DCACHEABLE)) + (!(defined(CONFIG_BF54x) || defined(CONFIG_BF60x)) \ + && defined(CONFIG_BFIN_EXTMEM_DCACHEABLE)) min_cclk = sclk * 2; #else min_cclk = sclk; @@ -173,7 +174,7 @@ static int bfin_target(struct cpufreq_policy *poli, #else ret = cpu_set_cclk(cpu, freqs.new * 1000); if (ret != 0) { - pr_debug("cpufreq set freq failed %d\n", ret); + WARN_ONCE(ret, "cpufreq set freq failed %d\n", ret); break; } #endif diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index 04c2fbe4..1c3d2c5 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -25,13 +25,6 @@ #include <asm/context.S> -#if defined(CONFIG_BFIN_SCRATCH_REG_RETN) -# define EX_SCRATCH_REG RETN -#elif defined(CONFIG_BFIN_SCRATCH_REG_RETE) -# define EX_SCRATCH_REG RETE -#else -# define EX_SCRATCH_REG CYCLES -#endif #ifdef CONFIG_EXCPT_IRQ_SYSC_L1 .section .l1.text diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c index 2729cba..7ca09ec 100644 --- a/arch/blackfin/mach-common/ints-priority.c +++ b/arch/blackfin/mach-common/ints-priority.c @@ -26,8 +26,9 @@ #include <asm/gpio.h> #include <asm/irq_handler.h> #include <asm/dpmc.h> +#include <asm/traps.h> -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL # define SIC_SYSIRQ(irq) (irq - (IRQ_CORETMR + 1)) #else # define SIC_SYSIRQ(irq) ((irq) - IVG15) @@ -56,7 +57,7 @@ unsigned long bfin_sic_iwr[3]; /* Up to 3 SIC_IWRx registers */ unsigned vr_wakeup; #endif -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL static struct ivgx { /* irq number for request_irq, available in mach-bf5xx/irq.h */ unsigned int irqno; @@ -143,7 +144,7 @@ static void bfin_core_unmask_irq(struct irq_data *d) void bfin_internal_mask_irq(unsigned int irq) { unsigned long flags = hard_local_irq_save(); -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL #ifdef SIC_IMASK0 unsigned mask_bank = SIC_SYSIRQ(irq) / 32; unsigned mask_bit = SIC_SYSIRQ(irq) % 32; @@ -175,7 +176,7 @@ void bfin_internal_unmask_irq(unsigned int irq) { unsigned long flags = hard_local_irq_save(); -#ifndef CONFIG_BF60x +#ifndef SEC_GCTL #ifdef SIC_IMASK0 unsigned mask_bank = SIC_SYSIRQ(irq) / 32; unsigned mask_bit = SIC_SYSIRQ(irq) % 32; @@ -199,7 +200,7 @@ void bfin_internal_unmask_irq(unsigned int irq) hard_local_irq_restore(flags); } -#ifdef CONFIG_BF60x +#ifdef SEC_GCTL static void bfin_sec_preflow_handler(struct irq_data *d) { unsigned long flags = hard_local_irq_save(); @@ -310,7 +311,24 @@ static void bfin_sec_disable(struct irq_data *d) hard_local_irq_restore(flags); } -static void bfin_sec_raise_irq(unsigned int sid) +static void bfin_sec_set_priority(unsigned int sec_int_levels, u8 *sec_int_priority) +{ + unsigned long flags = hard_local_irq_save(); + uint32_t reg_sctl; + int i; + + bfin_write_SEC_SCI(0, SEC_CPLVL, sec_int_levels); + + for (i = 0; i < SYS_IRQS - BFIN_IRQ(0); i++) { + reg_sctl = bfin_read_SEC_SCTL(i) & ~SEC_SCTL_PRIO; + reg_sctl |= sec_int_priority[i] << SEC_SCTL_PRIO_OFFSET; + bfin_write_SEC_SCTL(i, reg_sctl); + } + + hard_local_irq_restore(flags); +} + +void bfin_sec_raise_irq(unsigned int sid) { unsigned long flags = hard_local_irq_save(); @@ -396,24 +414,34 @@ void handle_sec_fault(unsigned int irq, struct irq_desc *desc) raw_spin_unlock(&desc->lock); } -static int sec_suspend(void) +void handle_core_fault(unsigned int irq, struct irq_desc *desc) { - return 0; -} + struct pt_regs *fp = get_irq_regs(); -static void sec_resume(void) -{ - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); - udelay(100); - bfin_write_SEC_GCTL(SEC_GCTL_EN); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); -} + raw_spin_lock(&desc->lock); -static struct syscore_ops sec_pm_syscore_ops = { - .suspend = sec_suspend, - .resume = sec_resume, -}; + switch (irq) { + case IRQ_C0_DBL_FAULT: + double_fault_c(fp); + break; + case IRQ_C0_HW_ERR: + dump_bfin_process(fp); + dump_bfin_mem(fp); + show_regs(fp); + printk(KERN_NOTICE "Kernel Stack\n"); + show_stack(current, NULL); + print_modules(); + panic("Kernel core hardware error"); + break; + case IRQ_C0_NMI_L1_PARITY_ERR: + panic("NMI occurs unexpectedly"); + break; + default: + panic("Core 1 fault occurs unexpectedly"); + } + raw_spin_unlock(&desc->lock); +} #endif #ifdef CONFIG_SMP @@ -437,7 +465,7 @@ static void bfin_internal_unmask_irq_chip(struct irq_data *d) } #endif -#if defined(CONFIG_PM) && !defined(CONFIG_BF60x) +#if defined(CONFIG_PM) && !defined(SEC_GCTL) int bfin_internal_set_wake(unsigned int irq, unsigned int state) { u32 bank, bit, wakeup = 0; @@ -496,7 +524,10 @@ static int bfin_internal_set_wake_chip(struct irq_data *d, unsigned int state) return bfin_internal_set_wake(d->irq, state); } #else -# define bfin_internal_set_wake(irq, state) +inline int bfin_internal_set_wake(unsigned int irq, unsigned int state) +{ + return 0; +} # define bfin_internal_set_wake_chip NULL #endif @@ -518,7 +549,7 @@ static struct irq_chip bfin_internal_irqchip = { .irq_set_wake = bfin_internal_set_wake_chip, }; -#ifdef CONFIG_BF60x +#ifdef SEC_GCTL static struct irq_chip bfin_sec_irqchip = { .name = "SEC", .irq_mask_ack = bfin_sec_mask_ack_irq, @@ -868,14 +899,6 @@ void bfin_demux_gpio_irq(unsigned int inta_irq, #else -# ifndef CONFIG_BF60x -#define NR_PINT_SYS_IRQS 4 -#define NR_PINTS 160 -# else -#define NR_PINT_SYS_IRQS 6 -#define NR_PINTS 112 -#endif - #define NR_PINT_BITS 32 #define IRQ_NOT_AVAIL 0xFF @@ -897,29 +920,21 @@ static struct bfin_pint_regs * const pint[NR_PINT_SYS_IRQS] = { #endif }; -#ifndef CONFIG_BF60x inline unsigned int get_irq_base(u32 bank, u8 bmap) { unsigned int irq_base; +#ifndef CONFIG_BF60x if (bank < 2) { /*PA-PB */ irq_base = IRQ_PA0 + bmap * 16; } else { /*PC-PJ */ irq_base = IRQ_PC0 + bmap * 16; } - - return irq_base; -} #else -inline unsigned int get_irq_base(u32 bank, u8 bmap) -{ - unsigned int irq_base; - irq_base = IRQ_PA0 + bank * 16 + bmap * 16; - +#endif return irq_base; } -#endif /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ void init_pint_lut(void) @@ -1089,6 +1104,9 @@ static int bfin_gpio_irq_type(struct irq_data *d, unsigned int type) } #ifdef CONFIG_PM +static struct bfin_pm_pint_save save_pint_reg[NR_PINT_SYS_IRQS]; +static u32 save_pint_sec_ctl[NR_PINT_SYS_IRQS]; + static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state) { u32 pint_irq; @@ -1124,6 +1142,59 @@ static int bfin_gpio_set_wake(struct irq_data *d, unsigned int state) return 0; } + +void bfin_pint_suspend(void) +{ + u32 bank; + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { + save_pint_reg[bank].mask_set = pint[bank]->mask_set; + save_pint_reg[bank].assign = pint[bank]->assign; + save_pint_reg[bank].edge_set = pint[bank]->edge_set; + save_pint_reg[bank].invert_set = pint[bank]->invert_set; + } +} + +void bfin_pint_resume(void) +{ + u32 bank; + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) { + pint[bank]->mask_set = save_pint_reg[bank].mask_set; + pint[bank]->assign = save_pint_reg[bank].assign; + pint[bank]->edge_set = save_pint_reg[bank].edge_set; + pint[bank]->invert_set = save_pint_reg[bank].invert_set; + } +} + +#ifdef SEC_GCTL +static int sec_suspend(void) +{ + u32 bank; + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) + save_pint_sec_ctl[bank] = bfin_read_SEC_SCTL(bank + SIC_SYSIRQ(IRQ_PINT0)); + return 0; +} + +static void sec_resume(void) +{ + u32 bank; + + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); + udelay(100); + bfin_write_SEC_GCTL(SEC_GCTL_EN); + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); + + for (bank = 0; bank < NR_PINT_SYS_IRQS; bank++) + bfin_write_SEC_SCTL(bank + SIC_SYSIRQ(IRQ_PINT0), save_pint_sec_ctl[bank]); +} + +static struct syscore_ops sec_pm_syscore_ops = { + .suspend = sec_suspend, + .resume = sec_resume, +}; +#endif #else # define bfin_gpio_set_wake NULL #endif @@ -1230,6 +1301,7 @@ void __cpuinit init_exception_vectors(void) CSYNC(); } +#ifndef SEC_GCTL /* * This function should be called during kernel startup to initialize * the BFin IRQ handling routines. @@ -1240,7 +1312,6 @@ int __init init_arch_irq(void) int irq; unsigned long ilat = 0; -#ifndef CONFIG_BF60x /* Disable all the peripheral intrs - page 4-29 HW Ref manual */ #ifdef SIC_IMASK0 bfin_write_SIC_IMASK0(SIC_UNMASK_ALL); @@ -1255,9 +1326,6 @@ int __init init_arch_irq(void) #else bfin_write_SIC_IMASK(SIC_UNMASK_ALL); #endif -#else /* CONFIG_BF60x */ - bfin_write_SEC_GCTL(SEC_GCTL_RESET); -#endif local_irq_disable(); @@ -1267,10 +1335,6 @@ int __init init_arch_irq(void) pint[1]->assign = CONFIG_PINT1_ASSIGN; pint[2]->assign = CONFIG_PINT2_ASSIGN; pint[3]->assign = CONFIG_PINT3_ASSIGN; -# ifdef CONFIG_BF60x - pint[4]->assign = CONFIG_PINT4_ASSIGN; - pint[5]->assign = CONFIG_PINT5_ASSIGN; -# endif # endif /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ init_pint_lut(); @@ -1283,7 +1347,6 @@ int __init init_arch_irq(void) irq_set_chip(irq, &bfin_internal_irqchip); switch (irq) { -#ifndef CONFIG_BF60x #if BFIN_GPIO_PINT case IRQ_PINT0: case IRQ_PINT1: @@ -1319,7 +1382,6 @@ int __init init_arch_irq(void) irq_set_handler(irq, handle_percpu_irq); break; #endif -#endif #ifdef CONFIG_TICKSOURCE_CORETMR case IRQ_CORETMR: @@ -1349,8 +1411,7 @@ int __init init_arch_irq(void) init_mach_irq(); -#ifndef CONFIG_BF60x -#if (defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)) && !defined(CONFIG_BF60x) +#if (defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE)) for (irq = IRQ_MAC_PHYINT; irq <= IRQ_MAC_STMDONE; irq++) irq_set_chip_and_handler(irq, &bfin_mac_status_irqchip, handle_level_irq); @@ -1360,28 +1421,6 @@ int __init init_arch_irq(void) irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, handle_level_irq); -#else - for (irq = BFIN_IRQ(0); irq <= SYS_IRQS; irq++) { - if (irq < CORE_IRQS) { - irq_set_chip(irq, &bfin_sec_irqchip); - __irq_set_handler(irq, handle_sec_fault, 0, NULL); - } else if (irq >= BFIN_IRQ(21) && irq <= BFIN_IRQ(26)) { - irq_set_chip(irq, &bfin_sec_irqchip); - irq_set_chained_handler(irq, bfin_demux_gpio_irq); - } else if (irq >= BFIN_IRQ(34) && irq <= BFIN_IRQ(37)) { - irq_set_chip(irq, &bfin_sec_irqchip); - irq_set_handler(irq, handle_percpu_irq); - } else { - irq_set_chip_and_handler(irq, &bfin_sec_irqchip, - handle_fasteoi_irq); - __irq_set_preflow_handler(irq, bfin_sec_preflow_handler); - } - } - for (irq = GPIO_IRQ_BASE; - irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) - irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, - handle_level_irq); -#endif bfin_write_IMASK(0); CSYNC(); ilat = bfin_read_ILAT(); @@ -1393,7 +1432,6 @@ int __init init_arch_irq(void) /* IMASK=xxx is equivalent to STI xx or bfin_irq_flags=xx, * local_irq_enable() */ -#ifndef CONFIG_BF60x program_IAR(); /* Therefore it's better to setup IARs before interrupts enabled */ search_IAR(); @@ -1427,23 +1465,6 @@ int __init init_arch_irq(void) #else bfin_write_SIC_IWR(IWR_DISABLE_ALL); #endif -#else /* CONFIG_BF60x */ - /* Enable interrupts IVG7-15 */ - bfin_irq_flags |= IMASK_IVG15 | - IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 | - IMASK_IVG10 | IMASK_IVG9 | IMASK_IVG8 | IMASK_IVG7 | IMASK_IVGHW; - - - bfin_write_SEC_FCTL(SEC_FCTL_EN | SEC_FCTL_SYSRST_EN | SEC_FCTL_FLTIN_EN); - bfin_sec_enable_sci(SIC_SYSIRQ(IRQ_WATCH0)); - bfin_sec_enable_ssi(SIC_SYSIRQ(IRQ_WATCH0)); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); - udelay(100); - bfin_write_SEC_GCTL(SEC_GCTL_EN); - bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); - init_software_driven_irq(); - register_syscore_ops(&sec_pm_syscore_ops); -#endif return 0; } @@ -1452,14 +1473,11 @@ __attribute__((l1_text)) #endif static int vec_to_irq(int vec) { -#ifndef CONFIG_BF60x struct ivgx *ivg = ivg7_13[vec - IVG7].ifirst; struct ivgx *ivg_stop = ivg7_13[vec - IVG7].istop; unsigned long sic_status[3]; -#endif if (likely(vec == EVT_IVTMR_P)) return IRQ_CORETMR; -#ifndef CONFIG_BF60x #ifdef SIC_ISR sic_status[0] = bfin_read_SIC_IMASK() & bfin_read_SIC_ISR(); #else @@ -1488,11 +1506,119 @@ static int vec_to_irq(int vec) #endif return ivg->irqno; } -#else - /* for bf60x read */ +} + +#else /* SEC_GCTL */ + +/* + * This function should be called during kernel startup to initialize + * the BFin IRQ handling routines. + */ + +int __init init_arch_irq(void) +{ + int irq; + unsigned long ilat = 0; + + bfin_write_SEC_GCTL(SEC_GCTL_RESET); + + local_irq_disable(); + +#if BFIN_GPIO_PINT +# ifdef CONFIG_PINTx_REASSIGN + pint[0]->assign = CONFIG_PINT0_ASSIGN; + pint[1]->assign = CONFIG_PINT1_ASSIGN; + pint[2]->assign = CONFIG_PINT2_ASSIGN; + pint[3]->assign = CONFIG_PINT3_ASSIGN; + pint[4]->assign = CONFIG_PINT4_ASSIGN; + pint[5]->assign = CONFIG_PINT5_ASSIGN; +# endif + /* Whenever PINTx_ASSIGN is altered init_pint_lut() must be executed! */ + init_pint_lut(); +#endif + + for (irq = 0; irq <= SYS_IRQS; irq++) { + if (irq <= IRQ_CORETMR) { + irq_set_chip(irq, &bfin_core_irqchip); +#ifdef CONFIG_TICKSOURCE_CORETMR + if (irq == IRQ_CORETMR) +# ifdef CONFIG_SMP + irq_set_handler(irq, handle_percpu_irq); +# else + irq_set_handler(irq, handle_simple_irq); +# endif +#endif + } else if (irq < BFIN_IRQ(0)) { + irq_set_chip_and_handler(irq, &bfin_internal_irqchip, + handle_simple_irq); + } else if (irq == IRQ_SEC_ERR) { + irq_set_chip_and_handler(irq, &bfin_sec_irqchip, + handle_sec_fault); + } else if (irq < CORE_IRQS && irq >= IRQ_C0_DBL_FAULT) { + irq_set_chip_and_handler(irq, &bfin_sec_irqchip, + handle_core_fault); + } else if (irq >= BFIN_IRQ(21) && irq <= BFIN_IRQ(26)) { + irq_set_chip(irq, &bfin_sec_irqchip); + irq_set_chained_handler(irq, bfin_demux_gpio_irq); + } else if (irq >= BFIN_IRQ(34) && irq <= BFIN_IRQ(37)) { + irq_set_chip(irq, &bfin_sec_irqchip); + irq_set_handler(irq, handle_percpu_irq); + } else { + irq_set_chip_and_handler(irq, &bfin_sec_irqchip, + handle_fasteoi_irq); + __irq_set_preflow_handler(irq, bfin_sec_preflow_handler); + } + } + for (irq = GPIO_IRQ_BASE; + irq < (GPIO_IRQ_BASE + MAX_BLACKFIN_GPIOS); irq++) + irq_set_chip_and_handler(irq, &bfin_gpio_irqchip, + handle_level_irq); + + bfin_write_IMASK(0); + CSYNC(); + ilat = bfin_read_ILAT(); + CSYNC(); + bfin_write_ILAT(ilat); + CSYNC(); + + printk(KERN_INFO "Configuring Blackfin Priority Driven Interrupts\n"); + + bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority); + + bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority); + + /* Enable interrupts IVG7-15 */ + bfin_irq_flags |= IMASK_IVG15 | + IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 | + IMASK_IVG10 | IMASK_IVG9 | IMASK_IVG8 | IMASK_IVG7 | IMASK_IVGHW; + + + bfin_write_SEC_FCTL(SEC_FCTL_EN | SEC_FCTL_SYSRST_EN | SEC_FCTL_FLTIN_EN); + bfin_sec_enable_sci(SIC_SYSIRQ(IRQ_WATCH0)); + bfin_sec_enable_ssi(SIC_SYSIRQ(IRQ_WATCH0)); + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_RESET); + udelay(100); + bfin_write_SEC_GCTL(SEC_GCTL_EN); + bfin_write_SEC_SCI(0, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); + bfin_write_SEC_SCI(1, SEC_CCTL, SEC_CCTL_EN | SEC_CCTL_NMI_EN); + + init_software_driven_irq(); + register_syscore_ops(&sec_pm_syscore_ops); + + return 0; +} + +#ifdef CONFIG_DO_IRQ_L1 +__attribute__((l1_text)) +#endif +static int vec_to_irq(int vec) +{ + if (likely(vec == EVT_IVTMR_P)) + return IRQ_CORETMR; + return BFIN_IRQ(bfin_read_SEC_SCI(0, SEC_CSID)); -#endif /* end of CONFIG_BF60x */ } +#endif /* SEC_GCTL */ #ifdef CONFIG_DO_IRQ_L1 __attribute__((l1_text)) @@ -1514,6 +1640,10 @@ int __ipipe_get_irq_priority(unsigned irq) if (irq <= IRQ_CORETMR) return irq; +#ifdef SEC_GCTL + if (irq >= BFIN_IRQ(0)) + return IVG11; +#else for (ient = 0; ient < NR_PERI_INTS; ient++) { struct ivgx *ivg = ivg_table + ient; if (ivg->irqno == irq) { @@ -1524,6 +1654,7 @@ int __ipipe_get_irq_priority(unsigned irq) } } } +#endif return IVG15; } @@ -1536,8 +1667,6 @@ asmlinkage int __ipipe_grab_irq(int vec, struct pt_regs *regs) { struct ipipe_percpu_domain_data *p = ipipe_root_cpudom_ptr(); struct ipipe_domain *this_domain = __ipipe_current_domain; - struct ivgx *ivg_stop = ivg7_13[vec-IVG7].istop; - struct ivgx *ivg = ivg7_13[vec-IVG7].ifirst; int irq, s = 0; irq = vec_to_irq(vec); diff --git a/arch/blackfin/mach-common/pm.c b/arch/blackfin/mach-common/pm.c index ca6655e..87bfe54 100644 --- a/arch/blackfin/mach-common/pm.c +++ b/arch/blackfin/mach-common/pm.c @@ -172,6 +172,10 @@ int bfin_pm_suspend_mem_enter(void) bfin_gpio_pm_hibernate_suspend(); +#if BFIN_GPIO_PINT + bfin_pint_suspend(); +#endif + #if defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK) flushinv_all_dcache(); #endif @@ -190,6 +194,10 @@ int bfin_pm_suspend_mem_enter(void) _enable_icplb(); _enable_dcplb(); +#if BFIN_GPIO_PINT + bfin_pint_resume(); +#endif + bfin_gpio_pm_hibernate_restore(); blackfin_dma_resume(); diff --git a/arch/c6x/boot/dts/evmc6678.dts b/arch/c6x/boot/dts/evmc6678.dts new file mode 100644 index 0000000..ab68630 --- /dev/null +++ b/arch/c6x/boot/dts/evmc6678.dts @@ -0,0 +1,83 @@ +/* + * arch/c6x/boot/dts/evmc6678.dts + * + * EVMC6678 Evaluation Platform For TMS320C6678 + * + * Copyright (C) 2012 Texas Instruments Incorporated + * + * Author: Ken Cox <jkc@redhat.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. + * + */ + +/dts-v1/; + +/include/ "tms320c6678.dtsi" + +/ { + model = "Advantech EVMC6678"; + compatible = "advantech,evmc6678"; + + chosen { + bootargs = "root=/dev/nfs ip=dhcp rw"; + }; + + memory { + device_type = "memory"; + reg = <0x80000000 0x20000000>; + }; + + soc { + megamod_pic: interrupt-controller@1800000 { + interrupts = < 12 13 14 15 >; + }; + + timer8: timer@2280000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 66 >; + }; + + timer9: timer@2290000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 68 >; + }; + + timer10: timer@22A0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 70 >; + }; + + timer11: timer@22B0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 72 >; + }; + + timer12: timer@22C0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 74 >; + }; + + timer13: timer@22D0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 76 >; + }; + + timer14: timer@22E0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 78 >; + }; + + timer15: timer@22F0000 { + interrupt-parent = <&megamod_pic>; + interrupts = < 80 >; + }; + + clock-controller@2310000 { + clock-frequency = <100000000>; + }; + }; +}; diff --git a/arch/c6x/boot/dts/tms320c6678.dtsi b/arch/c6x/boot/dts/tms320c6678.dtsi new file mode 100644 index 0000000..386196e --- /dev/null +++ b/arch/c6x/boot/dts/tms320c6678.dtsi @@ -0,0 +1,146 @@ + +/ { + #address-cells = <1>; + #size-cells = <1>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + reg = <0>; + model = "ti,c66x"; + }; + cpu@1 { + device_type = "cpu"; + reg = <1>; + model = "ti,c66x"; + }; + cpu@2 { + device_type = "cpu"; + reg = <2>; + model = "ti,c66x"; + }; + cpu@3 { + device_type = "cpu"; + reg = <3>; + model = "ti,c66x"; + }; + cpu@4 { + device_type = "cpu"; + reg = <4>; + model = "ti,c66x"; + }; + cpu@5 { + device_type = "cpu"; + reg = <5>; + model = "ti,c66x"; + }; + cpu@6 { + device_type = "cpu"; + reg = <6>; + model = "ti,c66x"; + }; + cpu@7 { + device_type = "cpu"; + reg = <7>; + model = "ti,c66x"; + }; + }; + + soc { + compatible = "simple-bus"; + model = "tms320c6678"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + core_pic: interrupt-controller { + compatible = "ti,c64x+core-pic"; + interrupt-controller; + #interrupt-cells = <1>; + }; + + megamod_pic: interrupt-controller@1800000 { + compatible = "ti,c64x+megamod-pic"; + interrupt-controller; + #interrupt-cells = <1>; + reg = <0x1800000 0x1000>; + interrupt-parent = <&core_pic>; + }; + + cache-controller@1840000 { + compatible = "ti,c64x+cache"; + reg = <0x01840000 0x8400>; + }; + + timer8: timer@2280000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x01 >; + reg = <0x2280000 0x40>; + }; + + timer9: timer@2290000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x02 >; + reg = <0x2290000 0x40>; + }; + + timer10: timer@22A0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x04 >; + reg = <0x22A0000 0x40>; + }; + + timer11: timer@22B0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x08 >; + reg = <0x22B0000 0x40>; + }; + + timer12: timer@22C0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x10 >; + reg = <0x22C0000 0x40>; + }; + + timer13: timer@22D0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x20 >; + reg = <0x22D0000 0x40>; + }; + + timer14: timer@22E0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x40 >; + reg = <0x22E0000 0x40>; + }; + + timer15: timer@22F0000 { + compatible = "ti,c64x+timer64"; + ti,core-mask = < 0x80 >; + reg = <0x22F0000 0x40>; + }; + + clock-controller@2310000 { + compatible = "ti,c6678-pll", "ti,c64x+pll"; + reg = <0x02310000 0x200>; + ti,c64x+pll-bypass-delay = <200>; + ti,c64x+pll-reset-delay = <12000>; + ti,c64x+pll-lock-delay = <80000>; + }; + + device-state-controller@2620000 { + compatible = "ti,c64x+dscr"; + reg = <0x02620000 0x1000>; + + ti,dscr-devstat = <0x20>; + ti,dscr-silicon-rev = <0x18 28 0xf>; + + ti,dscr-mac-fuse-regs = <0x110 1 2 3 4 + 0x114 5 6 0 0>; + + }; + }; +}; diff --git a/arch/c6x/configs/evmc6678_defconfig b/arch/c6x/configs/evmc6678_defconfig new file mode 100644 index 0000000..5f126d4 --- /dev/null +++ b/arch/c6x/configs/evmc6678_defconfig @@ -0,0 +1,42 @@ +CONFIG_SOC_TMS320C6678=y +CONFIG_EXPERIMENTAL=y +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_SYSVIPC=y +CONFIG_SPARSE_IRQ=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_USER_NS is not set +# CONFIG_PID_NS is not set +CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_EXPERT=y +# CONFIG_FUTEX is not set +# CONFIG_SLUB_DEBUG is not set +CONFIG_MODULES=y +CONFIG_MODULE_FORCE_LOAD=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="" +# CONFIG_CMDLINE_FORCE is not set +CONFIG_BOARD_EVM6678=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=2 +CONFIG_BLK_DEV_RAM_SIZE=17000 +CONFIG_MISC_DEVICES=y +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_IOMMU_SUPPORT is not set +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_CRC16=y +# CONFIG_ENABLE_MUST_CHECK is not set +# CONFIG_SCHED_DEBUG is not set +# CONFIG_DEBUG_BUGVERBOSE is not set diff --git a/arch/c6x/include/asm/irq.h b/arch/c6x/include/asm/irq.h index ab4577f..1324e62 100644 --- a/arch/c6x/include/asm/irq.h +++ b/arch/c6x/include/asm/irq.h @@ -34,8 +34,6 @@ */ #define NR_PRIORITY_IRQS 16 -#define NR_IRQS_LEGACY NR_PRIORITY_IRQS - /* Total number of virq in the platform */ #define NR_IRQS 256 diff --git a/arch/c6x/kernel/irq.c b/arch/c6x/kernel/irq.c index c90fb5e..247e0eb 100644 --- a/arch/c6x/kernel/irq.c +++ b/arch/c6x/kernel/irq.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2011 Texas Instruments Incorporated + * Copyright (C) 2011-2012 Texas Instruments Incorporated * * This borrows heavily from powerpc version, which is: * @@ -35,9 +35,7 @@ static DEFINE_RAW_SPINLOCK(core_irq_lock); static void mask_core_irq(struct irq_data *data) { - unsigned int prio = data->irq; - - BUG_ON(prio < 4 || prio >= NR_PRIORITY_IRQS); + unsigned int prio = data->hwirq; raw_spin_lock(&core_irq_lock); and_creg(IER, ~(1 << prio)); @@ -46,7 +44,7 @@ static void mask_core_irq(struct irq_data *data) static void unmask_core_irq(struct irq_data *data) { - unsigned int prio = data->irq; + unsigned int prio = data->hwirq; raw_spin_lock(&core_irq_lock); or_creg(IER, 1 << prio); @@ -59,15 +57,15 @@ static struct irq_chip core_chip = { .irq_unmask = unmask_core_irq, }; +static int prio_to_virq[NR_PRIORITY_IRQS]; + asmlinkage void c6x_do_IRQ(unsigned int prio, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); irq_enter(); - BUG_ON(prio < 4 || prio >= NR_PRIORITY_IRQS); - - generic_handle_irq(prio); + generic_handle_irq(prio_to_virq[prio]); irq_exit(); @@ -82,6 +80,8 @@ static int core_domain_map(struct irq_domain *h, unsigned int virq, if (hw < 4 || hw >= NR_PRIORITY_IRQS) return -EINVAL; + prio_to_virq[hw] = virq; + irq_set_status_flags(virq, IRQ_LEVEL); irq_set_chip_and_handler(virq, &core_chip, handle_level_irq); return 0; @@ -102,9 +102,8 @@ void __init init_IRQ(void) np = of_find_compatible_node(NULL, NULL, "ti,c64x+core-pic"); if (np != NULL) { /* create the core host */ - core_domain = irq_domain_add_legacy(np, NR_PRIORITY_IRQS, - 0, 0, &core_domain_ops, - NULL); + core_domain = irq_domain_add_linear(np, NR_PRIORITY_IRQS, + &core_domain_ops, NULL); if (core_domain) irq_set_default_host(core_domain); of_node_put(np); diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index ce46186..f4e72bd 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -143,6 +143,10 @@ static void __init get_cpuinfo(void) p->cpu_name = "C64x+"; p->cpu_voltage = "1.2"; break; + case 21: + p->cpu_name = "C66X"; + p->cpu_voltage = "1.2"; + break; default: p->cpu_name = "unknown"; break; diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c index 3d8f3c2..3998b24 100644 --- a/arch/c6x/kernel/signal.c +++ b/arch/c6x/kernel/signal.c @@ -249,8 +249,6 @@ static void handle_signal(int sig, siginfo_t *info, struct k_sigaction *ka, struct pt_regs *regs, int syscall) { - int ret; - /* Are we from a system call? */ if (syscall) { /* If so, check system call restarting.. */ diff --git a/arch/c6x/kernel/soc.c b/arch/c6x/kernel/soc.c index 0748c94..3ac7408 100644 --- a/arch/c6x/kernel/soc.c +++ b/arch/c6x/kernel/soc.c @@ -80,7 +80,7 @@ int soc_mac_addr(unsigned int index, u8 *addr) if (have_fuse_mac) memcpy(addr, c6x_fuse_mac, 6); else - random_ether_addr(addr); + eth_random_addr(addr); } /* adjust for specific EMAC device */ diff --git a/arch/c6x/platforms/Kconfig b/arch/c6x/platforms/Kconfig index 401ee67..c4a0fad 100644 --- a/arch/c6x/platforms/Kconfig +++ b/arch/c6x/platforms/Kconfig @@ -14,3 +14,7 @@ config SOC_TMS320C6472 config SOC_TMS320C6474 bool "TMS320C6474" default n + +config SOC_TMS320C6678 + bool "TMS320C6678" + default n diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c index c1c4e2a..74e3371 100644 --- a/arch/c6x/platforms/megamod-pic.c +++ b/arch/c6x/platforms/megamod-pic.c @@ -243,27 +243,37 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) * as their interrupt parent. */ for (i = 0; i < NR_COMBINERS; i++) { + struct irq_data *irq_data; + irq_hw_number_t hwirq; irq = irq_of_parse_and_map(np, i); if (irq == NO_IRQ) continue; + irq_data = irq_get_irq_data(irq); + if (!irq_data) { + pr_err("%s: combiner-%d no irq_data for virq %d!\n", + np->full_name, i, irq); + continue; + } + + hwirq = irq_data->hwirq; + /* - * We count on the core priority interrupts (4 - 15) being - * direct mapped. Check that device tree provided something - * in that range. + * Check that device tree provided something in the range + * of the core priority interrupts (4 - 15). */ - if (irq < 4 || irq >= NR_PRIORITY_IRQS) { - pr_err("%s: combiner-%d virq %d out of range!\n", - np->full_name, i, irq); + if (hwirq < 4 || hwirq >= NR_PRIORITY_IRQS) { + pr_err("%s: combiner-%d core irq %ld out of range!\n", + np->full_name, i, hwirq); continue; } /* record the mapping */ - mapping[irq - 4] = i; + mapping[hwirq - 4] = i; - pr_debug("%s: combiner-%d cascading to virq %d\n", - np->full_name, i, irq); + pr_debug("%s: combiner-%d cascading to hwirq %ld\n", + np->full_name, i, hwirq); cascade_data[i].pic = pic; cascade_data[i].index = i; diff --git a/arch/c6x/platforms/plldata.c b/arch/c6x/platforms/plldata.c index 2cfd6f4..755359e 100644 --- a/arch/c6x/platforms/plldata.c +++ b/arch/c6x/platforms/plldata.c @@ -335,6 +335,68 @@ static void __init c6474_setup_clocks(struct device_node *node) } #endif /* CONFIG_SOC_TMS320C6474 */ +#ifdef CONFIG_SOC_TMS320C6678 +static struct clk_lookup c6678_clks[] = { + CLK(NULL, "pll1", &c6x_soc_pll1.sysclks[0]), + CLK(NULL, "pll1_refclk", &c6x_soc_pll1.sysclks[1]), + CLK(NULL, "pll1_sysclk2", &c6x_soc_pll1.sysclks[2]), + CLK(NULL, "pll1_sysclk3", &c6x_soc_pll1.sysclks[3]), + CLK(NULL, "pll1_sysclk4", &c6x_soc_pll1.sysclks[4]), + CLK(NULL, "pll1_sysclk5", &c6x_soc_pll1.sysclks[5]), + CLK(NULL, "pll1_sysclk6", &c6x_soc_pll1.sysclks[6]), + CLK(NULL, "pll1_sysclk7", &c6x_soc_pll1.sysclks[7]), + CLK(NULL, "pll1_sysclk8", &c6x_soc_pll1.sysclks[8]), + CLK(NULL, "pll1_sysclk9", &c6x_soc_pll1.sysclks[9]), + CLK(NULL, "pll1_sysclk10", &c6x_soc_pll1.sysclks[10]), + CLK(NULL, "pll1_sysclk11", &c6x_soc_pll1.sysclks[11]), + CLK(NULL, "core", &c6x_core_clk), + CLK("", NULL, NULL) +}; + +static void __init c6678_setup_clocks(struct device_node *node) +{ + struct pll_data *pll = &c6x_soc_pll1; + struct clk *sysclks = pll->sysclks; + + pll->flags = PLL_HAS_MUL; + + sysclks[1].flags |= FIXED_DIV_PLL; + sysclks[1].div = 1; + + sysclks[2].div = PLLDIV2; + + sysclks[3].flags |= FIXED_DIV_PLL; + sysclks[3].div = 2; + + sysclks[4].flags |= FIXED_DIV_PLL; + sysclks[4].div = 3; + + sysclks[5].div = PLLDIV5; + + sysclks[6].flags |= FIXED_DIV_PLL; + sysclks[6].div = 64; + + sysclks[7].flags |= FIXED_DIV_PLL; + sysclks[7].div = 6; + + sysclks[8].div = PLLDIV8; + + sysclks[9].flags |= FIXED_DIV_PLL; + sysclks[9].div = 12; + + sysclks[10].flags |= FIXED_DIV_PLL; + sysclks[10].div = 3; + + sysclks[11].flags |= FIXED_DIV_PLL; + sysclks[11].div = 6; + + c6x_core_clk.parent = &sysclks[0]; + c6x_i2c_clk.parent = &sysclks[7]; + + c6x_clks_init(c6678_clks); +} +#endif /* CONFIG_SOC_TMS320C6678 */ + static struct of_device_id c6x_clkc_match[] __initdata = { #ifdef CONFIG_SOC_TMS320C6455 { .compatible = "ti,c6455-pll", .data = c6455_setup_clocks }, @@ -348,6 +410,9 @@ static struct of_device_id c6x_clkc_match[] __initdata = { #ifdef CONFIG_SOC_TMS320C6474 { .compatible = "ti,c6474-pll", .data = c6474_setup_clocks }, #endif +#ifdef CONFIG_SOC_TMS320C6678 + { .compatible = "ti,c6678-pll", .data = c6678_setup_clocks }, +#endif { .compatible = "ti,c64x+pll" }, {} }; diff --git a/arch/cris/arch-v32/drivers/pci/bios.c b/arch/cris/arch-v32/drivers/pci/bios.c index bc0cfda..5b1ee82 100644 --- a/arch/cris/arch-v32/drivers/pci/bios.c +++ b/arch/cris/arch-v32/drivers/pci/bios.c @@ -6,11 +6,6 @@ void __devinit pcibios_fixup_bus(struct pci_bus *b) { } -char * __devinit pcibios_setup(char *str) -{ - return NULL; -} - void pcibios_set_master(struct pci_dev *dev) { u8 lat; diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c index 6b0b82f..d04ed14 100644 --- a/arch/frv/mb93090-mb00/pci-vdk.c +++ b/arch/frv/mb93090-mb00/pci-vdk.c @@ -268,7 +268,7 @@ static void __init pci_fixup_umc_ide(struct pci_dev *d) d->resource[i].flags |= PCI_BASE_ADDRESS_SPACE_IO; } -static void __init pci_fixup_ide_bases(struct pci_dev *d) +static void __devinit pci_fixup_ide_bases(struct pci_dev *d) { int i; @@ -287,7 +287,7 @@ static void __init pci_fixup_ide_bases(struct pci_dev *d) } } -static void __init pci_fixup_ide_trash(struct pci_dev *d) +static void __devinit pci_fixup_ide_trash(struct pci_dev *d) { int i; diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h index b6a809f..105c93b 100644 --- a/arch/ia64/include/asm/iommu.h +++ b/arch/ia64/include/asm/iommu.h @@ -11,12 +11,10 @@ extern void no_iommu_init(void); extern int force_iommu, no_iommu; extern int iommu_pass_through; extern int iommu_detected; -extern int iommu_group_mf; #else #define iommu_pass_through (0) #define no_iommu (1) #define iommu_detected (0) -#define iommu_group_mf (0) #endif extern void iommu_dma_init(void); extern void machvec_init(const char *name); diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index b9f82c8..ec6c6b3 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -26,6 +26,7 @@ /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_IOAPIC +#define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_DEVICE_ASSIGNMENT /* Architectural interrupt line count. */ diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 7f4a0ed..5b7791d 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -12,7 +12,7 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(strlen); -#include<asm/pgtable.h> +#include <asm/pgtable.h> EXPORT_SYMBOL_GPL(empty_zero_page); #include <asm/checksum.h> diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index 7cdc89b..1ddcfe5 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -32,7 +32,6 @@ int force_iommu __read_mostly; #endif int iommu_pass_through; -int iommu_group_mf; /* Dummy device used for NULL arguments (normally ISA). Better would be probably a smaller DMA mask, but this is bug-to-bug compatible diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig index 9806e55..df5351e 100644 --- a/arch/ia64/kvm/Kconfig +++ b/arch/ia64/kvm/Kconfig @@ -19,6 +19,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" + depends on BROKEN depends on HAVE_KVM && MODULES && EXPERIMENTAL # for device assignment: depends on PCI diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c index f0b9cac..176a12c 100644 --- a/arch/ia64/kvm/vmm.c +++ b/arch/ia64/kvm/vmm.c @@ -20,9 +20,9 @@ */ -#include<linux/kernel.h> -#include<linux/module.h> -#include<asm/fpswa.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/fpswa.h> #include "vcpu.h" diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 02d29c2..8443daf 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -72,6 +72,10 @@ mapped_kernel_page_is_present (unsigned long address) return pte_present(pte); } +# define VM_READ_BIT 0 +# define VM_WRITE_BIT 1 +# define VM_EXEC_BIT 2 + void __kprobes ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs) { @@ -81,6 +85,12 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re struct siginfo si; unsigned long mask; int fault; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + + mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) + | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); + + flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0); /* mmap_sem is performance critical.... */ prefetchw(&mm->mmap_sem); @@ -109,6 +119,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (notify_page_fault(regs, TRAP_BRKPT)) return; +retry: down_read(&mm->mmap_sem); vma = find_vma_prev(mm, address, &prev_vma); @@ -130,10 +141,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re /* OK, we've got a good vm_area for this memory area. Check the access permissions: */ -# define VM_READ_BIT 0 -# define VM_WRITE_BIT 1 -# define VM_EXEC_BIT 2 - # if (((1 << VM_READ_BIT) != VM_READ || (1 << VM_WRITE_BIT) != VM_WRITE) \ || (1 << VM_EXEC_BIT) != VM_EXEC) # error File is out of sync with <linux/mm.h>. Please update. @@ -142,9 +149,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (((isr >> IA64_ISR_R_BIT) & 1UL) && (!(vma->vm_flags & (VM_READ | VM_WRITE)))) goto bad_area; - mask = ( (((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) - | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); - if ((vma->vm_flags & mask) != mask) goto bad_area; @@ -153,7 +157,11 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(mm, vma, address, flags); + + if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) + return; + if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened @@ -168,10 +176,24 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re } BUG(); } - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; + + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) + current->maj_flt++; + else + current->min_flt++; + if (fault & VM_FAULT_RETRY) { + flags &= ~FAULT_FLAG_ALLOW_RETRY; + + /* No need to up_read(&mm->mmap_sem) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + + goto retry; + } + } + up_read(&mm->mmap_sem); return; diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 524df42..81acc7a 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -351,6 +351,8 @@ pci_acpi_scan_root(struct acpi_pci_root *root) #endif INIT_LIST_HEAD(&info.resources); + /* insert busn resource at first */ + pci_add_resource(&info.resources, &root->secondary); acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_window, &windows); if (windows) { @@ -384,7 +386,7 @@ pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; } - pbus->subordinate = pci_scan_child_bus(pbus); + pci_scan_child_bus(pbus); return pbus; out3: @@ -496,15 +498,6 @@ pcibios_align_resource (void *data, const struct resource *res, return res->start; } -/* - * PCI BIOS setup, always defaults to SAL interface - */ -char * __init -pcibios_setup (char *str) -{ - return str; -} - int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) diff --git a/arch/m68k/include/asm/mcfne.h b/arch/m68k/include/asm/mcf8390.h index bf638be..a72a208 100644 --- a/arch/m68k/include/asm/mcfne.h +++ b/arch/m68k/include/asm/mcf8390.h @@ -1,7 +1,7 @@ /****************************************************************************/ /* - * mcfne.h -- NE2000 in ColdFire eval boards. + * mcf8390.h -- NS8390 support for ColdFire eval boards. * * (C) Copyright 1999-2000, Greg Ungerer (gerg@snapgear.com) * (C) Copyright 2000, Lineo (www.lineo.com) @@ -14,8 +14,8 @@ */ /****************************************************************************/ -#ifndef mcfne_h -#define mcfne_h +#ifndef mcf8390_h +#define mcf8390_h /****************************************************************************/ @@ -37,6 +37,7 @@ #if defined(CONFIG_ARN5206) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0xf0 #define NE2000_IRQ_PRIORITY 2 #define NE2000_IRQ_LEVEL 4 @@ -46,6 +47,7 @@ #if defined(CONFIG_M5206eC3) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1c #define NE2000_IRQ_PRIORITY 2 #define NE2000_IRQ_LEVEL 4 @@ -54,6 +56,7 @@ #if defined(CONFIG_M5206e) && defined(CONFIG_NETtel) #define NE2000_ADDR 0x30000300 +#define NE2000_ADDRSIZE 0x00001000 #define NE2000_IRQ_VECTOR 25 #define NE2000_IRQ_PRIORITY 1 #define NE2000_IRQ_LEVEL 3 @@ -63,6 +66,7 @@ #if defined(CONFIG_M5307C3) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1b #define NE2000_BYTE volatile unsigned short #endif @@ -70,6 +74,7 @@ #if defined(CONFIG_M5272) && defined(CONFIG_NETtel) #define NE2000_ADDR 0x30600300 #define NE2000_ODDOFFSET 0x00008000 +#define NE2000_ADDRSIZE 0x00010000 #define NE2000_IRQ_VECTOR 67 #undef BSWAP #define BSWAP(w) (w) @@ -82,6 +87,7 @@ #define NE2000_ADDR0 0x30600300 #define NE2000_ADDR1 0x30800300 #define NE2000_ODDOFFSET 0x00008000 +#define NE2000_ADDRSIZE 0x00010000 #define NE2000_IRQ_VECTOR0 27 #define NE2000_IRQ_VECTOR1 29 #undef BSWAP @@ -94,6 +100,7 @@ #if defined(CONFIG_M5307) && defined(CONFIG_SECUREEDGEMP3) #define NE2000_ADDR 0x30600300 #define NE2000_ODDOFFSET 0x00008000 +#define NE2000_ADDRSIZE 0x00010000 #define NE2000_IRQ_VECTOR 27 #undef BSWAP #define BSWAP(w) (w) @@ -105,6 +112,7 @@ #if defined(CONFIG_ARN5307) #define NE2000_ADDR 0xfe600300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1b #define NE2000_IRQ_PRIORITY 2 #define NE2000_IRQ_LEVEL 3 @@ -114,129 +122,10 @@ #if defined(CONFIG_M5407C3) #define NE2000_ADDR 0x40000300 #define NE2000_ODDOFFSET 0x00010000 +#define NE2000_ADDRSIZE 0x00020000 #define NE2000_IRQ_VECTOR 0x1b #define NE2000_BYTE volatile unsigned short #endif /****************************************************************************/ - -/* - * Side-band address space for odd address requires re-mapping - * many of the standard ISA access functions. - */ -#ifdef NE2000_ODDOFFSET - -#undef outb -#undef outb_p -#undef inb -#undef inb_p -#undef outsb -#undef outsw -#undef insb -#undef insw - -#define outb ne2000_outb -#define inb ne2000_inb -#define outb_p ne2000_outb -#define inb_p ne2000_inb -#define outsb ne2000_outsb -#define outsw ne2000_outsw -#define insb ne2000_insb -#define insw ne2000_insw - - -#ifndef COLDFIRE_NE2000_FUNCS - -void ne2000_outb(unsigned int val, unsigned int addr); -int ne2000_inb(unsigned int addr); -void ne2000_insb(unsigned int addr, void *vbuf, int unsigned long len); -void ne2000_insw(unsigned int addr, void *vbuf, unsigned long len); -void ne2000_outsb(unsigned int addr, void *vbuf, unsigned long len); -void ne2000_outsw(unsigned int addr, void *vbuf, unsigned long len); - -#else - -/* - * This macro converts a conventional register address into the - * real memory pointer of the mapped NE2000 device. - * On most NE2000 implementations on ColdFire boards the chip is - * mapped in kinda funny, due to its ISA heritage. - */ -#define NE2000_PTR(addr) ((addr&0x1)?(NE2000_ODDOFFSET+addr-1):(addr)) -#define NE2000_DATA_PTR(addr) (addr) - - -void ne2000_outb(unsigned int val, unsigned int addr) -{ - NE2000_BYTE *rp; - - rp = (NE2000_BYTE *) NE2000_PTR(addr); - *rp = RSWAP(val); -} - -int ne2000_inb(unsigned int addr) -{ - NE2000_BYTE *rp, val; - - rp = (NE2000_BYTE *) NE2000_PTR(addr); - val = *rp; - return((int) ((NE2000_BYTE) RSWAP(val))); -} - -void ne2000_insb(unsigned int addr, void *vbuf, int unsigned long len) -{ - NE2000_BYTE *rp, val; - unsigned char *buf; - - buf = (unsigned char *) vbuf; - rp = (NE2000_BYTE *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - val = *rp; - *buf++ = RSWAP(val); - } -} - -void ne2000_insw(unsigned int addr, void *vbuf, unsigned long len) -{ - volatile unsigned short *rp; - unsigned short w, *buf; - - buf = (unsigned short *) vbuf; - rp = (volatile unsigned short *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - w = *rp; - *buf++ = BSWAP(w); - } -} - -void ne2000_outsb(unsigned int addr, const void *vbuf, unsigned long len) -{ - NE2000_BYTE *rp, val; - unsigned char *buf; - - buf = (unsigned char *) vbuf; - rp = (NE2000_BYTE *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - val = *buf++; - *rp = RSWAP(val); - } -} - -void ne2000_outsw(unsigned int addr, const void *vbuf, unsigned long len) -{ - volatile unsigned short *rp; - unsigned short w, *buf; - - buf = (unsigned short *) vbuf; - rp = (volatile unsigned short *) NE2000_DATA_PTR(addr); - for (; (len > 0); len--) { - w = *buf++; - *rp = BSWAP(w); - } -} - -#endif /* COLDFIRE_NE2000_FUNCS */ -#endif /* NE2000_OFFOFFSET */ - -/****************************************************************************/ -#endif /* mcfne_h */ +#endif /* mcf8390_h */ diff --git a/arch/m68k/kernel/module.c b/arch/m68k/kernel/module.c index 34849c4..eb46fd6 100644 --- a/arch/m68k/kernel/module.c +++ b/arch/m68k/kernel/module.c @@ -47,7 +47,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_68K_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; default: @@ -87,7 +87,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, *location = rel[i].r_addend + sym->st_value; break; case R_68K_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location = rel[i].r_addend + sym->st_value - (uint32_t)location; break; default: diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index ed22bfc..4dbb505 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -192,11 +192,6 @@ void pcibios_set_master(struct pci_dev *dev) /* No special bus mastering setup handling */ } -char __devinit *pcibios_setup(char *str) -{ - return str; -} - /* * Reads the interrupt pin to determine if interrupt is use by card. * If the interrupt is used, then gets the interrupt line from the @@ -249,8 +244,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev) } else { pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", oirq.size, oirq.specifier[0], oirq.specifier[1], - oirq.controller ? oirq.controller->full_name : - "<default>"); + of_node_full_name(oirq.controller)); virq = irq_create_of_mapping(oirq.controller, oirq.specifier, oirq.size); @@ -1493,8 +1487,7 @@ static void __devinit pcibios_scan_phb(struct pci_controller *hose) struct pci_bus *bus; struct device_node *node = hose->dn; - pr_debug("PCI: Scanning PHB %s\n", - node ? node->full_name : "<NO NAME>"); + pr_debug("PCI: Scanning PHB %s\n", of_node_full_name(node)); pcibios_setup_phb_resources(hose, &resources); @@ -1506,10 +1499,10 @@ static void __devinit pcibios_scan_phb(struct pci_controller *hose) pci_free_resource_list(&resources); return; } - bus->secondary = hose->first_busno; + bus->busn_res.start = hose->first_busno; hose->bus = bus; - hose->last_busno = bus->subordinate; + hose->last_busno = bus->busn_res.end; } static int __init pcibios_init(void) diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 1a24d31..1bbc24b 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -310,10 +310,10 @@ static void __init cpmac_get_mac(int instance, unsigned char *dev_addr) &dev_addr[4], &dev_addr[5]) != 6) { pr_warning("cannot parse mac address, " "using random address\n"); - random_ether_addr(dev_addr); + eth_random_addr(dev_addr); } } else - random_ether_addr(dev_addr); + eth_random_addr(dev_addr); } /***************************************************************************** diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 271e8c4a..6903568 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -102,7 +102,7 @@ static void __devinit pcibios_scanbus(struct pci_controller *hose) need_domain_info = need_domain_info || hose->index; hose->need_domain_info = need_domain_info; if (bus) { - next_busno = bus->subordinate + 1; + next_busno = bus->busn_res.end + 1; /* Don't allow 8-bit bus number overflow inside the hose - reserve some space for bridges. */ if (next_busno > 224) { @@ -348,9 +348,9 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, vma->vm_end - vma->vm_start, vma->vm_page_prot); } -char * (*pcibios_plat_setup)(char *str) __devinitdata; +char * (*pcibios_plat_setup)(char *str) __initdata; -char *__devinit pcibios_setup(char *str) +char *__init pcibios_setup(char *str) { if (pcibios_plat_setup) return pcibios_plat_setup(str); diff --git a/arch/mips/pmc-sierra/yosemite/ht.c b/arch/mips/pmc-sierra/yosemite/ht.c index 63be40e..14dc9c8 100644 --- a/arch/mips/pmc-sierra/yosemite/ht.c +++ b/arch/mips/pmc-sierra/yosemite/ht.c @@ -395,17 +395,6 @@ void __init pcibios_init(void) pci_scan_bus(3, &titan_pci_ops, NULL); } -/* - * for parsing "pci=" kernel boot arguments. - */ -char *pcibios_setup(char *str) -{ - printk(KERN_INFO "rr: pcibios_setup\n"); - /* Nothing to do for now. */ - - return str; -} - unsigned __init int pcibios_assign_all_busses(void) { /* We want to use the PCI bus detection done by PMON */ diff --git a/arch/mips/powertv/powertv_setup.c b/arch/mips/powertv/powertv_setup.c index 3933c37..820b848 100644 --- a/arch/mips/powertv/powertv_setup.c +++ b/arch/mips/powertv/powertv_setup.c @@ -254,7 +254,7 @@ early_param("rfmac", rfmac_param); * Generates an Ethernet MAC address that is highly likely to be unique for * this particular system on a network with other systems of the same type. * - * The problem we are solving is that, when random_ether_addr() is used to + * The problem we are solving is that, when eth_random_addr() is used to * generate MAC addresses at startup, there isn't much entropy for the random * number generator to use and the addresses it produces are fairly likely to * be the same as those of other identical systems on the same local network. @@ -269,7 +269,7 @@ early_param("rfmac", rfmac_param); * Still, this does give us something to work with. * * The approach we take is: - * 1. If we can't get the RF MAC Address, just call random_ether_addr. + * 1. If we can't get the RF MAC Address, just call eth_random_addr. * 2. Use the 24-bit NIC-specific bits of the RF MAC address as the last 24 * bits of the new address. This is very likely to be unique, except for * the current box. @@ -299,7 +299,7 @@ void platform_random_ether_addr(u8 addr[ETH_ALEN]) if (!have_rfmac) { pr_warning("rfmac not available on command line; " "generating random MAC address\n"); - random_ether_addr(addr); + eth_random_addr(addr); } else { diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c index 64eb71b..125db32 100644 --- a/arch/mips/txx9/generic/pci.c +++ b/arch/mips/txx9/generic/pci.c @@ -256,7 +256,7 @@ static irqreturn_t i8259_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int __init +static int __devinit txx9_i8259_irq_setup(int irq) { int err; @@ -398,9 +398,9 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return txx9_board_vec->pci_map_irq(dev, slot, pin); } -char * (*txx9_board_pcibios_setup)(char *str) __devinitdata; +char * (*txx9_board_pcibios_setup)(char *str) __initdata; -char *__devinit txx9_pcibios_setup(char *str) +char *__init txx9_pcibios_setup(char *str) { if (txx9_board_pcibios_setup && !txx9_board_pcibios_setup(str)) return NULL; diff --git a/arch/parisc/include/asm/compat_rt_sigframe.h b/arch/parisc/include/asm/compat_rt_sigframe.h index 81bec28..b3f95a7 100644 --- a/arch/parisc/include/asm/compat_rt_sigframe.h +++ b/arch/parisc/include/asm/compat_rt_sigframe.h @@ -1,6 +1,6 @@ -#include<linux/compat.h> -#include<linux/compat_siginfo.h> -#include<asm/compat_ucontext.h> +#include <linux/compat.h> +#include <linux/compat_siginfo.h> +#include <asm/compat_ucontext.h> #ifndef _ASM_PARISC_COMPAT_RT_SIGFRAME_H #define _ASM_PARISC_COMPAT_RT_SIGFRAME_H diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c index 24644ac..6030905 100644 --- a/arch/parisc/kernel/pci.c +++ b/arch/parisc/kernel/pci.c @@ -139,11 +139,6 @@ void pcibios_fixup_bus(struct pci_bus *bus) } -char *pcibios_setup(char *str) -{ - return str; -} - /* * Called by pci_set_master() - a driver interface. * diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 050cb37..9a5d3cd 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -653,7 +653,7 @@ config SBUS config FSL_SOC bool select HAVE_CAN_FLEXCAN if NET && CAN - select PPC_CLOCK if CAN_FLEXCAN + select PPC_CLOCK config FSL_PCI bool diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug index e5f2689..5416e28 100644 --- a/arch/powerpc/Kconfig.debug +++ b/arch/powerpc/Kconfig.debug @@ -331,4 +331,13 @@ config STRICT_DEVMEM If you are unsure, say Y. +config FAIL_IOMMU + bool "Fault-injection capability for IOMMU" + depends on FAULT_INJECTION + help + Provide fault-injection capability for IOMMU. Each device can + be selectively enabled via the fail_iommu property. + + If you are unsure, say N. + endmenu diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index e8461cb..b7d8333 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -62,26 +62,45 @@ libfdtheader := fdt.h libfdt.h libfdt_internal.h $(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o): \ $(addprefix $(obj)/,$(libfdtheader)) -src-wlib := string.S crt0.S crtsavres.S stdio.c main.c \ +src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \ $(libfdt) libfdt-wrapper.c \ ns16550.c serial.c simple_alloc.c div64.S util.S \ - gunzip_util.c elf_util.c $(zlib) devtree.c oflib.c ofconsole.c \ - 4xx.c ebony.c mv64x60.c mpsc.c mv64x60_i2c.c cuboot.c bamboo.c \ - cpm-serial.c stdlib.c mpc52xx-psc.c planetcore.c uartlite.c \ - fsl-soc.c mpc8xx.c pq2.c ugecon.c -src-plat := of.c cuboot-52xx.c cuboot-824x.c cuboot-83xx.c cuboot-85xx.c holly.c \ - cuboot-ebony.c cuboot-hotfoot.c epapr.c treeboot-ebony.c \ - prpmc2800.c \ - ps3-head.S ps3-hvcall.S ps3.c treeboot-bamboo.c cuboot-8xx.c \ - cuboot-pq2.c cuboot-sequoia.c treeboot-walnut.c \ - cuboot-bamboo.c cuboot-mpc7448hpc2.c cuboot-taishan.c \ - fixed-head.S ep88xc.c ep405.c cuboot-c2k.c \ - cuboot-katmai.c cuboot-rainier.c redboot-8xx.c ep8248e.c \ - cuboot-warp.c cuboot-85xx-cpm2.c cuboot-yosemite.c simpleboot.c \ - virtex405-head.S virtex.c redboot-83xx.c cuboot-sam440ep.c \ - cuboot-acadia.c cuboot-amigaone.c cuboot-kilauea.c \ - gamecube-head.S gamecube.c wii-head.S wii.c treeboot-iss4xx.c \ - treeboot-currituck.c + gunzip_util.c elf_util.c $(zlib) devtree.c stdlib.c \ + oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \ + uartlite.c mpc52xx-psc.c +src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c +src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c +src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c +src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c +src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c + +src-plat-y := of.c +src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \ + treeboot-walnut.c cuboot-acadia.c \ + cuboot-kilauea.c simpleboot.c \ + virtex405-head.S virtex.c +src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \ + cuboot-bamboo.c cuboot-sam440ep.c \ + cuboot-sequoia.c cuboot-rainier.c \ + cuboot-taishan.c cuboot-katmai.c \ + cuboot-warp.c cuboot-yosemite.c \ + treeboot-iss4xx.c treeboot-currituck.c \ + simpleboot.c fixed-head.S virtex.c +src-plat-$(CONFIG_8xx) += cuboot-8xx.c fixed-head.S ep88xc.c redboot-8xx.c +src-plat-$(CONFIG_PPC_MPC52xx) += cuboot-52xx.c +src-plat-$(CONFIG_PPC_82xx) += cuboot-pq2.c fixed-head.S ep8248e.c cuboot-824x.c +src-plat-$(CONFIG_PPC_83xx) += cuboot-83xx.c fixed-head.S redboot-83xx.c +src-plat-$(CONFIG_FSL_SOC_BOOKE) += cuboot-85xx.c cuboot-85xx-cpm2.c +src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \ + cuboot-c2k.c gamecube-head.S \ + gamecube.c wii-head.S wii.c holly.c \ + prpmc2800.c +src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c +src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c +src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c + +src-wlib := $(sort $(src-wlib-y)) +src-plat := $(sort $(src-plat-y)) src-boot := $(src-wlib) $(src-plat) empty.c src-boot := $(addprefix $(obj)/, $(src-boot)) @@ -257,7 +276,6 @@ image-$(CONFIG_TQM8548) += cuImage.tqm8548 image-$(CONFIG_TQM8555) += cuImage.tqm8555 image-$(CONFIG_TQM8560) += cuImage.tqm8560 image-$(CONFIG_SBC8548) += cuImage.sbc8548 -image-$(CONFIG_SBC8560) += cuImage.sbc8560 image-$(CONFIG_KSI8560) += cuImage.ksi8560 # Board ports in arch/powerpc/platform/embedded6xx/Kconfig @@ -412,4 +430,3 @@ $(wrapper-installed): $(DESTDIR)$(WRAPPER_BINDIR) $(srctree)/$(obj)/wrapper | $( $(call cmd,install_wrapper) $(obj)/bootwrapper_install: $(all-installed) - diff --git a/arch/powerpc/boot/dts/bsc9131rdb.dts b/arch/powerpc/boot/dts/bsc9131rdb.dts new file mode 100644 index 0000000..e13d2d4 --- /dev/null +++ b/arch/powerpc/boot/dts/bsc9131rdb.dts @@ -0,0 +1,34 @@ +/* + * BSC9131 RDB Device Tree Source + * + * Copyright 2011-2012 Freescale Semiconductor Inc. + * + * 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. + */ + +/include/ "fsl/bsc9131si-pre.dtsi" + +/ { + model = "fsl,bsc9131rdb"; + compatible = "fsl,bsc9131rdb"; + + memory { + device_type = "memory"; + }; + + board_ifc: ifc: ifc@ff71e000 { + /* NAND Flash on board */ + ranges = <0x0 0x0 0x0 0xff800000 0x00004000>; + reg = <0x0 0xff71e000 0x0 0x2000>; + }; + + board_soc: soc: soc@ff700000 { + ranges = <0x0 0x0 0xff700000 0x100000>; + }; +}; + +/include/ "bsc9131rdb.dtsi" +/include/ "fsl/bsc9131si-post.dtsi" diff --git a/arch/powerpc/boot/dts/bsc9131rdb.dtsi b/arch/powerpc/boot/dts/bsc9131rdb.dtsi new file mode 100644 index 0000000..638adda --- /dev/null +++ b/arch/powerpc/boot/dts/bsc9131rdb.dtsi @@ -0,0 +1,142 @@ +/* + * BSC9131 RDB Device Tree Source stub (no addresses or top-level ranges) + * + * Copyright 2011-2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&board_ifc { + + nand@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,ifc-nand"; + reg = <0x0 0x0 0x4000>; + + partition@0 { + /* This location must not be altered */ + /* 3MB for u-boot Bootloader Image */ + reg = <0x0 0x00300000>; + label = "NAND U-Boot Image"; + read-only; + }; + + partition@300000 { + /* 1MB for DTB Image */ + reg = <0x00300000 0x00100000>; + label = "NAND DTB Image"; + }; + + partition@400000 { + /* 8MB for Linux Kernel Image */ + reg = <0x00400000 0x00800000>; + label = "NAND Linux Kernel Image"; + }; + + partition@c00000 { + /* Rest space for Root file System Image */ + reg = <0x00c00000 0x07400000>; + label = "NAND RFS Image"; + }; + }; +}; + +&board_soc { + /* BSC9131RDB does not have any device on i2c@3100 */ + i2c@3100 { + status = "disabled"; + }; + + spi@7000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "spansion,s25sl12801"; + reg = <0>; + spi-max-frequency = <50000000>; + + /* 512KB for u-boot Bootloader Image */ + partition@0 { + reg = <0x0 0x00080000>; + label = "SPI Flash U-Boot Image"; + read-only; + }; + + /* 512KB for DTB Image */ + partition@80000 { + reg = <0x00080000 0x00080000>; + label = "SPI Flash DTB Image"; + }; + + /* 4MB for Linux Kernel Image */ + partition@100000 { + reg = <0x00100000 0x00400000>; + label = "SPI Flash Kernel Image"; + }; + + /*11MB for RFS Image */ + partition@500000 { + reg = <0x00500000 0x00B00000>; + label = "SPI Flash RFS Image"; + }; + + }; + }; + + usb@22000 { + phy_type = "ulpi"; + }; + + mdio@24000 { + phy0: ethernet-phy@0 { + interrupts = <3 1 0 0>; + reg = <0x0>; + }; + + phy1: ethernet-phy@1 { + interrupts = <2 1 0 0>; + reg = <0x3>; + }; + }; + + sdhci@2e000 { + status = "disabled"; + }; + + enet0: ethernet@b0000 { + phy-handle = <&phy0>; + phy-connection-type = "rgmii-id"; + }; + + enet1: ethernet@b1000 { + phy-handle = <&phy1>; + phy-connection-type = "rgmii-id"; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi new file mode 100644 index 0000000..5180d9d --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi @@ -0,0 +1,193 @@ +/* + * BSC9131 Silicon/SoC Device Tree Source (post include) + * + * Copyright 2011-2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&ifc { + #address-cells = <2>; + #size-cells = <1>; + compatible = "fsl,ifc", "simple-bus"; + interrupts = <16 2 0 0 20 2 0 0>; +}; + +&soc { + #address-cells = <1>; + #size-cells = <1>; + device_type = "soc"; + compatible = "fsl,bsc9131-immr", "simple-bus"; + bus-frequency = <0>; // Filled out by uboot. + + ecm-law@0 { + compatible = "fsl,ecm-law"; + reg = <0x0 0x1000>; + fsl,num-laws = <12>; + }; + + ecm@1000 { + compatible = "fsl,bsc9131-ecm", "fsl,ecm"; + reg = <0x1000 0x1000>; + interrupts = <16 2 0 0>; + }; + + memory-controller@2000 { + compatible = "fsl,bsc9131-memory-controller"; + reg = <0x2000 0x1000>; + interrupts = <16 2 0 0>; + }; + +/include/ "pq3-i2c-0.dtsi" + i2c@3000 { + interrupts = <17 2 0 0>; + }; + +/include/ "pq3-i2c-1.dtsi" + i2c@3100 { + interrupts = <17 2 0 0>; + }; + +/include/ "pq3-duart-0.dtsi" + serial0: serial@4500 { + interrupts = <18 2 0 0>; + }; + + serial1: serial@4600 { + interrupts = <18 2 0 0 >; + }; +/include/ "pq3-espi-0.dtsi" + spi0: spi@7000 { + fsl,espi-num-chipselects = <1>; + interrupts = <22 0x2 0 0>; + }; + +/include/ "pq3-gpio-0.dtsi" + gpio-controller@f000 { + interrupts = <19 0x2 0 0>; + }; + + L2: l2-cache-controller@20000 { + compatible = "fsl,bsc9131-l2-cache-controller"; + reg = <0x20000 0x1000>; + cache-line-size = <32>; // 32 bytes + cache-size = <0x40000>; // L2,256K + interrupts = <16 2 0 0>; + }; + +/include/ "pq3-dma-0.dtsi" + +dma@21300 { + + dma-channel@0 { + interrupts = <62 2 0 0>; + }; + + dma-channel@80 { + interrupts = <63 2 0 0>; + }; + + dma-channel@100 { + interrupts = <64 2 0 0>; + }; + + dma-channel@180 { + interrupts = <65 2 0 0>; + }; +}; + +/include/ "pq3-usb2-dr-0.dtsi" +usb@22000 { + compatible = "fsl-usb2-dr","fsl-usb2-dr-v2.2"; + interrupts = <40 0x2 0 0>; +}; + +/include/ "pq3-esdhc-0.dtsi" + sdhc@2e000 { + fsl,sdhci-auto-cmd12; + interrupts = <41 0x2 0 0>; + }; + +/include/ "pq3-sec4.4-0.dtsi" +crypto@30000 { + interrupts = <57 2 0 0>; + + sec_jr0: jr@1000 { + interrupts = <58 2 0 0>; + }; + + sec_jr1: jr@2000 { + interrupts = <59 2 0 0>; + }; + + sec_jr2: jr@3000 { + interrupts = <60 2 0 0>; + }; + + sec_jr3: jr@4000 { + interrupts = <61 2 0 0>; + }; +}; + +/include/ "pq3-mpic.dtsi" + +timer@41100 { + compatible = "fsl,mpic-v1.2-msgr", "fsl,mpic-msg"; + reg = <0x41400 0x200>; + interrupts = < + 0xb0 2 + 0xb1 2 + 0xb2 2 + 0xb3 2>; +}; + +/include/ "pq3-etsec2-0.dtsi" +enet0: ethernet@b0000 { + queue-group@b0000 { + fsl,rx-bit-map = <0xff>; + fsl,tx-bit-map = <0xff>; + interrupts = <26 2 0 0 27 2 0 0 28 2 0 0>; + }; +}; + +/include/ "pq3-etsec2-1.dtsi" +enet1: ethernet@b1000 { + queue-group@b1000 { + fsl,rx-bit-map = <0xff>; + fsl,tx-bit-map = <0xff>; + interrupts = <33 2 0 0 34 2 0 0 35 2 0 0>; + }; +}; + +global-utilities@e0000 { + compatible = "fsl,bsc9131-guts"; + reg = <0xe0000 0x1000>; + fsl,has-rstcr; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/p3060si-pre.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-pre.dtsi index 00c8e70..743e4ae 100644 --- a/arch/powerpc/boot/dts/fsl/p3060si-pre.dtsi +++ b/arch/powerpc/boot/dts/fsl/bsc9131si-pre.dtsi @@ -1,7 +1,7 @@ /* - * P3060 Silicon/SoC Device Tree Source (pre include) + * BSC9131 Silicon/SoC Device Tree Source (pre include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011-2012 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -34,92 +34,26 @@ /dts-v1/; / { - compatible = "fsl,P3060"; + compatible = "fsl,BSC9131"; #address-cells = <2>; #size-cells = <2>; interrupt-parent = <&mpic>; aliases { - ccsr = &soc; - dcsr = &dcsr; - serial0 = &serial0; - serial1 = &serial1; - serial2 = &serial2; - serial3 = &serial3; - pci0 = &pci0; - pci1 = &pci1; - usb0 = &usb0; - usb1 = &usb1; - dma0 = &dma0; - dma1 = &dma1; - msi0 = &msi0; - msi1 = &msi1; - msi2 = &msi2; - - crypto = &crypto; - sec_jr0 = &sec_jr0; - sec_jr1 = &sec_jr1; - sec_jr2 = &sec_jr2; - sec_jr3 = &sec_jr3; - rtic_a = &rtic_a; - rtic_b = &rtic_b; - rtic_c = &rtic_c; - rtic_d = &rtic_d; - sec_mon = &sec_mon; + ethernet0 = &enet0; + ethernet1 = &enet1; }; cpus { #address-cells = <1>; #size-cells = <0>; - cpu0: PowerPC,e500mc@0 { - device_type = "cpu"; - reg = <0>; - next-level-cache = <&L2_0>; - L2_0: l2-cache { - next-level-cache = <&cpc>; - }; - }; - cpu1: PowerPC,e500mc@1 { - device_type = "cpu"; - reg = <1>; - next-level-cache = <&L2_1>; - L2_1: l2-cache { - next-level-cache = <&cpc>; - }; - }; - cpu4: PowerPC,e500mc@4 { - device_type = "cpu"; - reg = <4>; - next-level-cache = <&L2_4>; - L2_4: l2-cache { - next-level-cache = <&cpc>; - }; - }; - cpu5: PowerPC,e500mc@5 { - device_type = "cpu"; - reg = <5>; - next-level-cache = <&L2_5>; - L2_5: l2-cache { - next-level-cache = <&cpc>; - }; - }; - cpu6: PowerPC,e500mc@6 { - device_type = "cpu"; - reg = <6>; - next-level-cache = <&L2_6>; - L2_6: l2-cache { - next-level-cache = <&cpc>; - }; - }; - cpu7: PowerPC,e500mc@7 { + PowerPC,BSC9131@0 { device_type = "cpu"; - reg = <7>; - next-level-cache = <&L2_7>; - L2_7: l2-cache { - next-level-cache = <&cpc>; - }; + compatible = "fsl,e500v2"; + reg = <0x0>; + next-level-cache = <&L2>; }; }; }; diff --git a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi index 4252ef8..adb82fd 100644 --- a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi @@ -1,7 +1,7 @@ /* * P1021/P1012 Silicon/SoC Device Tree Source (post include) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2011-2012 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -213,6 +213,20 @@ interrupt-parent = <&qeic>; }; + ucc@2600 { + cell-index = <7>; + reg = <0x2600 0x200>; + interrupts = <42>; + interrupt-parent = <&qeic>; + }; + + ucc@2200 { + cell-index = <3>; + reg = <0x2200 0x200>; + interrupts = <34>; + interrupt-parent = <&qeic>; + }; + muram@10000 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi deleted file mode 100644 index b3e5692..0000000 --- a/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi +++ /dev/null @@ -1,302 +0,0 @@ -/* - * P3060 Silicon/SoC Device Tree Source (post include) - * - * Copyright 2011 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -&lbc { - compatible = "fsl,p3060-elbc", "fsl,elbc", "simple-bus"; - interrupts = <25 2 0 0>; - #address-cells = <2>; - #size-cells = <1>; -}; - -/* controller at 0x200000 */ -&pci0 { - compatible = "fsl,p3060-pcie", "fsl,qoriq-pcie-v2.2"; - device_type = "pci"; - #size-cells = <2>; - #address-cells = <3>; - bus-range = <0x0 0xff>; - clock-frequency = <33333333>; - interrupts = <16 2 1 15>; - pcie@0 { - reg = <0 0 0 0 0>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - device_type = "pci"; - interrupts = <16 2 1 15>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = < - /* IDSEL 0x0 */ - 0000 0 0 1 &mpic 40 1 0 0 - 0000 0 0 2 &mpic 1 1 0 0 - 0000 0 0 3 &mpic 2 1 0 0 - 0000 0 0 4 &mpic 3 1 0 0 - >; - }; -}; - -/* controller at 0x201000 */ -&pci1 { - compatible = "fsl,p3060-pcie", "fsl,qoriq-pcie-v2.2"; - device_type = "pci"; - #size-cells = <2>; - #address-cells = <3>; - bus-range = <0 0xff>; - clock-frequency = <33333333>; - interrupts = <16 2 1 14>; - pcie@0 { - reg = <0 0 0 0 0>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - device_type = "pci"; - interrupts = <16 2 1 14>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = < - /* IDSEL 0x0 */ - 0000 0 0 1 &mpic 41 1 0 0 - 0000 0 0 2 &mpic 5 1 0 0 - 0000 0 0 3 &mpic 6 1 0 0 - 0000 0 0 4 &mpic 7 1 0 0 - >; - }; -}; - -&rio { - compatible = "fsl,srio"; - interrupts = <16 2 1 11>; - #address-cells = <2>; - #size-cells = <2>; - fsl,srio-rmu-handle = <&rmu>; - ranges; - - port1 { - #address-cells = <2>; - #size-cells = <2>; - cell-index = <1>; - }; - - port2 { - #address-cells = <2>; - #size-cells = <2>; - cell-index = <2>; - }; -}; - -&dcsr { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,dcsr", "simple-bus"; - - dcsr-epu@0 { - compatible = "fsl,dcsr-epu"; - interrupts = <52 2 0 0 - 84 2 0 0 - 85 2 0 0>; - reg = <0x0 0x1000>; - }; - dcsr-npc { - compatible = "fsl,dcsr-npc"; - reg = <0x1000 0x1000 0x1000000 0x8000>; - }; - dcsr-nxc@2000 { - compatible = "fsl,dcsr-nxc"; - reg = <0x2000 0x1000>; - }; - dcsr-corenet { - compatible = "fsl,dcsr-corenet"; - reg = <0x8000 0x1000 0xB0000 0x1000>; - }; - dcsr-dpaa@9000 { - compatible = "fsl,p3060-dcsr-dpaa", "fsl,dcsr-dpaa"; - reg = <0x9000 0x1000>; - }; - dcsr-ocn@11000 { - compatible = "fsl,p3060-dcsr-ocn", "fsl,dcsr-ocn"; - reg = <0x11000 0x1000>; - }; - dcsr-ddr@12000 { - compatible = "fsl,dcsr-ddr"; - dev-handle = <&ddr1>; - reg = <0x12000 0x1000>; - }; - dcsr-nal@18000 { - compatible = "fsl,p3060-dcsr-nal", "fsl,dcsr-nal"; - reg = <0x18000 0x1000>; - }; - dcsr-rcpm@22000 { - compatible = "fsl,p3060-dcsr-rcpm", "fsl,dcsr-rcpm"; - reg = <0x22000 0x1000>; - }; - dcsr-cpu-sb-proxy@40000 { - compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; - cpu-handle = <&cpu0>; - reg = <0x40000 0x1000>; - }; - dcsr-cpu-sb-proxy@41000 { - compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; - cpu-handle = <&cpu1>; - reg = <0x41000 0x1000>; - }; - dcsr-cpu-sb-proxy@44000 { - compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; - cpu-handle = <&cpu4>; - reg = <0x44000 0x1000>; - }; - dcsr-cpu-sb-proxy@45000 { - compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; - cpu-handle = <&cpu5>; - reg = <0x45000 0x1000>; - }; - dcsr-cpu-sb-proxy@46000 { - compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; - cpu-handle = <&cpu6>; - reg = <0x46000 0x1000>; - }; - dcsr-cpu-sb-proxy@47000 { - compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy"; - cpu-handle = <&cpu7>; - reg = <0x47000 0x1000>; - }; - -}; - -&soc { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - - soc-sram-error { - compatible = "fsl,soc-sram-error"; - interrupts = <16 2 1 29>; - }; - - corenet-law@0 { - compatible = "fsl,corenet-law"; - reg = <0x0 0x1000>; - fsl,num-laws = <32>; - }; - - ddr1: memory-controller@8000 { - compatible = "fsl,qoriq-memory-controller-v4.4", "fsl,qoriq-memory-controller"; - reg = <0x8000 0x1000>; - interrupts = <16 2 1 23>; - }; - - cpc: l3-cache-controller@10000 { - compatible = "fsl,p3060-l3-cache-controller", "cache"; - reg = <0x10000 0x1000 - 0x11000 0x1000>; - interrupts = <16 2 1 27 - 16 2 1 26>; - }; - - corenet-cf@18000 { - compatible = "fsl,corenet-cf"; - reg = <0x18000 0x1000>; - interrupts = <16 2 1 31>; - fsl,ccf-num-csdids = <32>; - fsl,ccf-num-snoopids = <32>; - }; - - iommu@20000 { - compatible = "fsl,pamu-v1.0", "fsl,pamu"; - reg = <0x20000 0x5000>; - interrupts = < - 24 2 0 0 - 16 2 1 30>; - }; - -/include/ "qoriq-rmu-0.dtsi" -/include/ "qoriq-mpic.dtsi" - - guts: global-utilities@e0000 { - compatible = "fsl,qoriq-device-config-1.0"; - reg = <0xe0000 0xe00>; - fsl,has-rstcr; - #sleep-cells = <1>; - fsl,liodn-bits = <12>; - }; - - pins: global-utilities@e0e00 { - compatible = "fsl,qoriq-pin-control-1.0"; - reg = <0xe0e00 0x200>; - #sleep-cells = <2>; - }; - - clockgen: global-utilities@e1000 { - compatible = "fsl,p3060-clockgen", "fsl,qoriq-clockgen-1.0"; - reg = <0xe1000 0x1000>; - clock-frequency = <0>; - }; - - rcpm: global-utilities@e2000 { - compatible = "fsl,qoriq-rcpm-1.0"; - reg = <0xe2000 0x1000>; - #sleep-cells = <1>; - }; - - sfp: sfp@e8000 { - compatible = "fsl,p3060-sfp", "fsl,qoriq-sfp-1.0"; - reg = <0xe8000 0x1000>; - }; - - serdes: serdes@ea000 { - compatible = "fsl,p3060-serdes"; - reg = <0xea000 0x1000>; - }; - -/include/ "qoriq-dma-0.dtsi" -/include/ "qoriq-dma-1.dtsi" -/include/ "qoriq-espi-0.dtsi" - spi@110000 { - fsl,espi-num-chipselects = <4>; - }; - -/include/ "qoriq-i2c-0.dtsi" -/include/ "qoriq-i2c-1.dtsi" -/include/ "qoriq-duart-0.dtsi" -/include/ "qoriq-duart-1.dtsi" -/include/ "qoriq-gpio-0.dtsi" -/include/ "qoriq-usb2-mph-0.dtsi" - usb@210000 { - compatible = "fsl-usb2-mph-v2.2", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph"; - }; -/include/ "qoriq-usb2-dr-0.dtsi" - usb@211000 { - compatible = "fsl-usb2-dr-v2.2", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr"; - }; -/include/ "qoriq-sec4.1-0.dtsi" -}; diff --git a/arch/powerpc/boot/dts/mgcoge.dts b/arch/powerpc/boot/dts/mgcoge.dts index ededaf5..d72fb5e 100644 --- a/arch/powerpc/boot/dts/mgcoge.dts +++ b/arch/powerpc/boot/dts/mgcoge.dts @@ -222,6 +222,29 @@ interrupt-parent = <&PIC>; usb-clock = <5>; }; + spi@11aa0 { + cell-index = <0>; + compatible = "fsl,spi", "fsl,cpm2-spi"; + reg = <0x11a80 0x40 0x89fc 0x2>; + interrupts = <2 8>; + interrupt-parent = <&PIC>; + gpios = < &cpm2_pio_d 19 0>; + #address-cells = <1>; + #size-cells = <0>; + ds3106@1 { + compatible = "gen,spidev"; + reg = <0>; + spi-max-frequency = <8000000>; + }; + }; + + }; + + cpm2_pio_d: gpio-controller@10d60 { + #gpio-cells = <2>; + compatible = "fsl,cpm2-pario-bank"; + reg = <0x10d60 0x14>; + gpio-controller; }; cpm2_pio_c: gpio-controller@10d40 { diff --git a/arch/powerpc/boot/dts/mpc8536ds.dtsi b/arch/powerpc/boot/dts/mpc8536ds.dtsi index cc46dbd..d304a2d 100644 --- a/arch/powerpc/boot/dts/mpc8536ds.dtsi +++ b/arch/powerpc/boot/dts/mpc8536ds.dtsi @@ -203,6 +203,14 @@ reg = <1>; device_type = "ethernet-phy"; }; + sgmii_phy0: sgmii-phy@0 { + interrupts = <6 1 0 0>; + reg = <0x1d>; + }; + sgmii_phy1: sgmii-phy@1 { + interrupts = <6 1 0 0>; + reg = <0x1c>; + }; tbi0: tbi-phy@11 { reg = <0x11>; device_type = "tbi-phy"; diff --git a/arch/powerpc/boot/dts/mpc8544ds.dtsi b/arch/powerpc/boot/dts/mpc8544ds.dtsi index 270f64b..77ebc9f 100644 --- a/arch/powerpc/boot/dts/mpc8544ds.dtsi +++ b/arch/powerpc/boot/dts/mpc8544ds.dtsi @@ -51,6 +51,15 @@ device_type = "ethernet-phy"; }; + sgmii_phy0: sgmii-phy@0 { + interrupts = <6 1 0 0>; + reg = <0x1c>; + }; + sgmii_phy1: sgmii-phy@1 { + interrupts = <6 1 0 0>; + reg = <0x1d>; + }; + tbi0: tbi-phy@11 { reg = <0x11>; device_type = "tbi-phy"; diff --git a/arch/powerpc/boot/dts/mpc8572ds.dtsi b/arch/powerpc/boot/dts/mpc8572ds.dtsi index 1417894..357490b 100644 --- a/arch/powerpc/boot/dts/mpc8572ds.dtsi +++ b/arch/powerpc/boot/dts/mpc8572ds.dtsi @@ -169,6 +169,23 @@ reg = <0x3>; }; + sgmii_phy0: sgmii-phy@0 { + interrupts = <6 1 0 0>; + reg = <0x1c>; + }; + sgmii_phy1: sgmii-phy@1 { + interrupts = <6 1 0 0>; + reg = <0x1d>; + }; + sgmii_phy2: sgmii-phy@2 { + interrupts = <7 1 0 0>; + reg = <0x1e>; + }; + sgmii_phy3: sgmii-phy@3 { + interrupts = <7 1 0 0>; + reg = <0x1f>; + }; + tbi0: tbi-phy@11 { reg = <0x11>; device_type = "tbi-phy"; diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts index d34d127..ef9ef56 100644 --- a/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts +++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts @@ -67,10 +67,10 @@ msi@41600 { msi-available-ranges = <0 0x80>; interrupts = < - 0xe0 0 - 0xe1 0 - 0xe2 0 - 0xe3 0>; + 0xe0 0 0 0 + 0xe1 0 0 0 + 0xe2 0 0 0 + 0xe3 0 0 0>; }; timer@42100 { status = "disabled"; diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts index d6a8faf..24564ee 100644 --- a/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts +++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts @@ -67,9 +67,6 @@ ethernet@24000 { status = "disabled"; }; - mdio@24520 { - status = "disabled"; - }; ptp_clock@24e00 { status = "disabled"; }; @@ -100,10 +97,10 @@ msi@41600 { msi-available-ranges = <0x80 0x80>; interrupts = < - 0xe4 0 - 0xe5 0 - 0xe6 0 - 0xe7 0>; + 0xe4 0 0 0 + 0xe5 0 0 0 + 0xe6 0 0 0 + 0xe7 0 0 0>; }; global-utilities@e0000 { status = "disabled"; diff --git a/arch/powerpc/boot/dts/p1010rdb.dtsi b/arch/powerpc/boot/dts/p1010rdb.dtsi index 4977614..ec7c27a 100644 --- a/arch/powerpc/boot/dts/p1010rdb.dtsi +++ b/arch/powerpc/boot/dts/p1010rdb.dtsi @@ -126,12 +126,24 @@ &board_soc { i2c@3000 { + eeprom@50 { + compatible = "st,24c256"; + reg = <0x50>; + }; + rtc@68 { compatible = "pericom,pt7c4338"; reg = <0x68>; }; }; + i2c@3100 { + eeprom@52 { + compatible = "atmel,24c01"; + reg = <0x52>; + }; + }; + spi@7000 { flash@0 { #address-cells = <1>; diff --git a/arch/powerpc/boot/dts/p1021rdb.dtsi b/arch/powerpc/boot/dts/p1021rdb-pc.dtsi index b973461..c13abfb 100644 --- a/arch/powerpc/boot/dts/p1021rdb.dtsi +++ b/arch/powerpc/boot/dts/p1021rdb-pc.dtsi @@ -1,7 +1,7 @@ /* * P1021 RDB Device Tree Source stub (no addresses or top-level ranges) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2012 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: diff --git a/arch/powerpc/boot/dts/p1021rdb.dts b/arch/powerpc/boot/dts/p1021rdb-pc_32b.dts index 90b6b4c..7cefa12 100644 --- a/arch/powerpc/boot/dts/p1021rdb.dts +++ b/arch/powerpc/boot/dts/p1021rdb-pc_32b.dts @@ -1,7 +1,7 @@ /* * P1021 RDB Device Tree Source * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2012 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -92,5 +92,5 @@ }; }; -/include/ "p1021rdb.dtsi" +/include/ "p1021rdb-pc.dtsi" /include/ "fsl/p1021si-post.dtsi" diff --git a/arch/powerpc/boot/dts/p1021rdb_36b.dts b/arch/powerpc/boot/dts/p1021rdb-pc_36b.dts index ea6d8b5..53d0c88 100644 --- a/arch/powerpc/boot/dts/p1021rdb_36b.dts +++ b/arch/powerpc/boot/dts/p1021rdb-pc_36b.dts @@ -1,7 +1,7 @@ /* * P1021 RDB Device Tree Source (36-bit address map) * - * Copyright 2011 Freescale Semiconductor Inc. + * Copyright 2012 Freescale Semiconductor Inc. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -92,5 +92,5 @@ }; }; -/include/ "p1021rdb.dtsi" +/include/ "p1021rdb-pc.dtsi" /include/ "fsl/p1021si-post.dtsi" diff --git a/arch/powerpc/boot/dts/p1022ds.dtsi b/arch/powerpc/boot/dts/p1022ds.dtsi index 7cdb505..c3344b0 100644 --- a/arch/powerpc/boot/dts/p1022ds.dtsi +++ b/arch/powerpc/boot/dts/p1022ds.dtsi @@ -33,22 +33,6 @@ */ &board_lbc { - /* - * This node is used to access the pixis via "indirect" mode, - * which is done by writing the pixis register index to chip - * select 0 and the value to/from chip select 1. Indirect - * mode is the only way to access the pixis when DIU video - * is enabled. Note that this assumes that the first column - * of the 'ranges' property above is the chip select number. - */ - board-control@0,0 { - compatible = "fsl,p1022ds-indirect-pixis"; - reg = <0x0 0x0 1 /* CS0 */ - 0x1 0x0 1>; /* CS1 */ - interrupt-parent = <&mpic>; - interrupts = <8 0 0 0>; - }; - nor@0,0 { #address-cells = <1>; #size-cells = <1>; @@ -161,6 +145,10 @@ * the clock is enabled. */ }; + rtc@68 { + compatible = "dallas,ds1339"; + reg = <0x68>; + }; }; spi@7000 { diff --git a/arch/powerpc/boot/dts/p1024rdb.dtsi b/arch/powerpc/boot/dts/p1024rdb.dtsi new file mode 100644 index 0000000..b05dcb4 --- /dev/null +++ b/arch/powerpc/boot/dts/p1024rdb.dtsi @@ -0,0 +1,228 @@ +/* + * P1024 RDB Device Tree Source stub (no addresses or top-level ranges) + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +&lbc { + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x1000000>; + bank-width = <2>; + device-width = <1>; + + partition@0 { + /* This location must not be altered */ + /* 256KB for Vitesse 7385 Switch firmware */ + reg = <0x0 0x00040000>; + label = "NOR Vitesse-7385 Firmware"; + read-only; + }; + + partition@40000 { + /* 256KB for DTB Image */ + reg = <0x00040000 0x00040000>; + label = "NOR DTB Image"; + }; + + partition@80000 { + /* 3.5 MB for Linux Kernel Image */ + reg = <0x00080000 0x00380000>; + label = "NOR Linux Kernel Image"; + }; + + partition@400000 { + /* 11MB for JFFS2 based Root file System */ + reg = <0x00400000 0x00b00000>; + label = "NOR JFFS2 Root File System"; + }; + + partition@f00000 { + /* This location must not be altered */ + /* 512KB for u-boot Bootloader Image */ + /* 512KB for u-boot Environment Variables */ + reg = <0x00f00000 0x00100000>; + label = "NOR U-Boot Image"; + read-only; + }; + }; + + nand@1,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,p1020-fcm-nand", + "fsl,elbc-fcm-nand"; + reg = <0x1 0x0 0x40000>; + + partition@0 { + /* This location must not be altered */ + /* 1MB for u-boot Bootloader Image */ + reg = <0x0 0x00100000>; + label = "NAND U-Boot Image"; + read-only; + }; + + partition@100000 { + /* 1MB for DTB Image */ + reg = <0x00100000 0x00100000>; + label = "NAND DTB Image"; + }; + + partition@200000 { + /* 4MB for Linux Kernel Image */ + reg = <0x00200000 0x00400000>; + label = "NAND Linux Kernel Image"; + }; + + partition@600000 { + /* 4MB for Compressed Root file System Image */ + reg = <0x00600000 0x00400000>; + label = "NAND Compressed RFS Image"; + }; + + partition@a00000 { + /* 15MB for JFFS2 based Root file System */ + reg = <0x00a00000 0x00f00000>; + label = "NAND JFFS2 Root File System"; + }; + + partition@1900000 { + /* 7MB for User Writable Area */ + reg = <0x01900000 0x00700000>; + label = "NAND Writable User area"; + }; + }; +}; + +&soc { + spi@7000 { + flash@0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "spansion,m25p80"; + reg = <0>; + spi-max-frequency = <40000000>; + + partition@0 { + /* 512KB for u-boot Bootloader Image */ + reg = <0x0 0x00080000>; + label = "SPI U-Boot Image"; + read-only; + }; + + partition@80000 { + /* 512KB for DTB Image */ + reg = <0x00080000 0x00080000>; + label = "SPI DTB Image"; + }; + + partition@100000 { + /* 4MB for Linux Kernel Image */ + reg = <0x00100000 0x00400000>; + label = "SPI Linux Kernel Image"; + }; + + partition@500000 { + /* 4MB for Compressed RFS Image */ + reg = <0x00500000 0x00400000>; + label = "SPI Compressed RFS Image"; + }; + + partition@900000 { + /* 7MB for JFFS2 based RFS */ + reg = <0x00900000 0x00700000>; + label = "SPI JFFS2 RFS"; + }; + }; + }; + + i2c@3000 { + rtc@68 { + compatible = "dallas,ds1339"; + reg = <0x68>; + }; + }; + + usb@22000 { + phy_type = "ulpi"; + }; + + usb@23000 { + status = "disabled"; + }; + + mdio@24000 { + phy0: ethernet-phy@0 { + interrupts = <3 1 0 0>; + reg = <0x0>; + }; + phy1: ethernet-phy@1 { + interrupts = <2 1 0 0>; + reg = <0x1>; + }; + phy2: ethernet-phy@2 { + interrupts = <1 1 0 0>; + reg = <0x2>; + }; + }; + + mdio@25000 { + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26000 { + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + ethernet@b0000 { + phy-handle = <&phy2>; + phy-connection-type = "rgmii-id"; + }; + + ethernet@b1000 { + phy-handle = <&phy0>; + tbi-handle = <&tbi0>; + phy-connection-type = "sgmii"; + }; + + ethernet@b2000 { + phy-handle = <&phy1>; + phy-connection-type = "rgmii-id"; + }; +}; diff --git a/arch/powerpc/boot/dts/p1024rdb_32b.dts b/arch/powerpc/boot/dts/p1024rdb_32b.dts new file mode 100644 index 0000000..90e803e --- /dev/null +++ b/arch/powerpc/boot/dts/p1024rdb_32b.dts @@ -0,0 +1,87 @@ +/* + * P1024 RDB 32Bit Physical Address Map Device Tree Source + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/p1020si-pre.dtsi" +/ { + model = "fsl,P1024RDB"; + compatible = "fsl,P1024RDB"; + + memory { + device_type = "memory"; + }; + + lbc: localbus@ffe05000 { + reg = <0x0 0xffe05000 0 0x1000>; + ranges = <0x0 0x0 0x0 0xef000000 0x01000000 + 0x1 0x0 0x0 0xff800000 0x00040000>; + }; + + soc: soc@ffe00000 { + ranges = <0x0 0x0 0xffe00000 0x100000>; + }; + + pci0: pcie@ffe09000 { + reg = <0x0 0xffe09000 0 0x1000>; + ranges = <0x2000000 0x0 0xe0000000 0x0 0xa0000000 0x0 0x20000000 + 0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>; + pcie@0 { + ranges = <0x2000000 0x0 0xe0000000 + 0x2000000 0x0 0xe0000000 + 0x0 0x20000000 + + 0x1000000 0x0 0x0 + 0x1000000 0x0 0x0 + 0x0 0x100000>; + }; + }; + + pci1: pcie@ffe0a000 { + reg = <0x0 0xffe0a000 0 0x1000>; + ranges = <0x2000000 0x0 0xe0000000 0x0 0x80000000 0x0 0x20000000 + 0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>; + pcie@0 { + reg = <0x0 0x0 0x0 0x0 0x0>; + ranges = <0x2000000 0x0 0xe0000000 + 0x2000000 0x0 0xe0000000 + 0x0 0x20000000 + + 0x1000000 0x0 0x0 + 0x1000000 0x0 0x0 + 0x0 0x100000>; + }; + }; +}; + +/include/ "p1024rdb.dtsi" +/include/ "fsl/p1020si-post.dtsi" diff --git a/arch/powerpc/boot/dts/p1024rdb_36b.dts b/arch/powerpc/boot/dts/p1024rdb_36b.dts new file mode 100644 index 0000000..3656825 --- /dev/null +++ b/arch/powerpc/boot/dts/p1024rdb_36b.dts @@ -0,0 +1,87 @@ +/* + * P1024 RDB 36Bit Physical Address Map Device Tree Source + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/include/ "fsl/p1020si-pre.dtsi" +/ { + model = "fsl,P1024RDB"; + compatible = "fsl,P1024RDB"; + + memory { + device_type = "memory"; + }; + + lbc: localbus@fffe05000 { + reg = <0xf 0xffe05000 0 0x1000>; + ranges = <0x0 0x0 0xf 0xef000000 0x01000000 + 0x1 0x0 0xf 0xff800000 0x00040000>; + }; + + soc: soc@fffe00000 { + ranges = <0x0 0xf 0xffe00000 0x100000>; + }; + + pci0: pcie@fffe09000 { + reg = <0xf 0xffe09000 0 0x1000>; + ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000 + 0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>; + pcie@0 { + ranges = <0x2000000 0x0 0xe0000000 + 0x2000000 0x0 0xe0000000 + 0x0 0x20000000 + + 0x1000000 0x0 0x0 + 0x1000000 0x0 0x0 + 0x0 0x100000>; + }; + }; + + pci1: pcie@fffe0a000 { + reg = <0xf 0xffe0a000 0 0x1000>; + ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000 + 0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>; + pcie@0 { + reg = <0x0 0x0 0x0 0x0 0x0>; + ranges = <0x2000000 0x0 0xe0000000 + 0x2000000 0x0 0xe0000000 + 0x0 0x20000000 + + 0x1000000 0x0 0x0 + 0x1000000 0x0 0x0 + 0x0 0x100000>; + }; + }; +}; + +/include/ "p1024rdb.dtsi" +/include/ "fsl/p1020si-post.dtsi" diff --git a/arch/powerpc/boot/dts/p1025rdb.dtsi b/arch/powerpc/boot/dts/p1025rdb.dtsi index cf3676f..f502564 100644 --- a/arch/powerpc/boot/dts/p1025rdb.dtsi +++ b/arch/powerpc/boot/dts/p1025rdb.dtsi @@ -282,5 +282,45 @@ 0x1 0x4 0x2 0x0 0x2 0x0 /* ENET5_RX_DV_SER5_CTS_B */ 0x1 0x8 0x2 0x0 0x2 0x0>; /* ENET5_RX_ER_SER5_CD_B */ }; + + pio3: ucc_pin@03 { + pio-map = < + /* port pin dir open_drain assignment has_irq */ + 0x0 0x16 0x2 0x0 0x2 0x0 /* SER7_CD_B*/ + 0x0 0x12 0x2 0x0 0x2 0x0 /* SER7_CTS_B*/ + 0x0 0x13 0x1 0x0 0x2 0x0 /* SER7_RTS_B*/ + 0x0 0x14 0x2 0x0 0x2 0x0 /* SER7_RXD0*/ + 0x0 0x15 0x1 0x0 0x2 0x0>; /* SER7_TXD0*/ + }; + + pio4: ucc_pin@04 { + pio-map = < + /* port pin dir open_drain assignment has_irq */ + 0x1 0x0 0x2 0x0 0x2 0x0 /* SER3_CD_B*/ + 0x0 0x1c 0x2 0x0 0x2 0x0 /* SER3_CTS_B*/ + 0x0 0x1d 0x1 0x0 0x2 0x0 /* SER3_RTS_B*/ + 0x0 0x1e 0x2 0x0 0x2 0x0 /* SER3_RXD0*/ + 0x0 0x1f 0x1 0x0 0x2 0x0>; /* SER3_TXD0*/ + }; + }; +}; + +&qe { + serial2: ucc@2600 { + device_type = "serial"; + compatible = "ucc_uart"; + port-number = <0>; + rx-clock-name = "brg6"; + tx-clock-name = "brg6"; + pio-handle = <&pio3>; + }; + + serial3: ucc@2200 { + device_type = "serial"; + compatible = "ucc_uart"; + port-number = <1>; + rx-clock-name = "brg2"; + tx-clock-name = "brg2"; + pio-handle = <&pio4>; }; }; diff --git a/arch/powerpc/boot/dts/p2020ds.dtsi b/arch/powerpc/boot/dts/p2020ds.dtsi index d3b939c..e699cf9 100644 --- a/arch/powerpc/boot/dts/p2020ds.dtsi +++ b/arch/powerpc/boot/dts/p2020ds.dtsi @@ -150,6 +150,16 @@ interrupts = <3 1 0 0>; reg = <0x2>; }; + + sgmii_phy1: sgmii-phy@1 { + interrupts = <5 1 0 0>; + reg = <0x1c>; + }; + sgmii_phy2: sgmii-phy@2 { + interrupts = <5 1 0 0>; + reg = <0x1d>; + }; + tbi0: tbi-phy@11 { reg = <0x11>; device_type = "tbi-phy"; diff --git a/arch/powerpc/boot/dts/p2020rdb.dts b/arch/powerpc/boot/dts/p2020rdb.dts index 153bc76..4d52bce 100644 --- a/arch/powerpc/boot/dts/p2020rdb.dts +++ b/arch/powerpc/boot/dts/p2020rdb.dts @@ -34,7 +34,7 @@ /* NOR and NAND Flashes */ ranges = <0x0 0x0 0x0 0xef000000 0x01000000 - 0x1 0x0 0x0 0xff800000 0x00040000 + 0x1 0x0 0x0 0xffa00000 0x00040000 0x2 0x0 0x0 0xffb00000 0x00020000>; nor@0,0 { diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts index 2852139..baab034 100644 --- a/arch/powerpc/boot/dts/p2041rdb.dts +++ b/arch/powerpc/boot/dts/p2041rdb.dts @@ -121,7 +121,8 @@ lbc: localbus@ffe124000 { reg = <0xf 0xfe124000 0 0x1000>; - ranges = <0 0 0xf 0xe8000000 0x08000000>; + ranges = <0 0 0xf 0xe8000000 0x08000000 + 1 0 0xf 0xffa00000 0x00040000>; flash@0,0 { compatible = "cfi-flash"; @@ -129,6 +130,44 @@ bank-width = <2>; device-width = <2>; }; + + nand@1,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,elbc-fcm-nand"; + reg = <0x1 0x0 0x40000>; + + partition@0 { + label = "NAND U-Boot Image"; + reg = <0x0 0x02000000>; + read-only; + }; + + partition@2000000 { + label = "NAND Root File System"; + reg = <0x02000000 0x10000000>; + }; + + partition@12000000 { + label = "NAND Compressed RFS Image"; + reg = <0x12000000 0x08000000>; + }; + + partition@1a000000 { + label = "NAND Linux Kernel Image"; + reg = <0x1a000000 0x04000000>; + }; + + partition@1e000000 { + label = "NAND DTB Image"; + reg = <0x1e000000 0x01000000>; + }; + + partition@1f000000 { + label = "NAND Writable User area"; + reg = <0x1f000000 0x01000000>; + }; + }; }; pci0: pcie@ffe200000 { diff --git a/arch/powerpc/boot/dts/p3060qds.dts b/arch/powerpc/boot/dts/p3060qds.dts deleted file mode 100644 index 9ae875c..0000000 --- a/arch/powerpc/boot/dts/p3060qds.dts +++ /dev/null @@ -1,242 +0,0 @@ -/* - * P3060QDS Device Tree Source - * - * Copyright 2011 Freescale Semiconductor Inc. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * * Neither the name of Freescale Semiconductor nor the - * names of its contributors may be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * - * ALTERNATIVELY, this software may be distributed under the terms of the - * GNU General Public License ("GPL") as published by the Free Software - * Foundation, either version 2 of that License or (at your option) any - * later version. - * - * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY - * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED - * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY - * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; - * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND - * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -/include/ "fsl/p3060si-pre.dtsi" - -/ { - model = "fsl,P3060QDS"; - compatible = "fsl,P3060QDS"; - #address-cells = <2>; - #size-cells = <2>; - interrupt-parent = <&mpic>; - - memory { - device_type = "memory"; - }; - - dcsr: dcsr@f00000000 { - ranges = <0x00000000 0xf 0x00000000 0x01008000>; - }; - - soc: soc@ffe000000 { - ranges = <0x00000000 0xf 0xfe000000 0x1000000>; - reg = <0xf 0xfe000000 0 0x00001000>; - spi@110000 { - flash@0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "spansion,s25sl12801"; - reg = <0>; - spi-max-frequency = <40000000>; /* input clock */ - partition@u-boot { - label = "u-boot"; - reg = <0x00000000 0x00100000>; - read-only; - }; - partition@kernel { - label = "kernel"; - reg = <0x00100000 0x00500000>; - read-only; - }; - partition@dtb { - label = "dtb"; - reg = <0x00600000 0x00100000>; - read-only; - }; - partition@fs { - label = "file system"; - reg = <0x00700000 0x00900000>; - }; - }; - flash@1 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "spansion,en25q32b"; - reg = <1>; - spi-max-frequency = <40000000>; /* input clock */ - partition@spi1 { - label = "spi1"; - reg = <0x00000000 0x00400000>; - }; - }; - flash@2 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "atmel,at45db081d"; - reg = <2>; - spi-max-frequency = <40000000>; /* input clock */ - partition@spi1 { - label = "spi2"; - reg = <0x00000000 0x00100000>; - }; - }; - flash@3 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "spansion,sst25wf040"; - reg = <3>; - spi-max-frequency = <40000000>; /* input clock */ - partition@spi3 { - label = "spi3"; - reg = <0x00000000 0x00080000>; - }; - }; - }; - - i2c@118000 { - eeprom@51 { - compatible = "at24,24c256"; - reg = <0x51>; - }; - eeprom@53 { - compatible = "at24,24c256"; - reg = <0x53>; - }; - rtc@68 { - compatible = "dallas,ds3232"; - reg = <0x68>; - interrupts = <0x1 0x1 0 0>; - }; - }; - - usb0: usb@210000 { - phy_type = "ulpi"; - }; - - usb1: usb@211000 { - dr_mode = "host"; - phy_type = "ulpi"; - }; - }; - - rio: rapidio@ffe0c0000 { - reg = <0xf 0xfe0c0000 0 0x11000>; - - port1 { - ranges = <0 0 0xc 0x20000000 0 0x10000000>; - }; - port2 { - ranges = <0 0 0xc 0x30000000 0 0x10000000>; - }; - }; - - lbc: localbus@ffe124000 { - reg = <0xf 0xfe124000 0 0x1000>; - ranges = <0 0 0xf 0xe8000000 0x08000000 - 2 0 0xf 0xffa00000 0x00040000 - 3 0 0xf 0xffdf0000 0x00008000>; - - flash@0,0 { - compatible = "cfi-flash"; - reg = <0 0 0x08000000>; - bank-width = <2>; - device-width = <2>; - }; - - nand@2,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,elbc-fcm-nand"; - reg = <0x2 0x0 0x40000>; - - partition@0 { - label = "NAND U-Boot Image"; - reg = <0x0 0x02000000>; - read-only; - }; - - partition@2000000 { - label = "NAND Root File System"; - reg = <0x02000000 0x10000000>; - }; - - partition@12000000 { - label = "NAND Compressed RFS Image"; - reg = <0x12000000 0x08000000>; - }; - - partition@1a000000 { - label = "NAND Linux Kernel Image"; - reg = <0x1a000000 0x04000000>; - }; - - partition@1e000000 { - label = "NAND DTB Image"; - reg = <0x1e000000 0x01000000>; - }; - - partition@1f000000 { - label = "NAND Writable User area"; - reg = <0x1f000000 0x21000000>; - }; - }; - - board-control@3,0 { - compatible = "fsl,p3060qds-fpga", "fsl,fpga-qixis"; - reg = <3 0 0x100>; - }; - }; - - pci0: pcie@ffe200000 { - reg = <0xf 0xfe200000 0 0x1000>; - ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000 - 0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>; - pcie@0 { - ranges = <0x02000000 0 0xe0000000 - 0x02000000 0 0xe0000000 - 0 0x20000000 - - 0x01000000 0 0x00000000 - 0x01000000 0 0x00000000 - 0 0x00010000>; - }; - }; - - pci1: pcie@ffe201000 { - reg = <0xf 0xfe201000 0 0x1000>; - ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>; - pcie@0 { - ranges = <0x02000000 0 0xe0000000 - 0x02000000 0 0xe0000000 - 0 0x20000000 - - 0x01000000 0 0x00000000 - 0x01000000 0 0x00000000 - 0 0x00010000>; - }; - }; -}; - -/include/ "fsl/p3060si-post.dtsi" diff --git a/arch/powerpc/boot/dts/sbc8560.dts b/arch/powerpc/boot/dts/sbc8560.dts deleted file mode 100644 index 72078eb..0000000 --- a/arch/powerpc/boot/dts/sbc8560.dts +++ /dev/null @@ -1,406 +0,0 @@ -/* - * SBC8560 Device Tree Source - * - * Copyright 2007 Wind River Systems Inc. - * - * Paul Gortmaker (see MAINTAINERS for contact information) - * - * 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. - */ - -/dts-v1/; - -/ { - model = "SBC8560"; - compatible = "SBC8560"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - ethernet2 = &enet2; - ethernet3 = &enet3; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8560@0 { - device_type = "cpu"; - reg = <0>; - d-cache-line-size = <0x20>; // 32 bytes - i-cache-line-size = <0x20>; // 32 bytes - d-cache-size = <0x8000>; // L1, 32K - i-cache-size = <0x8000>; // L1, 32K - timebase-frequency = <0>; // From uboot - bus-frequency = <0>; - clock-frequency = <0>; - next-level-cache = <&L2>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x20000000>; - }; - - soc@ff700000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - ranges = <0x0 0xff700000 0x00100000>; - clock-frequency = <0>; - - ecm-law@0 { - compatible = "fsl,ecm-law"; - reg = <0x0 0x1000>; - fsl,num-laws = <8>; - }; - - ecm@1000 { - compatible = "fsl,mpc8560-ecm", "fsl,ecm"; - reg = <0x1000 0x1000>; - interrupts = <17 2>; - interrupt-parent = <&mpic>; - }; - - memory-controller@2000 { - compatible = "fsl,mpc8560-memory-controller"; - reg = <0x2000 0x1000>; - interrupt-parent = <&mpic>; - interrupts = <0x12 0x2>; - }; - - L2: l2-cache-controller@20000 { - compatible = "fsl,mpc8560-l2-cache-controller"; - reg = <0x20000 0x1000>; - cache-line-size = <0x20>; // 32 bytes - cache-size = <0x40000>; // L2, 256K - interrupt-parent = <&mpic>; - interrupts = <0x10 0x2>; - }; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <0x2b 0x2>; - interrupt-parent = <&mpic>; - dfsrr; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <0x2b 0x2>; - interrupt-parent = <&mpic>; - dfsrr; - }; - - dma@21300 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8560-dma", "fsl,eloplus-dma"; - reg = <0x21300 0x4>; - ranges = <0x0 0x21100 0x200>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8560-dma-channel", - "fsl,eloplus-dma-channel"; - reg = <0x0 0x80>; - cell-index = <0>; - interrupt-parent = <&mpic>; - interrupts = <20 2>; - }; - dma-channel@80 { - compatible = "fsl,mpc8560-dma-channel", - "fsl,eloplus-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&mpic>; - interrupts = <21 2>; - }; - dma-channel@100 { - compatible = "fsl,mpc8560-dma-channel", - "fsl,eloplus-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&mpic>; - interrupts = <22 2>; - }; - dma-channel@180 { - compatible = "fsl,mpc8560-dma-channel", - "fsl,eloplus-dma-channel"; - reg = <0x180 0x80>; - cell-index = <3>; - interrupt-parent = <&mpic>; - interrupts = <23 2>; - }; - }; - - enet0: ethernet@24000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <0>; - device_type = "network"; - model = "TSEC"; - compatible = "gianfar"; - reg = <0x24000 0x1000>; - ranges = <0x0 0x24000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <0x1d 0x2 0x1e 0x2 0x22 0x2>; - interrupt-parent = <&mpic>; - tbi-handle = <&tbi0>; - phy-handle = <&phy0>; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-mdio"; - reg = <0x520 0x20>; - phy0: ethernet-phy@19 { - interrupt-parent = <&mpic>; - interrupts = <0x6 0x1>; - reg = <0x19>; - device_type = "ethernet-phy"; - }; - phy1: ethernet-phy@1a { - interrupt-parent = <&mpic>; - interrupts = <0x7 0x1>; - reg = <0x1a>; - device_type = "ethernet-phy"; - }; - phy2: ethernet-phy@1b { - interrupt-parent = <&mpic>; - interrupts = <0x8 0x1>; - reg = <0x1b>; - device_type = "ethernet-phy"; - }; - phy3: ethernet-phy@1c { - interrupt-parent = <&mpic>; - interrupts = <0x8 0x1>; - reg = <0x1c>; - device_type = "ethernet-phy"; - }; - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - enet1: ethernet@25000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - device_type = "network"; - model = "TSEC"; - compatible = "gianfar"; - reg = <0x25000 0x1000>; - ranges = <0x0 0x25000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <0x23 0x2 0x24 0x2 0x28 0x2>; - interrupt-parent = <&mpic>; - tbi-handle = <&tbi1>; - phy-handle = <&phy1>; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-tbi"; - reg = <0x520 0x20>; - - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - mpic: pic@40000 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - compatible = "chrp,open-pic"; - reg = <0x40000 0x40000>; - device_type = "open-pic"; - }; - - cpm@919c0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8560-cpm", "fsl,cpm2"; - reg = <0x919c0 0x30>; - ranges; - - muram@80000 { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x80000 0x10000>; - - data@0 { - compatible = "fsl,cpm-muram-data"; - reg = <0x0 0x4000 0x9000 0x2000>; - }; - }; - - brg@919f0 { - compatible = "fsl,mpc8560-brg", - "fsl,cpm2-brg", - "fsl,cpm-brg"; - reg = <0x919f0 0x10 0x915f0 0x10>; - clock-frequency = <165000000>; - }; - - cpmpic: pic@90c00 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - interrupts = <0x2e 0x2>; - interrupt-parent = <&mpic>; - reg = <0x90c00 0x80>; - compatible = "fsl,mpc8560-cpm-pic", "fsl,cpm2-pic"; - }; - - enet2: ethernet@91320 { - device_type = "network"; - compatible = "fsl,mpc8560-fcc-enet", - "fsl,cpm2-fcc-enet"; - reg = <0x91320 0x20 0x88500 0x100 0x913b0 0x1>; - local-mac-address = [ 00 00 00 00 00 00 ]; - fsl,cpm-command = <0x16200300>; - interrupts = <0x21 0x8>; - interrupt-parent = <&cpmpic>; - phy-handle = <&phy2>; - }; - - enet3: ethernet@91340 { - device_type = "network"; - compatible = "fsl,mpc8560-fcc-enet", - "fsl,cpm2-fcc-enet"; - reg = <0x91340 0x20 0x88600 0x100 0x913d0 0x1>; - local-mac-address = [ 00 00 00 00 00 00 ]; - fsl,cpm-command = <0x1a400300>; - interrupts = <0x22 0x8>; - interrupt-parent = <&cpmpic>; - phy-handle = <&phy3>; - }; - }; - - global-utilities@e0000 { - compatible = "fsl,mpc8560-guts"; - reg = <0xe0000 0x1000>; - }; - }; - - pci0: pci@ff708000 { - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci"; - device_type = "pci"; - reg = <0xff708000 0x1000>; - clock-frequency = <66666666>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x02 */ - 0x1000 0x0 0x0 0x1 &mpic 0x2 0x1 - 0x1000 0x0 0x0 0x2 &mpic 0x3 0x1 - 0x1000 0x0 0x0 0x3 &mpic 0x4 0x1 - 0x1000 0x0 0x0 0x4 &mpic 0x5 0x1>; - - interrupt-parent = <&mpic>; - interrupts = <0x18 0x2>; - bus-range = <0x0 0x0>; - ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>; - }; - - localbus@ff705000 { - compatible = "fsl,mpc8560-localbus", "simple-bus"; - #address-cells = <2>; - #size-cells = <1>; - reg = <0xff705000 0x100>; // BRx, ORx, etc. - - ranges = < - 0x0 0x0 0xff800000 0x0800000 // 8MB boot flash - 0x1 0x0 0xe4000000 0x4000000 // 64MB flash - 0x3 0x0 0x20000000 0x4000000 // 64MB SDRAM - 0x4 0x0 0x24000000 0x4000000 // 64MB SDRAM - 0x5 0x0 0xfc000000 0x0c00000 // EPLD - 0x6 0x0 0xe0000000 0x4000000 // 64MB flash - 0x7 0x0 0x80000000 0x0200000 // ATM1,2 - >; - - epld@5,0 { - compatible = "wrs,epld-localbus"; - #address-cells = <2>; - #size-cells = <1>; - reg = <0x5 0x0 0xc00000>; - ranges = < - 0x0 0x0 0x5 0x000000 0x1fff // LED disp. - 0x1 0x0 0x5 0x100000 0x1fff // switches - 0x2 0x0 0x5 0x200000 0x1fff // ID reg. - 0x3 0x0 0x5 0x300000 0x1fff // status reg. - 0x4 0x0 0x5 0x400000 0x1fff // reset reg. - 0x5 0x0 0x5 0x500000 0x1fff // Wind port - 0x7 0x0 0x5 0x700000 0x1fff // UART #1 - 0x8 0x0 0x5 0x800000 0x1fff // UART #2 - 0x9 0x0 0x5 0x900000 0x1fff // RTC - 0xb 0x0 0x5 0xb00000 0x1fff // EEPROM - >; - - bidr@2,0 { - compatible = "wrs,sbc8560-bidr"; - reg = <0x2 0x0 0x10>; - }; - - bcsr@3,0 { - compatible = "wrs,sbc8560-bcsr"; - reg = <0x3 0x0 0x10>; - }; - - brstcr@4,0 { - compatible = "wrs,sbc8560-brstcr"; - reg = <0x4 0x0 0x10>; - }; - - serial0: serial@7,0 { - device_type = "serial"; - compatible = "ns16550"; - reg = <0x7 0x0 0x100>; - clock-frequency = <1843200>; - interrupts = <0x9 0x2>; - interrupt-parent = <&mpic>; - }; - - serial1: serial@8,0 { - device_type = "serial"; - compatible = "ns16550"; - reg = <0x8 0x0 0x100>; - clock-frequency = <1843200>; - interrupts = <0xa 0x2>; - interrupt-parent = <&mpic>; - }; - - rtc@9,0 { - compatible = "m48t59"; - reg = <0x9 0x0 0x1fff>; - }; - }; - }; -}; diff --git a/arch/powerpc/boot/flatdevtree_env.h b/arch/powerpc/boot/flatdevtree_env.h deleted file mode 100644 index 66e0ebb..0000000 --- a/arch/powerpc/boot/flatdevtree_env.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * This file adds the header file glue so that the shared files - * flatdevicetree.[ch] can compile and work in the powerpc bootwrapper. - * - * strncmp & strchr copied from <file:lib/string.c> - * Copyright (C) 1991, 1992 Linus Torvalds - * - * Maintained by: Mark A. Greer <mgreer@mvista.com> - */ -#ifndef _PPC_BOOT_FLATDEVTREE_ENV_H_ -#define _PPC_BOOT_FLATDEVTREE_ENV_H_ - -#include <stdarg.h> -#include <stddef.h> -#include "types.h" -#include "string.h" -#include "stdio.h" -#include "ops.h" - -#define be16_to_cpu(x) (x) -#define cpu_to_be16(x) (x) -#define be32_to_cpu(x) (x) -#define cpu_to_be32(x) (x) -#define be64_to_cpu(x) (x) -#define cpu_to_be64(x) (x) - -#endif /* _PPC_BOOT_FLATDEVTREE_ENV_H_ */ diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig index 07e1bba..a0dfef1 100644 --- a/arch/powerpc/configs/83xx/kmeter1_defconfig +++ b/arch/powerpc/configs/83xx/kmeter1_defconfig @@ -2,14 +2,14 @@ CONFIG_EXPERIMENTAL=y # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_SPARSE_IRQ=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_EXPERT=y -# CONFIG_HOTPLUG is not set CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +# CONFIG_MSDOS_PARTITION is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set # CONFIG_PPC_CHRP is not set @@ -31,11 +31,10 @@ CONFIG_IP_PNP=y # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set +CONFIG_TIPC=y CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=y CONFIG_MTD=y -CONFIG_MTD_CONCAT=y -CONFIG_MTD_PARTITIONS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y @@ -50,17 +49,15 @@ CONFIG_MTD_UBI_DEBUG=y CONFIG_PROC_DEVICETREE=y CONFIG_NETDEVICES=y CONFIG_DUMMY=y -CONFIG_TUN=y CONFIG_MII=y -CONFIG_MARVELL_PHY=y -CONFIG_NET_ETHERNET=y +CONFIG_TUN=y CONFIG_UCC_GETH=y -# CONFIG_NETDEV_10000 is not set -CONFIG_WAN=y -CONFIG_HDLC=y +CONFIG_MARVELL_PHY=y CONFIG_PPP=y CONFIG_PPP_MULTILINK=y CONFIG_PPPOE=y +CONFIG_WAN=y +CONFIG_HDLC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set @@ -77,10 +74,7 @@ CONFIG_UIO=y # CONFIG_DNOTIFY is not set CONFIG_TMPFS=y CONFIG_JFFS2_FS=y +CONFIG_UBIFS_FS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -# CONFIG_MSDOS_PARTITION is not set -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y diff --git a/arch/powerpc/configs/85xx/sbc8560_defconfig b/arch/powerpc/configs/85xx/sbc8560_defconfig deleted file mode 100644 index f7fdb03..0000000 --- a/arch/powerpc/configs/85xx/sbc8560_defconfig +++ /dev/null @@ -1,65 +0,0 @@ -CONFIG_PPC_85xx=y -CONFIG_EXPERIMENTAL=y -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_EXPERT=y -CONFIG_SLAB=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_SBC8560=y -CONFIG_BINFMT_MISC=y -CONFIG_SPARSE_IRQ=y -# CONFIG_SECCOMP is not set -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_INET_LRO is not set -# CONFIG_IPV6 is not set -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -# CONFIG_FW_LOADER is not set -CONFIG_PROC_DEVICETREE=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_NETDEVICES=y -CONFIG_BROADCOM_PHY=y -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -CONFIG_GIANFAR=y -# CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_8250_NR_UARTS=2 -CONFIG_SERIAL_8250_RUNTIME_UARTS=2 -# CONFIG_HW_RANDOM is not set -CONFIG_VIDEO_OUTPUT_CONTROL=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_M48T59=y -CONFIG_INOTIFY=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -# CONFIG_MSDOS_PARTITION is not set -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_DEBUG_MUTEXES=y -# CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y -CONFIG_PPC_EARLY_DEBUG=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig index 91db656..cbb98c1 100644 --- a/arch/powerpc/configs/corenet32_smp_defconfig +++ b/arch/powerpc/configs/corenet32_smp_defconfig @@ -23,7 +23,6 @@ CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set CONFIG_P2041_RDB=y CONFIG_P3041_DS=y -CONFIG_P3060_QDS=y CONFIG_P4080_DS=y CONFIG_P5020_DS=y CONFIG_HIGHMEM=y @@ -32,10 +31,12 @@ CONFIG_HIGH_RES_TIMERS=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_KEXEC=y +CONFIG_IRQ_ALL_CPUS=y CONFIG_FORCE_MAX_ZONEORDER=13 CONFIG_FSL_LBC=y CONFIG_PCI=y CONFIG_PCIEPORTBUS=y +CONFIG_PCI_MSI=y # CONFIG_PCIEASPM is not set CONFIG_RAPIDIO=y CONFIG_FSL_RIO=y @@ -76,6 +77,11 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_ECC=y +CONFIG_MTD_NAND_IDS=y +CONFIG_MTD_NAND_FSL_IFC=y +CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y @@ -136,6 +142,8 @@ CONFIG_USB_OHCI_HCD_PPC_OF_LE=y CONFIG_USB_STORAGE=y CONFIG_MMC=y CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_OF=y +CONFIG_MMC_SDHCI_OF_ESDHC=y CONFIG_EDAC=y CONFIG_EDAC_MM_EDAC=y CONFIG_EDAC_MPC85XX=y diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig index 6798343..dd89de8 100644 --- a/arch/powerpc/configs/corenet64_smp_defconfig +++ b/arch/powerpc/configs/corenet64_smp_defconfig @@ -6,7 +6,9 @@ CONFIG_NR_CPUS=2 CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y -CONFIG_SPARSE_IRQ=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -18,11 +20,14 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y CONFIG_P5020_DS=y # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_BINFMT_MISC=m +CONFIG_IRQ_ALL_CPUS=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_MSI=y CONFIG_RAPIDIO=y CONFIG_FSL_RIO=y CONFIG_NET=y @@ -51,12 +56,25 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_M25P80=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_FSL_ELBC=y +CONFIG_MTD_NAND_FSL_IFC=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_MISC_DEVICES=y CONFIG_EEPROM_LEGACY=y +CONFIG_ATA=y +CONFIG_SATA_FSL=y +CONFIG_SATA_SIL24=y CONFIG_NETDEVICES=y CONFIG_DUMMY=y CONFIG_INPUT_FF_MEMLESS=m @@ -66,39 +84,59 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_SERIO_LIBPS2=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y +CONFIG_SPI=y +CONFIG_SPI_GPIO=y +CONFIG_SPI_FSL_SPI=y +CONFIG_SPI_FSL_ESPI=y # CONFIG_HWMON is not set CONFIG_VIDEO_OUTPUT_CONTROL=y -# CONFIG_HID_SUPPORT is not set -# CONFIG_USB_SUPPORT is not set +CONFIG_USB_HID=m +CONFIG_USB=y +CONFIG_USB_MON=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_FSL=y +CONFIG_USB_STORAGE=y +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_EDAC=y +CONFIG_EDAC_MM_EDAC=y CONFIG_DMADEVICES=y CONFIG_FSL_DMA=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_ISO9660_FS=m +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_UDF_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=y +CONFIG_NTFS_FS=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y # CONFIG_MISC_FILESYSTEMS is not set -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y -CONFIG_NLS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V4=y +CONFIG_ROOT_NFS=y +CONFIG_NFSD=m +CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=m CONFIG_CRC_T10DIF=y -CONFIG_CRC_ITU_T=m CONFIG_FRAME_WARN=1024 +CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y +CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y -CONFIG_SYSCTL_SYSCALL_CHECK=y -CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_PCBC=m +CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_AES=y diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig index 0d36b0e..8fa84f1 100644 --- a/arch/powerpc/configs/mgcoge_defconfig +++ b/arch/powerpc/configs/mgcoge_defconfig @@ -2,7 +2,6 @@ CONFIG_EXPERIMENTAL=y # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_SPARSE_IRQ=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -12,6 +11,7 @@ CONFIG_KALLSYMS_ALL=y # CONFIG_PCSPKR_PLATFORM is not set CONFIG_EMBEDDED=y CONFIG_SLAB=y +CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set # CONFIG_PPC_PMAC is not set CONFIG_PPC_82xx=y @@ -49,12 +49,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_NETDEVICES=y -CONFIG_FIXED_PHY=y -CONFIG_NET_ETHERNET=y CONFIG_FS_ENET=y CONFIG_FS_ENET_MDIO_FCC=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set +CONFIG_FIXED_PHY=y # CONFIG_WLAN is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set @@ -64,6 +61,8 @@ CONFIG_SERIAL_CPM_CONSOLE=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_CPM=y +CONFIG_SPI=y +CONFIG_SPI_FSL_SPI=y # CONFIG_HWMON is not set CONFIG_USB_GADGET=y CONFIG_USB_FSL_USB2=y @@ -80,8 +79,6 @@ CONFIG_SQUASHFS=y CONFIG_NFS_FS=y CONFIG_NFS_V3=y CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_NLS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y @@ -90,7 +87,6 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y # CONFIG_SCHED_DEBUG is not set CONFIG_DEBUG_INFO=y -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_BDI_SWITCH=y CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index 62bb723..03ee911c 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -74,6 +74,30 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_FTL=y +CONFIG_MTD_GEN_PROBE=y +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_CFI_UTIL=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_OF_PARTS=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_FSL_ELBC=y +CONFIG_MTD_NAND_FSL_IFC=y +CONFIG_MTD_NAND_IDS=y +CONFIG_MTD_NAND_ECC=y +CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index d182842..fdfa84d 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -46,6 +46,7 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y +CONFIG_IRQ_ALL_CPUS=y CONFIG_FORCE_MAX_ZONEORDER=12 CONFIG_PCI=y CONFIG_PCI_MSI=y @@ -76,6 +77,30 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_CHAR=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_FTL=y +CONFIG_MTD_GEN_PROBE=y +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_MTD_CFI_UTIL=y +CONFIG_MTD_PHYSMAP_OF=y +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_OF_PARTS=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_FSL_ELBC=y +CONFIG_MTD_NAND_FSL_IFC=y +CONFIG_MTD_NAND_IDS=y +CONFIG_MTD_NAND_ECC=y +CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index c1442a3..f2fe0c2 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -16,6 +16,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y @@ -489,3 +490,4 @@ CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=y CONFIG_VHOST_NET=m +CONFIG_BPF_JIT=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 6608232..187fb8d 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -24,6 +24,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 5d7fbe1..6e82f5f 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -29,7 +29,7 @@ #define PPC_LLARX(t, a, b, eh) PPC_LDARX(t, a, b, eh) #define PPC_STLCX stringify_in_c(stdcx.) #define PPC_CNTLZL stringify_in_c(cntlzd) -#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), (RS)) +#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS) #define PPC_LR_STKOFF 16 #define PPC_MIN_STKFRM 112 #else /* 32-bit */ diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 37c32aba..a6f8c7a 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -26,8 +26,8 @@ unsigned int create_branch(const unsigned int *addr, unsigned long target, int flags); unsigned int create_cond_branch(const unsigned int *addr, unsigned long target, int flags); -void patch_branch(unsigned int *addr, unsigned long target, int flags); -void patch_instruction(unsigned int *addr, unsigned int instr); +int patch_branch(unsigned int *addr, unsigned long target, int flags); +int patch_instruction(unsigned int *addr, unsigned int instr); int instr_is_relative_branch(unsigned int instr); int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 63d5ca4..77e97dd 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -34,6 +34,9 @@ struct dev_archdata { #ifdef CONFIG_EEH struct eeh_dev *edev; #endif +#ifdef CONFIG_FAIL_IOMMU + int fail_iommu; +#endif }; struct pdev_archdata { diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h index 976835d..bf2c06c 100644 --- a/arch/powerpc/include/asm/epapr_hcalls.h +++ b/arch/powerpc/include/asm/epapr_hcalls.h @@ -153,6 +153,8 @@ #define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5" #define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4" +extern bool epapr_paravirt_enabled; +extern u32 epapr_hypercall_start[]; /* * We use "uintptr_t" to define a register because it's guaranteed to be a diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index d58fc4e..a43c147 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -293,7 +293,7 @@ label##_hv: \ #define RUNLATCH_ON \ BEGIN_FTR_SECTION \ - clrrdi r3,r1,THREAD_SHIFT; \ + CURRENT_THREAD_INFO(r3, r1); \ ld r4,TI_LOCAL_FLAGS(r3); \ andi. r0,r4,_TLF_RUNLATCH; \ beql ppc64_runlatch_on_trampoline; \ @@ -332,7 +332,7 @@ label##_common: \ #ifdef CONFIG_PPC_970_NAP #define FINISH_NAP \ BEGIN_FTR_SECTION \ - clrrdi r11,r1,THREAD_SHIFT; \ + CURRENT_THREAD_INFO(r11, r1); \ ld r9,TI_LOCAL_FLAGS(r11); \ andi. r10,r9,_TLF_NAPPING; \ bnel power4_fixup_nap; \ diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 0554ab0..e45c494 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -34,6 +34,8 @@ extern void __replay_interrupt(unsigned int vector); extern void timer_interrupt(struct pt_regs *); extern void performance_monitor_exception(struct pt_regs *regs); +extern void WatchdogException(struct pt_regs *regs); +extern void unknown_exception(struct pt_regs *regs); #ifdef CONFIG_PPC64 #include <asm/paca.h> diff --git a/arch/powerpc/include/asm/immap_qe.h b/arch/powerpc/include/asm/immap_qe.h index 0edb684..61e8490 100644 --- a/arch/powerpc/include/asm/immap_qe.h +++ b/arch/powerpc/include/asm/immap_qe.h @@ -26,7 +26,9 @@ struct qe_iram { __be32 iadd; /* I-RAM Address Register */ __be32 idata; /* I-RAM Data Register */ - u8 res0[0x78]; + u8 res0[0x04]; + __be32 iready; /* I-RAM Ready Register */ + u8 res1[0x70]; } __attribute__ ((packed)); /* QE Interrupt Controller */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index a3855b8..f94ef42 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -20,6 +20,14 @@ extern int check_legacy_ioport(unsigned long base_port); #define _PNPWRP 0xa79 #define PNPBIOS_BASE 0xf000 +#if defined(CONFIG_PPC64) && defined(CONFIG_PCI) +extern struct pci_dev *isa_bridge_pcidev; +/* + * has legacy ISA devices ? + */ +#define arch_has_dev_port() (isa_bridge_pcidev != NULL) +#endif + #include <linux/device.h> #include <linux/io.h> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 957a83f..cbfe678 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -53,6 +53,16 @@ static __inline__ __attribute_const__ int get_iommu_order(unsigned long size) */ #define IOMAP_MAX_ORDER 13 +#define IOMMU_POOL_HASHBITS 2 +#define IOMMU_NR_POOLS (1 << IOMMU_POOL_HASHBITS) + +struct iommu_pool { + unsigned long start; + unsigned long end; + unsigned long hint; + spinlock_t lock; +} ____cacheline_aligned_in_smp; + struct iommu_table { unsigned long it_busno; /* Bus number this table belongs to */ unsigned long it_size; /* Size of iommu table in entries */ @@ -61,10 +71,10 @@ struct iommu_table { unsigned long it_index; /* which iommu table this is */ unsigned long it_type; /* type: PCI or Virtual Bus */ unsigned long it_blocksize; /* Entries in each block (cacheline) */ - unsigned long it_hint; /* Hint for next alloc */ - unsigned long it_largehint; /* Hint for large allocs */ - unsigned long it_halfpoint; /* Breaking point for small/large allocs */ - spinlock_t it_lock; /* Protects it_map */ + unsigned long poolsize; + unsigned long nr_pools; + struct iommu_pool large_pool; + struct iommu_pool pools[IOMMU_NR_POOLS]; unsigned long *it_map; /* A simple allocation bitmap for now */ }; diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index b0c08b1..0dd1d86 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -36,11 +36,8 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) #define SPAPR_TCE_SHIFT 12 #ifdef CONFIG_KVM_BOOK3S_64_HV -/* For now use fixed-size 16MB page table */ -#define HPT_ORDER 24 -#define HPT_NPTEG (1ul << (HPT_ORDER - 7)) /* 128B per pteg */ -#define HPT_NPTE (HPT_NPTEG << 3) /* 8 PTEs per PTEG */ -#define HPT_HASH_MASK (HPT_NPTEG - 1) +#define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ +extern int kvm_hpt_order; /* order of preallocated HPTs */ #endif #define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 88609b2..bfcd00c 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -74,6 +74,7 @@ struct kvmppc_host_state { ulong vmhandler; ulong scratch0; ulong scratch1; + ulong sprg3; u8 in_guest; u8 restore_hid5; u8 napping; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index d848cdc..50ea12f 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -237,6 +237,10 @@ struct kvm_arch { unsigned long vrma_slb_v; int rma_setup_done; int using_mmu_notifiers; + u32 hpt_order; + atomic_t vcpus_running; + unsigned long hpt_npte; + unsigned long hpt_mask; spinlock_t slot_phys_lock; unsigned long *slot_phys[KVM_MEM_SLOTS_NUM]; int slot_npages[KVM_MEM_SLOTS_NUM]; @@ -414,7 +418,9 @@ struct kvm_vcpu_arch { ulong mcsrr1; ulong mcsr; u32 dec; +#ifdef CONFIG_BOOKE u32 decar; +#endif u32 tbl; u32 tbu; u32 tcr; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index f68c22f..0124937 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -119,7 +119,8 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu); extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu); extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); -extern long kvmppc_alloc_hpt(struct kvm *kvm); +extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp); +extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp); extern void kvmppc_free_hpt(struct kvm *kvm); extern long kvmppc_prepare_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem); diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index f014552..e8a26db 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -163,12 +163,7 @@ extern u64 ppc64_rma_size; * to think about, feedback welcome. --BenH. */ -/* There are #define as they have to be used in assembly - * - * WARNING: If you change this list, make sure to update the array of - * names currently in arch/powerpc/mm/hugetlbpage.c or bad things will - * happen - */ +/* These are #defines as they have to be used in assembly */ #define MMU_PAGE_4K 0 #define MMU_PAGE_16K 1 #define MMU_PAGE_64K 2 diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index ac39e6a..8cccbee 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -30,6 +30,7 @@ struct pci_controller { int first_busno; int last_busno; int self_busno; + struct resource busn; void __iomem *io_base_virt; #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 5c16b89..0bb2372 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -26,8 +26,13 @@ #include <asm/ptrace.h> #include <asm/reg.h> +/* + * Overload regs->result to specify whether we should use the MSR (result + * is zero) or the SIAR (result is non zero). + */ #define perf_arch_fetch_caller_regs(regs, __ip) \ do { \ + (regs)->result = 0; \ (regs)->nip = __ip; \ (regs)->gpr[1] = *(unsigned long *)__get_SP(); \ asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index d81f994..4c25319 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -15,6 +15,72 @@ #include <linux/stringify.h> #include <asm/asm-compat.h> +#define __REG_R0 0 +#define __REG_R1 1 +#define __REG_R2 2 +#define __REG_R3 3 +#define __REG_R4 4 +#define __REG_R5 5 +#define __REG_R6 6 +#define __REG_R7 7 +#define __REG_R8 8 +#define __REG_R9 9 +#define __REG_R10 10 +#define __REG_R11 11 +#define __REG_R12 12 +#define __REG_R13 13 +#define __REG_R14 14 +#define __REG_R15 15 +#define __REG_R16 16 +#define __REG_R17 17 +#define __REG_R18 18 +#define __REG_R19 19 +#define __REG_R20 20 +#define __REG_R21 21 +#define __REG_R22 22 +#define __REG_R23 23 +#define __REG_R24 24 +#define __REG_R25 25 +#define __REG_R26 26 +#define __REG_R27 27 +#define __REG_R28 28 +#define __REG_R29 29 +#define __REG_R30 30 +#define __REG_R31 31 + +#define __REGA0_0 0 +#define __REGA0_R1 1 +#define __REGA0_R2 2 +#define __REGA0_R3 3 +#define __REGA0_R4 4 +#define __REGA0_R5 5 +#define __REGA0_R6 6 +#define __REGA0_R7 7 +#define __REGA0_R8 8 +#define __REGA0_R9 9 +#define __REGA0_R10 10 +#define __REGA0_R11 11 +#define __REGA0_R12 12 +#define __REGA0_R13 13 +#define __REGA0_R14 14 +#define __REGA0_R15 15 +#define __REGA0_R16 16 +#define __REGA0_R17 17 +#define __REGA0_R18 18 +#define __REGA0_R19 19 +#define __REGA0_R20 20 +#define __REGA0_R21 21 +#define __REGA0_R22 22 +#define __REGA0_R23 23 +#define __REGA0_R24 24 +#define __REGA0_R25 25 +#define __REGA0_R26 26 +#define __REGA0_R27 27 +#define __REGA0_R28 28 +#define __REGA0_R29 29 +#define __REGA0_R30 30 +#define __REGA0_R31 31 + /* sorted alphabetically */ #define PPC_INST_DCBA 0x7c0005ec #define PPC_INST_DCBA_MASK 0xfc0007fe @@ -107,12 +173,19 @@ #define PPC_INST_NEG 0x7c0000d0 #define PPC_INST_BRANCH 0x48000000 #define PPC_INST_BRANCH_COND 0x40800000 +#define PPC_INST_LBZCIX 0x7c0006aa +#define PPC_INST_STBCIX 0x7c0007aa /* macros to insert fields into opcodes */ -#define __PPC_RA(a) (((a) & 0x1f) << 16) -#define __PPC_RB(b) (((b) & 0x1f) << 11) -#define __PPC_RS(s) (((s) & 0x1f) << 21) -#define __PPC_RT(s) __PPC_RS(s) +#define ___PPC_RA(a) (((a) & 0x1f) << 16) +#define ___PPC_RB(b) (((b) & 0x1f) << 11) +#define ___PPC_RS(s) (((s) & 0x1f) << 21) +#define ___PPC_RT(t) ___PPC_RS(t) +#define __PPC_RA(a) ___PPC_RA(__REG_##a) +#define __PPC_RA0(a) ___PPC_RA(__REGA0_##a) +#define __PPC_RB(b) ___PPC_RB(__REG_##b) +#define __PPC_RS(s) ___PPC_RS(__REG_##s) +#define __PPC_RT(t) ___PPC_RT(__REG_##t) #define __PPC_XA(a) ((((a) & 0x1f) << 16) | (((a) & 0x20) >> 3)) #define __PPC_XB(b) ((((b) & 0x1f) << 11) | (((b) & 0x20) >> 4)) #define __PPC_XS(s) ((((s) & 0x1f) << 21) | (((s) & 0x20) >> 5)) @@ -141,13 +214,13 @@ #define PPC_DCBZL(a, b) stringify_in_c(.long PPC_INST_DCBZL | \ __PPC_RA(a) | __PPC_RB(b)) #define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \ - __PPC_RT(t) | __PPC_RA(a) | \ - __PPC_RB(b) | __PPC_EH(eh)) + ___PPC_RT(t) | ___PPC_RA(a) | \ + ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \ - __PPC_RT(t) | __PPC_RA(a) | \ - __PPC_RB(b) | __PPC_EH(eh)) + ___PPC_RT(t) | ___PPC_RA(a) | \ + ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ - __PPC_RB(b)) + ___PPC_RB(b)) #define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ __PPC_RA(a) | __PPC_RS(s)) #define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_INST_POPCNTD | \ @@ -158,34 +231,39 @@ #define PPC_RFDI stringify_in_c(.long PPC_INST_RFDI) #define PPC_RFMCI stringify_in_c(.long PPC_INST_RFMCI) #define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_INST_TLBILX | \ - __PPC_T_TLB(t) | __PPC_RA(a) | __PPC_RB(b)) + __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) #define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b) #define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b) #define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b) #define PPC_WAIT(w) stringify_in_c(.long PPC_INST_WAIT | \ __PPC_WC(w)) #define PPC_TLBIE(lp,a) stringify_in_c(.long PPC_INST_TLBIE | \ - __PPC_RB(a) | __PPC_RS(lp)) + ___PPC_RB(a) | ___PPC_RS(lp)) #define PPC_TLBSRX_DOT(a,b) stringify_in_c(.long PPC_INST_TLBSRX_DOT | \ - __PPC_RA(a) | __PPC_RB(b)) + __PPC_RA0(a) | __PPC_RB(b)) #define PPC_TLBIVAX(a,b) stringify_in_c(.long PPC_INST_TLBIVAX | \ - __PPC_RA(a) | __PPC_RB(b)) + __PPC_RA0(a) | __PPC_RB(b)) #define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_INST_ERATWE | \ __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) #define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_INST_ERATRE | \ __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) #define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_INST_ERATILX | \ - __PPC_T_TLB(t) | __PPC_RA(a) | \ + __PPC_T_TLB(t) | __PPC_RA0(a) | \ __PPC_RB(b)) #define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_INST_ERATIVAX | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) + __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b)) #define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_INST_ERATSX | \ - __PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b)) + __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) #define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_INST_ERATSX_DOT | \ - __PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b)) + __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) #define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ __PPC_RT(t) | __PPC_RB(b)) +/* PASemi instructions */ +#define LBZCIX(t,a,b) stringify_in_c(.long PPC_INST_LBZCIX | \ + __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)) +#define STBCIX(s,a,b) stringify_in_c(.long PPC_INST_STBCIX | \ + __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) /* * Define what the VSX XX1 form instructions will look like, then add @@ -194,11 +272,11 @@ #define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b)) #define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b)) #define STXVD2X(s, a, b) stringify_in_c(.long PPC_INST_STXVD2X | \ - VSX_XX1((s), (a), (b))) + VSX_XX1((s), a, b)) #define LXVD2X(s, a, b) stringify_in_c(.long PPC_INST_LXVD2X | \ - VSX_XX1((s), (a), (b))) + VSX_XX1((s), a, b)) #define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ - VSX_XX3((t), (a), (b))) + VSX_XX3((t), a, b)) #define PPC_NAP stringify_in_c(.long PPC_INST_NAP) #define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 1544420..ea2a86e 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -126,26 +126,26 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base) /* Save the lower 32 VSRs in the thread VSR region */ -#define SAVE_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); STXVD2X(n,base,b) +#define SAVE_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); STXVD2X(n,R##base,R##b) #define SAVE_2VSRS(n,b,base) SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base) #define SAVE_4VSRS(n,b,base) SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base) #define SAVE_8VSRS(n,b,base) SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base) #define SAVE_16VSRS(n,b,base) SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base) #define SAVE_32VSRS(n,b,base) SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base) -#define REST_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); LXVD2X(n,base,b) +#define REST_VSR(n,b,base) li b,THREAD_VSR0+(16*(n)); LXVD2X(n,R##base,R##b) #define REST_2VSRS(n,b,base) REST_VSR(n,b,base); REST_VSR(n+1,b,base) #define REST_4VSRS(n,b,base) REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base) #define REST_8VSRS(n,b,base) REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base) #define REST_16VSRS(n,b,base) REST_8VSRS(n,b,base); REST_8VSRS(n+8,b,base) #define REST_32VSRS(n,b,base) REST_16VSRS(n,b,base); REST_16VSRS(n+16,b,base) /* Save the upper 32 VSRs (32-63) in the thread VSX region (0-31) */ -#define SAVE_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); STXVD2X(n+32,base,b) +#define SAVE_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); STXVD2X(n+32,R##base,R##b) #define SAVE_2VSRSU(n,b,base) SAVE_VSRU(n,b,base); SAVE_VSRU(n+1,b,base) #define SAVE_4VSRSU(n,b,base) SAVE_2VSRSU(n,b,base); SAVE_2VSRSU(n+2,b,base) #define SAVE_8VSRSU(n,b,base) SAVE_4VSRSU(n,b,base); SAVE_4VSRSU(n+4,b,base) #define SAVE_16VSRSU(n,b,base) SAVE_8VSRSU(n,b,base); SAVE_8VSRSU(n+8,b,base) #define SAVE_32VSRSU(n,b,base) SAVE_16VSRSU(n,b,base); SAVE_16VSRSU(n+16,b,base) -#define REST_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,base,b) +#define REST_VSRU(n,b,base) li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,R##base,R##b) #define REST_2VSRSU(n,b,base) REST_VSRU(n,b,base); REST_VSRU(n+1,b,base) #define REST_4VSRSU(n,b,base) REST_2VSRSU(n,b,base); REST_2VSRSU(n+2,b,base) #define REST_8VSRSU(n,b,base) REST_4VSRSU(n,b,base); REST_4VSRSU(n+4,b,base) @@ -178,9 +178,24 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) #define HMT_HIGH or 3,3,3 #define HMT_EXTRA_HIGH or 7,7,7 # power7 only +#ifdef CONFIG_PPC64 +#define ULONG_SIZE 8 +#else +#define ULONG_SIZE 4 +#endif +#define __VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) +#define VCPU_GPR(n) __VCPU_GPR(__REG_##n) + #ifdef __KERNEL__ #ifdef CONFIG_PPC64 +#define STACKFRAMESIZE 256 +#define __STK_REG(i) (112 + ((i)-14)*8) +#define STK_REG(i) __STK_REG(__REG_##i) + +#define __STK_PARAM(i) (48 + ((i)-3)*8) +#define STK_PARAM(i) __STK_PARAM(__REG_##i) + #define XGLUE(a,b) a##b #define GLUE(a,b) XGLUE(a,b) @@ -295,14 +310,14 @@ n: */ #ifdef __powerpc64__ #define LOAD_REG_IMMEDIATE(reg,expr) \ - lis (reg),(expr)@highest; \ - ori (reg),(reg),(expr)@higher; \ - rldicr (reg),(reg),32,31; \ - oris (reg),(reg),(expr)@h; \ - ori (reg),(reg),(expr)@l; + lis reg,(expr)@highest; \ + ori reg,reg,(expr)@higher; \ + rldicr reg,reg,32,31; \ + oris reg,reg,(expr)@h; \ + ori reg,reg,(expr)@l; #define LOAD_REG_ADDR(reg,name) \ - ld (reg),name@got(r2) + ld reg,name@got(r2) #define LOAD_REG_ADDRBASE(reg,name) LOAD_REG_ADDR(reg,name) #define ADDROFF(name) 0 @@ -313,12 +328,12 @@ n: #else /* 32-bit */ #define LOAD_REG_IMMEDIATE(reg,expr) \ - lis (reg),(expr)@ha; \ - addi (reg),(reg),(expr)@l; + lis reg,(expr)@ha; \ + addi reg,reg,(expr)@l; #define LOAD_REG_ADDR(reg,name) LOAD_REG_IMMEDIATE(reg, name) -#define LOAD_REG_ADDRBASE(reg, name) lis (reg),name@ha +#define LOAD_REG_ADDRBASE(reg, name) lis reg,name@ha #define ADDROFF(name) name@l /* offsets for stack frame layout */ @@ -372,9 +387,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #ifdef CONFIG_PPC64 #define MTOCRF(FXM, RS) \ BEGIN_FTR_SECTION_NESTED(848); \ - mtcrf (FXM), (RS); \ + mtcrf (FXM), RS; \ FTR_SECTION_ELSE_NESTED(848); \ - mtocrf (FXM), (RS); \ + mtocrf (FXM), RS; \ ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848) #endif @@ -463,6 +478,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #ifdef CONFIG_PPC_BOOK3S_64 #define RFI rfid #define MTMSRD(r) mtmsrd r +#define MTMSR_EERI(reg) mtmsrd reg,1 #else #define FIX_SRR1(ra, rb) #ifndef CONFIG_40x @@ -471,6 +487,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #define RFI rfi; b . /* Prevent prefetch past rfi */ #endif #define MTMSRD(r) mtmsr r +#define MTMSR_EERI(reg) mtmsr reg #define CLR_TOP32(r) #endif @@ -490,40 +507,46 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) #define cr7 7 -/* General Purpose Registers (GPRs) */ - -#define r0 0 -#define r1 1 -#define r2 2 -#define r3 3 -#define r4 4 -#define r5 5 -#define r6 6 -#define r7 7 -#define r8 8 -#define r9 9 -#define r10 10 -#define r11 11 -#define r12 12 -#define r13 13 -#define r14 14 -#define r15 15 -#define r16 16 -#define r17 17 -#define r18 18 -#define r19 19 -#define r20 20 -#define r21 21 -#define r22 22 -#define r23 23 -#define r24 24 -#define r25 25 -#define r26 26 -#define r27 27 -#define r28 28 -#define r29 29 -#define r30 30 -#define r31 31 +/* + * General Purpose Registers (GPRs) + * + * The lower case r0-r31 should be used in preference to the upper + * case R0-R31 as they provide more error checking in the assembler. + * Use R0-31 only when really nessesary. + */ + +#define r0 %r0 +#define r1 %r1 +#define r2 %r2 +#define r3 %r3 +#define r4 %r4 +#define r5 %r5 +#define r6 %r6 +#define r7 %r7 +#define r8 %r8 +#define r9 %r9 +#define r10 %r10 +#define r11 %r11 +#define r12 %r12 +#define r13 %r13 +#define r14 %r14 +#define r15 %r15 +#define r16 %r16 +#define r17 %r17 +#define r18 %r18 +#define r19 %r19 +#define r20 %r20 +#define r21 %r21 +#define r22 %r22 +#define r23 %r23 +#define r24 %r24 +#define r25 %r25 +#define r26 %r26 +#define r27 %r27 +#define r28 %r28 +#define r29 %r29 +#define r30 %r30 +#define r31 %r31 /* Floating Point Registers (FPRs) */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 413a5ea..53b6dfa 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -389,10 +389,8 @@ extern int powersave_nap; /* set if nap mode can be used in idle loop */ #ifdef CONFIG_PSERIES_IDLE extern void update_smt_snooze_delay(int snooze); -extern int pseries_notify_cpuidle_add_cpu(int cpu); #else static inline void update_smt_snooze_delay(int snooze) {} -static inline int pseries_notify_cpuidle_add_cpu(int cpu) { return 0; } #endif extern void flush_instruction_cache(void); diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h index 5e0b6d5..229571a 100644 --- a/arch/powerpc/include/asm/qe.h +++ b/arch/powerpc/include/asm/qe.h @@ -499,6 +499,7 @@ enum comm_dir { /* I-RAM */ #define QE_IRAM_IADD_AIE 0x80000000 /* Auto Increment Enable */ #define QE_IRAM_IADD_BADDR 0x00080000 /* Base Address */ +#define QE_IRAM_READY 0x80000000 /* Ready */ /* UPC */ #define UPGCR_PROTOCOL 0x80000000 /* protocol ul2 or pl2 */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index f0cb7f4..6386086 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -491,6 +491,7 @@ #define SPRN_SPRG1 0x111 /* Special Purpose Register General 1 */ #define SPRN_SPRG2 0x112 /* Special Purpose Register General 2 */ #define SPRN_SPRG3 0x113 /* Special Purpose Register General 3 */ +#define SPRN_USPRG3 0x103 /* SPRG3 userspace read */ #define SPRN_SPRG4 0x114 /* Special Purpose Register General 4 */ #define SPRN_SPRG5 0x115 /* Special Purpose Register General 5 */ #define SPRN_SPRG6 0x116 /* Special Purpose Register General 6 */ @@ -753,14 +754,14 @@ * 64-bit server: * - SPRG0 unused (reserved for HV on Power4) * - SPRG2 scratch for exception vectors - * - SPRG3 unused (user visible) + * - SPRG3 CPU and NUMA node for VDSO getcpu (user visible) * - HSPRG0 stores PACA in HV mode * - HSPRG1 scratch for "HV" exceptions * * 64-bit embedded * - SPRG0 generic exception scratch * - SPRG2 TLB exception stack - * - SPRG3 unused (user visible) + * - SPRG3 CPU and NUMA node for VDSO getcpu (user visible) * - SPRG4 unused (user visible) * - SPRG6 TLB miss scratch (user visible, sorry !) * - SPRG7 critical exception scratch @@ -1024,7 +1025,8 @@ /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ #define mfmsr() ({unsigned long rval; \ - asm volatile("mfmsr %0" : "=r" (rval)); rval;}) + asm volatile("mfmsr %0" : "=r" (rval) : \ + : "memory"); rval;}) #ifdef CONFIG_PPC_BOOK3S_64 #define __mtmsrd(v, l) asm volatile("mtmsrd %0," __stringify(l) \ : : "r" (v) : "memory") diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 68831e9..faf9352 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -22,6 +22,12 @@ #define THREAD_SIZE (1 << THREAD_SHIFT) +#ifdef CONFIG_PPC64 +#define CURRENT_THREAD_INFO(dest, sp) clrrdi dest, sp, THREAD_SHIFT +#else +#define CURRENT_THREAD_INFO(dest, sp) rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT +#endif + #ifndef __ASSEMBLY__ #include <linux/cache.h> #include <asm/processor.h> diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index cbe2297..5712f06 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -8,7 +8,7 @@ struct pt_regs; -TRACE_EVENT(irq_entry, +DECLARE_EVENT_CLASS(ppc64_interrupt_class, TP_PROTO(struct pt_regs *regs), @@ -25,55 +25,32 @@ TRACE_EVENT(irq_entry, TP_printk("pt_regs=%p", __entry->regs) ); -TRACE_EVENT(irq_exit, +DEFINE_EVENT(ppc64_interrupt_class, irq_entry, TP_PROTO(struct pt_regs *regs), - TP_ARGS(regs), - - TP_STRUCT__entry( - __field(struct pt_regs *, regs) - ), - - TP_fast_assign( - __entry->regs = regs; - ), - - TP_printk("pt_regs=%p", __entry->regs) + TP_ARGS(regs) ); -TRACE_EVENT(timer_interrupt_entry, +DEFINE_EVENT(ppc64_interrupt_class, irq_exit, TP_PROTO(struct pt_regs *regs), - TP_ARGS(regs), - - TP_STRUCT__entry( - __field(struct pt_regs *, regs) - ), - - TP_fast_assign( - __entry->regs = regs; - ), - - TP_printk("pt_regs=%p", __entry->regs) + TP_ARGS(regs) ); -TRACE_EVENT(timer_interrupt_exit, +DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_entry, TP_PROTO(struct pt_regs *regs), - TP_ARGS(regs), + TP_ARGS(regs) +); - TP_STRUCT__entry( - __field(struct pt_regs *, regs) - ), +DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit, - TP_fast_assign( - __entry->regs = regs; - ), + TP_PROTO(struct pt_regs *regs), - TP_printk("pt_regs=%p", __entry->regs) + TP_ARGS(regs) ); #ifdef CONFIG_PPC_PSERIES diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index dc0419b..50f261b 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -22,6 +22,8 @@ extern unsigned long vdso64_rt_sigtramp; extern unsigned long vdso32_sigtramp; extern unsigned long vdso32_rt_sigtramp; +int __cpuinit vdso_getcpu_init(void); + #else /* __ASSEMBLY__ */ #ifdef __VDSO64__ diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h index b19adf7..df81cb7 100644 --- a/arch/powerpc/include/asm/vio.h +++ b/arch/powerpc/include/asm/vio.h @@ -44,6 +44,8 @@ */ #define VIO_CMO_MIN_ENT 1562624 +extern struct bus_type vio_bus_type; + struct iommu_table; /* diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 83afacd..bb282dd 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -128,6 +128,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),) obj-y += ppc_save_regs.o endif +obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o # Disable GCOV in odd or sensitive code diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 52c7ad7..85b05c4 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -533,6 +533,7 @@ int main(void) HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler); HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); + HSTATE_FIELD(HSTATE_SPRG3, sprg3); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); HSTATE_FIELD(HSTATE_NAPPING, napping); diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S index ebc62f4..61f079e 100644 --- a/arch/powerpc/kernel/cpu_setup_a2.S +++ b/arch/powerpc/kernel/cpu_setup_a2.S @@ -100,19 +100,19 @@ _icswx_skip_guest: lis r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h mtspr SPRN_MMUCR0, r4 li r4,A2_IERAT_SIZE-1 - PPC_ERATWE(r4,r4,3) + PPC_ERATWE(R4,R4,3) /* Now set the D-ERAT watermark to 31 */ lis r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h mtspr SPRN_MMUCR0, r4 li r4,A2_DERAT_SIZE-1 - PPC_ERATWE(r4,r4,3) + PPC_ERATWE(R4,R4,3) /* And invalidate the beast just in case. That won't get rid of * a bolted entry though it will be in LRU and so will go away eventually * but let's not bother for now */ - PPC_ERATILX(0,0,0) + PPC_ERATILX(0,0,R0) 1: blr diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index b1ec983..289be75 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -11,6 +11,8 @@ #include <linux/gfp.h> #include <linux/memblock.h> #include <linux/export.h> +#include <linux/pci.h> +#include <asm/vio.h> #include <asm/bug.h> #include <asm/abs_addr.h> #include <asm/machdep.h> @@ -205,7 +207,13 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask); static int __init dma_init(void) { - dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); +#ifdef CONFIG_PCI + dma_debug_add_bus(&pci_bus_type); +#endif +#ifdef CONFIG_IBMVIO + dma_debug_add_bus(&vio_bus_type); +#endif return 0; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index ba3aeb4..5207d5a 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -92,7 +92,7 @@ crit_transfer_to_handler: mfspr r8,SPRN_SPRG_THREAD lwz r0,KSP_LIMIT(r8) stw r0,SAVED_KSP_LIMIT(r11) - rlwimi r0,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r0, r1) stw r0,KSP_LIMIT(r8) /* fall through */ #endif @@ -112,7 +112,7 @@ crit_transfer_to_handler: mfspr r8,SPRN_SPRG_THREAD lwz r0,KSP_LIMIT(r8) stw r0,saved_ksp_limit@l(0) - rlwimi r0,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r0, r1) stw r0,KSP_LIMIT(r8) /* fall through */ #endif @@ -158,7 +158,7 @@ transfer_to_handler: tophys(r11,r11) addi r11,r11,global_dbcr0@l #ifdef CONFIG_SMP - rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r9, r1) lwz r9,TI_CPU(r9) slwi r9,r9,3 add r11,r11,r9 @@ -179,7 +179,7 @@ transfer_to_handler: ble- stack_ovf /* then the kernel stack overflowed */ 5: #if defined(CONFIG_6xx) || defined(CONFIG_E500) - rlwinm r9,r1,0,0,31-THREAD_SHIFT + CURRENT_THREAD_INFO(r9, r1) tophys(r9,r9) /* check local flags */ lwz r12,TI_LOCAL_FLAGS(r9) mtcrf 0x01,r12 @@ -226,13 +226,7 @@ reenable_mmu: /* re-enable mmu so we can */ stw r3,16(r1) stw r4,20(r1) stw r5,24(r1) - andi. r12,r12,MSR_PR - b 11f bl trace_hardirqs_off - b 12f -11: - bl trace_hardirqs_off -12: lwz r5,24(r1) lwz r4,20(r1) lwz r3,16(r1) @@ -333,7 +327,7 @@ _GLOBAL(DoSyscall) mtmsr r11 1: #endif /* CONFIG_TRACE_IRQFLAGS */ - rlwinm r10,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + CURRENT_THREAD_INFO(r10, r1) lwz r11,TI_FLAGS(r10) andi. r11,r11,_TIF_SYSCALL_T_OR_A bne- syscall_dotrace @@ -354,7 +348,7 @@ ret_from_syscall: bl do_show_syscall_exit #endif mr r6,r3 - rlwinm r12,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + CURRENT_THREAD_INFO(r12, r1) /* disable interrupts so current_thread_info()->flags can't change */ LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */ /* Note: We don't bother telling lockdep about it */ @@ -815,7 +809,7 @@ ret_from_except: user_exc_return: /* r10 contains MSR_KERNEL here */ /* Check current_thread_info()->flags */ - rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r9, r1) lwz r9,TI_FLAGS(r9) andi. r0,r9,_TIF_USER_WORK_MASK bne do_work @@ -835,7 +829,7 @@ restore_user: /* N.B. the only way to get here is from the beq following ret_from_except. */ resume_kernel: /* check current_thread_info->preempt_count */ - rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r9, r1) lwz r0,TI_PREEMPT(r9) cmpwi 0,r0,0 /* if non-zero, just restore regs and return */ bne restore @@ -852,7 +846,7 @@ resume_kernel: bl trace_hardirqs_off #endif 1: bl preempt_schedule_irq - rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r9, r1) lwz r3,TI_FLAGS(r9) andi. r0,r3,_TIF_NEED_RESCHED bne- 1b @@ -1122,7 +1116,7 @@ ret_from_debug_exc: lwz r10,SAVED_KSP_LIMIT(r1) stw r10,KSP_LIMIT(r9) lwz r9,THREAD_INFO-THREAD(r9) - rlwinm r10,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r10, r1) lwz r10,TI_PREEMPT(r10) stw r10,TI_PREEMPT(r9) RESTORE_xSRR(SRR0,SRR1); @@ -1156,7 +1150,7 @@ load_dbcr0: lis r11,global_dbcr0@ha addi r11,r11,global_dbcr0@l #ifdef CONFIG_SMP - rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r9, r1) lwz r9,TI_CPU(r9) slwi r9,r9,3 add r11,r11,r9 @@ -1197,7 +1191,7 @@ recheck: LOAD_MSR_KERNEL(r10,MSR_KERNEL) SYNC MTMSRD(r10) /* disable interrupts */ - rlwinm r9,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r9, r1) lwz r9,TI_FLAGS(r9) andi. r0,r9,_TIF_NEED_RESCHED bne- do_resched diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 5971c85..4b01a25 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -146,7 +146,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) REST_2GPRS(7,r1) addi r9,r1,STACK_FRAME_OVERHEAD #endif - clrrdi r11,r1,THREAD_SHIFT + CURRENT_THREAD_INFO(r11, r1) ld r10,TI_FLAGS(r11) andi. r11,r10,_TIF_SYSCALL_T_OR_A bne- syscall_dotrace @@ -181,7 +181,7 @@ syscall_exit: bl .do_show_syscall_exit ld r3,RESULT(r1) #endif - clrrdi r12,r1,THREAD_SHIFT + CURRENT_THREAD_INFO(r12, r1) ld r8,_MSR(r1) #ifdef CONFIG_PPC_BOOK3S @@ -197,7 +197,16 @@ syscall_exit: wrteei 0 #else ld r10,PACAKMSR(r13) - mtmsrd r10,1 + /* + * For performance reasons we clear RI the same time that we + * clear EE. We only need to clear RI just before we restore r13 + * below, but batching it with EE saves us one expensive mtmsrd call. + * We have to be careful to restore RI if we branch anywhere from + * here (eg syscall_exit_work). + */ + li r9,MSR_RI + andc r11,r10,r9 + mtmsrd r11,1 #endif /* CONFIG_PPC_BOOK3E */ ld r9,TI_FLAGS(r12) @@ -214,17 +223,6 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) andi. r6,r8,MSR_PR ld r4,_LINK(r1) - /* - * Clear RI before restoring r13. If we are returning to - * userspace and we take an exception after restoring r13, - * we end up corrupting the userspace r13 value. - */ -#ifdef CONFIG_PPC_BOOK3S - /* No MSR:RI on BookE */ - li r12,MSR_RI - andc r11,r10,r12 - mtmsrd r11,1 /* clear MSR.RI */ -#endif /* CONFIG_PPC_BOOK3S */ beq- 1f ACCOUNT_CPU_USER_EXIT(r11, r12) @@ -262,7 +260,7 @@ syscall_dotrace: ld r7,GPR7(r1) ld r8,GPR8(r1) addi r9,r1,STACK_FRAME_OVERHEAD - clrrdi r10,r1,THREAD_SHIFT + CURRENT_THREAD_INFO(r10, r1) ld r10,TI_FLAGS(r10) b .Lsyscall_dotrace_cont @@ -271,6 +269,9 @@ syscall_enosys: b syscall_exit syscall_exit_work: +#ifdef CONFIG_PPC_BOOK3S + mtmsrd r10,1 /* Restore RI */ +#endif /* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr. If TIF_NOERROR is set, just save r3 as it is. */ @@ -499,7 +500,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) 2: #endif /* !CONFIG_PPC_BOOK3S */ - clrrdi r7,r8,THREAD_SHIFT /* base of new stack */ + CURRENT_THREAD_INFO(r7, r8) /* base of new stack */ /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE because we don't need to leave the 288-byte ABI gap at the top of the kernel stack. */ @@ -558,7 +559,7 @@ _GLOBAL(ret_from_except_lite) mtmsrd r10,1 /* Update machine state */ #endif /* CONFIG_PPC_BOOK3E */ - clrrdi r9,r1,THREAD_SHIFT /* current_thread_info() */ + CURRENT_THREAD_INFO(r9, r1) ld r3,_MSR(r1) ld r4,TI_FLAGS(r9) andi. r3,r3,MSR_PR @@ -601,7 +602,7 @@ resume_kernel: 1: bl .preempt_schedule_irq /* Re-test flags and eventually loop */ - clrrdi r9,r1,THREAD_SHIFT + CURRENT_THREAD_INFO(r9, r1) ld r4,TI_FLAGS(r9) andi. r0,r4,_TIF_NEED_RESCHED bne 1b diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S new file mode 100644 index 0000000..697b390 --- /dev/null +++ b/arch/powerpc/kernel/epapr_hcalls.S @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2012 Freescale Semiconductor, Inc. + * + * 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. + */ + +#include <linux/threads.h> +#include <asm/reg.h> +#include <asm/page.h> +#include <asm/cputable.h> +#include <asm/thread_info.h> +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + +/* Hypercall entry point. Will be patched with device tree instructions. */ +.global epapr_hypercall_start +epapr_hypercall_start: + li r3, -1 + nop + nop + nop + blr diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c new file mode 100644 index 0000000..028aeae --- /dev/null +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -0,0 +1,52 @@ +/* + * ePAPR para-virtualization support. + * + * 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. + * + * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + * + * Copyright (C) 2012 Freescale Semiconductor, Inc. + */ + +#include <linux/of.h> +#include <asm/epapr_hcalls.h> +#include <asm/cacheflush.h> +#include <asm/code-patching.h> + +bool epapr_paravirt_enabled; + +static int __init epapr_paravirt_init(void) +{ + struct device_node *hyper_node; + const u32 *insts; + int len, i; + + hyper_node = of_find_node_by_path("/hypervisor"); + if (!hyper_node) + return -ENODEV; + + insts = of_get_property(hyper_node, "hcall-instructions", &len); + if (!insts) + return -ENODEV; + + if (len % 4 || len > (4 * 4)) + return -ENODEV; + + for (i = 0; i < (len / 4); i++) + patch_instruction(epapr_hypercall_start + i, insts[i]); + + epapr_paravirt_enabled = true; + + return 0; +} + +early_initcall(epapr_paravirt_init); diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 7215cc2..98be7f0 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -222,7 +222,7 @@ exc_##n##_bad_stack: \ * interrupts happen before the wait instruction. */ #define CHECK_NAPPING() \ - clrrdi r11,r1,THREAD_SHIFT; \ + CURRENT_THREAD_INFO(r11, r1); \ ld r10,TI_LOCAL_FLAGS(r11); \ andi. r9,r10,_TLF_NAPPING; \ beq+ 1f; \ @@ -903,7 +903,7 @@ skpinv: addi r6,r6,1 /* Increment */ bne 1b /* If not, repeat */ /* Invalidate all TLBs */ - PPC_TLBILX_ALL(0,0) + PPC_TLBILX_ALL(0,R0) sync isync @@ -961,7 +961,7 @@ skpinv: addi r6,r6,1 /* Increment */ tlbwe /* Invalidate TLB1 */ - PPC_TLBILX_ALL(0,0) + PPC_TLBILX_ALL(0,R0) sync isync @@ -1020,7 +1020,7 @@ skpinv: addi r6,r6,1 /* Increment */ tlbwe /* Invalidate TLB1 */ - PPC_TLBILX_ALL(0,0) + PPC_TLBILX_ALL(0,R0) sync isync @@ -1138,7 +1138,7 @@ a2_tlbinit_after_iprot_flush: tlbwe #endif /* CONFIG_PPC_EARLY_DEBUG_WSP */ - PPC_TLBILX(0,0,0) + PPC_TLBILX(0,0,R0) sync isync diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 1c06d29..e894515 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -239,6 +239,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) * out of line to handle them */ . = 0xe00 +hv_exception_trampoline: b h_data_storage_hv . = 0xe20 b h_instr_storage_hv @@ -851,7 +852,7 @@ BEGIN_FTR_SECTION bne- do_ste_alloc /* If so handle it */ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB) - clrrdi r11,r1,THREAD_SHIFT + CURRENT_THREAD_INFO(r11, r1) lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */ bne 77f /* then don't call hash_page now */ diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index de36955..e0ada05 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -26,7 +26,7 @@ #include <asm/ptrace.h> #ifdef CONFIG_VSX -#define REST_32FPVSRS(n,c,base) \ +#define __REST_32FPVSRS(n,c,base) \ BEGIN_FTR_SECTION \ b 2f; \ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ @@ -35,7 +35,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ 2: REST_32VSRS(n,c,base); \ 3: -#define SAVE_32FPVSRS(n,c,base) \ +#define __SAVE_32FPVSRS(n,c,base) \ BEGIN_FTR_SECTION \ b 2f; \ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ @@ -44,9 +44,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ 2: SAVE_32VSRS(n,c,base); \ 3: #else -#define REST_32FPVSRS(n,b,base) REST_32FPRS(n, base) -#define SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base) +#define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base) +#define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base) #endif +#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) +#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) /* * This task wants to use the FPU now. @@ -79,7 +81,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) beq 1f toreal(r4) addi r4,r4,THREAD /* want last_task_used_math->thread */ - SAVE_32FPVSRS(0, r5, r4) + SAVE_32FPVSRS(0, R5, R4) mffs fr0 stfd fr0,THREAD_FPSCR(r4) PPC_LL r5,PT_REGS(r4) @@ -106,7 +108,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif lfd fr0,THREAD_FPSCR(r5) MTFSF_L(fr0) - REST_32FPVSRS(0, r4, r5) + REST_32FPVSRS(0, R4, R5) #ifndef CONFIG_SMP subi r4,r5,THREAD fromreal(r4) @@ -140,7 +142,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) addi r3,r3,THREAD /* want THREAD of task */ PPC_LL r5,PT_REGS(r3) PPC_LCMPI 0,r5,0 - SAVE_32FPVSRS(0, r4 ,r3) + SAVE_32FPVSRS(0, R4 ,R3) mffs fr0 stfd fr0,THREAD_FPSCR(r3) beq 1f diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index bf99cfa..91b46b7 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -63,11 +63,9 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) return -EINVAL; /* replace the text with the new text */ - if (probe_kernel_write((void *)ip, &new, MCOUNT_INSN_SIZE)) + if (patch_instruction((unsigned int *)ip, new)) return -EPERM; - flush_icache_range(ip, ip + 8); - return 0; } @@ -212,12 +210,9 @@ __ftrace_make_nop(struct module *mod, */ op = 0x48000008; /* b +8 */ - if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) + if (patch_instruction((unsigned int *)ip, op)) return -EPERM; - - flush_icache_range(ip, ip + 8); - return 0; } @@ -245,9 +240,9 @@ __ftrace_make_nop(struct module *mod, /* * On PPC32 the trampoline looks like: - * 0x3d, 0x60, 0x00, 0x00 lis r11,sym@ha - * 0x39, 0x6b, 0x00, 0x00 addi r11,r11,sym@l - * 0x7d, 0x69, 0x03, 0xa6 mtctr r11 + * 0x3d, 0x80, 0x00, 0x00 lis r12,sym@ha + * 0x39, 0x8c, 0x00, 0x00 addi r12,r12,sym@l + * 0x7d, 0x89, 0x03, 0xa6 mtctr r12 * 0x4e, 0x80, 0x04, 0x20 bctr */ @@ -262,9 +257,9 @@ __ftrace_make_nop(struct module *mod, pr_devel(" %08x %08x ", jmp[0], jmp[1]); /* verify that this is what we expect it to be */ - if (((jmp[0] & 0xffff0000) != 0x3d600000) || - ((jmp[1] & 0xffff0000) != 0x396b0000) || - (jmp[2] != 0x7d6903a6) || + if (((jmp[0] & 0xffff0000) != 0x3d800000) || + ((jmp[1] & 0xffff0000) != 0x398c0000) || + (jmp[2] != 0x7d8903a6) || (jmp[3] != 0x4e800420)) { printk(KERN_ERR "Not a trampoline\n"); return -EINVAL; @@ -286,11 +281,9 @@ __ftrace_make_nop(struct module *mod, op = PPC_INST_NOP; - if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) + if (patch_instruction((unsigned int *)ip, op)) return -EPERM; - flush_icache_range(ip, ip + 8); - return 0; } #endif /* PPC64 */ @@ -426,11 +419,9 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) pr_devel("write to %lx\n", rec->ip); - if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) + if (patch_instruction((unsigned int *)ip, op)) return -EPERM; - flush_icache_range(ip, ip + 8); - return 0; } #endif /* CONFIG_PPC64 */ @@ -484,6 +475,58 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } +static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) +{ + unsigned long ftrace_addr = (unsigned long)FTRACE_ADDR; + int ret; + + ret = ftrace_update_record(rec, enable); + + switch (ret) { + case FTRACE_UPDATE_IGNORE: + return 0; + case FTRACE_UPDATE_MAKE_CALL: + return ftrace_make_call(rec, ftrace_addr); + case FTRACE_UPDATE_MAKE_NOP: + return ftrace_make_nop(NULL, rec, ftrace_addr); + } + + return 0; +} + +void ftrace_replace_code(int enable) +{ + struct ftrace_rec_iter *iter; + struct dyn_ftrace *rec; + int ret; + + for (iter = ftrace_rec_iter_start(); iter; + iter = ftrace_rec_iter_next(iter)) { + rec = ftrace_rec_iter_record(iter); + ret = __ftrace_replace_code(rec, enable); + if (ret) { + ftrace_bug(ret, rec->ip); + return; + } + } +} + +void arch_ftrace_update_code(int command) +{ + if (command & FTRACE_UPDATE_CALLS) + ftrace_replace_code(1); + else if (command & FTRACE_DISABLE_CALLS) + ftrace_replace_code(0); + + if (command & FTRACE_UPDATE_TRACE_FUNC) + ftrace_update_ftrace_func(ftrace_trace_function); + + if (command & FTRACE_START_FUNC_RET) + ftrace_enable_ftrace_graph_caller(); + else if (command & FTRACE_STOP_FUNC_RET) + ftrace_disable_ftrace_graph_caller(); +} + int __init ftrace_dyn_arch_init(void *data) { /* caller expects data to be zero */ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index 1f4434a..0f59863 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -192,7 +192,7 @@ _ENTRY(__early_start) li r0,0 stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) - rlwinm r22,r1,0,0,31-THREAD_SHIFT /* current thread_info */ + CURRENT_THREAD_INFO(r22, r1) stw r24, TI_CPU(r22) bl early_init @@ -556,8 +556,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) /* SPE Unavailable */ START_EXCEPTION(SPEUnavailable) NORMAL_EXCEPTION_PROLOG(SPE_UNAVAIL) - bne load_up_spe - addi r3,r1,STACK_FRAME_OVERHEAD + beq 1f + bl load_up_spe + b fast_exception_return +1: addi r3,r1,STACK_FRAME_OVERHEAD EXC_XFER_EE_LITE(0x2010, KernelSPE) #else EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \ @@ -778,7 +780,7 @@ tlb_write_entry: /* Note that the SPE support is closely modeled after the AltiVec * support. Changes to one are likely to be applicable to the * other! */ -load_up_spe: +_GLOBAL(load_up_spe) /* * Disable SPE for the task which had SPE previously, * and save its SPE registers in its thread_struct. @@ -826,20 +828,7 @@ load_up_spe: subi r4,r5,THREAD stw r4,last_task_used_spe@l(r3) #endif /* !CONFIG_SMP */ - /* restore registers and return */ -2: REST_4GPRS(3, r11) - lwz r10,_CCR(r11) - REST_GPR(1, r11) - mtcr r10 - lwz r10,_LINK(r11) - mtlr r10 - REST_GPR(10, r11) - mtspr SPRN_SRR1,r9 - mtspr SPRN_SRR0,r12 - REST_GPR(9, r11) - REST_GPR(12, r11) - lwz r11,GPR11(r11) - rfi + blr /* * SPE unavailable trap from kernel - print a message, but let diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 2bc0584..f3a82dd 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -111,7 +111,7 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp) * and the single_step_dabr_instruction(), then cleanup the breakpoint * restoration variables to prevent dangling pointers. */ - if (bp->ctx->task) + if (bp->ctx && bp->ctx->task) bp->ctx->task->thread.last_hit_ubp = NULL; } diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S index 15c611d..1686916 100644 --- a/arch/powerpc/kernel/idle_6xx.S +++ b/arch/powerpc/kernel/idle_6xx.S @@ -135,7 +135,7 @@ BEGIN_FTR_SECTION DSSALL sync END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) - rlwinm r9,r1,0,0,31-THREAD_SHIFT /* current thread_info */ + CURRENT_THREAD_INFO(r9, r1) lwz r8,TI_LOCAL_FLAGS(r9) /* set napping bit */ ori r8,r8,_TLF_NAPPING /* so when we take an exception */ stw r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */ @@ -158,7 +158,7 @@ _GLOBAL(power_save_ppc32_restore) stw r9,_NIP(r11) /* make it do a blr */ #ifdef CONFIG_SMP - rlwinm r12,r11,0,0,31-THREAD_SHIFT + CURRENT_THREAD_INFO(r12, r11) lwz r11,TI_CPU(r12) /* get cpu number * 4 */ slwi r11,r11,2 #else diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S index ff007b5..4c7cb400 100644 --- a/arch/powerpc/kernel/idle_book3e.S +++ b/arch/powerpc/kernel/idle_book3e.S @@ -60,7 +60,7 @@ _GLOBAL(book3e_idle) 1: /* Let's set the _TLF_NAPPING flag so interrupts make us return * to the right spot */ - clrrdi r11,r1,THREAD_SHIFT + CURRENT_THREAD_INFO(r11, r1) ld r10,TI_LOCAL_FLAGS(r11) ori r10,r10,_TLF_NAPPING std r10,TI_LOCAL_FLAGS(r11) diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S index 4f0ab85..1544866 100644 --- a/arch/powerpc/kernel/idle_e500.S +++ b/arch/powerpc/kernel/idle_e500.S @@ -21,7 +21,7 @@ .text _GLOBAL(e500_idle) - rlwinm r3,r1,0,0,31-THREAD_SHIFT /* current thread_info */ + CURRENT_THREAD_INFO(r3, r1) lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */ ori r4,r4,_TLF_NAPPING /* so when we take an exception */ stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */ @@ -96,7 +96,7 @@ _GLOBAL(power_save_ppc32_restore) stw r9,_NIP(r11) /* make it do a blr */ #ifdef CONFIG_SMP - rlwinm r12,r1,0,0,31-THREAD_SHIFT + CURRENT_THREAD_INFO(r12, r1) lwz r11,TI_CPU(r12) /* get cpu number * 4 */ slwi r11,r11,2 #else diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index 2c71b0f..e3edaa1 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -59,7 +59,7 @@ BEGIN_FTR_SECTION DSSALL sync END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) - clrrdi r9,r1,THREAD_SHIFT /* current thread_info */ + CURRENT_THREAD_INFO(r9, r1) ld r8,TI_LOCAL_FLAGS(r9) /* set napping bit */ ori r8,r8,_TLF_NAPPING /* so when we take an exception */ std r8,TI_LOCAL_FLAGS(r9) /* it will return to our caller */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 359f078..ff5a6ce 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -33,6 +33,9 @@ #include <linux/bitmap.h> #include <linux/iommu-helper.h> #include <linux/crash_dump.h> +#include <linux/hash.h> +#include <linux/fault-inject.h> +#include <linux/pci.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/iommu.h> @@ -40,6 +43,7 @@ #include <asm/machdep.h> #include <asm/kdump.h> #include <asm/fadump.h> +#include <asm/vio.h> #define DBG(...) @@ -58,6 +62,114 @@ static int __init setup_iommu(char *str) __setup("iommu=", setup_iommu); +static DEFINE_PER_CPU(unsigned int, iommu_pool_hash); + +/* + * We precalculate the hash to avoid doing it on every allocation. + * + * The hash is important to spread CPUs across all the pools. For example, + * on a POWER7 with 4 way SMT we want interrupts on the primary threads and + * with 4 pools all primary threads would map to the same pool. + */ +static int __init setup_iommu_pool_hash(void) +{ + unsigned int i; + + for_each_possible_cpu(i) + per_cpu(iommu_pool_hash, i) = hash_32(i, IOMMU_POOL_HASHBITS); + + return 0; +} +subsys_initcall(setup_iommu_pool_hash); + +#ifdef CONFIG_FAIL_IOMMU + +static DECLARE_FAULT_ATTR(fail_iommu); + +static int __init setup_fail_iommu(char *str) +{ + return setup_fault_attr(&fail_iommu, str); +} +__setup("fail_iommu=", setup_fail_iommu); + +static bool should_fail_iommu(struct device *dev) +{ + return dev->archdata.fail_iommu && should_fail(&fail_iommu, 1); +} + +static int __init fail_iommu_debugfs(void) +{ + struct dentry *dir = fault_create_debugfs_attr("fail_iommu", + NULL, &fail_iommu); + + return IS_ERR(dir) ? PTR_ERR(dir) : 0; +} +late_initcall(fail_iommu_debugfs); + +static ssize_t fail_iommu_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", dev->archdata.fail_iommu); +} + +static ssize_t fail_iommu_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + int i; + + if (count > 0 && sscanf(buf, "%d", &i) > 0) + dev->archdata.fail_iommu = (i == 0) ? 0 : 1; + + return count; +} + +static DEVICE_ATTR(fail_iommu, S_IRUGO|S_IWUSR, fail_iommu_show, + fail_iommu_store); + +static int fail_iommu_bus_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + + if (action == BUS_NOTIFY_ADD_DEVICE) { + if (device_create_file(dev, &dev_attr_fail_iommu)) + pr_warn("Unable to create IOMMU fault injection sysfs " + "entries\n"); + } else if (action == BUS_NOTIFY_DEL_DEVICE) { + device_remove_file(dev, &dev_attr_fail_iommu); + } + + return 0; +} + +static struct notifier_block fail_iommu_bus_notifier = { + .notifier_call = fail_iommu_bus_notify +}; + +static int __init fail_iommu_setup(void) +{ +#ifdef CONFIG_PCI + bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier); +#endif +#ifdef CONFIG_IBMVIO + bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier); +#endif + + return 0; +} +/* + * Must execute after PCI and VIO subsystem have initialised but before + * devices are probed. + */ +arch_initcall(fail_iommu_setup); +#else +static inline bool should_fail_iommu(struct device *dev) +{ + return false; +} +#endif + static unsigned long iommu_range_alloc(struct device *dev, struct iommu_table *tbl, unsigned long npages, @@ -71,6 +183,9 @@ static unsigned long iommu_range_alloc(struct device *dev, int pass = 0; unsigned long align_mask; unsigned long boundary_size; + unsigned long flags; + unsigned int pool_nr; + struct iommu_pool *pool; align_mask = 0xffffffffffffffffl >> (64 - align_order); @@ -83,36 +198,49 @@ static unsigned long iommu_range_alloc(struct device *dev, return DMA_ERROR_CODE; } - if (handle && *handle) - start = *handle; + if (should_fail_iommu(dev)) + return DMA_ERROR_CODE; + + /* + * We don't need to disable preemption here because any CPU can + * safely use any IOMMU pool. + */ + pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1); + + if (largealloc) + pool = &(tbl->large_pool); else - start = largealloc ? tbl->it_largehint : tbl->it_hint; + pool = &(tbl->pools[pool_nr]); - /* Use only half of the table for small allocs (15 pages or less) */ - limit = largealloc ? tbl->it_size : tbl->it_halfpoint; + spin_lock_irqsave(&(pool->lock), flags); - if (largealloc && start < tbl->it_halfpoint) - start = tbl->it_halfpoint; +again: + if ((pass == 0) && handle && *handle) + start = *handle; + else + start = pool->hint; + + limit = pool->end; /* The case below can happen if we have a small segment appended * to a large, or when the previous alloc was at the very end of * the available space. If so, go back to the initial start. */ if (start >= limit) - start = largealloc ? tbl->it_largehint : tbl->it_hint; - - again: + start = pool->start; if (limit + tbl->it_offset > mask) { limit = mask - tbl->it_offset + 1; /* If we're constrained on address range, first try * at the masked hint to avoid O(n) search complexity, - * but on second pass, start at 0. + * but on second pass, start at 0 in pool 0. */ - if ((start & mask) >= limit || pass > 0) - start = 0; - else + if ((start & mask) >= limit || pass > 0) { + pool = &(tbl->pools[0]); + start = pool->start; + } else { start &= mask; + } } if (dev) @@ -126,16 +254,25 @@ static unsigned long iommu_range_alloc(struct device *dev, tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT, align_mask); if (n == -1) { - if (likely(pass < 2)) { - /* First failure, just rescan the half of the table. - * Second failure, rescan the other half of the table. - */ - start = (largealloc ^ pass) ? tbl->it_halfpoint : 0; - limit = pass ? tbl->it_size : limit; + if (likely(pass == 0)) { + /* First try the pool from the start */ + pool->hint = pool->start; pass++; goto again; + + } else if (pass <= tbl->nr_pools) { + /* Now try scanning all the other pools */ + spin_unlock(&(pool->lock)); + pool_nr = (pool_nr + 1) & (tbl->nr_pools - 1); + pool = &tbl->pools[pool_nr]; + spin_lock(&(pool->lock)); + pool->hint = pool->start; + pass++; + goto again; + } else { - /* Third failure, give up */ + /* Give up */ + spin_unlock_irqrestore(&(pool->lock), flags); return DMA_ERROR_CODE; } } @@ -145,10 +282,10 @@ static unsigned long iommu_range_alloc(struct device *dev, /* Bump the hint to a new block for small allocs. */ if (largealloc) { /* Don't bump to new block to avoid fragmentation */ - tbl->it_largehint = end; + pool->hint = end; } else { /* Overflow will be taken care of at the next allocation */ - tbl->it_hint = (end + tbl->it_blocksize - 1) & + pool->hint = (end + tbl->it_blocksize - 1) & ~(tbl->it_blocksize - 1); } @@ -156,6 +293,8 @@ static unsigned long iommu_range_alloc(struct device *dev, if (handle) *handle = end; + spin_unlock_irqrestore(&(pool->lock), flags); + return n; } @@ -165,18 +304,14 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, unsigned long mask, unsigned int align_order, struct dma_attrs *attrs) { - unsigned long entry, flags; + unsigned long entry; dma_addr_t ret = DMA_ERROR_CODE; int build_fail; - spin_lock_irqsave(&(tbl->it_lock), flags); - entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order); - if (unlikely(entry == DMA_ERROR_CODE)) { - spin_unlock_irqrestore(&(tbl->it_lock), flags); + if (unlikely(entry == DMA_ERROR_CODE)) return DMA_ERROR_CODE; - } entry += tbl->it_offset; /* Offset into real TCE table */ ret = entry << IOMMU_PAGE_SHIFT; /* Set the return dma address */ @@ -193,8 +328,6 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, */ if (unlikely(build_fail)) { __iommu_free(tbl, ret, npages); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); return DMA_ERROR_CODE; } @@ -202,16 +335,14 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, if (ppc_md.tce_flush) ppc_md.tce_flush(tbl); - spin_unlock_irqrestore(&(tbl->it_lock), flags); - /* Make sure updates are seen by hardware */ mb(); return ret; } -static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, - unsigned int npages) +static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr, + unsigned int npages) { unsigned long entry, free_entry; @@ -231,20 +362,57 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, printk(KERN_INFO "\tindex = 0x%llx\n", (u64)tbl->it_index); WARN_ON(1); } - return; + + return false; + } + + return true; +} + +static struct iommu_pool *get_pool(struct iommu_table *tbl, + unsigned long entry) +{ + struct iommu_pool *p; + unsigned long largepool_start = tbl->large_pool.start; + + /* The large pool is the last pool at the top of the table */ + if (entry >= largepool_start) { + p = &tbl->large_pool; + } else { + unsigned int pool_nr = entry / tbl->poolsize; + + BUG_ON(pool_nr > tbl->nr_pools); + p = &tbl->pools[pool_nr]; } + return p; +} + +static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, + unsigned int npages) +{ + unsigned long entry, free_entry; + unsigned long flags; + struct iommu_pool *pool; + + entry = dma_addr >> IOMMU_PAGE_SHIFT; + free_entry = entry - tbl->it_offset; + + pool = get_pool(tbl, free_entry); + + if (!iommu_free_check(tbl, dma_addr, npages)) + return; + ppc_md.tce_free(tbl, entry, npages); + + spin_lock_irqsave(&(pool->lock), flags); bitmap_clear(tbl->it_map, free_entry, npages); + spin_unlock_irqrestore(&(pool->lock), flags); } static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned int npages) { - unsigned long flags; - - spin_lock_irqsave(&(tbl->it_lock), flags); - __iommu_free(tbl, dma_addr, npages); /* Make sure TLB cache is flushed if the HW needs it. We do @@ -253,8 +421,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, */ if (ppc_md.tce_flush) ppc_md.tce_flush(tbl); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); } int iommu_map_sg(struct device *dev, struct iommu_table *tbl, @@ -263,7 +429,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, struct dma_attrs *attrs) { dma_addr_t dma_next = 0, dma_addr; - unsigned long flags; struct scatterlist *s, *outs, *segstart; int outcount, incount, i, build_fail = 0; unsigned int align; @@ -285,8 +450,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, DBG("sg mapping %d elements:\n", nelems); - spin_lock_irqsave(&(tbl->it_lock), flags); - max_seg_size = dma_get_max_seg_size(dev); for_each_sg(sglist, s, nelems, i) { unsigned long vaddr, npages, entry, slen; @@ -369,8 +532,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, if (ppc_md.tce_flush) ppc_md.tce_flush(tbl); - spin_unlock_irqrestore(&(tbl->it_lock), flags); - DBG("mapped %d elements:\n", outcount); /* For the sake of iommu_unmap_sg, we clear out the length in the @@ -402,7 +563,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl, if (s == outs) break; } - spin_unlock_irqrestore(&(tbl->it_lock), flags); return 0; } @@ -412,15 +572,12 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, struct dma_attrs *attrs) { struct scatterlist *sg; - unsigned long flags; BUG_ON(direction == DMA_NONE); if (!tbl) return; - spin_lock_irqsave(&(tbl->it_lock), flags); - sg = sglist; while (nelems--) { unsigned int npages; @@ -440,8 +597,6 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist, */ if (ppc_md.tce_flush) ppc_md.tce_flush(tbl); - - spin_unlock_irqrestore(&(tbl->it_lock), flags); } static void iommu_table_clear(struct iommu_table *tbl) @@ -494,9 +649,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) unsigned long sz; static int welcomed = 0; struct page *page; - - /* Set aside 1/4 of the table for large allocations. */ - tbl->it_halfpoint = tbl->it_size * 3 / 4; + unsigned int i; + struct iommu_pool *p; /* number of bytes needed for the bitmap */ sz = (tbl->it_size + 7) >> 3; @@ -515,9 +669,28 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) if (tbl->it_offset == 0) set_bit(0, tbl->it_map); - tbl->it_hint = 0; - tbl->it_largehint = tbl->it_halfpoint; - spin_lock_init(&tbl->it_lock); + /* We only split the IOMMU table if we have 1GB or more of space */ + if ((tbl->it_size << IOMMU_PAGE_SHIFT) >= (1UL * 1024 * 1024 * 1024)) + tbl->nr_pools = IOMMU_NR_POOLS; + else + tbl->nr_pools = 1; + + /* We reserve the top 1/4 of the table for large allocations */ + tbl->poolsize = (tbl->it_size * 3 / 4) / tbl->nr_pools; + + for (i = 0; i < tbl->nr_pools; i++) { + p = &tbl->pools[i]; + spin_lock_init(&(p->lock)); + p->start = tbl->poolsize * i; + p->hint = p->start; + p->end = p->start + tbl->poolsize; + } + + p = &tbl->large_pool; + spin_lock_init(&(p->lock)); + p->start = tbl->poolsize * i; + p->hint = p->start; + p->end = tbl->it_size; iommu_table_clear(tbl); diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 62bdf23..867db1d 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -31,6 +31,7 @@ #include <asm/cacheflush.h> #include <asm/disassemble.h> #include <asm/ppc-opcode.h> +#include <asm/epapr_hcalls.h> #define KVM_MAGIC_PAGE (-4096L) #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x) @@ -302,7 +303,7 @@ static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one) if (imm_one) { p[kvm_emulate_wrtee_reg_offs] = - KVM_INST_LI | __PPC_RT(30) | MSR_EE; + KVM_INST_LI | __PPC_RT(R30) | MSR_EE; } else { /* Make clobbered registers work too */ switch (get_rt(rt)) { @@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in, unsigned long register r11 asm("r11") = nr; unsigned long register r12 asm("r12"); - asm volatile("bl kvm_hypercall_start" + asm volatile("bl epapr_hypercall_start" : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6), "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11), "=r"(r12) @@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in, } EXPORT_SYMBOL_GPL(kvm_hypercall); -static int kvm_para_setup(void) -{ - extern u32 kvm_hypercall_start; - struct device_node *hyper_node; - u32 *insts; - int len, i; - - hyper_node = of_find_node_by_path("/hypervisor"); - if (!hyper_node) - return -1; - - insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len); - if (len % 4) - return -1; - if (len > (4 * 4)) - return -1; - - for (i = 0; i < (len / 4); i++) - kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]); - - return 0; -} - static __init void kvm_free_tmp(void) { unsigned long start, end; @@ -791,7 +769,7 @@ static int __init kvm_guest_init(void) if (!kvm_para_available()) goto free_tmp; - if (kvm_para_setup()) + if (!epapr_paravirt_enabled) goto free_tmp; if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE)) diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S index e291cf3..e100ff3 100644 --- a/arch/powerpc/kernel/kvm_emul.S +++ b/arch/powerpc/kernel/kvm_emul.S @@ -24,16 +24,6 @@ #include <asm/page.h> #include <asm/asm-offsets.h> -/* Hypercall entry point. Will be patched with device tree instructions. */ - -.global kvm_hypercall_start -kvm_hypercall_start: - li r3, -1 - nop - nop - nop - blr - #define KVM_MAGIC_PAGE (-4096) #ifdef CONFIG_64BIT @@ -132,7 +122,7 @@ kvm_emulate_mtmsrd_len: .long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4 -#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI) +#define MSR_SAFE_BITS (MSR_EE | MSR_RI) #define MSR_CRITICAL_BITS ~MSR_SAFE_BITS .global kvm_emulate_mtmsr diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 386d57f..407e293 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -179,7 +179,7 @@ _GLOBAL(low_choose_750fx_pll) mtspr SPRN_HID1,r4 /* Store new HID1 image */ - rlwinm r6,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r6, r1) lwz r6,TI_CPU(r6) slwi r6,r6,2 addis r6,r6,nap_save_hid1@ha @@ -699,7 +699,7 @@ _GLOBAL(kernel_thread) #ifdef CONFIG_SMP _GLOBAL(start_secondary_resume) /* Reset stack */ - rlwinm r1,r1,0,0,(31-THREAD_SHIFT) /* current_thread_info() */ + CURRENT_THREAD_INFO(r1, r1) addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD li r3,0 stw r3,0(r1) /* Zero the stack frame pointer */ diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 616921e..565b786 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -301,11 +301,6 @@ _GLOBAL(real_writeb) #ifdef CONFIG_PPC_PASEMI -/* No support in all binutils for these yet, so use defines */ -#define LBZCIX(RT,RA,RB) .long (0x7c0006aa|(RT<<21)|(RA<<16)|(RB << 11)) -#define STBCIX(RS,RA,RB) .long (0x7c0007aa|(RS<<21)|(RA<<16)|(RB << 11)) - - _GLOBAL(real_205_readb) mfmsr r7 ori r0,r7,MSR_DR @@ -314,7 +309,7 @@ _GLOBAL(real_205_readb) mtmsrd r0 sync isync - LBZCIX(r3,0,r3) + LBZCIX(R3,R0,R3) isync mtmsrd r7 sync @@ -329,7 +324,7 @@ _GLOBAL(real_205_writeb) mtmsrd r0 sync isync - STBCIX(r3,0,r4) + STBCIX(R3,R0,R4) isync mtmsrd r7 sync diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 8e78e93..2aa04f2 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -200,11 +200,6 @@ int pcibios_add_platform_entries(struct pci_dev *pdev) return device_create_file(&pdev->dev, &dev_attr_devspec); } -char __devinit *pcibios_setup(char *str) -{ - return str; -} - /* * Reads the interrupt pin to determine if interrupt is use by card. * If the interrupt is used, then gets the interrupt line from the @@ -248,8 +243,7 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) } else { pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", oirq.size, oirq.specifier[0], oirq.specifier[1], - oirq.controller ? oirq.controller->full_name : - "<default>"); + of_node_full_name(oirq.controller)); virq = irq_create_of_mapping(oirq.controller, oirq.specifier, oirq.size); @@ -1628,8 +1622,7 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) struct device_node *node = hose->dn; int mode; - pr_debug("PCI: Scanning PHB %s\n", - node ? node->full_name : "<NO NAME>"); + pr_debug("PCI: Scanning PHB %s\n", of_node_full_name(node)); /* Get some IO space for the new PHB */ pcibios_setup_phb_io_space(hose); @@ -1637,6 +1630,11 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) /* Wire up PHB bus resources */ pcibios_setup_phb_resources(hose, &resources); + hose->busn.start = hose->first_busno; + hose->busn.end = hose->last_busno; + hose->busn.flags = IORESOURCE_BUS; + pci_add_resource(&resources, &hose->busn); + /* Create an empty bus for the toplevel */ bus = pci_create_root_bus(hose->parent, hose->first_busno, hose->ops, hose, &resources); @@ -1646,7 +1644,6 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) pci_free_resource_list(&resources); return; } - bus->secondary = hose->first_busno; hose->bus = bus; /* Get probe mode and perform scan */ @@ -1654,13 +1651,14 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose) if (node && ppc_md.pci_probe_mode) mode = ppc_md.pci_probe_mode(bus); pr_debug(" probe mode: %d\n", mode); - if (mode == PCI_PROBE_DEVTREE) { - bus->subordinate = hose->last_busno; + if (mode == PCI_PROBE_DEVTREE) of_scan_bus(node, bus); - } - if (mode == PCI_PROBE_NORMAL) - hose->last_busno = bus->subordinate = pci_scan_child_bus(bus); + if (mode == PCI_PROBE_NORMAL) { + pci_bus_update_busn_res_end(bus, 255); + hose->last_busno = pci_scan_child_bus(bus); + pci_bus_update_busn_res_end(bus, hose->last_busno); + } /* Platform gets a chance to do some global fixups before * we proceed to resource allocation diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 94a54f6..4ff190f 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -236,7 +236,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, for (ln = pci_root_buses.next; ln != &pci_root_buses; ln = ln->next) { bus = pci_bus_b(ln); - if (in_bus >= bus->number && in_bus <= bus->subordinate) + if (in_bus >= bus->number && in_bus <= bus->busn_res.end) break; bus = NULL; } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 89dde17..30378a1 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -198,7 +198,6 @@ EXPORT_SYMBOL(of_create_pci_dev); /** * of_scan_pci_bridge - Set up a PCI bridge and scan for child nodes - * @node: device tree node of bridge * @dev: pci_dev structure for the bridge * * of_scan_bus() calls this routine for each PCI bridge that it finds, and @@ -240,7 +239,7 @@ void __devinit of_scan_pci_bridge(struct pci_dev *dev) } bus->primary = dev->bus->number; - bus->subordinate = busrange[1]; + pci_bus_insert_busn_res(bus, busrange[0], busrange[1]); bus->bridge_ctl = 0; /* parse ranges property */ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index afd4f05..bdc499c 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -720,6 +720,33 @@ static int powerpc_debugfs_init(void) arch_initcall(powerpc_debugfs_init); #endif +#ifdef CONFIG_BOOKE_WDT +extern u32 booke_wdt_enabled; +extern u32 booke_wdt_period; + +/* Checks wdt=x and wdt_period=xx command-line option */ +notrace int __init early_parse_wdt(char *p) +{ + if (p && strncmp(p, "0", 1) != 0) + booke_wdt_enabled = 1; + + return 0; +} +early_param("wdt", early_parse_wdt); + +int __init early_parse_wdt_period(char *p) +{ + unsigned long ret; + if (p) { + if (!kstrtol(p, 0, &ret)) + booke_wdt_period = ret; + } + + return 0; +} +early_param("wdt_period", early_parse_wdt_period); +#endif /* CONFIG_BOOKE_WDT */ + void ppc_printk_progress(char *s, unsigned short hex) { pr_info("%s\n", s); diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index ec8a53f..a8f54ec 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -149,30 +149,6 @@ notrace void __init machine_init(u64 dt_ptr) ppc_md.progress("id mach(): done", 0x200); } -#ifdef CONFIG_BOOKE_WDT -extern u32 booke_wdt_enabled; -extern u32 booke_wdt_period; - -/* Checks wdt=x and wdt_period=xx command-line option */ -notrace int __init early_parse_wdt(char *p) -{ - if (p && strncmp(p, "0", 1) != 0) - booke_wdt_enabled = 1; - - return 0; -} -early_param("wdt", early_parse_wdt); - -int __init early_parse_wdt_period (char *p) -{ - if (p) - booke_wdt_period = simple_strtoul(p, NULL, 0); - - return 0; -} -early_param("wdt_period", early_parse_wdt_period); -#endif /* CONFIG_BOOKE_WDT */ - /* Checks "l2cr=xxxx" command-line option */ int __init ppc_setup_l2cr(char *str) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e1417c4..0321007 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -48,6 +48,7 @@ #ifdef CONFIG_PPC64 #include <asm/paca.h> #endif +#include <asm/vdso.h> #include <asm/debug.h> #ifdef DEBUG @@ -570,6 +571,8 @@ void __devinit start_secondary(void *unused) #ifdef CONFIG_PPC64 if (system_state == SYSTEM_RUNNING) vdso_data->processorCount++; + + vdso_getcpu_init(); #endif notify_cpu_starting(cpu); set_cpu_online(cpu, true); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 9eb5b9b..b67db22 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -706,6 +706,34 @@ static void __init vdso_setup_syscall_map(void) } } +#ifdef CONFIG_PPC64 +int __cpuinit vdso_getcpu_init(void) +{ + unsigned long cpu, node, val; + + /* + * SPRG3 contains the CPU in the bottom 16 bits and the NUMA node in + * the next 16 bits. The VDSO uses this to implement getcpu(). + */ + cpu = get_cpu(); + WARN_ON_ONCE(cpu > 0xffff); + + node = cpu_to_node(cpu); + WARN_ON_ONCE(node > 0xffff); + + val = (cpu & 0xfff) | ((node & 0xffff) << 16); + mtspr(SPRN_SPRG3, val); +#ifdef CONFIG_KVM_BOOK3S_HANDLER + get_paca()->kvm_hstate.sprg3 = val; +#endif + + put_cpu(); + + return 0; +} +/* We need to call this before SMP init */ +early_initcall(vdso_getcpu_init); +#endif static int __init vdso_init(void) { diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 9a7946c..53e6c9b 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -1,7 +1,9 @@ # List of files in the vdso, has to be asm only for now -obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o +obj-vdso32-$(CONFIG_PPC64) = getcpu.o +obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \ + $(obj-vdso32-y) # Build rules diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S new file mode 100644 index 0000000..47afd08 --- /dev/null +++ b/arch/powerpc/kernel/vdso32/getcpu.S @@ -0,0 +1,45 @@ +/* + * 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) IBM Corporation, 2012 + * + * Author: Anton Blanchard <anton@au.ibm.com> + */ +#include <asm/ppc_asm.h> +#include <asm/vdso.h> + + .text +/* + * Exact prototype of getcpu + * + * int __kernel_getcpu(unsigned *cpu, unsigned *node); + * + */ +V_FUNCTION_BEGIN(__kernel_getcpu) + .cfi_startproc + mfspr r5,SPRN_USPRG3 + cmpdi cr0,r3,0 + cmpdi cr1,r4,0 + clrlwi r6,r5,16 + rlwinm r7,r5,16,31-15,31-0 + beq cr0,1f + stw r6,0(r3) +1: beq cr1,2f + stw r7,0(r4) +2: crclr cr0*4+so + li r3,0 /* always success */ + blr + .cfi_endproc +V_FUNCTION_END(__kernel_getcpu) diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 0546bcd..43200ba 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -147,6 +147,9 @@ VERSION __kernel_sync_dicache_p5; __kernel_sigtramp32; __kernel_sigtramp_rt32; +#ifdef CONFIG_PPC64 + __kernel_getcpu; +#endif local: *; }; diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 8c500d8..effca94 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -1,6 +1,6 @@ # List of files in the vdso, has to be asm only for now -obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o +obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o # Build rules diff --git a/arch/powerpc/kernel/vdso64/getcpu.S b/arch/powerpc/kernel/vdso64/getcpu.S new file mode 100644 index 0000000..47afd08 --- /dev/null +++ b/arch/powerpc/kernel/vdso64/getcpu.S @@ -0,0 +1,45 @@ +/* + * 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) IBM Corporation, 2012 + * + * Author: Anton Blanchard <anton@au.ibm.com> + */ +#include <asm/ppc_asm.h> +#include <asm/vdso.h> + + .text +/* + * Exact prototype of getcpu + * + * int __kernel_getcpu(unsigned *cpu, unsigned *node); + * + */ +V_FUNCTION_BEGIN(__kernel_getcpu) + .cfi_startproc + mfspr r5,SPRN_USPRG3 + cmpdi cr0,r3,0 + cmpdi cr1,r4,0 + clrlwi r6,r5,16 + rlwinm r7,r5,16,31-15,31-0 + beq cr0,1f + stw r6,0(r3) +1: beq cr1,2f + stw r7,0(r4) +2: crclr cr0*4+so + li r3,0 /* always success */ + blr + .cfi_endproc +V_FUNCTION_END(__kernel_getcpu) diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 0e61540..e6c1758 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -146,6 +146,7 @@ VERSION __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp_rt64; + __kernel_getcpu; local: *; }; diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index cb87301..3052a93 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -37,8 +37,6 @@ #include <asm/page.h> #include <asm/hvcall.h> -static struct bus_type vio_bus_type; - static struct vio_dev vio_bus_device = { /* fake "parent" device */ .name = "vio", .type = "", @@ -625,7 +623,7 @@ struct dma_map_ops vio_dma_mapping_ops = { * vio_cmo_set_dev_desired - Set desired entitlement for a device * * @viodev: struct vio_dev for device to alter - * @new_desired: new desired entitlement level in bytes + * @desired: new desired entitlement level in bytes * * For use by devices to request a change to their entitlement at runtime or * through sysfs. The desired entitlement level is changed and a balancing @@ -1262,7 +1260,7 @@ static int vio_bus_remove(struct device *dev) /** * vio_register_driver: - Register a new vio driver - * @drv: The vio_driver structure to be registered. + * @viodrv: The vio_driver structure to be registered. */ int __vio_register_driver(struct vio_driver *viodrv, struct module *owner, const char *mod_name) @@ -1282,7 +1280,7 @@ EXPORT_SYMBOL(__vio_register_driver); /** * vio_unregister_driver - Remove registration of vio driver. - * @driver: The vio_driver struct to be removed form registration + * @viodrv: The vio_driver struct to be removed form registration */ void vio_unregister_driver(struct vio_driver *viodrv) { @@ -1296,8 +1294,7 @@ static void __devinit vio_dev_release(struct device *dev) struct iommu_table *tbl = get_iommu_table_base(dev); if (tbl) - iommu_free_table(tbl, dev->of_node ? - dev->of_node->full_name : dev_name(dev)); + iommu_free_table(tbl, of_node_full_name(dev->of_node)); of_node_put(dev->of_node); kfree(to_vio_dev(dev)); } @@ -1397,21 +1394,27 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) viodev->name = of_node->name; viodev->dev.of_node = of_node_get(of_node); - if (firmware_has_feature(FW_FEATURE_CMO)) - vio_cmo_set_dma_ops(viodev); - else - set_dma_ops(&viodev->dev, &dma_iommu_ops); - set_iommu_table_base(&viodev->dev, vio_build_iommu_table(viodev)); set_dev_node(&viodev->dev, of_node_to_nid(of_node)); /* init generic 'struct device' fields: */ viodev->dev.parent = &vio_bus_device.dev; viodev->dev.bus = &vio_bus_type; viodev->dev.release = vio_dev_release; - /* needed to ensure proper operation of coherent allocations - * later, in case driver doesn't set it explicitly */ - dma_set_mask(&viodev->dev, DMA_BIT_MASK(64)); - dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64)); + + if (of_get_property(viodev->dev.of_node, "ibm,my-dma-window", NULL)) { + if (firmware_has_feature(FW_FEATURE_CMO)) + vio_cmo_set_dma_ops(viodev); + else + set_dma_ops(&viodev->dev, &dma_iommu_ops); + + set_iommu_table_base(&viodev->dev, + vio_build_iommu_table(viodev)); + + /* needed to ensure proper operation of coherent allocations + * later, in case driver doesn't set it explicitly */ + dma_set_mask(&viodev->dev, DMA_BIT_MASK(64)); + dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64)); + } /* register with generic device framework */ if (device_register(&viodev->dev)) { @@ -1491,12 +1494,18 @@ static int __init vio_bus_init(void) if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_bus_init(); + return 0; +} +postcore_initcall(vio_bus_init); + +static int __init vio_device_init(void) +{ vio_bus_scan_register_devices("vdevice"); vio_bus_scan_register_devices("ibm,platform-facilities"); return 0; } -__initcall(vio_bus_init); +device_initcall(vio_device_init); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1509,7 +1518,7 @@ static ssize_t devspec_show(struct device *dev, { struct device_node *of_node = dev->of_node; - return sprintf(buf, "%s\n", of_node ? of_node->full_name : "none"); + return sprintf(buf, "%s\n", of_node_full_name(of_node)); } static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, @@ -1568,7 +1577,7 @@ static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) return 0; } -static struct bus_type vio_bus_type = { +struct bus_type vio_bus_type = { .name = "vio", .dev_attrs = vio_dev_attrs, .uevent = vio_hotplug, diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 80a5775..d03eb6f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -37,56 +37,121 @@ /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */ #define MAX_LPID_970 63 -long kvmppc_alloc_hpt(struct kvm *kvm) +/* Power architecture requires HPT is at least 256kB */ +#define PPC_MIN_HPT_ORDER 18 + +long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) { unsigned long hpt; - long lpid; struct revmap_entry *rev; struct kvmppc_linear_info *li; + long order = kvm_hpt_order; - /* Allocate guest's hashed page table */ - li = kvm_alloc_hpt(); - if (li) { - /* using preallocated memory */ - hpt = (ulong)li->base_virt; - kvm->arch.hpt_li = li; - } else { - /* using dynamic memory */ + if (htab_orderp) { + order = *htab_orderp; + if (order < PPC_MIN_HPT_ORDER) + order = PPC_MIN_HPT_ORDER; + } + + /* + * If the user wants a different size from default, + * try first to allocate it from the kernel page allocator. + */ + hpt = 0; + if (order != kvm_hpt_order) { hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| - __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT); + __GFP_NOWARN, order - PAGE_SHIFT); + if (!hpt) + --order; } + /* Next try to allocate from the preallocated pool */ if (!hpt) { - pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n"); - return -ENOMEM; + li = kvm_alloc_hpt(); + if (li) { + hpt = (ulong)li->base_virt; + kvm->arch.hpt_li = li; + order = kvm_hpt_order; + } } + + /* Lastly try successively smaller sizes from the page allocator */ + while (!hpt && order > PPC_MIN_HPT_ORDER) { + hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| + __GFP_NOWARN, order - PAGE_SHIFT); + if (!hpt) + --order; + } + + if (!hpt) + return -ENOMEM; + kvm->arch.hpt_virt = hpt; + kvm->arch.hpt_order = order; + /* HPTEs are 2**4 bytes long */ + kvm->arch.hpt_npte = 1ul << (order - 4); + /* 128 (2**7) bytes in each HPTEG */ + kvm->arch.hpt_mask = (1ul << (order - 7)) - 1; /* Allocate reverse map array */ - rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE); + rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte); if (!rev) { pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n"); goto out_freehpt; } kvm->arch.revmap = rev; + kvm->arch.sdr1 = __pa(hpt) | (order - 18); - lpid = kvmppc_alloc_lpid(); - if (lpid < 0) - goto out_freeboth; + pr_info("KVM guest htab at %lx (order %ld), LPID %x\n", + hpt, order, kvm->arch.lpid); - kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18); - kvm->arch.lpid = lpid; - - pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid); + if (htab_orderp) + *htab_orderp = order; return 0; - out_freeboth: - vfree(rev); out_freehpt: - free_pages(hpt, HPT_ORDER - PAGE_SHIFT); + if (kvm->arch.hpt_li) + kvm_release_hpt(kvm->arch.hpt_li); + else + free_pages(hpt, order - PAGE_SHIFT); return -ENOMEM; } +long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp) +{ + long err = -EBUSY; + long order; + + mutex_lock(&kvm->lock); + if (kvm->arch.rma_setup_done) { + kvm->arch.rma_setup_done = 0; + /* order rma_setup_done vs. vcpus_running */ + smp_mb(); + if (atomic_read(&kvm->arch.vcpus_running)) { + kvm->arch.rma_setup_done = 1; + goto out; + } + } + if (kvm->arch.hpt_virt) { + order = kvm->arch.hpt_order; + /* Set the entire HPT to 0, i.e. invalid HPTEs */ + memset((void *)kvm->arch.hpt_virt, 0, 1ul << order); + /* + * Set the whole last_vcpu array to an invalid vcpu number. + * This ensures that each vcpu will flush its TLB on next entry. + */ + memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu)); + *htab_orderp = order; + err = 0; + } else { + err = kvmppc_alloc_hpt(kvm, htab_orderp); + order = *htab_orderp; + } + out: + mutex_unlock(&kvm->lock); + return err; +} + void kvmppc_free_hpt(struct kvm *kvm) { kvmppc_free_lpid(kvm->arch.lpid); @@ -94,7 +159,8 @@ void kvmppc_free_hpt(struct kvm *kvm) if (kvm->arch.hpt_li) kvm_release_hpt(kvm->arch.hpt_li); else - free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT); + free_pages(kvm->arch.hpt_virt, + kvm->arch.hpt_order - PAGE_SHIFT); } /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */ @@ -119,6 +185,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, unsigned long psize; unsigned long hp0, hp1; long ret; + struct kvm *kvm = vcpu->kvm; psize = 1ul << porder; npages = memslot->npages >> (porder - PAGE_SHIFT); @@ -127,8 +194,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, if (npages > 1ul << (40 - porder)) npages = 1ul << (40 - porder); /* Can't use more than 1 HPTE per HPTEG */ - if (npages > HPT_NPTEG) - npages = HPT_NPTEG; + if (npages > kvm->arch.hpt_mask + 1) + npages = kvm->arch.hpt_mask + 1; hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) | HPTE_V_BOLTED | hpte0_pgsize_encoding(psize); @@ -138,7 +205,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, for (i = 0; i < npages; ++i) { addr = i << porder; /* can't use hpt_hash since va > 64 bits */ - hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK; + hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask; /* * We assume that the hash table is empty and no * vcpus are using it at this stage. Since we create diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 3abe1b86..83e929e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -56,7 +56,7 @@ /* #define EXIT_DEBUG_INT */ static void kvmppc_end_cede(struct kvm_vcpu *vcpu); -static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu); +static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { @@ -1104,11 +1104,15 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) return -EINTR; } - /* On the first time here, set up VRMA or RMA */ + atomic_inc(&vcpu->kvm->arch.vcpus_running); + /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */ + smp_mb(); + + /* On the first time here, set up HTAB and VRMA or RMA */ if (!vcpu->kvm->arch.rma_setup_done) { - r = kvmppc_hv_setup_rma(vcpu); + r = kvmppc_hv_setup_htab_rma(vcpu); if (r) - return r; + goto out; } flush_fp_to_thread(current); @@ -1126,6 +1130,9 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); } } while (r == RESUME_GUEST); + + out: + atomic_dec(&vcpu->kvm->arch.vcpus_running); return r; } @@ -1341,7 +1348,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, { } -static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu) +static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { int err = 0; struct kvm *kvm = vcpu->kvm; @@ -1360,6 +1367,15 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu) if (kvm->arch.rma_setup_done) goto out; /* another vcpu beat us to it */ + /* Allocate hashed page table (if not done already) and reset it */ + if (!kvm->arch.hpt_virt) { + err = kvmppc_alloc_hpt(kvm, NULL); + if (err) { + pr_err("KVM: Couldn't alloc HPT\n"); + goto out; + } + } + /* Look up the memslot for guest physical address 0 */ memslot = gfn_to_memslot(kvm, 0); @@ -1471,13 +1487,14 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu) int kvmppc_core_init_vm(struct kvm *kvm) { - long r; - unsigned long lpcr; + unsigned long lpcr, lpid; - /* Allocate hashed page table */ - r = kvmppc_alloc_hpt(kvm); - if (r) - return r; + /* Allocate the guest's logical partition ID */ + + lpid = kvmppc_alloc_lpid(); + if (lpid < 0) + return -ENOMEM; + kvm->arch.lpid = lpid; INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables); @@ -1487,7 +1504,6 @@ int kvmppc_core_init_vm(struct kvm *kvm) if (cpu_has_feature(CPU_FTR_ARCH_201)) { /* PPC970; HID4 is effectively the LPCR */ - unsigned long lpid = kvm->arch.lpid; kvm->arch.host_lpid = 0; kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4); lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH)); diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index e1b60f5..fb4eac2 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -25,6 +25,9 @@ static void __init kvm_linear_init_one(ulong size, int count, int type); static struct kvmppc_linear_info *kvm_alloc_linear(int type); static void kvm_release_linear(struct kvmppc_linear_info *ri); +int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER; +EXPORT_SYMBOL_GPL(kvm_hpt_order); + /*************** RMA *************/ /* @@ -209,7 +212,7 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri) void __init kvm_linear_init(void) { /* HPT */ - kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT); + kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT); /* RMA */ /* Only do this on PPC970 in HV mode */ diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index cec4dad..5c70d19 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -237,7 +237,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, /* Find and lock the HPTEG slot to use */ do_insert: - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; if (likely((flags & H_EXACT) == 0)) { pte_index &= ~7UL; @@ -352,7 +352,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags, unsigned long v, r, rb; struct revmap_entry *rev; - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); while (!try_lock_hpte(hpte, HPTE_V_HVLOCK)) @@ -419,7 +419,8 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) i = 4; break; } - if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) { + if (req != 1 || flags == 3 || + pte_index >= kvm->arch.hpt_npte) { /* parameter error */ args[j] = ((0xa0 | flags) << 56) + pte_index; ret = H_PARAMETER; @@ -521,7 +522,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, struct revmap_entry *rev; unsigned long v, r, rb, mask, bits; - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4)); @@ -583,7 +584,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags, int i, n = 1; struct revmap_entry *rev = NULL; - if (pte_index >= HPT_NPTE) + if (pte_index >= kvm->arch.hpt_npte) return H_PARAMETER; if (flags & H_READ_4) { pte_index &= ~3; @@ -678,7 +679,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, somask = (1UL << 28) - 1; vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT; } - hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK; + hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask; avpn = slb_v & ~(somask >> 16); /* also includes B */ avpn |= (eaddr & somask) >> 16; @@ -723,7 +724,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v, if (val & HPTE_V_SECONDARY) break; val |= HPTE_V_SECONDARY; - hash = hash ^ HPT_HASH_MASK; + hash = hash ^ kvm->arch.hpt_mask; } return -1; } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index a1044f4..5a84c8d 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -72,9 +72,6 @@ _GLOBAL(kvmppc_hv_entry_trampoline) mtsrr1 r6 RFI -#define ULONG_SIZE 8 -#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) - /****************************************************************************** * * * Entry code * @@ -206,24 +203,24 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) /* Load up FP, VMX and VSX registers */ bl kvmppc_load_fp - ld r14, VCPU_GPR(r14)(r4) - ld r15, VCPU_GPR(r15)(r4) - ld r16, VCPU_GPR(r16)(r4) - ld r17, VCPU_GPR(r17)(r4) - ld r18, VCPU_GPR(r18)(r4) - ld r19, VCPU_GPR(r19)(r4) - ld r20, VCPU_GPR(r20)(r4) - ld r21, VCPU_GPR(r21)(r4) - ld r22, VCPU_GPR(r22)(r4) - ld r23, VCPU_GPR(r23)(r4) - ld r24, VCPU_GPR(r24)(r4) - ld r25, VCPU_GPR(r25)(r4) - ld r26, VCPU_GPR(r26)(r4) - ld r27, VCPU_GPR(r27)(r4) - ld r28, VCPU_GPR(r28)(r4) - ld r29, VCPU_GPR(r29)(r4) - ld r30, VCPU_GPR(r30)(r4) - ld r31, VCPU_GPR(r31)(r4) + ld r14, VCPU_GPR(R14)(r4) + ld r15, VCPU_GPR(R15)(r4) + ld r16, VCPU_GPR(R16)(r4) + ld r17, VCPU_GPR(R17)(r4) + ld r18, VCPU_GPR(R18)(r4) + ld r19, VCPU_GPR(R19)(r4) + ld r20, VCPU_GPR(R20)(r4) + ld r21, VCPU_GPR(R21)(r4) + ld r22, VCPU_GPR(R22)(r4) + ld r23, VCPU_GPR(R23)(r4) + ld r24, VCPU_GPR(R24)(r4) + ld r25, VCPU_GPR(R25)(r4) + ld r26, VCPU_GPR(R26)(r4) + ld r27, VCPU_GPR(R27)(r4) + ld r28, VCPU_GPR(R28)(r4) + ld r29, VCPU_GPR(R29)(r4) + ld r30, VCPU_GPR(R30)(r4) + ld r31, VCPU_GPR(R31)(r4) BEGIN_FTR_SECTION /* Switch DSCR to guest value */ @@ -547,21 +544,21 @@ fast_guest_return: mtlr r5 mtcr r6 - ld r0, VCPU_GPR(r0)(r4) - ld r1, VCPU_GPR(r1)(r4) - ld r2, VCPU_GPR(r2)(r4) - ld r3, VCPU_GPR(r3)(r4) - ld r5, VCPU_GPR(r5)(r4) - ld r6, VCPU_GPR(r6)(r4) - ld r7, VCPU_GPR(r7)(r4) - ld r8, VCPU_GPR(r8)(r4) - ld r9, VCPU_GPR(r9)(r4) - ld r10, VCPU_GPR(r10)(r4) - ld r11, VCPU_GPR(r11)(r4) - ld r12, VCPU_GPR(r12)(r4) - ld r13, VCPU_GPR(r13)(r4) - - ld r4, VCPU_GPR(r4)(r4) + ld r0, VCPU_GPR(R0)(r4) + ld r1, VCPU_GPR(R1)(r4) + ld r2, VCPU_GPR(R2)(r4) + ld r3, VCPU_GPR(R3)(r4) + ld r5, VCPU_GPR(R5)(r4) + ld r6, VCPU_GPR(R6)(r4) + ld r7, VCPU_GPR(R7)(r4) + ld r8, VCPU_GPR(R8)(r4) + ld r9, VCPU_GPR(R9)(r4) + ld r10, VCPU_GPR(R10)(r4) + ld r11, VCPU_GPR(R11)(r4) + ld r12, VCPU_GPR(R12)(r4) + ld r13, VCPU_GPR(R13)(r4) + + ld r4, VCPU_GPR(R4)(r4) hrfid b . @@ -590,22 +587,22 @@ kvmppc_interrupt: /* Save registers */ - std r0, VCPU_GPR(r0)(r9) - std r1, VCPU_GPR(r1)(r9) - std r2, VCPU_GPR(r2)(r9) - std r3, VCPU_GPR(r3)(r9) - std r4, VCPU_GPR(r4)(r9) - std r5, VCPU_GPR(r5)(r9) - std r6, VCPU_GPR(r6)(r9) - std r7, VCPU_GPR(r7)(r9) - std r8, VCPU_GPR(r8)(r9) + std r0, VCPU_GPR(R0)(r9) + std r1, VCPU_GPR(R1)(r9) + std r2, VCPU_GPR(R2)(r9) + std r3, VCPU_GPR(R3)(r9) + std r4, VCPU_GPR(R4)(r9) + std r5, VCPU_GPR(R5)(r9) + std r6, VCPU_GPR(R6)(r9) + std r7, VCPU_GPR(R7)(r9) + std r8, VCPU_GPR(R8)(r9) ld r0, HSTATE_HOST_R2(r13) - std r0, VCPU_GPR(r9)(r9) - std r10, VCPU_GPR(r10)(r9) - std r11, VCPU_GPR(r11)(r9) + std r0, VCPU_GPR(R9)(r9) + std r10, VCPU_GPR(R10)(r9) + std r11, VCPU_GPR(R11)(r9) ld r3, HSTATE_SCRATCH0(r13) lwz r4, HSTATE_SCRATCH1(r13) - std r3, VCPU_GPR(r12)(r9) + std r3, VCPU_GPR(R12)(r9) stw r4, VCPU_CR(r9) /* Restore R1/R2 so we can handle faults */ @@ -626,7 +623,7 @@ kvmppc_interrupt: GET_SCRATCH0(r3) mflr r4 - std r3, VCPU_GPR(r13)(r9) + std r3, VCPU_GPR(R13)(r9) std r4, VCPU_LR(r9) /* Unset guest mode */ @@ -968,24 +965,24 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) /* Save non-volatile GPRs */ - std r14, VCPU_GPR(r14)(r9) - std r15, VCPU_GPR(r15)(r9) - std r16, VCPU_GPR(r16)(r9) - std r17, VCPU_GPR(r17)(r9) - std r18, VCPU_GPR(r18)(r9) - std r19, VCPU_GPR(r19)(r9) - std r20, VCPU_GPR(r20)(r9) - std r21, VCPU_GPR(r21)(r9) - std r22, VCPU_GPR(r22)(r9) - std r23, VCPU_GPR(r23)(r9) - std r24, VCPU_GPR(r24)(r9) - std r25, VCPU_GPR(r25)(r9) - std r26, VCPU_GPR(r26)(r9) - std r27, VCPU_GPR(r27)(r9) - std r28, VCPU_GPR(r28)(r9) - std r29, VCPU_GPR(r29)(r9) - std r30, VCPU_GPR(r30)(r9) - std r31, VCPU_GPR(r31)(r9) + std r14, VCPU_GPR(R14)(r9) + std r15, VCPU_GPR(R15)(r9) + std r16, VCPU_GPR(R16)(r9) + std r17, VCPU_GPR(R17)(r9) + std r18, VCPU_GPR(R18)(r9) + std r19, VCPU_GPR(R19)(r9) + std r20, VCPU_GPR(R20)(r9) + std r21, VCPU_GPR(R21)(r9) + std r22, VCPU_GPR(R22)(r9) + std r23, VCPU_GPR(R23)(r9) + std r24, VCPU_GPR(R24)(r9) + std r25, VCPU_GPR(R25)(r9) + std r26, VCPU_GPR(R26)(r9) + std r27, VCPU_GPR(R27)(r9) + std r28, VCPU_GPR(R28)(r9) + std r29, VCPU_GPR(R29)(r9) + std r30, VCPU_GPR(R30)(r9) + std r31, VCPU_GPR(R31)(r9) /* Save SPRGs */ mfspr r3, SPRN_SPRG0 @@ -1067,6 +1064,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) mtspr SPRN_DABR,r5 mtspr SPRN_DABRX,r6 + /* Restore SPRG3 */ + ld r3,HSTATE_SPRG3(r13) + mtspr SPRN_SPRG3,r3 + /* * Reload DEC. HDEC interrupts were disabled when * we reloaded the host's LPCR value. @@ -1160,7 +1161,7 @@ kvmppc_hdsi: andi. r0, r11, MSR_DR /* data relocation enabled? */ beq 3f clrrdi r0, r4, 28 - PPC_SLBFEE_DOT(r5, r0) /* if so, look up SLB */ + PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */ bne 1f /* if no SLB entry found */ 4: std r4, VCPU_FAULT_DAR(r9) stw r6, VCPU_FAULT_DSISR(r9) @@ -1234,7 +1235,7 @@ kvmppc_hisi: andi. r0, r11, MSR_IR /* instruction relocation enabled? */ beq 3f clrrdi r0, r10, 28 - PPC_SLBFEE_DOT(r5, r0) /* if so, look up SLB */ + PPC_SLBFEE_DOT(R5, R0) /* if so, look up SLB */ bne 1f /* if no SLB entry found */ 4: /* Search the hash table. */ @@ -1278,7 +1279,7 @@ kvmppc_hisi: */ .globl hcall_try_real_mode hcall_try_real_mode: - ld r3,VCPU_GPR(r3)(r9) + ld r3,VCPU_GPR(R3)(r9) andi. r0,r11,MSR_PR bne hcall_real_cont clrrdi r3,r3,2 @@ -1291,12 +1292,12 @@ hcall_try_real_mode: add r3,r3,r4 mtctr r3 mr r3,r9 /* get vcpu pointer */ - ld r4,VCPU_GPR(r4)(r9) + ld r4,VCPU_GPR(R4)(r9) bctrl cmpdi r3,H_TOO_HARD beq hcall_real_fallback ld r4,HSTATE_KVM_VCPU(r13) - std r3,VCPU_GPR(r3)(r4) + std r3,VCPU_GPR(R3)(r4) ld r10,VCPU_PC(r4) ld r11,VCPU_MSR(r4) b fast_guest_return @@ -1424,7 +1425,7 @@ _GLOBAL(kvmppc_h_cede) li r0,0 /* set trap to 0 to say hcall is handled */ stw r0,VCPU_TRAP(r3) li r0,H_SUCCESS - std r0,VCPU_GPR(r3)(r3) + std r0,VCPU_GPR(R3)(r3) BEGIN_FTR_SECTION b 2f /* just send it up to host on 970 */ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) @@ -1443,7 +1444,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) addi r6,r5,VCORE_NAPPING_THREADS 31: lwarx r4,0,r6 or r4,r4,r0 - PPC_POPCNTW(r7,r4) + PPC_POPCNTW(R7,R4) cmpw r7,r8 bge 2f stwcx. r4,0,r6 @@ -1464,24 +1465,24 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) * DAR, DSISR, DABR, DABRX, DSCR, PMCx, MMCRx, SIAR, SDAR. */ /* Save non-volatile GPRs */ - std r14, VCPU_GPR(r14)(r3) - std r15, VCPU_GPR(r15)(r3) - std r16, VCPU_GPR(r16)(r3) - std r17, VCPU_GPR(r17)(r3) - std r18, VCPU_GPR(r18)(r3) - std r19, VCPU_GPR(r19)(r3) - std r20, VCPU_GPR(r20)(r3) - std r21, VCPU_GPR(r21)(r3) - std r22, VCPU_GPR(r22)(r3) - std r23, VCPU_GPR(r23)(r3) - std r24, VCPU_GPR(r24)(r3) - std r25, VCPU_GPR(r25)(r3) - std r26, VCPU_GPR(r26)(r3) - std r27, VCPU_GPR(r27)(r3) - std r28, VCPU_GPR(r28)(r3) - std r29, VCPU_GPR(r29)(r3) - std r30, VCPU_GPR(r30)(r3) - std r31, VCPU_GPR(r31)(r3) + std r14, VCPU_GPR(R14)(r3) + std r15, VCPU_GPR(R15)(r3) + std r16, VCPU_GPR(R16)(r3) + std r17, VCPU_GPR(R17)(r3) + std r18, VCPU_GPR(R18)(r3) + std r19, VCPU_GPR(R19)(r3) + std r20, VCPU_GPR(R20)(r3) + std r21, VCPU_GPR(R21)(r3) + std r22, VCPU_GPR(R22)(r3) + std r23, VCPU_GPR(R23)(r3) + std r24, VCPU_GPR(R24)(r3) + std r25, VCPU_GPR(R25)(r3) + std r26, VCPU_GPR(R26)(r3) + std r27, VCPU_GPR(R27)(r3) + std r28, VCPU_GPR(R28)(r3) + std r29, VCPU_GPR(R29)(r3) + std r30, VCPU_GPR(R30)(r3) + std r31, VCPU_GPR(R31)(r3) /* save FP state */ bl .kvmppc_save_fp @@ -1513,24 +1514,24 @@ kvm_end_cede: bl kvmppc_load_fp /* Load NV GPRS */ - ld r14, VCPU_GPR(r14)(r4) - ld r15, VCPU_GPR(r15)(r4) - ld r16, VCPU_GPR(r16)(r4) - ld r17, VCPU_GPR(r17)(r4) - ld r18, VCPU_GPR(r18)(r4) - ld r19, VCPU_GPR(r19)(r4) - ld r20, VCPU_GPR(r20)(r4) - ld r21, VCPU_GPR(r21)(r4) - ld r22, VCPU_GPR(r22)(r4) - ld r23, VCPU_GPR(r23)(r4) - ld r24, VCPU_GPR(r24)(r4) - ld r25, VCPU_GPR(r25)(r4) - ld r26, VCPU_GPR(r26)(r4) - ld r27, VCPU_GPR(r27)(r4) - ld r28, VCPU_GPR(r28)(r4) - ld r29, VCPU_GPR(r29)(r4) - ld r30, VCPU_GPR(r30)(r4) - ld r31, VCPU_GPR(r31)(r4) + ld r14, VCPU_GPR(R14)(r4) + ld r15, VCPU_GPR(R15)(r4) + ld r16, VCPU_GPR(R16)(r4) + ld r17, VCPU_GPR(R17)(r4) + ld r18, VCPU_GPR(R18)(r4) + ld r19, VCPU_GPR(R19)(r4) + ld r20, VCPU_GPR(R20)(r4) + ld r21, VCPU_GPR(R21)(r4) + ld r22, VCPU_GPR(R22)(r4) + ld r23, VCPU_GPR(R23)(r4) + ld r24, VCPU_GPR(R24)(r4) + ld r25, VCPU_GPR(R25)(r4) + ld r26, VCPU_GPR(R26)(r4) + ld r27, VCPU_GPR(R27)(r4) + ld r28, VCPU_GPR(R28)(r4) + ld r29, VCPU_GPR(R29)(r4) + ld r30, VCPU_GPR(R30)(r4) + ld r31, VCPU_GPR(R31)(r4) /* clear our bit in vcore->napping_threads */ 33: ld r5,HSTATE_KVM_VCORE(r13) @@ -1649,7 +1650,7 @@ BEGIN_FTR_SECTION reg = 0 .rept 32 li r6,reg*16+VCPU_VSRS - STXVD2X(reg,r6,r3) + STXVD2X(reg,R6,R3) reg = reg + 1 .endr FTR_SECTION_ELSE @@ -1711,7 +1712,7 @@ BEGIN_FTR_SECTION reg = 0 .rept 32 li r7,reg*16+VCPU_VSRS - LXVD2X(reg,r7,r4) + LXVD2X(reg,R7,R4) reg = reg + 1 .endr FTR_SECTION_ELSE diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 3e35383..48cbbf8 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -25,38 +25,30 @@ #include <asm/exception-64s.h> #if defined(CONFIG_PPC_BOOK3S_64) - -#define ULONG_SIZE 8 #define FUNC(name) GLUE(.,name) - #elif defined(CONFIG_PPC_BOOK3S_32) - -#define ULONG_SIZE 4 #define FUNC(name) name - #endif /* CONFIG_PPC_BOOK3S_XX */ - -#define VCPU_GPR(n) (VCPU_GPRS + (n * ULONG_SIZE)) #define VCPU_LOAD_NVGPRS(vcpu) \ - PPC_LL r14, VCPU_GPR(r14)(vcpu); \ - PPC_LL r15, VCPU_GPR(r15)(vcpu); \ - PPC_LL r16, VCPU_GPR(r16)(vcpu); \ - PPC_LL r17, VCPU_GPR(r17)(vcpu); \ - PPC_LL r18, VCPU_GPR(r18)(vcpu); \ - PPC_LL r19, VCPU_GPR(r19)(vcpu); \ - PPC_LL r20, VCPU_GPR(r20)(vcpu); \ - PPC_LL r21, VCPU_GPR(r21)(vcpu); \ - PPC_LL r22, VCPU_GPR(r22)(vcpu); \ - PPC_LL r23, VCPU_GPR(r23)(vcpu); \ - PPC_LL r24, VCPU_GPR(r24)(vcpu); \ - PPC_LL r25, VCPU_GPR(r25)(vcpu); \ - PPC_LL r26, VCPU_GPR(r26)(vcpu); \ - PPC_LL r27, VCPU_GPR(r27)(vcpu); \ - PPC_LL r28, VCPU_GPR(r28)(vcpu); \ - PPC_LL r29, VCPU_GPR(r29)(vcpu); \ - PPC_LL r30, VCPU_GPR(r30)(vcpu); \ - PPC_LL r31, VCPU_GPR(r31)(vcpu); \ + PPC_LL r14, VCPU_GPR(R14)(vcpu); \ + PPC_LL r15, VCPU_GPR(R15)(vcpu); \ + PPC_LL r16, VCPU_GPR(R16)(vcpu); \ + PPC_LL r17, VCPU_GPR(R17)(vcpu); \ + PPC_LL r18, VCPU_GPR(R18)(vcpu); \ + PPC_LL r19, VCPU_GPR(R19)(vcpu); \ + PPC_LL r20, VCPU_GPR(R20)(vcpu); \ + PPC_LL r21, VCPU_GPR(R21)(vcpu); \ + PPC_LL r22, VCPU_GPR(R22)(vcpu); \ + PPC_LL r23, VCPU_GPR(R23)(vcpu); \ + PPC_LL r24, VCPU_GPR(R24)(vcpu); \ + PPC_LL r25, VCPU_GPR(R25)(vcpu); \ + PPC_LL r26, VCPU_GPR(R26)(vcpu); \ + PPC_LL r27, VCPU_GPR(R27)(vcpu); \ + PPC_LL r28, VCPU_GPR(R28)(vcpu); \ + PPC_LL r29, VCPU_GPR(R29)(vcpu); \ + PPC_LL r30, VCPU_GPR(R30)(vcpu); \ + PPC_LL r31, VCPU_GPR(R31)(vcpu); \ /***************************************************************************** * * @@ -131,24 +123,24 @@ kvmppc_handler_highmem: /* R7 = vcpu */ PPC_LL r7, GPR4(r1) - PPC_STL r14, VCPU_GPR(r14)(r7) - PPC_STL r15, VCPU_GPR(r15)(r7) - PPC_STL r16, VCPU_GPR(r16)(r7) - PPC_STL r17, VCPU_GPR(r17)(r7) - PPC_STL r18, VCPU_GPR(r18)(r7) - PPC_STL r19, VCPU_GPR(r19)(r7) - PPC_STL r20, VCPU_GPR(r20)(r7) - PPC_STL r21, VCPU_GPR(r21)(r7) - PPC_STL r22, VCPU_GPR(r22)(r7) - PPC_STL r23, VCPU_GPR(r23)(r7) - PPC_STL r24, VCPU_GPR(r24)(r7) - PPC_STL r25, VCPU_GPR(r25)(r7) - PPC_STL r26, VCPU_GPR(r26)(r7) - PPC_STL r27, VCPU_GPR(r27)(r7) - PPC_STL r28, VCPU_GPR(r28)(r7) - PPC_STL r29, VCPU_GPR(r29)(r7) - PPC_STL r30, VCPU_GPR(r30)(r7) - PPC_STL r31, VCPU_GPR(r31)(r7) + PPC_STL r14, VCPU_GPR(R14)(r7) + PPC_STL r15, VCPU_GPR(R15)(r7) + PPC_STL r16, VCPU_GPR(R16)(r7) + PPC_STL r17, VCPU_GPR(R17)(r7) + PPC_STL r18, VCPU_GPR(R18)(r7) + PPC_STL r19, VCPU_GPR(R19)(r7) + PPC_STL r20, VCPU_GPR(R20)(r7) + PPC_STL r21, VCPU_GPR(R21)(r7) + PPC_STL r22, VCPU_GPR(R22)(r7) + PPC_STL r23, VCPU_GPR(R23)(r7) + PPC_STL r24, VCPU_GPR(R24)(r7) + PPC_STL r25, VCPU_GPR(R25)(r7) + PPC_STL r26, VCPU_GPR(R26)(r7) + PPC_STL r27, VCPU_GPR(R27)(r7) + PPC_STL r28, VCPU_GPR(R28)(r7) + PPC_STL r29, VCPU_GPR(R29)(r7) + PPC_STL r30, VCPU_GPR(R30)(r7) + PPC_STL r31, VCPU_GPR(R31)(r7) /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ mr r5, r12 diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 3418758..ab523f3 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -37,7 +37,6 @@ #if defined(CONFIG_PPC_BOOK3S_64) #define FUNC(name) GLUE(.,name) -#define MTMSR_EERI(reg) mtmsrd (reg),1 .globl kvmppc_skip_interrupt kvmppc_skip_interrupt: diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 798491a..1abe478 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -23,7 +23,6 @@ #define GET_SHADOW_VCPU(reg) \ mr reg, r13 -#define MTMSR_EERI(reg) mtmsrd (reg),1 #elif defined(CONFIG_PPC_BOOK3S_32) @@ -31,7 +30,6 @@ tophys(reg, r2); \ lwz reg, (THREAD + THREAD_KVM_SVCPU)(reg); \ tophys(reg, reg) -#define MTMSR_EERI(reg) mtmsr (reg) #endif diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 72f13f4..d25a097 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -612,6 +612,12 @@ static void kvmppc_fill_pt_regs(struct pt_regs *regs) regs->link = lr; } +/* + * For interrupts needed to be handled by host interrupt handlers, + * corresponding host handler are called from here in similar way + * (but not exact) as they are called from low level handler + * (such as from arch/powerpc/kernel/head_fsl_booke.S). + */ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, unsigned int exit_nr) { @@ -639,6 +645,17 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu, kvmppc_fill_pt_regs(®s); performance_monitor_exception(®s); break; + case BOOKE_INTERRUPT_WATCHDOG: + kvmppc_fill_pt_regs(®s); +#ifdef CONFIG_BOOKE_WDT + WatchdogException(®s); +#else + unknown_exception(®s); +#endif + break; + case BOOKE_INTERRUPT_CRITICAL: + unknown_exception(®s); + break; } } @@ -683,6 +700,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, r = RESUME_GUEST; break; + case BOOKE_INTERRUPT_WATCHDOG: + r = RESUME_GUEST; + break; + case BOOKE_INTERRUPT_DOORBELL: kvmppc_account_exit(vcpu, DBELL_EXITS); r = RESUME_GUEST; @@ -1267,6 +1288,11 @@ void kvmppc_decrementer_func(unsigned long data) { struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data; + if (vcpu->arch.tcr & TCR_ARE) { + vcpu->arch.dec = vcpu->arch.decar; + kvmppc_emulate_dec(vcpu); + } + kvmppc_set_tsr_bits(vcpu, TSR_DIS); } diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c index 6c76397..12834bb 100644 --- a/arch/powerpc/kvm/booke_emulate.c +++ b/arch/powerpc/kvm/booke_emulate.c @@ -24,6 +24,7 @@ #include "booke.h" #define OP_19_XOP_RFI 50 +#define OP_19_XOP_RFCI 51 #define OP_31_XOP_MFMSR 83 #define OP_31_XOP_WRTEE 131 @@ -36,6 +37,12 @@ static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu) kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1); } +static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pc = vcpu->arch.csrr0; + kvmppc_set_msr(vcpu, vcpu->arch.csrr1); +} + int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance) { @@ -52,6 +59,12 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, *advance = 0; break; + case OP_19_XOP_RFCI: + kvmppc_emul_rfci(vcpu); + kvmppc_set_exit_type(vcpu, EMULATED_RFCI_EXITS); + *advance = 0; + break; + default: emulated = EMULATE_FAIL; break; @@ -113,6 +126,12 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) case SPRN_ESR: vcpu->arch.shared->esr = spr_val; break; + case SPRN_CSRR0: + vcpu->arch.csrr0 = spr_val; + break; + case SPRN_CSRR1: + vcpu->arch.csrr1 = spr_val; + break; case SPRN_DBCR0: vcpu->arch.dbcr0 = spr_val; break; @@ -129,6 +148,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) kvmppc_set_tcr(vcpu, spr_val); break; + case SPRN_DECAR: + vcpu->arch.decar = spr_val; + break; /* * Note: SPRG4-7 are user-readable. * These values are loaded into the real SPRGs when resuming the @@ -229,6 +251,12 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) case SPRN_ESR: *spr_val = vcpu->arch.shared->esr; break; + case SPRN_CSRR0: + *spr_val = vcpu->arch.csrr0; + break; + case SPRN_CSRR1: + *spr_val = vcpu->arch.csrr1; + break; case SPRN_DBCR0: *spr_val = vcpu->arch.dbcr0; break; diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 8feec2f..bb46b32 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -25,8 +25,6 @@ #include <asm/page.h> #include <asm/asm-offsets.h> -#define VCPU_GPR(n) (VCPU_GPRS + (n * 4)) - /* The host stack layout: */ #define HOST_R1 0 /* Implied by stwu. */ #define HOST_CALLEE_LR 4 @@ -36,8 +34,9 @@ #define HOST_R2 12 #define HOST_CR 16 #define HOST_NV_GPRS 20 -#define HOST_NV_GPR(n) (HOST_NV_GPRS + ((n - 14) * 4)) -#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + 4) +#define __HOST_NV_GPR(n) (HOST_NV_GPRS + ((n - 14) * 4)) +#define HOST_NV_GPR(n) __HOST_NV_GPR(__REG_##n) +#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(R31) + 4) #define HOST_STACK_SIZE (((HOST_MIN_STACK_SIZE + 15) / 16) * 16) /* Align. */ #define HOST_STACK_LR (HOST_STACK_SIZE + 4) /* In caller stack frame. */ @@ -53,16 +52,21 @@ (1<<BOOKE_INTERRUPT_PROGRAM) | \ (1<<BOOKE_INTERRUPT_DTLB_MISS)) -.macro KVM_HANDLER ivor_nr +.macro KVM_HANDLER ivor_nr scratch srr0 _GLOBAL(kvmppc_handler_\ivor_nr) /* Get pointer to vcpu and record exit number. */ - mtspr SPRN_SPRG_WSCRATCH0, r4 + mtspr \scratch , r4 mfspr r4, SPRN_SPRG_RVCPU - stw r5, VCPU_GPR(r5)(r4) - stw r6, VCPU_GPR(r6)(r4) + stw r3, VCPU_GPR(R3)(r4) + stw r5, VCPU_GPR(R5)(r4) + stw r6, VCPU_GPR(R6)(r4) + mfspr r3, \scratch mfctr r5 - lis r6, kvmppc_resume_host@h + stw r3, VCPU_GPR(R4)(r4) stw r5, VCPU_CTR(r4) + mfspr r3, \srr0 + lis r6, kvmppc_resume_host@h + stw r3, VCPU_PC(r4) li r5, \ivor_nr ori r6, r6, kvmppc_resume_host@l mtctr r6 @@ -70,42 +74,40 @@ _GLOBAL(kvmppc_handler_\ivor_nr) .endm _GLOBAL(kvmppc_handlers_start) -KVM_HANDLER BOOKE_INTERRUPT_CRITICAL -KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK -KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE -KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE -KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL -KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT -KVM_HANDLER BOOKE_INTERRUPT_PROGRAM -KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL -KVM_HANDLER BOOKE_INTERRUPT_SYSCALL -KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL -KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER -KVM_HANDLER BOOKE_INTERRUPT_FIT -KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG -KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS -KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS -KVM_HANDLER BOOKE_INTERRUPT_DEBUG -KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL -KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA -KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND +KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0 +KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_PROGRAM SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_SYSCALL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0 +KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0 +KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0 _GLOBAL(kvmppc_handler_len) .long kvmppc_handler_1 - kvmppc_handler_0 - /* Registers: * SPRG_SCRATCH0: guest r4 * r4: vcpu pointer * r5: KVM exit number */ _GLOBAL(kvmppc_resume_host) - stw r3, VCPU_GPR(r3)(r4) mfcr r3 stw r3, VCPU_CR(r4) - stw r7, VCPU_GPR(r7)(r4) - stw r8, VCPU_GPR(r8)(r4) - stw r9, VCPU_GPR(r9)(r4) + stw r7, VCPU_GPR(R7)(r4) + stw r8, VCPU_GPR(R8)(r4) + stw r9, VCPU_GPR(R9)(r4) li r6, 1 slw r6, r6, r5 @@ -135,23 +137,23 @@ _GLOBAL(kvmppc_resume_host) isync stw r9, VCPU_LAST_INST(r4) - stw r15, VCPU_GPR(r15)(r4) - stw r16, VCPU_GPR(r16)(r4) - stw r17, VCPU_GPR(r17)(r4) - stw r18, VCPU_GPR(r18)(r4) - stw r19, VCPU_GPR(r19)(r4) - stw r20, VCPU_GPR(r20)(r4) - stw r21, VCPU_GPR(r21)(r4) - stw r22, VCPU_GPR(r22)(r4) - stw r23, VCPU_GPR(r23)(r4) - stw r24, VCPU_GPR(r24)(r4) - stw r25, VCPU_GPR(r25)(r4) - stw r26, VCPU_GPR(r26)(r4) - stw r27, VCPU_GPR(r27)(r4) - stw r28, VCPU_GPR(r28)(r4) - stw r29, VCPU_GPR(r29)(r4) - stw r30, VCPU_GPR(r30)(r4) - stw r31, VCPU_GPR(r31)(r4) + stw r15, VCPU_GPR(R15)(r4) + stw r16, VCPU_GPR(R16)(r4) + stw r17, VCPU_GPR(R17)(r4) + stw r18, VCPU_GPR(R18)(r4) + stw r19, VCPU_GPR(R19)(r4) + stw r20, VCPU_GPR(R20)(r4) + stw r21, VCPU_GPR(R21)(r4) + stw r22, VCPU_GPR(R22)(r4) + stw r23, VCPU_GPR(R23)(r4) + stw r24, VCPU_GPR(R24)(r4) + stw r25, VCPU_GPR(R25)(r4) + stw r26, VCPU_GPR(R26)(r4) + stw r27, VCPU_GPR(R27)(r4) + stw r28, VCPU_GPR(R28)(r4) + stw r29, VCPU_GPR(R29)(r4) + stw r30, VCPU_GPR(R30)(r4) + stw r31, VCPU_GPR(R31)(r4) ..skip_inst_copy: /* Also grab DEAR and ESR before the host can clobber them. */ @@ -169,22 +171,18 @@ _GLOBAL(kvmppc_resume_host) ..skip_esr: /* Save remaining volatile guest register state to vcpu. */ - stw r0, VCPU_GPR(r0)(r4) - stw r1, VCPU_GPR(r1)(r4) - stw r2, VCPU_GPR(r2)(r4) - stw r10, VCPU_GPR(r10)(r4) - stw r11, VCPU_GPR(r11)(r4) - stw r12, VCPU_GPR(r12)(r4) - stw r13, VCPU_GPR(r13)(r4) - stw r14, VCPU_GPR(r14)(r4) /* We need a NV GPR below. */ + stw r0, VCPU_GPR(R0)(r4) + stw r1, VCPU_GPR(R1)(r4) + stw r2, VCPU_GPR(R2)(r4) + stw r10, VCPU_GPR(R10)(r4) + stw r11, VCPU_GPR(R11)(r4) + stw r12, VCPU_GPR(R12)(r4) + stw r13, VCPU_GPR(R13)(r4) + stw r14, VCPU_GPR(R14)(r4) /* We need a NV GPR below. */ mflr r3 stw r3, VCPU_LR(r4) mfxer r3 stw r3, VCPU_XER(r4) - mfspr r3, SPRN_SPRG_RSCRATCH0 - stw r3, VCPU_GPR(r4)(r4) - mfspr r3, SPRN_SRR0 - stw r3, VCPU_PC(r4) /* Restore host stack pointer and PID before IVPR, since the host * exception handlers use them. */ @@ -214,28 +212,28 @@ _GLOBAL(kvmppc_resume_host) /* Restore vcpu pointer and the nonvolatiles we used. */ mr r4, r14 - lwz r14, VCPU_GPR(r14)(r4) + lwz r14, VCPU_GPR(R14)(r4) /* Sometimes instruction emulation must restore complete GPR state. */ andi. r5, r3, RESUME_FLAG_NV beq ..skip_nv_load - lwz r15, VCPU_GPR(r15)(r4) - lwz r16, VCPU_GPR(r16)(r4) - lwz r17, VCPU_GPR(r17)(r4) - lwz r18, VCPU_GPR(r18)(r4) - lwz r19, VCPU_GPR(r19)(r4) - lwz r20, VCPU_GPR(r20)(r4) - lwz r21, VCPU_GPR(r21)(r4) - lwz r22, VCPU_GPR(r22)(r4) - lwz r23, VCPU_GPR(r23)(r4) - lwz r24, VCPU_GPR(r24)(r4) - lwz r25, VCPU_GPR(r25)(r4) - lwz r26, VCPU_GPR(r26)(r4) - lwz r27, VCPU_GPR(r27)(r4) - lwz r28, VCPU_GPR(r28)(r4) - lwz r29, VCPU_GPR(r29)(r4) - lwz r30, VCPU_GPR(r30)(r4) - lwz r31, VCPU_GPR(r31)(r4) + lwz r15, VCPU_GPR(R15)(r4) + lwz r16, VCPU_GPR(R16)(r4) + lwz r17, VCPU_GPR(R17)(r4) + lwz r18, VCPU_GPR(R18)(r4) + lwz r19, VCPU_GPR(R19)(r4) + lwz r20, VCPU_GPR(R20)(r4) + lwz r21, VCPU_GPR(R21)(r4) + lwz r22, VCPU_GPR(R22)(r4) + lwz r23, VCPU_GPR(R23)(r4) + lwz r24, VCPU_GPR(R24)(r4) + lwz r25, VCPU_GPR(R25)(r4) + lwz r26, VCPU_GPR(R26)(r4) + lwz r27, VCPU_GPR(R27)(r4) + lwz r28, VCPU_GPR(R28)(r4) + lwz r29, VCPU_GPR(R29)(r4) + lwz r30, VCPU_GPR(R30)(r4) + lwz r31, VCPU_GPR(R31)(r4) ..skip_nv_load: /* Should we return to the guest? */ @@ -257,43 +255,43 @@ heavyweight_exit: /* We already saved guest volatile register state; now save the * non-volatiles. */ - stw r15, VCPU_GPR(r15)(r4) - stw r16, VCPU_GPR(r16)(r4) - stw r17, VCPU_GPR(r17)(r4) - stw r18, VCPU_GPR(r18)(r4) - stw r19, VCPU_GPR(r19)(r4) - stw r20, VCPU_GPR(r20)(r4) - stw r21, VCPU_GPR(r21)(r4) - stw r22, VCPU_GPR(r22)(r4) - stw r23, VCPU_GPR(r23)(r4) - stw r24, VCPU_GPR(r24)(r4) - stw r25, VCPU_GPR(r25)(r4) - stw r26, VCPU_GPR(r26)(r4) - stw r27, VCPU_GPR(r27)(r4) - stw r28, VCPU_GPR(r28)(r4) - stw r29, VCPU_GPR(r29)(r4) - stw r30, VCPU_GPR(r30)(r4) - stw r31, VCPU_GPR(r31)(r4) + stw r15, VCPU_GPR(R15)(r4) + stw r16, VCPU_GPR(R16)(r4) + stw r17, VCPU_GPR(R17)(r4) + stw r18, VCPU_GPR(R18)(r4) + stw r19, VCPU_GPR(R19)(r4) + stw r20, VCPU_GPR(R20)(r4) + stw r21, VCPU_GPR(R21)(r4) + stw r22, VCPU_GPR(R22)(r4) + stw r23, VCPU_GPR(R23)(r4) + stw r24, VCPU_GPR(R24)(r4) + stw r25, VCPU_GPR(R25)(r4) + stw r26, VCPU_GPR(R26)(r4) + stw r27, VCPU_GPR(R27)(r4) + stw r28, VCPU_GPR(R28)(r4) + stw r29, VCPU_GPR(R29)(r4) + stw r30, VCPU_GPR(R30)(r4) + stw r31, VCPU_GPR(R31)(r4) /* Load host non-volatile register state from host stack. */ - lwz r14, HOST_NV_GPR(r14)(r1) - lwz r15, HOST_NV_GPR(r15)(r1) - lwz r16, HOST_NV_GPR(r16)(r1) - lwz r17, HOST_NV_GPR(r17)(r1) - lwz r18, HOST_NV_GPR(r18)(r1) - lwz r19, HOST_NV_GPR(r19)(r1) - lwz r20, HOST_NV_GPR(r20)(r1) - lwz r21, HOST_NV_GPR(r21)(r1) - lwz r22, HOST_NV_GPR(r22)(r1) - lwz r23, HOST_NV_GPR(r23)(r1) - lwz r24, HOST_NV_GPR(r24)(r1) - lwz r25, HOST_NV_GPR(r25)(r1) - lwz r26, HOST_NV_GPR(r26)(r1) - lwz r27, HOST_NV_GPR(r27)(r1) - lwz r28, HOST_NV_GPR(r28)(r1) - lwz r29, HOST_NV_GPR(r29)(r1) - lwz r30, HOST_NV_GPR(r30)(r1) - lwz r31, HOST_NV_GPR(r31)(r1) + lwz r14, HOST_NV_GPR(R14)(r1) + lwz r15, HOST_NV_GPR(R15)(r1) + lwz r16, HOST_NV_GPR(R16)(r1) + lwz r17, HOST_NV_GPR(R17)(r1) + lwz r18, HOST_NV_GPR(R18)(r1) + lwz r19, HOST_NV_GPR(R19)(r1) + lwz r20, HOST_NV_GPR(R20)(r1) + lwz r21, HOST_NV_GPR(R21)(r1) + lwz r22, HOST_NV_GPR(R22)(r1) + lwz r23, HOST_NV_GPR(R23)(r1) + lwz r24, HOST_NV_GPR(R24)(r1) + lwz r25, HOST_NV_GPR(R25)(r1) + lwz r26, HOST_NV_GPR(R26)(r1) + lwz r27, HOST_NV_GPR(R27)(r1) + lwz r28, HOST_NV_GPR(R28)(r1) + lwz r29, HOST_NV_GPR(R29)(r1) + lwz r30, HOST_NV_GPR(R30)(r1) + lwz r31, HOST_NV_GPR(R31)(r1) /* Return to kvm_vcpu_run(). */ lwz r4, HOST_STACK_LR(r1) @@ -321,44 +319,44 @@ _GLOBAL(__kvmppc_vcpu_run) stw r5, HOST_CR(r1) /* Save host non-volatile register state to stack. */ - stw r14, HOST_NV_GPR(r14)(r1) - stw r15, HOST_NV_GPR(r15)(r1) - stw r16, HOST_NV_GPR(r16)(r1) - stw r17, HOST_NV_GPR(r17)(r1) - stw r18, HOST_NV_GPR(r18)(r1) - stw r19, HOST_NV_GPR(r19)(r1) - stw r20, HOST_NV_GPR(r20)(r1) - stw r21, HOST_NV_GPR(r21)(r1) - stw r22, HOST_NV_GPR(r22)(r1) - stw r23, HOST_NV_GPR(r23)(r1) - stw r24, HOST_NV_GPR(r24)(r1) - stw r25, HOST_NV_GPR(r25)(r1) - stw r26, HOST_NV_GPR(r26)(r1) - stw r27, HOST_NV_GPR(r27)(r1) - stw r28, HOST_NV_GPR(r28)(r1) - stw r29, HOST_NV_GPR(r29)(r1) - stw r30, HOST_NV_GPR(r30)(r1) - stw r31, HOST_NV_GPR(r31)(r1) + stw r14, HOST_NV_GPR(R14)(r1) + stw r15, HOST_NV_GPR(R15)(r1) + stw r16, HOST_NV_GPR(R16)(r1) + stw r17, HOST_NV_GPR(R17)(r1) + stw r18, HOST_NV_GPR(R18)(r1) + stw r19, HOST_NV_GPR(R19)(r1) + stw r20, HOST_NV_GPR(R20)(r1) + stw r21, HOST_NV_GPR(R21)(r1) + stw r22, HOST_NV_GPR(R22)(r1) + stw r23, HOST_NV_GPR(R23)(r1) + stw r24, HOST_NV_GPR(R24)(r1) + stw r25, HOST_NV_GPR(R25)(r1) + stw r26, HOST_NV_GPR(R26)(r1) + stw r27, HOST_NV_GPR(R27)(r1) + stw r28, HOST_NV_GPR(R28)(r1) + stw r29, HOST_NV_GPR(R29)(r1) + stw r30, HOST_NV_GPR(R30)(r1) + stw r31, HOST_NV_GPR(R31)(r1) /* Load guest non-volatiles. */ - lwz r14, VCPU_GPR(r14)(r4) - lwz r15, VCPU_GPR(r15)(r4) - lwz r16, VCPU_GPR(r16)(r4) - lwz r17, VCPU_GPR(r17)(r4) - lwz r18, VCPU_GPR(r18)(r4) - lwz r19, VCPU_GPR(r19)(r4) - lwz r20, VCPU_GPR(r20)(r4) - lwz r21, VCPU_GPR(r21)(r4) - lwz r22, VCPU_GPR(r22)(r4) - lwz r23, VCPU_GPR(r23)(r4) - lwz r24, VCPU_GPR(r24)(r4) - lwz r25, VCPU_GPR(r25)(r4) - lwz r26, VCPU_GPR(r26)(r4) - lwz r27, VCPU_GPR(r27)(r4) - lwz r28, VCPU_GPR(r28)(r4) - lwz r29, VCPU_GPR(r29)(r4) - lwz r30, VCPU_GPR(r30)(r4) - lwz r31, VCPU_GPR(r31)(r4) + lwz r14, VCPU_GPR(R14)(r4) + lwz r15, VCPU_GPR(R15)(r4) + lwz r16, VCPU_GPR(R16)(r4) + lwz r17, VCPU_GPR(R17)(r4) + lwz r18, VCPU_GPR(R18)(r4) + lwz r19, VCPU_GPR(R19)(r4) + lwz r20, VCPU_GPR(R20)(r4) + lwz r21, VCPU_GPR(R21)(r4) + lwz r22, VCPU_GPR(R22)(r4) + lwz r23, VCPU_GPR(R23)(r4) + lwz r24, VCPU_GPR(R24)(r4) + lwz r25, VCPU_GPR(R25)(r4) + lwz r26, VCPU_GPR(R26)(r4) + lwz r27, VCPU_GPR(R27)(r4) + lwz r28, VCPU_GPR(R28)(r4) + lwz r29, VCPU_GPR(R29)(r4) + lwz r30, VCPU_GPR(R30)(r4) + lwz r31, VCPU_GPR(R31)(r4) #ifdef CONFIG_SPE /* save host SPEFSCR and load guest SPEFSCR */ @@ -386,13 +384,13 @@ lightweight_exit: #endif /* Load some guest volatiles. */ - lwz r0, VCPU_GPR(r0)(r4) - lwz r2, VCPU_GPR(r2)(r4) - lwz r9, VCPU_GPR(r9)(r4) - lwz r10, VCPU_GPR(r10)(r4) - lwz r11, VCPU_GPR(r11)(r4) - lwz r12, VCPU_GPR(r12)(r4) - lwz r13, VCPU_GPR(r13)(r4) + lwz r0, VCPU_GPR(R0)(r4) + lwz r2, VCPU_GPR(R2)(r4) + lwz r9, VCPU_GPR(R9)(r4) + lwz r10, VCPU_GPR(R10)(r4) + lwz r11, VCPU_GPR(R11)(r4) + lwz r12, VCPU_GPR(R12)(r4) + lwz r13, VCPU_GPR(R13)(r4) lwz r3, VCPU_LR(r4) mtlr r3 lwz r3, VCPU_XER(r4) @@ -411,7 +409,7 @@ lightweight_exit: /* Can't switch the stack pointer until after IVPR is switched, * because host interrupt handlers would get confused. */ - lwz r1, VCPU_GPR(r1)(r4) + lwz r1, VCPU_GPR(R1)(r4) /* * Host interrupt handlers may have clobbered these @@ -449,10 +447,10 @@ lightweight_exit: mtcr r5 mtsrr0 r6 mtsrr1 r7 - lwz r5, VCPU_GPR(r5)(r4) - lwz r6, VCPU_GPR(r6)(r4) - lwz r7, VCPU_GPR(r7)(r4) - lwz r8, VCPU_GPR(r8)(r4) + lwz r5, VCPU_GPR(R5)(r4) + lwz r6, VCPU_GPR(R6)(r4) + lwz r7, VCPU_GPR(R7)(r4) + lwz r8, VCPU_GPR(R8)(r4) /* Clear any debug events which occurred since we disabled MSR[DE]. * XXX This gives us a 3-instruction window in which a breakpoint @@ -461,8 +459,8 @@ lightweight_exit: ori r3, r3, 0xffff mtspr SPRN_DBSR, r3 - lwz r3, VCPU_GPR(r3)(r4) - lwz r4, VCPU_GPR(r4)(r4) + lwz r3, VCPU_GPR(R3)(r4) + lwz r4, VCPU_GPR(R4)(r4) rfi #ifdef CONFIG_SPE diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index 6048a00..d28c2d4 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -37,7 +37,6 @@ #define LONGBYTES (BITS_PER_LONG / 8) -#define VCPU_GPR(n) (VCPU_GPRS + (n * LONGBYTES)) #define VCPU_GUEST_SPRG(n) (VCPU_GUEST_SPRGS + (n * LONGBYTES)) /* The host stack layout: */ @@ -67,15 +66,15 @@ */ .macro kvm_handler_common intno, srr0, flags /* Restore host stack pointer */ - PPC_STL r1, VCPU_GPR(r1)(r4) - PPC_STL r2, VCPU_GPR(r2)(r4) + PPC_STL r1, VCPU_GPR(R1)(r4) + PPC_STL r2, VCPU_GPR(R2)(r4) PPC_LL r1, VCPU_HOST_STACK(r4) PPC_LL r2, HOST_R2(r1) mfspr r10, SPRN_PID lwz r8, VCPU_HOST_PID(r4) PPC_LL r11, VCPU_SHARED(r4) - PPC_STL r14, VCPU_GPR(r14)(r4) /* We need a non-volatile GPR. */ + PPC_STL r14, VCPU_GPR(R14)(r4) /* We need a non-volatile GPR. */ li r14, \intno stw r10, VCPU_GUEST_PID(r4) @@ -137,35 +136,31 @@ */ mfspr r3, SPRN_EPLC /* will already have correct ELPID and EGS */ - PPC_STL r15, VCPU_GPR(r15)(r4) - PPC_STL r16, VCPU_GPR(r16)(r4) - PPC_STL r17, VCPU_GPR(r17)(r4) - PPC_STL r18, VCPU_GPR(r18)(r4) - PPC_STL r19, VCPU_GPR(r19)(r4) + PPC_STL r15, VCPU_GPR(R15)(r4) + PPC_STL r16, VCPU_GPR(R16)(r4) + PPC_STL r17, VCPU_GPR(R17)(r4) + PPC_STL r18, VCPU_GPR(R18)(r4) + PPC_STL r19, VCPU_GPR(R19)(r4) mr r8, r3 - PPC_STL r20, VCPU_GPR(r20)(r4) + PPC_STL r20, VCPU_GPR(R20)(r4) rlwimi r8, r6, EPC_EAS_SHIFT - MSR_IR_LG, EPC_EAS - PPC_STL r21, VCPU_GPR(r21)(r4) + PPC_STL r21, VCPU_GPR(R21)(r4) rlwimi r8, r6, EPC_EPR_SHIFT - MSR_PR_LG, EPC_EPR - PPC_STL r22, VCPU_GPR(r22)(r4) + PPC_STL r22, VCPU_GPR(R22)(r4) rlwimi r8, r10, EPC_EPID_SHIFT, EPC_EPID - PPC_STL r23, VCPU_GPR(r23)(r4) - PPC_STL r24, VCPU_GPR(r24)(r4) - PPC_STL r25, VCPU_GPR(r25)(r4) - PPC_STL r26, VCPU_GPR(r26)(r4) - PPC_STL r27, VCPU_GPR(r27)(r4) - PPC_STL r28, VCPU_GPR(r28)(r4) - PPC_STL r29, VCPU_GPR(r29)(r4) - PPC_STL r30, VCPU_GPR(r30)(r4) - PPC_STL r31, VCPU_GPR(r31)(r4) + PPC_STL r23, VCPU_GPR(R23)(r4) + PPC_STL r24, VCPU_GPR(R24)(r4) + PPC_STL r25, VCPU_GPR(R25)(r4) + PPC_STL r26, VCPU_GPR(R26)(r4) + PPC_STL r27, VCPU_GPR(R27)(r4) + PPC_STL r28, VCPU_GPR(R28)(r4) + PPC_STL r29, VCPU_GPR(R29)(r4) + PPC_STL r30, VCPU_GPR(R30)(r4) + PPC_STL r31, VCPU_GPR(R31)(r4) mtspr SPRN_EPLC, r8 /* disable preemption, so we are sure we hit the fixup handler */ -#ifdef CONFIG_PPC64 - clrrdi r8,r1,THREAD_SHIFT -#else - rlwinm r8,r1,0,0,31-THREAD_SHIFT /* current thread_info */ -#endif + CURRENT_THREAD_INFO(r8, r1) li r7, 1 stw r7, TI_PREEMPT(r8) @@ -211,24 +206,24 @@ .macro kvm_handler intno srr0, srr1, flags _GLOBAL(kvmppc_handler_\intno\()_\srr1) GET_VCPU(r11, r10) - PPC_STL r3, VCPU_GPR(r3)(r11) + PPC_STL r3, VCPU_GPR(R3)(r11) mfspr r3, SPRN_SPRG_RSCRATCH0 - PPC_STL r4, VCPU_GPR(r4)(r11) + PPC_STL r4, VCPU_GPR(R4)(r11) PPC_LL r4, THREAD_NORMSAVE(0)(r10) - PPC_STL r5, VCPU_GPR(r5)(r11) + PPC_STL r5, VCPU_GPR(R5)(r11) stw r13, VCPU_CR(r11) mfspr r5, \srr0 - PPC_STL r3, VCPU_GPR(r10)(r11) + PPC_STL r3, VCPU_GPR(R10)(r11) PPC_LL r3, THREAD_NORMSAVE(2)(r10) - PPC_STL r6, VCPU_GPR(r6)(r11) - PPC_STL r4, VCPU_GPR(r11)(r11) + PPC_STL r6, VCPU_GPR(R6)(r11) + PPC_STL r4, VCPU_GPR(R11)(r11) mfspr r6, \srr1 - PPC_STL r7, VCPU_GPR(r7)(r11) - PPC_STL r8, VCPU_GPR(r8)(r11) - PPC_STL r9, VCPU_GPR(r9)(r11) - PPC_STL r3, VCPU_GPR(r13)(r11) + PPC_STL r7, VCPU_GPR(R7)(r11) + PPC_STL r8, VCPU_GPR(R8)(r11) + PPC_STL r9, VCPU_GPR(R9)(r11) + PPC_STL r3, VCPU_GPR(R13)(r11) mfctr r7 - PPC_STL r12, VCPU_GPR(r12)(r11) + PPC_STL r12, VCPU_GPR(R12)(r11) PPC_STL r7, VCPU_CTR(r11) mr r4, r11 kvm_handler_common \intno, \srr0, \flags @@ -238,25 +233,25 @@ _GLOBAL(kvmppc_handler_\intno\()_\srr1) _GLOBAL(kvmppc_handler_\intno\()_\srr1) mfspr r10, SPRN_SPRG_THREAD GET_VCPU(r11, r10) - PPC_STL r3, VCPU_GPR(r3)(r11) + PPC_STL r3, VCPU_GPR(R3)(r11) mfspr r3, \scratch - PPC_STL r4, VCPU_GPR(r4)(r11) + PPC_STL r4, VCPU_GPR(R4)(r11) PPC_LL r4, GPR9(r8) - PPC_STL r5, VCPU_GPR(r5)(r11) + PPC_STL r5, VCPU_GPR(R5)(r11) stw r9, VCPU_CR(r11) mfspr r5, \srr0 - PPC_STL r3, VCPU_GPR(r8)(r11) + PPC_STL r3, VCPU_GPR(R8)(r11) PPC_LL r3, GPR10(r8) - PPC_STL r6, VCPU_GPR(r6)(r11) - PPC_STL r4, VCPU_GPR(r9)(r11) + PPC_STL r6, VCPU_GPR(R6)(r11) + PPC_STL r4, VCPU_GPR(R9)(r11) mfspr r6, \srr1 PPC_LL r4, GPR11(r8) - PPC_STL r7, VCPU_GPR(r7)(r11) - PPC_STL r3, VCPU_GPR(r10)(r11) + PPC_STL r7, VCPU_GPR(R7)(r11) + PPC_STL r3, VCPU_GPR(R10)(r11) mfctr r7 - PPC_STL r12, VCPU_GPR(r12)(r11) - PPC_STL r13, VCPU_GPR(r13)(r11) - PPC_STL r4, VCPU_GPR(r11)(r11) + PPC_STL r12, VCPU_GPR(R12)(r11) + PPC_STL r13, VCPU_GPR(R13)(r11) + PPC_STL r4, VCPU_GPR(R11)(r11) PPC_STL r7, VCPU_CTR(r11) mr r4, r11 kvm_handler_common \intno, \srr0, \flags @@ -267,7 +262,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_CRITICAL, \ kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \ SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0 kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \ - SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR) + SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR) kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0 kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \ @@ -310,7 +305,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \ _GLOBAL(kvmppc_resume_host) /* Save remaining volatile guest register state to vcpu. */ mfspr r3, SPRN_VRSAVE - PPC_STL r0, VCPU_GPR(r0)(r4) + PPC_STL r0, VCPU_GPR(R0)(r4) mflr r5 mfspr r6, SPRN_SPRG4 PPC_STL r5, VCPU_LR(r4) @@ -358,27 +353,27 @@ _GLOBAL(kvmppc_resume_host) /* Restore vcpu pointer and the nonvolatiles we used. */ mr r4, r14 - PPC_LL r14, VCPU_GPR(r14)(r4) + PPC_LL r14, VCPU_GPR(R14)(r4) andi. r5, r3, RESUME_FLAG_NV beq skip_nv_load - PPC_LL r15, VCPU_GPR(r15)(r4) - PPC_LL r16, VCPU_GPR(r16)(r4) - PPC_LL r17, VCPU_GPR(r17)(r4) - PPC_LL r18, VCPU_GPR(r18)(r4) - PPC_LL r19, VCPU_GPR(r19)(r4) - PPC_LL r20, VCPU_GPR(r20)(r4) - PPC_LL r21, VCPU_GPR(r21)(r4) - PPC_LL r22, VCPU_GPR(r22)(r4) - PPC_LL r23, VCPU_GPR(r23)(r4) - PPC_LL r24, VCPU_GPR(r24)(r4) - PPC_LL r25, VCPU_GPR(r25)(r4) - PPC_LL r26, VCPU_GPR(r26)(r4) - PPC_LL r27, VCPU_GPR(r27)(r4) - PPC_LL r28, VCPU_GPR(r28)(r4) - PPC_LL r29, VCPU_GPR(r29)(r4) - PPC_LL r30, VCPU_GPR(r30)(r4) - PPC_LL r31, VCPU_GPR(r31)(r4) + PPC_LL r15, VCPU_GPR(R15)(r4) + PPC_LL r16, VCPU_GPR(R16)(r4) + PPC_LL r17, VCPU_GPR(R17)(r4) + PPC_LL r18, VCPU_GPR(R18)(r4) + PPC_LL r19, VCPU_GPR(R19)(r4) + PPC_LL r20, VCPU_GPR(R20)(r4) + PPC_LL r21, VCPU_GPR(R21)(r4) + PPC_LL r22, VCPU_GPR(R22)(r4) + PPC_LL r23, VCPU_GPR(R23)(r4) + PPC_LL r24, VCPU_GPR(R24)(r4) + PPC_LL r25, VCPU_GPR(R25)(r4) + PPC_LL r26, VCPU_GPR(R26)(r4) + PPC_LL r27, VCPU_GPR(R27)(r4) + PPC_LL r28, VCPU_GPR(R28)(r4) + PPC_LL r29, VCPU_GPR(R29)(r4) + PPC_LL r30, VCPU_GPR(R30)(r4) + PPC_LL r31, VCPU_GPR(R31)(r4) skip_nv_load: /* Should we return to the guest? */ andi. r5, r3, RESUME_FLAG_HOST @@ -396,23 +391,23 @@ heavyweight_exit: * non-volatiles. */ - PPC_STL r15, VCPU_GPR(r15)(r4) - PPC_STL r16, VCPU_GPR(r16)(r4) - PPC_STL r17, VCPU_GPR(r17)(r4) - PPC_STL r18, VCPU_GPR(r18)(r4) - PPC_STL r19, VCPU_GPR(r19)(r4) - PPC_STL r20, VCPU_GPR(r20)(r4) - PPC_STL r21, VCPU_GPR(r21)(r4) - PPC_STL r22, VCPU_GPR(r22)(r4) - PPC_STL r23, VCPU_GPR(r23)(r4) - PPC_STL r24, VCPU_GPR(r24)(r4) - PPC_STL r25, VCPU_GPR(r25)(r4) - PPC_STL r26, VCPU_GPR(r26)(r4) - PPC_STL r27, VCPU_GPR(r27)(r4) - PPC_STL r28, VCPU_GPR(r28)(r4) - PPC_STL r29, VCPU_GPR(r29)(r4) - PPC_STL r30, VCPU_GPR(r30)(r4) - PPC_STL r31, VCPU_GPR(r31)(r4) + PPC_STL r15, VCPU_GPR(R15)(r4) + PPC_STL r16, VCPU_GPR(R16)(r4) + PPC_STL r17, VCPU_GPR(R17)(r4) + PPC_STL r18, VCPU_GPR(R18)(r4) + PPC_STL r19, VCPU_GPR(R19)(r4) + PPC_STL r20, VCPU_GPR(R20)(r4) + PPC_STL r21, VCPU_GPR(R21)(r4) + PPC_STL r22, VCPU_GPR(R22)(r4) + PPC_STL r23, VCPU_GPR(R23)(r4) + PPC_STL r24, VCPU_GPR(R24)(r4) + PPC_STL r25, VCPU_GPR(R25)(r4) + PPC_STL r26, VCPU_GPR(R26)(r4) + PPC_STL r27, VCPU_GPR(R27)(r4) + PPC_STL r28, VCPU_GPR(R28)(r4) + PPC_STL r29, VCPU_GPR(R29)(r4) + PPC_STL r30, VCPU_GPR(R30)(r4) + PPC_STL r31, VCPU_GPR(R31)(r4) /* Load host non-volatile register state from host stack. */ PPC_LL r14, HOST_NV_GPR(r14)(r1) @@ -478,24 +473,24 @@ _GLOBAL(__kvmppc_vcpu_run) PPC_STL r31, HOST_NV_GPR(r31)(r1) /* Load guest non-volatiles. */ - PPC_LL r14, VCPU_GPR(r14)(r4) - PPC_LL r15, VCPU_GPR(r15)(r4) - PPC_LL r16, VCPU_GPR(r16)(r4) - PPC_LL r17, VCPU_GPR(r17)(r4) - PPC_LL r18, VCPU_GPR(r18)(r4) - PPC_LL r19, VCPU_GPR(r19)(r4) - PPC_LL r20, VCPU_GPR(r20)(r4) - PPC_LL r21, VCPU_GPR(r21)(r4) - PPC_LL r22, VCPU_GPR(r22)(r4) - PPC_LL r23, VCPU_GPR(r23)(r4) - PPC_LL r24, VCPU_GPR(r24)(r4) - PPC_LL r25, VCPU_GPR(r25)(r4) - PPC_LL r26, VCPU_GPR(r26)(r4) - PPC_LL r27, VCPU_GPR(r27)(r4) - PPC_LL r28, VCPU_GPR(r28)(r4) - PPC_LL r29, VCPU_GPR(r29)(r4) - PPC_LL r30, VCPU_GPR(r30)(r4) - PPC_LL r31, VCPU_GPR(r31)(r4) + PPC_LL r14, VCPU_GPR(R14)(r4) + PPC_LL r15, VCPU_GPR(R15)(r4) + PPC_LL r16, VCPU_GPR(R16)(r4) + PPC_LL r17, VCPU_GPR(R17)(r4) + PPC_LL r18, VCPU_GPR(R18)(r4) + PPC_LL r19, VCPU_GPR(R19)(r4) + PPC_LL r20, VCPU_GPR(R20)(r4) + PPC_LL r21, VCPU_GPR(R21)(r4) + PPC_LL r22, VCPU_GPR(R22)(r4) + PPC_LL r23, VCPU_GPR(R23)(r4) + PPC_LL r24, VCPU_GPR(R24)(r4) + PPC_LL r25, VCPU_GPR(R25)(r4) + PPC_LL r26, VCPU_GPR(R26)(r4) + PPC_LL r27, VCPU_GPR(R27)(r4) + PPC_LL r28, VCPU_GPR(R28)(r4) + PPC_LL r29, VCPU_GPR(R29)(r4) + PPC_LL r30, VCPU_GPR(R30)(r4) + PPC_LL r31, VCPU_GPR(R31)(r4) lightweight_exit: @@ -554,13 +549,13 @@ lightweight_exit: lwz r7, VCPU_CR(r4) PPC_LL r8, VCPU_PC(r4) PPC_LD(r9, VCPU_SHARED_MSR, r11) - PPC_LL r0, VCPU_GPR(r0)(r4) - PPC_LL r1, VCPU_GPR(r1)(r4) - PPC_LL r2, VCPU_GPR(r2)(r4) - PPC_LL r10, VCPU_GPR(r10)(r4) - PPC_LL r11, VCPU_GPR(r11)(r4) - PPC_LL r12, VCPU_GPR(r12)(r4) - PPC_LL r13, VCPU_GPR(r13)(r4) + PPC_LL r0, VCPU_GPR(R0)(r4) + PPC_LL r1, VCPU_GPR(R1)(r4) + PPC_LL r2, VCPU_GPR(R2)(r4) + PPC_LL r10, VCPU_GPR(R10)(r4) + PPC_LL r11, VCPU_GPR(R11)(r4) + PPC_LL r12, VCPU_GPR(R12)(r4) + PPC_LL r13, VCPU_GPR(R13)(r4) mtlr r3 mtxer r5 mtctr r6 @@ -586,12 +581,12 @@ lightweight_exit: mtcr r7 /* Finish loading guest volatiles and jump to guest. */ - PPC_LL r5, VCPU_GPR(r5)(r4) - PPC_LL r6, VCPU_GPR(r6)(r4) - PPC_LL r7, VCPU_GPR(r7)(r4) - PPC_LL r8, VCPU_GPR(r8)(r4) - PPC_LL r9, VCPU_GPR(r9)(r4) - - PPC_LL r3, VCPU_GPR(r3)(r4) - PPC_LL r4, VCPU_GPR(r4)(r4) + PPC_LL r5, VCPU_GPR(R5)(r4) + PPC_LL r6, VCPU_GPR(R6)(r4) + PPC_LL r7, VCPU_GPR(R7)(r4) + PPC_LL r8, VCPU_GPR(R8)(r4) + PPC_LL r9, VCPU_GPR(R9)(r4) + + PPC_LL r3, VCPU_GPR(R3)(r4) + PPC_LL r4, VCPU_GPR(R4)(r4) rfi diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 8b99e07..e04b0ef 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -269,6 +269,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) *spr_val = vcpu->arch.shared->mas7_3 >> 32; break; #endif + case SPRN_DECAR: + *spr_val = vcpu->arch.decar; + break; case SPRN_TLB0CFG: *spr_val = vcpu->arch.tlbcfg[0]; break; diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index fe6c1de..1f89d26 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved. + * Copyright (C) 2010,2012 Freescale Semiconductor, Inc. All rights reserved. * * Author: Varun Sethi, <varun.sethi@freescale.com> * @@ -57,7 +57,8 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500, struct kvm_book3e_206_tlb_entry *gtlbe) { unsigned int tid, ts; - u32 val, eaddr, lpid; + gva_t eaddr; + u32 val, lpid; unsigned long flags; ts = get_tlb_ts(gtlbe); @@ -183,6 +184,9 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \ SPRN_EPCR_DUVD; +#ifdef CONFIG_64BIT + vcpu->arch.shadow_epcr |= SPRN_EPCR_ICM; +#endif vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP; vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT); vcpu->arch.epsc = vcpu->arch.eplc; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index f90e86d..ee04aba 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -59,11 +59,13 @@ #define OP_31_XOP_STHBRX 918 #define OP_LWZ 32 +#define OP_LD 58 #define OP_LWZU 33 #define OP_LBZ 34 #define OP_LBZU 35 #define OP_STW 36 #define OP_STWU 37 +#define OP_STD 62 #define OP_STB 38 #define OP_STBU 39 #define OP_LHZ 40 @@ -392,6 +394,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); break; + /* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */ + case OP_LD: + rt = get_rt(inst); + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + break; + case OP_LWZU: emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); @@ -412,6 +420,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) 4, 1); break; + /* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */ + case OP_STD: + rs = get_rs(inst); + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), + 8, 1); + break; + case OP_STWU: emulated = kvmppc_handle_store(run, vcpu, kvmppc_get_gpr(vcpu, rs), diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 1493c8d..87f4dc8 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -246,6 +246,7 @@ int kvm_dev_ioctl_check_extension(long ext) #endif #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: + case KVM_CAP_PPC_ALLOC_HTAB: r = 1; break; #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -802,6 +803,23 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; break; } + + case KVM_PPC_ALLOCATE_HTAB: { + struct kvm *kvm = filp->private_data; + u32 htab_order; + + r = -EFAULT; + if (get_user(htab_order, (u32 __user *)argp)) + break; + r = kvmppc_alloc_reset_hpt(kvm, &htab_order); + if (r) + break; + r = -EFAULT; + if (put_user(htab_order, (u32 __user *)argp)) + break; + r = 0; + break; + } #endif /* CONFIG_KVM_BOOK3S_64_HV */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 7735a2c..746e0c8 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -17,14 +17,15 @@ obj-$(CONFIG_HAS_IOMEM) += devres.o obj-$(CONFIG_PPC64) += copypage_64.o copyuser_64.o \ memcpy_64.o usercopy_64.o mem_64.o string.o \ checksum_wrappers_64.o hweight_64.o \ - copyuser_power7.o + copyuser_power7.o string_64.o copypage_power7.o \ + memcpy_power7.o obj-$(CONFIG_XMON) += sstep.o ldstfp.o obj-$(CONFIG_KPROBES) += sstep.o ldstfp.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += sstep.o ldstfp.o ifeq ($(CONFIG_PPC64),y) obj-$(CONFIG_SMP) += locks.o -obj-$(CONFIG_ALTIVEC) += copyuser_power7_vmx.o +obj-$(CONFIG_ALTIVEC) += vmx-helper.o endif obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S index 18245af..167f725 100644 --- a/arch/powerpc/lib/checksum_64.S +++ b/arch/powerpc/lib/checksum_64.S @@ -65,9 +65,6 @@ _GLOBAL(csum_tcpudp_magic) srwi r3,r3,16 blr -#define STACKFRAMESIZE 256 -#define STK_REG(i) (112 + ((i)-14)*8) - /* * Computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit). @@ -114,9 +111,9 @@ _GLOBAL(csum_partial) mtctr r6 stdu r1,-STACKFRAMESIZE(r1) - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) ld r6,0(r3) ld r9,8(r3) @@ -175,9 +172,9 @@ _GLOBAL(csum_partial) adde r0,r0,r15 adde r0,r0,r16 - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) addi r1,r1,STACKFRAMESIZE andi. r4,r4,63 @@ -299,9 +296,9 @@ dest; sth r6,0(r4) mtctr r6 stdu r1,-STACKFRAMESIZE(r1) - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) source; ld r6,0(r3) source; ld r9,8(r3) @@ -382,9 +379,9 @@ dest; std r16,56(r4) adde r0,r0,r15 adde r0,r0,r16 - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) addi r1,r1,STACKFRAMESIZE andi. r5,r5,63 diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 7c975d4..dd223b3 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -13,17 +13,23 @@ #include <linux/mm.h> #include <asm/page.h> #include <asm/code-patching.h> +#include <asm/uaccess.h> -void patch_instruction(unsigned int *addr, unsigned int instr) +int patch_instruction(unsigned int *addr, unsigned int instr) { - *addr = instr; + int err; + + err = __put_user(instr, addr); + if (err) + return err; asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr)); + return 0; } -void patch_branch(unsigned int *addr, unsigned long target, int flags) +int patch_branch(unsigned int *addr, unsigned long target, int flags) { - patch_instruction(addr, create_branch(addr, target, flags)); + return patch_instruction(addr, create_branch(addr, target, flags)); } unsigned int create_branch(const unsigned int *addr, diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 53dcb6b..9f9434a 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -17,7 +17,11 @@ PPC64_CACHES: .section ".text" _GLOBAL(copy_page) +BEGIN_FTR_SECTION lis r5,PAGE_SIZE@h +FTR_SECTION_ELSE + b .copypage_power7 +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) ori r5,r5,PAGE_SIZE@l BEGIN_FTR_SECTION ld r10,PPC64_CACHES@toc(r2) diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S new file mode 100644 index 0000000..0ef75bf --- /dev/null +++ b/arch/powerpc/lib/copypage_power7.S @@ -0,0 +1,165 @@ +/* + * 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) IBM Corporation, 2012 + * + * Author: Anton Blanchard <anton@au.ibm.com> + */ +#include <asm/page.h> +#include <asm/ppc_asm.h> + +_GLOBAL(copypage_power7) + /* + * We prefetch both the source and destination using enhanced touch + * instructions. We use a stream ID of 0 for the load side and + * 1 for the store side. Since source and destination are page + * aligned we don't need to clear the bottom 7 bits of either + * address. + */ + ori r9,r3,1 /* stream=1 */ + +#ifdef CONFIG_PPC_64K_PAGES + lis r7,0x0E01 /* depth=7, units=512 */ +#else + lis r7,0x0E00 /* depth=7 */ + ori r7,r7,0x1000 /* units=32 */ +#endif + ori r10,r7,1 /* stream=1 */ + + lis r8,0x8000 /* GO=1 */ + clrldi r8,r8,32 + +.machine push +.machine "power4" + dcbt r0,r4,0b01000 + dcbt r0,r7,0b01010 + dcbtst r0,r9,0b01000 + dcbtst r0,r10,0b01010 + eieio + dcbt r0,r8,0b01010 /* GO */ +.machine pop + +#ifdef CONFIG_ALTIVEC + mflr r0 + std r3,48(r1) + std r4,56(r1) + std r0,16(r1) + stdu r1,-STACKFRAMESIZE(r1) + bl .enter_vmx_copy + cmpwi r3,0 + ld r0,STACKFRAMESIZE+16(r1) + ld r3,STACKFRAMESIZE+48(r1) + ld r4,STACKFRAMESIZE+56(r1) + mtlr r0 + + li r0,(PAGE_SIZE/128) + mtctr r0 + + beq .Lnonvmx_copy + + addi r1,r1,STACKFRAMESIZE + + li r6,16 + li r7,32 + li r8,48 + li r9,64 + li r10,80 + li r11,96 + li r12,112 + + .align 5 +1: lvx vr7,r0,r4 + lvx vr6,r4,r6 + lvx vr5,r4,r7 + lvx vr4,r4,r8 + lvx vr3,r4,r9 + lvx vr2,r4,r10 + lvx vr1,r4,r11 + lvx vr0,r4,r12 + addi r4,r4,128 + stvx vr7,r0,r3 + stvx vr6,r3,r6 + stvx vr5,r3,r7 + stvx vr4,r3,r8 + stvx vr3,r3,r9 + stvx vr2,r3,r10 + stvx vr1,r3,r11 + stvx vr0,r3,r12 + addi r3,r3,128 + bdnz 1b + + b .exit_vmx_copy /* tail call optimise */ + +#else + li r0,(PAGE_SIZE/128) + mtctr r0 + + stdu r1,-STACKFRAMESIZE(r1) +#endif + +.Lnonvmx_copy: + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + +1: ld r0,0(r4) + ld r5,8(r4) + ld r6,16(r4) + ld r7,24(r4) + ld r8,32(r4) + ld r9,40(r4) + ld r10,48(r4) + ld r11,56(r4) + ld r12,64(r4) + ld r14,72(r4) + ld r15,80(r4) + ld r16,88(r4) + ld r17,96(r4) + ld r18,104(r4) + ld r19,112(r4) + ld r20,120(r4) + addi r4,r4,128 + std r0,0(r3) + std r5,8(r3) + std r6,16(r3) + std r7,24(r3) + std r8,32(r3) + std r9,40(r3) + std r10,48(r3) + std r11,56(r3) + std r12,64(r3) + std r14,72(r3) + std r15,80(r3) + std r16,88(r3) + std r17,96(r3) + std r18,104(r3) + std r19,112(r3) + std r20,120(r3) + addi r3,r3,128 + bdnz 1b + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + addi r1,r1,STACKFRAMESIZE + blr diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 497db7b..f9ede7c 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -19,9 +19,6 @@ */ #include <asm/ppc_asm.h> -#define STACKFRAMESIZE 256 -#define STK_REG(i) (112 + ((i)-14)*8) - .macro err1 100: .section __ex_table,"a" @@ -57,26 +54,26 @@ .Ldo_err4: - ld r16,STK_REG(r16)(r1) - ld r15,STK_REG(r15)(r1) - ld r14,STK_REG(r14)(r1) + ld r16,STK_REG(R16)(r1) + ld r15,STK_REG(R15)(r1) + ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl .exit_vmx_copy + bl .exit_vmx_usercopy ld r0,STACKFRAMESIZE+16(r1) mtlr r0 b .Lexit #endif /* CONFIG_ALTIVEC */ .Ldo_err2: - ld r22,STK_REG(r22)(r1) - ld r21,STK_REG(r21)(r1) - ld r20,STK_REG(r20)(r1) - ld r19,STK_REG(r19)(r1) - ld r18,STK_REG(r18)(r1) - ld r17,STK_REG(r17)(r1) - ld r16,STK_REG(r16)(r1) - ld r15,STK_REG(r15)(r1) - ld r14,STK_REG(r14)(r1) + ld r22,STK_REG(R22)(r1) + ld r21,STK_REG(R21)(r1) + ld r20,STK_REG(R20)(r1) + ld r19,STK_REG(R19)(r1) + ld r18,STK_REG(R18)(r1) + ld r17,STK_REG(R17)(r1) + ld r16,STK_REG(R16)(r1) + ld r15,STK_REG(R15)(r1) + ld r14,STK_REG(R14)(r1) .Lexit: addi r1,r1,STACKFRAMESIZE .Ldo_err1: @@ -137,15 +134,15 @@ err1; stw r0,0(r3) mflr r0 stdu r1,-STACKFRAMESIZE(r1) - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) - std r17,STK_REG(r17)(r1) - std r18,STK_REG(r18)(r1) - std r19,STK_REG(r19)(r1) - std r20,STK_REG(r20)(r1) - std r21,STK_REG(r21)(r1) - std r22,STK_REG(r22)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + std r21,STK_REG(R21)(r1) + std r22,STK_REG(R22)(r1) std r0,STACKFRAMESIZE+16(r1) srdi r6,r5,7 @@ -192,15 +189,15 @@ err2; std r21,120(r3) clrldi r5,r5,(64-7) - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) - ld r17,STK_REG(r17)(r1) - ld r18,STK_REG(r18)(r1) - ld r19,STK_REG(r19)(r1) - ld r20,STK_REG(r20)(r1) - ld r21,STK_REG(r21)(r1) - ld r22,STK_REG(r22)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + ld r21,STK_REG(R21)(r1) + ld r22,STK_REG(R22)(r1) addi r1,r1,STACKFRAMESIZE /* Up to 127B to go */ @@ -290,7 +287,7 @@ err1; stb r0,0(r3) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_copy + bl .enter_vmx_usercopy cmpwi r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STACKFRAMESIZE+48(r1) @@ -298,6 +295,68 @@ err1; stb r0,0(r3) ld r5,STACKFRAMESIZE+64(r1) mtlr r0 + /* + * We prefetch both the source and destination using enhanced touch + * instructions. We use a stream ID of 0 for the load side and + * 1 for the store side. + */ + clrrdi r6,r4,7 + clrrdi r9,r3,7 + ori r9,r9,1 /* stream=1 */ + + srdi r7,r5,7 /* length in cachelines, capped at 0x3FF */ + cmpldi r7,0x3FF + ble 1f + li r7,0x3FF +1: lis r0,0x0E00 /* depth=7 */ + sldi r7,r7,7 + or r7,r7,r0 + ori r10,r7,1 /* stream=1 */ + + lis r8,0x8000 /* GO=1 */ + clrldi r8,r8,32 + +.machine push +.machine "power4" + dcbt r0,r6,0b01000 + dcbt r0,r7,0b01010 + dcbtst r0,r9,0b01000 + dcbtst r0,r10,0b01010 + eieio + dcbt r0,r8,0b01010 /* GO */ +.machine pop + + /* + * We prefetch both the source and destination using enhanced touch + * instructions. We use a stream ID of 0 for the load side and + * 1 for the store side. + */ + clrrdi r6,r4,7 + clrrdi r9,r3,7 + ori r9,r9,1 /* stream=1 */ + + srdi r7,r5,7 /* length in cachelines, capped at 0x3FF */ + cmpldi cr1,r7,0x3FF + ble cr1,1f + li r7,0x3FF +1: lis r0,0x0E00 /* depth=7 */ + sldi r7,r7,7 + or r7,r7,r0 + ori r10,r7,1 /* stream=1 */ + + lis r8,0x8000 /* GO=1 */ + clrldi r8,r8,32 + +.machine push +.machine "power4" + dcbt r0,r6,0b01000 + dcbt r0,r7,0b01010 + dcbtst r0,r9,0b01000 + dcbtst r0,r10,0b01010 + eieio + dcbt r0,r8,0b01010 /* GO */ +.machine pop + beq .Lunwind_stack_nonvmx_copy /* @@ -378,9 +437,9 @@ err3; stvx vr0,r3,r11 7: sub r5,r5,r6 srdi r6,r5,7 - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) li r12,64 li r14,80 @@ -415,9 +474,9 @@ err4; stvx vr0,r3,r16 addi r3,r3,128 bdnz 8b - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) /* Up to 127B to go */ clrldi r5,r5,(64-7) @@ -476,7 +535,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_copy /* tail call optimise */ + b .exit_vmx_usercopy /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -563,9 +622,9 @@ err3; stvx vr11,r3,r11 7: sub r5,r5,r6 srdi r6,r5,7 - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) li r12,64 li r14,80 @@ -608,9 +667,9 @@ err4; stvx vr15,r3,r16 addi r3,r3,128 bdnz 8b - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) /* Up to 127B to go */ clrldi r5,r5,(64-7) @@ -679,5 +738,5 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_copy /* tail call optimise */ + b .exit_vmx_usercopy /* tail call optimise */ #endif /* CONFiG_ALTIVEC */ diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S index 1c893f0..b2c68ce 100644 --- a/arch/powerpc/lib/crtsavres.S +++ b/arch/powerpc/lib/crtsavres.S @@ -41,12 +41,13 @@ #include <asm/ppc_asm.h> .file "crtsavres.S" - .section ".text" #ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE #ifndef CONFIG_PPC64 + .section ".text" + /* Routines for saving integer registers, called by the compiler. */ /* Called with r11 pointing to the stack header word of the caller of the */ /* function, just beyond the end of the integer save area. */ @@ -232,6 +233,8 @@ _GLOBAL(_rest32gpr_31_x) #else /* CONFIG_PPC64 */ + .section ".text.save.restore","ax",@progbits + .globl _savegpr0_14 _savegpr0_14: std r14,-144(r1) diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S index fda2786..9b96ff2 100644 --- a/arch/powerpc/lib/hweight_64.S +++ b/arch/powerpc/lib/hweight_64.S @@ -28,7 +28,7 @@ BEGIN_FTR_SECTION nop nop FTR_SECTION_ELSE - PPC_POPCNTB(r3,r3) + PPC_POPCNTB(R3,R3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB) @@ -42,14 +42,14 @@ BEGIN_FTR_SECTION nop FTR_SECTION_ELSE BEGIN_FTR_SECTION_NESTED(50) - PPC_POPCNTB(r3,r3) + PPC_POPCNTB(R3,R3) srdi r4,r3,8 add r3,r4,r3 clrldi r3,r3,64-8 blr FTR_SECTION_ELSE_NESTED(50) clrlwi r3,r3,16 - PPC_POPCNTW(r3,r3) + PPC_POPCNTW(R3,R3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50) @@ -66,7 +66,7 @@ BEGIN_FTR_SECTION nop FTR_SECTION_ELSE BEGIN_FTR_SECTION_NESTED(51) - PPC_POPCNTB(r3,r3) + PPC_POPCNTB(R3,R3) srdi r4,r3,16 add r3,r4,r3 srdi r4,r3,8 @@ -74,7 +74,7 @@ FTR_SECTION_ELSE clrldi r3,r3,64-8 blr FTR_SECTION_ELSE_NESTED(51) - PPC_POPCNTW(r3,r3) + PPC_POPCNTW(R3,R3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51) @@ -93,7 +93,7 @@ BEGIN_FTR_SECTION nop FTR_SECTION_ELSE BEGIN_FTR_SECTION_NESTED(52) - PPC_POPCNTB(r3,r3) + PPC_POPCNTB(R3,R3) srdi r4,r3,32 add r3,r4,r3 srdi r4,r3,16 @@ -103,7 +103,7 @@ FTR_SECTION_ELSE clrldi r3,r3,64-8 blr FTR_SECTION_ELSE_NESTED(52) - PPC_POPCNTD(r3,r3) + PPC_POPCNTD(R3,R3) clrldi r3,r3,64-8 blr ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52) diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index 6a85380..85aec08 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -330,13 +330,13 @@ _GLOBAL(do_lxvd2x) MTMSRD(r7) isync beq cr7,1f - STXVD2X(0,r1,r8) + STXVD2X(0,R1,R8) 1: li r9,-EFAULT -2: LXVD2X(0,0,r4) +2: LXVD2X(0,R0,R4) li r9,0 3: beq cr7,4f bl put_vsr - LXVD2X(0,r1,r8) + LXVD2X(0,R1,R8) 4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) @@ -358,13 +358,13 @@ _GLOBAL(do_stxvd2x) MTMSRD(r7) isync beq cr7,1f - STXVD2X(0,r1,r8) + STXVD2X(0,R1,R8) bl get_vsr 1: li r9,-EFAULT -2: STXVD2X(0,0,r4) +2: STXVD2X(0,R0,R4) li r9,0 3: beq cr7,4f - LXVD2X(0,r1,r8) + LXVD2X(0,R1,R8) 4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S index 82fea39..d2bbbc8 100644 --- a/arch/powerpc/lib/memcpy_64.S +++ b/arch/powerpc/lib/memcpy_64.S @@ -11,7 +11,11 @@ .align 7 _GLOBAL(memcpy) +BEGIN_FTR_SECTION std r3,48(r1) /* save destination pointer for return value */ +FTR_SECTION_ELSE + b memcpy_power7 +ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) PPC_MTOCRF(0x01,r5) cmpldi cr1,r5,16 neg r6,r3 # LS 3 bits = # bytes to 8-byte dest bdry diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S new file mode 100644 index 0000000..0efdc51 --- /dev/null +++ b/arch/powerpc/lib/memcpy_power7.S @@ -0,0 +1,647 @@ +/* + * 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) IBM Corporation, 2012 + * + * Author: Anton Blanchard <anton@au.ibm.com> + */ +#include <asm/ppc_asm.h> + +_GLOBAL(memcpy_power7) +#ifdef CONFIG_ALTIVEC + cmpldi r5,16 + cmpldi cr1,r5,4096 + + std r3,48(r1) + + blt .Lshort_copy + bgt cr1,.Lvmx_copy +#else + cmpldi r5,16 + + std r3,48(r1) + + blt .Lshort_copy +#endif + +.Lnonvmx_copy: + /* Get the source 8B aligned */ + neg r6,r4 + mtocrf 0x01,r6 + clrldi r6,r6,(64-3) + + bf cr7*4+3,1f + lbz r0,0(r4) + addi r4,r4,1 + stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +3: sub r5,r5,r6 + cmpldi r5,128 + blt 5f + + mflr r0 + stdu r1,-STACKFRAMESIZE(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + std r21,STK_REG(R21)(r1) + std r22,STK_REG(R22)(r1) + std r0,STACKFRAMESIZE+16(r1) + + srdi r6,r5,7 + mtctr r6 + + /* Now do cacheline (128B) sized loads and stores. */ + .align 5 +4: + ld r0,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ld r8,24(r4) + ld r9,32(r4) + ld r10,40(r4) + ld r11,48(r4) + ld r12,56(r4) + ld r14,64(r4) + ld r15,72(r4) + ld r16,80(r4) + ld r17,88(r4) + ld r18,96(r4) + ld r19,104(r4) + ld r20,112(r4) + ld r21,120(r4) + addi r4,r4,128 + std r0,0(r3) + std r6,8(r3) + std r7,16(r3) + std r8,24(r3) + std r9,32(r3) + std r10,40(r3) + std r11,48(r3) + std r12,56(r3) + std r14,64(r3) + std r15,72(r3) + std r16,80(r3) + std r17,88(r3) + std r18,96(r3) + std r19,104(r3) + std r20,112(r3) + std r21,120(r3) + addi r3,r3,128 + bdnz 4b + + clrldi r5,r5,(64-7) + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + ld r21,STK_REG(R21)(r1) + ld r22,STK_REG(R22)(r1) + addi r1,r1,STACKFRAMESIZE + + /* Up to 127B to go */ +5: srdi r6,r5,4 + mtocrf 0x01,r6 + +6: bf cr7*4+1,7f + ld r0,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ld r8,24(r4) + ld r9,32(r4) + ld r10,40(r4) + ld r11,48(r4) + ld r12,56(r4) + addi r4,r4,64 + std r0,0(r3) + std r6,8(r3) + std r7,16(r3) + std r8,24(r3) + std r9,32(r3) + std r10,40(r3) + std r11,48(r3) + std r12,56(r3) + addi r3,r3,64 + + /* Up to 63B to go */ +7: bf cr7*4+2,8f + ld r0,0(r4) + ld r6,8(r4) + ld r7,16(r4) + ld r8,24(r4) + addi r4,r4,32 + std r0,0(r3) + std r6,8(r3) + std r7,16(r3) + std r8,24(r3) + addi r3,r3,32 + + /* Up to 31B to go */ +8: bf cr7*4+3,9f + ld r0,0(r4) + ld r6,8(r4) + addi r4,r4,16 + std r0,0(r3) + std r6,8(r3) + addi r3,r3,16 + +9: clrldi r5,r5,(64-4) + + /* Up to 15B to go */ +.Lshort_copy: + mtocrf 0x01,r5 + bf cr7*4+0,12f + lwz r0,0(r4) /* Less chance of a reject with word ops */ + lwz r6,4(r4) + addi r4,r4,8 + stw r0,0(r3) + stw r6,4(r3) + addi r3,r3,8 + +12: bf cr7*4+1,13f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +13: bf cr7*4+2,14f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +14: bf cr7*4+3,15f + lbz r0,0(r4) + stb r0,0(r3) + +15: ld r3,48(r1) + blr + +.Lunwind_stack_nonvmx_copy: + addi r1,r1,STACKFRAMESIZE + b .Lnonvmx_copy + +#ifdef CONFIG_ALTIVEC +.Lvmx_copy: + mflr r0 + std r4,56(r1) + std r5,64(r1) + std r0,16(r1) + stdu r1,-STACKFRAMESIZE(r1) + bl .enter_vmx_copy + cmpwi r3,0 + ld r0,STACKFRAMESIZE+16(r1) + ld r3,STACKFRAMESIZE+48(r1) + ld r4,STACKFRAMESIZE+56(r1) + ld r5,STACKFRAMESIZE+64(r1) + mtlr r0 + + /* + * We prefetch both the source and destination using enhanced touch + * instructions. We use a stream ID of 0 for the load side and + * 1 for the store side. + */ + clrrdi r6,r4,7 + clrrdi r9,r3,7 + ori r9,r9,1 /* stream=1 */ + + srdi r7,r5,7 /* length in cachelines, capped at 0x3FF */ + cmpldi cr1,r7,0x3FF + ble cr1,1f + li r7,0x3FF +1: lis r0,0x0E00 /* depth=7 */ + sldi r7,r7,7 + or r7,r7,r0 + ori r10,r7,1 /* stream=1 */ + + lis r8,0x8000 /* GO=1 */ + clrldi r8,r8,32 + +.machine push +.machine "power4" + dcbt r0,r6,0b01000 + dcbt r0,r7,0b01010 + dcbtst r0,r9,0b01000 + dcbtst r0,r10,0b01010 + eieio + dcbt r0,r8,0b01010 /* GO */ +.machine pop + + beq .Lunwind_stack_nonvmx_copy + + /* + * If source and destination are not relatively aligned we use a + * slower permute loop. + */ + xor r6,r4,r3 + rldicl. r6,r6,0,(64-4) + bne .Lvmx_unaligned_copy + + /* Get the destination 16B aligned */ + neg r6,r3 + mtocrf 0x01,r6 + clrldi r6,r6,(64-4) + + bf cr7*4+3,1f + lbz r0,0(r4) + addi r4,r4,1 + stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +3: bf cr7*4+0,4f + ld r0,0(r4) + addi r4,r4,8 + std r0,0(r3) + addi r3,r3,8 + +4: sub r5,r5,r6 + + /* Get the desination 128B aligned */ + neg r6,r3 + srdi r7,r6,4 + mtocrf 0x01,r7 + clrldi r6,r6,(64-7) + + li r9,16 + li r10,32 + li r11,48 + + bf cr7*4+3,5f + lvx vr1,r0,r4 + addi r4,r4,16 + stvx vr1,r0,r3 + addi r3,r3,16 + +5: bf cr7*4+2,6f + lvx vr1,r0,r4 + lvx vr0,r4,r9 + addi r4,r4,32 + stvx vr1,r0,r3 + stvx vr0,r3,r9 + addi r3,r3,32 + +6: bf cr7*4+1,7f + lvx vr3,r0,r4 + lvx vr2,r4,r9 + lvx vr1,r4,r10 + lvx vr0,r4,r11 + addi r4,r4,64 + stvx vr3,r0,r3 + stvx vr2,r3,r9 + stvx vr1,r3,r10 + stvx vr0,r3,r11 + addi r3,r3,64 + +7: sub r5,r5,r6 + srdi r6,r5,7 + + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + + li r12,64 + li r14,80 + li r15,96 + li r16,112 + + mtctr r6 + + /* + * Now do cacheline sized loads and stores. By this stage the + * cacheline stores are also cacheline aligned. + */ + .align 5 +8: + lvx vr7,r0,r4 + lvx vr6,r4,r9 + lvx vr5,r4,r10 + lvx vr4,r4,r11 + lvx vr3,r4,r12 + lvx vr2,r4,r14 + lvx vr1,r4,r15 + lvx vr0,r4,r16 + addi r4,r4,128 + stvx vr7,r0,r3 + stvx vr6,r3,r9 + stvx vr5,r3,r10 + stvx vr4,r3,r11 + stvx vr3,r3,r12 + stvx vr2,r3,r14 + stvx vr1,r3,r15 + stvx vr0,r3,r16 + addi r3,r3,128 + bdnz 8b + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + + /* Up to 127B to go */ + clrldi r5,r5,(64-7) + srdi r6,r5,4 + mtocrf 0x01,r6 + + bf cr7*4+1,9f + lvx vr3,r0,r4 + lvx vr2,r4,r9 + lvx vr1,r4,r10 + lvx vr0,r4,r11 + addi r4,r4,64 + stvx vr3,r0,r3 + stvx vr2,r3,r9 + stvx vr1,r3,r10 + stvx vr0,r3,r11 + addi r3,r3,64 + +9: bf cr7*4+2,10f + lvx vr1,r0,r4 + lvx vr0,r4,r9 + addi r4,r4,32 + stvx vr1,r0,r3 + stvx vr0,r3,r9 + addi r3,r3,32 + +10: bf cr7*4+3,11f + lvx vr1,r0,r4 + addi r4,r4,16 + stvx vr1,r0,r3 + addi r3,r3,16 + + /* Up to 15B to go */ +11: clrldi r5,r5,(64-4) + mtocrf 0x01,r5 + bf cr7*4+0,12f + ld r0,0(r4) + addi r4,r4,8 + std r0,0(r3) + addi r3,r3,8 + +12: bf cr7*4+1,13f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +13: bf cr7*4+2,14f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +14: bf cr7*4+3,15f + lbz r0,0(r4) + stb r0,0(r3) + +15: addi r1,r1,STACKFRAMESIZE + ld r3,48(r1) + b .exit_vmx_copy /* tail call optimise */ + +.Lvmx_unaligned_copy: + /* Get the destination 16B aligned */ + neg r6,r3 + mtocrf 0x01,r6 + clrldi r6,r6,(64-4) + + bf cr7*4+3,1f + lbz r0,0(r4) + addi r4,r4,1 + stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +3: bf cr7*4+0,4f + lwz r0,0(r4) /* Less chance of a reject with word ops */ + lwz r7,4(r4) + addi r4,r4,8 + stw r0,0(r3) + stw r7,4(r3) + addi r3,r3,8 + +4: sub r5,r5,r6 + + /* Get the desination 128B aligned */ + neg r6,r3 + srdi r7,r6,4 + mtocrf 0x01,r7 + clrldi r6,r6,(64-7) + + li r9,16 + li r10,32 + li r11,48 + + lvsl vr16,0,r4 /* Setup permute control vector */ + lvx vr0,0,r4 + addi r4,r4,16 + + bf cr7*4+3,5f + lvx vr1,r0,r4 + vperm vr8,vr0,vr1,vr16 + addi r4,r4,16 + stvx vr8,r0,r3 + addi r3,r3,16 + vor vr0,vr1,vr1 + +5: bf cr7*4+2,6f + lvx vr1,r0,r4 + vperm vr8,vr0,vr1,vr16 + lvx vr0,r4,r9 + vperm vr9,vr1,vr0,vr16 + addi r4,r4,32 + stvx vr8,r0,r3 + stvx vr9,r3,r9 + addi r3,r3,32 + +6: bf cr7*4+1,7f + lvx vr3,r0,r4 + vperm vr8,vr0,vr3,vr16 + lvx vr2,r4,r9 + vperm vr9,vr3,vr2,vr16 + lvx vr1,r4,r10 + vperm vr10,vr2,vr1,vr16 + lvx vr0,r4,r11 + vperm vr11,vr1,vr0,vr16 + addi r4,r4,64 + stvx vr8,r0,r3 + stvx vr9,r3,r9 + stvx vr10,r3,r10 + stvx vr11,r3,r11 + addi r3,r3,64 + +7: sub r5,r5,r6 + srdi r6,r5,7 + + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + + li r12,64 + li r14,80 + li r15,96 + li r16,112 + + mtctr r6 + + /* + * Now do cacheline sized loads and stores. By this stage the + * cacheline stores are also cacheline aligned. + */ + .align 5 +8: + lvx vr7,r0,r4 + vperm vr8,vr0,vr7,vr16 + lvx vr6,r4,r9 + vperm vr9,vr7,vr6,vr16 + lvx vr5,r4,r10 + vperm vr10,vr6,vr5,vr16 + lvx vr4,r4,r11 + vperm vr11,vr5,vr4,vr16 + lvx vr3,r4,r12 + vperm vr12,vr4,vr3,vr16 + lvx vr2,r4,r14 + vperm vr13,vr3,vr2,vr16 + lvx vr1,r4,r15 + vperm vr14,vr2,vr1,vr16 + lvx vr0,r4,r16 + vperm vr15,vr1,vr0,vr16 + addi r4,r4,128 + stvx vr8,r0,r3 + stvx vr9,r3,r9 + stvx vr10,r3,r10 + stvx vr11,r3,r11 + stvx vr12,r3,r12 + stvx vr13,r3,r14 + stvx vr14,r3,r15 + stvx vr15,r3,r16 + addi r3,r3,128 + bdnz 8b + + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + + /* Up to 127B to go */ + clrldi r5,r5,(64-7) + srdi r6,r5,4 + mtocrf 0x01,r6 + + bf cr7*4+1,9f + lvx vr3,r0,r4 + vperm vr8,vr0,vr3,vr16 + lvx vr2,r4,r9 + vperm vr9,vr3,vr2,vr16 + lvx vr1,r4,r10 + vperm vr10,vr2,vr1,vr16 + lvx vr0,r4,r11 + vperm vr11,vr1,vr0,vr16 + addi r4,r4,64 + stvx vr8,r0,r3 + stvx vr9,r3,r9 + stvx vr10,r3,r10 + stvx vr11,r3,r11 + addi r3,r3,64 + +9: bf cr7*4+2,10f + lvx vr1,r0,r4 + vperm vr8,vr0,vr1,vr16 + lvx vr0,r4,r9 + vperm vr9,vr1,vr0,vr16 + addi r4,r4,32 + stvx vr8,r0,r3 + stvx vr9,r3,r9 + addi r3,r3,32 + +10: bf cr7*4+3,11f + lvx vr1,r0,r4 + vperm vr8,vr0,vr1,vr16 + addi r4,r4,16 + stvx vr8,r0,r3 + addi r3,r3,16 + + /* Up to 15B to go */ +11: clrldi r5,r5,(64-4) + addi r4,r4,-16 /* Unwind the +16 load offset */ + mtocrf 0x01,r5 + bf cr7*4+0,12f + lwz r0,0(r4) /* Less chance of a reject with word ops */ + lwz r6,4(r4) + addi r4,r4,8 + stw r0,0(r3) + stw r6,4(r3) + addi r3,r3,8 + +12: bf cr7*4+1,13f + lwz r0,0(r4) + addi r4,r4,4 + stw r0,0(r3) + addi r3,r3,4 + +13: bf cr7*4+2,14f + lhz r0,0(r4) + addi r4,r4,2 + sth r0,0(r3) + addi r3,r3,2 + +14: bf cr7*4+3,15f + lbz r0,0(r4) + stb r0,0(r3) + +15: addi r1,r1,STACKFRAMESIZE + ld r3,48(r1) + b .exit_vmx_copy /* tail call optimise */ +#endif /* CONFiG_ALTIVEC */ diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S index 093d631..1b5a0a0 100644 --- a/arch/powerpc/lib/string.S +++ b/arch/powerpc/lib/string.S @@ -119,6 +119,7 @@ _GLOBAL(memchr) 2: li r3,0 blr +#ifdef CONFIG_PPC32 _GLOBAL(__clear_user) addi r6,r3,-4 li r3,0 @@ -160,3 +161,4 @@ _GLOBAL(__clear_user) PPC_LONG 1b,91b PPC_LONG 8b,92b .text +#endif diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S new file mode 100644 index 0000000..3b1e480 --- /dev/null +++ b/arch/powerpc/lib/string_64.S @@ -0,0 +1,202 @@ +/* + * 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) IBM Corporation, 2012 + * + * Author: Anton Blanchard <anton@au.ibm.com> + */ + +#include <asm/ppc_asm.h> +#include <asm/asm-offsets.h> + + .section ".toc","aw" +PPC64_CACHES: + .tc ppc64_caches[TC],ppc64_caches + .section ".text" + +/** + * __clear_user: - Zero a block of memory in user space, with less checking. + * @to: Destination address, in user space. + * @n: Number of bytes to zero. + * + * Zero a block of memory in user space. Caller must check + * the specified block with access_ok() before calling this function. + * + * Returns number of bytes that could not be cleared. + * On success, this will be zero. + */ + + .macro err1 +100: + .section __ex_table,"a" + .align 3 + .llong 100b,.Ldo_err1 + .previous + .endm + + .macro err2 +200: + .section __ex_table,"a" + .align 3 + .llong 200b,.Ldo_err2 + .previous + .endm + + .macro err3 +300: + .section __ex_table,"a" + .align 3 + .llong 300b,.Ldo_err3 + .previous + .endm + +.Ldo_err1: + mr r3,r8 + +.Ldo_err2: + mtctr r4 +1: +err3; stb r0,0(r3) + addi r3,r3,1 + addi r4,r4,-1 + bdnz 1b + +.Ldo_err3: + mr r3,r4 + blr + +_GLOBAL(__clear_user) + cmpdi r4,32 + neg r6,r3 + li r0,0 + blt .Lshort_clear + mr r8,r3 + mtocrf 0x01,r6 + clrldi r6,r6,(64-3) + + /* Get the destination 8 byte aligned */ + bf cr7*4+3,1f +err1; stb r0,0(r3) + addi r3,r3,1 + +1: bf cr7*4+2,2f +err1; sth r0,0(r3) + addi r3,r3,2 + +2: bf cr7*4+1,3f +err1; stw r0,0(r3) + addi r3,r3,4 + +3: sub r4,r4,r6 + + cmpdi r4,32 + cmpdi cr1,r4,512 + blt .Lshort_clear + bgt cr1,.Llong_clear + +.Lmedium_clear: + srdi r6,r4,5 + mtctr r6 + + /* Do 32 byte chunks */ +4: +err2; std r0,0(r3) +err2; std r0,8(r3) +err2; std r0,16(r3) +err2; std r0,24(r3) + addi r3,r3,32 + addi r4,r4,-32 + bdnz 4b + +.Lshort_clear: + /* up to 31 bytes to go */ + cmpdi r4,16 + blt 6f +err2; std r0,0(r3) +err2; std r0,8(r3) + addi r3,r3,16 + addi r4,r4,-16 + + /* Up to 15 bytes to go */ +6: mr r8,r3 + clrldi r4,r4,(64-4) + mtocrf 0x01,r4 + bf cr7*4+0,7f +err1; std r0,0(r3) + addi r3,r3,8 + +7: bf cr7*4+1,8f +err1; stw r0,0(r3) + addi r3,r3,4 + +8: bf cr7*4+2,9f +err1; sth r0,0(r3) + addi r3,r3,2 + +9: bf cr7*4+3,10f +err1; stb r0,0(r3) + +10: li r3,0 + blr + +.Llong_clear: + ld r5,PPC64_CACHES@toc(r2) + + bf cr7*4+0,11f +err2; std r0,0(r3) + addi r3,r3,8 + addi r4,r4,-8 + + /* Destination is 16 byte aligned, need to get it cacheline aligned */ +11: lwz r7,DCACHEL1LOGLINESIZE(r5) + lwz r9,DCACHEL1LINESIZE(r5) + + /* + * With worst case alignment the long clear loop takes a minimum + * of 1 byte less than 2 cachelines. + */ + sldi r10,r9,2 + cmpd r4,r10 + blt .Lmedium_clear + + neg r6,r3 + addi r10,r9,-1 + and. r5,r6,r10 + beq 13f + + srdi r6,r5,4 + mtctr r6 + mr r8,r3 +12: +err1; std r0,0(r3) +err1; std r0,8(r3) + addi r3,r3,16 + bdnz 12b + + sub r4,r4,r5 + +13: srd r6,r4,r7 + mtctr r6 + mr r8,r3 +14: +err1; dcbz r0,r3 + add r3,r3,r9 + bdnz 14b + + and r4,r4,r10 + + cmpdi r4,32 + blt .Lshort_clear + b .Lmedium_clear diff --git a/arch/powerpc/lib/copyuser_power7_vmx.c b/arch/powerpc/lib/vmx-helper.c index bf2654f2..3cf529c 100644 --- a/arch/powerpc/lib/copyuser_power7_vmx.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -22,7 +22,7 @@ #include <linux/hardirq.h> #include <asm/switch_to.h> -int enter_vmx_copy(void) +int enter_vmx_usercopy(void) { if (in_interrupt()) return 0; @@ -44,8 +44,31 @@ int enter_vmx_copy(void) * This function must return 0 because we tail call optimise when calling * from __copy_tofrom_user_power7 which returns 0 on success. */ -int exit_vmx_copy(void) +int exit_vmx_usercopy(void) { pagefault_enable(); return 0; } + +int enter_vmx_copy(void) +{ + if (in_interrupt()) + return 0; + + preempt_disable(); + + enable_kernel_altivec(); + + return 1; +} + +/* + * All calls to this function will be optimised into tail calls. We are + * passed a pointer to the destination which we return as required by a + * memcpy implementation. + */ +void *exit_vmx_copy(void *dest) +{ + preempt_enable(); + return dest; +} diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S index b13d589..115347f 100644 --- a/arch/powerpc/mm/hash_low_32.S +++ b/arch/powerpc/mm/hash_low_32.S @@ -184,7 +184,7 @@ _GLOBAL(add_hash_page) add r3,r3,r0 /* note create_hpte trims to 24 bits */ #ifdef CONFIG_SMP - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) /* use cpu number to make tag */ + CURRENT_THREAD_INFO(r8, r1) /* use cpu number to make tag */ lwz r8,TI_CPU(r8) /* to go in mmu_hash_lock */ oris r8,r8,12 #endif /* CONFIG_SMP */ @@ -545,7 +545,7 @@ _GLOBAL(flush_hash_pages) #ifdef CONFIG_SMP addis r9,r7,mmu_hash_lock@ha addi r9,r9,mmu_hash_lock@l - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r8, r1) add r8,r8,r7 lwz r8,TI_CPU(r8) oris r8,r8,9 @@ -639,7 +639,7 @@ _GLOBAL(flush_hash_patch_B) */ _GLOBAL(_tlbie) #ifdef CONFIG_SMP - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r8, r1) lwz r8,TI_CPU(r8) oris r8,r8,11 mfmsr r10 @@ -677,7 +677,7 @@ _GLOBAL(_tlbie) */ _GLOBAL(_tlbia) #if defined(CONFIG_SMP) - rlwinm r8,r1,0,0,(31-THREAD_SHIFT) + CURRENT_THREAD_INFO(r8, r1) lwz r8,TI_CPU(r8) oris r8,r8,10 mfmsr r10 diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index a242b5d..602aeb0 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -34,14 +34,6 @@ * | CR save area (SP + 8) * SP ---> +-- Back chain (SP + 0) */ -#define STACKFRAMESIZE 256 - -/* Save parameters offsets */ -#define STK_PARM(i) (STACKFRAMESIZE + 48 + ((i)-3)*8) - -/* Save non-volatile offsets */ -#define STK_REG(i) (112 + ((i)-14)*8) - #ifndef CONFIG_PPC_64K_PAGES @@ -64,9 +56,9 @@ _GLOBAL(__hash_page_4K) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) /* Save all params that we need after a function call */ - std r6,STK_PARM(r6)(r1) - std r8,STK_PARM(r8)(r1) - std r9,STK_PARM(r9)(r1) + std r6,STK_PARAM(R6)(r1) + std r8,STK_PARAM(R8)(r1) + std r9,STK_PARAM(R9)(r1) /* Save non-volatile registers. * r31 will hold "old PTE" @@ -75,11 +67,11 @@ _GLOBAL(__hash_page_4K) * r28 is a hash value * r27 is hashtab mask (maybe dynamic patched instead ?) */ - std r27,STK_REG(r27)(r1) - std r28,STK_REG(r28)(r1) - std r29,STK_REG(r29)(r1) - std r30,STK_REG(r30)(r1) - std r31,STK_REG(r31)(r1) + std r27,STK_REG(R27)(r1) + std r28,STK_REG(R28)(r1) + std r29,STK_REG(R29)(r1) + std r30,STK_REG(R30)(r1) + std r31,STK_REG(R31)(r1) /* Step 1: * @@ -162,7 +154,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in * place of "access" in the param area (sic) */ - std r3,STK_PARM(r4)(r1) + std r3,STK_PARAM(R4)(r1) /* Get htab_hash_mask */ ld r4,htab_hash_mask@got(2) @@ -192,11 +184,11 @@ htab_insert_pte: rldicr r3,r0,3,63-3 /* r3 = (hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retrieve new pp bits */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ mr r4,r29 /* Retrieve va */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARM(r9)(r1) /* segment size */ + ld r9,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -215,11 +207,11 @@ _GLOBAL(htab_call_hpte_insert1) rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retrieve new pp bits */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ mr r4,r29 /* Retrieve va */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARM(r9)(r1) /* segment size */ + ld r9,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -255,15 +247,15 @@ htab_pte_insert_ok: * (maybe add eieio may be good still ?) */ htab_write_out_pte: - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r30,0(r6) li r3, 0 htab_bail: - ld r27,STK_REG(r27)(r1) - ld r28,STK_REG(r28)(r1) - ld r29,STK_REG(r29)(r1) - ld r30,STK_REG(r30)(r1) - ld r31,STK_REG(r31)(r1) + ld r27,STK_REG(R27)(r1) + ld r28,STK_REG(R28)(r1) + ld r29,STK_REG(R29)(r1) + ld r30,STK_REG(R30)(r1) + ld r31,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE ld r0,16(r1) mtlr r0 @@ -288,8 +280,8 @@ htab_modify_pte: /* Call ppc_md.hpte_updatepp */ mr r5,r29 /* va */ li r6,MMU_PAGE_4K /* page size */ - ld r7,STK_PARM(r9)(r1) /* segment size */ - ld r8,STK_PARM(r8)(r1) /* get "local" param */ + ld r7,STK_PARAM(R9)(r1) /* segment size */ + ld r8,STK_PARAM(R8)(r1) /* get "local" param */ _GLOBAL(htab_call_hpte_updatepp) bl . /* Patched by htab_finish_init() */ @@ -312,7 +304,7 @@ htab_wrong_access: htab_pte_insert_failure: /* Bail out restoring old PTE */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r31,0(r6) li r3,-1 b htab_bail @@ -340,9 +332,9 @@ _GLOBAL(__hash_page_4K) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) /* Save all params that we need after a function call */ - std r6,STK_PARM(r6)(r1) - std r8,STK_PARM(r8)(r1) - std r9,STK_PARM(r9)(r1) + std r6,STK_PARAM(R6)(r1) + std r8,STK_PARAM(R8)(r1) + std r9,STK_PARAM(R9)(r1) /* Save non-volatile registers. * r31 will hold "old PTE" @@ -353,13 +345,13 @@ _GLOBAL(__hash_page_4K) * r26 is the hidx mask * r25 is the index in combo page */ - std r25,STK_REG(r25)(r1) - std r26,STK_REG(r26)(r1) - std r27,STK_REG(r27)(r1) - std r28,STK_REG(r28)(r1) - std r29,STK_REG(r29)(r1) - std r30,STK_REG(r30)(r1) - std r31,STK_REG(r31)(r1) + std r25,STK_REG(R25)(r1) + std r26,STK_REG(R26)(r1) + std r27,STK_REG(R27)(r1) + std r28,STK_REG(R28)(r1) + std r29,STK_REG(R29)(r1) + std r30,STK_REG(R30)(r1) + std r31,STK_REG(R31)(r1) /* Step 1: * @@ -452,7 +444,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in * place of "access" in the param area (sic) */ - std r3,STK_PARM(r4)(r1) + std r3,STK_PARAM(R4)(r1) /* Get htab_hash_mask */ ld r4,htab_hash_mask@got(2) @@ -473,7 +465,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) andis. r0,r31,_PAGE_COMBO@h beq htab_inval_old_hpte - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) ori r26,r6,0x8000 /* Load the hidx mask */ ld r26,0(r26) addi r5,r25,36 /* Check actual HPTE_SUB bit, this */ @@ -495,11 +487,11 @@ htab_special_pfn: rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retrieve new pp bits */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ mr r4,r29 /* Retrieve va */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARM(r9)(r1) /* segment size */ + ld r9,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -522,11 +514,11 @@ _GLOBAL(htab_call_hpte_insert1) rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retrieve new pp bits */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ mr r4,r29 /* Retrieve va */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ - ld r9,STK_PARM(r9)(r1) /* segment size */ + ld r9,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -559,8 +551,8 @@ htab_inval_old_hpte: mr r4,r31 /* PTE.pte */ li r5,0 /* PTE.hidx */ li r6,MMU_PAGE_64K /* psize */ - ld r7,STK_PARM(r9)(r1) /* ssize */ - ld r8,STK_PARM(r8)(r1) /* local */ + ld r7,STK_PARAM(R9)(r1) /* ssize */ + ld r8,STK_PARAM(R8)(r1) /* local */ bl .flush_hash_page /* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */ lis r0,_PAGE_HPTE_SUB@h @@ -576,7 +568,7 @@ htab_pte_insert_ok: /* Insert slot number & secondary bit in PTE second half, * clear _PAGE_BUSY and set approriate HPTE slot bit */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) li r0,_PAGE_BUSY andc r30,r30,r0 /* HPTE SUB bit */ @@ -597,13 +589,13 @@ htab_pte_insert_ok: std r30,0(r6) li r3, 0 htab_bail: - ld r25,STK_REG(r25)(r1) - ld r26,STK_REG(r26)(r1) - ld r27,STK_REG(r27)(r1) - ld r28,STK_REG(r28)(r1) - ld r29,STK_REG(r29)(r1) - ld r30,STK_REG(r30)(r1) - ld r31,STK_REG(r31)(r1) + ld r25,STK_REG(R25)(r1) + ld r26,STK_REG(R26)(r1) + ld r27,STK_REG(R27)(r1) + ld r28,STK_REG(R28)(r1) + ld r29,STK_REG(R29)(r1) + ld r30,STK_REG(R30)(r1) + ld r31,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE ld r0,16(r1) mtlr r0 @@ -630,8 +622,8 @@ htab_modify_pte: /* Call ppc_md.hpte_updatepp */ mr r5,r29 /* va */ li r6,MMU_PAGE_4K /* page size */ - ld r7,STK_PARM(r9)(r1) /* segment size */ - ld r8,STK_PARM(r8)(r1) /* get "local" param */ + ld r7,STK_PARAM(R9)(r1) /* segment size */ + ld r8,STK_PARAM(R8)(r1) /* get "local" param */ _GLOBAL(htab_call_hpte_updatepp) bl . /* patched by htab_finish_init() */ @@ -644,7 +636,7 @@ _GLOBAL(htab_call_hpte_updatepp) /* Clear the BUSY bit and Write out the PTE */ li r0,_PAGE_BUSY andc r30,r30,r0 - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r30,0(r6) li r3,0 b htab_bail @@ -657,7 +649,7 @@ htab_wrong_access: htab_pte_insert_failure: /* Bail out restoring old PTE */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r31,0(r6) li r3,-1 b htab_bail @@ -677,9 +669,9 @@ _GLOBAL(__hash_page_64K) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) /* Save all params that we need after a function call */ - std r6,STK_PARM(r6)(r1) - std r8,STK_PARM(r8)(r1) - std r9,STK_PARM(r9)(r1) + std r6,STK_PARAM(R6)(r1) + std r8,STK_PARAM(R8)(r1) + std r9,STK_PARAM(R9)(r1) /* Save non-volatile registers. * r31 will hold "old PTE" @@ -688,11 +680,11 @@ _GLOBAL(__hash_page_64K) * r28 is a hash value * r27 is hashtab mask (maybe dynamic patched instead ?) */ - std r27,STK_REG(r27)(r1) - std r28,STK_REG(r28)(r1) - std r29,STK_REG(r29)(r1) - std r30,STK_REG(r30)(r1) - std r31,STK_REG(r31)(r1) + std r27,STK_REG(R27)(r1) + std r28,STK_REG(R28)(r1) + std r29,STK_REG(R29)(r1) + std r30,STK_REG(R30)(r1) + std r31,STK_REG(R31)(r1) /* Step 1: * @@ -780,7 +772,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE) /* At this point, r3 contains new PP bits, save them in * place of "access" in the param area (sic) */ - std r3,STK_PARM(r4)(r1) + std r3,STK_PARAM(R4)(r1) /* Get htab_hash_mask */ ld r4,htab_hash_mask@got(2) @@ -813,11 +805,11 @@ ht64_insert_pte: rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retrieve new pp bits */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ mr r4,r29 /* Retrieve va */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_64K - ld r9,STK_PARM(r9)(r1) /* segment size */ + ld r9,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -836,11 +828,11 @@ _GLOBAL(ht64_call_hpte_insert1) rldicr r3,r0,3,63-3 /* r0 = (~hash & mask) << 3 */ /* Call ppc_md.hpte_insert */ - ld r6,STK_PARM(r4)(r1) /* Retrieve new pp bits */ + ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */ mr r4,r29 /* Retrieve va */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_64K - ld r9,STK_PARM(r9)(r1) /* segment size */ + ld r9,STK_PARAM(R9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -876,15 +868,15 @@ ht64_pte_insert_ok: * (maybe add eieio may be good still ?) */ ht64_write_out_pte: - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r30,0(r6) li r3, 0 ht64_bail: - ld r27,STK_REG(r27)(r1) - ld r28,STK_REG(r28)(r1) - ld r29,STK_REG(r29)(r1) - ld r30,STK_REG(r30)(r1) - ld r31,STK_REG(r31)(r1) + ld r27,STK_REG(R27)(r1) + ld r28,STK_REG(R28)(r1) + ld r29,STK_REG(R29)(r1) + ld r30,STK_REG(R30)(r1) + ld r31,STK_REG(R31)(r1) addi r1,r1,STACKFRAMESIZE ld r0,16(r1) mtlr r0 @@ -909,8 +901,8 @@ ht64_modify_pte: /* Call ppc_md.hpte_updatepp */ mr r5,r29 /* va */ li r6,MMU_PAGE_64K - ld r7,STK_PARM(r9)(r1) /* segment size */ - ld r8,STK_PARM(r8)(r1) /* get "local" param */ + ld r7,STK_PARAM(R9)(r1) /* segment size */ + ld r8,STK_PARAM(R8)(r1) /* get "local" param */ _GLOBAL(ht64_call_hpte_updatepp) bl . /* patched by htab_finish_init() */ @@ -933,7 +925,7 @@ ht64_wrong_access: ht64_pte_insert_failure: /* Bail out restoring old PTE */ - ld r6,STK_PARM(r6)(r1) + ld r6,STK_PARAM(R6)(r1) std r31,0(r6) li r3,-1 b ht64_bail diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 1e95556..39b1597 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -340,6 +340,8 @@ static int __init find_min_common_depth(void) dbg("Using form 1 affinity\n"); form1_affinity = 1; } + + of_node_put(chosen); } } diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index ff672bd..f09d48e 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -126,7 +126,7 @@ BEGIN_MMU_FTR_SECTION /* Set the TLB reservation and search for existing entry. Then load * the entry. */ - PPC_TLBSRX_DOT(0,r16) + PPC_TLBSRX_DOT(0,R16) ldx r14,r14,r15 /* grab pgd entry */ beq normal_tlb_miss_done /* tlb exists already, bail */ MMU_FTR_SECTION_ELSE @@ -395,7 +395,7 @@ BEGIN_MMU_FTR_SECTION /* Set the TLB reservation and search for existing entry. Then load * the entry. */ - PPC_TLBSRX_DOT(0,r16) + PPC_TLBSRX_DOT(0,R16) ld r14,0(r10) beq normal_tlb_miss_done MMU_FTR_SECTION_ELSE @@ -528,7 +528,7 @@ BEGIN_MMU_FTR_SECTION /* Search if we already have a TLB entry for that virtual address, and * if we do, bail out. */ - PPC_TLBSRX_DOT(0,r16) + PPC_TLBSRX_DOT(0,R16) beq virt_page_table_tlb_miss_done END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV) @@ -779,7 +779,7 @@ htw_tlb_miss: * * MAS1:IND should be already set based on MAS4 */ - PPC_TLBSRX_DOT(0,r16) + PPC_TLBSRX_DOT(0,R16) beq htw_tlb_miss_done /* Now, we need to walk the page tables. First check if we are in @@ -919,7 +919,7 @@ tlb_load_linear: mtspr SPRN_MAS1,r15 /* Already somebody there ? */ - PPC_TLBSRX_DOT(0,r16) + PPC_TLBSRX_DOT(0,R16) beq tlb_load_linear_done /* Now we build the remaining MAS. MAS0 and 2 should be fine diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index 7c63c0e..fab919f 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -266,7 +266,7 @@ BEGIN_MMU_FTR_SECTION andi. r3,r3,MMUCSR0_TLBFI@l bne 1b MMU_FTR_SECTION_ELSE - PPC_TLBILX_ALL(0,0) + PPC_TLBILX_ALL(0,R0) ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX) msync isync @@ -279,7 +279,7 @@ BEGIN_MMU_FTR_SECTION wrteei 0 mfspr r4,SPRN_MAS6 /* save MAS6 */ mtspr SPRN_MAS6,r3 - PPC_TLBILX_PID(0,0) + PPC_TLBILX_PID(0,R0) mtspr SPRN_MAS6,r4 /* restore MAS6 */ wrtee r10 MMU_FTR_SECTION_ELSE @@ -313,7 +313,7 @@ BEGIN_MMU_FTR_SECTION mtspr SPRN_MAS1,r4 tlbwe MMU_FTR_SECTION_ELSE - PPC_TLBILX_VA(0,r3) + PPC_TLBILX_VA(0,R3) ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX) msync isync @@ -331,7 +331,7 @@ _GLOBAL(_tlbil_pid) mfmsr r10 wrteei 0 mtspr SPRN_MAS6,r4 - PPC_TLBILX_PID(0,0) + PPC_TLBILX_PID(0,R0) wrtee r10 msync isync @@ -343,14 +343,14 @@ _GLOBAL(_tlbil_pid_noind) ori r4,r4,MAS6_SIND wrteei 0 mtspr SPRN_MAS6,r4 - PPC_TLBILX_PID(0,0) + PPC_TLBILX_PID(0,R0) wrtee r10 msync isync blr _GLOBAL(_tlbil_all) - PPC_TLBILX_ALL(0,0) + PPC_TLBILX_ALL(0,R0) msync isync blr @@ -364,7 +364,7 @@ _GLOBAL(_tlbil_va) beq 1f rlwimi r4,r6,MAS6_SIND_SHIFT,MAS6_SIND 1: mtspr SPRN_MAS6,r4 /* assume AS=0 for now */ - PPC_TLBILX_VA(0,r3) + PPC_TLBILX_VA(0,R3) msync isync wrtee r10 @@ -379,7 +379,7 @@ _GLOBAL(_tlbivax_bcast) beq 1f rlwimi r4,r6,MAS6_SIND_SHIFT,MAS6_SIND 1: mtspr SPRN_MAS6,r4 /* assume AS=0 for now */ - PPC_TLBIVAX(0,r3) + PPC_TLBIVAX(0,R3) eieio tlbsync sync diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 5c3cf2d..1fc8109 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -75,23 +75,23 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); #define PPC_NOP() EMIT(PPC_INST_NOP) #define PPC_BLR() EMIT(PPC_INST_BLR) #define PPC_BLRL() EMIT(PPC_INST_BLRL) -#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | __PPC_RT(r)) -#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | __PPC_RT(d) | \ - __PPC_RA(a) | IMM_L(i)) +#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | ___PPC_RT(r)) +#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | ___PPC_RT(d) | \ + ___PPC_RA(a) | IMM_L(i)) #define PPC_MR(d, a) PPC_OR(d, a, a) #define PPC_LI(r, i) PPC_ADDI(r, 0, i) #define PPC_ADDIS(d, a, i) EMIT(PPC_INST_ADDIS | \ - __PPC_RS(d) | __PPC_RA(a) | IMM_L(i)) + ___PPC_RS(d) | ___PPC_RA(a) | IMM_L(i)) #define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) -#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | __PPC_RS(r) | \ - __PPC_RA(base) | ((i) & 0xfffc)) - -#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | __PPC_RT(r) | \ - __PPC_RA(base) | IMM_L(i)) -#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | __PPC_RT(r) | \ - __PPC_RA(base) | IMM_L(i)) -#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | __PPC_RT(r) | \ - __PPC_RA(base) | IMM_L(i)) +#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \ + ___PPC_RA(base) | ((i) & 0xfffc)) + +#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \ + ___PPC_RA(base) | IMM_L(i)) +#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \ + ___PPC_RA(base) | IMM_L(i)) +#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \ + ___PPC_RA(base) | IMM_L(i)) /* Convenience helpers for the above with 'far' offsets: */ #define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i); \ else { PPC_ADDIS(r, base, IMM_HA(i)); \ @@ -105,52 +105,52 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); else { PPC_ADDIS(r, base, IMM_HA(i)); \ PPC_LHZ(r, r, IMM_L(i)); } } while(0) -#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | __PPC_RA(a) | IMM_L(i)) -#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | __PPC_RA(a) | IMM_L(i)) -#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | __PPC_RA(a) | IMM_L(i)) -#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | __PPC_RA(a) | __PPC_RB(b)) - -#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | __PPC_RT(d) | \ - __PPC_RB(a) | __PPC_RA(b)) -#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | __PPC_RT(d) | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_MUL(d, a, b) EMIT(PPC_INST_MULLW | __PPC_RT(d) | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | __PPC_RT(d) | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | __PPC_RT(d) | \ - __PPC_RA(a) | IMM_L(i)) -#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | __PPC_RT(d) | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_RB(b)) -#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | __PPC_RA(d) | \ - __PPC_RS(a) | IMM_L(i)) -#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_RB(b)) -#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_RB(b)) -#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | __PPC_RA(d) | \ - __PPC_RS(a) | IMM_L(i)) -#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | __PPC_RA(d) | \ - __PPC_RS(a) | IMM_L(i)) -#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_RB(s)) -#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_RB(s)) +#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i)) +#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | ___PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | ___PPC_RA(a) | ___PPC_RB(b)) + +#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | ___PPC_RT(d) | \ + ___PPC_RB(a) | ___PPC_RA(b)) +#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | ___PPC_RT(d) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_MUL(d, a, b) EMIT(PPC_INST_MULLW | ___PPC_RT(d) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | ___PPC_RT(d) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | ___PPC_RT(d) | \ + ___PPC_RA(a) | IMM_L(i)) +#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | ___PPC_RT(d) | \ + ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | ___PPC_RA(d) | \ + ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | ___PPC_RA(d) | \ + ___PPC_RS(a) | IMM_L(i)) +#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | ___PPC_RA(d) | \ + ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | ___PPC_RA(d) | \ + ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | ___PPC_RA(d) | \ + ___PPC_RS(a) | IMM_L(i)) +#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | ___PPC_RA(d) | \ + ___PPC_RS(a) | IMM_L(i)) +#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | ___PPC_RA(d) | \ + ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | ___PPC_RA(d) | \ + ___PPC_RS(a) | ___PPC_RB(s)) /* slwi = rlwinm Rx, Ry, n, 0, 31-n */ -#define PPC_SLWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_SH(i) | \ +#define PPC_SLWI(d, a, i) EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \ + ___PPC_RS(a) | __PPC_SH(i) | \ __PPC_MB(0) | __PPC_ME(31-(i))) /* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ -#define PPC_SRWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_SH(32-(i)) | \ +#define PPC_SRWI(d, a, i) EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \ + ___PPC_RS(a) | __PPC_SH(32-(i)) | \ __PPC_MB(i) | __PPC_ME(31)) /* sldi = rldicr Rx, Ry, n, 63-n */ -#define PPC_SLDI(d, a, i) EMIT(PPC_INST_RLDICR | __PPC_RA(d) | \ - __PPC_RS(a) | __PPC_SH(i) | \ +#define PPC_SLDI(d, a, i) EMIT(PPC_INST_RLDICR | ___PPC_RA(d) | \ + ___PPC_RS(a) | __PPC_SH(i) | \ __PPC_MB(63-(i)) | (((i) & 0x20) >> 4)) -#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | __PPC_RT(d) | __PPC_RA(a)) +#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | ___PPC_RT(d) | ___PPC_RA(a)) /* Long jump; (unconditional 'branch') */ #define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 2dc8b14..dd11306 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -39,7 +39,7 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image, /* Make stackframe */ if (ctx->seen & SEEN_DATAREF) { /* If we call any helpers (for loads), save LR */ - EMIT(PPC_INST_MFLR | __PPC_RT(0)); + EMIT(PPC_INST_MFLR | __PPC_RT(R0)); PPC_STD(0, 1, 16); /* Back up non-volatile regs. */ @@ -56,7 +56,7 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image, PPC_STD(i, 1, -(8*(32-i))); } } - EMIT(PPC_INST_STDU | __PPC_RS(1) | __PPC_RA(1) | + EMIT(PPC_INST_STDU | __PPC_RS(R1) | __PPC_RA(R1) | (-BPF_PPC_STACKFRAME & 0xfffc)); } diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index e8a18d1..74d1e78 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -57,7 +57,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) lr = regs->link; sp = regs->gpr[1]; - perf_callchain_store(entry, regs->nip); + perf_callchain_store(entry, perf_instruction_pointer(regs)); if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD)) return; @@ -238,7 +238,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry, struct signal_frame_64 __user *sigframe; unsigned long __user *fp, *uregs; - next_ip = regs->nip; + next_ip = perf_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); @@ -444,7 +444,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, long level = 0; unsigned int __user *fp, *uregs; - next_ip = regs->nip; + next_ip = perf_instruction_pointer(regs); lr = regs->link; sp = regs->gpr[1]; perf_callchain_store(entry, next_ip); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8f84bcb..77b49dd 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -73,7 +73,10 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) { return 0; } -static inline void perf_read_regs(struct pt_regs *regs) { } +static inline void perf_read_regs(struct pt_regs *regs) +{ + regs->result = 0; +} static inline int perf_intr_is_nmi(struct pt_regs *regs) { return 0; @@ -116,6 +119,26 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) *addrp = mfspr(SPRN_SDAR); } +static bool mmcra_sihv(unsigned long mmcra) +{ + unsigned long sihv = MMCRA_SIHV; + + if (ppmu->flags & PPMU_ALT_SIPR) + sihv = POWER6_MMCRA_SIHV; + + return !!(mmcra & sihv); +} + +static bool mmcra_sipr(unsigned long mmcra) +{ + unsigned long sipr = MMCRA_SIPR; + + if (ppmu->flags & PPMU_ALT_SIPR) + sipr = POWER6_MMCRA_SIPR; + + return !!(mmcra & sipr); +} + static inline u32 perf_flags_from_msr(struct pt_regs *regs) { if (regs->msr & MSR_PR) @@ -128,19 +151,9 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs) static inline u32 perf_get_misc_flags(struct pt_regs *regs) { unsigned long mmcra = regs->dsisr; - unsigned long sihv = MMCRA_SIHV; - unsigned long sipr = MMCRA_SIPR; + unsigned long use_siar = regs->result; - /* Not a PMU interrupt: Make up flags from regs->msr */ - if (TRAP(regs) != 0xf00) - return perf_flags_from_msr(regs); - - /* - * If we don't support continuous sampling and this - * is not a marked event, same deal - */ - if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) && - !(mmcra & MMCRA_SAMPLE_ENABLE)) + if (!use_siar) return perf_flags_from_msr(regs); /* @@ -156,15 +169,10 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) return PERF_RECORD_MISC_USER; } - if (ppmu->flags & PPMU_ALT_SIPR) { - sihv = POWER6_MMCRA_SIHV; - sipr = POWER6_MMCRA_SIPR; - } - /* PR has priority over HV, so order below is important */ - if (mmcra & sipr) + if (mmcra_sipr(mmcra)) return PERF_RECORD_MISC_USER; - if ((mmcra & sihv) && (freeze_events_kernel != MMCR0_FCHV)) + if (mmcra_sihv(mmcra) && (freeze_events_kernel != MMCR0_FCHV)) return PERF_RECORD_MISC_HYPERVISOR; return PERF_RECORD_MISC_KERNEL; } @@ -172,10 +180,45 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs) /* * Overload regs->dsisr to store MMCRA so we only need to read it once * on each interrupt. + * Overload regs->result to specify whether we should use the MSR (result + * is zero) or the SIAR (result is non zero). */ static inline void perf_read_regs(struct pt_regs *regs) { - regs->dsisr = mfspr(SPRN_MMCRA); + unsigned long mmcra = mfspr(SPRN_MMCRA); + int marked = mmcra & MMCRA_SAMPLE_ENABLE; + int use_siar; + + /* + * If this isn't a PMU exception (eg a software event) the SIAR is + * not valid. Use pt_regs. + * + * If it is a marked event use the SIAR. + * + * If the PMU doesn't update the SIAR for non marked events use + * pt_regs. + * + * If the PMU has HV/PR flags then check to see if they + * place the exception in userspace. If so, use pt_regs. In + * continuous sampling mode the SIAR and the PMU exception are + * not synchronised, so they may be many instructions apart. + * This can result in confusing backtraces. We still want + * hypervisor samples as well as samples in the kernel with + * interrupts off hence the userspace check. + */ + if (TRAP(regs) != 0xf00) + use_siar = 0; + else if (marked) + use_siar = 1; + else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING)) + use_siar = 0; + else if (!(ppmu->flags & PPMU_NO_SIPR) && mmcra_sipr(mmcra)) + use_siar = 0; + else + use_siar = 1; + + regs->dsisr = mmcra; + regs->result = use_siar; } /* @@ -1329,18 +1372,12 @@ unsigned long perf_misc_flags(struct pt_regs *regs) */ unsigned long perf_instruction_pointer(struct pt_regs *regs) { - unsigned long mmcra = regs->dsisr; + unsigned long use_siar = regs->result; - /* Not a PMU interrupt */ - if (TRAP(regs) != 0xf00) - return regs->nip; - - /* Processor doesn't support sampling non marked events */ - if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) && - !(mmcra & MMCRA_SAMPLE_ENABLE)) + if (use_siar) + return mfspr(SPRN_SIAR) + perf_ip_adjust(regs); + else return regs->nip; - - return mfspr(SPRN_SIAR) + perf_ip_adjust(regs); } static bool pmc_overflow(unsigned long val) diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/currituck.c index 583e67f..9f6c33d6 100644 --- a/arch/powerpc/platforms/44x/currituck.c +++ b/arch/powerpc/platforms/44x/currituck.c @@ -160,7 +160,7 @@ static void __init ppc47x_setup_arch(void) /* No need to check the DMA config as we /know/ our windows are all of * RAM. Lets hope that doesn't change */ #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > 0xffffffff) { + if ((memblock_end_of_DRAM() - 1) > 0xffffffff) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c index 3661bcd..cf964e1 100644 --- a/arch/powerpc/platforms/82xx/km82xx.c +++ b/arch/powerpc/platforms/82xx/km82xx.c @@ -128,6 +128,11 @@ static __initdata struct cpm_pin km82xx_pins[] = { {3, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, /* TXP */ {3, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, /* TXN */ {3, 25, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* RXD */ + + /* SPI */ + {3, 16, CPM_PIN_INPUT | CPM_PIN_SECONDARY},/* SPI_MISO PD16 */ + {3, 17, CPM_PIN_INPUT | CPM_PIN_SECONDARY},/* SPI_MOSI PD17 */ + {3, 18, CPM_PIN_INPUT | CPM_PIN_SECONDARY},/* SPI_CLK PD18 */ }; static void __init init_ioports(void) diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index a266ba8..89923d7 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -3,7 +3,7 @@ * Author: Heiko Schocher <hs@denx.de> * * Description: - * Keymile KMETER1 board specific routines. + * Keymile 83xx platform specific routines. * * 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 @@ -70,54 +70,88 @@ static void __init mpc83xx_km_setup_arch(void) for_each_node_by_name(np, "spi") par_io_of_config(np); - for (np = NULL; (np = of_find_node_by_name(np, "ucc")) != NULL;) + for_each_node_by_name(np, "ucc") par_io_of_config(np); } np = of_find_compatible_node(NULL, "network", "ucc_geth"); if (np != NULL) { - uint svid; + /* + * handle mpc8360E Erratum QE_ENET10: + * RGMII AC values do not meet the specification + */ + uint svid = mfspr(SPRN_SVR); + struct device_node *np_par; + struct resource res; + void __iomem *base; + int ret; + + np_par = of_find_node_by_name(NULL, "par_io"); + if (np_par == NULL) { + printk(KERN_WARNING "%s couldn;t find par_io node\n", + __func__); + return; + } + /* Map Parallel I/O ports registers */ + ret = of_address_to_resource(np_par, 0, &res); + if (ret) { + printk(KERN_WARNING "%s couldn;t map par_io registers\n", + __func__); + return; + } + + base = ioremap(res.start, res.end - res.start + 1); + + /* + * set output delay adjustments to default values according + * table 5 in Errata Rev. 5, 9/2011: + * + * write 0b01 to UCC1 bits 18:19 + * write 0b01 to UCC2 option 1 bits 4:5 + * write 0b01 to UCC2 option 2 bits 16:17 + */ + clrsetbits_be32((base + 0xa8), 0x0c00f000, 0x04005000); + + /* + * set output delay adjustments to default values according + * table 3-13 in Reference Manual Rev.3 05/2010: + * + * write 0b01 to UCC2 option 2 bits 16:17 + * write 0b0101 to UCC1 bits 20:23 + * write 0b0101 to UCC2 option 1 bits 24:27 + */ + clrsetbits_be32((base + 0xac), 0x0000cff0, 0x00004550); - /* handle mpc8360ea rev.2.1 erratum 2: RGMII Timing */ - svid = mfspr(SPRN_SVR); if (SVR_REV(svid) == 0x0021) { - struct device_node *np_par; - struct resource res; - void __iomem *base; - int ret; - - np_par = of_find_node_by_name(NULL, "par_io"); - if (np_par == NULL) { - printk(KERN_WARNING "%s couldn;t find par_io node\n", - __func__); - return; - } - /* Map Parallel I/O ports registers */ - ret = of_address_to_resource(np_par, 0, &res); - if (ret) { - printk(KERN_WARNING "%s couldn;t map par_io registers\n", - __func__); - return; - } - base = ioremap(res.start, resource_size(&res)); + /* + * UCC2 option 1: write 0b1010 to bits 24:27 + * at address IMMRBAR+0x14AC + */ + clrsetbits_be32((base + 0xac), 0x000000f0, 0x000000a0); + } else if (SVR_REV(svid) == 0x0020) { + /* + * UCC1: write 0b11 to bits 18:19 + * at address IMMRBAR+0x14A8 + */ + setbits32((base + 0xa8), 0x00003000); /* - * IMMR + 0x14A8[4:5] = 11 (clk delay for UCC 2) - * IMMR + 0x14A8[18:19] = 11 (clk delay for UCC 1) + * UCC2 option 1: write 0b11 to bits 4:5 + * at address IMMRBAR+0x14A8 */ - setbits32((base + 0xa8), 0x0c003000); + setbits32((base + 0xa8), 0x0c000000); /* - * IMMR + 0x14AC[20:27] = 10101010 - * (data delay for both UCC's) + * UCC2 option 2: write 0b11 to bits 16:17 + * at address IMMRBAR+0x14AC */ - clrsetbits_be32((base + 0xac), 0xff0, 0xaa0); - iounmap(base); - of_node_put(np_par); + setbits32((base + 0xac), 0x0000c000); } + iounmap(base); + of_node_put(np_par); of_node_put(np); } -#endif /* CONFIG_QUICC_ENGINE */ +#endif /* CONFIG_QUICC_ENGINE */ } machine_device_initcall(mpc83xx_km, mpc83xx_declare_of_platform_devices); diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index f000d81..159c01e 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -23,6 +23,15 @@ config FSL_85XX_CACHE_SRAM cache-sram-size and cache-sram-offset kernel boot parameters should be passed when this option is enabled. +config BSC9131_RDB + bool "Freescale BSC9131RDB" + select DEFAULT_UIMAGE + help + This option enables support for the Freescale BSC9131RDB board. + The BSC9131 is a heterogeneous SoC containing an e500v2 powerpc and a + StarCore SC3850 DSP + Manufacturer : Freescale Semiconductor, Inc + config MPC8540_ADS bool "Freescale MPC8540 ADS" select DEFAULT_UIMAGE @@ -175,12 +184,6 @@ config SBC8548 help This option enables support for the Wind River SBC8548 board -config SBC8560 - bool "Wind River SBC8560" - select DEFAULT_UIMAGE - help - This option enables support for the Wind River SBC8560 board - config GE_IMP3A bool "GE Intelligent Platforms IMP3A" select DEFAULT_UIMAGE @@ -222,18 +225,6 @@ config P3041_DS help This option enables support for the P3041 DS board -config P3060_QDS - bool "Freescale P3060 QDS" - select DEFAULT_UIMAGE - select PPC_E500MC - select PHYS_64BIT - select SWIOTLB - select GPIO_MPC8XXX - select HAS_RAPIDIO - select PPC_EPAPR_HV_PIC - help - This option enables support for the P3060 QDS board - config P4080_DS bool "Freescale P4080 DS" select DEFAULT_UIMAGE @@ -263,6 +254,22 @@ config P5020_DS help This option enables support for the P5020 DS board +config PPC_QEMU_E500 + bool "QEMU generic e500 platform" + depends on EXPERIMENTAL + select DEFAULT_UIMAGE + help + This option enables support for running as a QEMU guest using + QEMU's generic e500 machine. This is not required if you're + using a QEMU machine that targets a specific board, such as + mpc8544ds. + + Unlike most e500 boards that target a specific CPU, this + platform works with any e500-family CPU that QEMU supports. + Thus, you'll need to make sure CONFIG_PPC_E500MC is set or + unset based on the emulated CPU (or actual host CPU in the case + of KVM). + endif # FSL_SOC_BOOKE config TQM85xx diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 2125d4c..3dfe811 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_SMP) += smp.o obj-y += common.o +obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o @@ -17,14 +18,13 @@ obj-$(CONFIG_P1022_DS) += p1022_ds.o obj-$(CONFIG_P1023_RDS) += p1023_rds.o obj-$(CONFIG_P2041_RDB) += p2041_rdb.o corenet_ds.o obj-$(CONFIG_P3041_DS) += p3041_ds.o corenet_ds.o -obj-$(CONFIG_P3060_QDS) += p3060_qds.o corenet_ds.o obj-$(CONFIG_P4080_DS) += p4080_ds.o corenet_ds.o obj-$(CONFIG_P5020_DS) += p5020_ds.o corenet_ds.o obj-$(CONFIG_STX_GP3) += stx_gp3.o obj-$(CONFIG_TQM85xx) += tqm85xx.o -obj-$(CONFIG_SBC8560) += sbc8560.o obj-$(CONFIG_SBC8548) += sbc8548.o obj-$(CONFIG_SOCRATES) += socrates.o socrates_fpga_pic.o obj-$(CONFIG_KSI8560) += ksi8560.o obj-$(CONFIG_XES_MPC85xx) += xes_mpc85xx.o obj-$(CONFIG_GE_IMP3A) += ge_imp3a.o +obj-$(CONFIG_PPC_QEMU_E500) += qemu_e500.o diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c new file mode 100644 index 0000000..9d57bed --- /dev/null +++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c @@ -0,0 +1,67 @@ +/* + * BSC913xRDB Board Setup + * + * Author: Priyanka Jain <Priyanka.Jain@freescale.com> + * + * Copyright 2011-2012 Freescale Semiconductor Inc. + * + * 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. + */ + +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <asm/mpic.h> +#include <sysdev/fsl_soc.h> +#include <asm/udbg.h> + +#include "mpc85xx.h" + +void __init bsc913x_rdb_pic_init(void) +{ + struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | + MPIC_SINGLE_DEST_CPU, + 0, 256, " OpenPIC "); + + if (!mpic) + pr_err("bsc913x: Failed to allocate MPIC structure\n"); + else + mpic_init(mpic); +} + +/* + * Setup the architecture + */ +static void __init bsc913x_rdb_setup_arch(void) +{ + if (ppc_md.progress) + ppc_md.progress("bsc913x_rdb_setup_arch()", 0); + + pr_info("bsc913x board from Freescale Semiconductor\n"); +} + +machine_device_initcall(bsc9131_rdb, mpc85xx_common_publish_devices); + +/* + * Called very early, device-tree isn't unflattened + */ + +static int __init bsc9131_rdb_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "fsl,bsc9131rdb"); +} + +define_machine(bsc9131_rdb) { + .name = "BSC9131 RDB", + .probe = bsc9131_rdb_probe, + .setup_arch = bsc913x_rdb_setup_arch, + .init_IRQ = bsc913x_rdb_pic_init, + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c index dd3617c..925b028 100644 --- a/arch/powerpc/platforms/85xx/corenet_ds.c +++ b/arch/powerpc/platforms/85xx/corenet_ds.c @@ -77,7 +77,7 @@ void __init corenet_ds_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { + if ((memblock_end_of_DRAM() - 1) > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c index 1801462..b6a728b 100644 --- a/arch/powerpc/platforms/85xx/ge_imp3a.c +++ b/arch/powerpc/platforms/85xx/ge_imp3a.c @@ -125,7 +125,7 @@ static void __init ge_imp3a_setup_arch(void) mpc85xx_smp_init(); #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { + if ((memblock_end_of_DRAM() - 1) > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index 585bd22b..767c7cf 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -75,7 +75,7 @@ static void __init mpc8536_ds_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { + if ((memblock_end_of_DRAM() - 1) > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 1fd91e9..6d3265f 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -114,71 +114,53 @@ void __init mpc85xx_ds_pic_init(void) } #ifdef CONFIG_PCI -static int primary_phb_addr; extern int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn); +static struct device_node *pci_with_uli; + static int mpc85xx_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { - struct device_node* node; - struct resource rsrc; - - node = hose->dn; - of_address_to_resource(node, 0, &rsrc); - - if ((rsrc.start & 0xfffff) == primary_phb_addr) { + if (hose->dn == pci_with_uli) return uli_exclude_device(hose, bus, devfn); - } return PCIBIOS_SUCCESSFUL; } #endif /* CONFIG_PCI */ -/* - * Setup the architecture - */ -static void __init mpc85xx_ds_setup_arch(void) +static void __init mpc85xx_ds_pci_init(void) { #ifdef CONFIG_PCI - struct device_node *np; - struct pci_controller *hose; -#endif - dma_addr_t max = 0xffffffff; + struct device_node *node; - if (ppc_md.progress) - ppc_md.progress("mpc85xx_ds_setup_arch()", 0); + fsl_pci_init(); -#ifdef CONFIG_PCI - for_each_node_by_type(np, "pci") { - if (of_device_is_compatible(np, "fsl,mpc8540-pci") || - of_device_is_compatible(np, "fsl,mpc8548-pcie") || - of_device_is_compatible(np, "fsl,p2020-pcie")) { - struct resource rsrc; - of_address_to_resource(np, 0, &rsrc); - if ((rsrc.start & 0xfffff) == primary_phb_addr) - fsl_add_bridge(np, 1); - else - fsl_add_bridge(np, 0); - - hose = pci_find_hose_for_OF_device(np); - max = min(max, hose->dma_window_base_cur + - hose->dma_window_size); + /* See if we have a ULI under the primary */ + + node = of_find_node_by_name(NULL, "uli1575"); + while ((pci_with_uli = of_get_parent(node))) { + of_node_put(node); + node = pci_with_uli; + + if (pci_with_uli == fsl_pci_primary) { + ppc_md.pci_exclude_device = mpc85xx_exclude_device; + break; } } - - ppc_md.pci_exclude_device = mpc85xx_exclude_device; #endif +} - mpc85xx_smp_init(); +/* + * Setup the architecture + */ +static void __init mpc85xx_ds_setup_arch(void) +{ + if (ppc_md.progress) + ppc_md.progress("mpc85xx_ds_setup_arch()", 0); -#ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { - ppc_swiotlb_enable = 1; - set_pci_dma_ops(&swiotlb_dma_ops); - ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; - } -#endif + mpc85xx_ds_pci_init(); + mpc85xx_smp_init(); printk("MPC85xx DS board from Freescale Semiconductor\n"); } @@ -190,14 +172,7 @@ static int __init mpc8544_ds_probe(void) { unsigned long root = of_get_flat_dt_root(); - if (of_flat_dt_is_compatible(root, "MPC8544DS")) { -#ifdef CONFIG_PCI - primary_phb_addr = 0xb000; -#endif - return 1; - } - - return 0; + return !!of_flat_dt_is_compatible(root, "MPC8544DS"); } machine_device_initcall(mpc8544_ds, mpc85xx_common_publish_devices); @@ -215,14 +190,7 @@ static int __init mpc8572_ds_probe(void) { unsigned long root = of_get_flat_dt_root(); - if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS")) { -#ifdef CONFIG_PCI - primary_phb_addr = 0x8000; -#endif - return 1; - } - - return 0; + return !!of_flat_dt_is_compatible(root, "fsl,MPC8572DS"); } /* @@ -232,14 +200,7 @@ static int __init p2020_ds_probe(void) { unsigned long root = of_get_flat_dt_root(); - if (of_flat_dt_is_compatible(root, "fsl,P2020DS")) { -#ifdef CONFIG_PCI - primary_phb_addr = 0x9000; -#endif - return 1; - } - - return 0; + return !!of_flat_dt_is_compatible(root, "fsl,P2020DS"); } define_machine(mpc8544_ds) { diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index d208ebc..8e4b094 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -359,7 +359,7 @@ static void __init mpc85xx_mds_setup_arch(void) mpc85xx_mds_qe_init(); #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { + if ((memblock_end_of_DRAM() - 1) > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index 313fce4..1910fdc 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -169,6 +169,7 @@ machine_device_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices); machine_device_initcall(p1020_utm_pc, mpc85xx_common_publish_devices); machine_device_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices); machine_device_initcall(p1025_rdb, mpc85xx_common_publish_devices); +machine_device_initcall(p1024_rdb, mpc85xx_common_publish_devices); /* * Called very early, device-tree isn't unflattened @@ -237,6 +238,13 @@ static int __init p1020_utm_pc_probe(void) return of_flat_dt_is_compatible(root, "fsl,P1020UTM-PC"); } +static int __init p1024_rdb_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return of_flat_dt_is_compatible(root, "fsl,P1024RDB"); +} + define_machine(p2020_rdb) { .name = "P2020 RDB", .probe = p2020_rdb_probe, @@ -348,3 +356,17 @@ define_machine(p1020_rdb_pc) { .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; + +define_machine(p1024_rdb) { + .name = "P1024 RDB", + .probe = p1024_rdb_probe, + .setup_arch = mpc85xx_rdb_setup_arch, + .init_IRQ = mpc85xx_rdb_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index f700c81..89ee02c 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -27,6 +27,7 @@ #include <sysdev/fsl_pci.h> #include <asm/udbg.h> #include <asm/fsl_guts.h> +#include <asm/fsl_lbc.h> #include "smp.h" #include "mpc85xx.h" @@ -142,17 +143,73 @@ static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port, { } +struct fsl_law { + u32 lawbar; + u32 reserved1; + u32 lawar; + u32 reserved[5]; +}; + +#define LAWBAR_MASK 0x00F00000 +#define LAWBAR_SHIFT 12 + +#define LAWAR_EN 0x80000000 +#define LAWAR_TGT_MASK 0x01F00000 +#define LAW_TRGT_IF_LBC (0x04 << 20) + +#define LAWAR_MASK (LAWAR_EN | LAWAR_TGT_MASK) +#define LAWAR_MATCH (LAWAR_EN | LAW_TRGT_IF_LBC) + +#define BR_BA 0xFFFF8000 + +/* + * Map a BRx value to a physical address + * + * The localbus BRx registers only store the lower 32 bits of the address. To + * obtain the upper four bits, we need to scan the LAW table. The entry which + * maps to the localbus will contain the upper four bits. + */ +static phys_addr_t lbc_br_to_phys(const void *ecm, unsigned int count, u32 br) +{ +#ifndef CONFIG_PHYS_64BIT + /* + * If we only have 32-bit addressing, then the BRx address *is* the + * physical address. + */ + return br & BR_BA; +#else + const struct fsl_law *law = ecm + 0xc08; + unsigned int i; + + for (i = 0; i < count; i++) { + u64 lawbar = in_be32(&law[i].lawbar); + u32 lawar = in_be32(&law[i].lawar); + + if ((lawar & LAWAR_MASK) == LAWAR_MATCH) + /* Extract the upper four bits */ + return (br & BR_BA) | ((lawbar & LAWBAR_MASK) << 12); + } + + return 0; +#endif +} + /** * p1022ds_set_monitor_port: switch the output to a different monitor port - * */ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) { struct device_node *guts_node; - struct device_node *indirect_node = NULL; + struct device_node *lbc_node = NULL; + struct device_node *law_node = NULL; struct ccsr_guts __iomem *guts; + struct fsl_lbc_regs *lbc = NULL; + void *ecm = NULL; u8 __iomem *lbc_lcs0_ba = NULL; u8 __iomem *lbc_lcs1_ba = NULL; + phys_addr_t cs0_addr, cs1_addr; + const __be32 *iprop; + unsigned int num_laws; u8 b; /* Map the global utilities registers. */ @@ -168,24 +225,42 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) goto exit; } - indirect_node = of_find_compatible_node(NULL, NULL, - "fsl,p1022ds-indirect-pixis"); - if (!indirect_node) { - pr_err("p1022ds: missing pixis indirect mode node\n"); + lbc_node = of_find_compatible_node(NULL, NULL, "fsl,p1022-elbc"); + if (!lbc_node) { + pr_err("p1022ds: missing localbus node\n"); + goto exit; + } + + lbc = of_iomap(lbc_node, 0); + if (!lbc) { + pr_err("p1022ds: could not map localbus node\n"); + goto exit; + } + + law_node = of_find_compatible_node(NULL, NULL, "fsl,ecm-law"); + if (!law_node) { + pr_err("p1022ds: missing local access window node\n"); goto exit; } - lbc_lcs0_ba = of_iomap(indirect_node, 0); - if (!lbc_lcs0_ba) { - pr_err("p1022ds: could not map localbus chip select 0\n"); + ecm = of_iomap(law_node, 0); + if (!ecm) { + pr_err("p1022ds: could not map local access window node\n"); goto exit; } - lbc_lcs1_ba = of_iomap(indirect_node, 1); - if (!lbc_lcs1_ba) { - pr_err("p1022ds: could not map localbus chip select 1\n"); + iprop = of_get_property(law_node, "fsl,num-laws", 0); + if (!iprop) { + pr_err("p1022ds: LAW node is missing fsl,num-laws property\n"); goto exit; } + num_laws = be32_to_cpup(iprop); + + cs0_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[0].br)); + cs1_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[1].br)); + + lbc_lcs0_ba = ioremap(cs0_addr, 1); + lbc_lcs1_ba = ioremap(cs1_addr, 1); /* Make sure we're in indirect mode first. */ if ((in_be32(&guts->pmuxcr) & PMUXCR_ELBCDIU_MASK) != @@ -254,10 +329,15 @@ exit: iounmap(lbc_lcs1_ba); if (lbc_lcs0_ba) iounmap(lbc_lcs0_ba); + if (lbc) + iounmap(lbc); + if (ecm) + iounmap(ecm); if (guts) iounmap(guts); - of_node_put(indirect_node); + of_node_put(law_node); + of_node_put(lbc_node); of_node_put(guts_node); } @@ -348,13 +428,7 @@ void __init p1022_ds_pic_init(void) */ static void __init disable_one_node(struct device_node *np, struct property *new) { - struct property *old; - - old = of_find_property(np, new->name, NULL); - if (old) - prom_update_property(np, new, old); - else - prom_add_property(np, new); + prom_update_property(np, new); } /* TRUE if there is a "video=fslfb" command-line parameter. */ @@ -450,7 +524,7 @@ static void __init p1022_ds_setup_arch(void) mpc85xx_smp_init(); #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { + if ((memblock_end_of_DRAM() - 1) > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/85xx/p3060_qds.c b/arch/powerpc/platforms/85xx/p3060_qds.c deleted file mode 100644 index 081cf4a..0000000 --- a/arch/powerpc/platforms/85xx/p3060_qds.c +++ /dev/null @@ -1,77 +0,0 @@ -/* - * P3060 QDS Setup - * - * Copyright 2011 Freescale Semiconductor Inc. - * - * 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. - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/phy.h> -#include <asm/machdep.h> -#include <asm/udbg.h> -#include <asm/mpic.h> -#include <linux/of_platform.h> -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> -#include <asm/ehv_pic.h> -#include "corenet_ds.h" - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p3060_qds_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); -#ifdef CONFIG_SMP - extern struct smp_ops_t smp_85xx_ops; -#endif - - if (of_flat_dt_is_compatible(root, "fsl,P3060QDS")) - return 1; - - /* Check if we're running under the Freescale hypervisor */ - if (of_flat_dt_is_compatible(root, "fsl,P3060QDS-hv")) { - ppc_md.init_IRQ = ehv_pic_init; - ppc_md.get_irq = ehv_pic_get_irq; - ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; - ppc_md.halt = fsl_hv_halt; -#ifdef CONFIG_SMP - /* - * Disable the timebase sync operations because we can't write - * to the timebase registers under the hypervisor. - */ - smp_85xx_ops.give_timebase = NULL; - smp_85xx_ops.take_timebase = NULL; -#endif - return 1; - } - - return 0; -} - -define_machine(p3060_qds) { - .name = "P3060 QDS", - .probe = p3060_qds_probe, - .setup_arch = corenet_ds_setup_arch, - .init_IRQ = corenet_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif - .get_irq = mpic_get_coreint_irq, - .restart = fsl_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, - .power_save = e500_idle, -}; - -machine_device_initcall(p3060_qds, corenet_ds_publish_devices); - -#ifdef CONFIG_SWIOTLB -machine_arch_initcall(p3060_qds, swiotlb_setup_bus_notifier); -#endif diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c new file mode 100644 index 0000000..95a2e53 --- /dev/null +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -0,0 +1,72 @@ +/* + * Paravirt target for a generic QEMU e500 machine + * + * This is intended to be a flexible device-tree-driven platform, not fixed + * to a particular piece of hardware or a particular spec of virtual hardware, + * beyond the assumption of an e500-family CPU. Some things are still hardcoded + * here, such as MPIC, but this is a limitation of the current code rather than + * an interface contract with QEMU. + * + * Copyright 2012 Freescale Semiconductor Inc. + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/of_fdt.h> +#include <asm/machdep.h> +#include <asm/time.h> +#include <asm/udbg.h> +#include <asm/mpic.h> +#include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> +#include "smp.h" +#include "mpc85xx.h" + +void __init qemu_e500_pic_init(void) +{ + struct mpic *mpic; + + mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, + 0, 256, " OpenPIC "); + + BUG_ON(mpic == NULL); + mpic_init(mpic); +} + +static void __init qemu_e500_setup_arch(void) +{ + ppc_md.progress("qemu_e500_setup_arch()", 0); + + fsl_pci_init(); + mpc85xx_smp_init(); +} + +/* + * Called very early, device-tree isn't unflattened + */ +static int __init qemu_e500_probe(void) +{ + unsigned long root = of_get_flat_dt_root(); + + return !!of_flat_dt_is_compatible(root, "fsl,qemu-e500"); +} + +machine_device_initcall(qemu_e500, mpc85xx_common_publish_devices); + +define_machine(qemu_e500) { + .name = "QEMU e500", + .probe = qemu_e500_probe, + .setup_arch = qemu_e500_setup_arch, + .init_IRQ = qemu_e500_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif + .get_irq = mpic_get_irq, + .restart = fsl_rstcr_restart, + .calibrate_decr = generic_calibrate_decr, + .progress = udbg_progress, +}; diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c deleted file mode 100644 index b1be632..0000000 --- a/arch/powerpc/platforms/85xx/sbc8560.c +++ /dev/null @@ -1,254 +0,0 @@ -/* - * Wind River SBC8560 setup and early boot code. - * - * Copyright 2007 Wind River Systems Inc. - * - * By Paul Gortmaker (see MAINTAINERS for contact information) - * - * Based largely on the MPC8560ADS support - Copyright 2005 Freescale Inc. - * - * 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. - */ - -#include <linux/stddef.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/kdev_t.h> -#include <linux/delay.h> -#include <linux/seq_file.h> -#include <linux/of_platform.h> - -#include <asm/time.h> -#include <asm/machdep.h> -#include <asm/pci-bridge.h> -#include <asm/mpic.h> -#include <mm/mmu_decl.h> -#include <asm/udbg.h> - -#include <sysdev/fsl_soc.h> -#include <sysdev/fsl_pci.h> - -#include "mpc85xx.h" - -#ifdef CONFIG_CPM2 -#include <asm/cpm2.h> -#include <sysdev/cpm2_pic.h> -#endif - -static void __init sbc8560_pic_init(void) -{ - struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN, - 0, 256, " OpenPIC "); - BUG_ON(mpic == NULL); - mpic_init(mpic); - - mpc85xx_cpm2_pic_init(); -} - -/* - * Setup the architecture - */ -#ifdef CONFIG_CPM2 -struct cpm_pin { - int port, pin, flags; -}; - -static const struct cpm_pin sbc8560_pins[] = { - /* SCC1 */ - {3, 29, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 30, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {3, 31, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* SCC2 */ - {3, 26, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 27, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* FCC2 */ - {1, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 20, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 21, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 22, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 25, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 26, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 27, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 29, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {1, 30, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 31, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {2, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK14 */ - {2, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK13 */ - - /* FCC3 */ - {1, 4, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 5, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 6, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 7, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 8, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 9, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 10, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 11, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 12, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 13, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 14, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 15, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 16, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* CLK16 */ - {2, 17, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* CLK15 */ -}; - -static void __init init_ioports(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(sbc8560_pins); i++) { - const struct cpm_pin *pin = &sbc8560_pins[i]; - cpm2_set_pin(pin->port, pin->pin, pin->flags); - } - - cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK13, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK14, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK15, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK16, CPM_CLK_TX); -} -#endif - -static void __init sbc8560_setup_arch(void) -{ -#ifdef CONFIG_PCI - struct device_node *np; -#endif - - if (ppc_md.progress) - ppc_md.progress("sbc8560_setup_arch()", 0); - -#ifdef CONFIG_CPM2 - cpm2_reset(); - init_ioports(); -#endif - -#ifdef CONFIG_PCI - for_each_compatible_node(np, "pci", "fsl,mpc8540-pci") - fsl_add_bridge(np, 1); -#endif -} - -static void sbc8560_show_cpuinfo(struct seq_file *m) -{ - uint pvid, svid, phid1; - - pvid = mfspr(SPRN_PVR); - svid = mfspr(SPRN_SVR); - - seq_printf(m, "Vendor\t\t: Wind River\n"); - seq_printf(m, "PVR\t\t: 0x%x\n", pvid); - seq_printf(m, "SVR\t\t: 0x%x\n", svid); - - /* Display cpu Pll setting */ - phid1 = mfspr(SPRN_HID1); - seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f)); -} - -machine_device_initcall(sbc8560, mpc85xx_common_publish_devices); - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init sbc8560_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - return of_flat_dt_is_compatible(root, "SBC8560"); -} - -#ifdef CONFIG_RTC_DRV_M48T59 -static int __init sbc8560_rtc_init(void) -{ - struct device_node *np; - struct resource res; - struct platform_device *rtc_dev; - - np = of_find_compatible_node(NULL, NULL, "m48t59"); - if (np == NULL) { - printk("No RTC in DTB. Has it been eaten by wild dogs?\n"); - return -ENODEV; - } - - of_address_to_resource(np, 0, &res); - of_node_put(np); - - printk("Found RTC (m48t59) at i/o 0x%x\n", res.start); - - rtc_dev = platform_device_register_simple("rtc-m48t59", 0, &res, 1); - - if (IS_ERR(rtc_dev)) { - printk("Registering sbc8560 RTC device failed\n"); - return PTR_ERR(rtc_dev); - } - - return 0; -} - -arch_initcall(sbc8560_rtc_init); - -#endif /* M48T59 */ - -static __u8 __iomem *brstcr; - -static int __init sbc8560_bdrstcr_init(void) -{ - struct device_node *np; - struct resource res; - - np = of_find_compatible_node(NULL, NULL, "wrs,sbc8560-brstcr"); - if (np == NULL) { - printk(KERN_WARNING "sbc8560: No board specific RSTCR in DTB.\n"); - return -ENODEV; - } - - of_address_to_resource(np, 0, &res); - - printk(KERN_INFO "sbc8560: Found BRSTCR at %pR\n", &res); - - brstcr = ioremap(res.start, resource_size(&res)); - if(!brstcr) - printk(KERN_WARNING "sbc8560: ioremap of brstcr failed.\n"); - - of_node_put(np); - - return 0; -} - -arch_initcall(sbc8560_bdrstcr_init); - -void sbc8560_rstcr_restart(char * cmd) -{ - local_irq_disable(); - if(brstcr) - clrbits8(brstcr, 0x80); - - while(1); -} - -define_machine(sbc8560) { - .name = "SBC8560", - .probe = sbc8560_probe, - .setup_arch = sbc8560_setup_arch, - .init_IRQ = sbc8560_pic_init, - .show_cpuinfo = sbc8560_show_cpuinfo, - .get_irq = mpic_get_irq, - .restart = sbc8560_rstcr_restart, - .calibrate_decr = generic_calibrate_decr, - .progress = udbg_progress, -}; diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c index 4d786c2..3e70a20 100644 --- a/arch/powerpc/platforms/85xx/tqm85xx.c +++ b/arch/powerpc/platforms/85xx/tqm85xx.c @@ -102,7 +102,7 @@ static void tqm85xx_show_cpuinfo(struct seq_file *m) seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f)); } -static void __init tqm85xx_ti1520_fixup(struct pci_dev *pdev) +static void __devinit tqm85xx_ti1520_fixup(struct pci_dev *pdev) { unsigned int val; diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c index 1fca663..563aafa8 100644 --- a/arch/powerpc/platforms/86xx/gef_ppc9a.c +++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c @@ -164,7 +164,7 @@ static void gef_ppc9a_show_cpuinfo(struct seq_file *m) gef_ppc9a_get_vme_is_syscon() ? "yes" : "no"); } -static void __init gef_ppc9a_nec_fixup(struct pci_dev *pdev) +static void __devinit gef_ppc9a_nec_fixup(struct pci_dev *pdev) { unsigned int val; diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c index 14e0e576..cc6a91a 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc310.c +++ b/arch/powerpc/platforms/86xx/gef_sbc310.c @@ -152,7 +152,7 @@ static void gef_sbc310_show_cpuinfo(struct seq_file *m) } -static void __init gef_sbc310_nec_fixup(struct pci_dev *pdev) +static void __devinit gef_sbc310_nec_fixup(struct pci_dev *pdev) { unsigned int val; diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index 1638f43..aead6b3 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -141,7 +141,7 @@ static void gef_sbc610_show_cpuinfo(struct seq_file *m) seq_printf(m, "SVR\t\t: 0x%x\n", svid); } -static void __init gef_sbc610_nec_fixup(struct pci_dev *pdev) +static void __devinit gef_sbc610_nec_fixup(struct pci_dev *pdev) { unsigned int val; diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 3755e61..817245b 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -102,7 +102,7 @@ mpc86xx_hpcn_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (memblock_end_of_DRAM() > max) { + if ((memblock_end_of_DRAM() - 1) > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index a35ca44..e7a896a 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -25,6 +25,7 @@ source "arch/powerpc/platforms/wsp/Kconfig" config KVM_GUEST bool "KVM Guest support" default n + select EPAPR_PARAVIRT ---help--- This option enables various optimizations for running under the KVM hypervisor. Overhead for the kernel when not running inside KVM should @@ -32,6 +33,14 @@ config KVM_GUEST In case of doubt, say Y +config EPAPR_PARAVIRT + bool "ePAPR para-virtualization support" + default n + help + Enables ePAPR para-virtualization support for guests. + + In case of doubt, say Y + config PPC_NATIVE bool depends on 6xx || PPC64 diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 61c9550..30fd01d 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -159,6 +159,10 @@ config PPC_E500MC bool "e500mc Support" select PPC_FPU depends on E500 + help + This must be enabled for running on e500mc (and derivatives + such as e5500/e6500), and must be disabled for running on + e500v1 or e500v2. config PPC_FPU bool diff --git a/arch/powerpc/platforms/cell/beat_hvCall.S b/arch/powerpc/platforms/cell/beat_hvCall.S index 74c8174..96c8019 100644 --- a/arch/powerpc/platforms/cell/beat_hvCall.S +++ b/arch/powerpc/platforms/cell/beat_hvCall.S @@ -22,8 +22,6 @@ #include <asm/ppc_asm.h> -#define STK_PARM(i) (48 + ((i)-3)*8) - /* Not implemented on Beat, now */ #define HCALL_INST_PRECALL #define HCALL_INST_POSTCALL @@ -74,7 +72,7 @@ _GLOBAL(beat_hcall_norets8) mr r6,r7 mr r7,r8 mr r8,r9 - ld r10,STK_PARM(r10)(r1) + ld r10,STK_PARAM(R10)(r1) HVSC /* invoke the hypervisor */ @@ -94,7 +92,7 @@ _GLOBAL(beat_hcall1) HCALL_INST_PRECALL - std r4,STK_PARM(r4)(r1) /* save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* save ret buffer */ mr r11,r3 mr r3,r5 @@ -108,7 +106,7 @@ _GLOBAL(beat_hcall1) HCALL_INST_POSTCALL - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) lwz r0,8(r1) @@ -125,7 +123,7 @@ _GLOBAL(beat_hcall2) HCALL_INST_PRECALL - std r4,STK_PARM(r4)(r1) /* save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* save ret buffer */ mr r11,r3 mr r3,r5 @@ -139,7 +137,7 @@ _GLOBAL(beat_hcall2) HCALL_INST_POSTCALL - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) @@ -157,7 +155,7 @@ _GLOBAL(beat_hcall3) HCALL_INST_PRECALL - std r4,STK_PARM(r4)(r1) /* save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* save ret buffer */ mr r11,r3 mr r3,r5 @@ -171,7 +169,7 @@ _GLOBAL(beat_hcall3) HCALL_INST_POSTCALL - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) @@ -190,7 +188,7 @@ _GLOBAL(beat_hcall4) HCALL_INST_PRECALL - std r4,STK_PARM(r4)(r1) /* save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* save ret buffer */ mr r11,r3 mr r3,r5 @@ -204,7 +202,7 @@ _GLOBAL(beat_hcall4) HCALL_INST_POSTCALL - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) @@ -224,7 +222,7 @@ _GLOBAL(beat_hcall5) HCALL_INST_PRECALL - std r4,STK_PARM(r4)(r1) /* save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* save ret buffer */ mr r11,r3 mr r3,r5 @@ -238,7 +236,7 @@ _GLOBAL(beat_hcall5) HCALL_INST_POSTCALL - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) @@ -259,7 +257,7 @@ _GLOBAL(beat_hcall6) HCALL_INST_PRECALL - std r4,STK_PARM(r4)(r1) /* save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* save ret buffer */ mr r11,r3 mr r3,r5 @@ -273,7 +271,7 @@ _GLOBAL(beat_hcall6) HCALL_INST_POSTCALL - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index b9f509a..dca2136 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -518,7 +518,6 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, __set_bit(0, window->table.it_map); tce_build_cell(&window->table, window->table.it_offset, 1, (unsigned long)iommu->pad_page, DMA_TO_DEVICE, NULL); - window->table.it_hint = window->table.it_blocksize; return window; } @@ -552,8 +551,7 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev) iommu = cell_iommu_for_node(dev_to_node(dev)); if (iommu == NULL || list_empty(&iommu->windows)) { printk(KERN_ERR "iommu: missing iommu for %s (node %d)\n", - dev->of_node ? dev->of_node->full_name : "?", - dev_to_node(dev)); + of_node_full_name(dev->of_node), dev_to_node(dev)); return NULL; } window = list_entry(iommu->windows.next, struct iommu_window, list); diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S index 77b48b2..3cd2628 100644 --- a/arch/powerpc/platforms/powernv/opal-takeover.S +++ b/arch/powerpc/platforms/powernv/opal-takeover.S @@ -14,8 +14,6 @@ #include <asm/asm-offsets.h> #include <asm/opal.h> -#define STK_PARAM(i) (48 + ((i)-3)*8) - #define H_HAL_TAKEOVER 0x5124 #define H_HAL_TAKEOVER_QUERY_MAGIC -1 @@ -23,14 +21,14 @@ _GLOBAL(opal_query_takeover) mfcr r0 stw r0,8(r1) - std r3,STK_PARAM(r3)(r1) - std r4,STK_PARAM(r4)(r1) + std r3,STK_PARAM(R3)(r1) + std r4,STK_PARAM(R4)(r1) li r3,H_HAL_TAKEOVER li r4,H_HAL_TAKEOVER_QUERY_MAGIC HVSC - ld r10,STK_PARAM(r3)(r1) + ld r10,STK_PARAM(R3)(r1) std r4,0(r10) - ld r10,STK_PARAM(r4)(r1) + ld r10,STK_PARAM(R4)(r1) std r5,0(r10) lwz r0,8(r1) mtcrf 0xff,r0 diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index fbdd74d..9cda6a1 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -589,7 +589,7 @@ static int __devinit pnv_ioda_configure_pe(struct pnv_phb *phb, dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; parent = pe->pbus->self; - count = pe->pbus->subordinate - pe->pbus->secondary + 1; + count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1; switch(count) { case 1: bcomp = OpalPciBusAll; break; case 2: bcomp = OpalPciBus7Bits; break; @@ -816,11 +816,11 @@ static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev, pe->pdev = NULL; pe->tce32_seg = -1; pe->mve_number = -1; - pe->rid = bus->secondary << 8; + pe->rid = bus->busn_res.start << 8; pe->dma_weight = 0; - pe_info(pe, "Secondary busses %d..%d associated with PE\n", - bus->secondary, bus->subordinate); + pe_info(pe, "Secondary busses %pR associated with PE\n", + &bus->busn_res); if (pnv_ioda_configure_pe(phb, pe)) { /* XXX What do we do here ? */ diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c index 4cb375c..fb50631 100644 --- a/arch/powerpc/platforms/pseries/eeh_event.c +++ b/arch/powerpc/platforms/pseries/eeh_event.c @@ -85,8 +85,10 @@ static int eeh_event_handler(void * dummy) set_current_state(TASK_INTERRUPTIBLE); /* Don't add to load average */ edev = handle_eeh_events(event); - eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING); - pci_dev_put(edev->pdev); + if (edev) { + eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING); + pci_dev_put(edev->pdev); + } kfree(event); mutex_unlock(&eeh_event_mutex); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 8752f79..c33360ec 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -81,7 +81,7 @@ static int pseries_eeh_init(void) ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); ibm_configure_pe = rtas_token("ibm,configure-pe"); - ibm_configure_bridge = rtas_token ("ibm,configure-bridge"); + ibm_configure_bridge = rtas_token("ibm,configure-bridge"); /* necessary sanity check */ if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) { @@ -89,7 +89,7 @@ static int pseries_eeh_init(void) __func__); return -EINVAL; } else if (ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE) { - pr_warning("%s: RTAS service <ibm, set-slot-reset> invalid\n", + pr_warning("%s: RTAS service <ibm,set-slot-reset> invalid\n", __func__); return -EINVAL; } else if (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 3ce73d0..444fe77 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -13,8 +13,6 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> -#define STK_PARM(i) (48 + ((i)-3)*8) - #ifdef CONFIG_TRACEPOINTS .section ".toc","aw" @@ -26,7 +24,7 @@ hcall_tracepoint_refcount: .section ".text" /* - * precall must preserve all registers. use unused STK_PARM() + * precall must preserve all registers. use unused STK_PARAM() * areas to save snapshots and opcode. We branch around this * in early init (eg when populating the MMU hashtable) by using an * unconditional cpu feature. @@ -40,28 +38,28 @@ END_FTR_SECTION(0, 1); \ cmpdi r12,0; \ beq+ 1f; \ mflr r0; \ - std r3,STK_PARM(r3)(r1); \ - std r4,STK_PARM(r4)(r1); \ - std r5,STK_PARM(r5)(r1); \ - std r6,STK_PARM(r6)(r1); \ - std r7,STK_PARM(r7)(r1); \ - std r8,STK_PARM(r8)(r1); \ - std r9,STK_PARM(r9)(r1); \ - std r10,STK_PARM(r10)(r1); \ + std r3,STK_PARAM(R3)(r1); \ + std r4,STK_PARAM(R4)(r1); \ + std r5,STK_PARAM(R5)(r1); \ + std r6,STK_PARAM(R6)(r1); \ + std r7,STK_PARAM(R7)(r1); \ + std r8,STK_PARAM(R8)(r1); \ + std r9,STK_PARAM(R9)(r1); \ + std r10,STK_PARAM(R10)(r1); \ std r0,16(r1); \ - addi r4,r1,STK_PARM(FIRST_REG); \ + addi r4,r1,STK_PARAM(FIRST_REG); \ stdu r1,-STACK_FRAME_OVERHEAD(r1); \ bl .__trace_hcall_entry; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ - ld r3,STK_PARM(r3)(r1); \ - ld r4,STK_PARM(r4)(r1); \ - ld r5,STK_PARM(r5)(r1); \ - ld r6,STK_PARM(r6)(r1); \ - ld r7,STK_PARM(r7)(r1); \ - ld r8,STK_PARM(r8)(r1); \ - ld r9,STK_PARM(r9)(r1); \ - ld r10,STK_PARM(r10)(r1); \ + ld r3,STK_PARAM(R3)(r1); \ + ld r4,STK_PARAM(R4)(r1); \ + ld r5,STK_PARAM(R5)(r1); \ + ld r6,STK_PARAM(R6)(r1); \ + ld r7,STK_PARAM(R7)(r1); \ + ld r8,STK_PARAM(R8)(r1); \ + ld r9,STK_PARAM(R9)(r1); \ + ld r10,STK_PARAM(R10)(r1); \ mtlr r0; \ 1: @@ -79,8 +77,8 @@ END_FTR_SECTION(0, 1); \ cmpdi r12,0; \ beq+ 1f; \ mflr r0; \ - ld r6,STK_PARM(r3)(r1); \ - std r3,STK_PARM(r3)(r1); \ + ld r6,STK_PARAM(R3)(r1); \ + std r3,STK_PARAM(R3)(r1); \ mr r4,r3; \ mr r3,r6; \ std r0,16(r1); \ @@ -88,7 +86,7 @@ END_FTR_SECTION(0, 1); \ bl .__trace_hcall_exit; \ addi r1,r1,STACK_FRAME_OVERHEAD; \ ld r0,16(r1); \ - ld r3,STK_PARM(r3)(r1); \ + ld r3,STK_PARAM(R3)(r1); \ mtlr r0; \ 1: @@ -114,7 +112,7 @@ _GLOBAL(plpar_hcall_norets) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL(r4) + HCALL_INST_PRECALL(R4) HVSC /* invoke the hypervisor */ @@ -130,9 +128,9 @@ _GLOBAL(plpar_hcall) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL(r5) + HCALL_INST_PRECALL(R5) - std r4,STK_PARM(r4)(r1) /* Save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* Save ret buffer */ mr r4,r5 mr r5,r6 @@ -143,7 +141,7 @@ _GLOBAL(plpar_hcall) HVSC /* invoke the hypervisor */ - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) @@ -168,7 +166,7 @@ _GLOBAL(plpar_hcall_raw) mfcr r0 stw r0,8(r1) - std r4,STK_PARM(r4)(r1) /* Save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* Save ret buffer */ mr r4,r5 mr r5,r6 @@ -179,7 +177,7 @@ _GLOBAL(plpar_hcall_raw) HVSC /* invoke the hypervisor */ - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) @@ -196,9 +194,9 @@ _GLOBAL(plpar_hcall9) mfcr r0 stw r0,8(r1) - HCALL_INST_PRECALL(r5) + HCALL_INST_PRECALL(R5) - std r4,STK_PARM(r4)(r1) /* Save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* Save ret buffer */ mr r4,r5 mr r5,r6 @@ -206,14 +204,14 @@ _GLOBAL(plpar_hcall9) mr r7,r8 mr r8,r9 mr r9,r10 - ld r10,STK_PARM(r11)(r1) /* put arg7 in R10 */ - ld r11,STK_PARM(r12)(r1) /* put arg8 in R11 */ - ld r12,STK_PARM(r13)(r1) /* put arg9 in R12 */ + ld r10,STK_PARAM(R11)(r1) /* put arg7 in R10 */ + ld r11,STK_PARAM(R12)(r1) /* put arg8 in R11 */ + ld r12,STK_PARAM(R13)(r1) /* put arg9 in R12 */ HVSC /* invoke the hypervisor */ mr r0,r12 - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) @@ -238,7 +236,7 @@ _GLOBAL(plpar_hcall9_raw) mfcr r0 stw r0,8(r1) - std r4,STK_PARM(r4)(r1) /* Save ret buffer */ + std r4,STK_PARAM(R4)(r1) /* Save ret buffer */ mr r4,r5 mr r5,r6 @@ -246,14 +244,14 @@ _GLOBAL(plpar_hcall9_raw) mr r7,r8 mr r8,r9 mr r9,r10 - ld r10,STK_PARM(r11)(r1) /* put arg7 in R10 */ - ld r11,STK_PARM(r12)(r1) /* put arg8 in R11 */ - ld r12,STK_PARM(r13)(r1) /* put arg9 in R12 */ + ld r10,STK_PARAM(R11)(r1) /* put arg7 in R10 */ + ld r11,STK_PARAM(R12)(r1) /* put arg8 in R11 */ + ld r12,STK_PARAM(R13)(r1) /* put arg9 in R12 */ HVSC /* invoke the hypervisor */ mr r0,r12 - ld r12,STK_PARM(r4)(r1) + ld r12,STK_PARAM(R4)(r1) std r4, 0(r12) std r5, 8(r12) std r6, 16(r12) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 2d311c0..bca220f 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -192,12 +192,15 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long l, limit; long tcenum_start = tcenum, npages_start = npages; int ret = 0; + unsigned long flags; if (npages == 1) { return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, direction, attrs); } + local_irq_save(flags); /* to protect tcep and the page behind it */ + tcep = __get_cpu_var(tce_page); /* This is safe to do since interrupts are off when we're called @@ -207,6 +210,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcep = (u64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) { + local_irq_restore(flags); return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, direction, attrs); } @@ -240,6 +244,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcenum += limit; } while (npages > 0 && !rc); + local_irq_restore(flags); + if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { ret = (int)rc; tce_freemulti_pSeriesLP(tbl, tcenum_start, @@ -707,6 +713,21 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); +static inline void __remove_ddw(struct device_node *np, const u32 *ddw_avail, u64 liobn) +{ + int ret; + + ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); + if (ret) + pr_warning("%s: failed to remove DMA window: rtas returned " + "%d to ibm,remove-pe-dma-window(%x) %llx\n", + np->full_name, ret, ddw_avail[2], liobn); + else + pr_debug("%s: successfully removed DMA window: rtas returned " + "%d to ibm,remove-pe-dma-window(%x) %llx\n", + np->full_name, ret, ddw_avail[2], liobn); +} + static void remove_ddw(struct device_node *np) { struct dynamic_dma_window_prop *dwp; @@ -736,15 +757,7 @@ static void remove_ddw(struct device_node *np) pr_debug("%s successfully cleared tces in window.\n", np->full_name); - ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); - if (ret) - pr_warning("%s: failed to remove direct window: rtas returned " - "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); - else - pr_debug("%s: successfully removed direct window: rtas returned " - "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); + __remove_ddw(np, ddw_avail, liobn); delprop: ret = prom_remove_property(np, win64); @@ -869,6 +882,35 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, return ret; } +static void restore_default_window(struct pci_dev *dev, + u32 ddw_restore_token, unsigned long liobn) +{ + struct eeh_dev *edev; + u32 cfg_addr; + u64 buid; + int ret; + + /* + * Get the config address and phb buid of the PE window. + * Rely on eeh to retrieve this for us. + * Retrieve them from the pci device, not the node with the + * dma-window property + */ + edev = pci_dev_to_eeh_dev(dev); + cfg_addr = edev->config_addr; + if (edev->pe_config_addr) + cfg_addr = edev->pe_config_addr; + buid = edev->phb->buid; + + do { + ret = rtas_call(ddw_restore_token, 3, 1, NULL, cfg_addr, + BUID_HI(buid), BUID_LO(buid)); + } while (rtas_busy_delay(ret)); + dev_info(&dev->dev, + "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d\n", + ddw_restore_token, cfg_addr, BUID_HI(buid), BUID_LO(buid), ret); +} + /* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, @@ -889,9 +931,13 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) u64 dma_addr, max_addr; struct device_node *dn; const u32 *uninitialized_var(ddw_avail); + const u32 *uninitialized_var(ddw_extensions); + u32 ddw_restore_token = 0; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; + const void *dma_window = NULL; + unsigned long liobn, offset, size; mutex_lock(&direct_window_init_mutex); @@ -911,7 +957,40 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) if (!ddw_avail || len < 3 * sizeof(u32)) goto out_unlock; - /* + /* + * the extensions property is only required to exist in certain + * levels of firmware and later + * the ibm,ddw-extensions property is a list with the first + * element containing the number of extensions and each + * subsequent entry is a value corresponding to that extension + */ + ddw_extensions = of_get_property(pdn, "ibm,ddw-extensions", &len); + if (ddw_extensions) { + /* + * each new defined extension length should be added to + * the top of the switch so the "earlier" entries also + * get picked up + */ + switch (ddw_extensions[0]) { + /* ibm,reset-pe-dma-windows */ + case 1: + ddw_restore_token = ddw_extensions[1]; + break; + } + } + + /* + * Only remove the existing DMA window if we can restore back to + * the default state. Removing the existing window maximizes the + * resources available to firmware for dynamic window creation. + */ + if (ddw_restore_token) { + dma_window = of_get_property(pdn, "ibm,dma-window", NULL); + of_parse_dma_window(pdn, dma_window, &liobn, &offset, &size); + __remove_ddw(pdn, ddw_avail, liobn); + } + + /* * Query if there is a second window of size to map the * whole partition. Query returns number of windows, largest * block assigned to PE (partition endpoint), and two bitmasks @@ -920,7 +999,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dn = pci_device_to_OF_node(dev); ret = query_ddw(dev, ddw_avail, &query); if (ret != 0) - goto out_unlock; + goto out_restore_window; if (query.windows_available == 0) { /* @@ -929,7 +1008,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * trading in for a larger page size. */ dev_dbg(&dev->dev, "no free dynamic windows"); - goto out_unlock; + goto out_restore_window; } if (query.page_size & 4) { page_shift = 24; /* 16MB */ @@ -940,7 +1019,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) } else { dev_dbg(&dev->dev, "no supported direct page size in mask %x", query.page_size); - goto out_unlock; + goto out_restore_window; } /* verify the window * number of ptes will map the partition */ /* check largest block * page size > max memory hotplug addr */ @@ -949,14 +1028,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); - goto out_unlock; + goto out_restore_window; } len = order_base_2(max_addr); win64 = kzalloc(sizeof(struct property), GFP_KERNEL); if (!win64) { dev_info(&dev->dev, "couldn't allocate property for 64bit dma window\n"); - goto out_unlock; + goto out_restore_window; } win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); @@ -1018,6 +1097,10 @@ out_free_prop: kfree(win64->value); kfree(win64); +out_restore_window: + if (ddw_restore_token) + restore_default_window(dev, ddw_restore_token, liobn); + out_unlock: mutex_unlock(&direct_window_init_mutex); return dma_addr; @@ -1051,7 +1134,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%s\n", - pci_name(dev), dn? dn->full_name : "<null>"); + pci_name(dev), of_node_full_name(dn)); return; } pr_debug(" parent is %s\n", pdn->full_name); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 029a562..dd30b12 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -67,7 +67,6 @@ static int update_dt_property(struct device_node *dn, struct property **prop, const char *name, u32 vd, char *value) { struct property *new_prop = *prop; - struct property *old_prop; int more = 0; /* A negative 'vd' value indicates that only part of the new property @@ -117,12 +116,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, } if (!more) { - old_prop = of_find_property(dn, new_prop->name, NULL); - if (old_prop) - prom_update_property(dn, new_prop, old_prop); - else - prom_add_property(dn, new_prop); - + prom_update_property(dn, new_prop); new_prop = NULL; } diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 8b7bafa..3ccebc8 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -121,7 +121,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus) if (!num) return; pcibios_setup_bus_devices(bus); - max = bus->secondary; + max = bus->busn_res.start; for (pass=0; pass < 2; pass++) list_for_each_entry(dev, &bus->devices, bus_list) { if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index c71be66..455760b 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -11,6 +11,7 @@ #include <linux/moduleparam.h> #include <linux/cpuidle.h> #include <linux/cpu.h> +#include <linux/notifier.h> #include <asm/paca.h> #include <asm/reg.h> @@ -189,17 +190,40 @@ static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = { .enter = &shared_cede_loop }, }; -int pseries_notify_cpuidle_add_cpu(int cpu) +static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n, + unsigned long action, void *hcpu) { + int hotcpu = (unsigned long)hcpu; struct cpuidle_device *dev = - per_cpu_ptr(pseries_cpuidle_devices, cpu); + per_cpu_ptr(pseries_cpuidle_devices, hotcpu); + if (dev && cpuidle_get_driver()) { - cpuidle_disable_device(dev); - cpuidle_enable_device(dev); + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + cpuidle_pause_and_lock(); + cpuidle_enable_device(dev); + cpuidle_resume_and_unlock(); + break; + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + cpuidle_pause_and_lock(); + cpuidle_disable_device(dev); + cpuidle_resume_and_unlock(); + break; + + default: + return NOTIFY_DONE; + } } - return 0; + return NOTIFY_OK; } +static struct notifier_block setup_hotplug_notifier = { + .notifier_call = pseries_cpuidle_add_cpu_notifier, +}; + /* * pseries_cpuidle_driver_init() */ @@ -324,6 +348,7 @@ static int __init pseries_processor_idle_init(void) return retval; } + register_cpu_notifier(&setup_hotplug_notifier); printk(KERN_DEBUG "pseries_idle_driver registered\n"); return 0; @@ -332,6 +357,7 @@ static int __init pseries_processor_idle_init(void) static void __exit pseries_processor_idle_exit(void) { + unregister_cpu_notifier(&setup_hotplug_notifier); pseries_idle_devices_uninit(); cpuidle_unregister_driver(&pseries_idle_driver); diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 7b3bf76..39f71fb 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -432,7 +432,7 @@ static int do_update_property(char *buf, size_t bufsize) unsigned char *value; char *name, *end, *next_prop; int rc, length; - struct property *newprop, *oldprop; + struct property *newprop; buf = parse_node(buf, bufsize, &np); end = buf + bufsize; @@ -443,6 +443,9 @@ static int do_update_property(char *buf, size_t bufsize) if (!next_prop) return -EINVAL; + if (!strlen(name)) + return -ENODEV; + newprop = new_property(name, length, value, NULL); if (!newprop) return -ENOMEM; @@ -450,18 +453,11 @@ static int do_update_property(char *buf, size_t bufsize) if (!strcmp(name, "slb-size") || !strcmp(name, "ibm,slb-size")) slb_set_size(*(int *)value); - oldprop = of_find_property(np, name,NULL); - if (!oldprop) { - if (strlen(name)) - return prom_add_property(np, newprop); - return -ENODEV; - } - upd_value.node = np; upd_value.property = newprop; pSeries_reconfig_notify(PSERIES_UPDATE_PROPERTY, &upd_value); - rc = prom_update_property(np, newprop, oldprop); + rc = prom_update_property(np, newprop); if (rc) return rc; @@ -486,7 +482,7 @@ static int do_update_property(char *buf, size_t bufsize) rc = pSeries_reconfig_notify(action, value); if (rc) { - prom_update_property(np, oldprop, newprop); + prom_update_property(np, newprop); return rc; } } diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index e16bb8d..71706bc 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -147,7 +147,6 @@ static void __devinit smp_xics_setup_cpu(int cpu) set_cpu_current_state(cpu, CPU_STATE_ONLINE); set_default_offline_state(cpu); #endif - pseries_notify_cpuidle_add_cpu(cpu); } static int __devinit smp_pSeries_kick_cpu(int nr) diff --git a/arch/powerpc/sysdev/6xx-suspend.S b/arch/powerpc/sysdev/6xx-suspend.S index 21cda085d..cf48e9c 100644 --- a/arch/powerpc/sysdev/6xx-suspend.S +++ b/arch/powerpc/sysdev/6xx-suspend.S @@ -29,7 +29,7 @@ _GLOBAL(mpc6xx_enter_standby) ori r5, r5, ret_from_standby@l mtlr r5 - rlwinm r5, r1, 0, 0, 31-THREAD_SHIFT + CURRENT_THREAD_INFO(r5, r1) lwz r6, TI_LOCAL_FLAGS(r5) ori r6, r6, _TLF_SLEEPING stw r6, TI_LOCAL_FLAGS(r5) diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 6073288..a7b2a60 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -1,7 +1,7 @@ /* * MPC83xx/85xx/86xx PCI/PCIE support routing. * - * Copyright 2007-2011 Freescale Semiconductor, Inc. + * Copyright 2007-2012 Freescale Semiconductor, Inc. * Copyright 2008-2009 MontaVista Software, Inc. * * Initial author: Xianghua Xiao <x.xiao@freescale.com> @@ -36,7 +36,7 @@ static int fsl_pcie_bus_fixup, is_mpc83xx_pci; -static void __init quirk_fsl_pcie_header(struct pci_dev *dev) +static void __devinit quirk_fsl_pcie_header(struct pci_dev *dev) { u8 progif; @@ -807,3 +807,72 @@ u64 fsl_pci_immrbar_base(struct pci_controller *hose) return 0; } + +#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx) +static const struct of_device_id pci_ids[] = { + { .compatible = "fsl,mpc8540-pci", }, + { .compatible = "fsl,mpc8548-pcie", }, + { .compatible = "fsl,mpc8610-pci", }, + { .compatible = "fsl,mpc8641-pcie", }, + { .compatible = "fsl,p1022-pcie", }, + { .compatible = "fsl,p1010-pcie", }, + { .compatible = "fsl,p1023-pcie", }, + { .compatible = "fsl,p4080-pcie", }, + { .compatible = "fsl,qoriq-pcie-v2.3", }, + { .compatible = "fsl,qoriq-pcie-v2.2", }, + {}, +}; + +struct device_node *fsl_pci_primary; + +void __devinit fsl_pci_init(void) +{ + struct device_node *node; + struct pci_controller *hose; + dma_addr_t max = 0xffffffff; + + /* Callers can specify the primary bus using other means. */ + if (!fsl_pci_primary) { + /* If a PCI host bridge contains an ISA node, it's primary. */ + node = of_find_node_by_type(NULL, "isa"); + while ((fsl_pci_primary = of_get_parent(node))) { + of_node_put(node); + node = fsl_pci_primary; + + if (of_match_node(pci_ids, node)) + break; + } + } + + node = NULL; + for_each_node_by_type(node, "pci") { + if (of_match_node(pci_ids, node)) { + /* + * If there's no PCI host bridge with ISA, arbitrarily + * designate one as primary. This can go away once + * various bugs with primary-less systems are fixed. + */ + if (!fsl_pci_primary) + fsl_pci_primary = node; + + fsl_add_bridge(node, fsl_pci_primary == node); + hose = pci_find_hose_for_OF_device(node); + max = min(max, hose->dma_window_base_cur + + hose->dma_window_size); + } + } + +#ifdef CONFIG_SWIOTLB + /* + * if we couldn't map all of DRAM via the dma windows + * we need SWIOTLB to handle buffers located outside of + * dma capable memory region + */ + if (memblock_end_of_DRAM() - 1 > max) { + ppc_swiotlb_enable = 1; + set_pci_dma_ops(&swiotlb_dma_ops); + ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; + } +#endif +} +#endif diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h index a39ed5c..baa0fd1 100644 --- a/arch/powerpc/sysdev/fsl_pci.h +++ b/arch/powerpc/sysdev/fsl_pci.h @@ -93,5 +93,13 @@ extern void fsl_pcibios_fixup_bus(struct pci_bus *bus); extern int mpc83xx_add_bridge(struct device_node *dev); u64 fsl_pci_immrbar_base(struct pci_controller *hose); +extern struct device_node *fsl_pci_primary; + +#ifdef CONFIG_FSL_PCI +void fsl_pci_init(void); +#else +static inline void fsl_pci_init(void) {} +#endif + #endif /* __POWERPC_FSL_PCI_H */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 395af13..bfc6211 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1211,7 +1211,7 @@ struct mpic * __init mpic_alloc(struct device_node *node, if (of_get_property(node, "single-cpu-affinity", NULL)) flags |= MPIC_SINGLE_DEST_CPU; if (of_device_is_compatible(node, "fsl,mpic")) - flags |= MPIC_FSL; + flags |= MPIC_FSL | MPIC_LARGE_VECTORS; mpic = kzalloc(sizeof(struct mpic), GFP_KERNEL); if (mpic == NULL) @@ -1376,7 +1376,7 @@ struct mpic * __init mpic_alloc(struct device_node *node, mpic->isu_mask = (1 << mpic->isu_shift) - 1; mpic->irqhost = irq_domain_add_linear(mpic->node, - last_irq + 1, + intvec_top, &mpic_host_ops, mpic); /* diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c index b0037ce..364b14d 100644 --- a/arch/powerpc/sysdev/mv64x60_pci.c +++ b/arch/powerpc/sysdev/mv64x60_pci.c @@ -104,7 +104,7 @@ subsys_initcall(mv64x60_sysfs_init); #endif /* CONFIG_SYSFS */ -static void __init mv64x60_pci_fixup_early(struct pci_dev *dev) +static void __devinit mv64x60_pci_fixup_early(struct pci_dev *dev) { /* * Set the host bridge hdr_type to an invalid value so that diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 818e763..b043675 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -395,6 +395,9 @@ static void qe_upload_microcode(const void *base, for (i = 0; i < be32_to_cpu(ucode->count); i++) out_be32(&qe_immr->iram.idata, be32_to_cpu(code[i])); + + /* Set I-RAM Ready Register */ + out_be32(&qe_immr->iram.iready, be32_to_cpu(QE_IRAM_READY)); } /* diff --git a/arch/s390/appldata/appldata.h b/arch/s390/appldata/appldata.h index f0b23fc..4a67f2b 100644 --- a/arch/s390/appldata/appldata.h +++ b/arch/s390/appldata/appldata.h @@ -1,6 +1,4 @@ /* - * arch/s390/appldata/appldata.h - * * Definitions and interface for Linux - z/VM Monitor Stream. * * Copyright IBM Corp. 2003, 2008 diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 24bff4f..bae0f40 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -1,6 +1,4 @@ /* - * arch/s390/appldata/appldata_base.c - * * Base infrastructure for Linux-z/VM Monitor Stream, Stage 1. * Exports appldata_register_ops() and appldata_unregister_ops() for the * data gathering modules. @@ -29,7 +27,7 @@ #include <linux/suspend.h> #include <linux/platform_device.h> #include <asm/appldata.h> -#include <asm/timer.h> +#include <asm/vtimer.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/smp.h> @@ -84,8 +82,7 @@ static struct ctl_table appldata_dir_table[] = { /* * Timer */ -static DEFINE_PER_CPU(struct vtimer_list, appldata_timer); -static atomic_t appldata_expire_count = ATOMIC_INIT(0); +static struct vtimer_list appldata_timer; static DEFINE_SPINLOCK(appldata_timer_lock); static int appldata_interval = APPLDATA_CPU_INTERVAL; @@ -115,10 +112,7 @@ static LIST_HEAD(appldata_ops_list); */ static void appldata_timer_function(unsigned long data) { - if (atomic_dec_and_test(&appldata_expire_count)) { - atomic_set(&appldata_expire_count, num_online_cpus()); - queue_work(appldata_wq, (struct work_struct *) data); - } + queue_work(appldata_wq, (struct work_struct *) data); } /* @@ -131,7 +125,6 @@ static void appldata_work_fn(struct work_struct *work) struct list_head *lh; struct appldata_ops *ops; - get_online_cpus(); mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { ops = list_entry(lh, struct appldata_ops, list); @@ -140,7 +133,6 @@ static void appldata_work_fn(struct work_struct *work) } } mutex_unlock(&appldata_ops_mutex); - put_online_cpus(); } /* @@ -168,20 +160,6 @@ int appldata_diag(char record_nr, u16 function, unsigned long buffer, /****************************** /proc stuff **********************************/ -/* - * appldata_mod_vtimer_wrap() - * - * wrapper function for mod_virt_timer(), because smp_call_function_single() - * accepts only one parameter. - */ -static void __appldata_mod_vtimer_wrap(void *p) { - struct { - struct vtimer_list *timer; - u64 expires; - } *args = p; - mod_virt_timer_periodic(args->timer, args->expires); -} - #define APPLDATA_ADD_TIMER 0 #define APPLDATA_DEL_TIMER 1 #define APPLDATA_MOD_TIMER 2 @@ -192,49 +170,28 @@ static void __appldata_mod_vtimer_wrap(void *p) { * Add, delete or modify virtual timers on all online cpus. * The caller needs to get the appldata_timer_lock spinlock. */ -static void -__appldata_vtimer_setup(int cmd) +static void __appldata_vtimer_setup(int cmd) { - u64 per_cpu_interval; - int i; + u64 timer_interval = (u64) appldata_interval * 1000 * TOD_MICRO; switch (cmd) { case APPLDATA_ADD_TIMER: if (appldata_timer_active) break; - per_cpu_interval = (u64) (appldata_interval*1000 / - num_online_cpus()) * TOD_MICRO; - for_each_online_cpu(i) { - per_cpu(appldata_timer, i).expires = per_cpu_interval; - smp_call_function_single(i, add_virt_timer_periodic, - &per_cpu(appldata_timer, i), - 1); - } + appldata_timer.expires = timer_interval; + add_virt_timer_periodic(&appldata_timer); appldata_timer_active = 1; break; case APPLDATA_DEL_TIMER: - for_each_online_cpu(i) - del_virt_timer(&per_cpu(appldata_timer, i)); + del_virt_timer(&appldata_timer); if (!appldata_timer_active) break; appldata_timer_active = 0; - atomic_set(&appldata_expire_count, num_online_cpus()); break; case APPLDATA_MOD_TIMER: - per_cpu_interval = (u64) (appldata_interval*1000 / - num_online_cpus()) * TOD_MICRO; if (!appldata_timer_active) break; - for_each_online_cpu(i) { - struct { - struct vtimer_list *timer; - u64 expires; - } args; - args.timer = &per_cpu(appldata_timer, i); - args.expires = per_cpu_interval; - smp_call_function_single(i, __appldata_mod_vtimer_wrap, - &args, 1); - } + mod_virt_timer_periodic(&appldata_timer, timer_interval); } } @@ -265,14 +222,12 @@ appldata_timer_handler(ctl_table *ctl, int write, len = *lenp; if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) return -EFAULT; - get_online_cpus(); spin_lock(&appldata_timer_lock); if (buf[0] == '1') __appldata_vtimer_setup(APPLDATA_ADD_TIMER); else if (buf[0] == '0') __appldata_vtimer_setup(APPLDATA_DEL_TIMER); spin_unlock(&appldata_timer_lock); - put_online_cpus(); out: *lenp = len; *ppos += len; @@ -305,20 +260,17 @@ appldata_interval_handler(ctl_table *ctl, int write, goto out; } len = *lenp; - if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) { + if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) return -EFAULT; - } interval = 0; sscanf(buf, "%i", &interval); if (interval <= 0) return -EINVAL; - get_online_cpus(); spin_lock(&appldata_timer_lock); appldata_interval = interval; __appldata_vtimer_setup(APPLDATA_MOD_TIMER); spin_unlock(&appldata_timer_lock); - put_online_cpus(); out: *lenp = len; *ppos += len; @@ -485,14 +437,12 @@ static int appldata_freeze(struct device *dev) int rc; struct list_head *lh; - get_online_cpus(); spin_lock(&appldata_timer_lock); if (appldata_timer_active) { __appldata_vtimer_setup(APPLDATA_DEL_TIMER); appldata_timer_suspended = 1; } spin_unlock(&appldata_timer_lock); - put_online_cpus(); mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { @@ -516,14 +466,12 @@ static int appldata_restore(struct device *dev) int rc; struct list_head *lh; - get_online_cpus(); spin_lock(&appldata_timer_lock); if (appldata_timer_suspended) { __appldata_vtimer_setup(APPLDATA_ADD_TIMER); appldata_timer_suspended = 0; } spin_unlock(&appldata_timer_lock); - put_online_cpus(); mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { @@ -567,53 +515,6 @@ static struct platform_driver appldata_pdrv = { /******************************* init / exit *********************************/ -static void __cpuinit appldata_online_cpu(int cpu) -{ - init_virt_timer(&per_cpu(appldata_timer, cpu)); - per_cpu(appldata_timer, cpu).function = appldata_timer_function; - per_cpu(appldata_timer, cpu).data = (unsigned long) - &appldata_work; - atomic_inc(&appldata_expire_count); - spin_lock(&appldata_timer_lock); - __appldata_vtimer_setup(APPLDATA_MOD_TIMER); - spin_unlock(&appldata_timer_lock); -} - -static void __cpuinit appldata_offline_cpu(int cpu) -{ - del_virt_timer(&per_cpu(appldata_timer, cpu)); - if (atomic_dec_and_test(&appldata_expire_count)) { - atomic_set(&appldata_expire_count, num_online_cpus()); - queue_work(appldata_wq, &appldata_work); - } - spin_lock(&appldata_timer_lock); - __appldata_vtimer_setup(APPLDATA_MOD_TIMER); - spin_unlock(&appldata_timer_lock); -} - -static int __cpuinit appldata_cpu_notify(struct notifier_block *self, - unsigned long action, - void *hcpu) -{ - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - appldata_online_cpu((long) hcpu); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - appldata_offline_cpu((long) hcpu); - break; - default: - break; - } - return NOTIFY_OK; -} - -static struct notifier_block __cpuinitdata appldata_nb = { - .notifier_call = appldata_cpu_notify, -}; - /* * appldata_init() * @@ -621,7 +522,10 @@ static struct notifier_block __cpuinitdata appldata_nb = { */ static int __init appldata_init(void) { - int i, rc; + int rc; + + appldata_timer.function = appldata_timer_function; + appldata_timer.data = (unsigned long) &appldata_work; rc = platform_driver_register(&appldata_pdrv); if (rc) @@ -639,14 +543,6 @@ static int __init appldata_init(void) goto out_device; } - get_online_cpus(); - for_each_online_cpu(i) - appldata_online_cpu(i); - put_online_cpus(); - - /* Register cpu hotplug notifier */ - register_hotcpu_notifier(&appldata_nb); - appldata_sysctl_header = register_sysctl_table(appldata_dir_table); return 0; diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c index f7d3dc5..02d9a1c 100644 --- a/arch/s390/appldata/appldata_mem.c +++ b/arch/s390/appldata/appldata_mem.c @@ -1,10 +1,8 @@ /* - * arch/s390/appldata/appldata_mem.c - * * Data gathering module for Linux-VM Monitor Stream, Stage 1. * Collects data related to memory management. * - * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2003, 2006 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/appldata/appldata_net_sum.c b/arch/s390/appldata/appldata_net_sum.c index 5da7c56..1370e35 100644 --- a/arch/s390/appldata/appldata_net_sum.c +++ b/arch/s390/appldata/appldata_net_sum.c @@ -1,11 +1,9 @@ /* - * arch/s390/appldata/appldata_net_sum.c - * * Data gathering module for Linux-VM Monitor Stream, Stage 1. * Collects accumulated network statistics (Packets received/transmitted, * dropped, errors, ...). * - * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2003, 2006 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 4de031d6..87521ba 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -1,10 +1,8 @@ /* - * arch/s390/appldata/appldata_os.c - * * Data gathering module for Linux-VM Monitor Stream, Stage 1. * Collects misc. OS related data (CPU utilization, running processes). * - * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2003, 2006 * * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index a9ce135..e402a9d 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -4,7 +4,7 @@ * s390 implementation of the AES Cipher Algorithm. * * s390 Version: - * Copyright IBM Corp. 2005,2007 + * Copyright IBM Corp. 2005, 2007 * Author(s): Jan Glauber (jang@de.ibm.com) * Sebastian Siewior (sebastian@breakpoint.cc> SW-Fallback * diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h index 9178db6..6c5cc6d 100644 --- a/arch/s390/crypto/crypt_s390.h +++ b/arch/s390/crypto/crypt_s390.h @@ -3,7 +3,7 @@ * * Support for s390 cryptographic instructions. * - * Copyright IBM Corp. 2003,2007 + * Copyright IBM Corp. 2003, 2007 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) * diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index a52bfd1..1eaa371 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -3,7 +3,7 @@ * * s390 implementation of the DES Cipher Algorithm. * - * Copyright IBM Corp. 2003,2011 + * Copyright IBM Corp. 2003, 2011 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) * diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index 0808fbf..94a35a4 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2006,2007 + * Copyright IBM Corp. 2006, 2007 * Author(s): Jan Glauber <jan.glauber@de.ibm.com> * Driver for the s390 pseudo random number generator */ diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index e9868c6..a1b3a9d 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -8,7 +8,7 @@ * implementation written by Steve Reid. * * s390 Version: - * Copyright IBM Corp. 2003,2007 + * Copyright IBM Corp. 2003, 2007 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) * diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 0317a35..9b85380 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -4,7 +4,7 @@ * s390 implementation of the SHA256 and SHA224 Secure Hash Algorithm. * * s390 Version: - * Copyright IBM Corp. 2005,2011 + * Copyright IBM Corp. 2005, 2011 * Author(s): Jan Glauber (jang@de.ibm.com) * * This program is free software; you can redistribute it and/or modify it diff --git a/arch/s390/hypfs/hypfs.h b/arch/s390/hypfs/hypfs.h index d9df5a0..f41e0ef 100644 --- a/arch/s390/hypfs/hypfs.h +++ b/arch/s390/hypfs/hypfs.h @@ -1,8 +1,7 @@ /* - * arch/s390/hypfs/hypfs.h * Hypervisor filesystem for Linux on s390. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Michael Holzheu <holzheu@de.ibm.com> */ diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index b478013..13e76da 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -1,7 +1,7 @@ /* * Hypervisor filesystem for Linux on s390 - debugfs interface * - * Copyright (C) IBM Corp. 2010 + * Copyright IBM Corp. 2010 * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> */ diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 74c8f5e..7fd3690 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -1,5 +1,4 @@ /* - * arch/s390/hypfs/hypfs_diag.c * Hypervisor filesystem for Linux on s390. Diag 204 and 224 * implementation. * diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index e547960..4f6afaa 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -1,7 +1,7 @@ /* * Hypervisor filesystem for Linux on s390. z/VM implementation. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Michael Holzheu <holzheu@de.ibm.com> */ diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 73dae8b..6767b43 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -1,5 +1,4 @@ /* - * arch/s390/hypfs/inode.c * Hypervisor filesystem for Linux on s390. * * Copyright IBM Corp. 2006, 2008 @@ -103,6 +102,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode) if (ret) { struct hypfs_sb_info *hypfs_info = sb->s_fs_info; + ret->i_ino = get_next_ino(); ret->i_mode = mode; ret->i_uid = hypfs_info->uid; ret->i_gid = hypfs_info->gid; diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 1ac80d6..9819891 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/airq.h - * - * Copyright IBM Corp. 2002,2007 + * Copyright IBM Corp. 2002, 2007 * Author(s): Ingo Adlung <adlung@de.ibm.com> * Cornelia Huck <cornelia.huck@de.ibm.com> * Arnd Bergmann <arndb@de.ibm.com> diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h index 79283da..f328294 100644 --- a/arch/s390/include/asm/appldata.h +++ b/arch/s390/include/asm/appldata.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/appldata.h - * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * * Author(s): Melissa Howland <melissah@us.ibm.com> */ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 748347b..c797832 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -1,8 +1,5 @@ -#ifndef __ARCH_S390_ATOMIC__ -#define __ARCH_S390_ATOMIC__ - /* - * Copyright 1999,2009 IBM Corp. + * Copyright IBM Corp. 1999, 2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Denis Joseph Barrow, * Arnd Bergmann <arndb@de.ibm.com>, @@ -13,6 +10,9 @@ * */ +#ifndef __ARCH_S390_ATOMIC__ +#define __ARCH_S390_ATOMIC__ + #include <linux/compiler.h> #include <linux/types.h> #include <asm/cmpxchg.h> diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index a6ff5a8..6f57389 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -1,11 +1,6 @@ -#ifndef _S390_BITOPS_H -#define _S390_BITOPS_H - /* - * include/asm-s390/bitops.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/bitops.h" @@ -13,6 +8,9 @@ * */ +#ifndef _S390_BITOPS_H +#define _S390_BITOPS_H + #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif diff --git a/arch/s390/include/asm/bugs.h b/arch/s390/include/asm/bugs.h index 011f1e6..0f5bd89 100644 --- a/arch/s390/include/asm/bugs.h +++ b/arch/s390/include/asm/bugs.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/bugs.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/bugs.h" diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h index 2a30d5a..4d7ccac 100644 --- a/arch/s390/include/asm/cache.h +++ b/arch/s390/include/asm/cache.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/cache.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * * Derived from "include/asm-i386/cache.h" * Copyright (C) 1992, Linus Torvalds diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index 9381c92..1cb4bb3 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2002, 2009 + * Copyright IBM Corp. 2002, 2009 * * Author(s): Arnd Bergmann <arndb@de.ibm.com> * diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index f2ef34f..01a905e 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -6,14 +6,12 @@ struct ccw_driver; /** * struct ccwgroup_device - ccw group device - * @creator_id: unique number of the driver * @state: online/offline state * @count: number of attached slave devices * @dev: embedded device structure * @cdev: variable number of slave devices, allocated as needed */ struct ccwgroup_device { - unsigned long creator_id; enum { CCWGROUP_OFFLINE, CCWGROUP_ONLINE, diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 6c00f68..4f57a4f 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -1,18 +1,16 @@ -#ifndef _S390_CHECKSUM_H -#define _S390_CHECKSUM_H - /* - * include/asm-s390/checksum.h * S390 fast network checksum routines - * see also arch/S390/lib/checksum.c * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Ulrich Hild (first version) * Martin Schwidefsky (heavily optimized CKSM version) * D.J. Barrow (third attempt) */ +#ifndef _S390_CHECKSUM_H +#define _S390_CHECKSUM_H + #include <asm/uaccess.h> /* diff --git a/arch/s390/include/asm/chpid.h b/arch/s390/include/asm/chpid.h index 8e88e22..e5bde9f 100644 --- a/arch/s390/include/asm/chpid.h +++ b/arch/s390/include/asm/chpid.h @@ -1,6 +1,4 @@ /* - * drivers/s390/cio/chpid.h - * * Copyright IBM Corp. 2007 * Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com> */ diff --git a/arch/s390/include/asm/chsc.h b/arch/s390/include/asm/chsc.h index 4943654..bf115b4 100644 --- a/arch/s390/include/asm/chsc.h +++ b/arch/s390/include/asm/chsc.h @@ -1,7 +1,7 @@ /* * ioctl interface for /dev/chsc * - * Copyright 2008 IBM Corp. + * Copyright IBM Corp. 2008 * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> */ diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index 4c8d4d5..77043aa 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -1,7 +1,4 @@ /* - * include/asm-s390/cio.h - * include/asm-s390x/cio.h - * * Common interface for I/O on S/390 */ #ifndef _ASM_S390_CIO_H_ diff --git a/arch/s390/include/asm/cpcmd.h b/arch/s390/include/asm/cpcmd.h index 48a9eab..3dfadb5 100644 --- a/arch/s390/include/asm/cpcmd.h +++ b/arch/s390/include/asm/cpcmd.h @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/cpcmd.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Christian Borntraeger (cborntra@de.ibm.com), */ diff --git a/arch/s390/include/asm/cpu.h b/arch/s390/include/asm/cpu.h index e0b6954..f5a8e2f 100644 --- a/arch/s390/include/asm/cpu.h +++ b/arch/s390/include/asm/cpu.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Hartmut Penner <hp@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Christian Ehrhardt <ehrhardt@de.ibm.com>, diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 718374d..8709bde 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/cputime.h - * - * (C) Copyright IBM Corp. 2004 + * Copyright IBM Corp. 2004 * * Author: Martin Schwidefsky <schwidefsky@de.ibm.com> */ @@ -167,12 +165,14 @@ static inline clock_t cputime64_to_clock_t(cputime64_t cputime) } struct s390_idle_data { + int nohz_delay; unsigned int sequence; unsigned long long idle_count; - unsigned long long idle_enter; - unsigned long long idle_exit; unsigned long long idle_time; - int nohz_delay; + unsigned long long clock_idle_enter; + unsigned long long clock_idle_exit; + unsigned long long timer_idle_enter; + unsigned long long timer_idle_exit; }; DECLARE_PER_CPU(struct s390_idle_data, s390_idle); diff --git a/arch/s390/include/asm/crw.h b/arch/s390/include/asm/crw.h index 749a97e..7c31d3e 100644 --- a/arch/s390/include/asm/crw.h +++ b/arch/s390/include/asm/crw.h @@ -1,6 +1,6 @@ /* * Data definitions for channel report processing - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Ingo Adlung <adlung@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Cornelia Huck <cornelia.huck@de.ibm.com>, diff --git a/arch/s390/include/asm/current.h b/arch/s390/include/asm/current.h index 7a68084..b80941f 100644 --- a/arch/s390/include/asm/current.h +++ b/arch/s390/include/asm/current.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/current.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/current.h" diff --git a/arch/s390/include/asm/dasd.h b/arch/s390/include/asm/dasd.h index 0be28ef..38eca3b 100644 --- a/arch/s390/include/asm/dasd.h +++ b/arch/s390/include/asm/dasd.h @@ -1,8 +1,7 @@ /* - * File...........: linux/drivers/s390/block/dasd.c * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 1999,2000 + * Copyright IBM Corp. 1999, 2000 * EMC Symmetrix ioctl Copyright EMC Corporation, 2008 * Author.........: Nigel Hislop <hislop_nigel@emc.com> * diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 8a8245e..f39677e 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -1,9 +1,7 @@ /* - * include/asm-s390/debug.h * S/390 debug facility * - * Copyright (C) 1999, 2000 IBM Deutschland Entwicklung GmbH, - * IBM Corporation + * Copyright IBM Corp. 1999, 2000 */ #ifndef DEBUG_H diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h index 0e3b35f..3f6e409 100644 --- a/arch/s390/include/asm/delay.h +++ b/arch/s390/include/asm/delay.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/delay.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/delay.h" diff --git a/arch/s390/include/asm/dma.h b/arch/s390/include/asm/dma.h index 7425c6a..6fb6de4 100644 --- a/arch/s390/include/asm/dma.h +++ b/arch/s390/include/asm/dma.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/dma.h - * * S390 version */ diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h index 7f6f641..c5befc5 100644 --- a/arch/s390/include/asm/ebcdic.h +++ b/arch/s390/include/asm/ebcdic.h @@ -1,9 +1,8 @@ /* - * include/asm-s390/ebcdic.h * EBCDIC -> ASCII, ASCII -> EBCDIC conversion routines. * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 06151e6..32e8449 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/elf.h - * * S390 version * * Derived from "include/asm-i386/elf.h" diff --git a/arch/s390/include/asm/errno.h b/arch/s390/include/asm/errno.h index e41d5b3..395e97d 100644 --- a/arch/s390/include/asm/errno.h +++ b/arch/s390/include/asm/errno.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/errno.h - * * S390 version * */ diff --git a/arch/s390/include/asm/etr.h b/arch/s390/include/asm/etr.h index 538e1b3..a24b03b 100644 --- a/arch/s390/include/asm/etr.h +++ b/arch/s390/include/asm/etr.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/etr.h - * * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/extmem.h b/arch/s390/include/asm/extmem.h index 33837d7..6276002 100644 --- a/arch/s390/include/asm/extmem.h +++ b/arch/s390/include/asm/extmem.h @@ -1,8 +1,6 @@ /* - * include/asm-s390x/extmem.h - * * definitions for external memory segment support - * Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2003 */ #ifndef _ASM_S390X_DCSS_H diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index 510ba9e..0c82ba8 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/hardirq.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * diff --git a/arch/s390/include/asm/idals.h b/arch/s390/include/asm/idals.h index aef0dde..ea5a6e4 100644 --- a/arch/s390/include/asm/idals.h +++ b/arch/s390/include/asm/idals.h @@ -1,10 +1,9 @@ /* - * File...........: linux/include/asm-s390x/idals.h * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 2000a - + * Copyright IBM Corp. 2000 + * * History of changes * 07/24/00 new file * 05/04/02 code restructuring. diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index f81a097..559e921 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/io.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/io.h" diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h index 38fdf45..37b9091 100644 --- a/arch/s390/include/asm/irqflags.h +++ b/arch/s390/include/asm/irqflags.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2006,2010 + * Copyright IBM Corp. 2006, 2010 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index f4f3882..694bcd6 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/kexec.h - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Rolf Adelsberger <adelsberger@de.ibm.com> * diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index a231a94..dcf6948 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -17,7 +17,7 @@ * 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) IBM Corporation, 2002, 2006 + * Copyright IBM Corp. 2002, 2006 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation ( includes suggestions from diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index bdcbe0f..d25da59 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -1,7 +1,7 @@ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H /* - * asm-s390/kvm.h - KVM s390 specific structures and definitions + * KVM s390 specific structures and definitions * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index dd17537..b784154 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1,7 +1,7 @@ /* - * asm-s390/kvm_host.h - definition for kernel virtual machines on s390 + * definition for kernel virtual machines on s390 * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/include/asm/kvm_para.h b/arch/s390/include/asm/kvm_para.h index a988329..da44867 100644 --- a/arch/s390/include/asm/kvm_para.h +++ b/arch/s390/include/asm/kvm_para.h @@ -1,5 +1,5 @@ /* - * asm-s390/kvm_para.h - definition for paravirtual devices on s390 + * definition for paravirtual devices on s390 * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/include/asm/kvm_virtio.h b/arch/s390/include/asm/kvm_virtio.h index 72f6141..44a438c 100644 --- a/arch/s390/include/asm/kvm_virtio.h +++ b/arch/s390/include/asm/kvm_virtio.h @@ -1,5 +1,5 @@ /* - * kvm_virtio.h - definition for virtio for kvm on s390 + * definition for virtio for kvm on s390 * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 47853de..aab5555 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Hartmut Penner <hp@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Denis Joseph Barrow, @@ -302,12 +302,7 @@ struct _lowcore { */ __u64 ipib; /* 0x0e00 */ __u32 ipib_checksum; /* 0x0e08 */ - /* - * Because the vmcore_info pointer is not 8 byte aligned it never - * should not be accessed directly. For accessing the pointer, first - * copy it to a local pointer variable. - */ - __u8 vmcore_info[8]; /* 0x0e0c */ + __u64 vmcore_info; /* 0x0e0c */ __u8 pad_0x0e14[0x0e18-0x0e14]; /* 0x0e14 */ __u64 os_info; /* 0x0e18 */ __u8 pad_0x0e20[0x0f00-0x0e20]; /* 0x0e20 */ diff --git a/arch/s390/include/asm/mathemu.h b/arch/s390/include/asm/mathemu.h index e8dd1ba..614dfaf 100644 --- a/arch/s390/include/asm/mathemu.h +++ b/arch/s390/include/asm/mathemu.h @@ -1,9 +1,8 @@ /* - * arch/s390/kernel/mathemu.h * IEEE floating point emulation. * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/mman.h b/arch/s390/include/asm/mman.h index d49760e..abc1932 100644 --- a/arch/s390/include/asm/mman.h +++ b/arch/s390/include/asm/mman.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/mman.h - * * S390 version * * Derived from "include/asm-i386/mman.h" diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 69bdf72..5c63615 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/mmu_context.h - * * S390 version * * Derived from "include/asm-i386/mmu_context.h" diff --git a/arch/s390/include/asm/monwriter.h b/arch/s390/include/asm/monwriter.h index f0cbf96..f845c8e 100644 --- a/arch/s390/include/asm/monwriter.h +++ b/arch/s390/include/asm/monwriter.h @@ -1,7 +1,5 @@ /* - * include/asm-s390/monwriter.h - * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Character device driver for writing z/VM APPLDATA monitor records * Version 1.0 * Author(s): Melissa Howland <melissah@us.ibm.com> diff --git a/arch/s390/include/asm/nmi.h b/arch/s390/include/asm/nmi.h index f4b6044..35f8ec1 100644 --- a/arch/s390/include/asm/nmi.h +++ b/arch/s390/include/asm/nmi.h @@ -1,7 +1,7 @@ /* * Machine check handler definitions * - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Ingo Adlung <adlung@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Cornelia Huck <cornelia.huck@de.ibm.com>, diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index f7ec548..27ab3c7 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/page.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com) */ diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 43078c1..590c321 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/pgalloc.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com) * Martin Schwidefsky (schwidefsky@de.ibm.com) * diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b322741..6bd7d74 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/pgtable.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com) * Ulrich Weigand (weigand@de.ibm.com) * Martin Schwidefsky (schwidefsky@de.ibm.com) diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h index 7be104c..7bcc14e 100644 --- a/arch/s390/include/asm/posix_types.h +++ b/arch/s390/include/asm/posix_types.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/posix_types.h - * * S390 version * */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 20d0585..c40fa91 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/processor.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com), * Martin Schwidefsky (schwidefsky@de.ibm.com) * @@ -348,4 +346,14 @@ extern void (*s390_base_ext_handler_fn)(void); ".previous\n" #endif +extern int memcpy_real(void *, void *, size_t); +extern void memcpy_absolute(void *, void *, size_t); + +#define mem_assign_absolute(dest, val) { \ + __typeof__(dest) __tmp = (val); \ + \ + BUILD_BUG_ON(sizeof(__tmp) != sizeof(val)); \ + memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ +} + #endif /* __ASM_S390_PROCESSOR_H */ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index aeb77f0..d5f08ea 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/ptrace.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) */ diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index f039d86..57d0d7e 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -1,7 +1,5 @@ /* - * linux/include/asm-s390/qdio.h - * - * Copyright 2000,2008 IBM Corp. + * Copyright IBM Corp. 2000, 2008 * Author(s): Utz Bacher <utz.bacher@de.ibm.com> * Jan Glauber <jang@linux.vnet.ibm.com> * diff --git a/arch/s390/include/asm/qeth.h b/arch/s390/include/asm/qeth.h index 2c7c898..3a896cf 100644 --- a/arch/s390/include/asm/qeth.h +++ b/arch/s390/include/asm/qeth.h @@ -1,9 +1,7 @@ /* - * include/asm-s390/qeth.h - * * ioctl definitions for qeth driver * - * Copyright (C) 2004 IBM Corporation + * Copyright IBM Corp. 2004 * * Author(s): Thomas Spatzier <tspat@de.ibm.com> * diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h index 3d6ad4a..8045785 100644 --- a/arch/s390/include/asm/reset.h +++ b/arch/s390/include/asm/reset.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/reset.h - * * Copyright IBM Corp. 2006 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/include/asm/resource.h b/arch/s390/include/asm/resource.h index 366c01d..ec23d1c 100644 --- a/arch/s390/include/asm/resource.h +++ b/arch/s390/include/asm/resource.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/resource.h - * * S390 version * * Derived from "include/asm-i386/resources.h" diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h index 1ceee10..487f9b6 100644 --- a/arch/s390/include/asm/rwsem.h +++ b/arch/s390/include/asm/rwsem.h @@ -2,10 +2,8 @@ #define _S390_RWSEM_H /* - * include/asm-s390/rwsem.h - * * S390 version - * Copyright (C) 2002 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2002 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index bf238c5..e62a555 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/sclp.h - * * Copyright IBM Corp. 2007 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ @@ -55,5 +53,7 @@ int sclp_chp_configure(struct chp_id chpid); int sclp_chp_deconfigure(struct chp_id chpid); int sclp_chp_read_info(struct sclp_chp_info *info); void sclp_get_ipl_info(struct sclp_ipl_info *info); +bool sclp_has_linemode(void); +bool sclp_has_vt220(void); #endif /* _ASM_S390_SCLP_H */ diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h index de389cb..4071d00 100644 --- a/arch/s390/include/asm/scsw.h +++ b/arch/s390/include/asm/scsw.h @@ -1,7 +1,7 @@ /* * Helper functions for scsw access. * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com> */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 40eb2ff..57e8053 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/setup.h - * * S390 version - * Copyright IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 */ #ifndef _ASM_S390_SETUP_H diff --git a/arch/s390/include/asm/shmparam.h b/arch/s390/include/asm/shmparam.h index c2e0c05..e985182 100644 --- a/arch/s390/include/asm/shmparam.h +++ b/arch/s390/include/asm/shmparam.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/shmparam.h - * * S390 version * * Derived from "include/asm-i386/shmparam.h" diff --git a/arch/s390/include/asm/sigcontext.h b/arch/s390/include/asm/sigcontext.h index aeb6e0b..584787f 100644 --- a/arch/s390/include/asm/sigcontext.h +++ b/arch/s390/include/asm/sigcontext.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/sigcontext.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 */ #ifndef _ASM_S390_SIGCONTEXT_H diff --git a/arch/s390/include/asm/siginfo.h b/arch/s390/include/asm/siginfo.h index e0ff1ab..91fd3e4 100644 --- a/arch/s390/include/asm/siginfo.h +++ b/arch/s390/include/asm/siginfo.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/siginfo.h - * * S390 version * * Derived from "include/asm-i386/siginfo.h" diff --git a/arch/s390/include/asm/signal.h b/arch/s390/include/asm/signal.h index cdf5cb2..6d4d9d1 100644 --- a/arch/s390/include/asm/signal.h +++ b/arch/s390/include/asm/signal.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/signal.h - * * S390 version * * Derived from "include/asm-i386/signal.h" diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h new file mode 100644 index 0000000..5a87d16 --- /dev/null +++ b/arch/s390/include/asm/sigp.h @@ -0,0 +1,32 @@ +#ifndef __S390_ASM_SIGP_H +#define __S390_ASM_SIGP_H + +/* SIGP order codes */ +#define SIGP_SENSE 1 +#define SIGP_EXTERNAL_CALL 2 +#define SIGP_EMERGENCY_SIGNAL 3 +#define SIGP_STOP 5 +#define SIGP_RESTART 6 +#define SIGP_STOP_AND_STORE_STATUS 9 +#define SIGP_INITIAL_CPU_RESET 11 +#define SIGP_SET_PREFIX 13 +#define SIGP_STORE_STATUS_AT_ADDRESS 14 +#define SIGP_SET_ARCHITECTURE 18 +#define SIGP_SENSE_RUNNING 21 + +/* SIGP condition codes */ +#define SIGP_CC_ORDER_CODE_ACCEPTED 0 +#define SIGP_CC_STATUS_STORED 1 +#define SIGP_CC_BUSY 2 +#define SIGP_CC_NOT_OPERATIONAL 3 + +/* SIGP cpu status bits */ + +#define SIGP_STATUS_CHECK_STOP 0x00000010UL +#define SIGP_STATUS_STOPPED 0x00000040UL +#define SIGP_STATUS_EXT_CALL_PENDING 0x00000080UL +#define SIGP_STATUS_INVALID_PARAMETER 0x00000100UL +#define SIGP_STATUS_INCORRECT_STATE 0x00000200UL +#define SIGP_STATUS_NOT_RUNNING 0x00000400UL + +#endif /* __S390_ASM_SIGP_H */ diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 0b6f586..a0a8340 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Denis Joseph Barrow, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h index c91b720..69718cd 100644 --- a/arch/s390/include/asm/socket.h +++ b/arch/s390/include/asm/socket.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/socket.h - * * S390 version * * Derived from "include/asm-i386/socket.h" diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index fd94dfe..701fe8c 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/spinlock.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) * * Derived from "include/asm-i386/spinlock.h" diff --git a/arch/s390/include/asm/stat.h b/arch/s390/include/asm/stat.h index d92959e..b4ca97d 100644 --- a/arch/s390/include/asm/stat.h +++ b/arch/s390/include/asm/stat.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/stat.h - * * S390 version * * Derived from "include/asm-i386/stat.h" diff --git a/arch/s390/include/asm/statfs.h b/arch/s390/include/asm/statfs.h index 3be7fbd..5acca0a 100644 --- a/arch/s390/include/asm/statfs.h +++ b/arch/s390/include/asm/statfs.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/statfs.h - * * S390 version * * Derived from "include/asm-i386/statfs.h" diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 8cc160c..1bd1352 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/string.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), */ diff --git a/arch/s390/include/asm/swab.h b/arch/s390/include/asm/swab.h index a3e4ebb..da3bfe5 100644 --- a/arch/s390/include/asm/swab.h +++ b/arch/s390/include/asm/swab.h @@ -2,10 +2,8 @@ #define _S390_SWAB_H /* - * include/asm-s390/swab.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index 79d3d6e..282ee36 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -1,7 +1,7 @@ /* * definition for store system information stsi * - * Copyright IBM Corp. 2001,2008 + * Copyright IBM Corp. 2001, 2008 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/include/asm/tape390.h b/arch/s390/include/asm/tape390.h index 884fba4..b2bc4ba 100644 --- a/arch/s390/include/asm/tape390.h +++ b/arch/s390/include/asm/tape390.h @@ -1,10 +1,9 @@ /************************************************************************* * - * tape390.h * enables user programs to display messages and control encryption * on s390 tape devices * - * Copyright IBM Corp. 2001,2006 + * Copyright IBM Corp. 2001, 2006 * Author(s): Michael Holzheu <holzheu@de.ibm.com> * *************************************************************************/ diff --git a/arch/s390/include/asm/termios.h b/arch/s390/include/asm/termios.h index bc3a35c..cb9fe27 100644 --- a/arch/s390/include/asm/termios.h +++ b/arch/s390/include/asm/termios.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/termios.h - * * S390 version * * Derived from "include/asm-i386/termios.h" diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 4e40b25..bb08e2a 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/thread_info.h - * * S390 version - * Copyright (C) IBM Corp. 2002,2006 + * Copyright IBM Corp. 2002, 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/include/asm/timer.h b/arch/s390/include/asm/timer.h deleted file mode 100644 index 15d6479..0000000 --- a/arch/s390/include/asm/timer.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * include/asm-s390/timer.h - * - * (C) Copyright IBM Corp. 2003,2006 - * Virtual CPU timer - * - * Author: Jan Glauber (jang@de.ibm.com) - */ - -#ifndef _ASM_S390_TIMER_H -#define _ASM_S390_TIMER_H - -#include <linux/timer.h> - -#define VTIMER_MAX_SLICE (0x7ffffffffffff000LL) - -struct vtimer_list { - struct list_head entry; - - int cpu; - __u64 expires; - __u64 interval; - - void (*function)(unsigned long); - unsigned long data; -}; - -/* the vtimer value will wrap after ca. 71 years */ -struct vtimer_queue { - struct list_head list; - spinlock_t lock; - __u64 timer; /* last programmed timer */ - __u64 elapsed; /* elapsed time of timer expire values */ - __u64 idle_enter; /* cpu timer on idle enter */ - __u64 idle_exit; /* cpu timer on idle exit */ -}; - -extern void init_virt_timer(struct vtimer_list *timer); -extern void add_virt_timer(void *new); -extern void add_virt_timer_periodic(void *new); -extern int mod_virt_timer(struct vtimer_list *timer, __u64 expires); -extern int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires); -extern int del_virt_timer(struct vtimer_list *timer); - -extern void init_cpu_vtimer(void); -extern void vtime_init(void); - -extern void vtime_stop_cpu(void); -extern void vtime_start_leave(void); - -#endif /* _ASM_S390_TIMER_H */ diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 239ece9..fba4d66 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/timex.h - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * * Derived from "include/asm-i386/timex.h" * Copyright (C) 1992, Linus Torvalds diff --git a/arch/s390/include/asm/types.h b/arch/s390/include/asm/types.h index 6c8c35f..6ba7c2c 100644 --- a/arch/s390/include/asm/types.h +++ b/arch/s390/include/asm/types.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/types.h - * * S390 version * * Derived from "include/asm-i386/types.h" diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 1f3a79b..a8ab18b 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -1,8 +1,6 @@ /* - * include/asm-s390/uaccess.h - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Hartmut Penner (hp@de.ibm.com), * Martin Schwidefsky (schwidefsky@de.ibm.com) * @@ -381,8 +379,6 @@ clear_user(void __user *to, unsigned long n) return n; } -extern int memcpy_real(void *, void *, size_t); -extern void memcpy_absolute(void *, void *, size_t); extern int copy_to_user_real(void __user *dest, void *src, size_t count); extern int copy_from_user_real(void *dest, void __user *src, size_t count); diff --git a/arch/s390/include/asm/ucontext.h b/arch/s390/include/asm/ucontext.h index cfb874e..200e063 100644 --- a/arch/s390/include/asm/ucontext.h +++ b/arch/s390/include/asm/ucontext.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/ucontext.h - * * S390 version * * Derived from "include/asm-i386/ucontext.h" diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 8a8008f..2e37157 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/unistd.h - * * S390 version * * Derived from "include/asm-i386/unistd.h" diff --git a/arch/s390/include/asm/user.h b/arch/s390/include/asm/user.h index 1b050e3..6ed1d18 100644 --- a/arch/s390/include/asm/user.h +++ b/arch/s390/include/asm/user.h @@ -1,6 +1,4 @@ /* - * include/asm-s390/user.h - * * S390 version * * Derived from "include/asm-i386/usr.h" diff --git a/arch/s390/include/asm/vtimer.h b/arch/s390/include/asm/vtimer.h new file mode 100644 index 0000000..bfe25d5 --- /dev/null +++ b/arch/s390/include/asm/vtimer.h @@ -0,0 +1,33 @@ +/* + * Copyright IBM Corp. 2003, 2012 + * Virtual CPU timer + * + * Author(s): Jan Glauber <jan.glauber@de.ibm.com> + */ + +#ifndef _ASM_S390_TIMER_H +#define _ASM_S390_TIMER_H + +#define VTIMER_MAX_SLICE (0x7fffffffffffffffULL) + +struct vtimer_list { + struct list_head entry; + u64 expires; + u64 interval; + void (*function)(unsigned long); + unsigned long data; +}; + +extern void init_virt_timer(struct vtimer_list *timer); +extern void add_virt_timer(struct vtimer_list *timer); +extern void add_virt_timer_periodic(struct vtimer_list *timer); +extern int mod_virt_timer(struct vtimer_list *timer, u64 expires); +extern int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires); +extern int del_virt_timer(struct vtimer_list *timer); + +extern void init_cpu_vtimer(void); +extern void vtime_init(void); + +extern void vtime_stop_cpu(void); + +#endif /* _ASM_S390_TIMER_H */ diff --git a/arch/s390/include/asm/vtoc.h b/arch/s390/include/asm/vtoc.h index 8406a2b..221419d 100644 --- a/arch/s390/include/asm/vtoc.h +++ b/arch/s390/include/asm/vtoc.h @@ -1,9 +1,7 @@ /* - * include/asm-s390/vtoc.h - * * This file contains volume label definitions for DASD devices. * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Volker Sameske <sameske@de.ibm.com> * diff --git a/arch/s390/include/asm/zcrypt.h b/arch/s390/include/asm/zcrypt.h index 00d3bbd..e83fc11 100644 --- a/arch/s390/include/asm/zcrypt.h +++ b/arch/s390/include/asm/zcrypt.h @@ -3,7 +3,7 @@ * * zcrypt 2.1.0 (user-visible header) * - * Copyright (C) 2001, 2006 IBM Corporation + * Copyright IBM Corp. 2001, 2006 * Author(s): Robert Burroughs * Eric Rossman (edrossma@us.ibm.com) * diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 83e6edf..45ef1a7 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -9,7 +9,6 @@ #include <linux/kbuild.h> #include <linux/sched.h> #include <asm/cputime.h> -#include <asm/timer.h> #include <asm/vdso.h> #include <asm/pgtable.h> @@ -72,11 +71,10 @@ int main(void) DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); BLANK(); /* idle data offsets */ - DEFINE(__IDLE_ENTER, offsetof(struct s390_idle_data, idle_enter)); - DEFINE(__IDLE_EXIT, offsetof(struct s390_idle_data, idle_exit)); - /* vtimer queue offsets */ - DEFINE(__VQ_IDLE_ENTER, offsetof(struct vtimer_queue, idle_enter)); - DEFINE(__VQ_IDLE_EXIT, offsetof(struct vtimer_queue, idle_exit)); + DEFINE(__CLOCK_IDLE_ENTER, offsetof(struct s390_idle_data, clock_idle_enter)); + DEFINE(__CLOCK_IDLE_EXIT, offsetof(struct s390_idle_data, clock_idle_exit)); + DEFINE(__TIMER_IDLE_ENTER, offsetof(struct s390_idle_data, timer_idle_enter)); + DEFINE(__TIMER_IDLE_EXIT, offsetof(struct s390_idle_data, timer_idle_exit)); /* lowcore offsets */ DEFINE(__LC_EXT_PARAMS, offsetof(struct _lowcore, ext_params)); DEFINE(__LC_EXT_CPU_ADDR, offsetof(struct _lowcore, ext_cpu_addr)); @@ -131,6 +129,8 @@ int main(void) DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack)); DEFINE(__LC_RESTART_STACK, offsetof(struct _lowcore, restart_stack)); DEFINE(__LC_RESTART_FN, offsetof(struct _lowcore, restart_fn)); + DEFINE(__LC_RESTART_DATA, offsetof(struct _lowcore, restart_data)); + DEFINE(__LC_RESTART_SOURCE, offsetof(struct _lowcore, restart_source)); DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce)); DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index c880ff7..797a823 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -1,7 +1,7 @@ /* * arch/s390/kernel/base.S * - * Copyright IBM Corp. 2006,2007 + * Copyright IBM Corp. 2006, 2007 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> * Michael Holzheu <holzheu@de.ibm.com> */ @@ -9,6 +9,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> +#include <asm/sigp.h> #ifdef CONFIG_64BIT @@ -100,7 +101,7 @@ ENTRY(diag308_reset) .Lrestart_part2: lhi %r0,0 # Load r0 with zero lhi %r1,2 # Use mode 2 = ESAME (dump) - sigp %r1,%r0,0x12 # Switch to ESAME mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode sam64 # Switch to 64 bit addressing mode larl %r4,.Lctlregs # Restore control registers lctlg %c0,%c15,0(%r4) diff --git a/arch/s390/kernel/bitmap.c b/arch/s390/kernel/bitmap.c index 3ae4757..102da5e 100644 --- a/arch/s390/kernel/bitmap.c +++ b/arch/s390/kernel/bitmap.c @@ -2,7 +2,7 @@ * Bitmaps for set_bit, clear_bit, test_and_set_bit, ... * See include/asm/{bitops.h|posix_types.h} for details * - * Copyright IBM Corp. 1999,2009 + * Copyright IBM Corp. 1999, 2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, */ diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c index 914d494..765fabd 100644 --- a/arch/s390/kernel/compat_exec_domain.c +++ b/arch/s390/kernel/compat_exec_domain.c @@ -1,7 +1,7 @@ /* * Support for 32-bit Linux for S390 personality. * - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2000 * Author(s): Gerhard Tonn (ton@de.ibm.com) * * diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 6542652..d122508 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -1,8 +1,6 @@ /* - * arch/s390x/kernel/linux32.c - * * S390 version - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Gerhard Tonn (ton@de.ibm.com) * Thomas Spatzier (tspat@de.ibm.com) diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 3c0c198..a1e8a86 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/compat_signal.c - * - * Copyright (C) IBM Corp. 2000,2006 + * Copyright IBM Corp. 2000, 2006 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * Gerhard Tonn (ton@de.ibm.com) * diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index ff605a3..e835d6d 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1,8 +1,7 @@ /* -* arch/s390/kernel/compat_wrapper.S * wrapper for 31 bit compatible system calls. * -* Copyright (C) IBM Corp. 2000,2006 +* Copyright IBM Corp. 2000, 2006 * Author(s): Gerhard Tonn (ton@de.ibm.com), * Thomas Spatzier (tspat@de.ibm.com) */ diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c index e3dd886..d7b0c4d 100644 --- a/arch/s390/kernel/cpcmd.c +++ b/arch/s390/kernel/cpcmd.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/cpcmd.c - * * S390 version - * Copyright IBM Corp. 1999,2007 + * Copyright IBM Corp. 1999, 2007 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Christian Borntraeger (cborntra@de.ibm.com), */ diff --git a/arch/s390/kernel/crash.c b/arch/s390/kernel/crash.c index 8cc7c9f..3819153 100644 --- a/arch/s390/kernel/crash.c +++ b/arch/s390/kernel/crash.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/crash.c - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> * diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 19e5e9e..21be961 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1,5 +1,4 @@ /* - * arch/s390/kernel/debug.c * S/390 debug facility * * Copyright IBM Corp. 1999, 2012 diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 3221c6f..1f6b428 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1,6 +1,4 @@ /* - * arch/s390/kernel/dis.c - * * Disassemble s390 instructions. * * Copyright IBM Corp. 2007 @@ -613,6 +611,7 @@ static struct insn opcode_b2[] = { { "sie", 0x14, INSTR_S_RD }, { "pc", 0x18, INSTR_S_RD }, { "sac", 0x19, INSTR_S_RD }, + { "servc", 0x20, INSTR_RRE_RR }, { "cfc", 0x1a, INSTR_S_RD }, { "ipte", 0x21, INSTR_RRE_RR }, { "ipm", 0x22, INSTR_RRE_R0 }, diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 6684fff..bc95a8e 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -1,6 +1,4 @@ /* - * arch/s390/kernel/early.c - * * Copyright IBM Corp. 2007, 2009 * Author(s): Hongjie Yang <hongjie@us.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com> diff --git a/arch/s390/kernel/ebcdic.c b/arch/s390/kernel/ebcdic.c index cc0dc60..b971c6b 100644 --- a/arch/s390/kernel/ebcdic.c +++ b/arch/s390/kernel/ebcdic.c @@ -1,10 +1,9 @@ /* - * arch/s390/kernel/ebcdic.c * ECBDIC -> ASCII, ASCII -> ECBDIC, * upper to lower case (EBCDIC) conversion tables. * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> * Martin Peschke <peschke@fh-brandenburg.de> */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 1ae93b5..870bad6 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/entry.S * S390 low-level entry points. * - * Copyright (C) IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Hartmut Penner (hp@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), @@ -18,6 +17,7 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/page.h> +#include <asm/sigp.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 4 @@ -616,17 +616,13 @@ ext_skip: * Load idle PSW. The second "half" of this function is in cleanup_idle. */ ENTRY(psw_idle) - st %r4,__SF_EMPTY(%r15) + st %r3,__SF_EMPTY(%r15) basr %r1,0 la %r1,psw_idle_lpsw+4-.(%r1) st %r1,__SF_EMPTY+4(%r15) oi __SF_EMPTY+4(%r15),0x80 - la %r1,.Lvtimer_max-psw_idle_lpsw-4(%r1) - stck __IDLE_ENTER(%r2) - ltr %r5,%r5 - stpt __VQ_IDLE_ENTER(%r3) - jz psw_idle_lpsw - spt 0(%r1) + stck __CLOCK_IDLE_ENTER(%r2) + stpt __TIMER_IDLE_ENTER(%r2) psw_idle_lpsw: lpsw __SF_EMPTY(%r15) br %r14 @@ -723,15 +719,17 @@ ENTRY(restart_int_handler) mvc __PT_PSW(8,%r15),__LC_RST_OLD_PSW # store restart old psw ahi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15) - lm %r1,%r3,__LC_RESTART_FN # load fn, parm & source cpu + l %r1,__LC_RESTART_FN # load fn, parm & source cpu + l %r2,__LC_RESTART_DATA + l %r3,__LC_RESTART_SOURCE ltr %r3,%r3 # test source cpu address jm 1f # negative -> skip source stop -0: sigp %r4,%r3,1 # sigp sense to source cpu +0: sigp %r4,%r3,SIGP_SENSE # sigp sense to source cpu brc 10,0b # wait for status stored 1: basr %r14,%r1 # call function stap __SF_EMPTY(%r15) # store cpu address lh %r3,__SF_EMPTY(%r15) -2: sigp %r4,%r3,5 # sigp stop to current cpu +2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu brc 2,2b 3: j 3b @@ -883,33 +881,28 @@ cleanup_io_restore_insn: cleanup_idle: # copy interrupt clock & cpu timer - mvc __IDLE_EXIT(8,%r2),__LC_INT_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER chi %r11,__LC_SAVE_AREA_ASYNC je 0f - mvc __IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER 0: # check if stck has been executed cl %r9,BASED(cleanup_idle_insn) jhe 1f - mvc __IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2) - mvc __VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3) - j 2f -1: # check if the cpu timer has been reprogrammed - ltr %r5,%r5 - jz 2f - spt __VQ_IDLE_ENTER(%r3) -2: # account system time going idle + mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) + mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r3) +1: # account system time going idle lm %r9,%r10,__LC_STEAL_TIMER - ADD64 %r9,%r10,__IDLE_ENTER(%r2) + ADD64 %r9,%r10,__CLOCK_IDLE_ENTER(%r2) SUB64 %r9,%r10,__LC_LAST_UPDATE_CLOCK stm %r9,%r10,__LC_STEAL_TIMER - mvc __LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2) + mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2) lm %r9,%r10,__LC_SYSTEM_TIMER ADD64 %r9,%r10,__LC_LAST_UPDATE_TIMER - SUB64 %r9,%r10,__VQ_IDLE_ENTER(%r3) + SUB64 %r9,%r10,__TIMER_IDLE_ENTER(%r2) stm %r9,%r10,__LC_SYSTEM_TIMER - mvc __LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3) + mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw n %r8,BASED(cleanup_idle_wait) # clear wait state bit l %r9,24(%r11) # return from psw_idle diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index f66a229..a5f4dc4 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -5,7 +5,6 @@ #include <linux/signal.h> #include <asm/ptrace.h> #include <asm/cputime.h> -#include <asm/timer.h> extern void (*pgm_check_table[128])(struct pt_regs *); extern void *restart_stack; @@ -17,8 +16,7 @@ void io_int_handler(void); void mcck_int_handler(void); void restart_int_handler(void); void restart_call_handler(void); -void psw_idle(struct s390_idle_data *, struct vtimer_queue *, - unsigned long, int); +void psw_idle(struct s390_idle_data *, unsigned long); asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 229fe1d..349b7ee 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/entry64.S * S390 low-level entry points. * - * Copyright (C) IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Hartmut Penner (hp@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), @@ -18,6 +17,7 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/page.h> +#include <asm/sigp.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 8 @@ -642,15 +642,11 @@ ext_skip: * Load idle PSW. The second "half" of this function is in cleanup_idle. */ ENTRY(psw_idle) - stg %r4,__SF_EMPTY(%r15) + stg %r3,__SF_EMPTY(%r15) larl %r1,psw_idle_lpsw+4 stg %r1,__SF_EMPTY+8(%r15) - larl %r1,.Lvtimer_max - STCK __IDLE_ENTER(%r2) - ltr %r5,%r5 - stpt __VQ_IDLE_ENTER(%r3) - jz psw_idle_lpsw - spt 0(%r1) + STCK __CLOCK_IDLE_ENTER(%r2) + stpt __TIMER_IDLE_ENTER(%r2) psw_idle_lpsw: lpswe __SF_EMPTY(%r15) br %r14 @@ -750,15 +746,17 @@ ENTRY(restart_int_handler) mvc __PT_PSW(16,%r15),__LC_RST_OLD_PSW # store restart old psw aghi %r15,-STACK_FRAME_OVERHEAD # create stack frame on stack xc 0(STACK_FRAME_OVERHEAD,%r15),0(%r15) - lmg %r1,%r3,__LC_RESTART_FN # load fn, parm & source cpu + lg %r1,__LC_RESTART_FN # load fn, parm & source cpu + lg %r2,__LC_RESTART_DATA + lg %r3,__LC_RESTART_SOURCE ltgr %r3,%r3 # test source cpu address jm 1f # negative -> skip source stop -0: sigp %r4,%r3,1 # sigp sense to source cpu +0: sigp %r4,%r3,SIGP_SENSE # sigp sense to source cpu brc 10,0b # wait for status stored 1: basr %r14,%r1 # call function stap __SF_EMPTY(%r15) # store cpu address llgh %r3,__SF_EMPTY(%r15) -2: sigp %r4,%r3,5 # sigp stop to current cpu +2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu brc 2,2b 3: j 3b @@ -916,33 +914,28 @@ cleanup_io_restore_insn: cleanup_idle: # copy interrupt clock & cpu timer - mvc __IDLE_EXIT(8,%r2),__LC_INT_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_ASYNC_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER cghi %r11,__LC_SAVE_AREA_ASYNC je 0f - mvc __IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK - mvc __VQ_IDLE_EXIT(8,%r3),__LC_MCCK_ENTER_TIMER + mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER 0: # check if stck & stpt have been executed clg %r9,BASED(cleanup_idle_insn) jhe 1f - mvc __IDLE_ENTER(8,%r2),__IDLE_EXIT(%r2) - mvc __VQ_IDLE_ENTER(8,%r3),__VQ_IDLE_EXIT(%r3) - j 2f -1: # check if the cpu timer has been reprogrammed - ltr %r5,%r5 - jz 2f - spt __VQ_IDLE_ENTER(%r3) -2: # account system time going idle + mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) + mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2) +1: # account system time going idle lg %r9,__LC_STEAL_TIMER - alg %r9,__IDLE_ENTER(%r2) + alg %r9,__CLOCK_IDLE_ENTER(%r2) slg %r9,__LC_LAST_UPDATE_CLOCK stg %r9,__LC_STEAL_TIMER - mvc __LC_LAST_UPDATE_CLOCK(8),__IDLE_EXIT(%r2) + mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2) lg %r9,__LC_SYSTEM_TIMER alg %r9,__LC_LAST_UPDATE_TIMER - slg %r9,__VQ_IDLE_ENTER(%r3) + slg %r9,__TIMER_IDLE_ENTER(%r2) stg %r9,__LC_SYSTEM_TIMER - mvc __LC_LAST_UPDATE_TIMER(8),__VQ_IDLE_EXIT(%r3) + mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw nihh %r8,0xfffd # clear wait state bit lg %r9,48(%r11) # return from psw_idle @@ -958,8 +951,6 @@ cleanup_idle_insn: .quad __critical_start .Lcritical_length: .quad __critical_end - __critical_start -.Lvtimer_max: - .quad 0x7fffffffffffffff #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE) @@ -974,7 +965,6 @@ ENTRY(sie64a) stg %r3,__SF_EMPTY+8(%r15) # save guest register save area xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # host id == 0 lmg %r0,%r13,0(%r3) # load guest gprs 0-13 - lg %r14,__LC_THREAD_INFO # pointer thread_info struct sie_loop: lg %r14,__LC_THREAD_INFO # pointer thread_info struct tm __TI_flags+7(%r14),_TIF_EXIT_SIE diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 4939d15..805b668 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index d3f1ab7..a1372ae 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/head31.S - * - * Copyright (C) IBM Corp. 2005,2010 + * Copyright IBM Corp. 2005, 2010 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 99348c0..c108af2 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/head64.S - * - * Copyright (C) IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 * * Author(s): Hartmut Penner <hp@de.ibm.com> * Martin Schwidefsky <schwidefsky@de.ibm.com> diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S index 796c976..acaaaf4 100644 --- a/arch/s390/kernel/head_kdump.S +++ b/arch/s390/kernel/head_kdump.S @@ -5,6 +5,8 @@ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> */ +#include <asm/sigp.h> + #define DATAMOVER_ADDR 0x4000 #define COPY_PAGE_ADDR 0x6000 @@ -19,7 +21,7 @@ .align 2 .Lep_startup_kdump: lhi %r1,2 # mode 2 = esame (dump) - sigp %r1,%r0,0x12 # Switch to esame mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to esame mode sam64 # Switch to 64 bit addressing basr %r13,0 .Lbase: @@ -88,7 +90,7 @@ startup_kdump_relocated: sam31 # Switch to 31 bit addr mode sr %r1,%r1 # Erase register r1 sr %r2,%r2 # Erase register r2 - sigp %r1,%r2,0x12 # Switch to 31 bit arch mode + sigp %r1,%r2,SIGP_SET_ARCHITECTURE # Switch to 31 bit arch mode lpsw 0 # Start new kernel... .align 8 .Lrestart_psw: diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 2f6cfd4..e64d141 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1,8 +1,7 @@ /* - * arch/s390/kernel/ipl.c * ipl/reipl/dump support for Linux on s390. * - * Copyright IBM Corp. 2005,2012 + * Copyright IBM Corp. 2005, 2012 * Author(s): Michael Holzheu <holzheu@de.ibm.com> * Heiko Carstens <heiko.carstens@de.ibm.com> * Volker Sameske <sameske@de.ibm.com> @@ -1528,15 +1527,12 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - struct { - void *addr; - __u32 csum; - } __packed ipib; + unsigned long ipib = (unsigned long) reipl_block_actual; + unsigned int csum; - ipib.csum = csum_partial(reipl_block_actual, - reipl_block_actual->hdr.len, 0); - ipib.addr = reipl_block_actual; - memcpy_absolute(&S390_lowcore.ipib, &ipib, sizeof(ipib)); + csum = csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); + mem_assign_absolute(S390_lowcore.ipib, ipib); + mem_assign_absolute(S390_lowcore.ipib_checksum, csum); dump_run(trigger); } diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index b4f4a71..dd7630d 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2004,2011 + * Copyright IBM Corp. 2004, 2011 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Holger Smolinski <Holger.Smolinski@de.ibm.com>, * Thomas Spatzier <tspat@de.ibm.com>, diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 64b761a..8aa634f 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.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) IBM Corporation, 2002, 2006 + * Copyright IBM Corp. 2002, 2006 * * s390 port, used ppc64 as template. Mike Grundy <grundym@us.ibm.com> */ diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c index 87f080b..eca94e7 100644 --- a/arch/s390/kernel/lgr.c +++ b/arch/s390/kernel/lgr.c @@ -45,7 +45,7 @@ struct lgr_info { /* * LGR globals */ -static void *lgr_page; +static char lgr_page[PAGE_SIZE] __aligned(PAGE_SIZE); static struct lgr_info lgr_info_last; static struct lgr_info lgr_info_cur; static struct debug_info *lgr_dbf; @@ -74,7 +74,7 @@ static void cpascii(char *dst, char *src, int size) */ static void lgr_stsi_1_1_1(struct lgr_info *lgr_info) { - struct sysinfo_1_1_1 *si = lgr_page; + struct sysinfo_1_1_1 *si = (void *) lgr_page; if (stsi(si, 1, 1, 1) == -ENOSYS) return; @@ -91,7 +91,7 @@ static void lgr_stsi_1_1_1(struct lgr_info *lgr_info) */ static void lgr_stsi_2_2_2(struct lgr_info *lgr_info) { - struct sysinfo_2_2_2 *si = lgr_page; + struct sysinfo_2_2_2 *si = (void *) lgr_page; if (stsi(si, 2, 2, 2) == -ENOSYS) return; @@ -105,7 +105,7 @@ static void lgr_stsi_2_2_2(struct lgr_info *lgr_info) */ static void lgr_stsi_3_2_2(struct lgr_info *lgr_info) { - struct sysinfo_3_2_2 *si = lgr_page; + struct sysinfo_3_2_2 *si = (void *) lgr_page; int i; if (stsi(si, 3, 2, 2) == -ENOSYS) @@ -183,14 +183,9 @@ static void lgr_timer_set(void) */ static int __init lgr_init(void) { - lgr_page = (void *) __get_free_pages(GFP_KERNEL, 0); - if (!lgr_page) - return -ENOMEM; lgr_dbf = debug_register("lgr", 1, 1, sizeof(struct lgr_info)); - if (!lgr_dbf) { - free_page((unsigned long) lgr_page); + if (!lgr_dbf) return -ENOMEM; - } debug_register_view(lgr_dbf, &debug_hex_ascii_view); lgr_info_get(&lgr_info_last); debug_event(lgr_dbf, 1, &lgr_info_last, sizeof(lgr_info_last)); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index cdacf8f..493304b 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/machine_kexec.c - * - * Copyright IBM Corp. 2005,2011 + * Copyright IBM Corp. 2005, 2011 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 7e2c38b..4567ce2 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, * diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index f70cade..1133219 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>, * diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index dfcb343..46412b1 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -1,9 +1,8 @@ /* - * arch/s390/kernel/module.c - Kernel module help for s390. + * Kernel module help for s390. * * S390 version - * Copyright (C) 2002, 2003 IBM Deutschland Entwicklung GmbH, - * IBM Corporation + * Copyright IBM Corp. 2002, 2003 * Author(s): Arnd Bergmann (arndb@de.ibm.com) * Martin Schwidefsky (schwidefsky@de.ibm.com) * diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 8c372ca..a6daa5c 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -1,7 +1,7 @@ /* * Machine check handler * - * Copyright IBM Corp. 2000,2009 + * Copyright IBM Corp. 2000, 2009 * Author(s): Ingo Adlung <adlung@de.ibm.com>, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Cornelia Huck <cornelia.huck@de.ibm.com>, diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 95fa5ac..46480d8 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -60,7 +60,7 @@ void __init os_info_init(void) os_info.version_minor = OS_INFO_VERSION_MINOR; os_info.magic = OS_INFO_MAGIC; os_info.csum = os_info_csum(&os_info); - memcpy_absolute(&S390_lowcore.os_info, &ptr, sizeof(ptr)); + mem_assign_absolute(S390_lowcore.os_info, (unsigned long) ptr); } #ifdef CONFIG_CRASH_DUMP diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 60055ce..7331753 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -1,7 +1,7 @@ /* * This file handles the architecture dependent parts of process handling. * - * Copyright IBM Corp. 1999,2009 + * Copyright IBM Corp. 1999, 2009 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Hartmut Penner <hp@de.ibm.com>, * Denis Joseph Barrow, @@ -25,8 +25,8 @@ #include <linux/module.h> #include <asm/io.h> #include <asm/processor.h> +#include <asm/vtimer.h> #include <asm/irq.h> -#include <asm/timer.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/switch_to.h> diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 6e0073e..572d4c9 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -1,6 +1,4 @@ /* - * arch/s390/kernel/processor.c - * * Copyright IBM Corp. 2008 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ @@ -25,13 +23,15 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id); */ void __cpuinit cpu_init(void) { - struct cpuid *id = &per_cpu(cpu_id, smp_processor_id()); + struct s390_idle_data *idle = &__get_cpu_var(s390_idle); + struct cpuid *id = &__get_cpu_var(cpu_id); get_cpu_id(id); atomic_inc(&init_mm.mm_count); current->active_mm = &init_mm; BUG_ON(current->mm); enter_lazy_tlb(&init_mm, current); + memset(idle, 0, sizeof(*idle)); } /* diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 4993e68..f4eb376 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1,7 +1,7 @@ /* * Ptrace user space interface. * - * Copyright IBM Corp. 1999,2010 + * Copyright IBM Corp. 1999, 2010 * Author(s): Denis Joseph Barrow * Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index ad67c21..dd8016b 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -1,13 +1,12 @@ /* - * arch/s390/kernel/reipl.S - * * S390 version - * Copyright (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2000 * Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com) */ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/sigp.h> # # store_status: Empty implementation until kdump is supported on 31 bit @@ -60,7 +59,7 @@ ENTRY(do_reipl_asm) bas %r14,.Ldisab-.Lpg0(%r13) .L003: st %r1,__LC_SUBCHANNEL_ID lpsw 0 - sigp 0,0,0(6) + sigp 0,0,SIGP_RESTART .Ldisab: st %r14,.Ldispsw+4-.Lpg0(%r13) lpsw .Ldispsw-.Lpg0(%r13) .align 8 diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S index 36b3265..dc3b127 100644 --- a/arch/s390/kernel/reipl64.S +++ b/arch/s390/kernel/reipl64.S @@ -1,11 +1,12 @@ /* - * Copyright IBM Corp 2000,2011 + * Copyright IBM Corp 2000, 2011 * Author(s): Holger Smolinski <Holger.Smolinski@de.ibm.com>, * Denis Joseph Barrow, */ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/sigp.h> # # store_status @@ -106,7 +107,7 @@ ENTRY(do_reipl_asm) .L003: st %r1,__LC_SUBCHANNEL_ID lhi %r1,0 # mode 0 = esa slr %r0,%r0 # set cpuid to zero - sigp %r1,%r0,0x12 # switch to esa mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # switch to esa mode lpsw 0 .Ldisab: sll %r14,1 srl %r14,1 # need to kill hi bit to avoid specification exceptions. diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S index c91d70a..f4e6f20 100644 --- a/arch/s390/kernel/relocate_kernel.S +++ b/arch/s390/kernel/relocate_kernel.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/relocate_kernel.S - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> @@ -9,6 +7,7 @@ */ #include <linux/linkage.h> +#include <asm/sigp.h> /* * moves the new kernel to its destination... @@ -93,7 +92,7 @@ ENTRY(relocate_kernel) .no_diag308: sr %r1,%r1 # clear %r1 sr %r2,%r2 # clear %r2 - sigp %r1,%r2,0x12 # set cpuid to zero + sigp %r1,%r2,SIGP_SET_ARCHITECTURE # set cpuid to zero lpsw 0 # hopefully start new kernel... .align 8 diff --git a/arch/s390/kernel/relocate_kernel64.S b/arch/s390/kernel/relocate_kernel64.S index 7c3ce58..cfac283 100644 --- a/arch/s390/kernel/relocate_kernel64.S +++ b/arch/s390/kernel/relocate_kernel64.S @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/relocate_kernel64.S - * - * (C) Copyright IBM Corp. 2005 + * Copyright IBM Corp. 2005 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> @@ -9,6 +7,7 @@ */ #include <linux/linkage.h> +#include <asm/sigp.h> /* * moves the new kernel to its destination... @@ -45,7 +44,7 @@ ENTRY(relocate_kernel) diag %r0,%r0,0x308 .back: lhi %r1,1 # mode 1 = esame - sigp %r1,%r0,0x12 # switch to esame mode + sigp %r1,%r0,SIGP_SET_ARCHITECTURE # switch to esame mode sam64 # switch to 64 bit addressing mode basr %r13,0 .back_base: @@ -96,7 +95,7 @@ ENTRY(relocate_kernel) sam31 # 31 bit mode sr %r1,%r1 # erase register r1 sr %r2,%r2 # erase register r2 - sigp %r1,%r2,0x12 # set cpuid to zero + sigp %r1,%r2,SIGP_SET_ARCHITECTURE # set cpuid to zero lpsw 0 # hopefully start new kernel... .align 8 diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S index 95792d8..bf05389 100644 --- a/arch/s390/kernel/sclp.S +++ b/arch/s390/kernel/sclp.S @@ -1,7 +1,7 @@ /* * Mini SCLP driver. * - * Copyright IBM Corp. 2004,2009 + * Copyright IBM Corp. 2004, 2009 * * Author(s): Peter Oberparleiter <Peter.Oberparleiter@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 489d1d8..743c0f3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/setup.c - * * S390 version - * Copyright (C) IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Hartmut Penner (hp@de.ibm.com), * Martin Schwidefsky (schwidefsky@de.ibm.com) * @@ -63,6 +61,7 @@ #include <asm/kvm_virtio.h> #include <asm/diag.h> #include <asm/os_info.h> +#include <asm/sclp.h> #include "entry.h" long psw_kernel_bits = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY | @@ -138,9 +137,14 @@ __setup("condev=", condev_setup); static void __init set_preferred_console(void) { - if (MACHINE_IS_KVM) - add_preferred_console("hvc", 0, NULL); - else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) + if (MACHINE_IS_KVM) { + if (sclp_has_vt220()) + add_preferred_console("ttyS", 1, NULL); + else if (sclp_has_linemode()) + add_preferred_console("ttyS", 0, NULL); + else + add_preferred_console("hvc", 0, NULL); + } else if (CONSOLE_IS_3215 || CONSOLE_IS_SCLP) add_preferred_console("ttyS", 0, NULL); else if (CONSOLE_IS_3270) add_preferred_console("tty3270", 0, NULL); @@ -430,10 +434,11 @@ static void __init setup_lowcore(void) lc->restart_source = -1UL; /* Setup absolute zero lowcore */ - memcpy_absolute(&S390_lowcore.restart_stack, &lc->restart_stack, - 4 * sizeof(unsigned long)); - memcpy_absolute(&S390_lowcore.restart_psw, &lc->restart_psw, - sizeof(lc->restart_psw)); + mem_assign_absolute(S390_lowcore.restart_stack, lc->restart_stack); + mem_assign_absolute(S390_lowcore.restart_fn, lc->restart_fn); + mem_assign_absolute(S390_lowcore.restart_data, lc->restart_data); + mem_assign_absolute(S390_lowcore.restart_source, lc->restart_source); + mem_assign_absolute(S390_lowcore.restart_psw, lc->restart_psw); set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; @@ -598,9 +603,7 @@ static void __init setup_memory_end(void) static void __init setup_vmcoreinfo(void) { #ifdef CONFIG_KEXEC - unsigned long ptr = paddr_vmcoreinfo_note(); - - memcpy_absolute(&S390_lowcore.vmcore_info, &ptr, sizeof(ptr)); + mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note()); #endif } diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index ac565b4..c13a2a3 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -1,7 +1,5 @@ /* - * arch/s390/kernel/signal.c - * - * Copyright (C) IBM Corp. 1999,2006 + * Copyright IBM Corp. 1999, 2006 * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com) * * Based on Intel version diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 8dca9c2..720fda1 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1,7 +1,7 @@ /* * SMP related functions * - * Copyright IBM Corp. 1999,2012 + * Copyright IBM Corp. 1999, 2012 * Author(s): Denis Joseph Barrow, * Martin Schwidefsky <schwidefsky@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, @@ -38,40 +38,16 @@ #include <asm/setup.h> #include <asm/irq.h> #include <asm/tlbflush.h> -#include <asm/timer.h> +#include <asm/vtimer.h> #include <asm/lowcore.h> #include <asm/sclp.h> #include <asm/vdso.h> #include <asm/debug.h> #include <asm/os_info.h> +#include <asm/sigp.h> #include "entry.h" enum { - sigp_sense = 1, - sigp_external_call = 2, - sigp_emergency_signal = 3, - sigp_start = 4, - sigp_stop = 5, - sigp_restart = 6, - sigp_stop_and_store_status = 9, - sigp_initial_cpu_reset = 11, - sigp_cpu_reset = 12, - sigp_set_prefix = 13, - sigp_store_status_at_address = 14, - sigp_store_extended_status_at_address = 15, - sigp_set_architecture = 18, - sigp_conditional_emergency_signal = 19, - sigp_sense_running = 21, -}; - -enum { - sigp_order_code_accepted = 0, - sigp_status_stored = 1, - sigp_busy = 2, - sigp_not_operational = 3, -}; - -enum { ec_schedule = 0, ec_call_function, ec_call_function_single, @@ -124,7 +100,7 @@ static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status) while (1) { cc = __pcpu_sigp(addr, order, parm, status); - if (cc != sigp_busy) + if (cc != SIGP_CC_BUSY) return cc; cpu_relax(); } @@ -136,7 +112,7 @@ static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) for (retry = 0; ; retry++) { cc = __pcpu_sigp(pcpu->address, order, parm, &pcpu->status); - if (cc != sigp_busy) + if (cc != SIGP_CC_BUSY) break; if (retry >= 3) udelay(10); @@ -146,20 +122,19 @@ static int pcpu_sigp_retry(struct pcpu *pcpu, u8 order, u32 parm) static inline int pcpu_stopped(struct pcpu *pcpu) { - if (__pcpu_sigp(pcpu->address, sigp_sense, - 0, &pcpu->status) != sigp_status_stored) + if (__pcpu_sigp(pcpu->address, SIGP_SENSE, + 0, &pcpu->status) != SIGP_CC_STATUS_STORED) return 0; - /* Check for stopped and check stop state */ - return !!(pcpu->status & 0x50); + return !!(pcpu->status & (SIGP_STATUS_CHECK_STOP|SIGP_STATUS_STOPPED)); } static inline int pcpu_running(struct pcpu *pcpu) { - if (__pcpu_sigp(pcpu->address, sigp_sense_running, - 0, &pcpu->status) != sigp_status_stored) + if (__pcpu_sigp(pcpu->address, SIGP_SENSE_RUNNING, + 0, &pcpu->status) != SIGP_CC_STATUS_STORED) return 1; - /* Check for running status */ - return !(pcpu->status & 0x400); + /* Status stored condition code is equivalent to cpu not running. */ + return 0; } /* @@ -181,7 +156,7 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit) set_bit(ec_bit, &pcpu->ec_mask); order = pcpu_running(pcpu) ? - sigp_external_call : sigp_emergency_signal; + SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL; pcpu_sigp_retry(pcpu, order, 0); } @@ -214,7 +189,7 @@ static int __cpuinit pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) goto out; #endif lowcore_ptr[cpu] = lc; - pcpu_sigp_retry(pcpu, sigp_set_prefix, (u32)(unsigned long) lc); + pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc); return 0; out: if (pcpu != &pcpu_devices[0]) { @@ -229,7 +204,7 @@ out: static void pcpu_free_lowcore(struct pcpu *pcpu) { - pcpu_sigp_retry(pcpu, sigp_set_prefix, 0); + pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0); lowcore_ptr[pcpu - pcpu_devices] = NULL; #ifndef CONFIG_64BIT if (MACHINE_HAS_IEEE) { @@ -288,7 +263,7 @@ static void pcpu_start_fn(struct pcpu *pcpu, void (*func)(void *), void *data) lc->restart_fn = (unsigned long) func; lc->restart_data = (unsigned long) data; lc->restart_source = -1UL; - pcpu_sigp_retry(pcpu, sigp_restart, 0); + pcpu_sigp_retry(pcpu, SIGP_RESTART, 0); } /* @@ -298,26 +273,26 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), void *data, unsigned long stack) { struct _lowcore *lc = lowcore_ptr[pcpu - pcpu_devices]; - struct { - unsigned long stack; - void *func; - void *data; - unsigned long source; - } restart = { stack, func, data, stap() }; + unsigned long source_cpu = stap(); __load_psw_mask(psw_kernel_bits); - if (pcpu->address == restart.source) + if (pcpu->address == source_cpu) func(data); /* should not return */ /* Stop target cpu (if func returns this stops the current cpu). */ - pcpu_sigp_retry(pcpu, sigp_stop, 0); + pcpu_sigp_retry(pcpu, SIGP_STOP, 0); /* Restart func on the target cpu and stop the current cpu. */ - memcpy_absolute(&lc->restart_stack, &restart, sizeof(restart)); + mem_assign_absolute(lc->restart_stack, stack); + mem_assign_absolute(lc->restart_fn, (unsigned long) func); + mem_assign_absolute(lc->restart_data, (unsigned long) data); + mem_assign_absolute(lc->restart_source, source_cpu); asm volatile( - "0: sigp 0,%0,6 # sigp restart to target cpu\n" + "0: sigp 0,%0,%2 # sigp restart to target cpu\n" " brc 2,0b # busy, try again\n" - "1: sigp 0,%1,5 # sigp stop to current cpu\n" + "1: sigp 0,%1,%3 # sigp stop to current cpu\n" " brc 2,1b # busy, try again\n" - : : "d" (pcpu->address), "d" (restart.source) : "0", "1", "cc"); + : : "d" (pcpu->address), "d" (source_cpu), + "K" (SIGP_RESTART), "K" (SIGP_STOP) + : "0", "1", "cc"); for (;;) ; } @@ -388,8 +363,8 @@ void smp_emergency_stop(cpumask_t *cpumask) for_each_cpu(cpu, cpumask) { struct pcpu *pcpu = pcpu_devices + cpu; set_bit(ec_stop_cpu, &pcpu->ec_mask); - while (__pcpu_sigp(pcpu->address, sigp_emergency_signal, - 0, NULL) == sigp_busy && + while (__pcpu_sigp(pcpu->address, SIGP_EMERGENCY_SIGNAL, + 0, NULL) == SIGP_CC_BUSY && get_clock() < end) cpu_relax(); } @@ -425,7 +400,7 @@ void smp_send_stop(void) /* stop all processors */ for_each_cpu(cpu, &cpumask) { struct pcpu *pcpu = pcpu_devices + cpu; - pcpu_sigp_retry(pcpu, sigp_stop, 0); + pcpu_sigp_retry(pcpu, SIGP_STOP, 0); while (!pcpu_stopped(pcpu)) cpu_relax(); } @@ -436,7 +411,7 @@ void smp_send_stop(void) */ void smp_stop_cpu(void) { - pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0); + pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } @@ -590,7 +565,7 @@ static void __init smp_get_save_area(int cpu, u16 address) } #endif /* Get the registers of a non-boot cpu. */ - __pcpu_sigp_relax(address, sigp_stop_and_store_status, 0, NULL); + __pcpu_sigp_relax(address, SIGP_STOP_AND_STORE_STATUS, 0, NULL); memcpy_real(save_area, lc + SAVE_AREA_BASE, sizeof(*save_area)); } @@ -599,8 +574,8 @@ int smp_store_status(int cpu) struct pcpu *pcpu; pcpu = pcpu_devices + cpu; - if (__pcpu_sigp_relax(pcpu->address, sigp_stop_and_store_status, - 0, NULL) != sigp_order_code_accepted) + if (__pcpu_sigp_relax(pcpu->address, SIGP_STOP_AND_STORE_STATUS, + 0, NULL) != SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; return 0; } @@ -621,8 +596,8 @@ static struct sclp_cpu_info *smp_get_cpu_info(void) if (info && (use_sigp_detection || sclp_get_cpu_info(info))) { use_sigp_detection = 1; for (address = 0; address <= MAX_CPU_ADDRESS; address++) { - if (__pcpu_sigp_relax(address, sigp_sense, 0, NULL) == - sigp_not_operational) + if (__pcpu_sigp_relax(address, SIGP_SENSE, 0, NULL) == + SIGP_CC_NOT_OPERATIONAL) continue; info->cpu[info->configured].address = address; info->configured++; @@ -732,8 +707,8 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) pcpu = pcpu_devices + cpu; if (pcpu->state != CPU_STATE_CONFIGURED) return -EIO; - if (pcpu_sigp_retry(pcpu, sigp_initial_cpu_reset, 0) != - sigp_order_code_accepted) + if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) != + SIGP_CC_ORDER_CODE_ACCEPTED) return -EIO; rc = pcpu_alloc_lowcore(pcpu, cpu); @@ -793,7 +768,7 @@ void __cpu_die(unsigned int cpu) void __noreturn cpu_die(void) { idle_task_exit(); - pcpu_sigp_retry(pcpu_devices + smp_processor_id(), sigp_stop, 0); + pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } @@ -940,7 +915,7 @@ static ssize_t show_idle_count(struct device *dev, do { sequence = ACCESS_ONCE(idle->sequence); idle_count = ACCESS_ONCE(idle->idle_count); - if (ACCESS_ONCE(idle->idle_enter)) + if (ACCESS_ONCE(idle->clock_idle_enter)) idle_count++; } while ((sequence & 1) || (idle->sequence != sequence)); return sprintf(buf, "%llu\n", idle_count); @@ -958,8 +933,8 @@ static ssize_t show_idle_time(struct device *dev, now = get_clock(); sequence = ACCESS_ONCE(idle->sequence); idle_time = ACCESS_ONCE(idle->idle_time); - idle_enter = ACCESS_ONCE(idle->idle_enter); - idle_exit = ACCESS_ONCE(idle->idle_exit); + idle_enter = ACCESS_ONCE(idle->clock_idle_enter); + idle_exit = ACCESS_ONCE(idle->clock_idle_exit); } while ((sequence & 1) || (idle->sequence != sequence)); idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; return sprintf(buf, "%llu\n", idle_time >> 12); @@ -982,14 +957,11 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self, unsigned int cpu = (unsigned int)(long)hcpu; struct cpu *c = &pcpu_devices[cpu].cpu; struct device *s = &c->dev; - struct s390_idle_data *idle; int err = 0; switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - idle = &per_cpu(s390_idle, cpu); - memset(idle, 0, sizeof(struct s390_idle_data)); err = sysfs_create_group(&s->kobj, &cpu_online_attr_group); break; case CPU_DEAD: diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 8841919..1785cd8 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -1,9 +1,7 @@ /* - * arch/s390/kernel/stacktrace.c - * * Stack trace management functions * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index dd70ef0..d4ca4e0 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -12,6 +12,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/sigp.h> /* * Save register context in absolute 0 lowcore and call swsusp_save() to @@ -163,7 +164,7 @@ ENTRY(swsusp_arch_resume) diag %r0,%r0,0x308 restart_entry: lhi %r1,1 - sigp %r1,%r0,0x12 + sigp %r1,%r0,SIGP_SET_ARCHITECTURE sam64 larl %r1,.Lnew_pgm_check_psw lpswe 0(%r1) @@ -179,7 +180,7 @@ pgm_check_entry: larl %r4,.Lrestart_suspend_psw /* Set new restart PSW */ mvc __LC_RST_NEW_PSW(16,%r0),0(%r4) 3: - sigp %r9,%r1,11 /* sigp initial cpu reset */ + sigp %r9,%r1,SIGP_INITIAL_CPU_RESET /* sigp initial cpu reset */ brc 8,4f /* accepted */ brc 2,3b /* busy, try again */ @@ -190,16 +191,16 @@ pgm_check_entry: larl %r3,_sclp_print_early lghi %r1,0 sam31 - sigp %r1,%r0,0x12 + sigp %r1,%r0,SIGP_SET_ARCHITECTURE basr %r14,%r3 larl %r3,.Ldisabled_wait_31 lpsw 0(%r3) 4: /* Switch to suspend CPU */ - sigp %r9,%r1,6 /* sigp restart to suspend CPU */ + sigp %r9,%r1,SIGP_RESTART /* sigp restart to suspend CPU */ brc 2,4b /* busy, try again */ 5: - sigp %r9,%r2,5 /* sigp stop to current resume CPU */ + sigp %r9,%r2,SIGP_STOP /* sigp stop to current resume CPU */ brc 2,5b /* busy, try again */ 6: j 6b @@ -207,7 +208,7 @@ restart_suspend: larl %r1,.Lresume_cpu llgh %r2,0(%r1) 7: - sigp %r9,%r2,1 /* sigp sense, wait for resume CPU */ + sigp %r9,%r2,SIGP_SENSE /* sigp sense, wait for resume CPU */ brc 8,7b /* accepted, status 0, still running */ brc 2,7b /* busy, try again */ tmll %r9,0x40 /* Test if resume CPU is stopped */ diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index 78ea194..b4a29ee 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/sys_s390.c - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Thomas Spatzier (tspat@de.ibm.com) * diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index d4e1cb1..dcec960 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -1,5 +1,4 @@ /* - * arch/s390/kernel/time.c * Time of day based timer functions. * * S390 version @@ -45,7 +44,7 @@ #include <asm/vdso.h> #include <asm/irq.h> #include <asm/irq_regs.h> -#include <asm/timer.h> +#include <asm/vtimer.h> #include <asm/etr.h> #include <asm/cio.h> #include "entry.h" diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4f8dc94..05151e0 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2007,2011 + * Copyright IBM Corp. 2007, 2011 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 77cdf42..af2421a 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -1,8 +1,6 @@ /* - * arch/s390/kernel/traps.c - * * S390 version - * Copyright (C) 1999,2000 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2000 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com), * diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 39ebff5..4fc97b4 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -1,71 +1,82 @@ /* - * arch/s390/kernel/vtime.c * Virtual cpu timer based timer functions. * - * S390 version - * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2004, 2012 * Author(s): Jan Glauber <jan.glauber@de.ibm.com> */ -#include <linux/module.h> +#include <linux/kernel_stat.h> +#include <linux/notifier.h> +#include <linux/kprobes.h> +#include <linux/export.h> #include <linux/kernel.h> -#include <linux/time.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/smp.h> -#include <linux/types.h> #include <linux/timex.h> -#include <linux/notifier.h> -#include <linux/kernel_stat.h> -#include <linux/rcupdate.h> -#include <linux/posix-timers.h> +#include <linux/types.h> +#include <linux/time.h> #include <linux/cpu.h> -#include <linux/kprobes.h> +#include <linux/smp.h> -#include <asm/timer.h> #include <asm/irq_regs.h> #include <asm/cputime.h> +#include <asm/vtimer.h> #include <asm/irq.h> #include "entry.h" -static DEFINE_PER_CPU(struct vtimer_queue, virt_cpu_timer); +static void virt_timer_expire(void); DEFINE_PER_CPU(struct s390_idle_data, s390_idle); -static inline __u64 get_vtimer(void) +static LIST_HEAD(virt_timer_list); +static DEFINE_SPINLOCK(virt_timer_lock); +static atomic64_t virt_timer_current; +static atomic64_t virt_timer_elapsed; + +static inline u64 get_vtimer(void) { - __u64 timer; + u64 timer; - asm volatile("STPT %0" : "=m" (timer)); + asm volatile("stpt %0" : "=m" (timer)); return timer; } -static inline void set_vtimer(__u64 expires) +static inline void set_vtimer(u64 expires) { - __u64 timer; + u64 timer; - asm volatile (" STPT %0\n" /* Store current cpu timer value */ - " SPT %1" /* Set new value immediately afterwards */ - : "=m" (timer) : "m" (expires) ); + asm volatile( + " stpt %0\n" /* Store current cpu timer value */ + " spt %1" /* Set new value imm. afterwards */ + : "=m" (timer) : "m" (expires)); S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer; S390_lowcore.last_update_timer = expires; } +static inline int virt_timer_forward(u64 elapsed) +{ + BUG_ON(!irqs_disabled()); + + if (list_empty(&virt_timer_list)) + return 0; + elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed); + return elapsed >= atomic64_read(&virt_timer_current); +} + /* * Update process times based on virtual cpu times stored by entry.S * to the lowcore fields user_timer, system_timer & steal_clock. */ -static void do_account_vtime(struct task_struct *tsk, int hardirq_offset) +static int do_account_vtime(struct task_struct *tsk, int hardirq_offset) { struct thread_info *ti = task_thread_info(tsk); - __u64 timer, clock, user, system, steal; + u64 timer, clock, user, system, steal; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; - asm volatile (" STPT %0\n" /* Store current cpu timer value */ - " STCK %1" /* Store current tod clock value */ - : "=m" (S390_lowcore.last_update_timer), - "=m" (S390_lowcore.last_update_clock) ); + asm volatile( + " stpt %0\n" /* Store current cpu timer value */ + " stck %1" /* Store current tod clock value */ + : "=m" (S390_lowcore.last_update_timer), + "=m" (S390_lowcore.last_update_clock)); S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer; S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock; @@ -84,6 +95,8 @@ static void do_account_vtime(struct task_struct *tsk, int hardirq_offset) S390_lowcore.steal_timer = 0; account_steal_time(steal); } + + return virt_timer_forward(user + system); } void account_vtime(struct task_struct *prev, struct task_struct *next) @@ -101,7 +114,8 @@ void account_vtime(struct task_struct *prev, struct task_struct *next) void account_process_tick(struct task_struct *tsk, int user_tick) { - do_account_vtime(tsk, HARDIRQ_OFFSET); + if (do_account_vtime(tsk, HARDIRQ_OFFSET)) + virt_timer_expire(); } /* @@ -111,7 +125,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick) void account_system_vtime(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); - __u64 timer, system; + u64 timer, system; timer = S390_lowcore.last_update_timer; S390_lowcore.last_update_timer = get_vtimer(); @@ -121,13 +135,14 @@ void account_system_vtime(struct task_struct *tsk) S390_lowcore.steal_timer -= system; ti->system_timer = S390_lowcore.system_timer; account_system_time(tsk, 0, system, system); + + virt_timer_forward(system); } EXPORT_SYMBOL_GPL(account_system_vtime); void __kprobes vtime_stop_cpu(void) { struct s390_idle_data *idle = &__get_cpu_var(s390_idle); - struct vtimer_queue *vq = &__get_cpu_var(virt_cpu_timer); unsigned long long idle_time; unsigned long psw_mask; @@ -141,7 +156,7 @@ void __kprobes vtime_stop_cpu(void) idle->nohz_delay = 0; /* Call the assembler magic in entry.S */ - psw_idle(idle, vq, psw_mask, !list_empty(&vq->list)); + psw_idle(idle, psw_mask); /* Reenable preemption tracer. */ start_critical_timings(); @@ -149,9 +164,9 @@ void __kprobes vtime_stop_cpu(void) /* Account time spent with enabled wait psw loaded as idle time. */ idle->sequence++; smp_wmb(); - idle_time = idle->idle_exit - idle->idle_enter; + idle_time = idle->clock_idle_exit - idle->clock_idle_enter; + idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; - idle->idle_enter = idle->idle_exit = 0ULL; idle->idle_count++; account_idle_time(idle_time); smp_wmb(); @@ -167,10 +182,10 @@ cputime64_t s390_get_idle_time(int cpu) do { now = get_clock(); sequence = ACCESS_ONCE(idle->sequence); - idle_enter = ACCESS_ONCE(idle->idle_enter); - idle_exit = ACCESS_ONCE(idle->idle_exit); + idle_enter = ACCESS_ONCE(idle->clock_idle_enter); + idle_exit = ACCESS_ONCE(idle->clock_idle_exit); } while ((sequence & 1) || (idle->sequence != sequence)); - return idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; } /* @@ -179,11 +194,11 @@ cputime64_t s390_get_idle_time(int cpu) */ static void list_add_sorted(struct vtimer_list *timer, struct list_head *head) { - struct vtimer_list *event; + struct vtimer_list *tmp; - list_for_each_entry(event, head, entry) { - if (event->expires > timer->expires) { - list_add_tail(&timer->entry, &event->entry); + list_for_each_entry(tmp, head, entry) { + if (tmp->expires > timer->expires) { + list_add_tail(&timer->entry, &tmp->entry); return; } } @@ -191,82 +206,45 @@ static void list_add_sorted(struct vtimer_list *timer, struct list_head *head) } /* - * Do the callback functions of expired vtimer events. - * Called from within the interrupt handler. - */ -static void do_callbacks(struct list_head *cb_list) -{ - struct vtimer_queue *vq; - struct vtimer_list *event, *tmp; - - if (list_empty(cb_list)) - return; - - vq = &__get_cpu_var(virt_cpu_timer); - - list_for_each_entry_safe(event, tmp, cb_list, entry) { - list_del_init(&event->entry); - (event->function)(event->data); - if (event->interval) { - /* Recharge interval timer */ - event->expires = event->interval + vq->elapsed; - spin_lock(&vq->lock); - list_add_sorted(event, &vq->list); - spin_unlock(&vq->lock); - } - } -} - -/* - * Handler for the virtual CPU timer. + * Handler for expired virtual CPU timer. */ -static void do_cpu_timer_interrupt(struct ext_code ext_code, - unsigned int param32, unsigned long param64) +static void virt_timer_expire(void) { - struct vtimer_queue *vq; - struct vtimer_list *event, *tmp; - struct list_head cb_list; /* the callback queue */ - __u64 elapsed, next; - - kstat_cpu(smp_processor_id()).irqs[EXTINT_TMR]++; - INIT_LIST_HEAD(&cb_list); - vq = &__get_cpu_var(virt_cpu_timer); - - /* walk timer list, fire all expired events */ - spin_lock(&vq->lock); - - elapsed = vq->elapsed + (vq->timer - S390_lowcore.async_enter_timer); - BUG_ON((s64) elapsed < 0); - vq->elapsed = 0; - list_for_each_entry_safe(event, tmp, &vq->list, entry) { - if (event->expires < elapsed) + struct vtimer_list *timer, *tmp; + unsigned long elapsed; + LIST_HEAD(cb_list); + + /* walk timer list, fire all expired timers */ + spin_lock(&virt_timer_lock); + elapsed = atomic64_read(&virt_timer_elapsed); + list_for_each_entry_safe(timer, tmp, &virt_timer_list, entry) { + if (timer->expires < elapsed) /* move expired timer to the callback queue */ - list_move_tail(&event->entry, &cb_list); + list_move_tail(&timer->entry, &cb_list); else - event->expires -= elapsed; + timer->expires -= elapsed; } - spin_unlock(&vq->lock); - - do_callbacks(&cb_list); - - /* next event is first in list */ - next = VTIMER_MAX_SLICE; - spin_lock(&vq->lock); - if (!list_empty(&vq->list)) { - event = list_first_entry(&vq->list, struct vtimer_list, entry); - next = event->expires; + if (!list_empty(&virt_timer_list)) { + timer = list_first_entry(&virt_timer_list, + struct vtimer_list, entry); + atomic64_set(&virt_timer_current, timer->expires); + } + atomic64_sub(elapsed, &virt_timer_elapsed); + spin_unlock(&virt_timer_lock); + + /* Do callbacks and recharge periodic timers */ + list_for_each_entry_safe(timer, tmp, &cb_list, entry) { + list_del_init(&timer->entry); + timer->function(timer->data); + if (timer->interval) { + /* Recharge interval timer */ + timer->expires = timer->interval + + atomic64_read(&virt_timer_elapsed); + spin_lock(&virt_timer_lock); + list_add_sorted(timer, &virt_timer_list); + spin_unlock(&virt_timer_lock); + } } - spin_unlock(&vq->lock); - /* - * To improve precision add the time spent by the - * interrupt handler to the elapsed time. - * Note: CPU timer counts down and we got an interrupt, - * the current content is negative - */ - elapsed = S390_lowcore.async_enter_timer - get_vtimer(); - set_vtimer(next - elapsed); - vq->timer = next - elapsed; - vq->elapsed = elapsed; } void init_virt_timer(struct vtimer_list *timer) @@ -278,179 +256,108 @@ EXPORT_SYMBOL(init_virt_timer); static inline int vtimer_pending(struct vtimer_list *timer) { - return (!list_empty(&timer->entry)); + return !list_empty(&timer->entry); } -/* - * this function should only run on the specified CPU - */ static void internal_add_vtimer(struct vtimer_list *timer) { - struct vtimer_queue *vq; - unsigned long flags; - __u64 left, expires; - - vq = &per_cpu(virt_cpu_timer, timer->cpu); - spin_lock_irqsave(&vq->lock, flags); - - BUG_ON(timer->cpu != smp_processor_id()); - - if (list_empty(&vq->list)) { - /* First timer on this cpu, just program it. */ - list_add(&timer->entry, &vq->list); - set_vtimer(timer->expires); - vq->timer = timer->expires; - vq->elapsed = 0; + if (list_empty(&virt_timer_list)) { + /* First timer, just program it. */ + atomic64_set(&virt_timer_current, timer->expires); + atomic64_set(&virt_timer_elapsed, 0); + list_add(&timer->entry, &virt_timer_list); } else { - /* Check progress of old timers. */ - expires = timer->expires; - left = get_vtimer(); - if (likely((s64) expires < (s64) left)) { + /* Update timer against current base. */ + timer->expires += atomic64_read(&virt_timer_elapsed); + if (likely((s64) timer->expires < + (s64) atomic64_read(&virt_timer_current))) /* The new timer expires before the current timer. */ - set_vtimer(expires); - vq->elapsed += vq->timer - left; - vq->timer = expires; - } else { - vq->elapsed += vq->timer - left; - vq->timer = left; - } - /* Insert new timer into per cpu list. */ - timer->expires += vq->elapsed; - list_add_sorted(timer, &vq->list); + atomic64_set(&virt_timer_current, timer->expires); + /* Insert new timer into the list. */ + list_add_sorted(timer, &virt_timer_list); } - - spin_unlock_irqrestore(&vq->lock, flags); - /* release CPU acquired in prepare_vtimer or mod_virt_timer() */ - put_cpu(); } -static inline void prepare_vtimer(struct vtimer_list *timer) +static void __add_vtimer(struct vtimer_list *timer, int periodic) { - BUG_ON(!timer->function); - BUG_ON(!timer->expires || timer->expires > VTIMER_MAX_SLICE); - BUG_ON(vtimer_pending(timer)); - timer->cpu = get_cpu(); + unsigned long flags; + + timer->interval = periodic ? timer->expires : 0; + spin_lock_irqsave(&virt_timer_lock, flags); + internal_add_vtimer(timer); + spin_unlock_irqrestore(&virt_timer_lock, flags); } /* * add_virt_timer - add an oneshot virtual CPU timer */ -void add_virt_timer(void *new) +void add_virt_timer(struct vtimer_list *timer) { - struct vtimer_list *timer; - - timer = (struct vtimer_list *)new; - prepare_vtimer(timer); - timer->interval = 0; - internal_add_vtimer(timer); + __add_vtimer(timer, 0); } EXPORT_SYMBOL(add_virt_timer); /* * add_virt_timer_int - add an interval virtual CPU timer */ -void add_virt_timer_periodic(void *new) +void add_virt_timer_periodic(struct vtimer_list *timer) { - struct vtimer_list *timer; - - timer = (struct vtimer_list *)new; - prepare_vtimer(timer); - timer->interval = timer->expires; - internal_add_vtimer(timer); + __add_vtimer(timer, 1); } EXPORT_SYMBOL(add_virt_timer_periodic); -static int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) +static int __mod_vtimer(struct vtimer_list *timer, u64 expires, int periodic) { - struct vtimer_queue *vq; unsigned long flags; - int cpu; + int rc; BUG_ON(!timer->function); - BUG_ON(!expires || expires > VTIMER_MAX_SLICE); if (timer->expires == expires && vtimer_pending(timer)) return 1; - - cpu = get_cpu(); - vq = &per_cpu(virt_cpu_timer, cpu); - - /* disable interrupts before test if timer is pending */ - spin_lock_irqsave(&vq->lock, flags); - - /* if timer isn't pending add it on the current CPU */ - if (!vtimer_pending(timer)) { - spin_unlock_irqrestore(&vq->lock, flags); - - if (periodic) - timer->interval = expires; - else - timer->interval = 0; - timer->expires = expires; - timer->cpu = cpu; - internal_add_vtimer(timer); - return 0; - } - - /* check if we run on the right CPU */ - BUG_ON(timer->cpu != cpu); - - list_del_init(&timer->entry); + spin_lock_irqsave(&virt_timer_lock, flags); + rc = vtimer_pending(timer); + if (rc) + list_del_init(&timer->entry); + timer->interval = periodic ? expires : 0; timer->expires = expires; - if (periodic) - timer->interval = expires; - - /* the timer can't expire anymore so we can release the lock */ - spin_unlock_irqrestore(&vq->lock, flags); internal_add_vtimer(timer); - return 1; + spin_unlock_irqrestore(&virt_timer_lock, flags); + return rc; } /* - * If we change a pending timer the function must be called on the CPU - * where the timer is running on. - * * returns whether it has modified a pending timer (1) or not (0) */ -int mod_virt_timer(struct vtimer_list *timer, __u64 expires) +int mod_virt_timer(struct vtimer_list *timer, u64 expires) { return __mod_vtimer(timer, expires, 0); } EXPORT_SYMBOL(mod_virt_timer); /* - * If we change a pending timer the function must be called on the CPU - * where the timer is running on. - * * returns whether it has modified a pending timer (1) or not (0) */ -int mod_virt_timer_periodic(struct vtimer_list *timer, __u64 expires) +int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires) { return __mod_vtimer(timer, expires, 1); } EXPORT_SYMBOL(mod_virt_timer_periodic); /* - * delete a virtual timer + * Delete a virtual timer. * * returns whether the deleted timer was pending (1) or not (0) */ int del_virt_timer(struct vtimer_list *timer) { unsigned long flags; - struct vtimer_queue *vq; - /* check if timer is pending */ if (!vtimer_pending(timer)) return 0; - - vq = &per_cpu(virt_cpu_timer, timer->cpu); - spin_lock_irqsave(&vq->lock, flags); - - /* we don't interrupt a running timer, just let it expire! */ + spin_lock_irqsave(&virt_timer_lock, flags); list_del_init(&timer->entry); - - spin_unlock_irqrestore(&vq->lock, flags); + spin_unlock_irqrestore(&virt_timer_lock, flags); return 1; } EXPORT_SYMBOL(del_virt_timer); @@ -458,20 +365,10 @@ EXPORT_SYMBOL(del_virt_timer); /* * Start the virtual CPU timer on the current CPU. */ -void init_cpu_vtimer(void) +void __cpuinit init_cpu_vtimer(void) { - struct vtimer_queue *vq; - - /* initialize per cpu vtimer structure */ - vq = &__get_cpu_var(virt_cpu_timer); - INIT_LIST_HEAD(&vq->list); - spin_lock_init(&vq->lock); - - /* enable cpu timer interrupts */ - __ctl_set_bit(0,10); - /* set initial cpu timer */ - set_vtimer(0x7fffffffffffffffULL); + set_vtimer(VTIMER_MAX_SLICE); } static int __cpuinit s390_nohz_notify(struct notifier_block *self, @@ -493,12 +390,7 @@ static int __cpuinit s390_nohz_notify(struct notifier_block *self, void __init vtime_init(void) { - /* request the cpu timer external interrupt */ - if (register_external_interrupt(0x1005, do_cpu_timer_interrupt)) - panic("Couldn't request external interrupt 0x1005"); - /* Enable cpu timer interrupts on the boot cpu. */ init_cpu_vtimer(); cpu_notifier(s390_nohz_notify, 0); } - diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index b23d9ac..c88bb77 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -1,7 +1,7 @@ /* - * diag.c - handling diagnose instructions + * handling diagnose instructions * - * Copyright IBM Corp. 2008,2011 + * Copyright IBM Corp. 2008, 2011 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index c86f6ae..4703f12 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -1,7 +1,7 @@ /* - * access.h - access guest memory + * access guest memory * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 979cbe5..adae539 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -1,7 +1,7 @@ /* - * intercept.c - in-kernel handling for sie intercepts + * in-kernel handling for sie intercepts * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2d9f9a7..b7bc1aa 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1,5 +1,5 @@ /* - * interrupt.c - handling kvm guest interrupts + * handling kvm guest interrupts * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 664766d..d470ccb 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1,7 +1,7 @@ /* - * s390host.c -- hosting zSeries kernel virtual machines + * hosting zSeries kernel virtual machines * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -347,6 +347,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) vcpu->arch.guest_fpregs.fpc = 0; asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); vcpu->arch.sie_block->gbea = 1; + atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); } int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 2294377..d75bc5e 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -1,7 +1,7 @@ /* - * kvm_s390.h - definition for kvm on s390 + * definition for kvm on s390 * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 68a6b2e..60da903 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -1,5 +1,5 @@ /* - * priv.c - handling privileged instructions + * handling privileged instructions * * Copyright IBM Corp. 2008 * diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 0ad4cf2..56f80e1 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -1,7 +1,7 @@ /* - * sigp.c - handlinge interprocessor communication + * handling interprocessor communication * - * Copyright IBM Corp. 2008,2009 + * Copyright IBM Corp. 2008, 2009 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -15,38 +15,10 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/slab.h> +#include <asm/sigp.h> #include "gaccess.h" #include "kvm-s390.h" -/* sigp order codes */ -#define SIGP_SENSE 0x01 -#define SIGP_EXTERNAL_CALL 0x02 -#define SIGP_EMERGENCY 0x03 -#define SIGP_START 0x04 -#define SIGP_STOP 0x05 -#define SIGP_RESTART 0x06 -#define SIGP_STOP_STORE_STATUS 0x09 -#define SIGP_INITIAL_CPU_RESET 0x0b -#define SIGP_CPU_RESET 0x0c -#define SIGP_SET_PREFIX 0x0d -#define SIGP_STORE_STATUS_ADDR 0x0e -#define SIGP_SET_ARCH 0x12 -#define SIGP_SENSE_RUNNING 0x15 - -/* cpu status bits */ -#define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL -#define SIGP_STAT_NOT_RUNNING 0x00000400UL -#define SIGP_STAT_INCORRECT_STATE 0x00000200UL -#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL -#define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL -#define SIGP_STAT_STOPPED 0x00000040UL -#define SIGP_STAT_OPERATOR_INTERV 0x00000020UL -#define SIGP_STAT_CHECK_STOP 0x00000010UL -#define SIGP_STAT_INOPERATIVE 0x00000004UL -#define SIGP_STAT_INVALID_ORDER 0x00000002UL -#define SIGP_STAT_RECEIVER_CHECK 0x00000001UL - - static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg) { @@ -54,19 +26,23 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); if (fi->local_int[cpu_addr] == NULL) - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags) - & CPUSTAT_STOPPED)) { - *reg &= 0xffffffff00000000UL; - rc = 1; /* status stored */ - } else { + & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED))) + rc = SIGP_CC_ORDER_CODE_ACCEPTED; + else { *reg &= 0xffffffff00000000UL; - *reg |= SIGP_STAT_STOPPED; - rc = 1; /* status stored */ + if (atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_ECALL_PEND) + *reg |= SIGP_STATUS_EXT_CALL_PENDING; + if (atomic_read(fi->local_int[cpu_addr]->cpuflags) + & CPUSTAT_STOPPED) + *reg |= SIGP_STATUS_STOPPED; + rc = SIGP_CC_STATUS_STORED; } spin_unlock(&fi->lock); @@ -82,7 +58,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) @@ -94,7 +70,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; kfree(inti); goto unlock; } @@ -105,7 +81,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); unlock: spin_unlock(&fi->lock); @@ -120,7 +96,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) @@ -132,7 +108,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; kfree(inti); goto unlock; } @@ -143,7 +119,7 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); unlock: spin_unlock(&fi->lock); @@ -171,7 +147,7 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action) out: spin_unlock_bh(&li->lock); - return 0; /* order accepted */ + return SIGP_CC_ORDER_CODE_ACCEPTED; } static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) @@ -181,12 +157,12 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) int rc; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; goto unlock; } @@ -210,11 +186,11 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) switch (parameter & 0xff) { case 0: - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; break; case 1: case 2: - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; break; default: rc = -EOPNOTSUPP; @@ -235,21 +211,23 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, address = address & 0x7fffe000u; if (copy_from_guest_absolute(vcpu, &tmp, address, 1) || copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) { - *reg |= SIGP_STAT_INVALID_PARAMETER; - return 1; /* invalid parameter */ + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INVALID_PARAMETER; + return SIGP_CC_STATUS_STORED; } inti = kzalloc(sizeof(*inti), GFP_KERNEL); if (!inti) - return 2; /* busy */ + return SIGP_CC_BUSY; spin_lock(&fi->lock); if (cpu_addr < KVM_MAX_VCPUS) li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 1; /* incorrect state */ - *reg &= SIGP_STAT_INCORRECT_STATE; + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + rc = SIGP_CC_STATUS_STORED; kfree(inti); goto out_fi; } @@ -257,8 +235,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, spin_lock_bh(&li->lock); /* cpu must be in stopped state */ if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { - rc = 1; /* incorrect state */ - *reg &= SIGP_STAT_INCORRECT_STATE; + *reg &= 0xffffffff00000000UL; + *reg |= SIGP_STATUS_INCORRECT_STATE; + rc = SIGP_CC_STATUS_STORED; kfree(inti); goto out_li; } @@ -270,7 +249,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, atomic_set(&li->active, 1); if (waitqueue_active(&li->wq)) wake_up_interruptible(&li->wq); - rc = 0; /* order accepted */ + rc = SIGP_CC_ORDER_CODE_ACCEPTED; VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address); out_li: @@ -287,21 +266,21 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); if (fi->local_int[cpu_addr] == NULL) - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; else { if (atomic_read(fi->local_int[cpu_addr]->cpuflags) & CPUSTAT_RUNNING) { /* running */ - rc = 1; + rc = SIGP_CC_ORDER_CODE_ACCEPTED; } else { /* not running */ *reg &= 0xffffffff00000000UL; - *reg |= SIGP_STAT_NOT_RUNNING; - rc = 0; + *reg |= SIGP_STATUS_NOT_RUNNING; + rc = SIGP_CC_STATUS_STORED; } } spin_unlock(&fi->lock); @@ -314,23 +293,23 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr) { - int rc = 0; struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; struct kvm_s390_local_interrupt *li; + int rc = SIGP_CC_ORDER_CODE_ACCEPTED; if (cpu_addr >= KVM_MAX_VCPUS) - return 3; /* not operational */ + return SIGP_CC_NOT_OPERATIONAL; spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; if (li == NULL) { - rc = 3; /* not operational */ + rc = SIGP_CC_NOT_OPERATIONAL; goto out; } spin_lock_bh(&li->lock); if (li->action_bits & ACTION_STOP_ON_STOP) - rc = 2; /* busy */ + rc = SIGP_CC_BUSY; else VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace", cpu_addr); @@ -375,7 +354,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) vcpu->stat.instruction_sigp_external_call++; rc = __sigp_external_call(vcpu, cpu_addr); break; - case SIGP_EMERGENCY: + case SIGP_EMERGENCY_SIGNAL: vcpu->stat.instruction_sigp_emergency++; rc = __sigp_emergency(vcpu, cpu_addr); break; @@ -383,12 +362,12 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) vcpu->stat.instruction_sigp_stop++; rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP); break; - case SIGP_STOP_STORE_STATUS: + case SIGP_STOP_AND_STORE_STATUS: vcpu->stat.instruction_sigp_stop++; rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP | ACTION_STOP_ON_STOP); break; - case SIGP_SET_ARCH: + case SIGP_SET_ARCHITECTURE: vcpu->stat.instruction_sigp_arch++; rc = __sigp_set_arch(vcpu, parameter); break; @@ -405,7 +384,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) case SIGP_RESTART: vcpu->stat.instruction_sigp_restart++; rc = __sigp_restart(vcpu, cpu_addr); - if (rc == 2) /* busy */ + if (rc == SIGP_CC_BUSY) break; /* user space must know about restart */ default: diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 9f1f71e..42d0cf8 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -1,7 +1,7 @@ /* * Precise Delay Loops for S390 * - * Copyright IBM Corp. 1999,2008 + * Copyright IBM Corp. 1999, 2008 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * Heiko Carstens <heiko.carstens@de.ibm.com>, */ @@ -12,8 +12,8 @@ #include <linux/module.h> #include <linux/irqflags.h> #include <linux/interrupt.h> +#include <asm/vtimer.h> #include <asm/div64.h> -#include <asm/timer.h> void __delay(unsigned long loops) { diff --git a/arch/s390/lib/div64.c b/arch/s390/lib/div64.c index d9e62c0..261152f 100644 --- a/arch/s390/lib/div64.c +++ b/arch/s390/lib/div64.c @@ -1,9 +1,7 @@ /* - * arch/s390/lib/div64.c - * * __div64_32 implementation for 31 bit. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), */ diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 093eb69..f709983 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -1,8 +1,7 @@ /* - * arch/s390/lib/spinlock.c * Out of line spinlock code. * - * Copyright (C) IBM Corp. 2004, 2006 + * Copyright IBM Corp. 2004, 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index 4143b7c..846ec64 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -1,9 +1,8 @@ /* - * arch/s390/lib/string.c * Optimized string functions * * S390 version - * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2004 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com) */ diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h index 1d2536c..315dbe0 100644 --- a/arch/s390/lib/uaccess.h +++ b/arch/s390/lib/uaccess.h @@ -1,6 +1,4 @@ /* - * arch/s390/uaccess.h - * * Copyright IBM Corp. 2007 * */ diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c index 58a75a8..2443ae4 100644 --- a/arch/s390/lib/uaccess_mvcos.c +++ b/arch/s390/lib/uaccess_mvcos.c @@ -1,9 +1,7 @@ /* - * arch/s390/lib/uaccess_mvcos.c - * * Optimized user space space access functions based on mvcos. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Gerald Schaefer (gerald.schaefer@de.ibm.com) */ diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 342ae35..60ee2b8 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -1,6 +1,4 @@ /* - * arch/s390/lib/uaccess_pt.c - * * User access functions based on page table walks for enhanced * system layout without hardware support. * diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index 57e9429..6fbd063 100644 --- a/arch/s390/lib/uaccess_std.c +++ b/arch/s390/lib/uaccess_std.c @@ -1,10 +1,8 @@ /* - * arch/s390/lib/uaccess_std.c - * * Standard user space access functions based on mvcp/mvcs and doing * interesting things in the secondary space mode. * - * Copyright (C) IBM Corp. 2006 + * Copyright IBM Corp. 2006 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * Gerald Schaefer (gerald.schaefer@de.ibm.com) */ diff --git a/arch/s390/math-emu/math.c b/arch/s390/math-emu/math.c index cd4e9c1..58bff54 100644 --- a/arch/s390/math-emu/math.c +++ b/arch/s390/math-emu/math.c @@ -1,8 +1,6 @@ /* - * arch/s390/math-emu/math.c - * * S390 version - * Copyright (C) 1999-2001 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999, 2001 * Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com), * * 'math.c' emulates IEEE instructions on a S390 processor diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 1f1dba9..479e942 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -1,7 +1,7 @@ /* * Collaborative memory management interface. * - * Copyright IBM Corp 2003,2010 + * Copyright IBM Corp 2003, 2010 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>, * */ diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 075ddad..519bba7 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -1,10 +1,9 @@ /* - * File...........: arch/s390/mm/extmem.c * Author(s)......: Carsten Otte <cotte@de.ibm.com> * Rob M van der Heij <rvdheij@nl.ibm.com> * Steven Shultz <shultzss@us.ibm.com> * Bugreports.to..: <Linux390@de.ibm.com> - * (C) IBM Corporation 2002-2004 + * Copyright IBM Corp. 2002, 2004 */ #define KMSG_COMPONENT "extmem" diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 72cec9e..6a12d1b 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -1,8 +1,6 @@ /* - * arch/s390/mm/fault.c - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com) * Ulrich Weigand (uweigand@de.ibm.com) * diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 900de2b..532525e 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -1,7 +1,7 @@ /* * IBM System z Huge TLB Page Support for Kernel. * - * Copyright 2007 IBM Corp. + * Copyright IBM Corp. 2007 * Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com> */ diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 2bea060..6adbc08 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -1,8 +1,6 @@ /* - * arch/s390/mm/init.c - * * S390 version - * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 1999 * Author(s): Hartmut Penner (hp@de.ibm.com) * * Derived from "arch/i386/mm/init.c" diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 2857c48..5733842 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -1,6 +1,4 @@ /* - * linux/arch/s390/mm/mmap.c - * * flexible mmap layout support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a3db5a3..1cab221 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2007,2011 + * Copyright IBM Corp. 2007, 2011 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 71ae20d..6f896e7 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -1,6 +1,4 @@ /* - * arch/s390/mm/vmem.c - * * Copyright IBM Corp. 2006 * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com> */ diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c index bc4b84a..c82f62f 100644 --- a/arch/s390/oprofile/backtrace.c +++ b/arch/s390/oprofile/backtrace.c @@ -1,8 +1,6 @@ -/** - * arch/s390/oprofile/backtrace.c - * +/* * S390 Version - * Copyright (C) 2005 IBM Corporation, IBM Deutschland Entwicklung GmbH. + * Copyright IBM Corp. 2005 * Author(s): Andreas Krebbel <Andreas.Krebbel@de.ibm.com> */ diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c index a4a89fa..0cb385d 100644 --- a/arch/s390/oprofile/hwsampler.c +++ b/arch/s390/oprofile/hwsampler.c @@ -1,6 +1,4 @@ -/** - * arch/s390/oprofile/hwsampler.c - * +/* * Copyright IBM Corp. 2010 * Author: Heinz Graalfs <graalfs@de.ibm.com> */ diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 2297be4..a1e9d69 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -1,8 +1,6 @@ -/** - * arch/s390/oprofile/init.c - * +/* * S390 Version - * Copyright (C) 2002-2011 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright IBM Corp. 2002, 2011 * Author(s): Thomas Spatzier (tspat@de.ibm.com) * Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com) * Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com) diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h index 1a8d3ca..61b2531 100644 --- a/arch/s390/oprofile/op_counter.h +++ b/arch/s390/oprofile/op_counter.h @@ -1,7 +1,5 @@ -/** - * arch/s390/oprofile/op_counter.h - * - * Copyright (C) 2011 IBM Deutschland Entwicklung GmbH, IBM Corporation +/* + * Copyright IBM Corp. 2011 * Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com) * * @remark Copyright 2011 OProfile authors diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 31d9db7..a24595d 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -60,6 +60,7 @@ config SUPERH32 config SUPERH64 def_bool ARCH = "sh64" + select KALLSYMS config ARCH_DEFCONFIG string diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index 1f56b35..7048c03 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -44,6 +44,8 @@ config SH_7721_SOLUTION_ENGINE config SH_7722_SOLUTION_ENGINE bool "SolutionEngine7722" select SOLUTION_ENGINE + select GENERIC_IRQ_CHIP + select IRQ_DOMAIN depends on CPU_SUBTYPE_SH7722 help Select 7722 SolutionEngine if configuring for a Hitachi SH772 @@ -80,6 +82,8 @@ config SH_7780_SOLUTION_ENGINE config SH_7343_SOLUTION_ENGINE bool "SolutionEngine7343" select SOLUTION_ENGINE + select GENERIC_IRQ_CHIP + select IRQ_DOMAIN depends on CPU_SUBTYPE_SH7343 help Select 7343 SolutionEngine if configuring for a Hitachi @@ -295,6 +299,7 @@ config SH_X3PROTO bool "SH-X3 Prototype board" depends on CPU_SUBTYPE_SHX3 select NO_IOPORT if !PCI + select IRQ_DOMAIN config SH_MAGIC_PANEL_R2 bool "Magic Panel R2" diff --git a/arch/sh/boards/board-polaris.c b/arch/sh/boards/board-polaris.c index 37d03c0..0978ae2 100644 --- a/arch/sh/boards/board-polaris.c +++ b/arch/sh/boards/board-polaris.c @@ -1,5 +1,5 @@ /* - * June 2006 steve.glendinning@smsc.com + * June 2006 Steve Glendinning <steve.glendinning@shawell.net> * * Polaris-specific resource declaration * diff --git a/arch/sh/boards/mach-dreamcast/irq.c b/arch/sh/boards/mach-dreamcast/irq.c index f63d323..2789647 100644 --- a/arch/sh/boards/mach-dreamcast/irq.c +++ b/arch/sh/boards/mach-dreamcast/irq.c @@ -8,10 +8,11 @@ * This file is part of the LinuxDC project (www.linuxdc.org) * Released under the terms of the GNU GPL v2.0 */ - #include <linux/irq.h> #include <linux/io.h> -#include <asm/irq.h> +#include <linux/irq.h> +#include <linux/export.h> +#include <linux/err.h> #include <mach/sysasic.h> /* @@ -141,26 +142,15 @@ int systemasic_irq_demux(int irq) void systemasic_irq_init(void) { - int i, nid = cpu_to_node(boot_cpu_data); - - /* Assign all virtual IRQs to the System ASIC int. handler */ - for (i = HW_EVENT_IRQ_BASE; i < HW_EVENT_IRQ_MAX; i++) { - unsigned int irq; - - irq = create_irq_nr(i, nid); - if (unlikely(irq == 0)) { - pr_err("%s: failed hooking irq %d for systemasic\n", - __func__, i); - return; - } + int irq_base, i; - if (unlikely(irq != i)) { - pr_err("%s: got irq %d but wanted %d, bailing.\n", - __func__, irq, i); - destroy_irq(irq); - return; - } + irq_base = irq_alloc_descs(HW_EVENT_IRQ_BASE, HW_EVENT_IRQ_BASE, + HW_EVENT_IRQ_MAX - HW_EVENT_IRQ_BASE, -1); + if (IS_ERR_VALUE(irq_base)) { + pr_err("%s: failed hooking irqs\n", __func__); + return; + } + for (i = HW_EVENT_IRQ_BASE; i < HW_EVENT_IRQ_MAX; i++) irq_set_chip_and_handler(i, &systemasic_int, handle_level_irq); - } } diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c index fd45ffc..7646bf0 100644 --- a/arch/sh/boards/mach-se/7343/irq.c +++ b/arch/sh/boards/mach-se/7343/irq.c @@ -1,86 +1,129 @@ /* - * linux/arch/sh/boards/se/7343/irq.c + * Hitachi UL SolutionEngine 7343 FPGA IRQ Support. * * Copyright (C) 2008 Yoshihiro Shimoda + * Copyright (C) 2012 Paul Mundt * - * Based on linux/arch/sh/boards/se/7722/irq.c + * Based on linux/arch/sh/boards/se/7343/irq.c * Copyright (C) 2007 Nobuhiro Iwamatsu * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. */ +#define DRV_NAME "SE7343-FPGA" +#define pr_fmt(fmt) DRV_NAME ": " fmt + +#define irq_reg_readl ioread16 +#define irq_reg_writel iowrite16 + #include <linux/init.h> #include <linux/irq.h> #include <linux/interrupt.h> +#include <linux/irqdomain.h> #include <linux/io.h> +#include <asm/sizes.h> #include <mach-se/mach/se7343.h> -unsigned int se7343_fpga_irq[SE7343_FPGA_IRQ_NR] = { 0, }; +#define PA_CPLD_BASE_ADDR 0x11400000 +#define PA_CPLD_ST_REG 0x08 /* CPLD Interrupt status register */ +#define PA_CPLD_IMSK_REG 0x0a /* CPLD Interrupt mask register */ -static void disable_se7343_irq(struct irq_data *data) -{ - unsigned int bit = (unsigned int)irq_data_get_irq_chip_data(data); - __raw_writew(__raw_readw(PA_CPLD_IMSK) | 1 << bit, PA_CPLD_IMSK); -} +static void __iomem *se7343_irq_regs; +struct irq_domain *se7343_irq_domain; -static void enable_se7343_irq(struct irq_data *data) +static void se7343_irq_demux(unsigned int irq, struct irq_desc *desc) { - unsigned int bit = (unsigned int)irq_data_get_irq_chip_data(data); - __raw_writew(__raw_readw(PA_CPLD_IMSK) & ~(1 << bit), PA_CPLD_IMSK); -} + struct irq_data *data = irq_get_irq_data(irq); + struct irq_chip *chip = irq_data_get_irq_chip(data); + unsigned long mask; + int bit; -static struct irq_chip se7343_irq_chip __read_mostly = { - .name = "SE7343-FPGA", - .irq_mask = disable_se7343_irq, - .irq_unmask = enable_se7343_irq, -}; + chip->irq_mask_ack(data); -static void se7343_irq_demux(unsigned int irq, struct irq_desc *desc) + mask = ioread16(se7343_irq_regs + PA_CPLD_ST_REG); + + for_each_set_bit(bit, &mask, SE7343_FPGA_IRQ_NR) + generic_handle_irq(irq_linear_revmap(se7343_irq_domain, bit)); + + chip->irq_unmask(data); +} + +static void __init se7343_domain_init(void) { - unsigned short intv = __raw_readw(PA_CPLD_ST); - unsigned int ext_irq = 0; + int i; - intv &= (1 << SE7343_FPGA_IRQ_NR) - 1; + se7343_irq_domain = irq_domain_add_linear(NULL, SE7343_FPGA_IRQ_NR, + &irq_domain_simple_ops, NULL); + if (unlikely(!se7343_irq_domain)) { + printk("Failed to get IRQ domain\n"); + return; + } - for (; intv; intv >>= 1, ext_irq++) { - if (!(intv & 1)) - continue; + for (i = 0; i < SE7343_FPGA_IRQ_NR; i++) { + int irq = irq_create_mapping(se7343_irq_domain, i); - generic_handle_irq(se7343_fpga_irq[ext_irq]); + if (unlikely(irq == 0)) { + printk("Failed to allocate IRQ %d\n", i); + return; + } } } -/* - * Initialize IRQ setting - */ -void __init init_7343se_IRQ(void) +static void __init se7343_gc_init(void) { - int i, irq; + struct irq_chip_generic *gc; + struct irq_chip_type *ct; + unsigned int irq_base; - __raw_writew(0, PA_CPLD_IMSK); /* disable all irqs */ - __raw_writew(0x2000, 0xb03fffec); /* mrshpc irq enable */ + irq_base = irq_linear_revmap(se7343_irq_domain, 0); - for (i = 0; i < SE7343_FPGA_IRQ_NR; i++) { - irq = create_irq(); - if (irq < 0) - return; - se7343_fpga_irq[i] = irq; + gc = irq_alloc_generic_chip(DRV_NAME, 1, irq_base, se7343_irq_regs, + handle_level_irq); + if (unlikely(!gc)) + return; - irq_set_chip_and_handler_name(se7343_fpga_irq[i], - &se7343_irq_chip, - handle_level_irq, - "level"); + ct = gc->chip_types; + ct->chip.irq_mask = irq_gc_mask_set_bit; + ct->chip.irq_unmask = irq_gc_mask_clr_bit; - irq_set_chip_data(se7343_fpga_irq[i], (void *)i); - } + ct->regs.mask = PA_CPLD_IMSK_REG; + + irq_setup_generic_chip(gc, IRQ_MSK(SE7343_FPGA_IRQ_NR), + IRQ_GC_INIT_MASK_CACHE, + IRQ_NOREQUEST | IRQ_NOPROBE, 0); irq_set_chained_handler(IRQ0_IRQ, se7343_irq_demux); irq_set_irq_type(IRQ0_IRQ, IRQ_TYPE_LEVEL_LOW); + irq_set_chained_handler(IRQ1_IRQ, se7343_irq_demux); irq_set_irq_type(IRQ1_IRQ, IRQ_TYPE_LEVEL_LOW); + irq_set_chained_handler(IRQ4_IRQ, se7343_irq_demux); irq_set_irq_type(IRQ4_IRQ, IRQ_TYPE_LEVEL_LOW); + irq_set_chained_handler(IRQ5_IRQ, se7343_irq_demux); irq_set_irq_type(IRQ5_IRQ, IRQ_TYPE_LEVEL_LOW); } + +/* + * Initialize IRQ setting + */ +void __init init_7343se_IRQ(void) +{ + se7343_irq_regs = ioremap(PA_CPLD_BASE_ADDR, SZ_16); + if (unlikely(!se7343_irq_regs)) { + pr_err("Failed to remap CPLD\n"); + return; + } + + /* + * All FPGA IRQs disabled by default + */ + iowrite16(0, se7343_irq_regs + PA_CPLD_IMSK_REG); + + __raw_writew(0x2000, 0xb03fffec); /* mrshpc irq enable */ + + se7343_domain_init(); + se7343_gc_init(); +} diff --git a/arch/sh/boards/mach-se/7343/setup.c b/arch/sh/boards/mach-se/7343/setup.c index d2370af..8ce4f2a 100644 --- a/arch/sh/boards/mach-se/7343/setup.c +++ b/arch/sh/boards/mach-se/7343/setup.c @@ -5,6 +5,7 @@ #include <linux/serial_reg.h> #include <linux/usb/isp116x.h> #include <linux/delay.h> +#include <linux/irqdomain.h> #include <asm/machvec.h> #include <mach-se/mach/se7343.h> #include <asm/heartbeat.h> @@ -145,11 +146,12 @@ static struct platform_device *sh7343se_platform_devices[] __initdata = { static int __init sh7343se_devices_setup(void) { /* Wire-up dynamic vectors */ - serial_platform_data[0].irq = se7343_fpga_irq[SE7343_FPGA_IRQ_UARTA]; - serial_platform_data[1].irq = se7343_fpga_irq[SE7343_FPGA_IRQ_UARTB]; - + serial_platform_data[0].irq = irq_find_mapping(se7343_irq_domain, + SE7343_FPGA_IRQ_UARTA); + serial_platform_data[1].irq = irq_find_mapping(se7343_irq_domain, + SE7343_FPGA_IRQ_UARTB); usb_resources[2].start = usb_resources[2].end = - se7343_fpga_irq[SE7343_FPGA_IRQ_USB]; + irq_find_mapping(se7343_irq_domain, SE7343_FPGA_IRQ_USB); return platform_add_devices(sh7343se_platform_devices, ARRAY_SIZE(sh7343se_platform_devices)); diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c index aac92f2..f5e2af1b 100644 --- a/arch/sh/boards/mach-se/7722/irq.c +++ b/arch/sh/boards/mach-se/7722/irq.c @@ -1,79 +1,96 @@ /* - * linux/arch/sh/boards/se/7722/irq.c + * Hitachi UL SolutionEngine 7722 FPGA IRQ Support. * * Copyright (C) 2007 Nobuhiro Iwamatsu - * - * Hitachi UL SolutionEngine 7722 Support. + * Copyright (C) 2012 Paul Mundt * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive * for more details. */ +#define DRV_NAME "SE7722-FPGA" +#define pr_fmt(fmt) DRV_NAME ": " fmt + +#define irq_reg_readl ioread16 +#define irq_reg_writel iowrite16 + #include <linux/init.h> #include <linux/irq.h> #include <linux/interrupt.h> -#include <asm/irq.h> -#include <asm/io.h> +#include <linux/irqdomain.h> +#include <linux/io.h> +#include <linux/err.h> +#include <asm/sizes.h> #include <mach-se/mach/se7722.h> -unsigned int se7722_fpga_irq[SE7722_FPGA_IRQ_NR] = { 0, }; +#define IRQ01_BASE_ADDR 0x11800000 +#define IRQ01_MODE_REG 0 +#define IRQ01_STS_REG 4 +#define IRQ01_MASK_REG 8 -static void disable_se7722_irq(struct irq_data *data) -{ - unsigned int bit = (unsigned int)irq_data_get_irq_chip_data(data); - __raw_writew(__raw_readw(IRQ01_MASK) | 1 << bit, IRQ01_MASK); -} +static void __iomem *se7722_irq_regs; +struct irq_domain *se7722_irq_domain; -static void enable_se7722_irq(struct irq_data *data) +static void se7722_irq_demux(unsigned int irq, struct irq_desc *desc) { - unsigned int bit = (unsigned int)irq_data_get_irq_chip_data(data); - __raw_writew(__raw_readw(IRQ01_MASK) & ~(1 << bit), IRQ01_MASK); -} + struct irq_data *data = irq_get_irq_data(irq); + struct irq_chip *chip = irq_data_get_irq_chip(data); + unsigned long mask; + int bit; -static struct irq_chip se7722_irq_chip __read_mostly = { - .name = "SE7722-FPGA", - .irq_mask = disable_se7722_irq, - .irq_unmask = enable_se7722_irq, -}; + chip->irq_mask_ack(data); -static void se7722_irq_demux(unsigned int irq, struct irq_desc *desc) + mask = ioread16(se7722_irq_regs + IRQ01_STS_REG); + + for_each_set_bit(bit, &mask, SE7722_FPGA_IRQ_NR) + generic_handle_irq(irq_linear_revmap(se7722_irq_domain, bit)); + + chip->irq_unmask(data); +} + +static void __init se7722_domain_init(void) { - unsigned short intv = __raw_readw(IRQ01_STS); - unsigned int ext_irq = 0; + int i; - intv &= (1 << SE7722_FPGA_IRQ_NR) - 1; + se7722_irq_domain = irq_domain_add_linear(NULL, SE7722_FPGA_IRQ_NR, + &irq_domain_simple_ops, NULL); + if (unlikely(!se7722_irq_domain)) { + printk("Failed to get IRQ domain\n"); + return; + } - for (; intv; intv >>= 1, ext_irq++) { - if (!(intv & 1)) - continue; + for (i = 0; i < SE7722_FPGA_IRQ_NR; i++) { + int irq = irq_create_mapping(se7722_irq_domain, i); - generic_handle_irq(se7722_fpga_irq[ext_irq]); + if (unlikely(irq == 0)) { + printk("Failed to allocate IRQ %d\n", i); + return; + } } } -/* - * Initialize IRQ setting - */ -void __init init_se7722_IRQ(void) +static void __init se7722_gc_init(void) { - int i, irq; + struct irq_chip_generic *gc; + struct irq_chip_type *ct; + unsigned int irq_base; - __raw_writew(0, IRQ01_MASK); /* disable all irqs */ - __raw_writew(0x2000, 0xb03fffec); /* mrshpc irq enable */ + irq_base = irq_linear_revmap(se7722_irq_domain, 0); - for (i = 0; i < SE7722_FPGA_IRQ_NR; i++) { - irq = create_irq(); - if (irq < 0) - return; - se7722_fpga_irq[i] = irq; + gc = irq_alloc_generic_chip(DRV_NAME, 1, irq_base, se7722_irq_regs, + handle_level_irq); + if (unlikely(!gc)) + return; - irq_set_chip_and_handler_name(se7722_fpga_irq[i], - &se7722_irq_chip, - handle_level_irq, - "level"); + ct = gc->chip_types; + ct->chip.irq_mask = irq_gc_mask_set_bit; + ct->chip.irq_unmask = irq_gc_mask_clr_bit; - irq_set_chip_data(se7722_fpga_irq[i], (void *)i); - } + ct->regs.mask = IRQ01_MASK_REG; + + irq_setup_generic_chip(gc, IRQ_MSK(SE7722_FPGA_IRQ_NR), + IRQ_GC_INIT_MASK_CACHE, + IRQ_NOREQUEST | IRQ_NOPROBE, 0); irq_set_chained_handler(IRQ0_IRQ, se7722_irq_demux); irq_set_irq_type(IRQ0_IRQ, IRQ_TYPE_LEVEL_LOW); @@ -81,3 +98,25 @@ void __init init_se7722_IRQ(void) irq_set_chained_handler(IRQ1_IRQ, se7722_irq_demux); irq_set_irq_type(IRQ1_IRQ, IRQ_TYPE_LEVEL_LOW); } + +/* + * Initialize FPGA IRQs + */ +void __init init_se7722_IRQ(void) +{ + se7722_irq_regs = ioremap(IRQ01_BASE_ADDR, SZ_16); + if (unlikely(!se7722_irq_regs)) { + printk("Failed to remap IRQ01 regs\n"); + return; + } + + /* + * All FPGA IRQs disabled by default + */ + iowrite16(0, se7722_irq_regs + IRQ01_MASK_REG); + + __raw_writew(0x2000, 0xb03fffec); /* mrshpc irq enable */ + + se7722_domain_init(); + se7722_gc_init(); +} diff --git a/arch/sh/boards/mach-se/7722/setup.c b/arch/sh/boards/mach-se/7722/setup.c index 8f7f055..e04e2bc 100644 --- a/arch/sh/boards/mach-se/7722/setup.c +++ b/arch/sh/boards/mach-se/7722/setup.c @@ -2,6 +2,7 @@ * linux/arch/sh/boards/se/7722/setup.c * * Copyright (C) 2007 Nobuhiro Iwamatsu + * Copyright (C) 2012 Paul Mundt * * Hitachi UL SolutionEngine 7722 Support. * @@ -15,6 +16,7 @@ #include <linux/ata_platform.h> #include <linux/input.h> #include <linux/input/sh_keysc.h> +#include <linux/irqdomain.h> #include <linux/smc91x.h> #include <linux/sh_intc.h> #include <mach-se/mach/se7722.h> @@ -143,10 +145,10 @@ static int __init se7722_devices_setup(void) /* Wire-up dynamic vectors */ cf_ide_resources[2].start = cf_ide_resources[2].end = - se7722_fpga_irq[SE7722_FPGA_IRQ_MRSHPC0]; + irq_find_mapping(se7722_irq_domain, SE7722_FPGA_IRQ_MRSHPC0); smc91x_eth_resources[1].start = smc91x_eth_resources[1].end = - se7722_fpga_irq[SE7722_FPGA_IRQ_SMC]; + irq_find_mapping(se7722_irq_domain, SE7722_FPGA_IRQ_SMC); return platform_add_devices(se7722_devices, ARRAY_SIZE(se7722_devices)); } diff --git a/arch/sh/boards/mach-se/7724/irq.c b/arch/sh/boards/mach-se/7724/irq.c index c6342ce..5d1d3ec 100644 --- a/arch/sh/boards/mach-se/7724/irq.c +++ b/arch/sh/boards/mach-se/7724/irq.c @@ -17,8 +17,10 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/interrupt.h> -#include <asm/irq.h> -#include <asm/io.h> +#include <linux/export.h> +#include <linux/topology.h> +#include <linux/io.h> +#include <linux/err.h> #include <mach-se/mach/se7724.h> struct fpga_irq { @@ -111,7 +113,7 @@ static void se7724_irq_demux(unsigned int irq, struct irq_desc *desc) */ void __init init_se7724_IRQ(void) { - int i, nid = cpu_to_node(boot_cpu_data); + int irq_base, i; __raw_writew(0xffff, IRQ0_MR); /* mask all */ __raw_writew(0xffff, IRQ1_MR); /* mask all */ @@ -121,28 +123,16 @@ void __init init_se7724_IRQ(void) __raw_writew(0x0000, IRQ2_SR); /* clear irq */ __raw_writew(0x002a, IRQ_MODE); /* set irq type */ - for (i = 0; i < SE7724_FPGA_IRQ_NR; i++) { - int irq, wanted; - - wanted = SE7724_FPGA_IRQ_BASE + i; - - irq = create_irq_nr(wanted, nid); - if (unlikely(irq == 0)) { - pr_err("%s: failed hooking irq %d for FPGA\n", - __func__, wanted); - return; - } - - if (unlikely(irq != wanted)) { - pr_err("%s: got irq %d but wanted %d, bailing.\n", - __func__, irq, wanted); - destroy_irq(irq); - return; - } + irq_base = irq_alloc_descs(SE7724_FPGA_IRQ_BASE, SE7724_FPGA_IRQ_BASE, + SE7724_FPGA_IRQ_NR, numa_node_id()); + if (IS_ERR_VALUE(irq_base)) { + pr_err("%s: failed hooking irqs for FPGA\n", __func__); + return; + } - irq_set_chip_and_handler_name(irq, &se7724_irq_chip, + for (i = 0; i < SE7724_FPGA_IRQ_NR; i++) + irq_set_chip_and_handler_name(irq_base + i, &se7724_irq_chip, handle_level_irq, "level"); - } irq_set_chained_handler(IRQ0_IRQ, se7724_irq_demux); irq_set_irq_type(IRQ0_IRQ, IRQ_TYPE_LEVEL_LOW); diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c index f33b2b5..3ea65e9 100644 --- a/arch/sh/boards/mach-x3proto/gpio.c +++ b/arch/sh/boards/mach-x3proto/gpio.c @@ -3,7 +3,7 @@ * * Renesas SH-X3 Prototype Baseboard GPIO Support. * - * Copyright (C) 2010 Paul Mundt + * Copyright (C) 2010 - 2012 Paul Mundt * * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive @@ -17,6 +17,7 @@ #include <linux/irq.h> #include <linux/kernel.h> #include <linux/spinlock.h> +#include <linux/irqdomain.h> #include <linux/io.h> #include <mach/ilsel.h> #include <mach/hardware.h> @@ -26,7 +27,7 @@ #define KEYDETR 0xb81c0004 static DEFINE_SPINLOCK(x3proto_gpio_lock); -static unsigned int x3proto_gpio_irq_map[NR_BASEBOARD_GPIOS] = { 0, }; +static struct irq_domain *x3proto_irq_domain; static int x3proto_gpio_direction_input(struct gpio_chip *chip, unsigned gpio) { @@ -49,7 +50,14 @@ static int x3proto_gpio_get(struct gpio_chip *chip, unsigned gpio) static int x3proto_gpio_to_irq(struct gpio_chip *chip, unsigned gpio) { - return x3proto_gpio_irq_map[gpio]; + int virq; + + if (gpio < chip->ngpio) + virq = irq_create_mapping(x3proto_irq_domain, gpio); + else + virq = -ENXIO; + + return virq; } static void x3proto_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) @@ -62,9 +70,8 @@ static void x3proto_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) chip->irq_mask_ack(data); mask = __raw_readw(KEYDETR); - for_each_set_bit(pin, &mask, NR_BASEBOARD_GPIOS) - generic_handle_irq(x3proto_gpio_to_irq(NULL, pin)); + generic_handle_irq(irq_linear_revmap(x3proto_irq_domain, pin)); chip->irq_unmask(data); } @@ -78,10 +85,23 @@ struct gpio_chip x3proto_gpio_chip = { .ngpio = NR_BASEBOARD_GPIOS, }; +static int x3proto_gpio_irq_map(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler_name(virq, &dummy_irq_chip, handle_simple_irq, + "gpio"); + + return 0; +} + +static struct irq_domain_ops x3proto_gpio_irq_ops = { + .map = x3proto_gpio_irq_map, + .xlate = irq_domain_xlate_twocell, +}; + int __init x3proto_gpio_setup(void) { - int ilsel; - int ret, i; + int ilsel, ret; ilsel = ilsel_enable(ILSEL_KEY); if (unlikely(ilsel < 0)) @@ -91,21 +111,10 @@ int __init x3proto_gpio_setup(void) if (unlikely(ret)) goto err_gpio; - for (i = 0; i < NR_BASEBOARD_GPIOS; i++) { - unsigned long flags; - int irq = create_irq(); - - if (unlikely(irq < 0)) { - ret = -EINVAL; - goto err_irq; - } - - spin_lock_irqsave(&x3proto_gpio_lock, flags); - x3proto_gpio_irq_map[i] = irq; - irq_set_chip_and_handler_name(irq, &dummy_irq_chip, - handle_simple_irq, "gpio"); - spin_unlock_irqrestore(&x3proto_gpio_lock, flags); - } + x3proto_irq_domain = irq_domain_add_linear(NULL, NR_BASEBOARD_GPIOS, + &x3proto_gpio_irq_ops, NULL); + if (unlikely(!x3proto_irq_domain)) + goto err_irq; pr_info("registering '%s' support, handling GPIOs %u -> %u, " "bound to IRQ %u\n", @@ -119,10 +128,6 @@ int __init x3proto_gpio_setup(void) return 0; err_irq: - for (; i >= 0; --i) - if (x3proto_gpio_irq_map[i]) - destroy_irq(x3proto_gpio_irq_map[i]); - ret = gpiochip_remove(&x3proto_gpio_chip); if (unlikely(ret)) pr_err("Failed deregistering GPIO\n"); diff --git a/arch/sh/cchips/hd6446x/hd64461.c b/arch/sh/cchips/hd6446x/hd64461.c index eb4ea4d..e973561 100644 --- a/arch/sh/cchips/hd6446x/hd64461.c +++ b/arch/sh/cchips/hd6446x/hd64461.c @@ -73,10 +73,7 @@ static void hd64461_irq_demux(unsigned int irq, struct irq_desc *desc) int __init setup_hd64461(void) { - int i, nid = cpu_to_node(boot_cpu_data); - - if (!MACH_HD64461) - return 0; + int irq_base, i; printk(KERN_INFO "HD64461 configured at 0x%x on irq %d(mapped into %d to %d)\n", @@ -89,28 +86,16 @@ int __init setup_hd64461(void) #endif __raw_writew(0xffff, HD64461_NIMR); - /* IRQ 80 -> 95 belongs to HD64461 */ - for (i = HD64461_IRQBASE; i < HD64461_IRQBASE + 16; i++) { - unsigned int irq; - - irq = create_irq_nr(i, nid); - if (unlikely(irq == 0)) { - pr_err("%s: failed hooking irq %d for HD64461\n", - __func__, i); - return -EBUSY; - } - - if (unlikely(irq != i)) { - pr_err("%s: got irq %d but wanted %d, bailing.\n", - __func__, irq, i); - destroy_irq(irq); - return -EINVAL; - } - - irq_set_chip_and_handler(i, &hd64461_irq_chip, - handle_level_irq); + irq_base = irq_alloc_descs(HD64461_IRQBASE, HD64461_IRQBASE, 16, -1); + if (IS_ERR_VALUE(irq_base)) { + pr_err("%s: failed hooking irqs for HD64461\n", __func__); + return irq_base; } + for (i = 0; i < 16; i++) + irq_set_chip_and_handler(irq_base + i, &hd64461_irq_chip, + handle_level_irq); + irq_set_chained_handler(CONFIG_HD64461_IRQ, hd64461_irq_demux); irq_set_irq_type(CONFIG_HD64461_IRQ, IRQ_TYPE_LEVEL_LOW); diff --git a/arch/sh/drivers/pci/fixups-dreamcast.c b/arch/sh/drivers/pci/fixups-dreamcast.c index edeea89..a5fe1b5 100644 --- a/arch/sh/drivers/pci/fixups-dreamcast.c +++ b/arch/sh/drivers/pci/fixups-dreamcast.c @@ -28,7 +28,7 @@ #include <asm/irq.h> #include <mach/pci.h> -static void __init gapspci_fixup_resources(struct pci_dev *dev) +static void __devinit gapspci_fixup_resources(struct pci_dev *dev) { struct pci_channel *p = dev->sysdata; diff --git a/arch/sh/drivers/pci/fixups-sdk7786.c b/arch/sh/drivers/pci/fixups-sdk7786.c index 0e18ee3..36eb6fc 100644 --- a/arch/sh/drivers/pci/fixups-sdk7786.c +++ b/arch/sh/drivers/pci/fixups-sdk7786.c @@ -23,9 +23,9 @@ * Misconfigurations can be detected through the FPGA via the slot * resistors to determine card presence. Hotplug remains unsupported. */ -static unsigned int slot4en __devinitdata; +static unsigned int slot4en __initdata; -char *__devinit pcibios_setup(char *str) +char *__init pcibios_setup(char *str) { if (strcmp(str, "slot4en") == 0) { slot4en = 1; diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index 9d10a3c..40db2d0 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -59,7 +59,7 @@ static void __devinit pcibios_scanbus(struct pci_channel *hose) need_domain_info = need_domain_info || hose->index; hose->need_domain_info = need_domain_info; if (bus) { - next_busno = bus->subordinate + 1; + next_busno = bus->busn_res.end + 1; /* Don't allow 8-bit bus number overflow inside the hose - reserve some space for bridges. */ if (next_busno > 224) { @@ -197,11 +197,6 @@ void __init pcibios_update_irq(struct pci_dev *dev, int irq) pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq); } -char * __devinit __weak pcibios_setup(char *str) -{ - return str; -} - static void __init pcibios_bus_report_status_early(struct pci_channel *hose, int top_bus, int current_bus, diff --git a/arch/sh/include/asm/bug.h b/arch/sh/include/asm/bug.h index 2b87d86..dcf2780 100644 --- a/arch/sh/include/asm/bug.h +++ b/arch/sh/include/asm/bug.h @@ -110,6 +110,10 @@ do { \ #include <asm-generic/bug.h> struct pt_regs; + +/* arch/sh/kernel/traps.c */ extern void die(const char *str, struct pt_regs *regs, long err) __attribute__ ((noreturn)); +extern void die_if_kernel(const char *str, struct pt_regs *regs, long err); +extern void die_if_no_fixup(const char *str, struct pt_regs *regs, long err); #endif /* __ASM_SH_BUG_H */ diff --git a/arch/sh/include/asm/kdebug.h b/arch/sh/include/asm/kdebug.h index a6201f1..8d6a831 100644 --- a/arch/sh/include/asm/kdebug.h +++ b/arch/sh/include/asm/kdebug.h @@ -10,6 +10,8 @@ enum die_val { DIE_SSTEP, }; +/* arch/sh/kernel/dumpstack.c */ extern void printk_address(unsigned long address, int reliable); +extern void dump_mem(const char *str, unsigned long bottom, unsigned long top); #endif /* __ASM_SH_KDEBUG_H */ diff --git a/arch/sh/include/mach-se/mach/se7343.h b/arch/sh/include/mach-se/mach/se7343.h index 50b5d57..542521c 100644 --- a/arch/sh/include/mach-se/mach/se7343.h +++ b/arch/sh/include/mach-se/mach/se7343.h @@ -50,9 +50,6 @@ #define PA_LED 0xb0C00000 /* LED */ #define LED_SHIFT 0 #define PA_DIPSW 0xb0900000 /* Dip switch 31 */ -#define PA_CPLD_MODESET 0xb1400004 /* CPLD Mode set register */ -#define PA_CPLD_ST 0xb1400008 /* CPLD Interrupt status register */ -#define PA_CPLD_IMSK 0xb140000a /* CPLD Interrupt mask register */ /* Area 5 */ #define PA_EXT5 0x14000000 #define PA_EXT5_SIZE 0x04000000 @@ -135,8 +132,10 @@ #define SE7343_FPGA_IRQ_NR 12 +struct irq_domain; + /* arch/sh/boards/se/7343/irq.c */ -extern unsigned int se7343_fpga_irq[]; +extern struct irq_domain *se7343_irq_domain; void init_7343se_IRQ(void); diff --git a/arch/sh/include/mach-se/mach/se7722.h b/arch/sh/include/mach-se/mach/se7722.h index 201081e..637e7ac 100644 --- a/arch/sh/include/mach-se/mach/se7722.h +++ b/arch/sh/include/mach-se/mach/se7722.h @@ -81,12 +81,6 @@ #define IRQ0_IRQ evt2irq(0x600) #define IRQ1_IRQ evt2irq(0x620) -#define IRQ01_MODE 0xb1800000 -#define IRQ01_STS 0xb1800004 -#define IRQ01_MASK 0xb1800008 - -/* Bits in IRQ01_* registers */ - #define SE7722_FPGA_IRQ_USB 0 /* IRQ0 */ #define SE7722_FPGA_IRQ_SMC 1 /* IRQ0 */ #define SE7722_FPGA_IRQ_MRSHPC0 2 /* IRQ1 */ @@ -95,8 +89,10 @@ #define SE7722_FPGA_IRQ_MRSHPC3 5 /* IRQ1 */ #define SE7722_FPGA_IRQ_NR 6 +struct irq_domain; + /* arch/sh/boards/se/7722/irq.c */ -extern unsigned int se7722_fpga_irq[]; +extern struct irq_domain *se7722_irq_domain; void init_se7722_IRQ(void); diff --git a/arch/sh/kernel/cpu/sh5/unwind.c b/arch/sh/kernel/cpu/sh5/unwind.c index b205b25..10aed41 100644 --- a/arch/sh/kernel/cpu/sh5/unwind.c +++ b/arch/sh/kernel/cpu/sh5/unwind.c @@ -16,6 +16,8 @@ #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/io.h> +#include <asm/unwinder.h> +#include <asm/stacktrace.h> static u8 regcache[63]; @@ -199,8 +201,11 @@ static int lookup_prev_stack_frame(unsigned long fp, unsigned long pc, return 0; } -/* Don't put this on the stack since we'll want to call sh64_unwind - * when we're close to underflowing the stack anyway. */ +/* + * Don't put this on the stack since we'll want to call in to + * sh64_unwinder_dump() when we're close to underflowing the stack + * anyway. + */ static struct pt_regs here_regs; extern const char syscall_ret; @@ -208,17 +213,19 @@ extern const char ret_from_syscall; extern const char ret_from_exception; extern const char ret_from_irq; -static void sh64_unwind_inner(struct pt_regs *regs); +static void sh64_unwind_inner(const struct stacktrace_ops *ops, + void *data, struct pt_regs *regs); -static void unwind_nested (unsigned long pc, unsigned long fp) +static inline void unwind_nested(const struct stacktrace_ops *ops, void *data, + unsigned long pc, unsigned long fp) { if ((fp >= __MEMORY_START) && - ((fp & 7) == 0)) { - sh64_unwind_inner((struct pt_regs *) fp); - } + ((fp & 7) == 0)) + sh64_unwind_inner(ops, data, (struct pt_regs *)fp); } -static void sh64_unwind_inner(struct pt_regs *regs) +static void sh64_unwind_inner(const struct stacktrace_ops *ops, + void *data, struct pt_regs *regs) { unsigned long pc, fp; int ofs = 0; @@ -232,29 +239,29 @@ static void sh64_unwind_inner(struct pt_regs *regs) int cond; unsigned long next_fp, next_pc; - if (pc == ((unsigned long) &syscall_ret & ~1)) { + if (pc == ((unsigned long)&syscall_ret & ~1)) { printk("SYSCALL\n"); - unwind_nested(pc,fp); + unwind_nested(ops, data, pc, fp); return; } - if (pc == ((unsigned long) &ret_from_syscall & ~1)) { + if (pc == ((unsigned long)&ret_from_syscall & ~1)) { printk("SYSCALL (PREEMPTED)\n"); - unwind_nested(pc,fp); + unwind_nested(ops, data, pc, fp); return; } /* In this case, the PC is discovered by lookup_prev_stack_frame but it has 4 taken off it to look like the 'caller' */ - if (pc == ((unsigned long) &ret_from_exception & ~1)) { + if (pc == ((unsigned long)&ret_from_exception & ~1)) { printk("EXCEPTION\n"); - unwind_nested(pc,fp); + unwind_nested(ops, data, pc, fp); return; } - if (pc == ((unsigned long) &ret_from_irq & ~1)) { + if (pc == ((unsigned long)&ret_from_irq & ~1)) { printk("IRQ\n"); - unwind_nested(pc,fp); + unwind_nested(ops, data, pc, fp); return; } @@ -263,8 +270,7 @@ static void sh64_unwind_inner(struct pt_regs *regs) pc -= ofs; - printk("[<%08lx>] ", pc); - print_symbol("%s\n", pc); + ops->address(data, pc, 1); if (first_pass) { /* If the innermost frame is a leaf function, it's @@ -287,10 +293,13 @@ static void sh64_unwind_inner(struct pt_regs *regs) } printk("\n"); - } -void sh64_unwind(struct pt_regs *regs) +static void sh64_unwinder_dump(struct task_struct *task, + struct pt_regs *regs, + unsigned long *sp, + const struct stacktrace_ops *ops, + void *data) { if (!regs) { /* @@ -320,7 +329,17 @@ void sh64_unwind(struct pt_regs *regs) ); } - printk("\nCall Trace:\n"); - sh64_unwind_inner(regs); + sh64_unwind_inner(ops, data, regs); } +static struct unwinder sh64_unwinder = { + .name = "sh64-unwinder", + .dump = sh64_unwinder_dump, + .rating = 150, +}; + +static int __init sh64_unwinder_init(void) +{ + return unwinder_register(&sh64_unwinder); +} +early_initcall(sh64_unwinder_init); diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c index 694158b..7617dc4 100644 --- a/arch/sh/kernel/dumpstack.c +++ b/arch/sh/kernel/dumpstack.c @@ -2,13 +2,48 @@ * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs * Copyright (C) 2009 Matt Fleming + * Copyright (C) 2002 - 2012 Paul Mundt + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. */ #include <linux/kallsyms.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <linux/kdebug.h> +#include <linux/export.h> +#include <linux/uaccess.h> #include <asm/unwinder.h> #include <asm/stacktrace.h> +void dump_mem(const char *str, unsigned long bottom, unsigned long top) +{ + unsigned long p; + int i; + + printk("%s(0x%08lx to 0x%08lx)\n", str, bottom, top); + + for (p = bottom & ~31; p < top; ) { + printk("%04lx: ", p & 0xffff); + + for (i = 0; i < 8; i++, p += 4) { + unsigned int val; + + if (p < bottom || p >= top) + printk(" "); + else { + if (__get_user(val, (unsigned int __user *)p)) { + printk("\n"); + return; + } + printk("%08x ", val); + } + } + printk("\n"); + } +} + void printk_address(unsigned long address, int reliable) { printk(" [<%p>] %s%pS\n", (void *) address, @@ -106,3 +141,26 @@ void show_trace(struct task_struct *tsk, unsigned long *sp, debug_show_held_locks(tsk); } + +void show_stack(struct task_struct *tsk, unsigned long *sp) +{ + unsigned long stack; + + if (!tsk) + tsk = current; + if (tsk == current) + sp = (unsigned long *)current_stack_pointer; + else + sp = (unsigned long *)tsk->thread.sp; + + stack = (unsigned long)sp; + dump_mem("Stack: ", stack, THREAD_SIZE + + (unsigned long)task_stack_page(tsk)); + show_trace(tsk, sp, NULL); +} + +void dump_stack(void) +{ + show_stack(NULL, NULL); +} +EXPORT_SYMBOL(dump_stack); diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index dadce73..063af10 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -231,16 +231,6 @@ void __init init_IRQ(void) irq_ctx_init(smp_processor_id()); } -#ifdef CONFIG_SPARSE_IRQ -int __init arch_probe_nr_irqs(void) -{ - /* - * No pre-allocated IRQs. - */ - return 0; -} -#endif - #ifdef CONFIG_HOTPLUG_CPU static void route_irq(struct irq_data *data, unsigned int irq, unsigned int cpu) { diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index a87e58a..72246bc 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -6,9 +6,80 @@ #include <linux/sched.h> #include <linux/uaccess.h> #include <linux/hardirq.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/module.h> #include <asm/unwinder.h> #include <asm/traps.h> +static DEFINE_SPINLOCK(die_lock); + +void die(const char *str, struct pt_regs *regs, long err) +{ + static int die_counter; + + oops_enter(); + + spin_lock_irq(&die_lock); + console_verbose(); + bust_spinlocks(1); + + printk("%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); + print_modules(); + show_regs(regs); + + printk("Process: %s (pid: %d, stack limit = %p)\n", current->comm, + task_pid_nr(current), task_stack_page(current) + 1); + + if (!user_mode(regs) || in_interrupt()) + dump_mem("Stack: ", regs->regs[15], THREAD_SIZE + + (unsigned long)task_stack_page(current)); + + notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV); + + bust_spinlocks(0); + add_taint(TAINT_DIE); + spin_unlock_irq(&die_lock); + oops_exit(); + + if (kexec_should_crash(current)) + crash_kexec(regs); + + if (in_interrupt()) + panic("Fatal exception in interrupt"); + + if (panic_on_oops) + panic("Fatal exception"); + + do_exit(SIGSEGV); +} + +void die_if_kernel(const char *str, struct pt_regs *regs, long err) +{ + if (!user_mode(regs)) + die(str, regs, err); +} + +/* + * try and fix up kernelspace address errors + * - userspace errors just cause EFAULT to be returned, resulting in SEGV + * - kernel/userspace interfaces cause a jump to an appropriate handler + * - other kernel errors are bad + */ +void die_if_no_fixup(const char *str, struct pt_regs *regs, long err) +{ + if (!user_mode(regs)) { + const struct exception_table_entry *fixup; + fixup = search_exception_tables(regs->pc); + if (fixup) { + regs->pc = fixup->fixup; + return; + } + + die(str, regs, err); + } +} + #ifdef CONFIG_GENERIC_BUG static void handle_BUG(struct pt_regs *regs) { diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index a37175d..5f513a6 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -16,13 +16,11 @@ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/spinlock.h> -#include <linux/module.h> #include <linux/kallsyms.h> #include <linux/io.h> #include <linux/bug.h> #include <linux/debug_locks.h> #include <linux/kdebug.h> -#include <linux/kexec.h> #include <linux/limits.h> #include <linux/sysfs.h> #include <linux/uaccess.h> @@ -48,102 +46,6 @@ #define TRAP_ILLEGAL_SLOT_INST 13 #endif -static void dump_mem(const char *str, unsigned long bottom, unsigned long top) -{ - unsigned long p; - int i; - - printk("%s(0x%08lx to 0x%08lx)\n", str, bottom, top); - - for (p = bottom & ~31; p < top; ) { - printk("%04lx: ", p & 0xffff); - - for (i = 0; i < 8; i++, p += 4) { - unsigned int val; - - if (p < bottom || p >= top) - printk(" "); - else { - if (__get_user(val, (unsigned int __user *)p)) { - printk("\n"); - return; - } - printk("%08x ", val); - } - } - printk("\n"); - } -} - -static DEFINE_SPINLOCK(die_lock); - -void die(const char * str, struct pt_regs * regs, long err) -{ - static int die_counter; - - oops_enter(); - - spin_lock_irq(&die_lock); - console_verbose(); - bust_spinlocks(1); - - printk("%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); - print_modules(); - show_regs(regs); - - printk("Process: %s (pid: %d, stack limit = %p)\n", current->comm, - task_pid_nr(current), task_stack_page(current) + 1); - - if (!user_mode(regs) || in_interrupt()) - dump_mem("Stack: ", regs->regs[15], THREAD_SIZE + - (unsigned long)task_stack_page(current)); - - notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV); - - bust_spinlocks(0); - add_taint(TAINT_DIE); - spin_unlock_irq(&die_lock); - oops_exit(); - - if (kexec_should_crash(current)) - crash_kexec(regs); - - if (in_interrupt()) - panic("Fatal exception in interrupt"); - - if (panic_on_oops) - panic("Fatal exception"); - - do_exit(SIGSEGV); -} - -static inline void die_if_kernel(const char *str, struct pt_regs *regs, - long err) -{ - if (!user_mode(regs)) - die(str, regs, err); -} - -/* - * try and fix up kernelspace address errors - * - userspace errors just cause EFAULT to be returned, resulting in SEGV - * - kernel/userspace interfaces cause a jump to an appropriate handler - * - other kernel errors are bad - */ -static void die_if_no_fixup(const char * str, struct pt_regs * regs, long err) -{ - if (!user_mode(regs)) { - const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->pc); - if (fixup) { - regs->pc = fixup->fixup; - return; - } - - die(str, regs, err); - } -} - static inline void sign_extend(unsigned int count, unsigned char *dst) { #ifdef __LITTLE_ENDIAN__ @@ -900,26 +802,3 @@ void __init trap_init(void) set_exception_table_vec(TRAP_UBC, breakpoint_trap_handler); #endif } - -void show_stack(struct task_struct *tsk, unsigned long *sp) -{ - unsigned long stack; - - if (!tsk) - tsk = current; - if (tsk == current) - sp = (unsigned long *)current_stack_pointer; - else - sp = (unsigned long *)tsk->thread.sp; - - stack = (unsigned long)sp; - dump_mem("Stack: ", stack, THREAD_SIZE + - (unsigned long)task_stack_page(tsk)); - show_trace(tsk, sp, NULL); -} - -void dump_stack(void) -{ - show_stack(NULL, NULL); -} -EXPORT_SYMBOL(dump_stack); diff --git a/arch/sh/kernel/traps_64.c b/arch/sh/kernel/traps_64.c index 8dae93e..f87d20d 100644 --- a/arch/sh/kernel/traps_64.c +++ b/arch/sh/kernel/traps_64.c @@ -27,283 +27,25 @@ #include <linux/perf_event.h> #include <asm/uaccess.h> #include <asm/io.h> -#include <linux/atomic.h> +#include <asm/alignment.h> #include <asm/processor.h> #include <asm/pgtable.h> #include <asm/fpu.h> -#undef DEBUG_EXCEPTION -#ifdef DEBUG_EXCEPTION -/* implemented in ../lib/dbg.c */ -extern void show_excp_regs(char *fname, int trapnr, int signr, - struct pt_regs *regs); -#else -#define show_excp_regs(a, b, c, d) -#endif - -static void do_unhandled_exception(int trapnr, int signr, char *str, char *fn_name, - unsigned long error_code, struct pt_regs *regs, struct task_struct *tsk); - -#define DO_ERROR(trapnr, signr, str, name, tsk) \ -asmlinkage void do_##name(unsigned long error_code, struct pt_regs *regs) \ -{ \ - do_unhandled_exception(trapnr, signr, str, __stringify(name), error_code, regs, current); \ -} - -static DEFINE_SPINLOCK(die_lock); - -void die(const char * str, struct pt_regs * regs, long err) -{ - console_verbose(); - spin_lock_irq(&die_lock); - printk("%s: %lx\n", str, (err & 0xffffff)); - show_regs(regs); - spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); -} - -static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) -{ - if (!user_mode(regs)) - die(str, regs, err); -} - -static void die_if_no_fixup(const char * str, struct pt_regs * regs, long err) -{ - if (!user_mode(regs)) { - const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->pc); - if (fixup) { - regs->pc = fixup->fixup; - return; - } - die(str, regs, err); - } -} - -DO_ERROR(13, SIGILL, "illegal slot instruction", illegal_slot_inst, current) -DO_ERROR(87, SIGSEGV, "address error (exec)", address_error_exec, current) - - -/* Implement misaligned load/store handling for kernel (and optionally for user - mode too). Limitation : only SHmedia mode code is handled - there is no - handling at all for misaligned accesses occurring in SHcompact code yet. */ - -static int misaligned_fixup(struct pt_regs *regs); - -asmlinkage void do_address_error_load(unsigned long error_code, struct pt_regs *regs) -{ - if (misaligned_fixup(regs) < 0) { - do_unhandled_exception(7, SIGSEGV, "address error(load)", - "do_address_error_load", - error_code, regs, current); - } - return; -} - -asmlinkage void do_address_error_store(unsigned long error_code, struct pt_regs *regs) -{ - if (misaligned_fixup(regs) < 0) { - do_unhandled_exception(8, SIGSEGV, "address error(store)", - "do_address_error_store", - error_code, regs, current); - } - return; -} - -#if defined(CONFIG_SH64_ID2815_WORKAROUND) - -#define OPCODE_INVALID 0 -#define OPCODE_USER_VALID 1 -#define OPCODE_PRIV_VALID 2 - -/* getcon/putcon - requires checking which control register is referenced. */ -#define OPCODE_CTRL_REG 3 - -/* Table of valid opcodes for SHmedia mode. - Form a 10-bit value by concatenating the major/minor opcodes i.e. - opcode[31:26,20:16]. The 6 MSBs of this value index into the following - array. The 4 LSBs select the bit-pair in the entry (bits 1:0 correspond to - LSBs==4'b0000 etc). */ -static unsigned long shmedia_opcode_table[64] = { - 0x55554044,0x54445055,0x15141514,0x14541414,0x00000000,0x10001000,0x01110055,0x04050015, - 0x00000444,0xc0000000,0x44545515,0x40405555,0x55550015,0x10005555,0x55555505,0x04050000, - 0x00000555,0x00000404,0x00040445,0x15151414,0x00000000,0x00000000,0x00000000,0x00000000, - 0x00000055,0x40404444,0x00000404,0xc0009495,0x00000000,0x00000000,0x00000000,0x00000000, - 0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555, - 0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555, - 0x80005050,0x04005055,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555, - 0x81055554,0x00000404,0x55555555,0x55555555,0x00000000,0x00000000,0x00000000,0x00000000 -}; - -void do_reserved_inst(unsigned long error_code, struct pt_regs *regs) -{ - /* Workaround SH5-101 cut2 silicon defect #2815 : - in some situations, inter-mode branches from SHcompact -> SHmedia - which should take ITLBMISS or EXECPROT exceptions at the target - falsely take RESINST at the target instead. */ - - unsigned long opcode = 0x6ff4fff0; /* guaranteed reserved opcode */ - unsigned long pc, aligned_pc; - int get_user_error; - int trapnr = 12; - int signr = SIGILL; - char *exception_name = "reserved_instruction"; - - pc = regs->pc; - if ((pc & 3) == 1) { - /* SHmedia : check for defect. This requires executable vmas - to be readable too. */ - aligned_pc = pc & ~3; - if (!access_ok(VERIFY_READ, aligned_pc, sizeof(unsigned long))) { - get_user_error = -EFAULT; - } else { - get_user_error = __get_user(opcode, (unsigned long *)aligned_pc); - } - if (get_user_error >= 0) { - unsigned long index, shift; - unsigned long major, minor, combined; - unsigned long reserved_field; - reserved_field = opcode & 0xf; /* These bits are currently reserved as zero in all valid opcodes */ - major = (opcode >> 26) & 0x3f; - minor = (opcode >> 16) & 0xf; - combined = (major << 4) | minor; - index = major; - shift = minor << 1; - if (reserved_field == 0) { - int opcode_state = (shmedia_opcode_table[index] >> shift) & 0x3; - switch (opcode_state) { - case OPCODE_INVALID: - /* Trap. */ - break; - case OPCODE_USER_VALID: - /* Restart the instruction : the branch to the instruction will now be from an RTE - not from SHcompact so the silicon defect won't be triggered. */ - return; - case OPCODE_PRIV_VALID: - if (!user_mode(regs)) { - /* Should only ever get here if a module has - SHcompact code inside it. If so, the same fix up is needed. */ - return; /* same reason */ - } - /* Otherwise, user mode trying to execute a privileged instruction - - fall through to trap. */ - break; - case OPCODE_CTRL_REG: - /* If in privileged mode, return as above. */ - if (!user_mode(regs)) return; - /* In user mode ... */ - if (combined == 0x9f) { /* GETCON */ - unsigned long regno = (opcode >> 20) & 0x3f; - if (regno >= 62) { - return; - } - /* Otherwise, reserved or privileged control register, => trap */ - } else if (combined == 0x1bf) { /* PUTCON */ - unsigned long regno = (opcode >> 4) & 0x3f; - if (regno >= 62) { - return; - } - /* Otherwise, reserved or privileged control register, => trap */ - } else { - /* Trap */ - } - break; - default: - /* Fall through to trap. */ - break; - } - } - /* fall through to normal resinst processing */ - } else { - /* Error trying to read opcode. This typically means a - real fault, not a RESINST any more. So change the - codes. */ - trapnr = 87; - exception_name = "address error (exec)"; - signr = SIGSEGV; - } - } - - do_unhandled_exception(trapnr, signr, exception_name, "do_reserved_inst", error_code, regs, current); -} - -#else /* CONFIG_SH64_ID2815_WORKAROUND */ - -/* If the workaround isn't needed, this is just a straightforward reserved - instruction */ -DO_ERROR(12, SIGILL, "reserved instruction", reserved_inst, current) - -#endif /* CONFIG_SH64_ID2815_WORKAROUND */ - -/* Called with interrupts disabled */ -asmlinkage void do_exception_error(unsigned long ex, struct pt_regs *regs) -{ - show_excp_regs(__func__, -1, -1, regs); - die_if_kernel("exception", regs, ex); -} - -int do_unknown_trapa(unsigned long scId, struct pt_regs *regs) -{ - /* Syscall debug */ - printk("System call ID error: [0x1#args:8 #syscall:16 0x%lx]\n", scId); - - die_if_kernel("unknown trapa", regs, scId); - - return -ENOSYS; -} - -void show_stack(struct task_struct *tsk, unsigned long *sp) -{ -#ifdef CONFIG_KALLSYMS - extern void sh64_unwind(struct pt_regs *regs); - struct pt_regs *regs; - - regs = tsk ? tsk->thread.kregs : NULL; - - sh64_unwind(regs); -#else - printk(KERN_ERR "Can't backtrace on sh64 without CONFIG_KALLSYMS\n"); -#endif -} - -void show_task(unsigned long *sp) -{ - show_stack(NULL, sp); -} - -void dump_stack(void) -{ - show_task(NULL); -} -/* Needed by any user of WARN_ON in view of the defn in include/asm-sh/bug.h */ -EXPORT_SYMBOL(dump_stack); - -static void do_unhandled_exception(int trapnr, int signr, char *str, char *fn_name, - unsigned long error_code, struct pt_regs *regs, struct task_struct *tsk) -{ - show_excp_regs(fn_name, trapnr, signr, regs); - - if (user_mode(regs)) - force_sig(signr, tsk); - - die_if_no_fixup(str, regs, error_code); -} - -static int read_opcode(unsigned long long pc, unsigned long *result_opcode, int from_user_mode) +static int read_opcode(reg_size_t pc, insn_size_t *result_opcode, int from_user_mode) { int get_user_error; unsigned long aligned_pc; - unsigned long opcode; + insn_size_t opcode; if ((pc & 3) == 1) { /* SHmedia */ aligned_pc = pc & ~3; if (from_user_mode) { - if (!access_ok(VERIFY_READ, aligned_pc, sizeof(unsigned long))) { + if (!access_ok(VERIFY_READ, aligned_pc, sizeof(insn_size_t))) { get_user_error = -EFAULT; } else { - get_user_error = __get_user(opcode, (unsigned long *)aligned_pc); + get_user_error = __get_user(opcode, (insn_size_t *)aligned_pc); *result_opcode = opcode; } return get_user_error; @@ -311,7 +53,7 @@ static int read_opcode(unsigned long long pc, unsigned long *result_opcode, int /* If the fault was in the kernel, we can either read * this directly, or if not, we fault. */ - *result_opcode = *(unsigned long *) aligned_pc; + *result_opcode = *(insn_size_t *)aligned_pc; return 0; } } else if ((pc & 1) == 0) { @@ -337,17 +79,23 @@ static int address_is_sign_extended(__u64 a) #endif } +/* return -1 for fault, 0 for OK */ static int generate_and_check_address(struct pt_regs *regs, - __u32 opcode, + insn_size_t opcode, int displacement_not_indexed, int width_shift, __u64 *address) { - /* return -1 for fault, 0 for OK */ - __u64 base_address, addr; int basereg; + switch (1 << width_shift) { + case 1: inc_unaligned_byte_access(); break; + case 2: inc_unaligned_word_access(); break; + case 4: inc_unaligned_dword_access(); break; + case 8: inc_unaligned_multi_access(); break; + } + basereg = (opcode >> 20) & 0x3f; base_address = regs->regs[basereg]; if (displacement_not_indexed) { @@ -364,28 +112,28 @@ static int generate_and_check_address(struct pt_regs *regs, } /* Check sign extended */ - if (!address_is_sign_extended(addr)) { + if (!address_is_sign_extended(addr)) return -1; - } /* Check accessible. For misaligned access in the kernel, assume the address is always accessible (and if not, just fault when the load/store gets done.) */ if (user_mode(regs)) { - if (addr >= TASK_SIZE) { + inc_unaligned_user_access(); + + if (addr >= TASK_SIZE) return -1; - } - /* Do access_ok check later - it depends on whether it's a load or a store. */ - } + } else + inc_unaligned_kernel_access(); *address = addr; + + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, addr); + unaligned_fixups_notify(current, opcode, regs); + return 0; } -static int user_mode_unaligned_fixup_count = 10; -static int user_mode_unaligned_fixup_enable = 1; -static int kernel_mode_unaligned_fixup_count = 32; - static void misaligned_kernel_word_load(__u64 address, int do_sign_extend, __u64 *result) { unsigned short x; @@ -415,7 +163,7 @@ static void misaligned_kernel_word_store(__u64 address, __u64 value) } static int misaligned_load(struct pt_regs *regs, - __u32 opcode, + insn_size_t opcode, int displacement_not_indexed, int width_shift, int do_sign_extend) @@ -427,11 +175,8 @@ static int misaligned_load(struct pt_regs *regs, error = generate_and_check_address(regs, opcode, displacement_not_indexed, width_shift, &address); - if (error < 0) { + if (error < 0) return error; - } - - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address); destreg = (opcode >> 4) & 0x3f; if (user_mode(regs)) { @@ -490,11 +235,10 @@ static int misaligned_load(struct pt_regs *regs, } return 0; - } static int misaligned_store(struct pt_regs *regs, - __u32 opcode, + insn_size_t opcode, int displacement_not_indexed, int width_shift) { @@ -505,11 +249,8 @@ static int misaligned_store(struct pt_regs *regs, error = generate_and_check_address(regs, opcode, displacement_not_indexed, width_shift, &address); - if (error < 0) { + if (error < 0) return error; - } - - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address); srcreg = (opcode >> 4) & 0x3f; if (user_mode(regs)) { @@ -563,13 +304,12 @@ static int misaligned_store(struct pt_regs *regs, } return 0; - } /* Never need to fix up misaligned FPU accesses within the kernel since that's a real error. */ static int misaligned_fpu_load(struct pt_regs *regs, - __u32 opcode, + insn_size_t opcode, int displacement_not_indexed, int width_shift, int do_paired_load) @@ -581,11 +321,8 @@ static int misaligned_fpu_load(struct pt_regs *regs, error = generate_and_check_address(regs, opcode, displacement_not_indexed, width_shift, &address); - if (error < 0) { + if (error < 0) return error; - } - - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, address); destreg = (opcode >> 4) & 0x3f; if (user_mode(regs)) { @@ -641,12 +378,10 @@ static int misaligned_fpu_load(struct pt_regs *regs, die ("Misaligned FPU load inside kernel", regs, 0); return -1; } - - } static int misaligned_fpu_store(struct pt_regs *regs, - __u32 opcode, + insn_size_t opcode, int displacement_not_indexed, int width_shift, int do_paired_load) @@ -658,11 +393,8 @@ static int misaligned_fpu_store(struct pt_regs *regs, error = generate_and_check_address(regs, opcode, displacement_not_indexed, width_shift, &address); - if (error < 0) { + if (error < 0) return error; - } - - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, address); srcreg = (opcode >> 4) & 0x3f; if (user_mode(regs)) { @@ -723,11 +455,13 @@ static int misaligned_fpu_store(struct pt_regs *regs, static int misaligned_fixup(struct pt_regs *regs) { - unsigned long opcode; + insn_size_t opcode; int error; int major, minor; + unsigned int user_action; - if (!user_mode_unaligned_fixup_enable) + user_action = unaligned_user_action(); + if (!(user_action & UM_FIXUP)) return -1; error = read_opcode(regs->pc, &opcode, user_mode(regs)); @@ -737,23 +471,6 @@ static int misaligned_fixup(struct pt_regs *regs) major = (opcode >> 26) & 0x3f; minor = (opcode >> 16) & 0xf; - if (user_mode(regs) && (user_mode_unaligned_fixup_count > 0)) { - --user_mode_unaligned_fixup_count; - /* Only do 'count' worth of these reports, to remove a potential DoS against syslog */ - printk("Fixing up unaligned userspace access in \"%s\" pid=%d pc=0x%08x ins=0x%08lx\n", - current->comm, task_pid_nr(current), (__u32)regs->pc, opcode); - } else if (!user_mode(regs) && (kernel_mode_unaligned_fixup_count > 0)) { - --kernel_mode_unaligned_fixup_count; - if (in_interrupt()) { - printk("Fixing up unaligned kernelspace access in interrupt pc=0x%08x ins=0x%08lx\n", - (__u32)regs->pc, opcode); - } else { - printk("Fixing up unaligned kernelspace access in \"%s\" pid=%d pc=0x%08x ins=0x%08lx\n", - current->comm, task_pid_nr(current), (__u32)regs->pc, opcode); - } - } - - switch (major) { case (0x84>>2): /* LD.W */ error = misaligned_load(regs, opcode, 1, 1, 1); @@ -878,59 +595,202 @@ static int misaligned_fixup(struct pt_regs *regs) regs->pc += 4; /* Skip the instruction that's just been emulated */ return 0; } +} + +static void do_unhandled_exception(int signr, char *str, unsigned long error, + struct pt_regs *regs) +{ + if (user_mode(regs)) + force_sig(signr, current); + die_if_no_fixup(str, regs, error); } -static ctl_table unaligned_table[] = { - { - .procname = "kernel_reports", - .data = &kernel_mode_unaligned_fixup_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "user_reports", - .data = &user_mode_unaligned_fixup_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "user_enable", - .data = &user_mode_unaligned_fixup_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec}, - {} -}; +#define DO_ERROR(signr, str, name) \ +asmlinkage void do_##name(unsigned long error_code, struct pt_regs *regs) \ +{ \ + do_unhandled_exception(signr, str, error_code, regs); \ +} -static ctl_table unaligned_root[] = { - { - .procname = "unaligned_fixup", - .mode = 0555, - .child = unaligned_table - }, - {} -}; +DO_ERROR(SIGILL, "illegal slot instruction", illegal_slot_inst) +DO_ERROR(SIGSEGV, "address error (exec)", address_error_exec) + +#if defined(CONFIG_SH64_ID2815_WORKAROUND) + +#define OPCODE_INVALID 0 +#define OPCODE_USER_VALID 1 +#define OPCODE_PRIV_VALID 2 -static ctl_table sh64_root[] = { - { - .procname = "sh64", - .mode = 0555, - .child = unaligned_root - }, - {} +/* getcon/putcon - requires checking which control register is referenced. */ +#define OPCODE_CTRL_REG 3 + +/* Table of valid opcodes for SHmedia mode. + Form a 10-bit value by concatenating the major/minor opcodes i.e. + opcode[31:26,20:16]. The 6 MSBs of this value index into the following + array. The 4 LSBs select the bit-pair in the entry (bits 1:0 correspond to + LSBs==4'b0000 etc). */ +static unsigned long shmedia_opcode_table[64] = { + 0x55554044,0x54445055,0x15141514,0x14541414,0x00000000,0x10001000,0x01110055,0x04050015, + 0x00000444,0xc0000000,0x44545515,0x40405555,0x55550015,0x10005555,0x55555505,0x04050000, + 0x00000555,0x00000404,0x00040445,0x15151414,0x00000000,0x00000000,0x00000000,0x00000000, + 0x00000055,0x40404444,0x00000404,0xc0009495,0x00000000,0x00000000,0x00000000,0x00000000, + 0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555, + 0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555, + 0x80005050,0x04005055,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555,0x55555555, + 0x81055554,0x00000404,0x55555555,0x55555555,0x00000000,0x00000000,0x00000000,0x00000000 }; -static struct ctl_table_header *sysctl_header; -static int __init init_sysctl(void) + +/* Workaround SH5-101 cut2 silicon defect #2815 : + in some situations, inter-mode branches from SHcompact -> SHmedia + which should take ITLBMISS or EXECPROT exceptions at the target + falsely take RESINST at the target instead. */ +void do_reserved_inst(unsigned long error_code, struct pt_regs *regs) { - sysctl_header = register_sysctl_table(sh64_root); - return 0; + insn_size_t opcode = 0x6ff4fff0; /* guaranteed reserved opcode */ + unsigned long pc, aligned_pc; + unsigned long index, shift; + unsigned long major, minor, combined; + unsigned long reserved_field; + int opcode_state; + int get_user_error; + int signr = SIGILL; + char *exception_name = "reserved_instruction"; + + pc = regs->pc; + + /* SHcompact is not handled */ + if (unlikely((pc & 3) == 0)) + goto out; + + /* SHmedia : check for defect. This requires executable vmas + to be readable too. */ + aligned_pc = pc & ~3; + if (!access_ok(VERIFY_READ, aligned_pc, sizeof(insn_size_t))) + get_user_error = -EFAULT; + else + get_user_error = __get_user(opcode, (insn_size_t *)aligned_pc); + + if (get_user_error < 0) { + /* + * Error trying to read opcode. This typically means a + * real fault, not a RESINST any more. So change the + * codes. + */ + exception_name = "address error (exec)"; + signr = SIGSEGV; + goto out; + } + + /* These bits are currently reserved as zero in all valid opcodes */ + reserved_field = opcode & 0xf; + if (unlikely(reserved_field)) + goto out; /* invalid opcode */ + + major = (opcode >> 26) & 0x3f; + minor = (opcode >> 16) & 0xf; + combined = (major << 4) | minor; + index = major; + shift = minor << 1; + opcode_state = (shmedia_opcode_table[index] >> shift) & 0x3; + switch (opcode_state) { + case OPCODE_INVALID: + /* Trap. */ + break; + case OPCODE_USER_VALID: + /* + * Restart the instruction: the branch to the instruction + * will now be from an RTE not from SHcompact so the + * silicon defect won't be triggered. + */ + return; + case OPCODE_PRIV_VALID: + if (!user_mode(regs)) { + /* + * Should only ever get here if a module has + * SHcompact code inside it. If so, the same fix + * up is needed. + */ + return; /* same reason */ + } + + /* + * Otherwise, user mode trying to execute a privileged + * instruction - fall through to trap. + */ + break; + case OPCODE_CTRL_REG: + /* If in privileged mode, return as above. */ + if (!user_mode(regs)) + return; + + /* In user mode ... */ + if (combined == 0x9f) { /* GETCON */ + unsigned long regno = (opcode >> 20) & 0x3f; + + if (regno >= 62) + return; + + /* reserved/privileged control register => trap */ + } else if (combined == 0x1bf) { /* PUTCON */ + unsigned long regno = (opcode >> 4) & 0x3f; + + if (regno >= 62) + return; + + /* reserved/privileged control register => trap */ + } + + break; + default: + /* Fall through to trap. */ + break; + } + +out: + do_unhandled_exception(signr, exception_name, error_code, regs); } -__initcall(init_sysctl); +#else /* CONFIG_SH64_ID2815_WORKAROUND */ +/* If the workaround isn't needed, this is just a straightforward reserved + instruction */ +DO_ERROR(SIGILL, "reserved instruction", reserved_inst) + +#endif /* CONFIG_SH64_ID2815_WORKAROUND */ + +/* Called with interrupts disabled */ +asmlinkage void do_exception_error(unsigned long ex, struct pt_regs *regs) +{ + die_if_kernel("exception", regs, ex); +} + +asmlinkage int do_unknown_trapa(unsigned long scId, struct pt_regs *regs) +{ + /* Syscall debug */ + printk("System call ID error: [0x1#args:8 #syscall:16 0x%lx]\n", scId); + + die_if_kernel("unknown trapa", regs, scId); + + return -ENOSYS; +} + +/* Implement misaligned load/store handling for kernel (and optionally for user + mode too). Limitation : only SHmedia mode code is handled - there is no + handling at all for misaligned accesses occurring in SHcompact code yet. */ + +asmlinkage void do_address_error_load(unsigned long error_code, struct pt_regs *regs) +{ + if (misaligned_fixup(regs) < 0) + do_unhandled_exception(SIGSEGV, "address error(load)", + error_code, regs); +} + +asmlinkage void do_address_error_store(unsigned long error_code, struct pt_regs *regs) +{ + if (misaligned_fixup(regs) < 0) + do_unhandled_exception(SIGSEGV, "address error(store)", + error_code, regs); +} asmlinkage void do_debug_interrupt(unsigned long code, struct pt_regs *regs) { @@ -942,10 +802,9 @@ asmlinkage void do_debug_interrupt(unsigned long code, struct pt_regs *regs) of access we make to them - just go direct to their physical addresses. */ exp_cause = peek_real_address_q(DM_EXP_CAUSE_PHY); - if (exp_cause & ~4) { + if (exp_cause & ~4) printk("DM.EXP_CAUSE had unexpected bits set (=%08lx)\n", (unsigned long)(exp_cause & 0xffffffff)); - } show_state(); /* Clear all DEBUGINT causes */ poke_real_address_q(DM_EXP_CAUSE_PHY, 0x0); diff --git a/arch/sh/lib64/Makefile b/arch/sh/lib64/Makefile index 1fee75a..69779ff 100644 --- a/arch/sh/lib64/Makefile +++ b/arch/sh/lib64/Makefile @@ -10,7 +10,7 @@ # # Panic should really be compiled as PIC -lib-y := udelay.o dbg.o panic.o memcpy.o memset.o \ +lib-y := udelay.o panic.o memcpy.o memset.o \ copy_user_memcpy.o copy_page.o strcpy.o strlen.o # Extracted from libgcc diff --git a/arch/sh/lib64/dbg.c b/arch/sh/lib64/dbg.c deleted file mode 100644 index 6152a6a..0000000 --- a/arch/sh/lib64/dbg.c +++ /dev/null @@ -1,248 +0,0 @@ -/*-------------------------------------------------------------------------- --- --- Identity : Linux50 Debug Funcions --- --- File : arch/sh/lib64/dbg.c --- --- Copyright 2000, 2001 STMicroelectronics Limited. --- Copyright 2004 Richard Curnow (evt_debug etc) --- ---------------------------------------------------------------------------*/ -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/fs.h> -#include <asm/mmu_context.h> - -typedef u64 regType_t; - -static regType_t getConfigReg(u64 id) -{ - register u64 reg __asm__("r2"); - asm volatile ("getcfg %1, 0, %0":"=r" (reg):"r"(id)); - return (reg); -} - -/* ======================================================================= */ - -static char *szTab[] = { "4k", "64k", "1M", "512M" }; -static char *protTab[] = { "----", - "---R", - "--X-", - "--XR", - "-W--", - "-W-R", - "-WX-", - "-WXR", - "U---", - "U--R", - "U-X-", - "U-XR", - "UW--", - "UW-R", - "UWX-", - "UWXR" -}; -#define ITLB_BASE 0x00000000 -#define DTLB_BASE 0x00800000 -#define MAX_TLBs 64 -/* PTE High */ -#define GET_VALID(pte) ((pte) & 0x1) -#define GET_SHARED(pte) ((pte) & 0x2) -#define GET_ASID(pte) ((pte >> 2) & 0x0ff) -#define GET_EPN(pte) ((pte) & 0xfffff000) - -/* PTE Low */ -#define GET_CBEHAVIOR(pte) ((pte) & 0x3) -#define GET_PAGE_SIZE(pte) szTab[((pte >> 3) & 0x3)] -#define GET_PROTECTION(pte) protTab[((pte >> 6) & 0xf)] -#define GET_PPN(pte) ((pte) & 0xfffff000) - -#define PAGE_1K_MASK 0x00000000 -#define PAGE_4K_MASK 0x00000010 -#define PAGE_64K_MASK 0x00000080 -#define MMU_PAGESIZE_MASK (PAGE_64K_MASK | PAGE_4K_MASK) -#define PAGE_1MB_MASK MMU_PAGESIZE_MASK -#define PAGE_1K (1024) -#define PAGE_4K (1024 * 4) -#define PAGE_64K (1024 * 64) -#define PAGE_1MB (1024 * 1024) - -#define HOW_TO_READ_TLB_CONTENT \ - "[ ID] PPN EPN ASID Share CB P.Size PROT.\n" - -void print_single_tlb(unsigned long tlb, int single_print) -{ - regType_t pteH; - regType_t pteL; - unsigned int valid, shared, asid, epn, cb, ppn; - char *pSize; - char *pProt; - - /* - ** in case of single print <single_print> is true, this implies: - ** 1) print the TLB in any case also if NOT VALID - ** 2) print out the header - */ - - pteH = getConfigReg(tlb); - valid = GET_VALID(pteH); - if (single_print) - printk(HOW_TO_READ_TLB_CONTENT); - else if (!valid) - return; - - pteL = getConfigReg(tlb + 1); - - shared = GET_SHARED(pteH); - asid = GET_ASID(pteH); - epn = GET_EPN(pteH); - cb = GET_CBEHAVIOR(pteL); - pSize = GET_PAGE_SIZE(pteL); - pProt = GET_PROTECTION(pteL); - ppn = GET_PPN(pteL); - printk("[%c%2ld] 0x%08x 0x%08x %03d %02x %02x %4s %s\n", - ((valid) ? ' ' : 'u'), ((tlb & 0x0ffff) / TLB_STEP), - ppn, epn, asid, shared, cb, pSize, pProt); -} - -void print_dtlb(void) -{ - int count; - unsigned long tlb; - - printk(" ================= SH-5 D-TLBs Status ===================\n"); - printk(HOW_TO_READ_TLB_CONTENT); - tlb = DTLB_BASE; - for (count = 0; count < MAX_TLBs; count++, tlb += TLB_STEP) - print_single_tlb(tlb, 0); - printk - (" =============================================================\n"); -} - -void print_itlb(void) -{ - int count; - unsigned long tlb; - - printk(" ================= SH-5 I-TLBs Status ===================\n"); - printk(HOW_TO_READ_TLB_CONTENT); - tlb = ITLB_BASE; - for (count = 0; count < MAX_TLBs; count++, tlb += TLB_STEP) - print_single_tlb(tlb, 0); - printk - (" =============================================================\n"); -} - -void show_excp_regs(char *from, int trapnr, int signr, struct pt_regs *regs) -{ - - unsigned long long ah, al, bh, bl, ch, cl; - - printk("\n"); - printk("EXCEPTION - %s: task %d; Linux trap # %d; signal = %d\n", - ((from) ? from : "???"), current->pid, trapnr, signr); - - asm volatile ("getcon " __EXPEVT ", %0":"=r"(ah)); - asm volatile ("getcon " __EXPEVT ", %0":"=r"(al)); - ah = (ah) >> 32; - al = (al) & 0xffffffff; - asm volatile ("getcon " __KCR1 ", %0":"=r"(bh)); - asm volatile ("getcon " __KCR1 ", %0":"=r"(bl)); - bh = (bh) >> 32; - bl = (bl) & 0xffffffff; - asm volatile ("getcon " __INTEVT ", %0":"=r"(ch)); - asm volatile ("getcon " __INTEVT ", %0":"=r"(cl)); - ch = (ch) >> 32; - cl = (cl) & 0xffffffff; - printk("EXPE: %08Lx%08Lx KCR1: %08Lx%08Lx INTE: %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - asm volatile ("getcon " __PEXPEVT ", %0":"=r"(ah)); - asm volatile ("getcon " __PEXPEVT ", %0":"=r"(al)); - ah = (ah) >> 32; - al = (al) & 0xffffffff; - asm volatile ("getcon " __PSPC ", %0":"=r"(bh)); - asm volatile ("getcon " __PSPC ", %0":"=r"(bl)); - bh = (bh) >> 32; - bl = (bl) & 0xffffffff; - asm volatile ("getcon " __PSSR ", %0":"=r"(ch)); - asm volatile ("getcon " __PSSR ", %0":"=r"(cl)); - ch = (ch) >> 32; - cl = (cl) & 0xffffffff; - printk("PEXP: %08Lx%08Lx PSPC: %08Lx%08Lx PSSR: %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - ah = (regs->pc) >> 32; - al = (regs->pc) & 0xffffffff; - bh = (regs->regs[18]) >> 32; - bl = (regs->regs[18]) & 0xffffffff; - ch = (regs->regs[15]) >> 32; - cl = (regs->regs[15]) & 0xffffffff; - printk("PC : %08Lx%08Lx LINK: %08Lx%08Lx SP : %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - ah = (regs->sr) >> 32; - al = (regs->sr) & 0xffffffff; - asm volatile ("getcon " __TEA ", %0":"=r"(bh)); - asm volatile ("getcon " __TEA ", %0":"=r"(bl)); - bh = (bh) >> 32; - bl = (bl) & 0xffffffff; - asm volatile ("getcon " __KCR0 ", %0":"=r"(ch)); - asm volatile ("getcon " __KCR0 ", %0":"=r"(cl)); - ch = (ch) >> 32; - cl = (cl) & 0xffffffff; - printk("SR : %08Lx%08Lx TEA : %08Lx%08Lx KCR0: %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - ah = (regs->regs[0]) >> 32; - al = (regs->regs[0]) & 0xffffffff; - bh = (regs->regs[1]) >> 32; - bl = (regs->regs[1]) & 0xffffffff; - ch = (regs->regs[2]) >> 32; - cl = (regs->regs[2]) & 0xffffffff; - printk("R0 : %08Lx%08Lx R1 : %08Lx%08Lx R2 : %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - ah = (regs->regs[3]) >> 32; - al = (regs->regs[3]) & 0xffffffff; - bh = (regs->regs[4]) >> 32; - bl = (regs->regs[4]) & 0xffffffff; - ch = (regs->regs[5]) >> 32; - cl = (regs->regs[5]) & 0xffffffff; - printk("R3 : %08Lx%08Lx R4 : %08Lx%08Lx R5 : %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - ah = (regs->regs[6]) >> 32; - al = (regs->regs[6]) & 0xffffffff; - bh = (regs->regs[7]) >> 32; - bl = (regs->regs[7]) & 0xffffffff; - ch = (regs->regs[8]) >> 32; - cl = (regs->regs[8]) & 0xffffffff; - printk("R6 : %08Lx%08Lx R7 : %08Lx%08Lx R8 : %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - - ah = (regs->regs[9]) >> 32; - al = (regs->regs[9]) & 0xffffffff; - bh = (regs->regs[10]) >> 32; - bl = (regs->regs[10]) & 0xffffffff; - ch = (regs->regs[11]) >> 32; - cl = (regs->regs[11]) & 0xffffffff; - printk("R9 : %08Lx%08Lx R10 : %08Lx%08Lx R11 : %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - printk("....\n"); - - ah = (regs->tregs[0]) >> 32; - al = (regs->tregs[0]) & 0xffffffff; - bh = (regs->tregs[1]) >> 32; - bl = (regs->tregs[1]) & 0xffffffff; - ch = (regs->tregs[2]) >> 32; - cl = (regs->tregs[2]) & 0xffffffff; - printk("T0 : %08Lx%08Lx T1 : %08Lx%08Lx T2 : %08Lx%08Lx\n", - ah, al, bh, bl, ch, cl); - printk("....\n"); - - print_dtlb(); - print_itlb(); -} diff --git a/arch/sh/mm/tlb-sh5.c b/arch/sh/mm/tlb-sh5.c index 3aea25d..ff1c40a 100644 --- a/arch/sh/mm/tlb-sh5.c +++ b/arch/sh/mm/tlb-sh5.c @@ -17,7 +17,7 @@ /** * sh64_tlb_init - Perform initial setup for the DTLB and ITLB. */ -int __init sh64_tlb_init(void) +int __cpuinit sh64_tlb_init(void) { /* Assign some sane DTLB defaults */ cpu_data->dtlb.entries = 64; diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c index 19f5605..21dcda7 100644 --- a/arch/sparc/kernel/leon_pci.c +++ b/arch/sparc/kernel/leon_pci.c @@ -91,14 +91,6 @@ void __devinit pcibios_fixup_bus(struct pci_bus *pbus) } } -/* - * Other archs parse arguments here. - */ -char * __devinit pcibios_setup(char *str) -{ - return str; -} - resource_size_t pcibios_align_resource(void *data, const struct resource *res, resource_size_t size, resource_size_t align) { diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 7a3be6f..7bbdc26 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -580,7 +580,7 @@ static unsigned int __init build_one_device_irq(struct platform_device *op, printk("%s: Apply [%s:%x] imap --> [%s:%x]\n", op->dev.of_node->full_name, pp->full_name, this_orig_irq, - (iret ? iret->full_name : "NULL"), irq); + of_node_full_name(iret), irq); if (!iret) break; diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index fdaf218..065b88c 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -375,93 +375,6 @@ static void __devinit apb_calc_first_last(u8 map, u32 *first_p, u32 *last_p) *last_p = last; } -/* For PCI bus devices which lack a 'ranges' property we interrogate - * the config space values to set the resources, just like the generic - * Linux PCI probing code does. - */ -static void __devinit pci_cfg_fake_ranges(struct pci_dev *dev, - struct pci_bus *bus, - struct pci_pbm_info *pbm) -{ - struct pci_bus_region region; - struct resource *res, res2; - u8 io_base_lo, io_limit_lo; - u16 mem_base_lo, mem_limit_lo; - unsigned long base, limit; - - pci_read_config_byte(dev, PCI_IO_BASE, &io_base_lo); - pci_read_config_byte(dev, PCI_IO_LIMIT, &io_limit_lo); - base = (io_base_lo & PCI_IO_RANGE_MASK) << 8; - limit = (io_limit_lo & PCI_IO_RANGE_MASK) << 8; - - if ((io_base_lo & PCI_IO_RANGE_TYPE_MASK) == PCI_IO_RANGE_TYPE_32) { - u16 io_base_hi, io_limit_hi; - - pci_read_config_word(dev, PCI_IO_BASE_UPPER16, &io_base_hi); - pci_read_config_word(dev, PCI_IO_LIMIT_UPPER16, &io_limit_hi); - base |= (io_base_hi << 16); - limit |= (io_limit_hi << 16); - } - - res = bus->resource[0]; - if (base <= limit) { - res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO; - res2.flags = res->flags; - region.start = base; - region.end = limit + 0xfff; - pcibios_bus_to_resource(dev, &res2, ®ion); - if (!res->start) - res->start = res2.start; - if (!res->end) - res->end = res2.end; - } - - pci_read_config_word(dev, PCI_MEMORY_BASE, &mem_base_lo); - pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo); - base = (mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16; - limit = (mem_limit_lo & PCI_MEMORY_RANGE_MASK) << 16; - - res = bus->resource[1]; - if (base <= limit) { - res->flags = ((mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | - IORESOURCE_MEM); - region.start = base; - region.end = limit + 0xfffff; - pcibios_bus_to_resource(dev, res, ®ion); - } - - pci_read_config_word(dev, PCI_PREF_MEMORY_BASE, &mem_base_lo); - pci_read_config_word(dev, PCI_PREF_MEMORY_LIMIT, &mem_limit_lo); - base = (mem_base_lo & PCI_PREF_RANGE_MASK) << 16; - limit = (mem_limit_lo & PCI_PREF_RANGE_MASK) << 16; - - if ((mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) == PCI_PREF_RANGE_TYPE_64) { - u32 mem_base_hi, mem_limit_hi; - - pci_read_config_dword(dev, PCI_PREF_BASE_UPPER32, &mem_base_hi); - pci_read_config_dword(dev, PCI_PREF_LIMIT_UPPER32, &mem_limit_hi); - - /* - * Some bridges set the base > limit by default, and some - * (broken) BIOSes do not initialize them. If we find - * this, just assume they are not being used. - */ - if (mem_base_hi <= mem_limit_hi) { - base |= ((long) mem_base_hi) << 32; - limit |= ((long) mem_limit_hi) << 32; - } - } - - res = bus->resource[2]; - if (base <= limit) { - res->flags = ((mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | - IORESOURCE_MEM | IORESOURCE_PREFETCH); - region.start = base; - region.end = limit + 0xfffff; - pcibios_bus_to_resource(dev, res, ®ion); - } -} - /* Cook up fake bus resources for SUNW,simba PCI bridges which lack * a proper 'ranges' property. */ @@ -535,7 +448,7 @@ static void __devinit of_scan_pci_bridge(struct pci_pbm_info *pbm, } bus->primary = dev->bus->number; - bus->subordinate = busrange[1]; + pci_bus_insert_busn_res(bus, busrange[0], busrange[1]); bus->bridge_ctl = 0; /* parse ranges property, or cook one up by hand for Simba */ @@ -550,7 +463,7 @@ static void __devinit of_scan_pci_bridge(struct pci_pbm_info *pbm, apb_fake_ranges(dev, bus, pbm); goto after_ranges; } else if (ranges == NULL) { - pci_cfg_fake_ranges(dev, bus, pbm); + pci_read_bridge_bases(bus); goto after_ranges; } i = 1; @@ -685,6 +598,10 @@ struct pci_bus * __devinit pci_scan_one_pbm(struct pci_pbm_info *pbm, pbm->io_space.start); pci_add_resource_offset(&resources, &pbm->mem_space, pbm->mem_space.start); + pbm->busn.start = pbm->pci_first_busno; + pbm->busn.end = pbm->pci_last_busno; + pbm->busn.flags = IORESOURCE_BUS; + pci_add_resource(&resources, &pbm->busn); bus = pci_create_root_bus(parent, pbm->pci_first_busno, pbm->pci_ops, pbm, &resources); if (!bus) { @@ -693,8 +610,6 @@ struct pci_bus * __devinit pci_scan_one_pbm(struct pci_pbm_info *pbm, pci_free_resource_list(&resources); return NULL; } - bus->secondary = pbm->pci_first_busno; - bus->subordinate = pbm->pci_last_busno; pci_of_scan_bus(pbm, node, bus); pci_bus_add_devices(bus); @@ -747,11 +662,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask) return 0; } -char * __devinit pcibios_setup(char *str) -{ - return str; -} - /* Platform support for /proc/bus/pci/X/Y mmap()s. */ /* If the user uses a host-bridge as the PCI device, he may use diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h index 6beb60d..918a203 100644 --- a/arch/sparc/kernel/pci_impl.h +++ b/arch/sparc/kernel/pci_impl.h @@ -97,6 +97,7 @@ struct pci_pbm_info { /* PBM I/O and Memory space resources. */ struct resource io_space; struct resource mem_space; + struct resource busn; /* Base of PCI Config space, can be per-PBM or shared. */ unsigned long config_space; diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index ded3f60..521fdf1 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -767,14 +767,6 @@ static void watchdog_reset() { } #endif -/* - * Other archs parse arguments here. - */ -char * __devinit pcibios_setup(char *str) -{ - return str; -} - resource_size_t pcibios_align_resource(void *data, const struct resource *res, resource_size_t size, resource_size_t align) { @@ -884,11 +876,6 @@ void __init sun4m_pci_init_IRQ(void) sparc_config.load_profile_irq = pcic_load_profile_irq; } -int pcibios_assign_resource(struct pci_dev *pdev, int resource) -{ - return -ENXIO; -} - /* * This probably belongs here rather than ioport.c because * we do not want this crud linked into SBus kernels. diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 1a69244..e9073e9 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -96,6 +96,7 @@ static void bpf_flush_icache(void *start_, void *end_) #define AND F3(2, 0x01) #define ANDCC F3(2, 0x11) #define OR F3(2, 0x02) +#define XOR F3(2, 0x03) #define SUB F3(2, 0x04) #define SUBCC F3(2, 0x14) #define MUL F3(2, 0x0a) /* umul */ @@ -462,6 +463,9 @@ void bpf_jit_compile(struct sk_filter *fp) case BPF_S_ALU_OR_K: /* A |= K */ emit_alu_K(OR, K); break; + case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ + emit_alu_X(XOR); + break; case BPF_S_ALU_LSH_X: /* A <<= X */ emit_alu_X(SLL); break; diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index fe12881..932e443 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -3,6 +3,8 @@ config TILE def_bool y + select HAVE_DMA_ATTRS + select HAVE_DMA_API_DEBUG select HAVE_KVM if !TILEGX select GENERIC_FIND_FIRST_BIT select USE_GENERIC_SMP_HELPERS @@ -79,6 +81,9 @@ config ARCH_DMA_ADDR_T_64BIT config NEED_DMA_MAP_STATE def_bool y +config ARCH_HAS_DMA_SET_COHERENT_MASK + bool + config LOCKDEP_SUPPORT def_bool y @@ -212,6 +217,22 @@ config HIGHMEM If unsure, say "true". +config ZONE_DMA + def_bool y + +config IOMMU_HELPER + bool + +config NEED_SG_DMA_LENGTH + bool + +config SWIOTLB + bool + default TILEGX + select IOMMU_HELPER + select NEED_SG_DMA_LENGTH + select ARCH_HAS_DMA_SET_COHERENT_MASK + # We do not currently support disabling NUMA. config NUMA bool # "NUMA Memory Allocation and Scheduler Support" @@ -345,6 +366,8 @@ config KERNEL_PL kernel will be built to run at. Generally you should use the default value here. +source "arch/tile/gxio/Kconfig" + endmenu # Tilera-specific configuration menu "Bus options" @@ -354,6 +377,9 @@ config PCI default y select PCI_DOMAINS select GENERIC_PCI_IOMAP + select TILE_GXIO_TRIO if TILEGX + select ARCH_SUPPORTS_MSI if TILEGX + select PCI_MSI if TILEGX ---help--- Enable PCI root complex support, so PCIe endpoint devices can be attached to the Tile chip. Many, but not all, PCI devices @@ -370,6 +396,22 @@ config NO_IOPORT source "drivers/pci/Kconfig" +config TILE_USB + tristate "Tilera USB host adapter support" + default y + depends on USB + depends on TILEGX + select TILE_GXIO_USB_HOST + ---help--- + Provides USB host adapter support for the built-in EHCI and OHCI + interfaces on TILE-Gx chips. + +# USB OHCI needs the bounce pool since tilegx will often have more +# than 4GB of memory, but we don't currently use the IOTLB to present +# a 32-bit address to OHCI. So we need to use a bounce pool instead. +config NEED_BOUNCE_POOL + def_bool USB_OHCI_HCD + config HOTPLUG bool "Support for hot-pluggable devices" ---help--- diff --git a/arch/tile/Makefile b/arch/tile/Makefile index e20b0a0..55640cf 100644 --- a/arch/tile/Makefile +++ b/arch/tile/Makefile @@ -59,6 +59,8 @@ libs-y += $(LIBGCC_PATH) # See arch/tile/Kbuild for content of core part of the kernel core-y += arch/tile/ +core-$(CONFIG_TILE_GXIO) += arch/tile/gxio/ + ifdef TILERA_ROOT INSTALL_PATH ?= $(TILERA_ROOT)/tile/boot endif diff --git a/arch/tile/gxio/Kconfig b/arch/tile/gxio/Kconfig new file mode 100644 index 0000000..d221f8d --- /dev/null +++ b/arch/tile/gxio/Kconfig @@ -0,0 +1,28 @@ +# Support direct access to TILE-Gx hardware from user space, via the +# gxio library, or from kernel space, via kernel IORPC support. +config TILE_GXIO + bool + depends on TILEGX + +# Support direct access to the common I/O DMA facility within the +# TILE-Gx mPIPE and Trio hardware from kernel space. +config TILE_GXIO_DMA + bool + select TILE_GXIO + +# Support direct access to the TILE-Gx mPIPE hardware from kernel space. +config TILE_GXIO_MPIPE + bool + select TILE_GXIO + select TILE_GXIO_DMA + +# Support direct access to the TILE-Gx TRIO hardware from kernel space. +config TILE_GXIO_TRIO + bool + select TILE_GXIO + select TILE_GXIO_DMA + +# Support direct access to the TILE-Gx USB hardware from kernel space. +config TILE_GXIO_USB_HOST + bool + select TILE_GXIO diff --git a/arch/tile/gxio/Makefile b/arch/tile/gxio/Makefile new file mode 100644 index 0000000..8684bca --- /dev/null +++ b/arch/tile/gxio/Makefile @@ -0,0 +1,9 @@ +# +# Makefile for the Tile-Gx device access support. +# + +obj-$(CONFIG_TILE_GXIO) += iorpc_globals.o kiorpc.o +obj-$(CONFIG_TILE_GXIO_DMA) += dma_queue.o +obj-$(CONFIG_TILE_GXIO_MPIPE) += mpipe.o iorpc_mpipe.o iorpc_mpipe_info.o +obj-$(CONFIG_TILE_GXIO_TRIO) += trio.o iorpc_trio.o +obj-$(CONFIG_TILE_GXIO_USB_HOST) += usb_host.o iorpc_usb_host.o diff --git a/arch/tile/gxio/dma_queue.c b/arch/tile/gxio/dma_queue.c new file mode 100644 index 0000000..baa6035 --- /dev/null +++ b/arch/tile/gxio/dma_queue.c @@ -0,0 +1,176 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#include <linux/io.h> +#include <linux/atomic.h> +#include <linux/module.h> +#include <gxio/dma_queue.h> + +/* Wait for a memory read to complete. */ +#define wait_for_value(val) \ + __asm__ __volatile__("move %0, %0" :: "r"(val)) + +/* The index is in the low 16. */ +#define DMA_QUEUE_INDEX_MASK ((1 << 16) - 1) + +/* + * The hardware descriptor-ring type. + * This matches the types used by mpipe (MPIPE_EDMA_POST_REGION_VAL_t) + * and trio (TRIO_PUSH_DMA_REGION_VAL_t or TRIO_PULL_DMA_REGION_VAL_t). + * See those types for more documentation on the individual fields. + */ +typedef union { + struct { +#ifndef __BIG_ENDIAN__ + uint64_t ring_idx:16; + uint64_t count:16; + uint64_t gen:1; + uint64_t __reserved:31; +#else + uint64_t __reserved:31; + uint64_t gen:1; + uint64_t count:16; + uint64_t ring_idx:16; +#endif + }; + uint64_t word; +} __gxio_ring_t; + +void __gxio_dma_queue_init(__gxio_dma_queue_t *dma_queue, + void *post_region_addr, unsigned int num_entries) +{ + /* + * Limit 65536 entry rings to 65535 credits because we only have a + * 16 bit completion counter. + */ + int64_t credits = (num_entries < 65536) ? num_entries : 65535; + + memset(dma_queue, 0, sizeof(*dma_queue)); + + dma_queue->post_region_addr = post_region_addr; + dma_queue->hw_complete_count = 0; + dma_queue->credits_and_next_index = credits << DMA_QUEUE_CREDIT_SHIFT; +} + +EXPORT_SYMBOL_GPL(__gxio_dma_queue_init); + +void __gxio_dma_queue_update_credits(__gxio_dma_queue_t *dma_queue) +{ + __gxio_ring_t val; + uint64_t count; + uint64_t delta; + uint64_t new_count; + + /* + * Read the 64-bit completion count without touching the cache, so + * we later avoid having to evict any sharers of this cache line + * when we update it below. + */ + uint64_t orig_hw_complete_count = + cmpxchg(&dma_queue->hw_complete_count, + -1, -1); + + /* Make sure the load completes before we access the hardware. */ + wait_for_value(orig_hw_complete_count); + + /* Read the 16-bit count of how many packets it has completed. */ + val.word = __gxio_mmio_read(dma_queue->post_region_addr); + count = val.count; + + /* + * Calculate the number of completions since we last updated the + * 64-bit counter. It's safe to ignore the high bits because the + * maximum credit value is 65535. + */ + delta = (count - orig_hw_complete_count) & 0xffff; + if (delta == 0) + return; + + /* + * Try to write back the count, advanced by delta. If we race with + * another thread, this might fail, in which case we return + * immediately on the assumption that some credits are (or at least + * were) available. + */ + new_count = orig_hw_complete_count + delta; + if (cmpxchg(&dma_queue->hw_complete_count, + orig_hw_complete_count, + new_count) != orig_hw_complete_count) + return; + + /* + * We succeeded in advancing the completion count; add back the + * corresponding number of egress credits. + */ + __insn_fetchadd(&dma_queue->credits_and_next_index, + (delta << DMA_QUEUE_CREDIT_SHIFT)); +} + +EXPORT_SYMBOL_GPL(__gxio_dma_queue_update_credits); + +/* + * A separate 'blocked' method for put() so that backtraces and + * profiles will clearly indicate that we're wasting time spinning on + * egress availability rather than actually posting commands. + */ +int64_t __gxio_dma_queue_wait_for_credits(__gxio_dma_queue_t *dma_queue, + int64_t modifier) +{ + int backoff = 16; + int64_t old; + + do { + int i; + /* Back off to avoid spamming memory networks. */ + for (i = backoff; i > 0; i--) + __insn_mfspr(SPR_PASS); + + /* Check credits again. */ + __gxio_dma_queue_update_credits(dma_queue); + old = __insn_fetchaddgez(&dma_queue->credits_and_next_index, + modifier); + + /* Calculate bounded exponential backoff for next iteration. */ + if (backoff < 256) + backoff *= 2; + } while (old + modifier < 0); + + return old; +} + +EXPORT_SYMBOL_GPL(__gxio_dma_queue_wait_for_credits); + +int64_t __gxio_dma_queue_reserve_aux(__gxio_dma_queue_t *dma_queue, + unsigned int num, int wait) +{ + return __gxio_dma_queue_reserve(dma_queue, num, wait != 0, true); +} + +EXPORT_SYMBOL_GPL(__gxio_dma_queue_reserve_aux); + +int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue, + int64_t completion_slot, int update) +{ + if (update) { + if (ACCESS_ONCE(dma_queue->hw_complete_count) > + completion_slot) + return 1; + + __gxio_dma_queue_update_credits(dma_queue); + } + + return ACCESS_ONCE(dma_queue->hw_complete_count) > completion_slot; +} + +EXPORT_SYMBOL_GPL(__gxio_dma_queue_is_complete); diff --git a/arch/tile/gxio/iorpc_globals.c b/arch/tile/gxio/iorpc_globals.c new file mode 100644 index 0000000..e178e90 --- /dev/null +++ b/arch/tile/gxio/iorpc_globals.c @@ -0,0 +1,89 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#include "gxio/iorpc_globals.h" + +struct arm_pollfd_param { + union iorpc_pollfd pollfd; +}; + +int __iorpc_arm_pollfd(int fd, int pollfd_cookie) +{ + struct arm_pollfd_param temp; + struct arm_pollfd_param *params = &temp; + + params->pollfd.kernel.cookie = pollfd_cookie; + + return hv_dev_pwrite(fd, 0, (HV_VirtAddr) params, sizeof(*params), + IORPC_OP_ARM_POLLFD); +} + +EXPORT_SYMBOL(__iorpc_arm_pollfd); + +struct close_pollfd_param { + union iorpc_pollfd pollfd; +}; + +int __iorpc_close_pollfd(int fd, int pollfd_cookie) +{ + struct close_pollfd_param temp; + struct close_pollfd_param *params = &temp; + + params->pollfd.kernel.cookie = pollfd_cookie; + + return hv_dev_pwrite(fd, 0, (HV_VirtAddr) params, sizeof(*params), + IORPC_OP_CLOSE_POLLFD); +} + +EXPORT_SYMBOL(__iorpc_close_pollfd); + +struct get_mmio_base_param { + HV_PTE base; +}; + +int __iorpc_get_mmio_base(int fd, HV_PTE *base) +{ + int __result; + struct get_mmio_base_param temp; + struct get_mmio_base_param *params = &temp; + + __result = + hv_dev_pread(fd, 0, (HV_VirtAddr) params, sizeof(*params), + IORPC_OP_GET_MMIO_BASE); + *base = params->base; + + return __result; +} + +EXPORT_SYMBOL(__iorpc_get_mmio_base); + +struct check_mmio_offset_param { + unsigned long offset; + unsigned long size; +}; + +int __iorpc_check_mmio_offset(int fd, unsigned long offset, unsigned long size) +{ + struct check_mmio_offset_param temp; + struct check_mmio_offset_param *params = &temp; + + params->offset = offset; + params->size = size; + + return hv_dev_pwrite(fd, 0, (HV_VirtAddr) params, sizeof(*params), + IORPC_OP_CHECK_MMIO_OFFSET); +} + +EXPORT_SYMBOL(__iorpc_check_mmio_offset); diff --git a/arch/tile/gxio/iorpc_mpipe.c b/arch/tile/gxio/iorpc_mpipe.c new file mode 100644 index 0000000..31b87bf --- /dev/null +++ b/arch/tile/gxio/iorpc_mpipe.c @@ -0,0 +1,529 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#include "gxio/iorpc_mpipe.h" + +struct alloc_buffer_stacks_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags) +{ + struct alloc_buffer_stacks_param temp; + struct alloc_buffer_stacks_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_ALLOC_BUFFER_STACKS); +} + +EXPORT_SYMBOL(gxio_mpipe_alloc_buffer_stacks); + +struct init_buffer_stack_aux_param { + union iorpc_mem_buffer buffer; + unsigned int stack; + unsigned int buffer_size_enum; +}; + +int gxio_mpipe_init_buffer_stack_aux(gxio_mpipe_context_t * context, + void *mem_va, size_t mem_size, + unsigned int mem_flags, unsigned int stack, + unsigned int buffer_size_enum) +{ + int __result; + unsigned long long __cpa; + pte_t __pte; + struct init_buffer_stack_aux_param temp; + struct init_buffer_stack_aux_param *params = &temp; + + __result = va_to_cpa_and_pte(mem_va, &__cpa, &__pte); + if (__result != 0) + return __result; + params->buffer.kernel.cpa = __cpa; + params->buffer.kernel.size = mem_size; + params->buffer.kernel.pte = __pte; + params->buffer.kernel.flags = mem_flags; + params->stack = stack; + params->buffer_size_enum = buffer_size_enum; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_INIT_BUFFER_STACK_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_init_buffer_stack_aux); + + +struct alloc_notif_rings_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags) +{ + struct alloc_notif_rings_param temp; + struct alloc_notif_rings_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_ALLOC_NOTIF_RINGS); +} + +EXPORT_SYMBOL(gxio_mpipe_alloc_notif_rings); + +struct init_notif_ring_aux_param { + union iorpc_mem_buffer buffer; + unsigned int ring; +}; + +int gxio_mpipe_init_notif_ring_aux(gxio_mpipe_context_t * context, void *mem_va, + size_t mem_size, unsigned int mem_flags, + unsigned int ring) +{ + int __result; + unsigned long long __cpa; + pte_t __pte; + struct init_notif_ring_aux_param temp; + struct init_notif_ring_aux_param *params = &temp; + + __result = va_to_cpa_and_pte(mem_va, &__cpa, &__pte); + if (__result != 0) + return __result; + params->buffer.kernel.cpa = __cpa; + params->buffer.kernel.size = mem_size; + params->buffer.kernel.pte = __pte; + params->buffer.kernel.flags = mem_flags; + params->ring = ring; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_INIT_NOTIF_RING_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_init_notif_ring_aux); + +struct request_notif_ring_interrupt_param { + union iorpc_interrupt interrupt; + unsigned int ring; +}; + +int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t * context, + int inter_x, int inter_y, + int inter_ipi, int inter_event, + unsigned int ring) +{ + struct request_notif_ring_interrupt_param temp; + struct request_notif_ring_interrupt_param *params = &temp; + + params->interrupt.kernel.x = inter_x; + params->interrupt.kernel.y = inter_y; + params->interrupt.kernel.ipi = inter_ipi; + params->interrupt.kernel.event = inter_event; + params->ring = ring; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_REQUEST_NOTIF_RING_INTERRUPT); +} + +EXPORT_SYMBOL(gxio_mpipe_request_notif_ring_interrupt); + +struct enable_notif_ring_interrupt_param { + unsigned int ring; +}; + +int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t * context, + unsigned int ring) +{ + struct enable_notif_ring_interrupt_param temp; + struct enable_notif_ring_interrupt_param *params = &temp; + + params->ring = ring; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_ENABLE_NOTIF_RING_INTERRUPT); +} + +EXPORT_SYMBOL(gxio_mpipe_enable_notif_ring_interrupt); + +struct alloc_notif_groups_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags) +{ + struct alloc_notif_groups_param temp; + struct alloc_notif_groups_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_ALLOC_NOTIF_GROUPS); +} + +EXPORT_SYMBOL(gxio_mpipe_alloc_notif_groups); + +struct init_notif_group_param { + unsigned int group; + gxio_mpipe_notif_group_bits_t bits; +}; + +int gxio_mpipe_init_notif_group(gxio_mpipe_context_t * context, + unsigned int group, + gxio_mpipe_notif_group_bits_t bits) +{ + struct init_notif_group_param temp; + struct init_notif_group_param *params = &temp; + + params->group = group; + params->bits = bits; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_INIT_NOTIF_GROUP); +} + +EXPORT_SYMBOL(gxio_mpipe_init_notif_group); + +struct alloc_buckets_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t * context, unsigned int count, + unsigned int first, unsigned int flags) +{ + struct alloc_buckets_param temp; + struct alloc_buckets_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_ALLOC_BUCKETS); +} + +EXPORT_SYMBOL(gxio_mpipe_alloc_buckets); + +struct init_bucket_param { + unsigned int bucket; + MPIPE_LBL_INIT_DAT_BSTS_TBL_t bucket_info; +}; + +int gxio_mpipe_init_bucket(gxio_mpipe_context_t * context, unsigned int bucket, + MPIPE_LBL_INIT_DAT_BSTS_TBL_t bucket_info) +{ + struct init_bucket_param temp; + struct init_bucket_param *params = &temp; + + params->bucket = bucket; + params->bucket_info = bucket_info; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_INIT_BUCKET); +} + +EXPORT_SYMBOL(gxio_mpipe_init_bucket); + +struct alloc_edma_rings_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags) +{ + struct alloc_edma_rings_param temp; + struct alloc_edma_rings_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_ALLOC_EDMA_RINGS); +} + +EXPORT_SYMBOL(gxio_mpipe_alloc_edma_rings); + +struct init_edma_ring_aux_param { + union iorpc_mem_buffer buffer; + unsigned int ring; + unsigned int channel; +}; + +int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t * context, void *mem_va, + size_t mem_size, unsigned int mem_flags, + unsigned int ring, unsigned int channel) +{ + int __result; + unsigned long long __cpa; + pte_t __pte; + struct init_edma_ring_aux_param temp; + struct init_edma_ring_aux_param *params = &temp; + + __result = va_to_cpa_and_pte(mem_va, &__cpa, &__pte); + if (__result != 0) + return __result; + params->buffer.kernel.cpa = __cpa; + params->buffer.kernel.size = mem_size; + params->buffer.kernel.pte = __pte; + params->buffer.kernel.flags = mem_flags; + params->ring = ring; + params->channel = channel; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_INIT_EDMA_RING_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_init_edma_ring_aux); + + +int gxio_mpipe_commit_rules(gxio_mpipe_context_t * context, const void *blob, + size_t blob_size) +{ + const void *params = blob; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, blob_size, + GXIO_MPIPE_OP_COMMIT_RULES); +} + +EXPORT_SYMBOL(gxio_mpipe_commit_rules); + +struct register_client_memory_param { + unsigned int iotlb; + HV_PTE pte; + unsigned int flags; +}; + +int gxio_mpipe_register_client_memory(gxio_mpipe_context_t * context, + unsigned int iotlb, HV_PTE pte, + unsigned int flags) +{ + struct register_client_memory_param temp; + struct register_client_memory_param *params = &temp; + + params->iotlb = iotlb; + params->pte = pte; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_REGISTER_CLIENT_MEMORY); +} + +EXPORT_SYMBOL(gxio_mpipe_register_client_memory); + +struct link_open_aux_param { + _gxio_mpipe_link_name_t name; + unsigned int flags; +}; + +int gxio_mpipe_link_open_aux(gxio_mpipe_context_t * context, + _gxio_mpipe_link_name_t name, unsigned int flags) +{ + struct link_open_aux_param temp; + struct link_open_aux_param *params = &temp; + + params->name = name; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_LINK_OPEN_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_link_open_aux); + +struct link_close_aux_param { + int mac; +}; + +int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac) +{ + struct link_close_aux_param temp; + struct link_close_aux_param *params = &temp; + + params->mac = mac; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_LINK_CLOSE_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_link_close_aux); + + +struct get_timestamp_aux_param { + uint64_t sec; + uint64_t nsec; + uint64_t cycles; +}; + +int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t * context, uint64_t * sec, + uint64_t * nsec, uint64_t * cycles) +{ + int __result; + struct get_timestamp_aux_param temp; + struct get_timestamp_aux_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + GXIO_MPIPE_OP_GET_TIMESTAMP_AUX); + *sec = params->sec; + *nsec = params->nsec; + *cycles = params->cycles; + + return __result; +} + +EXPORT_SYMBOL(gxio_mpipe_get_timestamp_aux); + +struct set_timestamp_aux_param { + uint64_t sec; + uint64_t nsec; + uint64_t cycles; +}; + +int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t * context, uint64_t sec, + uint64_t nsec, uint64_t cycles) +{ + struct set_timestamp_aux_param temp; + struct set_timestamp_aux_param *params = &temp; + + params->sec = sec; + params->nsec = nsec; + params->cycles = cycles; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_SET_TIMESTAMP_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_set_timestamp_aux); + +struct adjust_timestamp_aux_param { + int64_t nsec; +}; + +int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context, + int64_t nsec) +{ + struct adjust_timestamp_aux_param temp; + struct adjust_timestamp_aux_param *params = &temp; + + params->nsec = nsec; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_aux); + +struct arm_pollfd_param { + union iorpc_pollfd pollfd; +}; + +int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie) +{ + struct arm_pollfd_param temp; + struct arm_pollfd_param *params = &temp; + + params->pollfd.kernel.cookie = pollfd_cookie; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_ARM_POLLFD); +} + +EXPORT_SYMBOL(gxio_mpipe_arm_pollfd); + +struct close_pollfd_param { + union iorpc_pollfd pollfd; +}; + +int gxio_mpipe_close_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie) +{ + struct close_pollfd_param temp; + struct close_pollfd_param *params = &temp; + + params->pollfd.kernel.cookie = pollfd_cookie; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_CLOSE_POLLFD); +} + +EXPORT_SYMBOL(gxio_mpipe_close_pollfd); + +struct get_mmio_base_param { + HV_PTE base; +}; + +int gxio_mpipe_get_mmio_base(gxio_mpipe_context_t * context, HV_PTE *base) +{ + int __result; + struct get_mmio_base_param temp; + struct get_mmio_base_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + GXIO_MPIPE_OP_GET_MMIO_BASE); + *base = params->base; + + return __result; +} + +EXPORT_SYMBOL(gxio_mpipe_get_mmio_base); + +struct check_mmio_offset_param { + unsigned long offset; + unsigned long size; +}; + +int gxio_mpipe_check_mmio_offset(gxio_mpipe_context_t * context, + unsigned long offset, unsigned long size) +{ + struct check_mmio_offset_param temp; + struct check_mmio_offset_param *params = &temp; + + params->offset = offset; + params->size = size; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_CHECK_MMIO_OFFSET); +} + +EXPORT_SYMBOL(gxio_mpipe_check_mmio_offset); diff --git a/arch/tile/gxio/iorpc_mpipe_info.c b/arch/tile/gxio/iorpc_mpipe_info.c new file mode 100644 index 0000000..d0254aa --- /dev/null +++ b/arch/tile/gxio/iorpc_mpipe_info.c @@ -0,0 +1,85 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#include "gxio/iorpc_mpipe_info.h" + + +struct enumerate_aux_param { + _gxio_mpipe_link_name_t name; + _gxio_mpipe_link_mac_t mac; +}; + +int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context, + unsigned int idx, + _gxio_mpipe_link_name_t * name, + _gxio_mpipe_link_mac_t * mac) +{ + int __result; + struct enumerate_aux_param temp; + struct enumerate_aux_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + (((uint64_t) idx << 32) | + GXIO_MPIPE_INFO_OP_ENUMERATE_AUX)); + *name = params->name; + *mac = params->mac; + + return __result; +} + +EXPORT_SYMBOL(gxio_mpipe_info_enumerate_aux); + +struct get_mmio_base_param { + HV_PTE base; +}; + +int gxio_mpipe_info_get_mmio_base(gxio_mpipe_info_context_t * context, + HV_PTE *base) +{ + int __result; + struct get_mmio_base_param temp; + struct get_mmio_base_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + GXIO_MPIPE_INFO_OP_GET_MMIO_BASE); + *base = params->base; + + return __result; +} + +EXPORT_SYMBOL(gxio_mpipe_info_get_mmio_base); + +struct check_mmio_offset_param { + unsigned long offset; + unsigned long size; +}; + +int gxio_mpipe_info_check_mmio_offset(gxio_mpipe_info_context_t * context, + unsigned long offset, unsigned long size) +{ + struct check_mmio_offset_param temp; + struct check_mmio_offset_param *params = &temp; + + params->offset = offset; + params->size = size; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_INFO_OP_CHECK_MMIO_OFFSET); +} + +EXPORT_SYMBOL(gxio_mpipe_info_check_mmio_offset); diff --git a/arch/tile/gxio/iorpc_trio.c b/arch/tile/gxio/iorpc_trio.c new file mode 100644 index 0000000..cef4b22 --- /dev/null +++ b/arch/tile/gxio/iorpc_trio.c @@ -0,0 +1,327 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#include "gxio/iorpc_trio.h" + +struct alloc_asids_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_trio_alloc_asids(gxio_trio_context_t * context, unsigned int count, + unsigned int first, unsigned int flags) +{ + struct alloc_asids_param temp; + struct alloc_asids_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_ALLOC_ASIDS); +} + +EXPORT_SYMBOL(gxio_trio_alloc_asids); + + +struct alloc_memory_maps_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_trio_alloc_memory_maps(gxio_trio_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags) +{ + struct alloc_memory_maps_param temp; + struct alloc_memory_maps_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_ALLOC_MEMORY_MAPS); +} + +EXPORT_SYMBOL(gxio_trio_alloc_memory_maps); + + +struct alloc_pio_regions_param { + unsigned int count; + unsigned int first; + unsigned int flags; +}; + +int gxio_trio_alloc_pio_regions(gxio_trio_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags) +{ + struct alloc_pio_regions_param temp; + struct alloc_pio_regions_param *params = &temp; + + params->count = count; + params->first = first; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_ALLOC_PIO_REGIONS); +} + +EXPORT_SYMBOL(gxio_trio_alloc_pio_regions); + +struct init_pio_region_aux_param { + unsigned int pio_region; + unsigned int mac; + uint32_t bus_address_hi; + unsigned int flags; +}; + +int gxio_trio_init_pio_region_aux(gxio_trio_context_t * context, + unsigned int pio_region, unsigned int mac, + uint32_t bus_address_hi, unsigned int flags) +{ + struct init_pio_region_aux_param temp; + struct init_pio_region_aux_param *params = &temp; + + params->pio_region = pio_region; + params->mac = mac; + params->bus_address_hi = bus_address_hi; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_INIT_PIO_REGION_AUX); +} + +EXPORT_SYMBOL(gxio_trio_init_pio_region_aux); + + +struct init_memory_map_mmu_aux_param { + unsigned int map; + unsigned long va; + uint64_t size; + unsigned int asid; + unsigned int mac; + uint64_t bus_address; + unsigned int node; + unsigned int order_mode; +}; + +int gxio_trio_init_memory_map_mmu_aux(gxio_trio_context_t * context, + unsigned int map, unsigned long va, + uint64_t size, unsigned int asid, + unsigned int mac, uint64_t bus_address, + unsigned int node, + unsigned int order_mode) +{ + struct init_memory_map_mmu_aux_param temp; + struct init_memory_map_mmu_aux_param *params = &temp; + + params->map = map; + params->va = va; + params->size = size; + params->asid = asid; + params->mac = mac; + params->bus_address = bus_address; + params->node = node; + params->order_mode = order_mode; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_TRIO_OP_INIT_MEMORY_MAP_MMU_AUX); +} + +EXPORT_SYMBOL(gxio_trio_init_memory_map_mmu_aux); + +struct get_port_property_param { + struct pcie_trio_ports_property trio_ports; +}; + +int gxio_trio_get_port_property(gxio_trio_context_t * context, + struct pcie_trio_ports_property *trio_ports) +{ + int __result; + struct get_port_property_param temp; + struct get_port_property_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + GXIO_TRIO_OP_GET_PORT_PROPERTY); + *trio_ports = params->trio_ports; + + return __result; +} + +EXPORT_SYMBOL(gxio_trio_get_port_property); + +struct config_legacy_intr_param { + union iorpc_interrupt interrupt; + unsigned int mac; + unsigned int intx; +}; + +int gxio_trio_config_legacy_intr(gxio_trio_context_t * context, int inter_x, + int inter_y, int inter_ipi, int inter_event, + unsigned int mac, unsigned int intx) +{ + struct config_legacy_intr_param temp; + struct config_legacy_intr_param *params = &temp; + + params->interrupt.kernel.x = inter_x; + params->interrupt.kernel.y = inter_y; + params->interrupt.kernel.ipi = inter_ipi; + params->interrupt.kernel.event = inter_event; + params->mac = mac; + params->intx = intx; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_CONFIG_LEGACY_INTR); +} + +EXPORT_SYMBOL(gxio_trio_config_legacy_intr); + +struct config_msi_intr_param { + union iorpc_interrupt interrupt; + unsigned int mac; + unsigned int mem_map; + uint64_t mem_map_base; + uint64_t mem_map_limit; + unsigned int asid; +}; + +int gxio_trio_config_msi_intr(gxio_trio_context_t * context, int inter_x, + int inter_y, int inter_ipi, int inter_event, + unsigned int mac, unsigned int mem_map, + uint64_t mem_map_base, uint64_t mem_map_limit, + unsigned int asid) +{ + struct config_msi_intr_param temp; + struct config_msi_intr_param *params = &temp; + + params->interrupt.kernel.x = inter_x; + params->interrupt.kernel.y = inter_y; + params->interrupt.kernel.ipi = inter_ipi; + params->interrupt.kernel.event = inter_event; + params->mac = mac; + params->mem_map = mem_map; + params->mem_map_base = mem_map_base; + params->mem_map_limit = mem_map_limit; + params->asid = asid; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_CONFIG_MSI_INTR); +} + +EXPORT_SYMBOL(gxio_trio_config_msi_intr); + + +struct set_mps_mrs_param { + uint16_t mps; + uint16_t mrs; + unsigned int mac; +}; + +int gxio_trio_set_mps_mrs(gxio_trio_context_t * context, uint16_t mps, + uint16_t mrs, unsigned int mac) +{ + struct set_mps_mrs_param temp; + struct set_mps_mrs_param *params = &temp; + + params->mps = mps; + params->mrs = mrs; + params->mac = mac; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_SET_MPS_MRS); +} + +EXPORT_SYMBOL(gxio_trio_set_mps_mrs); + +struct force_rc_link_up_param { + unsigned int mac; +}; + +int gxio_trio_force_rc_link_up(gxio_trio_context_t * context, unsigned int mac) +{ + struct force_rc_link_up_param temp; + struct force_rc_link_up_param *params = &temp; + + params->mac = mac; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_FORCE_RC_LINK_UP); +} + +EXPORT_SYMBOL(gxio_trio_force_rc_link_up); + +struct force_ep_link_up_param { + unsigned int mac; +}; + +int gxio_trio_force_ep_link_up(gxio_trio_context_t * context, unsigned int mac) +{ + struct force_ep_link_up_param temp; + struct force_ep_link_up_param *params = &temp; + + params->mac = mac; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_FORCE_EP_LINK_UP); +} + +EXPORT_SYMBOL(gxio_trio_force_ep_link_up); + +struct get_mmio_base_param { + HV_PTE base; +}; + +int gxio_trio_get_mmio_base(gxio_trio_context_t * context, HV_PTE *base) +{ + int __result; + struct get_mmio_base_param temp; + struct get_mmio_base_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + GXIO_TRIO_OP_GET_MMIO_BASE); + *base = params->base; + + return __result; +} + +EXPORT_SYMBOL(gxio_trio_get_mmio_base); + +struct check_mmio_offset_param { + unsigned long offset; + unsigned long size; +}; + +int gxio_trio_check_mmio_offset(gxio_trio_context_t * context, + unsigned long offset, unsigned long size) +{ + struct check_mmio_offset_param temp; + struct check_mmio_offset_param *params = &temp; + + params->offset = offset; + params->size = size; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_TRIO_OP_CHECK_MMIO_OFFSET); +} + +EXPORT_SYMBOL(gxio_trio_check_mmio_offset); diff --git a/arch/tile/gxio/iorpc_usb_host.c b/arch/tile/gxio/iorpc_usb_host.c new file mode 100644 index 0000000..cf3c3cc --- /dev/null +++ b/arch/tile/gxio/iorpc_usb_host.c @@ -0,0 +1,99 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#include "gxio/iorpc_usb_host.h" + +struct cfg_interrupt_param { + union iorpc_interrupt interrupt; +}; + +int gxio_usb_host_cfg_interrupt(gxio_usb_host_context_t * context, int inter_x, + int inter_y, int inter_ipi, int inter_event) +{ + struct cfg_interrupt_param temp; + struct cfg_interrupt_param *params = &temp; + + params->interrupt.kernel.x = inter_x; + params->interrupt.kernel.y = inter_y; + params->interrupt.kernel.ipi = inter_ipi; + params->interrupt.kernel.event = inter_event; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_USB_HOST_OP_CFG_INTERRUPT); +} + +EXPORT_SYMBOL(gxio_usb_host_cfg_interrupt); + +struct register_client_memory_param { + HV_PTE pte; + unsigned int flags; +}; + +int gxio_usb_host_register_client_memory(gxio_usb_host_context_t * context, + HV_PTE pte, unsigned int flags) +{ + struct register_client_memory_param temp; + struct register_client_memory_param *params = &temp; + + params->pte = pte; + params->flags = flags; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_USB_HOST_OP_REGISTER_CLIENT_MEMORY); +} + +EXPORT_SYMBOL(gxio_usb_host_register_client_memory); + +struct get_mmio_base_param { + HV_PTE base; +}; + +int gxio_usb_host_get_mmio_base(gxio_usb_host_context_t * context, HV_PTE *base) +{ + int __result; + struct get_mmio_base_param temp; + struct get_mmio_base_param *params = &temp; + + __result = + hv_dev_pread(context->fd, 0, (HV_VirtAddr) params, sizeof(*params), + GXIO_USB_HOST_OP_GET_MMIO_BASE); + *base = params->base; + + return __result; +} + +EXPORT_SYMBOL(gxio_usb_host_get_mmio_base); + +struct check_mmio_offset_param { + unsigned long offset; + unsigned long size; +}; + +int gxio_usb_host_check_mmio_offset(gxio_usb_host_context_t * context, + unsigned long offset, unsigned long size) +{ + struct check_mmio_offset_param temp; + struct check_mmio_offset_param *params = &temp; + + params->offset = offset; + params->size = size; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_USB_HOST_OP_CHECK_MMIO_OFFSET); +} + +EXPORT_SYMBOL(gxio_usb_host_check_mmio_offset); diff --git a/arch/tile/gxio/kiorpc.c b/arch/tile/gxio/kiorpc.c new file mode 100644 index 0000000..c8096aa --- /dev/null +++ b/arch/tile/gxio/kiorpc.c @@ -0,0 +1,61 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + * + * TILE-Gx IORPC support for kernel I/O drivers. + */ + +#include <linux/mmzone.h> +#include <linux/module.h> +#include <linux/io.h> +#include <gxio/iorpc_globals.h> +#include <gxio/kiorpc.h> + +#ifdef DEBUG_IORPC +#define TRACE(FMT, ...) pr_info(SIMPLE_MSG_LINE FMT, ## __VA_ARGS__) +#else +#define TRACE(...) +#endif + +/* Create kernel-VA-space MMIO mapping for an on-chip IO device. */ +void __iomem *iorpc_ioremap(int hv_fd, resource_size_t offset, + unsigned long size) +{ + pgprot_t mmio_base, prot = { 0 }; + unsigned long pfn; + int err; + + /* Look up the shim's lotar and base PA. */ + err = __iorpc_get_mmio_base(hv_fd, &mmio_base); + if (err) { + TRACE("get_mmio_base() failure: %d\n", err); + return NULL; + } + + /* Make sure the HV driver approves of our offset and size. */ + err = __iorpc_check_mmio_offset(hv_fd, offset, size); + if (err) { + TRACE("check_mmio_offset() failure: %d\n", err); + return NULL; + } + + /* + * mmio_base contains a base pfn and homing coordinates. Turn + * it into an MMIO pgprot and offset pfn. + */ + prot = hv_pte_set_lotar(prot, hv_pte_get_lotar(mmio_base)); + pfn = pte_pfn(mmio_base) + PFN_DOWN(offset); + + return ioremap_prot(PFN_PHYS(pfn), size, prot); +} + +EXPORT_SYMBOL(iorpc_ioremap); diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c new file mode 100644 index 0000000..e71c633 --- /dev/null +++ b/arch/tile/gxio/mpipe.c @@ -0,0 +1,545 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* + * Implementation of mpipe gxio calls. + */ + +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/module.h> + +#include <gxio/iorpc_globals.h> +#include <gxio/iorpc_mpipe.h> +#include <gxio/iorpc_mpipe_info.h> +#include <gxio/kiorpc.h> +#include <gxio/mpipe.h> + +/* HACK: Avoid pointless "shadow" warnings. */ +#define link link_shadow + +int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index) +{ + char file[32]; + + int fd; + int i; + + snprintf(file, sizeof(file), "mpipe/%d/iorpc", mpipe_index); + fd = hv_dev_open((HV_VirtAddr) file, 0); + if (fd < 0) { + if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX) + return fd; + else + return -ENODEV; + } + + context->fd = fd; + + /* Map in the MMIO space. */ + context->mmio_cfg_base = (void __force *) + iorpc_ioremap(fd, HV_MPIPE_CONFIG_MMIO_OFFSET, + HV_MPIPE_CONFIG_MMIO_SIZE); + if (context->mmio_cfg_base == NULL) + goto cfg_failed; + + context->mmio_fast_base = (void __force *) + iorpc_ioremap(fd, HV_MPIPE_FAST_MMIO_OFFSET, + HV_MPIPE_FAST_MMIO_SIZE); + if (context->mmio_fast_base == NULL) + goto fast_failed; + + /* Initialize the stacks. */ + for (i = 0; i < 8; i++) + context->__stacks.stacks[i] = 255; + + return 0; + + fast_failed: + iounmap((void __force __iomem *)(context->mmio_cfg_base)); + cfg_failed: + hv_dev_close(context->fd); + return -ENODEV; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_init); + +int gxio_mpipe_destroy(gxio_mpipe_context_t *context) +{ + iounmap((void __force __iomem *)(context->mmio_cfg_base)); + iounmap((void __force __iomem *)(context->mmio_fast_base)); + return hv_dev_close(context->fd); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_destroy); + +static int16_t gxio_mpipe_buffer_sizes[8] = + { 128, 256, 512, 1024, 1664, 4096, 10368, 16384 }; + +gxio_mpipe_buffer_size_enum_t gxio_mpipe_buffer_size_to_buffer_size_enum(size_t + size) +{ + int i; + for (i = 0; i < 7; i++) + if (size <= gxio_mpipe_buffer_sizes[i]) + break; + return i; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_buffer_size_to_buffer_size_enum); + +size_t gxio_mpipe_buffer_size_enum_to_buffer_size(gxio_mpipe_buffer_size_enum_t + buffer_size_enum) +{ + if (buffer_size_enum > 7) + buffer_size_enum = 7; + + return gxio_mpipe_buffer_sizes[buffer_size_enum]; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_buffer_size_enum_to_buffer_size); + +size_t gxio_mpipe_calc_buffer_stack_bytes(unsigned long buffers) +{ + const int BUFFERS_PER_LINE = 12; + + /* Count the number of cachlines. */ + unsigned long lines = + (buffers + BUFFERS_PER_LINE - 1) / BUFFERS_PER_LINE; + + /* Convert to bytes. */ + return lines * CHIP_L2_LINE_SIZE(); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_calc_buffer_stack_bytes); + +int gxio_mpipe_init_buffer_stack(gxio_mpipe_context_t *context, + unsigned int stack, + gxio_mpipe_buffer_size_enum_t + buffer_size_enum, void *mem, size_t mem_size, + unsigned int mem_flags) +{ + int result; + + memset(mem, 0, mem_size); + + result = gxio_mpipe_init_buffer_stack_aux(context, mem, mem_size, + mem_flags, stack, + buffer_size_enum); + if (result < 0) + return result; + + /* Save the stack. */ + context->__stacks.stacks[buffer_size_enum] = stack; + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_init_buffer_stack); + +int gxio_mpipe_init_notif_ring(gxio_mpipe_context_t *context, + unsigned int ring, + void *mem, size_t mem_size, + unsigned int mem_flags) +{ + return gxio_mpipe_init_notif_ring_aux(context, mem, mem_size, + mem_flags, ring); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_init_notif_ring); + +int gxio_mpipe_init_notif_group_and_buckets(gxio_mpipe_context_t *context, + unsigned int group, + unsigned int ring, + unsigned int num_rings, + unsigned int bucket, + unsigned int num_buckets, + gxio_mpipe_bucket_mode_t mode) +{ + int i; + int result; + + gxio_mpipe_bucket_info_t bucket_info = { { + .group = group, + .mode = mode, + } + }; + + gxio_mpipe_notif_group_bits_t bits = { {0} }; + + for (i = 0; i < num_rings; i++) + gxio_mpipe_notif_group_add_ring(&bits, ring + i); + + result = gxio_mpipe_init_notif_group(context, group, bits); + if (result != 0) + return result; + + for (i = 0; i < num_buckets; i++) { + bucket_info.notifring = ring + (i % num_rings); + + result = gxio_mpipe_init_bucket(context, bucket + i, + bucket_info); + if (result != 0) + return result; + } + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_init_notif_group_and_buckets); + +int gxio_mpipe_init_edma_ring(gxio_mpipe_context_t *context, + unsigned int ring, unsigned int channel, + void *mem, size_t mem_size, + unsigned int mem_flags) +{ + memset(mem, 0, mem_size); + + return gxio_mpipe_init_edma_ring_aux(context, mem, mem_size, mem_flags, + ring, channel); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_init_edma_ring); + +void gxio_mpipe_rules_init(gxio_mpipe_rules_t *rules, + gxio_mpipe_context_t *context) +{ + rules->context = context; + memset(&rules->list, 0, sizeof(rules->list)); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_rules_init); + +int gxio_mpipe_rules_begin(gxio_mpipe_rules_t *rules, + unsigned int bucket, unsigned int num_buckets, + gxio_mpipe_rules_stacks_t *stacks) +{ + int i; + int stack = 255; + + gxio_mpipe_rules_list_t *list = &rules->list; + + /* Current rule. */ + gxio_mpipe_rules_rule_t *rule = + (gxio_mpipe_rules_rule_t *) (list->rules + list->head); + + unsigned int head = list->tail; + + /* + * Align next rule properly. + *Note that "dmacs_and_vlans" will also be aligned. + */ + unsigned int pad = 0; + while (((head + pad) % __alignof__(gxio_mpipe_rules_rule_t)) != 0) + pad++; + + /* + * Verify room. + * ISSUE: Mark rules as broken on error? + */ + if (head + pad + sizeof(*rule) >= sizeof(list->rules)) + return GXIO_MPIPE_ERR_RULES_FULL; + + /* Verify num_buckets is a power of 2. */ + if (__builtin_popcount(num_buckets) != 1) + return GXIO_MPIPE_ERR_RULES_INVALID; + + /* Add padding to previous rule. */ + rule->size += pad; + + /* Start a new rule. */ + list->head = head + pad; + + rule = (gxio_mpipe_rules_rule_t *) (list->rules + list->head); + + /* Default some values. */ + rule->headroom = 2; + rule->tailroom = 0; + rule->capacity = 16384; + + /* Save the bucket info. */ + rule->bucket_mask = num_buckets - 1; + rule->bucket_first = bucket; + + for (i = 8 - 1; i >= 0; i--) { + int maybe = + stacks ? stacks->stacks[i] : rules->context->__stacks. + stacks[i]; + if (maybe != 255) + stack = maybe; + rule->stacks.stacks[i] = stack; + } + + if (stack == 255) + return GXIO_MPIPE_ERR_RULES_INVALID; + + /* NOTE: Only entries at the end of the array can be 255. */ + for (i = 8 - 1; i > 0; i--) { + if (rule->stacks.stacks[i] == 255) { + rule->stacks.stacks[i] = stack; + rule->capacity = + gxio_mpipe_buffer_size_enum_to_buffer_size(i - + 1); + } + } + + rule->size = sizeof(*rule); + list->tail = list->head + rule->size; + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_rules_begin); + +int gxio_mpipe_rules_add_channel(gxio_mpipe_rules_t *rules, + unsigned int channel) +{ + gxio_mpipe_rules_list_t *list = &rules->list; + + gxio_mpipe_rules_rule_t *rule = + (gxio_mpipe_rules_rule_t *) (list->rules + list->head); + + /* Verify channel. */ + if (channel >= 32) + return GXIO_MPIPE_ERR_RULES_INVALID; + + /* Verify begun. */ + if (list->tail == 0) + return GXIO_MPIPE_ERR_RULES_EMPTY; + + rule->channel_bits |= (1UL << channel); + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_rules_add_channel); + +int gxio_mpipe_rules_set_headroom(gxio_mpipe_rules_t *rules, uint8_t headroom) +{ + gxio_mpipe_rules_list_t *list = &rules->list; + + gxio_mpipe_rules_rule_t *rule = + (gxio_mpipe_rules_rule_t *) (list->rules + list->head); + + /* Verify begun. */ + if (list->tail == 0) + return GXIO_MPIPE_ERR_RULES_EMPTY; + + rule->headroom = headroom; + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_rules_set_headroom); + +int gxio_mpipe_rules_commit(gxio_mpipe_rules_t *rules) +{ + gxio_mpipe_rules_list_t *list = &rules->list; + unsigned int size = + offsetof(gxio_mpipe_rules_list_t, rules) + list->tail; + return gxio_mpipe_commit_rules(rules->context, list, size); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_rules_commit); + +int gxio_mpipe_iqueue_init(gxio_mpipe_iqueue_t *iqueue, + gxio_mpipe_context_t *context, + unsigned int ring, + void *mem, size_t mem_size, unsigned int mem_flags) +{ + /* The init call below will verify that "mem_size" is legal. */ + unsigned int num_entries = mem_size / sizeof(gxio_mpipe_idesc_t); + + iqueue->context = context; + iqueue->idescs = (gxio_mpipe_idesc_t *)mem; + iqueue->ring = ring; + iqueue->num_entries = num_entries; + iqueue->mask_num_entries = num_entries - 1; + iqueue->log2_num_entries = __builtin_ctz(num_entries); + iqueue->head = 1; +#ifdef __BIG_ENDIAN__ + iqueue->swapped = 0; +#endif + + /* Initialize the "tail". */ + __gxio_mmio_write(mem, iqueue->head); + + return gxio_mpipe_init_notif_ring(context, ring, mem, mem_size, + mem_flags); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_iqueue_init); + +int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, + gxio_mpipe_context_t *context, + unsigned int edma_ring_id, + unsigned int channel, + void *mem, unsigned int mem_size, + unsigned int mem_flags) +{ + /* The init call below will verify that "mem_size" is legal. */ + unsigned int num_entries = mem_size / sizeof(gxio_mpipe_edesc_t); + + /* Offset used to read number of completed commands. */ + MPIPE_EDMA_POST_REGION_ADDR_t offset; + + int result = gxio_mpipe_init_edma_ring(context, edma_ring_id, channel, + mem, mem_size, mem_flags); + if (result < 0) + return result; + + memset(equeue, 0, sizeof(*equeue)); + + offset.word = 0; + offset.region = + MPIPE_MMIO_ADDR__REGION_VAL_EDMA - + MPIPE_MMIO_ADDR__REGION_VAL_IDMA; + offset.ring = edma_ring_id; + + __gxio_dma_queue_init(&equeue->dma_queue, + context->mmio_fast_base + offset.word, + num_entries); + equeue->edescs = mem; + equeue->mask_num_entries = num_entries - 1; + equeue->log2_num_entries = __builtin_ctz(num_entries); + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_equeue_init); + +int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context, + const struct timespec *ts) +{ + cycles_t cycles = get_cycles(); + return gxio_mpipe_set_timestamp_aux(context, (uint64_t)ts->tv_sec, + (uint64_t)ts->tv_nsec, + (uint64_t)cycles); +} + +int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context, + struct timespec *ts) +{ + int ret; + cycles_t cycles_prev, cycles_now, clock_rate; + cycles_prev = get_cycles(); + ret = gxio_mpipe_get_timestamp_aux(context, (uint64_t *)&ts->tv_sec, + (uint64_t *)&ts->tv_nsec, + (uint64_t *)&cycles_now); + if (ret < 0) { + return ret; + } + + clock_rate = get_clock_rate(); + ts->tv_nsec -= (cycles_now - cycles_prev) * 1000000000LL / clock_rate; + if (ts->tv_nsec < 0) { + ts->tv_nsec += 1000000000LL; + ts->tv_sec -= 1; + } + return ret; +} + +int gxio_mpipe_adjust_timestamp(gxio_mpipe_context_t *context, int64_t delta) +{ + return gxio_mpipe_adjust_timestamp_aux(context, delta); +} + +/* Get our internal context used for link name access. This context is + * special in that it is not associated with an mPIPE service domain. + */ +static gxio_mpipe_context_t *_gxio_get_link_context(void) +{ + static gxio_mpipe_context_t context; + static gxio_mpipe_context_t *contextp; + static int tried_open = 0; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + + if (!tried_open) { + int i = 0; + tried_open = 1; + + /* + * "4" here is the maximum possible number of mPIPE shims; it's + * an exaggeration but we shouldn't ever go beyond 2 anyway. + */ + for (i = 0; i < 4; i++) { + char file[80]; + + snprintf(file, sizeof(file), "mpipe/%d/iorpc_info", i); + context.fd = hv_dev_open((HV_VirtAddr) file, 0); + if (context.fd < 0) + continue; + + contextp = &context; + break; + } + } + + mutex_unlock(&mutex); + + return contextp; +} + +int gxio_mpipe_link_enumerate_mac(int idx, char *link_name, uint8_t *link_mac) +{ + int rv; + _gxio_mpipe_link_name_t name; + _gxio_mpipe_link_mac_t mac; + + gxio_mpipe_context_t *context = _gxio_get_link_context(); + if (!context) + return GXIO_ERR_NO_DEVICE; + + rv = gxio_mpipe_info_enumerate_aux(context, idx, &name, &mac); + if (rv >= 0) { + strncpy(link_name, name.name, sizeof(name.name)); + memcpy(link_mac, mac.mac, sizeof(mac.mac)); + } + + return rv; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_link_enumerate_mac); + +int gxio_mpipe_link_open(gxio_mpipe_link_t *link, + gxio_mpipe_context_t *context, const char *link_name, + unsigned int flags) +{ + _gxio_mpipe_link_name_t name; + int rv; + + strncpy(name.name, link_name, sizeof(name.name)); + name.name[GXIO_MPIPE_LINK_NAME_LEN - 1] = '\0'; + + rv = gxio_mpipe_link_open_aux(context, name, flags); + if (rv < 0) + return rv; + + link->context = context; + link->channel = rv >> 8; + link->mac = rv & 0xFF; + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_link_open); + +int gxio_mpipe_link_close(gxio_mpipe_link_t *link) +{ + return gxio_mpipe_link_close_aux(link->context, link->mac); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_link_close); diff --git a/arch/tile/gxio/trio.c b/arch/tile/gxio/trio.c new file mode 100644 index 0000000..69f0b8d --- /dev/null +++ b/arch/tile/gxio/trio.c @@ -0,0 +1,49 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* + * Implementation of trio gxio calls. + */ + +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/module.h> + +#include <gxio/trio.h> +#include <gxio/iorpc_globals.h> +#include <gxio/iorpc_trio.h> +#include <gxio/kiorpc.h> + +int gxio_trio_init(gxio_trio_context_t *context, unsigned int trio_index) +{ + char file[32]; + int fd; + + snprintf(file, sizeof(file), "trio/%d/iorpc", trio_index); + fd = hv_dev_open((HV_VirtAddr) file, 0); + if (fd < 0) { + context->fd = -1; + + if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX) + return fd; + else + return -ENODEV; + } + + context->fd = fd; + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_trio_init); diff --git a/arch/tile/gxio/usb_host.c b/arch/tile/gxio/usb_host.c new file mode 100644 index 0000000..66b002f --- /dev/null +++ b/arch/tile/gxio/usb_host.c @@ -0,0 +1,91 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* + * + * Implementation of USB gxio calls. + */ + +#include <linux/io.h> +#include <linux/errno.h> +#include <linux/module.h> + +#include <gxio/iorpc_globals.h> +#include <gxio/iorpc_usb_host.h> +#include <gxio/kiorpc.h> +#include <gxio/usb_host.h> + +int gxio_usb_host_init(gxio_usb_host_context_t * context, int usb_index, + int is_ehci) +{ + char file[32]; + int fd; + + if (is_ehci) + snprintf(file, sizeof(file), "usb_host/%d/iorpc/ehci", + usb_index); + else + snprintf(file, sizeof(file), "usb_host/%d/iorpc/ohci", + usb_index); + + fd = hv_dev_open((HV_VirtAddr) file, 0); + if (fd < 0) { + if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX) + return fd; + else + return -ENODEV; + } + + context->fd = fd; + + // Map in the MMIO space. + context->mmio_base = + (void __force *)iorpc_ioremap(fd, 0, HV_USB_HOST_MMIO_SIZE); + + if (context->mmio_base == NULL) { + hv_dev_close(context->fd); + return -ENODEV; + } + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_usb_host_init); + +int gxio_usb_host_destroy(gxio_usb_host_context_t * context) +{ + iounmap((void __force __iomem *)(context->mmio_base)); + hv_dev_close(context->fd); + + context->mmio_base = NULL; + context->fd = -1; + + return 0; +} + +EXPORT_SYMBOL_GPL(gxio_usb_host_destroy); + +void *gxio_usb_host_get_reg_start(gxio_usb_host_context_t * context) +{ + return context->mmio_base; +} + +EXPORT_SYMBOL_GPL(gxio_usb_host_get_reg_start); + +size_t gxio_usb_host_get_reg_len(gxio_usb_host_context_t * context) +{ + return HV_USB_HOST_MMIO_SIZE; +} + +EXPORT_SYMBOL_GPL(gxio_usb_host_get_reg_len); diff --git a/arch/tile/include/arch/mpipe.h b/arch/tile/include/arch/mpipe.h new file mode 100644 index 0000000..8a33912 --- /dev/null +++ b/arch/tile/include/arch/mpipe.h @@ -0,0 +1,359 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_MPIPE_H__ +#define __ARCH_MPIPE_H__ + +#include <arch/abi.h> +#include <arch/mpipe_def.h> + +#ifndef __ASSEMBLER__ + +/* + * MMIO Ingress DMA Release Region Address. + * This is a description of the physical addresses used to manipulate ingress + * credit counters. Accesses to this address space should use an address of + * this form and a value like that specified in IDMA_RELEASE_REGION_VAL. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Reserved. */ + uint_reg_t __reserved_0 : 3; + /* NotifRing to be released */ + uint_reg_t ring : 8; + /* Bucket to be released */ + uint_reg_t bucket : 13; + /* Enable NotifRing release */ + uint_reg_t ring_enable : 1; + /* Enable Bucket release */ + uint_reg_t bucket_enable : 1; + /* + * This field of the address selects the region (address space) to be + * accessed. For the iDMA release region, this field must be 4. + */ + uint_reg_t region : 3; + /* Reserved. */ + uint_reg_t __reserved_1 : 6; + /* This field of the address indexes the 32 entry service domain table. */ + uint_reg_t svc_dom : 5; + /* Reserved. */ + uint_reg_t __reserved_2 : 24; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_2 : 24; + uint_reg_t svc_dom : 5; + uint_reg_t __reserved_1 : 6; + uint_reg_t region : 3; + uint_reg_t bucket_enable : 1; + uint_reg_t ring_enable : 1; + uint_reg_t bucket : 13; + uint_reg_t ring : 8; + uint_reg_t __reserved_0 : 3; +#endif + }; + + uint_reg_t word; +} MPIPE_IDMA_RELEASE_REGION_ADDR_t; + +/* + * MMIO Ingress DMA Release Region Value - Release NotifRing and/or Bucket. + * Provides release of the associated NotifRing. The address of the MMIO + * operation is described in IDMA_RELEASE_REGION_ADDR. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* + * Number of packets being released. The load balancer's count of + * inflight packets will be decremented by this amount for the associated + * Bucket and/or NotifRing + */ + uint_reg_t count : 16; + /* Reserved. */ + uint_reg_t __reserved : 48; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved : 48; + uint_reg_t count : 16; +#endif + }; + + uint_reg_t word; +} MPIPE_IDMA_RELEASE_REGION_VAL_t; + +/* + * MMIO Buffer Stack Manager Region Address. + * This MMIO region is used for posting or fetching buffers to/from the + * buffer stack manager. On an MMIO load, this pops a buffer descriptor from + * the top of stack if one is available. On an MMIO store, this pushes a + * buffer to the stack. The value read or written is described in + * BSM_REGION_VAL. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Reserved. */ + uint_reg_t __reserved_0 : 3; + /* BufferStack being accessed. */ + uint_reg_t stack : 5; + /* Reserved. */ + uint_reg_t __reserved_1 : 18; + /* + * This field of the address selects the region (address space) to be + * accessed. For the buffer stack manager region, this field must be 6. + */ + uint_reg_t region : 3; + /* Reserved. */ + uint_reg_t __reserved_2 : 6; + /* This field of the address indexes the 32 entry service domain table. */ + uint_reg_t svc_dom : 5; + /* Reserved. */ + uint_reg_t __reserved_3 : 24; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_3 : 24; + uint_reg_t svc_dom : 5; + uint_reg_t __reserved_2 : 6; + uint_reg_t region : 3; + uint_reg_t __reserved_1 : 18; + uint_reg_t stack : 5; + uint_reg_t __reserved_0 : 3; +#endif + }; + + uint_reg_t word; +} MPIPE_BSM_REGION_ADDR_t; + +/* + * MMIO Buffer Stack Manager Region Value. + * This MMIO region is used for posting or fetching buffers to/from the + * buffer stack manager. On an MMIO load, this pops a buffer descriptor from + * the top of stack if one is available. On an MMIO store, this pushes a + * buffer to the stack. The address of the MMIO operation is described in + * BSM_REGION_ADDR. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Reserved. */ + uint_reg_t __reserved_0 : 7; + /* + * Base virtual address of the buffer. Must be sign extended by consumer. + */ + int_reg_t va : 35; + /* Reserved. */ + uint_reg_t __reserved_1 : 6; + /* + * Index of the buffer stack to which this buffer belongs. Ignored on + * writes since the offset bits specify the stack being accessed. + */ + uint_reg_t stack_idx : 5; + /* Reserved. */ + uint_reg_t __reserved_2 : 5; + /* + * Reads as one to indicate that this is a hardware managed buffer. + * Ignored on writes since all buffers on a given stack are the same size. + */ + uint_reg_t hwb : 1; + /* + * Encoded size of buffer (ignored on writes): + * 0 = 128 bytes + * 1 = 256 bytes + * 2 = 512 bytes + * 3 = 1024 bytes + * 4 = 1664 bytes + * 5 = 4096 bytes + * 6 = 10368 bytes + * 7 = 16384 bytes + */ + uint_reg_t size : 3; + /* + * Valid indication for the buffer. Ignored on writes. + * 0 : Valid buffer descriptor popped from stack. + * 3 : Could not pop a buffer from the stack. Either the stack is empty, + * or the hardware's prefetch buffer is empty for this stack. + */ + uint_reg_t c : 2; +#else /* __BIG_ENDIAN__ */ + uint_reg_t c : 2; + uint_reg_t size : 3; + uint_reg_t hwb : 1; + uint_reg_t __reserved_2 : 5; + uint_reg_t stack_idx : 5; + uint_reg_t __reserved_1 : 6; + int_reg_t va : 35; + uint_reg_t __reserved_0 : 7; +#endif + }; + + uint_reg_t word; +} MPIPE_BSM_REGION_VAL_t; + +/* + * MMIO Egress DMA Post Region Address. + * Used to post descriptor locations to the eDMA descriptor engine. The + * value to be written is described in EDMA_POST_REGION_VAL + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Reserved. */ + uint_reg_t __reserved_0 : 3; + /* eDMA ring being accessed */ + uint_reg_t ring : 5; + /* Reserved. */ + uint_reg_t __reserved_1 : 18; + /* + * This field of the address selects the region (address space) to be + * accessed. For the egress DMA post region, this field must be 5. + */ + uint_reg_t region : 3; + /* Reserved. */ + uint_reg_t __reserved_2 : 6; + /* This field of the address indexes the 32 entry service domain table. */ + uint_reg_t svc_dom : 5; + /* Reserved. */ + uint_reg_t __reserved_3 : 24; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_3 : 24; + uint_reg_t svc_dom : 5; + uint_reg_t __reserved_2 : 6; + uint_reg_t region : 3; + uint_reg_t __reserved_1 : 18; + uint_reg_t ring : 5; + uint_reg_t __reserved_0 : 3; +#endif + }; + + uint_reg_t word; +} MPIPE_EDMA_POST_REGION_ADDR_t; + +/* + * MMIO Egress DMA Post Region Value. + * Used to post descriptor locations to the eDMA descriptor engine. The + * address is described in EDMA_POST_REGION_ADDR. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* + * For writes, this specifies the current ring tail pointer prior to any + * post. For example, to post 1 or more descriptors starting at location + * 23, this would contain 23 (not 24). On writes, this index must be + * masked based on the ring size. The new tail pointer after this post + * is COUNT+RING_IDX (masked by the ring size). + * + * For reads, this provides the hardware descriptor fetcher's head + * pointer. The descriptors prior to the head pointer, however, may not + * yet have been processed so this indicator is only used to determine + * how full the ring is and if software may post more descriptors. + */ + uint_reg_t ring_idx : 16; + /* + * For writes, this specifies number of contiguous descriptors that are + * being posted. Software may post up to RingSize descriptors with a + * single MMIO store. A zero in this field on a write will "wake up" an + * eDMA ring and cause it fetch descriptors regardless of the hardware's + * current view of the state of the tail pointer. + * + * For reads, this field provides a rolling count of the number of + * descriptors that have been completely processed. This may be used by + * software to determine when buffers associated with a descriptor may be + * returned or reused. When the ring's flush bit is cleared by software + * (after having been set by HW or SW), the COUNT will be cleared. + */ + uint_reg_t count : 16; + /* + * For writes, this specifies the generation number of the tail being + * posted. Note that if tail+cnt wraps to the beginning of the ring, the + * eDMA hardware assumes that the descriptors posted at the beginning of + * the ring are also valid so it is okay to post around the wrap point. + * + * For reads, this is the current generation number. Valid descriptors + * will have the inverse of this generation number. + */ + uint_reg_t gen : 1; + /* Reserved. */ + uint_reg_t __reserved : 31; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved : 31; + uint_reg_t gen : 1; + uint_reg_t count : 16; + uint_reg_t ring_idx : 16; +#endif + }; + + uint_reg_t word; +} MPIPE_EDMA_POST_REGION_VAL_t; + +/* + * Load Balancer Bucket Status Data. + * Read/Write data for load balancer Bucket-Status Table. 4160 entries + * indexed by LBL_INIT_CTL.IDX when LBL_INIT_CTL.STRUCT_SEL is BSTS_TBL + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* NotifRing currently assigned to this bucket. */ + uint_reg_t notifring : 8; + /* Current reference count. */ + uint_reg_t count : 16; + /* Group associated with this bucket. */ + uint_reg_t group : 5; + /* Mode select for this bucket. */ + uint_reg_t mode : 3; + /* Reserved. */ + uint_reg_t __reserved : 32; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved : 32; + uint_reg_t mode : 3; + uint_reg_t group : 5; + uint_reg_t count : 16; + uint_reg_t notifring : 8; +#endif + }; + + uint_reg_t word; +} MPIPE_LBL_INIT_DAT_BSTS_TBL_t; +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_MPIPE_H__) */ diff --git a/arch/tile/include/arch/mpipe_constants.h b/arch/tile/include/arch/mpipe_constants.h new file mode 100644 index 0000000..410a040 --- /dev/null +++ b/arch/tile/include/arch/mpipe_constants.h @@ -0,0 +1,42 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + + +#ifndef __ARCH_MPIPE_CONSTANTS_H__ +#define __ARCH_MPIPE_CONSTANTS_H__ + +#define MPIPE_NUM_CLASSIFIERS 10 +#define MPIPE_CLS_MHZ 1200 + +#define MPIPE_NUM_EDMA_RINGS 32 + +#define MPIPE_NUM_SGMII_MACS 16 +#define MPIPE_NUM_XAUI_MACS 4 +#define MPIPE_NUM_LOOPBACK_CHANNELS 4 +#define MPIPE_NUM_NON_LB_CHANNELS 28 + +#define MPIPE_NUM_IPKT_BLOCKS 1536 + +#define MPIPE_NUM_BUCKETS 4160 + +#define MPIPE_NUM_NOTIF_RINGS 256 + +#define MPIPE_NUM_NOTIF_GROUPS 32 + +#define MPIPE_NUM_TLBS_PER_ASID 16 +#define MPIPE_TLB_IDX_WIDTH 4 + +#define MPIPE_MMIO_NUM_SVC_DOM 32 + +#endif /* __ARCH_MPIPE_CONSTANTS_H__ */ diff --git a/arch/tile/include/arch/mpipe_def.h b/arch/tile/include/arch/mpipe_def.h new file mode 100644 index 0000000..c3d3021 --- /dev/null +++ b/arch/tile/include/arch/mpipe_def.h @@ -0,0 +1,39 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_MPIPE_DEF_H__ +#define __ARCH_MPIPE_DEF_H__ +#define MPIPE_MMIO_ADDR__REGION_SHIFT 26 +#define MPIPE_MMIO_ADDR__REGION_VAL_CFG 0x0 +#define MPIPE_MMIO_ADDR__REGION_VAL_IDMA 0x4 +#define MPIPE_MMIO_ADDR__REGION_VAL_EDMA 0x5 +#define MPIPE_MMIO_ADDR__REGION_VAL_BSM 0x6 +#define MPIPE_BSM_REGION_VAL__VA_SHIFT 7 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_128 0x0 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_256 0x1 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_512 0x2 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_1024 0x3 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_1664 0x4 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_4096 0x5 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_10368 0x6 +#define MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_16384 0x7 +#define MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_DFA 0x0 +#define MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_FIXED 0x1 +#define MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_ALWAYS_PICK 0x2 +#define MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_STICKY 0x3 +#define MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_STICKY_RAND 0x7 +#define MPIPE_LBL_NR_STATE__FIRST_WORD 0x2138 +#endif /* !defined(__ARCH_MPIPE_DEF_H__) */ diff --git a/arch/tile/include/arch/mpipe_shm.h b/arch/tile/include/arch/mpipe_shm.h new file mode 100644 index 0000000..f2e9e12 --- /dev/null +++ b/arch/tile/include/arch/mpipe_shm.h @@ -0,0 +1,509 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + + +#ifndef __ARCH_MPIPE_SHM_H__ +#define __ARCH_MPIPE_SHM_H__ + +#include <arch/abi.h> +#include <arch/mpipe_shm_def.h> + +#ifndef __ASSEMBLER__ +/** + * MPIPE eDMA Descriptor. + * The eDMA descriptor is written by software and consumed by hardware. It + * is used to specify the location of egress packet data to be sent out of + * the chip via one of the packet interfaces. + */ + +__extension__ +typedef union +{ + struct + { + /* Word 0 */ + +#ifndef __BIG_ENDIAN__ + /** + * Generation number. Used to indicate a valid descriptor in ring. When + * a new descriptor is written into the ring, software must toggle this + * bit. The net effect is that the GEN bit being written into new + * descriptors toggles each time the ring tail pointer wraps. + */ + uint_reg_t gen : 1; + /** Reserved. Must be zero. */ + uint_reg_t r0 : 7; + /** Checksum generation enabled for this transfer. */ + uint_reg_t csum : 1; + /** + * Nothing to be sent. Used, for example, when software has dropped a + * packet but still wishes to return all of the associated buffers. + */ + uint_reg_t ns : 1; + /** + * Notification interrupt will be delivered when packet has been egressed. + */ + uint_reg_t notif : 1; + /** + * Boundary indicator. When 1, this transfer includes the EOP for this + * command. Must be clear on all but the last descriptor for an egress + * packet. + */ + uint_reg_t bound : 1; + /** Reserved. Must be zero. */ + uint_reg_t r1 : 4; + /** + * Number of bytes to be sent for this descriptor. When zero, no data + * will be moved and the buffer descriptor will be ignored. If the + * buffer descriptor indicates that it is chained, the low 7 bits of the + * VA indicate the offset within the first buffer (e.g. 127 bytes is the + * maximum offset into the first buffer). If the size exceeds a single + * buffer, subsequent buffer descriptors will be fetched prior to + * processing the next eDMA descriptor in the ring. + */ + uint_reg_t xfer_size : 14; + /** Reserved. Must be zero. */ + uint_reg_t r2 : 2; + /** + * Destination of checksum relative to CSUM_START relative to the first + * byte moved by this descriptor. Must be zero if CSUM=0 in this + * descriptor. Must be less than XFER_SIZE (e.g. the first byte of the + * CSUM_DEST must be within the span of this descriptor). + */ + uint_reg_t csum_dest : 8; + /** + * Start byte of checksum relative to the first byte moved by this + * descriptor. If this is not the first descriptor for the egress + * packet, CSUM_START is still relative to the first byte in this + * descriptor. Must be zero if CSUM=0 in this descriptor. + */ + uint_reg_t csum_start : 8; + /** + * Initial value for 16-bit 1's compliment checksum if enabled via CSUM. + * Specified in network order. That is, bits[7:0] will be added to the + * byte pointed to by CSUM_START and bits[15:8] will be added to the byte + * pointed to by CSUM_START+1 (with appropriate 1's compliment carries). + * Must be zero if CSUM=0 in this descriptor. + */ + uint_reg_t csum_seed : 16; +#else /* __BIG_ENDIAN__ */ + uint_reg_t csum_seed : 16; + uint_reg_t csum_start : 8; + uint_reg_t csum_dest : 8; + uint_reg_t r2 : 2; + uint_reg_t xfer_size : 14; + uint_reg_t r1 : 4; + uint_reg_t bound : 1; + uint_reg_t notif : 1; + uint_reg_t ns : 1; + uint_reg_t csum : 1; + uint_reg_t r0 : 7; + uint_reg_t gen : 1; +#endif + + /* Word 1 */ + +#ifndef __BIG_ENDIAN__ + /** Virtual address. Must be sign extended by consumer. */ + int_reg_t va : 42; + /** Reserved. */ + uint_reg_t __reserved_0 : 6; + /** Index of the buffer stack to which this buffer belongs. */ + uint_reg_t stack_idx : 5; + /** Reserved. */ + uint_reg_t __reserved_1 : 3; + /** + * Instance ID. For devices that support more than one mPIPE instance, + * this field indicates the buffer owner. If the INST field does not + * match the mPIPE's instance number when a packet is egressed, buffers + * with HWB set will be returned to the other mPIPE instance. + */ + uint_reg_t inst : 1; + /** Reserved. */ + uint_reg_t __reserved_2 : 1; + /** + * Always set to one by hardware in iDMA packet descriptors. For eDMA, + * indicates whether the buffer will be released to the buffer stack + * manager. When 0, software is responsible for releasing the buffer. + */ + uint_reg_t hwb : 1; + /** + * Encoded size of buffer. Set by the ingress hardware for iDMA packet + * descriptors. For eDMA descriptors, indicates the buffer size if .c + * indicates a chained packet. If an eDMA descriptor is not chained and + * the .hwb bit is not set, this field is ignored and the size is + * specified by the .xfer_size field. + * 0 = 128 bytes + * 1 = 256 bytes + * 2 = 512 bytes + * 3 = 1024 bytes + * 4 = 1664 bytes + * 5 = 4096 bytes + * 6 = 10368 bytes + * 7 = 16384 bytes + */ + uint_reg_t size : 3; + /** + * Chaining configuration for the buffer. Indicates that an ingress + * packet or egress command is chained across multiple buffers, with each + * buffer's size indicated by the .size field. + */ + uint_reg_t c : 2; +#else /* __BIG_ENDIAN__ */ + uint_reg_t c : 2; + uint_reg_t size : 3; + uint_reg_t hwb : 1; + uint_reg_t __reserved_2 : 1; + uint_reg_t inst : 1; + uint_reg_t __reserved_1 : 3; + uint_reg_t stack_idx : 5; + uint_reg_t __reserved_0 : 6; + int_reg_t va : 42; +#endif + + }; + + /** Word access */ + uint_reg_t words[2]; +} MPIPE_EDMA_DESC_t; + +/** + * MPIPE Packet Descriptor. + * The packet descriptor is filled by the mPIPE's classification, + * load-balancing, and buffer management services. Some fields are consumed + * by mPIPE hardware, and others are consumed by Tile software. + */ + +__extension__ +typedef union +{ + struct + { + /* Word 0 */ + +#ifndef __BIG_ENDIAN__ + /** + * Notification ring into which this packet descriptor is written. + * Typically written by load balancer, but can be overridden by + * classification program if NR is asserted. + */ + uint_reg_t notif_ring : 8; + /** Source channel for this packet. Written by mPIPE DMA hardware. */ + uint_reg_t channel : 5; + /** Reserved. */ + uint_reg_t __reserved_0 : 1; + /** + * MAC Error. + * Generated by the MAC interface. Asserted if there was an overrun of + * the MAC's receive FIFO. This condition generally only occurs if the + * mPIPE clock is running too slowly. + */ + uint_reg_t me : 1; + /** + * Truncation Error. + * Written by the iDMA hardware. Asserted if packet was truncated due to + * insufficient space in iPkt buffer + */ + uint_reg_t tr : 1; + /** + * Written by the iDMA hardware. Indicates the number of bytes written + * to Tile memory. In general, this is the actual size of the packet as + * received from the MAC. But if the packet is truncated due to running + * out of buffers or due to the iPkt buffer filling up, then the L2_SIZE + * will be reduced to reflect the actual number of valid bytes written to + * Tile memory. + */ + uint_reg_t l2_size : 14; + /** + * CRC Error. + * Generated by the MAC. Asserted if MAC indicated an L2 CRC error or + * other L2 error (bad length etc.) on the packet. + */ + uint_reg_t ce : 1; + /** + * Cut Through. + * Written by the iDMA hardware. Asserted if packet was not completely + * received before being sent to classifier. L2_Size will indicate + * number of bytes received so far. + */ + uint_reg_t ct : 1; + /** + * Written by the classification program. Used by the load balancer to + * select the ring into which this packet descriptor is written. + */ + uint_reg_t bucket_id : 13; + /** Reserved. */ + uint_reg_t __reserved_1 : 3; + /** + * Checksum. + * Written by classification program. When 1, the checksum engine will + * perform checksum based on the CSUM_SEED, CSUM_START, and CSUM_BYTES + * fields. The result will be placed in CSUM_VAL. + */ + uint_reg_t cs : 1; + /** + * Notification Ring Select. + * Written by the classification program. When 1, the NotifRingIDX is + * set by classification program rather than being set by load balancer. + */ + uint_reg_t nr : 1; + /** + * Written by classification program. Indicates whether packet and + * descriptor should both be dropped, both be delivered, or only the + * descriptor should be delivered. + */ + uint_reg_t dest : 2; + /** + * General Purpose Sequence Number Enable. + * Written by the classification program. When 1, the GP_SQN_SEL field + * contains the sequence number selector and the GP_SQN field will be + * replaced with the associated sequence number. When clear, the GP_SQN + * field is left intact and be used as "Custom" bytes. + */ + uint_reg_t sq : 1; + /** + * TimeStamp Enable. + * Enable TimeStamp insertion. When clear, timestamp field may be filled + * with custom data by classifier. When set, hardware inserts the + * timestamp when the start of packet is received from the MAC. + */ + uint_reg_t ts : 1; + /** + * Packet Sequence Number Enable. + * Enable PacketSQN insertion. When clear, PacketSQN field may be filled + * with custom data by classifier. When set, hardware inserts the packet + * sequence number when the packet descriptor is written to a + * notification ring. + */ + uint_reg_t ps : 1; + /** + * Buffer Error. + * Written by the iDMA hardware. Asserted if iDMA ran out of buffers + * while writing the packet. Software must still return any buffer + * descriptors whose C field indicates a valid descriptor was consumed. + */ + uint_reg_t be : 1; + /** + * Written by the classification program. The associated counter is + * incremented when the packet is sent. + */ + uint_reg_t ctr0 : 5; + /** Reserved. */ + uint_reg_t __reserved_2 : 3; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_2 : 3; + uint_reg_t ctr0 : 5; + uint_reg_t be : 1; + uint_reg_t ps : 1; + uint_reg_t ts : 1; + uint_reg_t sq : 1; + uint_reg_t dest : 2; + uint_reg_t nr : 1; + uint_reg_t cs : 1; + uint_reg_t __reserved_1 : 3; + uint_reg_t bucket_id : 13; + uint_reg_t ct : 1; + uint_reg_t ce : 1; + uint_reg_t l2_size : 14; + uint_reg_t tr : 1; + uint_reg_t me : 1; + uint_reg_t __reserved_0 : 1; + uint_reg_t channel : 5; + uint_reg_t notif_ring : 8; +#endif + + /* Word 1 */ + +#ifndef __BIG_ENDIAN__ + /** + * Written by the classification program. The associated counter is + * incremented when the packet is sent. + */ + uint_reg_t ctr1 : 5; + /** Reserved. */ + uint_reg_t __reserved_3 : 3; + /** + * Written by classification program. Indicates the start byte for + * checksum. Relative to 1st byte received from MAC. + */ + uint_reg_t csum_start : 8; + /** + * Checksum seed written by classification program. Overwritten with + * resultant checksum if CS bit is asserted. The endianness of the CSUM + * value bits when viewed by Tile software match the packet byte order. + * That is, bits[7:0] of the resulting checksum value correspond to + * earlier (more significant) bytes in the packet. To avoid classifier + * software from having to byte swap the CSUM_SEED, the iDMA checksum + * engine byte swaps the classifier's result before seeding the checksum + * calculation. Thus, the CSUM_START byte of packet data is added to + * bits[15:8] of the CSUM_SEED field generated by the classifier. This + * byte swap will be visible to Tile software if the CS bit is clear. + */ + uint_reg_t csum_seed_val : 16; + /** + * Written by the classification program. Not interpreted by mPIPE + * hardware. + */ + uint_reg_t custom0 : 32; +#else /* __BIG_ENDIAN__ */ + uint_reg_t custom0 : 32; + uint_reg_t csum_seed_val : 16; + uint_reg_t csum_start : 8; + uint_reg_t __reserved_3 : 3; + uint_reg_t ctr1 : 5; +#endif + + /* Word 2 */ + +#ifndef __BIG_ENDIAN__ + /** + * Written by the classification program. Not interpreted by mPIPE + * hardware. + */ + uint_reg_t custom1 : 64; +#else /* __BIG_ENDIAN__ */ + uint_reg_t custom1 : 64; +#endif + + /* Word 3 */ + +#ifndef __BIG_ENDIAN__ + /** + * Written by the classification program. Not interpreted by mPIPE + * hardware. + */ + uint_reg_t custom2 : 64; +#else /* __BIG_ENDIAN__ */ + uint_reg_t custom2 : 64; +#endif + + /* Word 4 */ + +#ifndef __BIG_ENDIAN__ + /** + * Written by the classification program. Not interpreted by mPIPE + * hardware. + */ + uint_reg_t custom3 : 64; +#else /* __BIG_ENDIAN__ */ + uint_reg_t custom3 : 64; +#endif + + /* Word 5 */ + +#ifndef __BIG_ENDIAN__ + /** + * Sequence number applied when packet is distributed. Classifier + * selects which sequence number is to be applied by writing the 13-bit + * SQN-selector into this field. + */ + uint_reg_t gp_sqn : 16; + /** + * Written by notification hardware. The packet sequence number is + * incremented for each packet that wasn't dropped. + */ + uint_reg_t packet_sqn : 48; +#else /* __BIG_ENDIAN__ */ + uint_reg_t packet_sqn : 48; + uint_reg_t gp_sqn : 16; +#endif + + /* Word 6 */ + +#ifndef __BIG_ENDIAN__ + /** + * Written by hardware when the start-of-packet is received by the mPIPE + * from the MAC. This is the nanoseconds part of the packet timestamp. + */ + uint_reg_t time_stamp_ns : 32; + /** + * Written by hardware when the start-of-packet is received by the mPIPE + * from the MAC. This is the seconds part of the packet timestamp. + */ + uint_reg_t time_stamp_sec : 32; +#else /* __BIG_ENDIAN__ */ + uint_reg_t time_stamp_sec : 32; + uint_reg_t time_stamp_ns : 32; +#endif + + /* Word 7 */ + +#ifndef __BIG_ENDIAN__ + /** Virtual address. Must be sign extended by consumer. */ + int_reg_t va : 42; + /** Reserved. */ + uint_reg_t __reserved_4 : 6; + /** Index of the buffer stack to which this buffer belongs. */ + uint_reg_t stack_idx : 5; + /** Reserved. */ + uint_reg_t __reserved_5 : 3; + /** + * Instance ID. For devices that support more than one mPIPE instance, + * this field indicates the buffer owner. If the INST field does not + * match the mPIPE's instance number when a packet is egressed, buffers + * with HWB set will be returned to the other mPIPE instance. + */ + uint_reg_t inst : 1; + /** Reserved. */ + uint_reg_t __reserved_6 : 1; + /** + * Always set to one by hardware in iDMA packet descriptors. For eDMA, + * indicates whether the buffer will be released to the buffer stack + * manager. When 0, software is responsible for releasing the buffer. + */ + uint_reg_t hwb : 1; + /** + * Encoded size of buffer. Set by the ingress hardware for iDMA packet + * descriptors. For eDMA descriptors, indicates the buffer size if .c + * indicates a chained packet. If an eDMA descriptor is not chained and + * the .hwb bit is not set, this field is ignored and the size is + * specified by the .xfer_size field. + * 0 = 128 bytes + * 1 = 256 bytes + * 2 = 512 bytes + * 3 = 1024 bytes + * 4 = 1664 bytes + * 5 = 4096 bytes + * 6 = 10368 bytes + * 7 = 16384 bytes + */ + uint_reg_t size : 3; + /** + * Chaining configuration for the buffer. Indicates that an ingress + * packet or egress command is chained across multiple buffers, with each + * buffer's size indicated by the .size field. + */ + uint_reg_t c : 2; +#else /* __BIG_ENDIAN__ */ + uint_reg_t c : 2; + uint_reg_t size : 3; + uint_reg_t hwb : 1; + uint_reg_t __reserved_6 : 1; + uint_reg_t inst : 1; + uint_reg_t __reserved_5 : 3; + uint_reg_t stack_idx : 5; + uint_reg_t __reserved_4 : 6; + int_reg_t va : 42; +#endif + + }; + + /** Word access */ + uint_reg_t words[8]; +} MPIPE_PDESC_t; +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_MPIPE_SHM_H__) */ diff --git a/arch/tile/include/arch/mpipe_shm_def.h b/arch/tile/include/arch/mpipe_shm_def.h new file mode 100644 index 0000000..6124d39 --- /dev/null +++ b/arch/tile/include/arch/mpipe_shm_def.h @@ -0,0 +1,23 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_MPIPE_SHM_DEF_H__ +#define __ARCH_MPIPE_SHM_DEF_H__ +#define MPIPE_EDMA_DESC_WORD1__C_VAL_UNCHAINED 0x0 +#define MPIPE_EDMA_DESC_WORD1__C_VAL_CHAINED 0x1 +#define MPIPE_EDMA_DESC_WORD1__C_VAL_NOT_RDY 0x2 +#define MPIPE_EDMA_DESC_WORD1__C_VAL_INVALID 0x3 +#endif /* !defined(__ARCH_MPIPE_SHM_DEF_H__) */ diff --git a/arch/tile/include/arch/trio.h b/arch/tile/include/arch/trio.h new file mode 100644 index 0000000..d3000a8 --- /dev/null +++ b/arch/tile/include/arch/trio.h @@ -0,0 +1,72 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_H__ +#define __ARCH_TRIO_H__ + +#include <arch/abi.h> +#include <arch/trio_def.h> + +#ifndef __ASSEMBLER__ + +/* + * Tile PIO Region Configuration - CFG Address Format. + * This register describes the address format for PIO accesses when the + * associated region is setup with TYPE=CFG. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Register Address (full byte address). */ + uint_reg_t reg_addr : 12; + /* Function Number */ + uint_reg_t fn : 3; + /* Device Number */ + uint_reg_t dev : 5; + /* BUS Number */ + uint_reg_t bus : 8; + /* Config Type: 0 for access to directly-attached device. 1 otherwise. */ + uint_reg_t type : 1; + /* Reserved. */ + uint_reg_t __reserved_0 : 1; + /* + * MAC select. This must match the configuration in + * TILE_PIO_REGION_SETUP.MAC. + */ + uint_reg_t mac : 2; + /* Reserved. */ + uint_reg_t __reserved_1 : 32; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_1 : 32; + uint_reg_t mac : 2; + uint_reg_t __reserved_0 : 1; + uint_reg_t type : 1; + uint_reg_t bus : 8; + uint_reg_t dev : 5; + uint_reg_t fn : 3; + uint_reg_t reg_addr : 12; +#endif + }; + + uint_reg_t word; +} TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR_t; +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_TRIO_H__) */ diff --git a/arch/tile/include/arch/trio_constants.h b/arch/tile/include/arch/trio_constants.h new file mode 100644 index 0000000..628b045 --- /dev/null +++ b/arch/tile/include/arch/trio_constants.h @@ -0,0 +1,36 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + + +#ifndef __ARCH_TRIO_CONSTANTS_H__ +#define __ARCH_TRIO_CONSTANTS_H__ + +#define TRIO_NUM_ASIDS 16 +#define TRIO_NUM_TLBS_PER_ASID 16 + +#define TRIO_NUM_TPIO_REGIONS 8 +#define TRIO_LOG2_NUM_TPIO_REGIONS 3 + +#define TRIO_NUM_MAP_MEM_REGIONS 16 +#define TRIO_LOG2_NUM_MAP_MEM_REGIONS 4 +#define TRIO_NUM_MAP_SQ_REGIONS 8 +#define TRIO_LOG2_NUM_MAP_SQ_REGIONS 3 + +#define TRIO_LOG2_NUM_SQ_FIFO_ENTRIES 6 + +#define TRIO_NUM_PUSH_DMA_RINGS 32 + +#define TRIO_NUM_PULL_DMA_RINGS 32 + +#endif /* __ARCH_TRIO_CONSTANTS_H__ */ diff --git a/arch/tile/include/arch/trio_def.h b/arch/tile/include/arch/trio_def.h new file mode 100644 index 0000000..e805003 --- /dev/null +++ b/arch/tile/include/arch/trio_def.h @@ -0,0 +1,41 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_DEF_H__ +#define __ARCH_TRIO_DEF_H__ +#define TRIO_CFG_REGION_ADDR__REG_SHIFT 0 +#define TRIO_CFG_REGION_ADDR__INTFC_SHIFT 16 +#define TRIO_CFG_REGION_ADDR__INTFC_VAL_TRIO 0x0 +#define TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE 0x1 +#define TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_STANDARD 0x2 +#define TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_PROTECTED 0x3 +#define TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT 18 +#define TRIO_CFG_REGION_ADDR__PROT_SHIFT 20 +#define TRIO_PIO_REGIONS_ADDR__REGION_SHIFT 32 +#define TRIO_MAP_MEM_REG_INT0 0x1000000000 +#define TRIO_MAP_MEM_REG_INT1 0x1000000008 +#define TRIO_MAP_MEM_REG_INT2 0x1000000010 +#define TRIO_MAP_MEM_REG_INT3 0x1000000018 +#define TRIO_MAP_MEM_REG_INT4 0x1000000020 +#define TRIO_MAP_MEM_REG_INT5 0x1000000028 +#define TRIO_MAP_MEM_REG_INT6 0x1000000030 +#define TRIO_MAP_MEM_REG_INT7 0x1000000038 +#define TRIO_MAP_MEM_LIM__ADDR_SHIFT 12 +#define TRIO_MAP_MEM_SETUP__ORDER_MODE_VAL_UNORDERED 0x0 +#define TRIO_MAP_MEM_SETUP__ORDER_MODE_VAL_STRICT 0x1 +#define TRIO_MAP_MEM_SETUP__ORDER_MODE_VAL_REL_ORD 0x2 +#define TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT 30 +#endif /* !defined(__ARCH_TRIO_DEF_H__) */ diff --git a/arch/tile/include/arch/trio_pcie_intfc.h b/arch/tile/include/arch/trio_pcie_intfc.h new file mode 100644 index 0000000..0487fdb --- /dev/null +++ b/arch/tile/include/arch/trio_pcie_intfc.h @@ -0,0 +1,229 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_PCIE_INTFC_H__ +#define __ARCH_TRIO_PCIE_INTFC_H__ + +#include <arch/abi.h> +#include <arch/trio_pcie_intfc_def.h> + +#ifndef __ASSEMBLER__ + +/* + * Port Configuration. + * Configuration of the PCIe Port + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Provides the state of the strapping pins for this port. */ + uint_reg_t strap_state : 3; + /* Reserved. */ + uint_reg_t __reserved_0 : 1; + /* + * When 1, the device type will be overridden using OVD_DEV_TYPE_VAL. + * When 0, the device type is determined based on the STRAP_STATE. + */ + uint_reg_t ovd_dev_type : 1; + /* Provides the device type when OVD_DEV_TYPE is 1. */ + uint_reg_t ovd_dev_type_val : 4; + /* Determines how link is trained. */ + uint_reg_t train_mode : 2; + /* Reserved. */ + uint_reg_t __reserved_1 : 1; + /* + * For PCIe, used to flip physical RX lanes that were not properly wired. + * This is not the same as lane reversal which is handled automatically + * during link training. When 0, RX Lane0 must be wired to the link + * partner (either to its Lane0 or it's LaneN). When RX_LANE_FLIP is 1, + * the highest numbered lane for this port becomes Lane0 and Lane0 does + * NOT have to be wired to the link partner. + */ + uint_reg_t rx_lane_flip : 1; + /* + * For PCIe, used to flip physical TX lanes that were not properly wired. + * This is not the same as lane reversal which is handled automatically + * during link training. When 0, TX Lane0 must be wired to the link + * partner (either to its Lane0 or it's LaneN). When TX_LANE_FLIP is 1, + * the highest numbered lane for this port becomes Lane0 and Lane0 does + * NOT have to be wired to the link partner. + */ + uint_reg_t tx_lane_flip : 1; + /* + * For StreamIO port, configures the width of the port when TRAIN_MODE is + * not STRAP. + */ + uint_reg_t stream_width : 2; + /* + * For StreamIO port, configures the rate of the port when TRAIN_MODE is + * not STRAP. + */ + uint_reg_t stream_rate : 2; + /* Reserved. */ + uint_reg_t __reserved_2 : 46; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_2 : 46; + uint_reg_t stream_rate : 2; + uint_reg_t stream_width : 2; + uint_reg_t tx_lane_flip : 1; + uint_reg_t rx_lane_flip : 1; + uint_reg_t __reserved_1 : 1; + uint_reg_t train_mode : 2; + uint_reg_t ovd_dev_type_val : 4; + uint_reg_t ovd_dev_type : 1; + uint_reg_t __reserved_0 : 1; + uint_reg_t strap_state : 3; +#endif + }; + + uint_reg_t word; +} TRIO_PCIE_INTFC_PORT_CONFIG_t; + +/* + * Port Status. + * Status of the PCIe Port. This register applies to the StreamIO port when + * StreamIO is enabled. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* + * Indicates the DL state of the port. When 1, the port is up and ready + * to receive traffic. + */ + uint_reg_t dl_up : 1; + /* + * Indicates the number of times the link has gone down. Clears on read. + */ + uint_reg_t dl_down_cnt : 7; + /* Indicates the SERDES PLL has spun up and is providing a valid clock. */ + uint_reg_t clock_ready : 1; + /* Reserved. */ + uint_reg_t __reserved_0 : 7; + /* Device revision ID. */ + uint_reg_t device_rev : 8; + /* Link state (PCIe). */ + uint_reg_t ltssm_state : 6; + /* Link power management state (PCIe). */ + uint_reg_t pm_state : 3; + /* Reserved. */ + uint_reg_t __reserved_1 : 31; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_1 : 31; + uint_reg_t pm_state : 3; + uint_reg_t ltssm_state : 6; + uint_reg_t device_rev : 8; + uint_reg_t __reserved_0 : 7; + uint_reg_t clock_ready : 1; + uint_reg_t dl_down_cnt : 7; + uint_reg_t dl_up : 1; +#endif + }; + + uint_reg_t word; +} TRIO_PCIE_INTFC_PORT_STATUS_t; + +/* + * Transmit FIFO Control. + * Contains TX FIFO thresholds. These registers are for diagnostics purposes + * only. Changing these values causes undefined behavior. + */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* + * Almost-Empty level for TX0 data. Typically set to at least + * roundup(38.0*M/N) where N=tclk frequency and M=MAC symbol rate in MHz + * for a x4 port (250MHz). + */ + uint_reg_t tx0_data_ae_lvl : 7; + /* Reserved. */ + uint_reg_t __reserved_0 : 1; + /* Almost-Empty level for TX1 data. */ + uint_reg_t tx1_data_ae_lvl : 7; + /* Reserved. */ + uint_reg_t __reserved_1 : 1; + /* Almost-Full level for TX0 data. */ + uint_reg_t tx0_data_af_lvl : 7; + /* Reserved. */ + uint_reg_t __reserved_2 : 1; + /* Almost-Full level for TX1 data. */ + uint_reg_t tx1_data_af_lvl : 7; + /* Reserved. */ + uint_reg_t __reserved_3 : 1; + /* Almost-Full level for TX0 info. */ + uint_reg_t tx0_info_af_lvl : 5; + /* Reserved. */ + uint_reg_t __reserved_4 : 3; + /* Almost-Full level for TX1 info. */ + uint_reg_t tx1_info_af_lvl : 5; + /* Reserved. */ + uint_reg_t __reserved_5 : 3; + /* + * This register provides performance adjustment for high bandwidth + * flows. The MAC will assert almost-full to TRIO if non-posted credits + * fall below this level. Note that setting this larger than the initial + * PORT_CREDIT.NPH value will cause READS to never be sent. If the + * initial credit value from the link partner is smaller than this value + * when the link comes up, the value will be reset to the initial credit + * value to prevent lockup. + */ + uint_reg_t min_np_credits : 8; + /* + * This register provides performance adjustment for high bandwidth + * flows. The MAC will assert almost-full to TRIO if posted credits fall + * below this level. Note that setting this larger than the initial + * PORT_CREDIT.PH value will cause WRITES to never be sent. If the + * initial credit value from the link partner is smaller than this value + * when the link comes up, the value will be reset to the initial credit + * value to prevent lockup. + */ + uint_reg_t min_p_credits : 8; +#else /* __BIG_ENDIAN__ */ + uint_reg_t min_p_credits : 8; + uint_reg_t min_np_credits : 8; + uint_reg_t __reserved_5 : 3; + uint_reg_t tx1_info_af_lvl : 5; + uint_reg_t __reserved_4 : 3; + uint_reg_t tx0_info_af_lvl : 5; + uint_reg_t __reserved_3 : 1; + uint_reg_t tx1_data_af_lvl : 7; + uint_reg_t __reserved_2 : 1; + uint_reg_t tx0_data_af_lvl : 7; + uint_reg_t __reserved_1 : 1; + uint_reg_t tx1_data_ae_lvl : 7; + uint_reg_t __reserved_0 : 1; + uint_reg_t tx0_data_ae_lvl : 7; +#endif + }; + + uint_reg_t word; +} TRIO_PCIE_INTFC_TX_FIFO_CTL_t; +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_TRIO_PCIE_INTFC_H__) */ diff --git a/arch/tile/include/arch/trio_pcie_intfc_def.h b/arch/tile/include/arch/trio_pcie_intfc_def.h new file mode 100644 index 0000000..d3fd678 --- /dev/null +++ b/arch/tile/include/arch/trio_pcie_intfc_def.h @@ -0,0 +1,32 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_PCIE_INTFC_DEF_H__ +#define __ARCH_TRIO_PCIE_INTFC_DEF_H__ +#define TRIO_PCIE_INTFC_MAC_INT_STS 0x0000 +#define TRIO_PCIE_INTFC_MAC_INT_STS__INT_LEVEL_MASK 0xf000 +#define TRIO_PCIE_INTFC_PORT_CONFIG 0x0018 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_DISABLED 0x0 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT 0x1 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC 0x2 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT_G1 0x3 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC_G1 0x4 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_XLINK 0x5 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_STREAM_X1 0x6 +#define TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_STREAM_X4 0x7 +#define TRIO_PCIE_INTFC_PORT_STATUS 0x0020 +#define TRIO_PCIE_INTFC_TX_FIFO_CTL 0x0050 +#endif /* !defined(__ARCH_TRIO_PCIE_INTFC_DEF_H__) */ diff --git a/arch/tile/include/arch/trio_pcie_rc.h b/arch/tile/include/arch/trio_pcie_rc.h new file mode 100644 index 0000000..6a25d0a --- /dev/null +++ b/arch/tile/include/arch/trio_pcie_rc.h @@ -0,0 +1,156 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_PCIE_RC_H__ +#define __ARCH_TRIO_PCIE_RC_H__ + +#include <arch/abi.h> +#include <arch/trio_pcie_rc_def.h> + +#ifndef __ASSEMBLER__ + +/* Device Capabilities Register. */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* + * Max_Payload_Size Supported, writablethrough the MAC_STANDARD interface + */ + uint_reg_t mps_sup : 3; + /* + * This field is writable through the MAC_STANDARD interface. However, + * Phantom Function is not supported. Therefore, the application must + * not write any value other than 0x0 to this field. + */ + uint_reg_t phantom_function_supported : 2; + /* This bit is writable through the MAC_STANDARD interface. */ + uint_reg_t ext_tag_field_supported : 1; + /* Reserved. */ + uint_reg_t __reserved_0 : 3; + /* Endpoint L1 Acceptable Latency Must be 0x0 for non-Endpoint devices. */ + uint_reg_t l1_lat : 3; + /* + * Undefined since PCI Express 1.1 (Was Attention Button Present for PCI + * Express 1.0a) + */ + uint_reg_t r1 : 1; + /* + * Undefined since PCI Express 1.1 (Was Attention Indicator Present for + * PCI Express 1.0a) + */ + uint_reg_t r2 : 1; + /* + * Undefined since PCI Express 1.1 (Was Power Indicator Present for PCI + * Express 1.0a) + */ + uint_reg_t r3 : 1; + /* + * Role-Based Error Reporting, writable through the MAC_STANDARD + * interface. Required to be set for device compliant to 1.1 spec and + * later. + */ + uint_reg_t rer : 1; + /* Reserved. */ + uint_reg_t __reserved_1 : 2; + /* Captured Slot Power Limit Value Upstream port only. */ + uint_reg_t slot_pwr_lim : 8; + /* Captured Slot Power Limit Scale Upstream port only. */ + uint_reg_t slot_pwr_scale : 2; + /* Reserved. */ + uint_reg_t __reserved_2 : 4; + /* Endpoint L0s Acceptable LatencyMust be 0x0 for non-Endpoint devices. */ + uint_reg_t l0s_lat : 1; + /* Reserved. */ + uint_reg_t __reserved_3 : 31; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved_3 : 31; + uint_reg_t l0s_lat : 1; + uint_reg_t __reserved_2 : 4; + uint_reg_t slot_pwr_scale : 2; + uint_reg_t slot_pwr_lim : 8; + uint_reg_t __reserved_1 : 2; + uint_reg_t rer : 1; + uint_reg_t r3 : 1; + uint_reg_t r2 : 1; + uint_reg_t r1 : 1; + uint_reg_t l1_lat : 3; + uint_reg_t __reserved_0 : 3; + uint_reg_t ext_tag_field_supported : 1; + uint_reg_t phantom_function_supported : 2; + uint_reg_t mps_sup : 3; +#endif + }; + + uint_reg_t word; +} TRIO_PCIE_RC_DEVICE_CAP_t; + +/* Device Control Register. */ + +__extension__ +typedef union +{ + struct + { +#ifndef __BIG_ENDIAN__ + /* Correctable Error Reporting Enable */ + uint_reg_t cor_err_ena : 1; + /* Non-Fatal Error Reporting Enable */ + uint_reg_t nf_err_ena : 1; + /* Fatal Error Reporting Enable */ + uint_reg_t fatal_err_ena : 1; + /* Unsupported Request Reporting Enable */ + uint_reg_t ur_ena : 1; + /* Relaxed orderring enable */ + uint_reg_t ro_ena : 1; + /* Max Payload Size */ + uint_reg_t max_payload_size : 3; + /* Extended Tag Field Enable */ + uint_reg_t ext_tag : 1; + /* Phantom Function Enable */ + uint_reg_t ph_fn_ena : 1; + /* AUX Power PM Enable */ + uint_reg_t aux_pm_ena : 1; + /* Enable NoSnoop */ + uint_reg_t no_snoop : 1; + /* Max read request size */ + uint_reg_t max_read_req_sz : 3; + /* Reserved. */ + uint_reg_t __reserved : 49; +#else /* __BIG_ENDIAN__ */ + uint_reg_t __reserved : 49; + uint_reg_t max_read_req_sz : 3; + uint_reg_t no_snoop : 1; + uint_reg_t aux_pm_ena : 1; + uint_reg_t ph_fn_ena : 1; + uint_reg_t ext_tag : 1; + uint_reg_t max_payload_size : 3; + uint_reg_t ro_ena : 1; + uint_reg_t ur_ena : 1; + uint_reg_t fatal_err_ena : 1; + uint_reg_t nf_err_ena : 1; + uint_reg_t cor_err_ena : 1; +#endif + }; + + uint_reg_t word; +} TRIO_PCIE_RC_DEVICE_CONTROL_t; +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_TRIO_PCIE_RC_H__) */ diff --git a/arch/tile/include/arch/trio_pcie_rc_def.h b/arch/tile/include/arch/trio_pcie_rc_def.h new file mode 100644 index 0000000..74081a6 --- /dev/null +++ b/arch/tile/include/arch/trio_pcie_rc_def.h @@ -0,0 +1,24 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_PCIE_RC_DEF_H__ +#define __ARCH_TRIO_PCIE_RC_DEF_H__ +#define TRIO_PCIE_RC_DEVICE_CAP 0x0074 +#define TRIO_PCIE_RC_DEVICE_CONTROL 0x0078 +#define TRIO_PCIE_RC_DEVICE_ID_VEN_ID 0x0000 +#define TRIO_PCIE_RC_DEVICE_ID_VEN_ID__DEV_ID_SHIFT 16 +#define TRIO_PCIE_RC_REVISION_ID 0x0008 +#endif /* !defined(__ARCH_TRIO_PCIE_RC_DEF_H__) */ diff --git a/arch/tile/include/arch/trio_shm.h b/arch/tile/include/arch/trio_shm.h new file mode 100644 index 0000000..3382e38 --- /dev/null +++ b/arch/tile/include/arch/trio_shm.h @@ -0,0 +1,125 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + + +#ifndef __ARCH_TRIO_SHM_H__ +#define __ARCH_TRIO_SHM_H__ + +#include <arch/abi.h> +#include <arch/trio_shm_def.h> + +#ifndef __ASSEMBLER__ +/** + * TRIO DMA Descriptor. + * The TRIO DMA descriptor is written by software and consumed by hardware. + * It is used to specify the location of transaction data in the IO and Tile + * domains. + */ + +__extension__ +typedef union +{ + struct + { + /* Word 0 */ + +#ifndef __BIG_ENDIAN__ + /** Tile side virtual address. */ + int_reg_t va : 42; + /** + * Encoded size of buffer used on push DMA when C=1: + * 0 = 128 bytes + * 1 = 256 bytes + * 2 = 512 bytes + * 3 = 1024 bytes + * 4 = 1664 bytes + * 5 = 4096 bytes + * 6 = 10368 bytes + * 7 = 16384 bytes + */ + uint_reg_t bsz : 3; + /** + * Chaining designation. Always zero for pull DMA + * 0 : Unchained buffer pointer + * 1 : Chained buffer pointer. Next buffer descriptor (e.g. VA) stored + * in 1st 8-bytes in buffer. For chained buffers, first 8-bytes of each + * buffer contain the next buffer descriptor formatted exactly like a PDE + * buffer descriptor. This allows a chained PDE buffer to be sent using + * push DMA. + */ + uint_reg_t c : 1; + /** + * Notification interrupt will be delivered when the transaction has + * completed (all data has been read from or written to the Tile-side + * buffer). + */ + uint_reg_t notif : 1; + /** + * When 0, the XSIZE field specifies the total byte count for the + * transaction. When 1, the XSIZE field is encoded as 2^(N+14) for N in + * {0..6}: + * 0 = 16KB + * 1 = 32KB + * 2 = 64KB + * 3 = 128KB + * 4 = 256KB + * 5 = 512KB + * 6 = 1MB + * All other encodings of the XSIZE field are reserved when SMOD=1 + */ + uint_reg_t smod : 1; + /** + * Total number of bytes to move for this transaction. When SMOD=1, + * this field is encoded - see SMOD description. + */ + uint_reg_t xsize : 14; + /** Reserved. */ + uint_reg_t __reserved_0 : 1; + /** + * Generation number. Used to indicate a valid descriptor in ring. When + * a new descriptor is written into the ring, software must toggle this + * bit. The net effect is that the GEN bit being written into new + * descriptors toggles each time the ring tail pointer wraps. + */ + uint_reg_t gen : 1; +#else /* __BIG_ENDIAN__ */ + uint_reg_t gen : 1; + uint_reg_t __reserved_0 : 1; + uint_reg_t xsize : 14; + uint_reg_t smod : 1; + uint_reg_t notif : 1; + uint_reg_t c : 1; + uint_reg_t bsz : 3; + int_reg_t va : 42; +#endif + + /* Word 1 */ + +#ifndef __BIG_ENDIAN__ + /** IO-side address */ + uint_reg_t io_address : 64; +#else /* __BIG_ENDIAN__ */ + uint_reg_t io_address : 64; +#endif + + }; + + /** Word access */ + uint_reg_t words[2]; +} TRIO_DMA_DESC_t; +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_TRIO_SHM_H__) */ diff --git a/arch/tile/include/arch/trio_shm_def.h b/arch/tile/include/arch/trio_shm_def.h new file mode 100644 index 0000000..72a59c8 --- /dev/null +++ b/arch/tile/include/arch/trio_shm_def.h @@ -0,0 +1,19 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_TRIO_SHM_DEF_H__ +#define __ARCH_TRIO_SHM_DEF_H__ +#endif /* !defined(__ARCH_TRIO_SHM_DEF_H__) */ diff --git a/arch/tile/include/arch/usb_host.h b/arch/tile/include/arch/usb_host.h new file mode 100644 index 0000000..d09f326 --- /dev/null +++ b/arch/tile/include/arch/usb_host.h @@ -0,0 +1,26 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_USB_HOST_H__ +#define __ARCH_USB_HOST_H__ + +#include <arch/abi.h> +#include <arch/usb_host_def.h> + +#ifndef __ASSEMBLER__ +#endif /* !defined(__ASSEMBLER__) */ + +#endif /* !defined(__ARCH_USB_HOST_H__) */ diff --git a/arch/tile/include/arch/usb_host_def.h b/arch/tile/include/arch/usb_host_def.h new file mode 100644 index 0000000..aeed775 --- /dev/null +++ b/arch/tile/include/arch/usb_host_def.h @@ -0,0 +1,19 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* Machine-generated file; do not edit. */ + +#ifndef __ARCH_USB_HOST_DEF_H__ +#define __ARCH_USB_HOST_DEF_H__ +#endif /* !defined(__ARCH_USB_HOST_DEF_H__) */ diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild index 143473e..fb7c65a 100644 --- a/arch/tile/include/asm/Kbuild +++ b/arch/tile/include/asm/Kbuild @@ -9,7 +9,6 @@ header-y += hardwall.h generic-y += bug.h generic-y += bugs.h generic-y += cputime.h -generic-y += device.h generic-y += div64.h generic-y += emergency-restart.h generic-y += errno.h diff --git a/arch/tile/include/asm/cache.h b/arch/tile/include/asm/cache.h index 392e533..a9a5299 100644 --- a/arch/tile/include/asm/cache.h +++ b/arch/tile/include/asm/cache.h @@ -27,11 +27,17 @@ #define L2_CACHE_ALIGN(x) (((x)+(L2_CACHE_BYTES-1)) & -L2_CACHE_BYTES) /* - * TILE-Gx is fully coherent so we don't need to define ARCH_DMA_MINALIGN. + * TILEPro I/O is not always coherent (networking typically uses coherent + * I/O, but PCI traffic does not) and setting ARCH_DMA_MINALIGN to the + * L2 cacheline size helps ensure that kernel heap allocations are aligned. + * TILE-Gx I/O is always coherent when used on hash-for-home pages. + * + * However, it's possible at runtime to request not to use hash-for-home + * for the kernel heap, in which case the kernel will use flush-and-inval + * to manage coherence. As a result, we use L2_CACHE_BYTES for the + * DMA minimum alignment to avoid false sharing in the kernel heap. */ -#ifndef __tilegx__ #define ARCH_DMA_MINALIGN L2_CACHE_BYTES -#endif /* use the cache line size for the L2, which is where it counts */ #define SMP_CACHE_BYTES_SHIFT L2_CACHE_SHIFT diff --git a/arch/tile/include/asm/checksum.h b/arch/tile/include/asm/checksum.h index a120766..b21a2fd 100644 --- a/arch/tile/include/asm/checksum.h +++ b/arch/tile/include/asm/checksum.h @@ -21,4 +21,22 @@ __wsum do_csum(const unsigned char *buff, int len); #define do_csum do_csum +/* + * Return the sum of all the 16-bit subwords in a long. + * This sums two subwords on a 32-bit machine, and four on 64 bits. + * The implementation does two vector adds to capture any overflow. + */ +static inline unsigned int csum_long(unsigned long x) +{ + unsigned long ret; +#ifdef __tilegx__ + ret = __insn_v2sadu(x, 0); + ret = __insn_v2sadu(ret, 0); +#else + ret = __insn_sadh_u(x, 0); + ret = __insn_sadh_u(ret, 0); +#endif + return ret; +} + #endif /* _ASM_TILE_CHECKSUM_H */ diff --git a/arch/tile/include/asm/device.h b/arch/tile/include/asm/device.h new file mode 100644 index 0000000..5182705 --- /dev/null +++ b/arch/tile/include/asm/device.h @@ -0,0 +1,33 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + * Arch specific extensions to struct device + */ + +#ifndef _ASM_TILE_DEVICE_H +#define _ASM_TILE_DEVICE_H + +struct dev_archdata { + /* DMA operations on that device */ + struct dma_map_ops *dma_ops; + + /* Offset of the DMA address from the PA. */ + dma_addr_t dma_offset; + + /* Highest DMA address that can be generated by this device. */ + dma_addr_t max_direct_dma_addr; +}; + +struct pdev_archdata { +}; + +#endif /* _ASM_TILE_DEVICE_H */ diff --git a/arch/tile/include/asm/dma-mapping.h b/arch/tile/include/asm/dma-mapping.h index eaa06d1..4b6247d 100644 --- a/arch/tile/include/asm/dma-mapping.h +++ b/arch/tile/include/asm/dma-mapping.h @@ -20,69 +20,80 @@ #include <linux/cache.h> #include <linux/io.h> -/* - * Note that on x86 and powerpc, there is a "struct dma_mapping_ops" - * that is used for all the DMA operations. For now, we don't have an - * equivalent on tile, because we only have a single way of doing DMA. - * (Tilera bug 7994 to use dma_mapping_ops.) - */ +extern struct dma_map_ops *tile_dma_map_ops; +extern struct dma_map_ops *gx_pci_dma_map_ops; +extern struct dma_map_ops *gx_legacy_pci_dma_map_ops; + +static inline struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (dev && dev->archdata.dma_ops) + return dev->archdata.dma_ops; + else + return tile_dma_map_ops; +} + +static inline dma_addr_t get_dma_offset(struct device *dev) +{ + return dev->archdata.dma_offset; +} + +static inline void set_dma_offset(struct device *dev, dma_addr_t off) +{ + dev->archdata.dma_offset = off; +} -#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) - -extern dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction); -extern void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, enum dma_data_direction); -extern int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction); -extern void dma_unmap_sg(struct device *dev, struct scatterlist *sg, - int nhwentries, enum dma_data_direction); -extern dma_addr_t dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction); -extern void dma_unmap_page(struct device *dev, dma_addr_t dma_address, - size_t size, enum dma_data_direction); -extern void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction); -extern void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction); - - -void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flag); - -void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - -extern void dma_sync_single_for_cpu(struct device *, dma_addr_t, size_t, - enum dma_data_direction); -extern void dma_sync_single_for_device(struct device *, dma_addr_t, - size_t, enum dma_data_direction); -extern void dma_sync_single_range_for_cpu(struct device *, dma_addr_t, - unsigned long offset, size_t, - enum dma_data_direction); -extern void dma_sync_single_range_for_device(struct device *, dma_addr_t, - unsigned long offset, size_t, - enum dma_data_direction); -extern void dma_cache_sync(struct device *dev, void *vaddr, size_t, - enum dma_data_direction); +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr) +{ + return paddr + get_dma_offset(dev); +} + +static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) +{ + return daddr - get_dma_offset(dev); +} + +static inline void dma_mark_clean(void *addr, size_t size) {} + +#include <asm-generic/dma-mapping-common.h> + +static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops) +{ + dev->archdata.dma_ops = ops; +} + +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ + if (!dev->dma_mask) + return 0; + + return addr + size - 1 <= *dev->dma_mask; +} static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - return 0; + return get_dma_ops(dev)->mapping_error(dev, dma_addr); } static inline int dma_supported(struct device *dev, u64 mask) { - return 1; + return get_dma_ops(dev)->dma_supported(dev, mask); } static inline int dma_set_mask(struct device *dev, u64 mask) { + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + /* Handle legacy PCI devices with limited memory addressability. */ + if ((dma_ops == gx_pci_dma_map_ops) && (mask <= DMA_BIT_MASK(32))) { + set_dma_ops(dev, gx_legacy_pci_dma_map_ops); + set_dma_offset(dev, 0); + if (mask > dev->archdata.max_direct_dma_addr) + mask = dev->archdata.max_direct_dma_addr; + } + if (!dev->dma_mask || !dma_supported(dev, mask)) return -EIO; @@ -91,4 +102,43 @@ dma_set_mask(struct device *dev, u64 mask) return 0; } +static inline void *dma_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + void *cpu_addr; + + cpu_addr = dma_ops->alloc(dev, size, dma_handle, flag, attrs); + + debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr); + + return cpu_addr; +} + +static inline void dma_free_attrs(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); + + dma_ops->free(dev, size, cpu_addr, dma_handle, attrs); +} + +#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL) +#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL) +#define dma_free_coherent(d, s, v, h) dma_free_attrs(d, s, v, h, NULL) +#define dma_free_noncoherent(d, s, v, h) dma_free_attrs(d, s, v, h, NULL) + +/* + * dma_alloc_noncoherent() is #defined to return coherent memory, + * so there's no need to do any flushing here. + */ +static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction direction) +{ +} + #endif /* _ASM_TILE_DMA_MAPPING_H */ diff --git a/arch/tile/include/asm/fixmap.h b/arch/tile/include/asm/fixmap.h index c66f793..e16dbf9 100644 --- a/arch/tile/include/asm/fixmap.h +++ b/arch/tile/include/asm/fixmap.h @@ -45,15 +45,23 @@ * * TLB entries of such buffers will not be flushed across * task switches. - * - * We don't bother with a FIX_HOLE since above the fixmaps - * is unmapped memory in any case. */ enum fixed_addresses { +#ifdef __tilegx__ + /* + * TILEPro has unmapped memory above so the hole isn't needed, + * and in any case the hole pushes us over a single 16MB pmd. + */ + FIX_HOLE, +#endif #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, #endif +#ifdef __tilegx__ /* see homecache.c */ + FIX_HOMECACHE_BEGIN, + FIX_HOMECACHE_END = FIX_HOMECACHE_BEGIN+(NR_CPUS)-1, +#endif __end_of_permanent_fixed_addresses, /* diff --git a/arch/tile/include/asm/homecache.h b/arch/tile/include/asm/homecache.h index a824386..7b77713 100644 --- a/arch/tile/include/asm/homecache.h +++ b/arch/tile/include/asm/homecache.h @@ -79,10 +79,17 @@ extern void homecache_change_page_home(struct page *, int order, int home); /* * Flush a page out of whatever cache(s) it is in. * This is more than just finv, since it properly handles waiting - * for the data to reach memory on tilepro, but it can be quite - * heavyweight, particularly on hash-for-home memory. + * for the data to reach memory, but it can be quite + * heavyweight, particularly on incoherent or immutable memory. */ -extern void homecache_flush_cache(struct page *, int order); +extern void homecache_finv_page(struct page *); + +/* + * Flush a page out of the specified home cache. + * Note that the specified home need not be the actual home of the page, + * as for example might be the case when coordinating with I/O devices. + */ +extern void homecache_finv_map_page(struct page *, int home); /* * Allocate a page with the given GFP flags, home, and optionally @@ -104,10 +111,10 @@ extern struct page *homecache_alloc_pages_node(int nid, gfp_t gfp_mask, * routines use homecache_change_page_home() to reset the home * back to the default before returning the page to the allocator. */ +void __homecache_free_pages(struct page *, unsigned int order); void homecache_free_pages(unsigned long addr, unsigned int order); -#define homecache_free_page(page) \ - homecache_free_pages((page), 0) - +#define __homecache_free_page(page) __homecache_free_pages((page), 0) +#define homecache_free_page(page) homecache_free_pages((page), 0) /* diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h index d2152de..2a9b293 100644 --- a/arch/tile/include/asm/io.h +++ b/arch/tile/include/asm/io.h @@ -62,6 +62,92 @@ extern void iounmap(volatile void __iomem *addr); #define mm_ptov(addr) ((void *)phys_to_virt(addr)) #define mm_vtop(addr) ((unsigned long)virt_to_phys(addr)) +#if CHIP_HAS_MMIO() + +/* + * We use inline assembly to guarantee that the compiler does not + * split an access into multiple byte-sized accesses as it might + * sometimes do if a register data structure is marked "packed". + * Obviously on tile we can't tolerate such an access being + * actually unaligned, but we want to avoid the case where the + * compiler conservatively would generate multiple accesses even + * for an aligned read or write. + */ + +static inline u8 __raw_readb(const volatile void __iomem *addr) +{ + return *(const volatile u8 __force *)addr; +} + +static inline u16 __raw_readw(const volatile void __iomem *addr) +{ + u16 ret; + asm volatile("ld2u %0, %1" : "=r" (ret) : "r" (addr)); + barrier(); + return le16_to_cpu(ret); +} + +static inline u32 __raw_readl(const volatile void __iomem *addr) +{ + u32 ret; + /* Sign-extend to conform to u32 ABI sign-extension convention. */ + asm volatile("ld4s %0, %1" : "=r" (ret) : "r" (addr)); + barrier(); + return le32_to_cpu(ret); +} + +static inline u64 __raw_readq(const volatile void __iomem *addr) +{ + u64 ret; + asm volatile("ld %0, %1" : "=r" (ret) : "r" (addr)); + barrier(); + return le64_to_cpu(ret); +} + +static inline void __raw_writeb(u8 val, volatile void __iomem *addr) +{ + *(volatile u8 __force *)addr = val; +} + +static inline void __raw_writew(u16 val, volatile void __iomem *addr) +{ + asm volatile("st2 %0, %1" :: "r" (addr), "r" (cpu_to_le16(val))); +} + +static inline void __raw_writel(u32 val, volatile void __iomem *addr) +{ + asm volatile("st4 %0, %1" :: "r" (addr), "r" (cpu_to_le32(val))); +} + +static inline void __raw_writeq(u64 val, volatile void __iomem *addr) +{ + asm volatile("st %0, %1" :: "r" (addr), "r" (cpu_to_le64(val))); +} + +/* + * The on-chip I/O hardware on tilegx is configured with VA=PA for the + * kernel's PA range. The low-level APIs and field names use "va" and + * "void *" nomenclature, to be consistent with the general notion + * that the addresses in question are virtualizable, but in the kernel + * context we are actually manipulating PA values. (In other contexts, + * e.g. access from user space, we do in fact use real virtual addresses + * in the va fields.) To allow readers of the code to understand what's + * happening, we direct their attention to this comment by using the + * following two functions that just duplicate __va() and __pa(). + */ +typedef unsigned long tile_io_addr_t; +static inline tile_io_addr_t va_to_tile_io_addr(void *va) +{ + BUILD_BUG_ON(sizeof(phys_addr_t) != sizeof(tile_io_addr_t)); + return __pa(va); +} +static inline void *tile_io_addr_to_va(tile_io_addr_t tile_io_addr) +{ + return __va(tile_io_addr); +} + +#else /* CHIP_HAS_MMIO() */ + #ifdef CONFIG_PCI extern u8 _tile_readb(unsigned long addr); @@ -73,10 +159,19 @@ extern void _tile_writew(u16 val, unsigned long addr); extern void _tile_writel(u32 val, unsigned long addr); extern void _tile_writeq(u64 val, unsigned long addr); -#else +#define __raw_readb(addr) _tile_readb((unsigned long)addr) +#define __raw_readw(addr) _tile_readw((unsigned long)addr) +#define __raw_readl(addr) _tile_readl((unsigned long)addr) +#define __raw_readq(addr) _tile_readq((unsigned long)addr) +#define __raw_writeb(val, addr) _tile_writeb(val, (unsigned long)addr) +#define __raw_writew(val, addr) _tile_writew(val, (unsigned long)addr) +#define __raw_writel(val, addr) _tile_writel(val, (unsigned long)addr) +#define __raw_writeq(val, addr) _tile_writeq(val, (unsigned long)addr) + +#else /* CONFIG_PCI */ /* - * The Tile architecture does not support IOMEM unless PCI is enabled. + * The tilepro architecture does not support IOMEM unless PCI is enabled. * Unfortunately we can't yet simply not declare these methods, * since some generic code that compiles into the kernel, but * we never run, uses them unconditionally. @@ -88,65 +183,58 @@ static inline int iomem_panic(void) return 0; } -static inline u8 _tile_readb(unsigned long addr) +static inline u8 readb(unsigned long addr) { return iomem_panic(); } -static inline u16 _tile_readw(unsigned long addr) +static inline u16 _readw(unsigned long addr) { return iomem_panic(); } -static inline u32 _tile_readl(unsigned long addr) +static inline u32 readl(unsigned long addr) { return iomem_panic(); } -static inline u64 _tile_readq(unsigned long addr) +static inline u64 readq(unsigned long addr) { return iomem_panic(); } -static inline void _tile_writeb(u8 val, unsigned long addr) +static inline void writeb(u8 val, unsigned long addr) { iomem_panic(); } -static inline void _tile_writew(u16 val, unsigned long addr) +static inline void writew(u16 val, unsigned long addr) { iomem_panic(); } -static inline void _tile_writel(u32 val, unsigned long addr) +static inline void writel(u32 val, unsigned long addr) { iomem_panic(); } -static inline void _tile_writeq(u64 val, unsigned long addr) +static inline void writeq(u64 val, unsigned long addr) { iomem_panic(); } -#endif +#endif /* CONFIG_PCI */ + +#endif /* CHIP_HAS_MMIO() */ -#define readb(addr) _tile_readb((unsigned long)addr) -#define readw(addr) _tile_readw((unsigned long)addr) -#define readl(addr) _tile_readl((unsigned long)addr) -#define readq(addr) _tile_readq((unsigned long)addr) -#define writeb(val, addr) _tile_writeb(val, (unsigned long)addr) -#define writew(val, addr) _tile_writew(val, (unsigned long)addr) -#define writel(val, addr) _tile_writel(val, (unsigned long)addr) -#define writeq(val, addr) _tile_writeq(val, (unsigned long)addr) - -#define __raw_readb readb -#define __raw_readw readw -#define __raw_readl readl -#define __raw_readq readq -#define __raw_writeb writeb -#define __raw_writew writew -#define __raw_writel writel -#define __raw_writeq writeq +#define readb __raw_readb +#define readw __raw_readw +#define readl __raw_readl +#define readq __raw_readq +#define writeb __raw_writeb +#define writew __raw_writew +#define writel __raw_writel +#define writeq __raw_writeq #define readb_relaxed readb #define readw_relaxed readw diff --git a/arch/tile/include/asm/memprof.h b/arch/tile/include/asm/memprof.h deleted file mode 100644 index 359949b..0000000 --- a/arch/tile/include/asm/memprof.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Copyright 2010 Tilera Corporation. All Rights Reserved. - * - * 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, version 2. - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for - * more details. - * - * The hypervisor's memory controller profiling infrastructure allows - * the programmer to find out what fraction of the available memory - * bandwidth is being consumed at each memory controller. The - * profiler provides start, stop, and clear operations to allows - * profiling over a specific time window, as well as an interface for - * reading the most recent profile values. - * - * This header declares IOCTL codes necessary to control memprof. - */ -#ifndef _ASM_TILE_MEMPROF_H -#define _ASM_TILE_MEMPROF_H - -#include <linux/ioctl.h> - -#define MEMPROF_IOCTL_TYPE 0xB4 -#define MEMPROF_IOCTL_START _IO(MEMPROF_IOCTL_TYPE, 0) -#define MEMPROF_IOCTL_STOP _IO(MEMPROF_IOCTL_TYPE, 1) -#define MEMPROF_IOCTL_CLEAR _IO(MEMPROF_IOCTL_TYPE, 2) - -#endif /* _ASM_TILE_MEMPROF_H */ diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h index 9d9131e..dd033a4 100644 --- a/arch/tile/include/asm/page.h +++ b/arch/tile/include/asm/page.h @@ -174,7 +174,9 @@ static inline __attribute_const__ int get_order(unsigned long size) #define MEM_LOW_END (HALF_VA_SPACE - 1) /* low half */ #define MEM_HIGH_START (-HALF_VA_SPACE) /* high half */ #define PAGE_OFFSET MEM_HIGH_START -#define _VMALLOC_START _AC(0xfffffff500000000, UL) /* 4 GB */ +#define FIXADDR_BASE _AC(0xfffffff400000000, UL) /* 4 GB */ +#define FIXADDR_TOP _AC(0xfffffff500000000, UL) /* 4 GB */ +#define _VMALLOC_START FIXADDR_TOP #define HUGE_VMAP_BASE _AC(0xfffffff600000000, UL) /* 4 GB */ #define MEM_SV_START _AC(0xfffffff700000000, UL) /* 256 MB */ #define MEM_SV_INTRPT MEM_SV_START @@ -185,9 +187,6 @@ static inline __attribute_const__ int get_order(unsigned long size) /* Highest DTLB address we will use */ #define KERNEL_HIGH_VADDR MEM_SV_START -/* Since we don't currently provide any fixmaps, we use an impossible VA. */ -#define FIXADDR_TOP MEM_HV_START - #else /* !__tilegx__ */ /* diff --git a/arch/tile/include/asm/pci.h b/arch/tile/include/asm/pci.h index 32e6cbe..302cdf7 100644 --- a/arch/tile/include/asm/pci.h +++ b/arch/tile/include/asm/pci.h @@ -15,9 +15,13 @@ #ifndef _ASM_TILE_PCI_H #define _ASM_TILE_PCI_H +#include <linux/dma-mapping.h> #include <linux/pci.h> +#include <linux/numa.h> #include <asm-generic/pci_iomap.h> +#ifndef __tilegx__ + /* * Structure of a PCI controller (host bridge) */ @@ -41,21 +45,151 @@ struct pci_controller { }; /* + * This flag tells if the platform is TILEmpower that needs + * special configuration for the PLX switch chip. + */ +extern int tile_plx_gen1; + +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) {} + +#define TILE_NUM_PCIE 2 + +/* * The hypervisor maps the entirety of CPA-space as bus addresses, so * bus addresses are physical addresses. The networking and block * device layers use this boolean for bounce buffer decisions. */ #define PCI_DMA_BUS_IS_PHYS 1 +/* generic pci stuff */ +#include <asm-generic/pci.h> + +#else + +#include <asm/page.h> +#include <gxio/trio.h> + +/** + * We reserve the hugepage-size address range at the top of the 64-bit address + * space to serve as the PCI window, emulating the BAR0 space of an endpoint + * device. This window is used by the chip-to-chip applications running on + * the RC node. The reason for carving out this window is that Mem-Maps that + * back up this window will not overlap with those that map the real physical + * memory. + */ +#define PCIE_HOST_BAR0_SIZE HPAGE_SIZE +#define PCIE_HOST_BAR0_START HPAGE_MASK + +/** + * The first PAGE_SIZE of the above "BAR" window is mapped to the + * gxpci_host_regs structure. + */ +#define PCIE_HOST_REGS_SIZE PAGE_SIZE + +/* + * This is the PCI address where the Mem-Map interrupt regions start. + * We use the 2nd to the last huge page of the 64-bit address space. + * The last huge page is used for the rootcomplex "bar", for C2C purpose. + */ +#define MEM_MAP_INTR_REGIONS_BASE (HPAGE_MASK - HPAGE_SIZE) + +/* + * Each Mem-Map interrupt region occupies 4KB. + */ +#define MEM_MAP_INTR_REGION_SIZE (1 << TRIO_MAP_MEM_LIM__ADDR_SHIFT) + +/* + * Allocate the PCI BAR window right below 4GB. + */ +#define TILE_PCI_BAR_WINDOW_TOP (1ULL << 32) + +/* + * Allocate 1GB for the PCI BAR window. + */ +#define TILE_PCI_BAR_WINDOW_SIZE (1 << 30) + +/* + * This is the highest bus address targeting the host memory that + * can be generated by legacy PCI devices with 32-bit or less + * DMA capability, dictated by the BAR window size and location. + */ +#define TILE_PCI_MAX_DIRECT_DMA_ADDRESS \ + (TILE_PCI_BAR_WINDOW_TOP - TILE_PCI_BAR_WINDOW_SIZE - 1) + +/* + * We shift the PCI bus range for all the physical memory up by the whole PA + * range. The corresponding CPA of an incoming PCI request will be the PCI + * address minus TILE_PCI_MEM_MAP_BASE_OFFSET. This also implies + * that the 64-bit capable devices will be given DMA addresses as + * the CPA plus TILE_PCI_MEM_MAP_BASE_OFFSET. To support 32-bit + * devices, we create a separate map region that handles the low + * 4GB. + */ +#define TILE_PCI_MEM_MAP_BASE_OFFSET (1ULL << CHIP_PA_WIDTH()) + +/* + * Start of the PCI memory resource, which starts at the end of the + * maximum system physical RAM address. + */ +#define TILE_PCI_MEM_START (1ULL << CHIP_PA_WIDTH()) + +/* + * Structure of a PCI controller (host bridge) on Gx. + */ +struct pci_controller { + + /* Pointer back to the TRIO that this PCIe port is connected to. */ + gxio_trio_context_t *trio; + int mac; /* PCIe mac index on the TRIO shim */ + int trio_index; /* Index of TRIO shim that contains the MAC. */ + + int pio_mem_index; /* PIO region index for memory access */ + + /* + * Mem-Map regions for all the memory controllers so that Linux can + * map all of its physical memory space to the PCI bus. + */ + int mem_maps[MAX_NUMNODES]; + + int index; /* PCI domain number */ + struct pci_bus *root_bus; + + /* PCI memory space resource for this controller. */ + struct resource mem_space; + char mem_space_name[32]; + + uint64_t mem_offset; /* cpu->bus memory mapping offset. */ + + int first_busno; + + struct pci_ops *ops; + + /* Table that maps the INTx numbers to Linux irq numbers. */ + int irq_intx_table[4]; + + /* Address ranges that are routed to this controller/bridge. */ + struct resource mem_resources[3]; +}; + +extern struct pci_controller pci_controllers[TILEGX_NUM_TRIO * TILEGX_TRIO_PCIES]; +extern gxio_trio_context_t trio_contexts[TILEGX_NUM_TRIO]; + +extern void pci_iounmap(struct pci_dev *dev, void __iomem *); + +/* + * The PCI address space does not equal the physical memory address + * space (we have an IOMMU). The IDE and SCSI device layers use this + * boolean for bounce buffer decisions. + */ +#define PCI_DMA_BUS_IS_PHYS 0 + +#endif /* __tilegx__ */ + int __init tile_pci_init(void); int __init pcibios_init(void); -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) {} - void __devinit pcibios_fixup_bus(struct pci_bus *bus); -#define TILE_NUM_PCIE 2 - #define pci_domain_nr(bus) (((struct pci_controller *)(bus)->sysdata)->index) /* @@ -79,19 +213,10 @@ static inline int pcibios_assign_all_busses(void) #define PCIBIOS_MIN_MEM 0 #define PCIBIOS_MIN_IO 0 -/* - * This flag tells if the platform is TILEmpower that needs - * special configuration for the PLX switch chip. - */ -extern int tile_plx_gen1; - /* Use any cpu for PCI. */ #define cpumask_of_pcibus(bus) cpu_online_mask /* implement the pci_ DMA API in terms of the generic device dma_ one */ #include <asm-generic/pci-dma-compat.h> -/* generic pci stuff */ -#include <asm-generic/pci.h> - #endif /* _ASM_TILE_PCI_H */ diff --git a/arch/tile/include/gxio/common.h b/arch/tile/include/gxio/common.h new file mode 100644 index 0000000..724595a --- /dev/null +++ b/arch/tile/include/gxio/common.h @@ -0,0 +1,40 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#ifndef _GXIO_COMMON_H_ +#define _GXIO_COMMON_H_ + +/* + * Routines shared between the various GXIO device components. + */ + +#include <hv/iorpc.h> + +#include <linux/types.h> +#include <linux/compiler.h> +#include <linux/io.h> + +/* Define the standard gxio MMIO functions using kernel functions. */ +#define __gxio_mmio_read8(addr) readb(addr) +#define __gxio_mmio_read16(addr) readw(addr) +#define __gxio_mmio_read32(addr) readl(addr) +#define __gxio_mmio_read64(addr) readq(addr) +#define __gxio_mmio_write8(addr, val) writeb((val), (addr)) +#define __gxio_mmio_write16(addr, val) writew((val), (addr)) +#define __gxio_mmio_write32(addr, val) writel((val), (addr)) +#define __gxio_mmio_write64(addr, val) writeq((val), (addr)) +#define __gxio_mmio_read(addr) __gxio_mmio_read64(addr) +#define __gxio_mmio_write(addr, val) __gxio_mmio_write64((addr), (val)) + +#endif /* !_GXIO_COMMON_H_ */ diff --git a/arch/tile/include/gxio/dma_queue.h b/arch/tile/include/gxio/dma_queue.h new file mode 100644 index 0000000..00654fe --- /dev/null +++ b/arch/tile/include/gxio/dma_queue.h @@ -0,0 +1,161 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#ifndef _GXIO_DMA_QUEUE_H_ +#define _GXIO_DMA_QUEUE_H_ + +/* + * DMA queue management APIs shared between TRIO and mPIPE. + */ + +#include "common.h" + +/* The credit counter lives in the high 32 bits. */ +#define DMA_QUEUE_CREDIT_SHIFT 32 + +/* + * State object that tracks a DMA queue's head and tail indices, as + * well as the number of commands posted and completed. The + * structure is accessed via a thread-safe, lock-free algorithm. + */ +typedef struct { + /* + * Address of a MPIPE_EDMA_POST_REGION_VAL_t, + * TRIO_PUSH_DMA_REGION_VAL_t, or TRIO_PULL_DMA_REGION_VAL_t + * register. These register have identical encodings and provide + * information about how many commands have been processed. + */ + void *post_region_addr; + + /* + * A lazily-updated count of how many edescs the hardware has + * completed. + */ + uint64_t hw_complete_count __attribute__ ((aligned(64))); + + /* + * High 32 bits are a count of available egress command credits, + * low 24 bits are the next egress "slot". + */ + int64_t credits_and_next_index; + +} __gxio_dma_queue_t; + +/* Initialize a dma queue. */ +extern void __gxio_dma_queue_init(__gxio_dma_queue_t *dma_queue, + void *post_region_addr, + unsigned int num_entries); + +/* + * Update the "credits_and_next_index" and "hw_complete_count" fields + * based on pending hardware completions. Note that some other thread + * may have already done this and, importantly, may still be in the + * process of updating "credits_and_next_index". + */ +extern void __gxio_dma_queue_update_credits(__gxio_dma_queue_t *dma_queue); + +/* Wait for credits to become available. */ +extern int64_t __gxio_dma_queue_wait_for_credits(__gxio_dma_queue_t *dma_queue, + int64_t modifier); + +/* Reserve slots in the queue, optionally waiting for slots to become + * available, and optionally returning a "completion_slot" suitable for + * direct comparison to "hw_complete_count". + */ +static inline int64_t __gxio_dma_queue_reserve(__gxio_dma_queue_t *dma_queue, + unsigned int num, bool wait, + bool completion) +{ + uint64_t slot; + + /* + * Try to reserve 'num' egress command slots. We do this by + * constructing a constant that subtracts N credits and adds N to + * the index, and using fetchaddgez to only apply it if the credits + * count doesn't go negative. + */ + int64_t modifier = (((int64_t)(-num)) << DMA_QUEUE_CREDIT_SHIFT) | num; + int64_t old = + __insn_fetchaddgez(&dma_queue->credits_and_next_index, + modifier); + + if (unlikely(old + modifier < 0)) { + /* + * We're out of credits. Try once to get more by checking for + * completed egress commands. If that fails, wait or fail. + */ + __gxio_dma_queue_update_credits(dma_queue); + old = __insn_fetchaddgez(&dma_queue->credits_and_next_index, + modifier); + if (old + modifier < 0) { + if (wait) + old = __gxio_dma_queue_wait_for_credits + (dma_queue, modifier); + else + return GXIO_ERR_DMA_CREDITS; + } + } + + /* The bottom 24 bits of old encode the "slot". */ + slot = (old & 0xffffff); + + if (completion) { + /* + * A "completion_slot" is a "slot" which can be compared to + * "hw_complete_count" at any time in the future. To convert + * "slot" into a "completion_slot", we access "hw_complete_count" + * once (knowing that we have reserved a slot, and thus, it will + * be "basically" accurate), and combine its high 40 bits with + * the 24 bit "slot", and handle "wrapping" by adding "1 << 24" + * if the result is LESS than "hw_complete_count". + */ + uint64_t complete; + complete = ACCESS_ONCE(dma_queue->hw_complete_count); + slot |= (complete & 0xffffffffff000000); + if (slot < complete) + slot += 0x1000000; + } + + /* + * If any of our slots mod 256 were equivalent to 0, go ahead and + * collect some egress credits, and update "hw_complete_count", and + * make sure the index doesn't overflow into the credits. + */ + if (unlikely(((old + num) & 0xff) < num)) { + __gxio_dma_queue_update_credits(dma_queue); + + /* Make sure the index doesn't overflow into the credits. */ +#ifdef __BIG_ENDIAN__ + *(((uint8_t *)&dma_queue->credits_and_next_index) + 4) = 0; +#else + *(((uint8_t *)&dma_queue->credits_and_next_index) + 3) = 0; +#endif + } + + return slot; +} + +/* Non-inlinable "__gxio_dma_queue_reserve(..., true)". */ +extern int64_t __gxio_dma_queue_reserve_aux(__gxio_dma_queue_t *dma_queue, + unsigned int num, int wait); + +/* Check whether a particular "completion slot" has completed. + * + * Note that this function requires a "completion slot", and thus + * cannot be used with the result of any "reserve_fast" function. + */ +extern int __gxio_dma_queue_is_complete(__gxio_dma_queue_t *dma_queue, + int64_t completion_slot, int update); + +#endif /* !_GXIO_DMA_QUEUE_H_ */ diff --git a/arch/tile/include/gxio/iorpc_globals.h b/arch/tile/include/gxio/iorpc_globals.h new file mode 100644 index 0000000..52c721f --- /dev/null +++ b/arch/tile/include/gxio/iorpc_globals.h @@ -0,0 +1,38 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#ifndef __IORPC_LINUX_RPC_H__ +#define __IORPC_LINUX_RPC_H__ + +#include <hv/iorpc.h> + +#include <linux/string.h> +#include <linux/module.h> +#include <asm/pgtable.h> + +#define IORPC_OP_ARM_POLLFD IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9000) +#define IORPC_OP_CLOSE_POLLFD IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9001) +#define IORPC_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) +#define IORPC_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) + +int __iorpc_arm_pollfd(int fd, int pollfd_cookie); + +int __iorpc_close_pollfd(int fd, int pollfd_cookie); + +int __iorpc_get_mmio_base(int fd, HV_PTE *base); + +int __iorpc_check_mmio_offset(int fd, unsigned long offset, unsigned long size); + +#endif /* !__IORPC_LINUX_RPC_H__ */ diff --git a/arch/tile/include/gxio/iorpc_mpipe.h b/arch/tile/include/gxio/iorpc_mpipe.h new file mode 100644 index 0000000..9d50fce --- /dev/null +++ b/arch/tile/include/gxio/iorpc_mpipe.h @@ -0,0 +1,136 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#ifndef __GXIO_MPIPE_LINUX_RPC_H__ +#define __GXIO_MPIPE_LINUX_RPC_H__ + +#include <hv/iorpc.h> + +#include <hv/drv_mpipe_intf.h> +#include <asm/page.h> +#include <gxio/kiorpc.h> +#include <gxio/mpipe.h> +#include <linux/string.h> +#include <linux/module.h> +#include <asm/pgtable.h> + +#define GXIO_MPIPE_OP_ALLOC_BUFFER_STACKS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1200) +#define GXIO_MPIPE_OP_INIT_BUFFER_STACK_AUX IORPC_OPCODE(IORPC_FORMAT_KERNEL_MEM, 0x1201) + +#define GXIO_MPIPE_OP_ALLOC_NOTIF_RINGS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1203) +#define GXIO_MPIPE_OP_INIT_NOTIF_RING_AUX IORPC_OPCODE(IORPC_FORMAT_KERNEL_MEM, 0x1204) +#define GXIO_MPIPE_OP_REQUEST_NOTIF_RING_INTERRUPT IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1205) +#define GXIO_MPIPE_OP_ENABLE_NOTIF_RING_INTERRUPT IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1206) +#define GXIO_MPIPE_OP_ALLOC_NOTIF_GROUPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1207) +#define GXIO_MPIPE_OP_INIT_NOTIF_GROUP IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1208) +#define GXIO_MPIPE_OP_ALLOC_BUCKETS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1209) +#define GXIO_MPIPE_OP_INIT_BUCKET IORPC_OPCODE(IORPC_FORMAT_NONE, 0x120a) +#define GXIO_MPIPE_OP_ALLOC_EDMA_RINGS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x120b) +#define GXIO_MPIPE_OP_INIT_EDMA_RING_AUX IORPC_OPCODE(IORPC_FORMAT_KERNEL_MEM, 0x120c) + +#define GXIO_MPIPE_OP_COMMIT_RULES IORPC_OPCODE(IORPC_FORMAT_NONE, 0x120f) +#define GXIO_MPIPE_OP_REGISTER_CLIENT_MEMORY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1210) +#define GXIO_MPIPE_OP_LINK_OPEN_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1211) +#define GXIO_MPIPE_OP_LINK_CLOSE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1212) + +#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121e) +#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121f) +#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1220) +#define GXIO_MPIPE_OP_ARM_POLLFD IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9000) +#define GXIO_MPIPE_OP_CLOSE_POLLFD IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9001) +#define GXIO_MPIPE_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) +#define GXIO_MPIPE_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) + +int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags); + +int gxio_mpipe_init_buffer_stack_aux(gxio_mpipe_context_t * context, + void *mem_va, size_t mem_size, + unsigned int mem_flags, unsigned int stack, + unsigned int buffer_size_enum); + + +int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags); + +int gxio_mpipe_init_notif_ring_aux(gxio_mpipe_context_t * context, void *mem_va, + size_t mem_size, unsigned int mem_flags, + unsigned int ring); + +int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t * context, + int inter_x, int inter_y, + int inter_ipi, int inter_event, + unsigned int ring); + +int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t * context, + unsigned int ring); + +int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags); + +int gxio_mpipe_init_notif_group(gxio_mpipe_context_t * context, + unsigned int group, + gxio_mpipe_notif_group_bits_t bits); + +int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t * context, unsigned int count, + unsigned int first, unsigned int flags); + +int gxio_mpipe_init_bucket(gxio_mpipe_context_t * context, unsigned int bucket, + MPIPE_LBL_INIT_DAT_BSTS_TBL_t bucket_info); + +int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags); + +int gxio_mpipe_init_edma_ring_aux(gxio_mpipe_context_t * context, void *mem_va, + size_t mem_size, unsigned int mem_flags, + unsigned int ring, unsigned int channel); + + +int gxio_mpipe_commit_rules(gxio_mpipe_context_t * context, const void *blob, + size_t blob_size); + +int gxio_mpipe_register_client_memory(gxio_mpipe_context_t * context, + unsigned int iotlb, HV_PTE pte, + unsigned int flags); + +int gxio_mpipe_link_open_aux(gxio_mpipe_context_t * context, + _gxio_mpipe_link_name_t name, unsigned int flags); + +int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac); + + +int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t * context, uint64_t * sec, + uint64_t * nsec, uint64_t * cycles); + +int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t * context, uint64_t sec, + uint64_t nsec, uint64_t cycles); + +int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context, + int64_t nsec); + +int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie); + +int gxio_mpipe_close_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie); + +int gxio_mpipe_get_mmio_base(gxio_mpipe_context_t * context, HV_PTE *base); + +int gxio_mpipe_check_mmio_offset(gxio_mpipe_context_t * context, + unsigned long offset, unsigned long size); + +#endif /* !__GXIO_MPIPE_LINUX_RPC_H__ */ diff --git a/arch/tile/include/gxio/iorpc_mpipe_info.h b/arch/tile/include/gxio/iorpc_mpipe_info.h new file mode 100644 index 0000000..0bcf3f7 --- /dev/null +++ b/arch/tile/include/gxio/iorpc_mpipe_info.h @@ -0,0 +1,46 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#ifndef __GXIO_MPIPE_INFO_LINUX_RPC_H__ +#define __GXIO_MPIPE_INFO_LINUX_RPC_H__ + +#include <hv/iorpc.h> + +#include <hv/drv_mpipe_intf.h> +#include <asm/page.h> +#include <gxio/kiorpc.h> +#include <gxio/mpipe.h> +#include <linux/string.h> +#include <linux/module.h> +#include <asm/pgtable.h> + + +#define GXIO_MPIPE_INFO_OP_ENUMERATE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1251) +#define GXIO_MPIPE_INFO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) +#define GXIO_MPIPE_INFO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) + + +int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context, + unsigned int idx, + _gxio_mpipe_link_name_t * name, + _gxio_mpipe_link_mac_t * mac); + +int gxio_mpipe_info_get_mmio_base(gxio_mpipe_info_context_t * context, + HV_PTE *base); + +int gxio_mpipe_info_check_mmio_offset(gxio_mpipe_info_context_t * context, + unsigned long offset, unsigned long size); + +#endif /* !__GXIO_MPIPE_INFO_LINUX_RPC_H__ */ diff --git a/arch/tile/include/gxio/iorpc_trio.h b/arch/tile/include/gxio/iorpc_trio.h new file mode 100644 index 0000000..15fb779 --- /dev/null +++ b/arch/tile/include/gxio/iorpc_trio.h @@ -0,0 +1,97 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#ifndef __GXIO_TRIO_LINUX_RPC_H__ +#define __GXIO_TRIO_LINUX_RPC_H__ + +#include <hv/iorpc.h> + +#include <hv/drv_trio_intf.h> +#include <gxio/trio.h> +#include <gxio/kiorpc.h> +#include <linux/string.h> +#include <linux/module.h> +#include <asm/pgtable.h> + +#define GXIO_TRIO_OP_ALLOC_ASIDS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1400) + +#define GXIO_TRIO_OP_ALLOC_MEMORY_MAPS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1402) + +#define GXIO_TRIO_OP_ALLOC_PIO_REGIONS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140e) +#define GXIO_TRIO_OP_INIT_PIO_REGION_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x140f) + +#define GXIO_TRIO_OP_INIT_MEMORY_MAP_MMU_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1417) +#define GXIO_TRIO_OP_GET_PORT_PROPERTY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1418) +#define GXIO_TRIO_OP_CONFIG_LEGACY_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1419) +#define GXIO_TRIO_OP_CONFIG_MSI_INTR IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x141a) + +#define GXIO_TRIO_OP_SET_MPS_MRS IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141c) +#define GXIO_TRIO_OP_FORCE_RC_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141d) +#define GXIO_TRIO_OP_FORCE_EP_LINK_UP IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x141e) +#define GXIO_TRIO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) +#define GXIO_TRIO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) + +int gxio_trio_alloc_asids(gxio_trio_context_t * context, unsigned int count, + unsigned int first, unsigned int flags); + + +int gxio_trio_alloc_memory_maps(gxio_trio_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags); + + +int gxio_trio_alloc_pio_regions(gxio_trio_context_t * context, + unsigned int count, unsigned int first, + unsigned int flags); + +int gxio_trio_init_pio_region_aux(gxio_trio_context_t * context, + unsigned int pio_region, unsigned int mac, + uint32_t bus_address_hi, unsigned int flags); + + +int gxio_trio_init_memory_map_mmu_aux(gxio_trio_context_t * context, + unsigned int map, unsigned long va, + uint64_t size, unsigned int asid, + unsigned int mac, uint64_t bus_address, + unsigned int node, + unsigned int order_mode); + +int gxio_trio_get_port_property(gxio_trio_context_t * context, + struct pcie_trio_ports_property *trio_ports); + +int gxio_trio_config_legacy_intr(gxio_trio_context_t * context, int inter_x, + int inter_y, int inter_ipi, int inter_event, + unsigned int mac, unsigned int intx); + +int gxio_trio_config_msi_intr(gxio_trio_context_t * context, int inter_x, + int inter_y, int inter_ipi, int inter_event, + unsigned int mac, unsigned int mem_map, + uint64_t mem_map_base, uint64_t mem_map_limit, + unsigned int asid); + + +int gxio_trio_set_mps_mrs(gxio_trio_context_t * context, uint16_t mps, + uint16_t mrs, unsigned int mac); + +int gxio_trio_force_rc_link_up(gxio_trio_context_t * context, unsigned int mac); + +int gxio_trio_force_ep_link_up(gxio_trio_context_t * context, unsigned int mac); + +int gxio_trio_get_mmio_base(gxio_trio_context_t * context, HV_PTE *base); + +int gxio_trio_check_mmio_offset(gxio_trio_context_t * context, + unsigned long offset, unsigned long size); + +#endif /* !__GXIO_TRIO_LINUX_RPC_H__ */ diff --git a/arch/tile/include/gxio/iorpc_usb_host.h b/arch/tile/include/gxio/iorpc_usb_host.h new file mode 100644 index 0000000..8622e7d --- /dev/null +++ b/arch/tile/include/gxio/iorpc_usb_host.h @@ -0,0 +1,46 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* This file is machine-generated; DO NOT EDIT! */ +#ifndef __GXIO_USB_HOST_LINUX_RPC_H__ +#define __GXIO_USB_HOST_LINUX_RPC_H__ + +#include <hv/iorpc.h> + +#include <hv/drv_usb_host_intf.h> +#include <asm/page.h> +#include <gxio/kiorpc.h> +#include <gxio/usb_host.h> +#include <linux/string.h> +#include <linux/module.h> +#include <asm/pgtable.h> + +#define GXIO_USB_HOST_OP_CFG_INTERRUPT IORPC_OPCODE(IORPC_FORMAT_KERNEL_INTERRUPT, 0x1800) +#define GXIO_USB_HOST_OP_REGISTER_CLIENT_MEMORY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1801) +#define GXIO_USB_HOST_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) +#define GXIO_USB_HOST_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) + +int gxio_usb_host_cfg_interrupt(gxio_usb_host_context_t * context, int inter_x, + int inter_y, int inter_ipi, int inter_event); + +int gxio_usb_host_register_client_memory(gxio_usb_host_context_t * context, + HV_PTE pte, unsigned int flags); + +int gxio_usb_host_get_mmio_base(gxio_usb_host_context_t * context, + HV_PTE *base); + +int gxio_usb_host_check_mmio_offset(gxio_usb_host_context_t * context, + unsigned long offset, unsigned long size); + +#endif /* !__GXIO_USB_HOST_LINUX_RPC_H__ */ diff --git a/arch/tile/include/gxio/kiorpc.h b/arch/tile/include/gxio/kiorpc.h new file mode 100644 index 0000000..ee58209 --- /dev/null +++ b/arch/tile/include/gxio/kiorpc.h @@ -0,0 +1,29 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + * + * Support routines for kernel IORPC drivers. + */ + +#ifndef _GXIO_KIORPC_H +#define _GXIO_KIORPC_H + +#include <linux/types.h> +#include <asm/page.h> +#include <arch/chip.h> + +#if CHIP_HAS_MMIO() +void __iomem *iorpc_ioremap(int hv_fd, resource_size_t offset, + unsigned long size); +#endif + +#endif /* _GXIO_KIORPC_H */ diff --git a/arch/tile/include/gxio/mpipe.h b/arch/tile/include/gxio/mpipe.h new file mode 100644 index 0000000..78c5986 --- /dev/null +++ b/arch/tile/include/gxio/mpipe.h @@ -0,0 +1,1736 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#ifndef _GXIO_MPIPE_H_ +#define _GXIO_MPIPE_H_ + +/* + * + * An API for allocating, configuring, and manipulating mPIPE hardware + * resources. + */ + +#include "common.h" +#include "dma_queue.h" + +#include <linux/time.h> + +#include <arch/mpipe_def.h> +#include <arch/mpipe_shm.h> + +#include <hv/drv_mpipe_intf.h> +#include <hv/iorpc.h> + +/* + * + * The TILE-Gx mPIPE&tm; shim provides Ethernet connectivity, packet + * classification, and packet load balancing services. The + * gxio_mpipe_ API, declared in <gxio/mpipe.h>, allows applications to + * allocate mPIPE IO channels, configure packet distribution + * parameters, and send and receive Ethernet packets. The API is + * designed to be a minimal wrapper around the mPIPE hardware, making + * system calls only where necessary to preserve inter-process + * protection guarantees. + * + * The APIs described below allow the programmer to allocate and + * configure mPIPE resources. As described below, the mPIPE is a + * single shared hardware device that provides partitionable resources + * that are shared between all applications in the system. The + * gxio_mpipe_ API allows userspace code to make resource request + * calls to the hypervisor, which in turns keeps track of the + * resources in use by all applications, maintains protection + * guarantees, and resets resources upon application shutdown. + * + * We strongly recommend reading the mPIPE section of the IO Device + * Guide (UG404) before working with this API. Most functions in the + * gxio_mpipe_ API are directly analogous to hardware interfaces and + * the documentation assumes that the reader understands those + * hardware interfaces. + * + * @section mpipe__ingress mPIPE Ingress Hardware Resources + * + * The mPIPE ingress hardware provides extensive hardware offload for + * tasks like packet header parsing, load balancing, and memory + * management. This section provides a brief introduction to the + * hardware components and the gxio_mpipe_ calls used to manage them; + * see the IO Device Guide for a much more detailed description of the + * mPIPE's capabilities. + * + * When a packet arrives at one of the mPIPE's Ethernet MACs, it is + * assigned a channel number indicating which MAC received it. It + * then proceeds through the following hardware pipeline: + * + * @subsection mpipe__classification Classification + * + * A set of classification processors run header parsing code on each + * incoming packet, extracting information including the destination + * MAC address, VLAN, Ethernet type, and five-tuple hash. Some of + * this information is then used to choose which buffer stack will be + * used to hold the packet, and which bucket will be used by the load + * balancer to determine which application will receive the packet. + * + * The rules by which the buffer stack and bucket are chosen can be + * configured via the @ref gxio_mpipe_classifier API. A given app can + * specify multiple rules, each one specifying a bucket range, and a + * set of buffer stacks, to be used for packets matching the rule. + * Each rule can optionally specify a restricted set of channels, + * VLANs, and/or dMACs, in which it is interested. By default, a + * given rule starts out matching all channels associated with the + * mPIPE context's set of open links; all VLANs; and all dMACs. + * Subsequent restrictions can then be added. + * + * @subsection mpipe__load_balancing Load Balancing + * + * The mPIPE load balancer is responsible for choosing the NotifRing + * to which the packet will be delivered. This decision is based on + * the bucket number indicated by the classification program. In + * general, the bucket number is based on some number of low bits of + * the packet's flow hash (applications that aren't interested in flow + * hashing use a single bucket). Each load balancer bucket keeps a + * record of the NotifRing to which packets directed to that bucket + * are currently being delivered. Based on the bucket's load + * balancing mode (@ref gxio_mpipe_bucket_mode_t), the load balancer + * either forwards the packet to the previously assigned NotifRing or + * decides to choose a new NotifRing. If a new NotifRing is required, + * the load balancer chooses the least loaded ring in the NotifGroup + * associated with the bucket. + * + * The load balancer is a shared resource. Each application needs to + * explicitly allocate NotifRings, NotifGroups, and buckets, using + * gxio_mpipe_alloc_notif_rings(), gxio_mpipe_alloc_notif_groups(), + * and gxio_mpipe_alloc_buckets(). Then the application needs to + * configure them using gxio_mpipe_init_notif_ring() and + * gxio_mpipe_init_notif_group_and_buckets(). + * + * @subsection mpipe__buffers Buffer Selection and Packet Delivery + * + * Once the load balancer has chosen the destination NotifRing, the + * mPIPE DMA engine pops at least one buffer off of the 'buffer stack' + * chosen by the classification program and DMAs the packet data into + * that buffer. Each buffer stack provides a hardware-accelerated + * stack of data buffers with the same size. If the packet data is + * larger than the buffers provided by the chosen buffer stack, the + * mPIPE hardware pops off multiple buffers and chains the packet data + * through a multi-buffer linked list. Once the packet data is + * delivered to the buffer(s), the mPIPE hardware writes the + * ::gxio_mpipe_idesc_t metadata object (calculated by the classifier) + * into the NotifRing and increments the number of packets delivered + * to that ring. + * + * Applications can push buffers onto a buffer stack by calling + * gxio_mpipe_push_buffer() or by egressing a packet with the + * ::gxio_mpipe_edesc_t::hwb bit set, indicating that the egressed + * buffers should be returned to the stack. + * + * Applications can allocate and initialize buffer stacks with the + * gxio_mpipe_alloc_buffer_stacks() and gxio_mpipe_init_buffer_stack() + * APIs. + * + * The application must also register the memory pages that will hold + * packets. This requires calling gxio_mpipe_register_page() for each + * memory page that will hold packets allocated by the application for + * a given buffer stack. Since each buffer stack is limited to 16 + * registered pages, it may be necessary to use huge pages, or even + * extremely huge pages, to hold all the buffers. + * + * @subsection mpipe__iqueue NotifRings + * + * Each NotifRing is a region of shared memory, allocated by the + * application, to which the mPIPE delivers packet descriptors + * (::gxio_mpipe_idesc_t). The application can allocate them via + * gxio_mpipe_alloc_notif_rings(). The application can then either + * explicitly initialize them with gxio_mpipe_init_notif_ring() and + * then read from them manually, or can make use of the convenience + * wrappers provided by @ref gxio_mpipe_wrappers. + * + * @section mpipe__egress mPIPE Egress Hardware + * + * Applications use eDMA rings to queue packets for egress. The + * application can allocate them via gxio_mpipe_alloc_edma_rings(). + * The application can then either explicitly initialize them with + * gxio_mpipe_init_edma_ring() and then write to them manually, or + * can make use of the convenience wrappers provided by + * @ref gxio_mpipe_wrappers. + * + * @section gxio__shortcomings Plans for Future API Revisions + * + * The API defined here is only an initial version of the mPIPE API. + * Future plans include: + * + * - Higher level wrapper functions to provide common initialization + * patterns. This should help users start writing mPIPE programs + * without having to learn the details of the hardware. + * + * - Support for reset and deallocation of resources, including + * cleanup upon application shutdown. + * + * - Support for calling these APIs in the BME. + * + * - Support for IO interrupts. + * + * - Clearer definitions of thread safety guarantees. + * + * @section gxio__mpipe_examples Examples + * + * See the following mPIPE example programs for more information about + * allocating mPIPE resources and using them in real applications: + * + * - @ref mpipe/ingress/app.c : Receiving packets. + * + * - @ref mpipe/forward/app.c : Forwarding packets. + * + * Note that there are several more examples. + */ + +/* Flags that can be passed to resource allocation functions. */ +enum gxio_mpipe_alloc_flags_e { + /* Require an allocation to start at a specified resource index. */ + GXIO_MPIPE_ALLOC_FIXED = HV_MPIPE_ALLOC_FIXED, +}; + +/* Flags that can be passed to memory registration functions. */ +enum gxio_mpipe_mem_flags_e { + /* Do not fill L3 when writing, and invalidate lines upon egress. */ + GXIO_MPIPE_MEM_FLAG_NT_HINT = IORPC_MEM_BUFFER_FLAG_NT_HINT, + + /* L3 cache fills should only populate IO cache ways. */ + GXIO_MPIPE_MEM_FLAG_IO_PIN = IORPC_MEM_BUFFER_FLAG_IO_PIN, +}; + +/* An ingress packet descriptor. When a packet arrives, the mPIPE + * hardware generates this structure and writes it into a NotifRing. + */ +typedef MPIPE_PDESC_t gxio_mpipe_idesc_t; + +/* An egress command descriptor. Applications write this structure + * into eDMA rings and the hardware performs the indicated operation + * (normally involving egressing some bytes). Note that egressing a + * single packet may involve multiple egress command descriptors. + */ +typedef MPIPE_EDMA_DESC_t gxio_mpipe_edesc_t; + +/* Get the "va" field from an "idesc". + * + * This is the address at which the ingress hardware copied the first + * byte of the packet. + * + * If the classifier detected a custom header, then this will point to + * the custom header, and gxio_mpipe_idesc_get_l2_start() will point + * to the actual L2 header. + * + * Note that this value may be misleading if "idesc->be" is set. + * + * @param idesc An ingress packet descriptor. + */ +static inline unsigned char *gxio_mpipe_idesc_get_va(gxio_mpipe_idesc_t *idesc) +{ + return (unsigned char *)(long)idesc->va; +} + +/* Get the "xfer_size" from an "idesc". + * + * This is the actual number of packet bytes transferred into memory + * by the hardware. + * + * Note that this value may be misleading if "idesc->be" is set. + * + * @param idesc An ingress packet descriptor. + * + * ISSUE: Is this the best name for this? + * FIXME: Add more docs about chaining, clipping, etc. + */ +static inline unsigned int gxio_mpipe_idesc_get_xfer_size(gxio_mpipe_idesc_t + *idesc) +{ + return idesc->l2_size; +} + +/* Get the "l2_offset" from an "idesc". + * + * Extremely customized classifiers might not support this function. + * + * This is the number of bytes between the "va" and the L2 header. + * + * The L2 header consists of a destination mac address, a source mac + * address, and an initial ethertype. Various initial ethertypes + * allow encoding extra information in the L2 header, often including + * a vlan, and/or a new ethertype. + * + * Note that the "l2_offset" will be non-zero if (and only if) the + * classifier processed a custom header for the packet. + * + * @param idesc An ingress packet descriptor. + */ +static inline uint8_t gxio_mpipe_idesc_get_l2_offset(gxio_mpipe_idesc_t *idesc) +{ + return (idesc->custom1 >> 32) & 0xFF; +} + +/* Get the "l2_start" from an "idesc". + * + * This is simply gxio_mpipe_idesc_get_va() plus + * gxio_mpipe_idesc_get_l2_offset(). + * + * @param idesc An ingress packet descriptor. + */ +static inline unsigned char *gxio_mpipe_idesc_get_l2_start(gxio_mpipe_idesc_t + *idesc) +{ + unsigned char *va = gxio_mpipe_idesc_get_va(idesc); + return va + gxio_mpipe_idesc_get_l2_offset(idesc); +} + +/* Get the "l2_length" from an "idesc". + * + * This is simply gxio_mpipe_idesc_get_xfer_size() minus + * gxio_mpipe_idesc_get_l2_offset(). + * + * @param idesc An ingress packet descriptor. + */ +static inline unsigned int gxio_mpipe_idesc_get_l2_length(gxio_mpipe_idesc_t + *idesc) +{ + unsigned int xfer_size = idesc->l2_size; + return xfer_size - gxio_mpipe_idesc_get_l2_offset(idesc); +} + +/* A context object used to manage mPIPE hardware resources. */ +typedef struct { + + /* File descriptor for calling up to Linux (and thus the HV). */ + int fd; + + /* The VA at which configuration registers are mapped. */ + char *mmio_cfg_base; + + /* The VA at which IDMA, EDMA, and buffer manager are mapped. */ + char *mmio_fast_base; + + /* The "initialized" buffer stacks. */ + gxio_mpipe_rules_stacks_t __stacks; + +} gxio_mpipe_context_t; + +/* This is only used internally, but it's most easily made visible here. */ +typedef gxio_mpipe_context_t gxio_mpipe_info_context_t; + +/* Initialize an mPIPE context. + * + * This function allocates an mPIPE "service domain" and maps the MMIO + * registers into the caller's VA space. + * + * @param context Context object to be initialized. + * @param mpipe_instance Instance number of mPIPE shim to be controlled via + * context. + */ +extern int gxio_mpipe_init(gxio_mpipe_context_t *context, + unsigned int mpipe_instance); + +/* Destroy an mPIPE context. + * + * This function frees the mPIPE "service domain" and unmaps the MMIO + * registers from the caller's VA space. + * + * If a user process exits without calling this routine, the kernel + * will destroy the mPIPE context as part of process teardown. + * + * @param context Context object to be destroyed. + */ +extern int gxio_mpipe_destroy(gxio_mpipe_context_t *context); + +/***************************************************************** + * Buffer Stacks * + ******************************************************************/ + +/* Allocate a set of buffer stacks. + * + * The return value is NOT interesting if count is zero. + * + * @param context An initialized mPIPE context. + * @param count Number of stacks required. + * @param first Index of first stack if ::GXIO_MPIPE_ALLOC_FIXED flag is set, + * otherwise ignored. + * @param flags Flag bits from ::gxio_mpipe_alloc_flags_e. + * @return Index of first allocated buffer stack, or + * ::GXIO_MPIPE_ERR_NO_BUFFER_STACK if allocation failed. + */ +extern int gxio_mpipe_alloc_buffer_stacks(gxio_mpipe_context_t *context, + unsigned int count, + unsigned int first, + unsigned int flags); + +/* Enum codes for buffer sizes supported by mPIPE. */ +typedef enum { + /* 128 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_128 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_128, + /* 256 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_256 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_256, + /* 512 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_512 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_512, + /* 1024 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_1024 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_1024, + /* 1664 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_1664 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_1664, + /* 4096 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_4096 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_4096, + /* 10368 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_10368 = + MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_10368, + /* 16384 byte packet data buffer. */ + GXIO_MPIPE_BUFFER_SIZE_16384 = MPIPE_BSM_INIT_DAT_1__SIZE_VAL_BSZ_16384 +} gxio_mpipe_buffer_size_enum_t; + +/* Convert a buffer size in bytes into a buffer size enum. */ +extern gxio_mpipe_buffer_size_enum_t +gxio_mpipe_buffer_size_to_buffer_size_enum(size_t size); + +/* Convert a buffer size enum into a buffer size in bytes. */ +extern size_t +gxio_mpipe_buffer_size_enum_to_buffer_size(gxio_mpipe_buffer_size_enum_t + buffer_size_enum); + +/* Calculate the number of bytes required to store a given number of + * buffers in the memory registered with a buffer stack via + * gxio_mpipe_init_buffer_stack(). + */ +extern size_t gxio_mpipe_calc_buffer_stack_bytes(unsigned long buffers); + +/* Initialize a buffer stack. This function binds a region of memory + * to be used by the hardware for storing buffer addresses pushed via + * gxio_mpipe_push_buffer() or as the result of sending a buffer out + * the egress with the 'push to stack when done' bit set. Once this + * function returns, the memory region's contents may be arbitrarily + * modified by the hardware at any time and software should not access + * the memory region again. + * + * @param context An initialized mPIPE context. + * @param stack The buffer stack index. + * @param buffer_size_enum The size of each buffer in the buffer stack, + * as an enum. + * @param mem The address of the buffer stack. This memory must be + * physically contiguous and aligned to a 64kB boundary. + * @param mem_size The size of the buffer stack, in bytes. + * @param mem_flags ::gxio_mpipe_mem_flags_e memory flags. + * @return Zero on success, ::GXIO_MPIPE_ERR_INVAL_BUFFER_SIZE if + * buffer_size_enum is invalid, ::GXIO_MPIPE_ERR_BAD_BUFFER_STACK if + * stack has not been allocated. + */ +extern int gxio_mpipe_init_buffer_stack(gxio_mpipe_context_t *context, + unsigned int stack, + gxio_mpipe_buffer_size_enum_t + buffer_size_enum, void *mem, + size_t mem_size, + unsigned int mem_flags); + +/* Push a buffer onto a previously initialized buffer stack. + * + * The size of the buffer being pushed must match the size that was + * registered with gxio_mpipe_init_buffer_stack(). All packet buffer + * addresses are 128-byte aligned; the low 7 bits of the specified + * buffer address will be ignored. + * + * @param context An initialized mPIPE context. + * @param stack The buffer stack index. + * @param buffer The buffer (the low seven bits are ignored). + */ +static inline void gxio_mpipe_push_buffer(gxio_mpipe_context_t *context, + unsigned int stack, void *buffer) +{ + MPIPE_BSM_REGION_ADDR_t offset = { {0} }; + MPIPE_BSM_REGION_VAL_t val = { {0} }; + + /* + * The mmio_fast_base region starts at the IDMA region, so subtract + * off that initial offset. + */ + offset.region = + MPIPE_MMIO_ADDR__REGION_VAL_BSM - + MPIPE_MMIO_ADDR__REGION_VAL_IDMA; + offset.stack = stack; + +#if __SIZEOF_POINTER__ == 4 + val.va = ((ulong) buffer) >> MPIPE_BSM_REGION_VAL__VA_SHIFT; +#else + val.va = ((long)buffer) >> MPIPE_BSM_REGION_VAL__VA_SHIFT; +#endif + + __gxio_mmio_write(context->mmio_fast_base + offset.word, val.word); +} + +/* Pop a buffer off of a previously initialized buffer stack. + * + * @param context An initialized mPIPE context. + * @param stack The buffer stack index. + * @return The buffer, or NULL if the stack is empty. + */ +static inline void *gxio_mpipe_pop_buffer(gxio_mpipe_context_t *context, + unsigned int stack) +{ + MPIPE_BSM_REGION_ADDR_t offset = { {0} }; + + /* + * The mmio_fast_base region starts at the IDMA region, so subtract + * off that initial offset. + */ + offset.region = + MPIPE_MMIO_ADDR__REGION_VAL_BSM - + MPIPE_MMIO_ADDR__REGION_VAL_IDMA; + offset.stack = stack; + + while (1) { + /* + * Case 1: val.c == ..._UNCHAINED, va is non-zero. + * Case 2: val.c == ..._INVALID, va is zero. + * Case 3: val.c == ..._NOT_RDY, va is zero. + */ + MPIPE_BSM_REGION_VAL_t val; + val.word = + __gxio_mmio_read(context->mmio_fast_base + + offset.word); + + /* + * Handle case 1 and 2 by returning the buffer (or NULL). + * Handle case 3 by waiting for the prefetch buffer to refill. + */ + if (val.c != MPIPE_EDMA_DESC_WORD1__C_VAL_NOT_RDY) + return (void *)((unsigned long)val. + va << MPIPE_BSM_REGION_VAL__VA_SHIFT); + } +} + +/***************************************************************** + * NotifRings * + ******************************************************************/ + +/* Allocate a set of NotifRings. + * + * The return value is NOT interesting if count is zero. + * + * Note that NotifRings are allocated in chunks, so allocating one at + * a time is much less efficient than allocating several at once. + * + * @param context An initialized mPIPE context. + * @param count Number of NotifRings required. + * @param first Index of first NotifRing if ::GXIO_MPIPE_ALLOC_FIXED flag + * is set, otherwise ignored. + * @param flags Flag bits from ::gxio_mpipe_alloc_flags_e. + * @return Index of first allocated buffer NotifRing, or + * ::GXIO_MPIPE_ERR_NO_NOTIF_RING if allocation failed. + */ +extern int gxio_mpipe_alloc_notif_rings(gxio_mpipe_context_t *context, + unsigned int count, unsigned int first, + unsigned int flags); + +/* Initialize a NotifRing, using the given memory and size. + * + * @param context An initialized mPIPE context. + * @param ring The NotifRing index. + * @param mem A physically contiguous region of memory to be filled + * with a ring of ::gxio_mpipe_idesc_t structures. + * @param mem_size Number of bytes in the ring. Must be 128, 512, + * 2048, or 65536 * sizeof(gxio_mpipe_idesc_t). + * @param mem_flags ::gxio_mpipe_mem_flags_e memory flags. + * + * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_NOTIF_RING or + * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure. + */ +extern int gxio_mpipe_init_notif_ring(gxio_mpipe_context_t *context, + unsigned int ring, + void *mem, size_t mem_size, + unsigned int mem_flags); + +/* Configure an interrupt to be sent to a tile on incoming NotifRing + * traffic. Once an interrupt is sent for a particular ring, no more + * will be sent until gxio_mica_enable_notif_ring_interrupt() is called. + * + * @param context An initialized mPIPE context. + * @param x X coordinate of interrupt target tile. + * @param y Y coordinate of interrupt target tile. + * @param i Index of the IPI register which will receive the interrupt. + * @param e Specific event which will be set in the target IPI register when + * the interrupt occurs. + * @param ring The NotifRing index. + * @return Zero on success, GXIO_ERR_INVAL if params are out of range. + */ +extern int gxio_mpipe_request_notif_ring_interrupt(gxio_mpipe_context_t + *context, int x, int y, + int i, int e, + unsigned int ring); + +/* Enable an interrupt on incoming NotifRing traffic. + * + * @param context An initialized mPIPE context. + * @param ring The NotifRing index. + * @return Zero on success, GXIO_ERR_INVAL if params are out of range. + */ +extern int gxio_mpipe_enable_notif_ring_interrupt(gxio_mpipe_context_t + *context, unsigned int ring); + +/* Map all of a client's memory via the given IOTLB. + * @param context An initialized mPIPE context. + * @param iotlb IOTLB index. + * @param pte Page table entry. + * @param flags Flags. + * @return Zero on success, or a negative error code. + */ +extern int gxio_mpipe_register_client_memory(gxio_mpipe_context_t *context, + unsigned int iotlb, HV_PTE pte, + unsigned int flags); + +/***************************************************************** + * Notif Groups * + ******************************************************************/ + +/* Allocate a set of NotifGroups. + * + * The return value is NOT interesting if count is zero. + * + * @param context An initialized mPIPE context. + * @param count Number of NotifGroups required. + * @param first Index of first NotifGroup if ::GXIO_MPIPE_ALLOC_FIXED flag + * is set, otherwise ignored. + * @param flags Flag bits from ::gxio_mpipe_alloc_flags_e. + * @return Index of first allocated buffer NotifGroup, or + * ::GXIO_MPIPE_ERR_NO_NOTIF_GROUP if allocation failed. + */ +extern int gxio_mpipe_alloc_notif_groups(gxio_mpipe_context_t *context, + unsigned int count, + unsigned int first, + unsigned int flags); + +/* Add a NotifRing to a NotifGroup. This only sets a bit in the + * application's 'group' object; the hardware NotifGroup can be + * initialized by passing 'group' to gxio_mpipe_init_notif_group() or + * gxio_mpipe_init_notif_group_and_buckets(). + */ +static inline void +gxio_mpipe_notif_group_add_ring(gxio_mpipe_notif_group_bits_t *bits, int ring) +{ + bits->ring_mask[ring / 64] |= (1ull << (ring % 64)); +} + +/* Set a particular NotifGroup bitmask. Since the load balancer + * makes decisions based on both bucket and NotifGroup state, most + * applications should use gxio_mpipe_init_notif_group_and_buckets() + * rather than using this function to configure just a NotifGroup. + */ +extern int gxio_mpipe_init_notif_group(gxio_mpipe_context_t *context, + unsigned int group, + gxio_mpipe_notif_group_bits_t bits); + +/***************************************************************** + * Load Balancer * + ******************************************************************/ + +/* Allocate a set of load balancer buckets. + * + * The return value is NOT interesting if count is zero. + * + * Note that buckets are allocated in chunks, so allocating one at + * a time is much less efficient than allocating several at once. + * + * Note that the buckets are actually divided into two sub-ranges, of + * different sizes, and different chunk sizes, and the range you get + * by default is determined by the size of the request. Allocations + * cannot span the two sub-ranges. + * + * @param context An initialized mPIPE context. + * @param count Number of buckets required. + * @param first Index of first bucket if ::GXIO_MPIPE_ALLOC_FIXED flag is set, + * otherwise ignored. + * @param flags Flag bits from ::gxio_mpipe_alloc_flags_e. + * @return Index of first allocated buffer bucket, or + * ::GXIO_MPIPE_ERR_NO_BUCKET if allocation failed. + */ +extern int gxio_mpipe_alloc_buckets(gxio_mpipe_context_t *context, + unsigned int count, unsigned int first, + unsigned int flags); + +/* The legal modes for gxio_mpipe_bucket_info_t and + * gxio_mpipe_init_notif_group_and_buckets(). + * + * All modes except ::GXIO_MPIPE_BUCKET_ROUND_ROBIN expect that the user + * will allocate a power-of-two number of buckets and initialize them + * to the same mode. The classifier program then uses the appropriate + * number of low bits from the incoming packet's flow hash to choose a + * load balancer bucket. Based on that bucket's load balancing mode, + * reference count, and currently active NotifRing, the load balancer + * chooses the NotifRing to which the packet will be delivered. + */ +typedef enum { + /* All packets for a bucket go to the same NotifRing unless the + * NotifRing gets full, in which case packets will be dropped. If + * the bucket reference count ever reaches zero, a new NotifRing may + * be chosen. + */ + GXIO_MPIPE_BUCKET_DYNAMIC_FLOW_AFFINITY = + MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_DFA, + + /* All packets for a bucket always go to the same NotifRing. + */ + GXIO_MPIPE_BUCKET_STATIC_FLOW_AFFINITY = + MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_FIXED, + + /* All packets for a bucket go to the least full NotifRing in the + * group, providing load balancing round robin behavior. + */ + GXIO_MPIPE_BUCKET_ROUND_ROBIN = + MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_ALWAYS_PICK, + + /* All packets for a bucket go to the same NotifRing unless the + * NotifRing gets full, at which point the bucket starts using the + * least full NotifRing in the group. If all NotifRings in the + * group are full, packets will be dropped. + */ + GXIO_MPIPE_BUCKET_STICKY_FLOW_LOCALITY = + MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_STICKY, + + /* All packets for a bucket go to the same NotifRing unless the + * NotifRing gets full, or a random timer fires, at which point the + * bucket starts using the least full NotifRing in the group. If + * all NotifRings in the group are full, packets will be dropped. + * WARNING: This mode is BROKEN on chips with fewer than 64 tiles. + */ + GXIO_MPIPE_BUCKET_PREFER_FLOW_LOCALITY = + MPIPE_LBL_INIT_DAT_BSTS_TBL__MODE_VAL_STICKY_RAND, + +} gxio_mpipe_bucket_mode_t; + +/* Copy a set of bucket initialization values into the mPIPE + * hardware. Since the load balancer makes decisions based on both + * bucket and NotifGroup state, most applications should use + * gxio_mpipe_init_notif_group_and_buckets() rather than using this + * function to configure a single bucket. + * + * @param context An initialized mPIPE context. + * @param bucket Bucket index to be initialized. + * @param bucket_info Initial reference count, NotifRing index, and mode. + * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_BUCKET on failure. + */ +extern int gxio_mpipe_init_bucket(gxio_mpipe_context_t *context, + unsigned int bucket, + gxio_mpipe_bucket_info_t bucket_info); + +/* Initializes a group and range of buckets and range of rings such + * that the load balancer runs a particular load balancing function. + * + * First, the group is initialized with the given rings. + * + * Second, each bucket is initialized with the mode and group, and a + * ring chosen round-robin from the given rings. + * + * Normally, the classifier picks a bucket, and then the load balancer + * picks a ring, based on the bucket's mode, group, and current ring, + * possibly updating the bucket's ring. + * + * @param context An initialized mPIPE context. + * @param group The group. + * @param ring The first ring. + * @param num_rings The number of rings. + * @param bucket The first bucket. + * @param num_buckets The number of buckets. + * @param mode The load balancing mode. + * + * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_BUCKET, + * ::GXIO_MPIPE_ERR_BAD_NOTIF_GROUP, or + * ::GXIO_MPIPE_ERR_BAD_NOTIF_RING on failure. + */ +extern int gxio_mpipe_init_notif_group_and_buckets(gxio_mpipe_context_t + *context, + unsigned int group, + unsigned int ring, + unsigned int num_rings, + unsigned int bucket, + unsigned int num_buckets, + gxio_mpipe_bucket_mode_t + mode); + +/* Return credits to a NotifRing and/or bucket. + * + * @param context An initialized mPIPE context. + * @param ring The NotifRing index, or -1. + * @param bucket The bucket, or -1. + * @param count The number of credits to return. + */ +static inline void gxio_mpipe_credit(gxio_mpipe_context_t *context, + int ring, int bucket, unsigned int count) +{ + /* NOTE: Fancy struct initialization would break "C89" header test. */ + + MPIPE_IDMA_RELEASE_REGION_ADDR_t offset = { {0} }; + MPIPE_IDMA_RELEASE_REGION_VAL_t val = { {0} }; + + /* + * The mmio_fast_base region starts at the IDMA region, so subtract + * off that initial offset. + */ + offset.region = + MPIPE_MMIO_ADDR__REGION_VAL_IDMA - + MPIPE_MMIO_ADDR__REGION_VAL_IDMA; + offset.ring = ring; + offset.bucket = bucket; + offset.ring_enable = (ring >= 0); + offset.bucket_enable = (bucket >= 0); + val.count = count; + + __gxio_mmio_write(context->mmio_fast_base + offset.word, val.word); +} + +/***************************************************************** + * Egress Rings * + ******************************************************************/ + +/* Allocate a set of eDMA rings. + * + * The return value is NOT interesting if count is zero. + * + * @param context An initialized mPIPE context. + * @param count Number of eDMA rings required. + * @param first Index of first eDMA ring if ::GXIO_MPIPE_ALLOC_FIXED flag + * is set, otherwise ignored. + * @param flags Flag bits from ::gxio_mpipe_alloc_flags_e. + * @return Index of first allocated buffer eDMA ring, or + * ::GXIO_MPIPE_ERR_NO_EDMA_RING if allocation failed. + */ +extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context, + unsigned int count, unsigned int first, + unsigned int flags); + +/* Initialize an eDMA ring, using the given memory and size. + * + * @param context An initialized mPIPE context. + * @param ring The eDMA ring index. + * @param channel The channel to use. This must be one of the channels + * associated with the context's set of open links. + * @param mem A physically contiguous region of memory to be filled + * with a ring of ::gxio_mpipe_edesc_t structures. + * @param mem_size Number of bytes in the ring. Must be 512, 2048, + * 8192 or 65536, times 16 (i.e. sizeof(gxio_mpipe_edesc_t)). + * @param mem_flags ::gxio_mpipe_mem_flags_e memory flags. + * + * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_EDMA_RING or + * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure. + */ +extern int gxio_mpipe_init_edma_ring(gxio_mpipe_context_t *context, + unsigned int ring, unsigned int channel, + void *mem, size_t mem_size, + unsigned int mem_flags); + +/***************************************************************** + * Classifier Program * + ******************************************************************/ + +/* + * + * Functions for loading or configuring the mPIPE classifier program. + * + * The mPIPE classification processors all run a special "classifier" + * program which, for each incoming packet, parses the packet headers, + * encodes some packet metadata in the "idesc", and either drops the + * packet, or picks a notif ring to handle the packet, and a buffer + * stack to contain the packet, usually based on the channel, VLAN, + * dMAC, flow hash, and packet size, under the guidance of the "rules" + * API described below. + * + * @section gxio_mpipe_classifier_default Default Classifier + * + * The MDE provides a simple "default" classifier program. It is + * shipped as source in "$TILERA_ROOT/src/sys/mpipe/classifier.c", + * which serves as its official documentation. It is shipped as a + * binary program in "$TILERA_ROOT/tile/boot/classifier", which is + * automatically included in bootroms created by "tile-monitor", and + * is automatically loaded by the hypervisor at boot time. + * + * The L2 analysis handles LLC packets, SNAP packets, and "VLAN + * wrappers" (keeping the outer VLAN). + * + * The L3 analysis handles IPv4 and IPv6, dropping packets with bad + * IPv4 header checksums, requesting computation of a TCP/UDP checksum + * if appropriate, and hashing the dest and src IP addresses, plus the + * ports for TCP/UDP packets, into the flow hash. No special analysis + * is done for "fragmented" packets or "tunneling" protocols. Thus, + * the first fragment of a fragmented TCP/UDP packet is hashed using + * src/dest IP address and ports and all subsequent fragments are only + * hashed according to src/dest IP address. + * + * The L3 analysis handles other packets too, hashing the dMAC + * smac into a flow hash. + * + * The channel, VLAN, and dMAC used to pick a "rule" (see the + * "rules" APIs below), which in turn is used to pick a buffer stack + * (based on the packet size) and a bucket (based on the flow hash). + * + * To receive traffic matching a particular (channel/VLAN/dMAC + * pattern, an application should allocate its own buffer stacks and + * load balancer buckets, and map traffic to those stacks and buckets, + * as decribed by the "rules" API below. + * + * Various packet metadata is encoded in the idesc. The flow hash is + * four bytes at 0x0C. The VLAN is two bytes at 0x10. The ethtype is + * two bytes at 0x12. The l3 start is one byte at 0x14. The l4 start + * is one byte at 0x15 for IPv4 and IPv6 packets, and otherwise zero. + * The protocol is one byte at 0x16 for IPv4 and IPv6 packets, and + * otherwise zero. + * + * @section gxio_mpipe_classifier_custom Custom Classifiers. + * + * A custom classifier may be created using "tile-mpipe-cc" with a + * customized version of the default classifier sources. + * + * The custom classifier may be included in bootroms using the + * "--classifier" option to "tile-monitor", or loaded dynamically + * using gxio_mpipe_classifier_load_from_file(). + * + * Be aware that "extreme" customizations may break the assumptions of + * the "rules" APIs described below, but simple customizations, such + * as adding new packet metadata, should be fine. + */ + +/* A set of classifier rules, plus a context. */ +typedef struct { + + /* The context. */ + gxio_mpipe_context_t *context; + + /* The actual rules. */ + gxio_mpipe_rules_list_t list; + +} gxio_mpipe_rules_t; + +/* Initialize a classifier program rules list. + * + * This function can be called on a previously initialized rules list + * to discard any previously added rules. + * + * @param rules Rules list to initialize. + * @param context An initialized mPIPE context. + */ +extern void gxio_mpipe_rules_init(gxio_mpipe_rules_t *rules, + gxio_mpipe_context_t *context); + +/* Begin a new rule on the indicated rules list. + * + * Note that an empty rule matches all packets, but an empty rule list + * matches no packets. + * + * @param rules Rules list to which new rule is appended. + * @param bucket First load balancer bucket to which packets will be + * delivered. + * @param num_buckets Number of buckets (must be a power of two) across + * which packets will be distributed based on the "flow hash". + * @param stacks Either NULL, to assign each packet to the smallest + * initialized buffer stack which does not induce chaining (and to + * drop packets which exceed the largest initialized buffer stack + * buffer size), or an array, with each entry indicating which buffer + * stack should be used for packets up to that size (with 255 + * indicating that those packets should be dropped). + * @return 0 on success, or a negative error code on failure. + */ +extern int gxio_mpipe_rules_begin(gxio_mpipe_rules_t *rules, + unsigned int bucket, + unsigned int num_buckets, + gxio_mpipe_rules_stacks_t *stacks); + +/* Set the headroom of the current rule. + * + * @param rules Rules list whose current rule will be modified. + * @param headroom The headroom. + * @return 0 on success, or a negative error code on failure. + */ +extern int gxio_mpipe_rules_set_headroom(gxio_mpipe_rules_t *rules, + uint8_t headroom); + +/* Indicate that packets from a particular channel can be delivered + * to the buckets and buffer stacks associated with the current rule. + * + * Channels added must be associated with links opened by the mPIPE context + * used in gxio_mpipe_rules_init(). A rule with no channels is equivalent + * to a rule naming all such associated channels. + * + * @param rules Rules list whose current rule will be modified. + * @param channel The channel to add. + * @return 0 on success, or a negative error code on failure. + */ +extern int gxio_mpipe_rules_add_channel(gxio_mpipe_rules_t *rules, + unsigned int channel); + +/* Commit rules. + * + * The rules are sent to the hypervisor, where they are combined with + * the rules from other apps, and used to program the hardware classifier. + * + * Note that if this function returns an error, then the rules will NOT + * have been committed, even if the error is due to interactions with + * rules from another app. + * + * @param rules Rules list to commit. + * @return 0 on success, or a negative error code on failure. + */ +extern int gxio_mpipe_rules_commit(gxio_mpipe_rules_t *rules); + +/***************************************************************** + * Ingress Queue Wrapper * + ******************************************************************/ + +/* + * + * Convenience functions for receiving packets from a NotifRing and + * sending packets via an eDMA ring. + * + * The mpipe ingress and egress hardware uses shared memory packet + * descriptors to describe packets that have arrived on ingress or + * are destined for egress. These descriptors are stored in shared + * memory ring buffers and written or read by hardware as necessary. + * The gxio library provides wrapper functions that manage the head and + * tail pointers for these rings, allowing the user to easily read or + * write packet descriptors. + * + * The initialization interface for ingress and egress rings is quite + * similar. For example, to create an ingress queue, the user passes + * a ::gxio_mpipe_iqueue_t state object, a ring number from + * gxio_mpipe_alloc_notif_rings(), and the address of memory to hold a + * ring buffer to the gxio_mpipe_iqueue_init() function. The function + * returns success when the state object has been initialized and the + * hardware configured to deliver packets to the specified ring + * buffer. Similarly, gxio_mpipe_equeue_init() takes a + * ::gxio_mpipe_equeue_t state object, a ring number from + * gxio_mpipe_alloc_edma_rings(), and a shared memory buffer. + * + * @section gxio_mpipe_iqueue Working with Ingress Queues + * + * Once initialized, the gxio_mpipe_iqueue_t API provides two flows + * for getting the ::gxio_mpipe_idesc_t packet descriptor associated + * with incoming packets. The simplest is to call + * gxio_mpipe_iqueue_get() or gxio_mpipe_iqueue_try_get(). These + * functions copy the oldest packet descriptor out of the NotifRing and + * into a descriptor provided by the caller. They also immediately + * inform the hardware that a descriptor has been processed. + * + * For applications with stringent performance requirements, higher + * efficiency can be achieved by avoiding the packet descriptor copy + * and processing multiple descriptors at once. The + * gxio_mpipe_iqueue_peek() and gxio_mpipe_iqueue_try_peek() functions + * allow such optimizations. These functions provide a pointer to the + * next valid ingress descriptor in the NotifRing's shared memory ring + * buffer, and a count of how many contiguous descriptors are ready to + * be processed. The application can then process any number of those + * descriptors in place, calling gxio_mpipe_iqueue_consume() to inform + * the hardware after each one has been processed. + * + * @section gxio_mpipe_equeue Working with Egress Queues + * + * Similarly, the egress queue API provides a high-performance + * interface plus a simple wrapper for use in posting + * ::gxio_mpipe_edesc_t egress packet descriptors. The simple + * version, gxio_mpipe_equeue_put(), allows the programmer to wait for + * an eDMA ring slot to become available and write a single descriptor + * into the ring. + * + * Alternatively, you can reserve slots in the eDMA ring using + * gxio_mpipe_equeue_reserve() or gxio_mpipe_equeue_try_reserve(), and + * then fill in each slot using gxio_mpipe_equeue_put_at(). This + * capability can be used to amortize the cost of reserving slots + * across several packets. It also allows gather operations to be + * performed on a shared equeue, by ensuring that the edescs for all + * the fragments are all contiguous in the eDMA ring. + * + * The gxio_mpipe_equeue_reserve() and gxio_mpipe_equeue_try_reserve() + * functions return a 63-bit "completion slot", which is actually a + * sequence number, the low bits of which indicate the ring buffer + * index and the high bits the number of times the application has + * gone around the egress ring buffer. The extra bits allow an + * application to check for egress completion by calling + * gxio_mpipe_equeue_is_complete() to see whether a particular 'slot' + * number has finished. Given the maximum packet rates of the Gx + * processor, the 63-bit slot number will never wrap. + * + * In practice, most applications use the ::gxio_mpipe_edesc_t::hwb + * bit to indicate that the buffers containing egress packet data + * should be pushed onto a buffer stack when egress is complete. Such + * applications generally do not need to know when an egress operation + * completes (since there is no need to free a buffer post-egress), + * and thus can use the optimized gxio_mpipe_equeue_reserve_fast() or + * gxio_mpipe_equeue_try_reserve_fast() functions, which return a 24 + * bit "slot", instead of a 63-bit "completion slot". + * + * Once a slot has been "reserved", it MUST be filled. If the + * application reserves a slot and then decides that it does not + * actually need it, it can set the ::gxio_mpipe_edesc_t::ns (no send) + * bit on the descriptor passed to gxio_mpipe_equeue_put_at() to + * indicate that no data should be sent. This technique can also be + * used to drop an incoming packet, instead of forwarding it, since + * any buffer will still be pushed onto the buffer stack when the + * egress descriptor is processed. + */ + +/* A convenient interface to a NotifRing, for use by a single thread. + */ +typedef struct { + + /* The context. */ + gxio_mpipe_context_t *context; + + /* The actual NotifRing. */ + gxio_mpipe_idesc_t *idescs; + + /* The number of entries. */ + unsigned long num_entries; + + /* The number of entries minus one. */ + unsigned long mask_num_entries; + + /* The log2() of the number of entries. */ + unsigned long log2_num_entries; + + /* The next entry. */ + unsigned int head; + + /* The NotifRing id. */ + unsigned int ring; + +#ifdef __BIG_ENDIAN__ + /* The number of byteswapped entries. */ + unsigned int swapped; +#endif + +} gxio_mpipe_iqueue_t; + +/* Initialize an "iqueue". + * + * Takes the iqueue plus the same args as gxio_mpipe_init_notif_ring(). + */ +extern int gxio_mpipe_iqueue_init(gxio_mpipe_iqueue_t *iqueue, + gxio_mpipe_context_t *context, + unsigned int ring, + void *mem, size_t mem_size, + unsigned int mem_flags); + +/* Advance over some old entries in an iqueue. + * + * Please see the documentation for gxio_mpipe_iqueue_consume(). + * + * @param iqueue An ingress queue initialized via gxio_mpipe_iqueue_init(). + * @param count The number of entries to advance over. + */ +static inline void gxio_mpipe_iqueue_advance(gxio_mpipe_iqueue_t *iqueue, + int count) +{ + /* Advance with proper wrap. */ + int head = iqueue->head + count; + iqueue->head = + (head & iqueue->mask_num_entries) + + (head >> iqueue->log2_num_entries); + +#ifdef __BIG_ENDIAN__ + /* HACK: Track swapped entries. */ + iqueue->swapped -= count; +#endif +} + +/* Release the ring and bucket for an old entry in an iqueue. + * + * Releasing the ring allows more packets to be delivered to the ring. + * + * Releasing the bucket allows flows using the bucket to be moved to a + * new ring when using GXIO_MPIPE_BUCKET_DYNAMIC_FLOW_AFFINITY. + * + * This function is shorthand for "gxio_mpipe_credit(iqueue->context, + * iqueue->ring, idesc->bucket_id, 1)", and it may be more convenient + * to make that underlying call, using those values, instead of + * tracking the entire "idesc". + * + * If packet processing is deferred, optimal performance requires that + * the releasing be deferred as well. + * + * Please see the documentation for gxio_mpipe_iqueue_consume(). + * + * @param iqueue An ingress queue initialized via gxio_mpipe_iqueue_init(). + * @param idesc The descriptor which was processed. + */ +static inline void gxio_mpipe_iqueue_release(gxio_mpipe_iqueue_t *iqueue, + gxio_mpipe_idesc_t *idesc) +{ + gxio_mpipe_credit(iqueue->context, iqueue->ring, idesc->bucket_id, 1); +} + +/* Consume a packet from an "iqueue". + * + * After processing packets peeked at via gxio_mpipe_iqueue_peek() + * or gxio_mpipe_iqueue_try_peek(), you must call this function, or + * gxio_mpipe_iqueue_advance() plus gxio_mpipe_iqueue_release(), to + * advance over those entries, and release their rings and buckets. + * + * You may call this function as each packet is processed, or you can + * wait until several packets have been processed. + * + * Note that if you are using a single bucket, and you are handling + * batches of N packets, then you can replace several calls to this + * function with calls to "gxio_mpipe_iqueue_advance(iqueue, N)" and + * "gxio_mpipe_credit(iqueue->context, iqueue->ring, bucket, N)". + * + * Note that if your classifier sets "idesc->nr", then you should + * explicitly call "gxio_mpipe_iqueue_advance(iqueue, idesc)" plus + * "gxio_mpipe_credit(iqueue->context, iqueue->ring, -1, 1)", to + * avoid incorrectly crediting the (unused) bucket. + * + * @param iqueue An ingress queue initialized via gxio_mpipe_iqueue_init(). + * @param idesc The descriptor which was processed. + */ +static inline void gxio_mpipe_iqueue_consume(gxio_mpipe_iqueue_t *iqueue, + gxio_mpipe_idesc_t *idesc) +{ + gxio_mpipe_iqueue_advance(iqueue, 1); + gxio_mpipe_iqueue_release(iqueue, idesc); +} + +/* Peek at the next packet(s) in an "iqueue", without waiting. + * + * If no packets are available, fills idesc_ref with NULL, and then + * returns ::GXIO_MPIPE_ERR_IQUEUE_EMPTY. Otherwise, fills idesc_ref + * with the address of the next valid packet descriptor, and returns + * the maximum number of valid descriptors which can be processed. + * You may process fewer descriptors if desired. + * + * Call gxio_mpipe_iqueue_consume() on each packet once it has been + * processed (or dropped), to allow more packets to be delivered. + * + * @param iqueue An ingress queue initialized via gxio_mpipe_iqueue_init(). + * @param idesc_ref A pointer to a packet descriptor pointer. + * @return The (positive) number of packets which can be processed, + * or ::GXIO_MPIPE_ERR_IQUEUE_EMPTY if no packets are available. + */ +static inline int gxio_mpipe_iqueue_try_peek(gxio_mpipe_iqueue_t *iqueue, + gxio_mpipe_idesc_t **idesc_ref) +{ + gxio_mpipe_idesc_t *next; + + uint64_t head = iqueue->head; + uint64_t tail = __gxio_mmio_read(iqueue->idescs); + + /* Available entries. */ + uint64_t avail = + (tail >= head) ? (tail - head) : (iqueue->num_entries - head); + + if (avail == 0) { + *idesc_ref = NULL; + return GXIO_MPIPE_ERR_IQUEUE_EMPTY; + } + + next = &iqueue->idescs[head]; + + /* ISSUE: Is this helpful? */ + __insn_prefetch(next); + +#ifdef __BIG_ENDIAN__ + /* HACK: Swap new entries directly in memory. */ + { + int i, j; + for (i = iqueue->swapped; i < avail; i++) { + for (j = 0; j < 8; j++) + next[i].words[j] = + __builtin_bswap64(next[i].words[j]); + } + iqueue->swapped = avail; + } +#endif + + *idesc_ref = next; + + return avail; +} + +/* Drop a packet by pushing its buffer (if appropriate). + * + * NOTE: The caller must still call gxio_mpipe_iqueue_consume() if idesc + * came from gxio_mpipe_iqueue_try_peek() or gxio_mpipe_iqueue_peek(). + * + * @param iqueue An ingress queue initialized via gxio_mpipe_iqueue_init(). + * @param idesc A packet descriptor. + */ +static inline void gxio_mpipe_iqueue_drop(gxio_mpipe_iqueue_t *iqueue, + gxio_mpipe_idesc_t *idesc) +{ + /* FIXME: Handle "chaining" properly. */ + + if (!idesc->be) { + unsigned char *va = gxio_mpipe_idesc_get_va(idesc); + gxio_mpipe_push_buffer(iqueue->context, idesc->stack_idx, va); + } +} + +/***************************************************************** + * Egress Queue Wrapper * + ******************************************************************/ + +/* A convenient, thread-safe interface to an eDMA ring. */ +typedef struct { + + /* State object for tracking head and tail pointers. */ + __gxio_dma_queue_t dma_queue; + + /* The ring entries. */ + gxio_mpipe_edesc_t *edescs; + + /* The number of entries minus one. */ + unsigned long mask_num_entries; + + /* The log2() of the number of entries. */ + unsigned long log2_num_entries; + +} gxio_mpipe_equeue_t; + +/* Initialize an "equeue". + * + * Takes the equeue plus the same args as gxio_mpipe_init_edma_ring(). + */ +extern int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, + gxio_mpipe_context_t *context, + unsigned int edma_ring_id, + unsigned int channel, + void *mem, unsigned int mem_size, + unsigned int mem_flags); + +/* Reserve completion slots for edescs. + * + * Use gxio_mpipe_equeue_put_at() to actually populate the slots. + * + * This function is slower than gxio_mpipe_equeue_reserve_fast(), but + * returns a full 64 bit completion slot, which can be used with + * gxio_mpipe_equeue_is_complete(). + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param num Number of slots to reserve (must be non-zero). + * @return The first reserved completion slot, or a negative error code. + */ +static inline int64_t gxio_mpipe_equeue_reserve(gxio_mpipe_equeue_t *equeue, + unsigned int num) +{ + return __gxio_dma_queue_reserve_aux(&equeue->dma_queue, num, true); +} + +/* Reserve completion slots for edescs, if possible. + * + * Use gxio_mpipe_equeue_put_at() to actually populate the slots. + * + * This function is slower than gxio_mpipe_equeue_try_reserve_fast(), + * but returns a full 64 bit completion slot, which can be used with + * gxio_mpipe_equeue_is_complete(). + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param num Number of slots to reserve (must be non-zero). + * @return The first reserved completion slot, or a negative error code. + */ +static inline int64_t gxio_mpipe_equeue_try_reserve(gxio_mpipe_equeue_t + *equeue, unsigned int num) +{ + return __gxio_dma_queue_reserve_aux(&equeue->dma_queue, num, false); +} + +/* Reserve slots for edescs. + * + * Use gxio_mpipe_equeue_put_at() to actually populate the slots. + * + * This function is faster than gxio_mpipe_equeue_reserve(), but + * returns a 24 bit slot (instead of a 64 bit completion slot), which + * thus cannot be used with gxio_mpipe_equeue_is_complete(). + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param num Number of slots to reserve (should be non-zero). + * @return The first reserved slot, or a negative error code. + */ +static inline int64_t gxio_mpipe_equeue_reserve_fast(gxio_mpipe_equeue_t + *equeue, unsigned int num) +{ + return __gxio_dma_queue_reserve(&equeue->dma_queue, num, true, false); +} + +/* Reserve slots for edescs, if possible. + * + * Use gxio_mpipe_equeue_put_at() to actually populate the slots. + * + * This function is faster than gxio_mpipe_equeue_try_reserve(), but + * returns a 24 bit slot (instead of a 64 bit completion slot), which + * thus cannot be used with gxio_mpipe_equeue_is_complete(). + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param num Number of slots to reserve (should be non-zero). + * @return The first reserved slot, or a negative error code. + */ +static inline int64_t gxio_mpipe_equeue_try_reserve_fast(gxio_mpipe_equeue_t + *equeue, + unsigned int num) +{ + return __gxio_dma_queue_reserve(&equeue->dma_queue, num, false, false); +} + +/* + * HACK: This helper function tricks gcc 4.6 into avoiding saving + * a copy of "edesc->words[0]" on the stack for no obvious reason. + */ + +static inline void gxio_mpipe_equeue_put_at_aux(gxio_mpipe_equeue_t *equeue, + uint_reg_t ew[2], + unsigned long slot) +{ + unsigned long edma_slot = slot & equeue->mask_num_entries; + gxio_mpipe_edesc_t *edesc_p = &equeue->edescs[edma_slot]; + + /* + * ISSUE: Could set eDMA ring to be on generation 1 at start, which + * would avoid the negation here, perhaps allowing "__insn_bfins()". + */ + ew[0] |= !((slot >> equeue->log2_num_entries) & 1); + + /* + * NOTE: We use "__gxio_mpipe_write()", plus the fact that the eDMA + * queue alignment restrictions ensure that these two words are on + * the same cacheline, to force proper ordering between the stores. + */ + __gxio_mmio_write64(&edesc_p->words[1], ew[1]); + __gxio_mmio_write64(&edesc_p->words[0], ew[0]); +} + +/* Post an edesc to a given slot in an equeue. + * + * This function copies the supplied edesc into entry "slot mod N" in + * the underlying ring, setting the "gen" bit to the appropriate value + * based on "(slot mod N*2)", where "N" is the size of the ring. Note + * that the higher bits of slot are unused, and thus, this function + * can handle "slots" as well as "completion slots". + * + * Normally this function is used to fill in slots reserved by + * gxio_mpipe_equeue_try_reserve(), gxio_mpipe_equeue_reserve(), + * gxio_mpipe_equeue_try_reserve_fast(), or + * gxio_mpipe_equeue_reserve_fast(), + * + * This function can also be used without "reserving" slots, if the + * application KNOWS that the ring can never overflow, for example, by + * pushing fewer buffers into the buffer stacks than there are total + * slots in the equeue, but this is NOT recommended. + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param edesc The egress descriptor to be posted. + * @param slot An egress slot (only the low bits are actually used). + */ +static inline void gxio_mpipe_equeue_put_at(gxio_mpipe_equeue_t *equeue, + gxio_mpipe_edesc_t edesc, + unsigned long slot) +{ + gxio_mpipe_equeue_put_at_aux(equeue, edesc.words, slot); +} + +/* Post an edesc to the next slot in an equeue. + * + * This is a convenience wrapper around + * gxio_mpipe_equeue_reserve_fast() and gxio_mpipe_equeue_put_at(). + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param edesc The egress descriptor to be posted. + * @return 0 on success. + */ +static inline int gxio_mpipe_equeue_put(gxio_mpipe_equeue_t *equeue, + gxio_mpipe_edesc_t edesc) +{ + int64_t slot = gxio_mpipe_equeue_reserve_fast(equeue, 1); + if (slot < 0) + return (int)slot; + + gxio_mpipe_equeue_put_at(equeue, edesc, slot); + + return 0; +} + +/* Ask the mPIPE hardware to egress outstanding packets immediately. + * + * This call is not necessary, but may slightly reduce overall latency. + * + * Technically, you should flush all gxio_mpipe_equeue_put_at() writes + * to memory before calling this function, to ensure the descriptors + * are visible in memory before the mPIPE hardware actually looks for + * them. But this should be very rare, and the only side effect would + * be increased latency, so it is up to the caller to decide whether + * or not to flush memory. + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + */ +static inline void gxio_mpipe_equeue_flush(gxio_mpipe_equeue_t *equeue) +{ + /* Use "ring_idx = 0" and "count = 0" to "wake up" the eDMA ring. */ + MPIPE_EDMA_POST_REGION_VAL_t val = { {0} }; + /* Flush the write buffers. */ + __insn_flushwb(); + __gxio_mmio_write(equeue->dma_queue.post_region_addr, val.word); +} + +/* Determine if a given edesc has been completed. + * + * Note that this function requires a "completion slot", and thus may + * NOT be used with a "slot" from gxio_mpipe_equeue_reserve_fast() or + * gxio_mpipe_equeue_try_reserve_fast(). + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param completion_slot The completion slot used by the edesc. + * @param update If true, and the desc does not appear to have completed + * yet, then update any software cache of the hardware completion counter, + * and check again. This should normally be true. + * @return True iff the given edesc has been completed. + */ +static inline int gxio_mpipe_equeue_is_complete(gxio_mpipe_equeue_t *equeue, + int64_t completion_slot, + int update) +{ + return __gxio_dma_queue_is_complete(&equeue->dma_queue, + completion_slot, update); +} + +/***************************************************************** + * Link Management * + ******************************************************************/ + +/* + * + * Functions for manipulating and sensing the state and configuration + * of physical network links. + * + * @section gxio_mpipe_link_perm Link Permissions + * + * Opening a link (with gxio_mpipe_link_open()) requests a set of link + * permissions, which control what may be done with the link, and potentially + * what permissions may be granted to other processes. + * + * Data permission allows the process to receive packets from the link by + * specifying the link's channel number in mPIPE packet distribution rules, + * and to send packets to the link by using the link's channel number as + * the target for an eDMA ring. + * + * Stats permission allows the process to retrieve link attributes (such as + * the speeds it is capable of running at, or whether it is currently up), and + * to read and write certain statistics-related registers in the link's MAC. + * + * Control permission allows the process to retrieve and modify link attributes + * (so that it may, for example, bring the link up and take it down), and + * read and write many registers in the link's MAC and PHY. + * + * Any permission may be requested as shared, which allows other processes + * to also request shared permission, or exclusive, which prevents other + * processes from requesting it. In keeping with GXIO's typical usage in + * an embedded environment, the defaults for all permissions are shared. + * + * Permissions are granted on a first-come, first-served basis, so if two + * applications request an exclusive permission on the same link, the one + * to run first will win. Note, however, that some system components, like + * the kernel Ethernet driver, may get an opportunity to open links before + * any applications run. + * + * @section gxio_mpipe_link_names Link Names + * + * Link names are of the form gbe<em>number</em> (for Gigabit Ethernet), + * xgbe<em>number</em> (for 10 Gigabit Ethernet), loop<em>number</em> (for + * internal mPIPE loopback), or ilk<em>number</em>/<em>channel</em> + * (for Interlaken links); for instance, gbe0, xgbe1, loop3, and + * ilk0/12 are all possible link names. The correspondence between + * the link name and an mPIPE instance number or mPIPE channel number is + * system-dependent; all links will not exist on all systems, and the set + * of numbers used for a particular link type may not start at zero and may + * not be contiguous. Use gxio_mpipe_link_enumerate() to retrieve the set of + * links which exist on a system, and always use gxio_mpipe_link_instance() + * to determine which mPIPE controls a particular link. + * + * Note that in some cases, links may share hardware, such as PHYs, or + * internal mPIPE buffers; in these cases, only one of the links may be + * opened at a time. This is especially common with xgbe and gbe ports, + * since each xgbe port uses 4 SERDES lanes, each of which may also be + * configured as one gbe port. + * + * @section gxio_mpipe_link_states Link States + * + * The mPIPE link management model revolves around three different states, + * which are maintained for each link: + * + * 1. The <em>current</em> link state: is the link up now, and if so, at + * what speed? + * + * 2. The <em>desired</em> link state: what do we want the link state to be? + * The system is always working to make this state the current state; + * thus, if the desired state is up, and the link is down, we'll be + * constantly trying to bring it up, automatically. + * + * 3. The <em>possible</em> link state: what speeds are valid for this + * particular link? Or, in other words, what are the capabilities of + * the link hardware? + * + * These link states are not, strictly speaking, related to application + * state; they may be manipulated at any time, whether or not the link + * is currently being used for data transfer. However, for convenience, + * gxio_mpipe_link_open() and gxio_mpipe_link_close() (or application exit) + * can affect the link state. These implicit link management operations + * may be modified or disabled by the use of link open flags. + * + * From an application, you can use gxio_mpipe_link_get_attr() + * and gxio_mpipe_link_set_attr() to manipulate the link states. + * gxio_mpipe_link_get_attr() with ::GXIO_MPIPE_LINK_POSSIBLE_STATE + * gets you the possible link state. gxio_mpipe_link_get_attr() with + * ::GXIO_MPIPE_LINK_CURRENT_STATE gets you the current link state. + * Finally, gxio_mpipe_link_set_attr() and gxio_mpipe_link_get_attr() + * with ::GXIO_MPIPE_LINK_DESIRED_STATE allow you to modify or retrieve + * the desired link state. + * + * If you want to manage a link from a part of your application which isn't + * involved in packet processing, you can use the ::GXIO_MPIPE_LINK_NO_DATA + * flags on a gxio_mpipe_link_open() call. This opens the link, but does + * not request data permission, so it does not conflict with any exclusive + * permissions which may be held by other processes. You can then can use + * gxio_mpipe_link_get_attr() and gxio_mpipe_link_set_attr() on this link + * object to bring up or take down the link. + * + * Some links support link state bits which support various loopback + * modes. ::GXIO_MPIPE_LINK_LOOP_MAC tests datapaths within the Tile + * Processor itself; ::GXIO_MPIPE_LINK_LOOP_PHY tests the datapath between + * the Tile Processor and the external physical layer interface chip; and + * ::GXIO_MPIPE_LINK_LOOP_EXT tests the entire network datapath with the + * aid of an external loopback connector. In addition to enabling hardware + * testing, such configuration can be useful for software testing, as well. + * + * When LOOP_MAC or LOOP_PHY is enabled, packets transmitted on a channel + * will be received by that channel, instead of being emitted on the + * physical link, and packets received on the physical link will be ignored. + * Other than that, all standard GXIO operations work as you might expect. + * Note that loopback operation requires that the link be brought up using + * one or more of the GXIO_MPIPE_LINK_SPEED_xxx link state bits. + * + * Those familiar with previous versions of the MDE on TILEPro hardware + * will notice significant similarities between the NetIO link management + * model and the mPIPE link management model. However, the NetIO model + * was developed in stages, and some of its features -- for instance, + * the default setting of certain flags -- were shaped by the need to be + * compatible with previous versions of NetIO. Since the features provided + * by the mPIPE hardware and the mPIPE GXIO library are significantly + * different than those provided by NetIO, in some cases, we have made + * different choices in the mPIPE link management API. Thus, please read + * this documentation carefully before assuming that mPIPE link management + * operations are exactly equivalent to their NetIO counterparts. + */ + +/* An object used to manage mPIPE link state and resources. */ +typedef struct { + /* The overall mPIPE context. */ + gxio_mpipe_context_t *context; + + /* The channel number used by this link. */ + uint8_t channel; + + /* The MAC index used by this link. */ + uint8_t mac; +} gxio_mpipe_link_t; + +/* Retrieve one of this system's legal link names, and its MAC address. + * + * @param index Link name index. If a system supports N legal link names, + * then indices between 0 and N - 1, inclusive, each correspond to one of + * those names. Thus, to retrieve all of a system's legal link names, + * call this function in a loop, starting with an index of zero, and + * incrementing it once per iteration until -1 is returned. + * @param link_name Pointer to the buffer which will receive the retrieved + * link name. The buffer should contain space for at least + * ::GXIO_MPIPE_LINK_NAME_LEN bytes; the returned name, including the + * terminating null byte, will be no longer than that. + * @param link_name Pointer to the buffer which will receive the retrieved + * MAC address. The buffer should contain space for at least 6 bytes. + * @return Zero if a link name was successfully retrieved; -1 if one was + * not. + */ +extern int gxio_mpipe_link_enumerate_mac(int index, char *link_name, + uint8_t *mac_addr); + +/* Open an mPIPE link. + * + * A link must be opened before it may be used to send or receive packets, + * and before its state may be examined or changed. Depending up on the + * link's intended use, one or more link permissions may be requested via + * the flags parameter; see @ref gxio_mpipe_link_perm. In addition, flags + * may request that the link's state be modified at open time. See @ref + * gxio_mpipe_link_states and @ref gxio_mpipe_link_open_flags for more detail. + * + * @param link A link state object, which will be initialized if this + * function completes successfully. + * @param context An initialized mPIPE context. + * @param link_name Name of the link. + * @param flags Zero or more @ref gxio_mpipe_link_open_flags, ORed together. + * @return 0 if the link was successfully opened, or a negative error code. + * + */ +extern int gxio_mpipe_link_open(gxio_mpipe_link_t *link, + gxio_mpipe_context_t *context, + const char *link_name, unsigned int flags); + +/* Close an mPIPE link. + * + * Closing a link makes it available for use by other processes. Once + * a link has been closed, packets may no longer be sent on or received + * from the link, and its state may not be examined or changed. + * + * @param link A link state object, which will no longer be initialized + * if this function completes successfully. + * @return 0 if the link was successfully closed, or a negative error code. + * + */ +extern int gxio_mpipe_link_close(gxio_mpipe_link_t *link); + +/* Return a link's channel number. + * + * @param link A properly initialized link state object. + * @return The channel number for the link. + */ +static inline int gxio_mpipe_link_channel(gxio_mpipe_link_t *link) +{ + return link->channel; +} + +/////////////////////////////////////////////////////////////////// +// Timestamp // +/////////////////////////////////////////////////////////////////// + +/* Get the timestamp of mPIPE when this routine is called. + * + * @param context An initialized mPIPE context. + * @param ts A timespec structure to store the current clock. + * @return If the call was successful, zero; otherwise, a negative error + * code. + */ +extern int gxio_mpipe_get_timestamp(gxio_mpipe_context_t *context, + struct timespec *ts); + +/* Set the timestamp of mPIPE. + * + * @param context An initialized mPIPE context. + * @param ts A timespec structure to store the requested clock. + * @return If the call was successful, zero; otherwise, a negative error + * code. + */ +extern int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context, + const struct timespec *ts); + +/* Adjust the timestamp of mPIPE. + * + * @param context An initialized mPIPE context. + * @param delta A signed time offset to adjust, in nanoseconds. + * The absolute value of this parameter must be less than or + * equal to 1000000000. + * @return If the call was successful, zero; otherwise, a negative error + * code. + */ +extern int gxio_mpipe_adjust_timestamp(gxio_mpipe_context_t *context, + int64_t delta); + +#endif /* !_GXIO_MPIPE_H_ */ diff --git a/arch/tile/include/gxio/trio.h b/arch/tile/include/gxio/trio.h new file mode 100644 index 0000000..77b80cd --- /dev/null +++ b/arch/tile/include/gxio/trio.h @@ -0,0 +1,298 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/* + * + * An API for allocating, configuring, and manipulating TRIO hardware + * resources + */ + +/* + * + * The TILE-Gx TRIO shim provides connections to external devices via + * PCIe or other transaction IO standards. The gxio_trio_ API, + * declared in <gxio/trio.h>, allows applications to allocate and + * configure TRIO IO resources like DMA command rings, memory map + * windows, and device interrupts. The following sections introduce + * the various components of the API. We strongly recommend reading + * the TRIO section of the IO Device Guide (UG404) before working with + * this API. + * + * @section trio__ingress TRIO Ingress Hardware Resources + * + * The TRIO ingress hardware is responsible for examining incoming + * PCIe or StreamIO packets and choosing a processing mechanism based + * on the packets' bus address. The gxio_trio_ API can be used to + * configure different handlers for different ranges of bus address + * space. The user can configure "mapped memory" and "scatter queue" + * regions to match incoming packets within 4kB-aligned ranges of bus + * addresses. Each range specifies a different set of mapping + * parameters to be applied when handling the ingress packet. The + * following sections describe how to work with MapMem and scatter + * queue regions. + * + * @subsection trio__mapmem TRIO MapMem Regions + * + * TRIO mapped memory (or MapMem) regions allow the user to map + * incoming read and write requests directly to the application's + * memory space. MapMem regions are allocated via + * gxio_trio_alloc_memory_maps(). Given an integer MapMem number, + * applications can use gxio_trio_init_memory_map() to specify the + * range of bus addresses that will match the region and the range of + * virtual addresses to which those packets will be applied. + * + * As with many other gxio APIs, the programmer must be sure to + * register memory pages that will be used with MapMem regions. Pages + * can be registered with TRIO by allocating an ASID (address space + * identifier) and then using gxio_trio_register_page() to register up to + * 16 pages with the hardware. The initialization functions for + * resources that require registered memory (MapMem, scatter queues, + * push DMA, and pull DMA) then take an 'asid' parameter in order to + * configure which set of registered pages is used by each resource. + * + * @subsection trio__scatter_queue TRIO Scatter Queues + * + * The TRIO shim's scatter queue regions allow users to dynamically + * map buffers from a large address space into a small range of bus + * addresses. This is particularly helpful for PCIe endpoint devices, + * where the host generally limits the size of BARs to tens of + * megabytes. + * + * Each scatter queue consists of a memory map region, a queue of + * tile-side buffer VAs to be mapped to that region, and a bus-mapped + * "doorbell" register that the remote endpoint can write to trigger a + * dequeue of the current buffer VA, thus swapping in a new buffer. + * The VAs pushed onto a scatter queue must be 4kB aligned, so + * applications may need to use higher-level protocols to inform + * remote entities that they should apply some additional, sub-4kB + * offset when reading or writing the scatter queue region. For more + * information, see the IO Device Guide (UG404). + * + * @section trio__egress TRIO Egress Hardware Resources + * + * The TRIO shim supports two mechanisms for egress packet generation: + * programmed IO (PIO) and push/pull DMA. PIO allows applications to + * create MMIO mappings for PCIe or StreamIO address space, such that + * the application can generate word-sized read or write transactions + * by issuing load or store instructions. Push and pull DMA are tuned + * for larger transactions; they use specialized hardware engines to + * transfer large blocks of data at line rate. + * + * @subsection trio__pio TRIO Programmed IO + * + * Programmed IO allows applications to create MMIO mappings for PCIe + * or StreamIO address space. The hardware PIO regions support access + * to PCIe configuration, IO, and memory space, but the gxio_trio API + * only supports memory space accesses. PIO regions are allocated + * with gxio_trio_alloc_pio_regions() and initialized via + * gxio_trio_init_pio_region(). Once a region is bound to a range of + * bus address via the initialization function, the application can + * use gxio_trio_map_pio_region() to create MMIO mappings from its VA + * space onto the range of bus addresses supported by the PIO region. + * + * @subsection trio_dma TRIO Push and Pull DMA + * + * The TRIO push and pull DMA engines allow users to copy blocks of + * data between application memory and the bus. Push DMA generates + * write packets that copy from application memory to the bus and pull + * DMA generates read packets that copy from the bus into application + * memory. The DMA engines are managed via an API that is very + * similar to the mPIPE eDMA interface. For a detailed explanation of + * the eDMA queue API, see @ref gxio_mpipe_wrappers. + * + * Push and pull DMA queues are allocated via + * gxio_trio_alloc_push_dma_ring() / gxio_trio_alloc_pull_dma_ring(). + * Once allocated, users generally use a ::gxio_trio_dma_queue_t + * object to manage the queue, providing easy wrappers for reserving + * command slots in the DMA command ring, filling those slots, and + * waiting for commands to complete. DMA queues can be initialized + * via gxio_trio_init_push_dma_queue() or + * gxio_trio_init_pull_dma_queue(). + * + * See @ref trio/push_dma/app.c for an example of how to use push DMA. + * + * @section trio_shortcomings Plans for Future API Revisions + * + * The simulation framework is incomplete. Future features include: + * + * - Support for reset and deallocation of resources. + * + * - Support for pull DMA. + * + * - Support for interrupt regions and user-space interrupt delivery. + * + * - Support for getting BAR mappings and reserving regions of BAR + * address space. + */ +#ifndef _GXIO_TRIO_H_ +#define _GXIO_TRIO_H_ + +#include <linux/types.h> + +#include "common.h" +#include "dma_queue.h" + +#include <arch/trio_constants.h> +#include <arch/trio.h> +#include <arch/trio_pcie_intfc.h> +#include <arch/trio_pcie_rc.h> +#include <arch/trio_shm.h> +#include <hv/drv_trio_intf.h> +#include <hv/iorpc.h> + +/* A context object used to manage TRIO hardware resources. */ +typedef struct { + + /* File descriptor for calling up to Linux (and thus the HV). */ + int fd; + + /* The VA at which the MAC MMIO registers are mapped. */ + char *mmio_base_mac; + + /* The VA at which the PIO config space are mapped for each PCIe MAC. + Gx36 has max 3 PCIe MACs per TRIO shim. */ + char *mmio_base_pio_cfg[TILEGX_TRIO_PCIES]; + +#ifdef USE_SHARED_PCIE_CONFIG_REGION + /* Index of the shared PIO region for PCI config access. */ + int pio_cfg_index; +#else + /* Index of the PIO region for PCI config access per MAC. */ + int pio_cfg_index[TILEGX_TRIO_PCIES]; +#endif + + /* The VA at which the push DMA MMIO registers are mapped. */ + char *mmio_push_dma[TRIO_NUM_PUSH_DMA_RINGS]; + + /* The VA at which the pull DMA MMIO registers are mapped. */ + char *mmio_pull_dma[TRIO_NUM_PUSH_DMA_RINGS]; + + /* Application space ID. */ + unsigned int asid; + +} gxio_trio_context_t; + +/* Command descriptor for push or pull DMA. */ +typedef TRIO_DMA_DESC_t gxio_trio_dma_desc_t; + +/* A convenient, thread-safe interface to an eDMA ring. */ +typedef struct { + + /* State object for tracking head and tail pointers. */ + __gxio_dma_queue_t dma_queue; + + /* The ring entries. */ + gxio_trio_dma_desc_t *dma_descs; + + /* The number of entries minus one. */ + unsigned long mask_num_entries; + + /* The log2() of the number of entries. */ + unsigned int log2_num_entries; + +} gxio_trio_dma_queue_t; + +/* Initialize a TRIO context. + * + * This function allocates a TRIO "service domain" and maps the MMIO + * registers into the the caller's VA space. + * + * @param trio_index Which TRIO shim; Gx36 must pass 0. + * @param context Context object to be initialized. + */ +extern int gxio_trio_init(gxio_trio_context_t *context, + unsigned int trio_index); + +/* This indicates that an ASID hasn't been allocated. */ +#define GXIO_ASID_NULL -1 + +/* Ordering modes for map memory regions and scatter queue regions. */ +typedef enum gxio_trio_order_mode_e { + /* Writes are not ordered. Reads always wait for previous writes. */ + GXIO_TRIO_ORDER_MODE_UNORDERED = + TRIO_MAP_MEM_SETUP__ORDER_MODE_VAL_UNORDERED, + /* Both writes and reads wait for previous transactions to complete. */ + GXIO_TRIO_ORDER_MODE_STRICT = + TRIO_MAP_MEM_SETUP__ORDER_MODE_VAL_STRICT, + /* Writes are ordered unless the incoming packet has the + relaxed-ordering attributes set. */ + GXIO_TRIO_ORDER_MODE_OBEY_PACKET = + TRIO_MAP_MEM_SETUP__ORDER_MODE_VAL_REL_ORD +} gxio_trio_order_mode_t; + +/* Initialize a memory mapping region. + * + * @param context An initialized TRIO context. + * @param map A Memory map region allocated by gxio_trio_alloc_memory_map(). + * @param target_mem VA of backing memory, should be registered via + * gxio_trio_register_page() and aligned to 4kB. + * @param target_size Length of the memory mapping, must be a multiple + * of 4kB. + * @param asid ASID to be used for Tile-side address translation. + * @param mac MAC number. + * @param bus_address Bus address at which the mapping starts. + * @param order_mode Memory ordering mode for this mapping. + * @return Zero on success, else ::GXIO_TRIO_ERR_BAD_MEMORY_MAP, + * GXIO_TRIO_ERR_BAD_ASID, or ::GXIO_TRIO_ERR_BAD_BUS_RANGE. + */ +extern int gxio_trio_init_memory_map(gxio_trio_context_t *context, + unsigned int map, void *target_mem, + size_t target_size, unsigned int asid, + unsigned int mac, uint64_t bus_address, + gxio_trio_order_mode_t order_mode); + +/* Flags that can be passed to resource allocation functions. */ +enum gxio_trio_alloc_flags_e { + GXIO_TRIO_ALLOC_FIXED = HV_TRIO_ALLOC_FIXED, +}; + +/* Flags that can be passed to memory registration functions. */ +enum gxio_trio_mem_flags_e { + /* Do not fill L3 when writing, and invalidate lines upon egress. */ + GXIO_TRIO_MEM_FLAG_NT_HINT = IORPC_MEM_BUFFER_FLAG_NT_HINT, + + /* L3 cache fills should only populate IO cache ways. */ + GXIO_TRIO_MEM_FLAG_IO_PIN = IORPC_MEM_BUFFER_FLAG_IO_PIN, +}; + +/* Flag indicating a request generator uses a special traffic + class. */ +#define GXIO_TRIO_FLAG_TRAFFIC_CLASS(N) HV_TRIO_FLAG_TC(N) + +/* Flag indicating a request generator uses a virtual function + number. */ +#define GXIO_TRIO_FLAG_VFUNC(N) HV_TRIO_FLAG_VFUNC(N) + +/***************************************************************** + * Memory Registration * + ******************************************************************/ + +/* Allocate Application Space Identifiers (ASIDs). Each ASID can + * register up to 16 page translations. ASIDs are used by memory map + * regions, scatter queues, and DMA queues to translate application + * VAs into memory system PAs. + * + * @param context An initialized TRIO context. + * @param count Number of ASIDs required. + * @param first Index of first ASID if ::GXIO_TRIO_ALLOC_FIXED flag + * is set, otherwise ignored. + * @param flags Flag bits, including bits from ::gxio_trio_alloc_flags_e. + * @return Index of first ASID, or ::GXIO_TRIO_ERR_NO_ASID if allocation + * failed. + */ +extern int gxio_trio_alloc_asids(gxio_trio_context_t *context, + unsigned int count, unsigned int first, + unsigned int flags); + +#endif /* ! _GXIO_TRIO_H_ */ diff --git a/arch/tile/include/gxio/usb_host.h b/arch/tile/include/gxio/usb_host.h new file mode 100644 index 0000000..a60a126 --- /dev/null +++ b/arch/tile/include/gxio/usb_host.h @@ -0,0 +1,87 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ +#ifndef _GXIO_USB_H_ +#define _GXIO_USB_H_ + +#include "common.h" + +#include <hv/drv_usb_host_intf.h> +#include <hv/iorpc.h> + +/* + * + * An API for manipulating general-purpose I/O pins. + */ + +/* + * + * The USB shim allows access to the processor's Universal Serial Bus + * connections. + */ + +/* A context object used to manage USB hardware resources. */ +typedef struct { + + /* File descriptor for calling up to the hypervisor. */ + int fd; + + /* The VA at which our MMIO registers are mapped. */ + char *mmio_base; +} gxio_usb_host_context_t; + +/* Initialize a USB context. + * + * A properly initialized context must be obtained before any of the other + * gxio_usb_host routines may be used. + * + * @param context Pointer to a gxio_usb_host_context_t, which will be + * initialized by this routine, if it succeeds. + * @param usb_index Index of the USB shim to use. + * @param is_ehci Nonzero to use the EHCI interface; zero to use the OHCI + * intereface. + * @return Zero if the context was successfully initialized, else a + * GXIO_ERR_xxx error code. + */ +extern int gxio_usb_host_init(gxio_usb_host_context_t * context, int usb_index, + int is_ehci); + +/* Destroy a USB context. + * + * Once destroyed, a context may not be used with any gxio_usb_host routines + * other than gxio_usb_host_init(). After this routine returns, no further + * interrupts or signals requested on this context will be delivered. The + * state and configuration of the pins which had been attached to this + * context are unchanged by this operation. + * + * @param context Pointer to a gxio_usb_host_context_t. + * @return Zero if the context was successfully destroyed, else a + * GXIO_ERR_xxx error code. + */ +extern int gxio_usb_host_destroy(gxio_usb_host_context_t * context); + +/* Retrieve the address of the shim's MMIO registers. + * + * @param context Pointer to a properly initialized gxio_usb_host_context_t. + * @return The address of the shim's MMIO registers. + */ +extern void *gxio_usb_host_get_reg_start(gxio_usb_host_context_t * context); + +/* Retrieve the length of the shim's MMIO registers. + * + * @param context Pointer to a properly initialized gxio_usb_host_context_t. + * @return The length of the shim's MMIO registers. + */ +extern size_t gxio_usb_host_get_reg_len(gxio_usb_host_context_t * context); + +#endif /* _GXIO_USB_H_ */ diff --git a/arch/tile/include/hv/drv_mpipe_intf.h b/arch/tile/include/hv/drv_mpipe_intf.h new file mode 100644 index 0000000..6cdae3b --- /dev/null +++ b/arch/tile/include/hv/drv_mpipe_intf.h @@ -0,0 +1,602 @@ +/* + * Copyright 2011 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * Interface definitions for the mpipe driver. + */ + +#ifndef _SYS_HV_DRV_MPIPE_INTF_H +#define _SYS_HV_DRV_MPIPE_INTF_H + +#include <arch/mpipe.h> +#include <arch/mpipe_constants.h> + + +/** Number of buffer stacks (32). */ +#define HV_MPIPE_NUM_BUFFER_STACKS \ + (MPIPE_MMIO_INIT_DAT_GX36_1__BUFFER_STACK_MASK_WIDTH) + +/** Number of NotifRings (256). */ +#define HV_MPIPE_NUM_NOTIF_RINGS (MPIPE_NUM_NOTIF_RINGS) + +/** Number of NotifGroups (32). */ +#define HV_MPIPE_NUM_NOTIF_GROUPS (MPIPE_NUM_NOTIF_GROUPS) + +/** Number of buckets (4160). */ +#define HV_MPIPE_NUM_BUCKETS (MPIPE_NUM_BUCKETS) + +/** Number of "lo" buckets (4096). */ +#define HV_MPIPE_NUM_LO_BUCKETS 4096 + +/** Number of "hi" buckets (64). */ +#define HV_MPIPE_NUM_HI_BUCKETS \ + (HV_MPIPE_NUM_BUCKETS - HV_MPIPE_NUM_LO_BUCKETS) + +/** Number of edma rings (24). */ +#define HV_MPIPE_NUM_EDMA_RINGS \ + (MPIPE_MMIO_INIT_DAT_GX36_1__EDMA_POST_MASK_WIDTH) + + + + +/** A flag bit indicating a fixed resource allocation. */ +#define HV_MPIPE_ALLOC_FIXED 0x01 + +/** Offset for the config register MMIO region. */ +#define HV_MPIPE_CONFIG_MMIO_OFFSET \ + (MPIPE_MMIO_ADDR__REGION_VAL_CFG << MPIPE_MMIO_ADDR__REGION_SHIFT) + +/** Size of the config register MMIO region. */ +#define HV_MPIPE_CONFIG_MMIO_SIZE (64 * 1024) + +/** Offset for the config register MMIO region. */ +#define HV_MPIPE_FAST_MMIO_OFFSET \ + (MPIPE_MMIO_ADDR__REGION_VAL_IDMA << MPIPE_MMIO_ADDR__REGION_SHIFT) + +/** Size of the fast register MMIO region (IDMA, EDMA, buffer stack). */ +#define HV_MPIPE_FAST_MMIO_SIZE \ + ((MPIPE_MMIO_ADDR__REGION_VAL_BSM + 1 - MPIPE_MMIO_ADDR__REGION_VAL_IDMA) \ + << MPIPE_MMIO_ADDR__REGION_SHIFT) + + +/* + * Each type of resource allocation comes in quantized chunks, where + * XXX_BITS is the number of chunks, and XXX_RES_PER_BIT is the number + * of resources in each chunk. + */ + +/** Number of buffer stack chunks available (32). */ +#define HV_MPIPE_ALLOC_BUFFER_STACKS_BITS \ + MPIPE_MMIO_INIT_DAT_GX36_1__BUFFER_STACK_MASK_WIDTH + +/** Granularity of buffer stack allocation (1). */ +#define HV_MPIPE_ALLOC_BUFFER_STACKS_RES_PER_BIT \ + (HV_MPIPE_NUM_BUFFER_STACKS / HV_MPIPE_ALLOC_BUFFER_STACKS_BITS) + +/** Number of NotifRing chunks available (32). */ +#define HV_MPIPE_ALLOC_NOTIF_RINGS_BITS \ + MPIPE_MMIO_INIT_DAT_GX36_0__NOTIF_RING_MASK_WIDTH + +/** Granularity of NotifRing allocation (8). */ +#define HV_MPIPE_ALLOC_NOTIF_RINGS_RES_PER_BIT \ + (HV_MPIPE_NUM_NOTIF_RINGS / HV_MPIPE_ALLOC_NOTIF_RINGS_BITS) + +/** Number of NotifGroup chunks available (32). */ +#define HV_MPIPE_ALLOC_NOTIF_GROUPS_BITS \ + HV_MPIPE_NUM_NOTIF_GROUPS + +/** Granularity of NotifGroup allocation (1). */ +#define HV_MPIPE_ALLOC_NOTIF_GROUPS_RES_PER_BIT \ + (HV_MPIPE_NUM_NOTIF_GROUPS / HV_MPIPE_ALLOC_NOTIF_GROUPS_BITS) + +/** Number of lo bucket chunks available (16). */ +#define HV_MPIPE_ALLOC_LO_BUCKETS_BITS \ + MPIPE_MMIO_INIT_DAT_GX36_0__BUCKET_RELEASE_MASK_LO_WIDTH + +/** Granularity of lo bucket allocation (256). */ +#define HV_MPIPE_ALLOC_LO_BUCKETS_RES_PER_BIT \ + (HV_MPIPE_NUM_LO_BUCKETS / HV_MPIPE_ALLOC_LO_BUCKETS_BITS) + +/** Number of hi bucket chunks available (16). */ +#define HV_MPIPE_ALLOC_HI_BUCKETS_BITS \ + MPIPE_MMIO_INIT_DAT_GX36_0__BUCKET_RELEASE_MASK_HI_WIDTH + +/** Granularity of hi bucket allocation (4). */ +#define HV_MPIPE_ALLOC_HI_BUCKETS_RES_PER_BIT \ + (HV_MPIPE_NUM_HI_BUCKETS / HV_MPIPE_ALLOC_HI_BUCKETS_BITS) + +/** Number of eDMA ring chunks available (24). */ +#define HV_MPIPE_ALLOC_EDMA_RINGS_BITS \ + MPIPE_MMIO_INIT_DAT_GX36_1__EDMA_POST_MASK_WIDTH + +/** Granularity of eDMA ring allocation (1). */ +#define HV_MPIPE_ALLOC_EDMA_RINGS_RES_PER_BIT \ + (HV_MPIPE_NUM_EDMA_RINGS / HV_MPIPE_ALLOC_EDMA_RINGS_BITS) + + + + +/** Bit vector encoding which NotifRings are in a NotifGroup. */ +typedef struct +{ + /** The actual bits. */ + uint64_t ring_mask[4]; + +} gxio_mpipe_notif_group_bits_t; + + +/** Another name for MPIPE_LBL_INIT_DAT_BSTS_TBL_t. */ +typedef MPIPE_LBL_INIT_DAT_BSTS_TBL_t gxio_mpipe_bucket_info_t; + + + +/** Eight buffer stack ids. */ +typedef struct +{ + /** The stacks. */ + uint8_t stacks[8]; + +} gxio_mpipe_rules_stacks_t; + + +/** A destination mac address. */ +typedef struct +{ + /** The octets. */ + uint8_t octets[6]; + +} gxio_mpipe_rules_dmac_t; + + +/** A vlan. */ +typedef uint16_t gxio_mpipe_rules_vlan_t; + + + +/** Maximum number of characters in a link name. */ +#define GXIO_MPIPE_LINK_NAME_LEN 32 + + +/** Structure holding a link name. Only needed, and only typedef'ed, + * because the IORPC stub generator only handles types which are single + * words coming before the parameter name. */ +typedef struct +{ + /** The name itself. */ + char name[GXIO_MPIPE_LINK_NAME_LEN]; +} +_gxio_mpipe_link_name_t; + +/** Maximum number of characters in a symbol name. */ +#define GXIO_MPIPE_SYMBOL_NAME_LEN 128 + + +/** Structure holding a symbol name. Only needed, and only typedef'ed, + * because the IORPC stub generator only handles types which are single + * words coming before the parameter name. */ +typedef struct +{ + /** The name itself. */ + char name[GXIO_MPIPE_SYMBOL_NAME_LEN]; +} +_gxio_mpipe_symbol_name_t; + + +/** Structure holding a MAC address. */ +typedef struct +{ + /** The address. */ + uint8_t mac[6]; +} +_gxio_mpipe_link_mac_t; + + + +/** Request shared data permission -- that is, the ability to send and + * receive packets -- on the specified link. Other processes may also + * request shared data permission on the same link. + * + * No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA, + * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed. + */ +#define GXIO_MPIPE_LINK_DATA 0x00000001UL + +/** Do not request data permission on the specified link. + * + * No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA, + * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed. + */ +#define GXIO_MPIPE_LINK_NO_DATA 0x00000002UL + +/** Request exclusive data permission -- that is, the ability to send and + * receive packets -- on the specified link. No other processes may + * request data permission on this link, and if any process already has + * data permission on it, this open will fail. + * + * No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA, + * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed. + */ +#define GXIO_MPIPE_LINK_EXCL_DATA 0x00000004UL + +/** Request shared stats permission -- that is, the ability to read and write + * registers which contain link statistics, and to get link attributes -- + * on the specified link. Other processes may also request shared stats + * permission on the same link. + * + * No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS, + * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed. + */ +#define GXIO_MPIPE_LINK_STATS 0x00000008UL + +/** Do not request stats permission on the specified link. + * + * No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS, + * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed. + */ +#define GXIO_MPIPE_LINK_NO_STATS 0x00000010UL + +/** Request exclusive stats permission -- that is, the ability to read and + * write registers which contain link statistics, and to get link + * attributes -- on the specified link. No other processes may request + * stats permission on this link, and if any process already + * has stats permission on it, this open will fail. + * + * Requesting exclusive stats permission is normally a very bad idea, since + * it prevents programs like mpipe-stat from providing information on this + * link. Applications should only do this if they use MAC statistics + * registers, and cannot tolerate any of the clear-on-read registers being + * reset by other statistics programs. + * + * No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS, + * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed. + */ +#define GXIO_MPIPE_LINK_EXCL_STATS 0x00000020UL + +/** Request shared control permission -- that is, the ability to modify link + * attributes, and read and write MAC and MDIO registers -- on the + * specified link. Other processes may also request shared control + * permission on the same link. + * + * No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL, + * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed. + */ +#define GXIO_MPIPE_LINK_CTL 0x00000040UL + +/** Do not request control permission on the specified link. + * + * No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL, + * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed. + */ +#define GXIO_MPIPE_LINK_NO_CTL 0x00000080UL + +/** Request exclusive control permission -- that is, the ability to modify + * link attributes, and read and write MAC and MDIO registers -- on the + * specified link. No other processes may request control permission on + * this link, and if any process already has control permission on it, + * this open will fail. + * + * Requesting exclusive control permission is not always a good idea, since + * it prevents programs like mpipe-link from configuring the link. + * + * No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL, + * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed. + */ +#define GXIO_MPIPE_LINK_EXCL_CTL 0x00000100UL + +/** Set the desired state of the link to up, allowing any speeds which are + * supported by the link hardware, as part of this open operation; do not + * change the desired state of the link when it is closed or the process + * exits. No more than one of ::GXIO_MPIPE_LINK_AUTO_UP, + * ::GXIO_MPIPE_LINK_AUTO_UPDOWN, ::GXIO_MPIPE_LINK_AUTO_DOWN, or + * ::GXIO_MPIPE_LINK_AUTO_NONE may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. + */ +#define GXIO_MPIPE_LINK_AUTO_UP 0x00000200UL + +/** Set the desired state of the link to up, allowing any speeds which are + * supported by the link hardware, as part of this open operation; when the + * link is closed or this process exits, if no other process has the link + * open, set the desired state of the link to down. No more than one of + * ::GXIO_MPIPE_LINK_AUTO_UP, ::GXIO_MPIPE_LINK_AUTO_UPDOWN, + * ::GXIO_MPIPE_LINK_AUTO_DOWN, or ::GXIO_MPIPE_LINK_AUTO_NONE may be + * specifed in a gxio_mpipe_link_open() call. If none are specified, + * ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. + */ +#define GXIO_MPIPE_LINK_AUTO_UPDOWN 0x00000400UL + +/** Do not change the desired state of the link as part of the open + * operation; when the link is closed or this process exits, if no other + * process has the link open, set the desired state of the link to down. + * No more than one of ::GXIO_MPIPE_LINK_AUTO_UP, + * ::GXIO_MPIPE_LINK_AUTO_UPDOWN, ::GXIO_MPIPE_LINK_AUTO_DOWN, or + * ::GXIO_MPIPE_LINK_AUTO_NONE may be specifed in a gxio_mpipe_link_open() + * call. If none are specified, ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. + */ +#define GXIO_MPIPE_LINK_AUTO_DOWN 0x00000800UL + +/** Do not change the desired state of the link as part of the open + * operation; do not change the desired state of the link when it is + * closed or the process exits. No more than one of + * ::GXIO_MPIPE_LINK_AUTO_UP, ::GXIO_MPIPE_LINK_AUTO_UPDOWN, + * ::GXIO_MPIPE_LINK_AUTO_DOWN, or ::GXIO_MPIPE_LINK_AUTO_NONE may be + * specifed in a gxio_mpipe_link_open() call. If none are specified, + * ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed. + */ +#define GXIO_MPIPE_LINK_AUTO_NONE 0x00001000UL + +/** Request that this open call not complete until the network link is up. + * The process will wait as long as necessary for this to happen; + * applications which wish to abandon waiting for the link after a + * specific time period should not specify this flag when opening a link, + * but should instead call gxio_mpipe_link_wait() afterward. The link + * must be opened with stats permission. Note that this flag by itself + * does not change the desired link state; if other open flags or previous + * link state changes have not requested a desired state of up, the open + * call will never complete. This flag is not available to kernel + * clients. + */ +#define GXIO_MPIPE_LINK_WAIT 0x00002000UL + + +/* + * Note: link attributes must fit in 24 bits, since we use the top 8 bits + * of the IORPC offset word for the channel number. + */ + +/** Determine whether jumbo frames may be received. If this attribute's + * value value is nonzero, the MAC will accept frames of up to 10240 bytes. + * If the value is zero, the MAC will only accept frames of up to 1544 + * bytes. The default value is zero. */ +#define GXIO_MPIPE_LINK_RECEIVE_JUMBO 0x010000 + +/** Determine whether to send pause frames on this link if the mPIPE packet + * FIFO is nearly full. If the value is zero, pause frames are not sent. + * If the value is nonzero, it is the delay value which will be sent in any + * pause frames which are output, in units of 512 bit times. + * + * Bear in mind that in almost all circumstances, the mPIPE packet FIFO + * will never fill up, since mPIPE will empty it as fast as or faster than + * the incoming data rate, by either delivering or dropping packets. The + * only situation in which this is not true is if the memory and cache + * subsystem is extremely heavily loaded, and mPIPE cannot perform DMA of + * packet data to memory in a timely fashion. In particular, pause frames + * will <em>not</em> be sent if packets cannot be delivered because + * NotifRings are full, buckets are full, or buffers are not available in + * a buffer stack. */ +#define GXIO_MPIPE_LINK_SEND_PAUSE 0x020000 + +/** Determine whether to suspend output on the receipt of pause frames. + * If the value is nonzero, mPIPE shim will suspend output on the link's + * channel when a pause frame is received. If the value is zero, pause + * frames will be ignored. The default value is zero. */ +#define GXIO_MPIPE_LINK_RECEIVE_PAUSE 0x030000 + +/** Interface MAC address. The value is a 6-byte MAC address, in the least + * significant 48 bits of the value; in other words, an address which would + * be printed as '12:34:56:78:90:AB' in IEEE 802 canonical format would + * be returned as 0x12345678ab. + * + * Depending upon the overall system design, a MAC address may or may not + * be available for each interface. Note that the interface's MAC address + * does not limit the packets received on its channel, although the + * classifier's rules could be configured to do that. Similarly, the MAC + * address is not used when transmitting packets, although applications + * could certainly decide to use the assigned address as a source MAC + * address when doing so. This attribute may only be retrieved with + * gxio_mpipe_link_get_attr(); it may not be modified. + */ +#define GXIO_MPIPE_LINK_MAC 0x040000 + +/** Determine whether to discard egress packets on link down. If this value + * is nonzero, packets sent on this link while the link is down will be + * discarded. If this value is zero, no packets will be sent on this link + * while it is down. The default value is one. */ +#define GXIO_MPIPE_LINK_DISCARD_IF_DOWN 0x050000 + +/** Possible link state. The value is a combination of link state flags, + * ORed together, that indicate link modes which are actually supported by + * the hardware. This attribute may only be retrieved with + * gxio_mpipe_link_get_attr(); it may not be modified. */ +#define GXIO_MPIPE_LINK_POSSIBLE_STATE 0x060000 + +/** Current link state. The value is a combination of link state flags, + * ORed together, that indicate the current state of the hardware. If the + * link is down, the value ANDed with ::GXIO_MPIPE_LINK_SPEED will be zero; + * if the link is up, the value ANDed with ::GXIO_MPIPE_LINK_SPEED will + * result in exactly one of the speed values, indicating the current speed. + * This attribute may only be retrieved with gxio_mpipe_link_get_attr(); it + * may not be modified. */ +#define GXIO_MPIPE_LINK_CURRENT_STATE 0x070000 + +/** Desired link state. The value is a conbination of flags, which specify + * the desired state for the link. With gxio_mpipe_link_set_attr(), this + * will, in the background, attempt to bring up the link using whichever of + * the requested flags are reasonable, or take down the link if the flags + * are zero. The actual link up or down operation may happen after this + * call completes. If the link state changes in the future, the system + * will continue to try to get back to the desired link state; for + * instance, if the link is brought up successfully, and then the network + * cable is disconnected, the link will go down. However, the desired + * state of the link is still up, so if the cable is reconnected, the link + * will be brought up again. + * + * With gxio_mpipe_link_set_attr(), this will indicate the desired state + * for the link, as set with a previous gxio_mpipe_link_set_attr() call, + * or implicitly by a gxio_mpipe_link_open() or link close operation. + * This may not reflect the current state of the link; to get that, use + * ::GXIO_MPIPE_LINK_CURRENT_STATE. + */ +#define GXIO_MPIPE_LINK_DESIRED_STATE 0x080000 + + + +/** Link can run, should run, or is running at 10 Mbps. */ +#define GXIO_MPIPE_LINK_10M 0x0000000000000001UL + +/** Link can run, should run, or is running at 100 Mbps. */ +#define GXIO_MPIPE_LINK_100M 0x0000000000000002UL + +/** Link can run, should run, or is running at 1 Gbps. */ +#define GXIO_MPIPE_LINK_1G 0x0000000000000004UL + +/** Link can run, should run, or is running at 10 Gbps. */ +#define GXIO_MPIPE_LINK_10G 0x0000000000000008UL + +/** Link can run, should run, or is running at 20 Gbps. */ +#define GXIO_MPIPE_LINK_20G 0x0000000000000010UL + +/** Link can run, should run, or is running at 25 Gbps. */ +#define GXIO_MPIPE_LINK_25G 0x0000000000000020UL + +/** Link can run, should run, or is running at 50 Gbps. */ +#define GXIO_MPIPE_LINK_50G 0x0000000000000040UL + +/** Link should run at the highest speed supported by the link and by + * the device connected to the link. Only usable as a value for + * the link's desired state; never returned as a value for the current + * or possible states. */ +#define GXIO_MPIPE_LINK_ANYSPEED 0x0000000000000800UL + +/** All legal link speeds. This value is provided for use in extracting + * the speed-related subset of the link state flags; it is not intended + * to be set directly as a value for one of the GXIO_MPIPE_LINK_xxx_STATE + * attributes. A link is up or is requested to be up if its current or + * desired state, respectively, ANDED with this value, is nonzero. */ +#define GXIO_MPIPE_LINK_SPEED_MASK 0x0000000000000FFFUL + +/** Link can run, should run, or is running in MAC loopback mode. This + * loops transmitted packets back to the receiver, inside the Tile + * Processor. */ +#define GXIO_MPIPE_LINK_LOOP_MAC 0x0000000000001000UL + +/** Link can run, should run, or is running in PHY loopback mode. This + * loops transmitted packets back to the receiver, inside the external + * PHY chip. */ +#define GXIO_MPIPE_LINK_LOOP_PHY 0x0000000000002000UL + +/** Link can run, should run, or is running in external loopback mode. + * This requires that an external loopback plug be installed on the + * Ethernet port. Note that only some links require that this be + * configured via the gxio_mpipe_link routines; other links can do + * external loopack with the plug and no special configuration. */ +#define GXIO_MPIPE_LINK_LOOP_EXT 0x0000000000004000UL + +/** All legal loopback types. */ +#define GXIO_MPIPE_LINK_LOOP_MASK 0x000000000000F000UL + +/** Link can run, should run, or is running in full-duplex mode. + * If neither ::GXIO_MPIPE_LINK_FDX nor ::GXIO_MPIPE_LINK_HDX are + * specified in a set of desired state flags, both are assumed. */ +#define GXIO_MPIPE_LINK_FDX 0x0000000000010000UL + +/** Link can run, should run, or is running in half-duplex mode. + * If neither ::GXIO_MPIPE_LINK_FDX nor ::GXIO_MPIPE_LINK_HDX are + * specified in a set of desired state flags, both are assumed. */ +#define GXIO_MPIPE_LINK_HDX 0x0000000000020000UL + + +/** An individual rule. */ +typedef struct +{ + /** The total size. */ + uint16_t size; + + /** The priority. */ + int16_t priority; + + /** The "headroom" in each buffer. */ + uint8_t headroom; + + /** The "tailroom" in each buffer. */ + uint8_t tailroom; + + /** The "capacity" of the largest buffer. */ + uint16_t capacity; + + /** The mask for converting a flow hash into a bucket. */ + uint16_t bucket_mask; + + /** The offset for converting a flow hash into a bucket. */ + uint16_t bucket_first; + + /** The buffer stack ids. */ + gxio_mpipe_rules_stacks_t stacks; + + /** The actual channels. */ + uint32_t channel_bits; + + /** The number of dmacs. */ + uint16_t num_dmacs; + + /** The number of vlans. */ + uint16_t num_vlans; + + /** The actual dmacs and vlans. */ + uint8_t dmacs_and_vlans[]; + +} gxio_mpipe_rules_rule_t; + + +/** A list of classifier rules. */ +typedef struct +{ + /** The offset to the end of the current rule. */ + uint16_t tail; + + /** The offset to the start of the current rule. */ + uint16_t head; + + /** The actual rules. */ + uint8_t rules[4096 - 4]; + +} gxio_mpipe_rules_list_t; + + + + +/** mPIPE statistics structure. These counters include all relevant + * events occurring on all links within the mPIPE shim. */ +typedef struct +{ + /** Number of ingress packets dropped for any reason. */ + uint64_t ingress_drops; + /** Number of ingress packets dropped because a buffer stack was empty. */ + uint64_t ingress_drops_no_buf; + /** Number of ingress packets dropped or truncated due to lack of space in + * the iPkt buffer. */ + uint64_t ingress_drops_ipkt; + /** Number of ingress packets dropped by the classifier or load balancer */ + uint64_t ingress_drops_cls_lb; + /** Total number of ingress packets. */ + uint64_t ingress_packets; + /** Total number of egress packets. */ + uint64_t egress_packets; + /** Total number of ingress bytes. */ + uint64_t ingress_bytes; + /** Total number of egress bytes. */ + uint64_t egress_bytes; +} +gxio_mpipe_stats_t; + + +#endif /* _SYS_HV_DRV_MPIPE_INTF_H */ diff --git a/arch/tile/include/hv/drv_trio_intf.h b/arch/tile/include/hv/drv_trio_intf.h new file mode 100644 index 0000000..ef9f3f5 --- /dev/null +++ b/arch/tile/include/hv/drv_trio_intf.h @@ -0,0 +1,195 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * Interface definitions for the trio driver. + */ + +#ifndef _SYS_HV_DRV_TRIO_INTF_H +#define _SYS_HV_DRV_TRIO_INTF_H + +#include <arch/trio.h> + +/** The vendor ID for all Tilera processors. */ +#define TILERA_VENDOR_ID 0x1a41 + +/** The device ID for the Gx36 processor. */ +#define TILERA_GX36_DEV_ID 0x0200 + +/** Device ID for our internal bridge when running as RC. */ +#define TILERA_GX36_RC_DEV_ID 0x2000 + +/** Maximum number of TRIO interfaces. */ +#define TILEGX_NUM_TRIO 2 + +/** Gx36 has max 3 PCIe MACs per TRIO interface. */ +#define TILEGX_TRIO_PCIES 3 + +/** Specify port properties for a PCIe MAC. */ +struct pcie_port_property +{ + /** If true, the link can be configured in PCIe root complex mode. */ + uint8_t allow_rc: 1; + + /** If true, the link can be configured in PCIe endpoint mode. */ + uint8_t allow_ep: 1; + + /** If true, the link can be configured in StreamIO mode. */ + uint8_t allow_sio: 1; + + /** If true, the link is allowed to support 1-lane operation. Software + * will not consider it an error if the link comes up as a x1 link. */ + uint8_t allow_x1: 1; + + /** If true, the link is allowed to support 2-lane operation. Software + * will not consider it an error if the link comes up as a x2 link. */ + uint8_t allow_x2: 1; + + /** If true, the link is allowed to support 4-lane operation. Software + * will not consider it an error if the link comes up as a x4 link. */ + uint8_t allow_x4: 1; + + /** If true, the link is allowed to support 8-lane operation. Software + * will not consider it an error if the link comes up as a x8 link. */ + uint8_t allow_x8: 1; + + /** Reserved. */ + uint8_t reserved: 1; + +}; + +/** Configurations can be issued to configure a char stream interrupt. */ +typedef enum pcie_stream_intr_config_sel_e +{ + /** Interrupt configuration for memory map regions. */ + MEM_MAP_SEL, + + /** Interrupt configuration for push DMAs. */ + PUSH_DMA_SEL, + + /** Interrupt configuration for pull DMAs. */ + PULL_DMA_SEL, +} +pcie_stream_intr_config_sel_t; + + +/** The mmap file offset (PA) of the TRIO config region. */ +#define HV_TRIO_CONFIG_OFFSET \ + ((unsigned long long)TRIO_MMIO_ADDRESS_SPACE__REGION_VAL_CFG << \ + TRIO_MMIO_ADDRESS_SPACE__REGION_SHIFT) + +/** The maximum size of the TRIO config region. */ +#define HV_TRIO_CONFIG_SIZE \ + (1ULL << TRIO_CFG_REGION_ADDR__REGION_SHIFT) + +/** Size of the config region mapped into client. We can't use + * TRIO_MMIO_ADDRESS_SPACE__OFFSET_WIDTH because it + * will require the kernel to allocate 4GB VA space + * from the VMALLOC region which has a total range + * of 4GB. + */ +#define HV_TRIO_CONFIG_IOREMAP_SIZE \ + ((uint64_t) 1 << TRIO_CFG_REGION_ADDR__PROT_SHIFT) + +/** The mmap file offset (PA) of a scatter queue region. */ +#define HV_TRIO_SQ_OFFSET(queue) \ + (((unsigned long long)TRIO_MMIO_ADDRESS_SPACE__REGION_VAL_MAP_SQ << \ + TRIO_MMIO_ADDRESS_SPACE__REGION_SHIFT) | \ + ((queue) << TRIO_MAP_SQ_REGION_ADDR__SQ_SEL_SHIFT)) + +/** The maximum size of a scatter queue region. */ +#define HV_TRIO_SQ_SIZE \ + (1ULL << TRIO_MAP_SQ_REGION_ADDR__SQ_SEL_SHIFT) + + +/** The "hardware MMIO region" of the first PIO region. */ +#define HV_TRIO_FIRST_PIO_REGION 8 + +/** The mmap file offset (PA) of a PIO region. */ +#define HV_TRIO_PIO_OFFSET(region) \ + (((unsigned long long)(region) + HV_TRIO_FIRST_PIO_REGION) \ + << TRIO_PIO_REGIONS_ADDR__REGION_SHIFT) + +/** The maximum size of a PIO region. */ +#define HV_TRIO_PIO_SIZE (1ULL << TRIO_PIO_REGIONS_ADDR__ADDR_WIDTH) + + +/** The mmap file offset (PA) of a push DMA region. */ +#define HV_TRIO_PUSH_DMA_OFFSET(ring) \ + (((unsigned long long)TRIO_MMIO_ADDRESS_SPACE__REGION_VAL_PUSH_DMA << \ + TRIO_MMIO_ADDRESS_SPACE__REGION_SHIFT) | \ + ((ring) << TRIO_PUSH_DMA_REGION_ADDR__RING_SEL_SHIFT)) + +/** The mmap file offset (PA) of a pull DMA region. */ +#define HV_TRIO_PULL_DMA_OFFSET(ring) \ + (((unsigned long long)TRIO_MMIO_ADDRESS_SPACE__REGION_VAL_PULL_DMA << \ + TRIO_MMIO_ADDRESS_SPACE__REGION_SHIFT) | \ + ((ring) << TRIO_PULL_DMA_REGION_ADDR__RING_SEL_SHIFT)) + +/** The maximum size of a DMA region. */ +#define HV_TRIO_DMA_REGION_SIZE \ + (1ULL << TRIO_PUSH_DMA_REGION_ADDR__RING_SEL_SHIFT) + + +/** The mmap file offset (PA) of a Mem-Map interrupt region. */ +#define HV_TRIO_MEM_MAP_INTR_OFFSET(map) \ + (((unsigned long long)TRIO_MMIO_ADDRESS_SPACE__REGION_VAL_MAP_MEM << \ + TRIO_MMIO_ADDRESS_SPACE__REGION_SHIFT) | \ + ((map) << TRIO_MAP_MEM_REGION_ADDR__MAP_SEL_SHIFT)) + +/** The maximum size of a Mem-Map interrupt region. */ +#define HV_TRIO_MEM_MAP_INTR_SIZE \ + (1ULL << TRIO_MAP_MEM_REGION_ADDR__MAP_SEL_SHIFT) + + +/** A flag bit indicating a fixed resource allocation. */ +#define HV_TRIO_ALLOC_FIXED 0x01 + +/** TRIO requires that all mappings have 4kB aligned start addresses. */ +#define HV_TRIO_PAGE_SHIFT 12 + +/** TRIO requires that all mappings have 4kB aligned start addresses. */ +#define HV_TRIO_PAGE_SIZE (1ull << HV_TRIO_PAGE_SHIFT) + + +/* Specify all PCIe port properties for a TRIO. */ +struct pcie_trio_ports_property +{ + struct pcie_port_property ports[TILEGX_TRIO_PCIES]; +}; + +/* Flags indicating traffic class. */ +#define HV_TRIO_FLAG_TC_SHIFT 4 +#define HV_TRIO_FLAG_TC_RMASK 0xf +#define HV_TRIO_FLAG_TC(N) \ + ((((N) & HV_TRIO_FLAG_TC_RMASK) + 1) << HV_TRIO_FLAG_TC_SHIFT) + +/* Flags indicating virtual functions. */ +#define HV_TRIO_FLAG_VFUNC_SHIFT 8 +#define HV_TRIO_FLAG_VFUNC_RMASK 0xff +#define HV_TRIO_FLAG_VFUNC(N) \ + ((((N) & HV_TRIO_FLAG_VFUNC_RMASK) + 1) << HV_TRIO_FLAG_VFUNC_SHIFT) + + +/* Flag indicating an ordered PIO region. */ +#define HV_TRIO_PIO_FLAG_ORDERED (1 << 16) + +/* Flags indicating special types of PIO regions. */ +#define HV_TRIO_PIO_FLAG_SPACE_SHIFT 17 +#define HV_TRIO_PIO_FLAG_SPACE_MASK (0x3 << HV_TRIO_PIO_FLAG_SPACE_SHIFT) +#define HV_TRIO_PIO_FLAG_CONFIG_SPACE (0x1 << HV_TRIO_PIO_FLAG_SPACE_SHIFT) +#define HV_TRIO_PIO_FLAG_IO_SPACE (0x2 << HV_TRIO_PIO_FLAG_SPACE_SHIFT) + + +#endif /* _SYS_HV_DRV_TRIO_INTF_H */ diff --git a/arch/tile/include/hv/drv_usb_host_intf.h b/arch/tile/include/hv/drv_usb_host_intf.h new file mode 100644 index 0000000..24ce774 --- /dev/null +++ b/arch/tile/include/hv/drv_usb_host_intf.h @@ -0,0 +1,39 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +/** + * Interface definitions for the USB host driver. + */ + +#ifndef _SYS_HV_DRV_USB_HOST_INTF_H +#define _SYS_HV_DRV_USB_HOST_INTF_H + +#include <arch/usb_host.h> + + +/** Offset for the EHCI register MMIO region. */ +#define HV_USB_HOST_MMIO_OFFSET_EHCI ((uint64_t) USB_HOST_HCCAPBASE_REG) + +/** Offset for the OHCI register MMIO region. */ +#define HV_USB_HOST_MMIO_OFFSET_OHCI ((uint64_t) USB_HOST_OHCD_HC_REVISION_REG) + +/** Size of the register MMIO region. This turns out to be the same for + * both EHCI and OHCI. */ +#define HV_USB_HOST_MMIO_SIZE ((uint64_t) 0x1000) + +/** The number of service domains supported by the USB host shim. */ +#define HV_USB_HOST_NUM_SVC_DOM 1 + + +#endif /* _SYS_HV_DRV_USB_HOST_INTF_H */ diff --git a/arch/tile/include/hv/iorpc.h b/arch/tile/include/hv/iorpc.h new file mode 100644 index 0000000..89c72a5 --- /dev/null +++ b/arch/tile/include/hv/iorpc.h @@ -0,0 +1,714 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ +#ifndef _HV_IORPC_H_ +#define _HV_IORPC_H_ + +/** + * + * Error codes and struct definitions for the IO RPC library. + * + * The hypervisor's IO RPC component provides a convenient way for + * driver authors to proxy system calls between user space, linux, and + * the hypervisor driver. The core of the system is a set of Python + * files that take ".idl" files as input and generates the following + * source code: + * + * - _rpc_call() routines for use in userspace IO libraries. These + * routines take an argument list specified in the .idl file, pack the + * arguments in to a buffer, and read or write that buffer via the + * Linux iorpc driver. + * + * - dispatch_read() and dispatch_write() routines that hypervisor + * drivers can use to implement most of their dev_pread() and + * dev_pwrite() methods. These routines decode the incoming parameter + * blob, permission check and translate parameters where appropriate, + * and then invoke a callback routine for whichever RPC call has + * arrived. The driver simply implements the set of callback + * routines. + * + * The IO RPC system also includes the Linux 'iorpc' driver, which + * proxies calls between the userspace library and the hypervisor + * driver. The Linux driver is almost entirely device agnostic; it + * watches for special flags indicating cases where a memory buffer + * address might need to be translated, etc. As a result, driver + * writers can avoid many of the problem cases related to registering + * hardware resources like memory pages or interrupts. However, the + * drivers must be careful to obey the conventions documented below in + * order to work properly with the generic Linux iorpc driver. + * + * @section iorpc_domains Service Domains + * + * All iorpc-based drivers must support a notion of service domains. + * A service domain is basically an application context - state + * indicating resources that are allocated to that particular app + * which it may access and (perhaps) other applications may not + * access. Drivers can support any number of service domains they + * choose. In some cases the design is limited by a number of service + * domains supported by the IO hardware; in other cases the service + * domains are a purely software concept and the driver chooses a + * maximum number of domains based on how much state memory it is + * willing to preallocate. + * + * For example, the mPIPE driver only supports as many service domains + * as are supported by the mPIPE hardware. This limitation is + * required because the hardware implements its own MMIO protection + * scheme to allow large MMIO mappings while still protecting small + * register ranges within the page that should only be accessed by the + * hypervisor. + * + * In contrast, drivers with no hardware service domain limitations + * (for instance the TRIO shim) can implement an arbitrary number of + * service domains. In these cases, each service domain is limited to + * a carefully restricted set of legal MMIO addresses if necessary to + * keep one application from corrupting another application's state. + * + * @section iorpc_conventions System Call Conventions + * + * The driver's open routine is responsible for allocating a new + * service domain for each hv_dev_open() call. By convention, the + * return value from open() should be the service domain number on + * success, or GXIO_ERR_NO_SVC_DOM if no more service domains are + * available. + * + * The implementations of hv_dev_pread() and hv_dev_pwrite() are + * responsible for validating the devhdl value passed up by the + * client. Since the device handle returned by hv_dev_open() should + * embed the positive service domain number, drivers should make sure + * that DRV_HDL2BITS(devhdl) is a legal service domain. If the client + * passes an illegal service domain number, the routine should return + * GXIO_ERR_INVAL_SVC_DOM. Once the service domain number has been + * validated, the driver can copy to/from the client buffer and call + * the dispatch_read() or dispatch_write() methods created by the RPC + * generator. + * + * The hv_dev_close() implementation should reset all service domain + * state and put the service domain back on a free list for + * reallocation by a future application. In most cases, this will + * require executing a hardware reset or drain flow and denying any + * MMIO regions that were created for the service domain. + * + * @section iorpc_data Special Data Types + * + * The .idl file syntax allows the creation of syscalls with special + * parameters that require permission checks or translations as part + * of the system call path. Because of limitations in the code + * generator, APIs are generally limited to just one of these special + * parameters per system call, and they are sometimes required to be + * the first or last parameter to the call. Special parameters + * include: + * + * @subsection iorpc_mem_buffer MEM_BUFFER + * + * The MEM_BUFFER() datatype allows user space to "register" memory + * buffers with a device. Registering memory accomplishes two tasks: + * Linux keeps track of all buffers that might be modified by a + * hardware device, and the hardware device drivers bind registered + * buffers to particular hardware resources like ingress NotifRings. + * The MEM_BUFFER() idl syntax can take extra flags like ALIGN_64KB, + * ALIGN_SELF_SIZE, and FLAGS indicating that memory buffers must have + * certain alignment or that the user should be able to pass a "memory + * flags" word specifying attributes like nt_hint or IO cache pinning. + * The parser will accept multiple MEM_BUFFER() flags. + * + * Implementations must obey the following conventions when + * registering memory buffers via the iorpc flow. These rules are a + * result of the Linux driver implementation, which needs to keep + * track of how many times a particular page has been registered with + * the hardware so that it can release the page when all those + * registrations are cleared. + * + * - Memory registrations that refer to a resource which has already + * been bound must return GXIO_ERR_ALREADY_INIT. Thus, it is an + * error to register memory twice without resetting (i.e. closing) the + * resource in between. This convention keeps the Linux driver from + * having to track which particular devices a page is bound to. + * + * - At present, a memory registration is only cleared when the + * service domain is reset. In this case, the Linux driver simply + * closes the HV device file handle and then decrements the reference + * counts of all pages that were previously registered with the + * device. + * + * - In the future, we may add a mechanism for unregistering memory. + * One possible implementation would require that the user specify + * which buffer is currently registered. The HV would then verify + * that that page was actually the one currently mapped and return + * success or failure to Linux, which would then only decrement the + * page reference count if the addresses were mapped. Another scheme + * might allow Linux to pass a token to the HV to be returned when the + * resource is unmapped. + * + * @subsection iorpc_interrupt INTERRUPT + * + * The INTERRUPT .idl datatype allows the client to bind hardware + * interrupts to a particular combination of IPI parameters - CPU, IPI + * PL, and event bit number. This data is passed via a special + * datatype so that the Linux driver can validate the CPU and PL and + * the HV generic iorpc code can translate client CPUs to real CPUs. + * + * @subsection iorpc_pollfd_setup POLLFD_SETUP + * + * The POLLFD_SETUP .idl datatype allows the client to set up hardware + * interrupt bindings which are received by Linux but which are made + * visible to user processes as state transitions on a file descriptor; + * this allows user processes to use Linux primitives, such as poll(), to + * await particular hardware events. This data is passed via a special + * datatype so that the Linux driver may recognize the pollable file + * descriptor and translate it to a set of interrupt target information, + * and so that the HV generic iorpc code can translate client CPUs to real + * CPUs. + * + * @subsection iorpc_pollfd POLLFD + * + * The POLLFD .idl datatype allows manipulation of hardware interrupt + * bindings set up via the POLLFD_SETUP datatype; common operations are + * resetting the state of the requested interrupt events, and unbinding any + * bound interrupts. This data is passed via a special datatype so that + * the Linux driver may recognize the pollable file descriptor and + * translate it to an interrupt identifier previously supplied by the + * hypervisor as the result of an earlier pollfd_setup operation. + * + * @subsection iorpc_blob BLOB + * + * The BLOB .idl datatype allows the client to write an arbitrary + * length string of bytes up to the hypervisor driver. This can be + * useful for passing up large, arbitrarily structured data like + * classifier programs. The iorpc stack takes care of validating the + * buffer VA and CPA as the data passes up to the hypervisor. Unlike + * MEM_BUFFER(), the buffer is not registered - Linux does not bump + * page refcounts and the HV driver should not reuse the buffer once + * the system call is complete. + * + * @section iorpc_translation Translating User Space Calls + * + * The ::iorpc_offset structure describes the formatting of the offset + * that is passed to pread() or pwrite() as part of the generated RPC code. + * When the user calls up to Linux, the rpc code fills in all the fields of + * the offset, including a 16-bit opcode, a 16 bit format indicator, and 32 + * bits of user-specified "sub-offset". The opcode indicates which syscall + * is being requested. The format indicates whether there is a "prefix + * struct" at the start of the memory buffer passed to pwrite(), and if so + * what data is in that prefix struct. These prefix structs are used to + * implement special datatypes like MEM_BUFFER() and INTERRUPT - we arrange + * to put data that needs translation and permission checks at the start of + * the buffer so that the Linux driver and generic portions of the HV iorpc + * code can easily access the data. The 32 bits of user-specified + * "sub-offset" are most useful for pread() calls where the user needs to + * also pass in a few bits indicating which register to read, etc. + * + * The Linux iorpc driver watches for system calls that contain prefix + * structs so that it can translate parameters and bump reference + * counts as appropriate. It does not (currently) have any knowledge + * of the per-device opcodes - it doesn't care what operation you're + * doing to mPIPE, so long as it can do all the generic book-keeping. + * The hv/iorpc.h header file defines all of the generic encoding bits + * needed to translate iorpc calls without knowing which particular + * opcode is being issued. + * + * @section iorpc_globals Global iorpc Calls + * + * Implementing mmap() required adding some special iorpc syscalls + * that are only called by the Linux driver, never by userspace. + * These include get_mmio_base() and check_mmio_offset(). These + * routines are described in globals.idl and must be included in every + * iorpc driver. By providing these routines in every driver, Linux's + * mmap implementation can easily get the PTE bits it needs and + * validate the PA offset without needing to know the per-device + * opcodes to perform those tasks. + * + * @section iorpc_kernel Supporting gxio APIs in the Kernel + * + * The iorpc code generator also supports generation of kernel code + * implementing the gxio APIs. This capability is currently used by + * the mPIPE network driver, and will likely be used by the TRIO root + * complex and endpoint drivers and perhaps an in-kernel crypto + * driver. Each driver that wants to instantiate iorpc calls in the + * kernel needs to generate a kernel version of the generate rpc code + * and (probably) copy any related gxio source files into the kernel. + * The mPIPE driver provides a good example of this pattern. + */ + +#ifdef __KERNEL__ +#include <linux/stddef.h> +#else +#include <stddef.h> +#endif + +#if defined(__HV__) +#include <hv/hypervisor.h> +#elif defined(__KERNEL__) +#include "hypervisor.h" +#include <linux/types.h> +#else +#include <stdint.h> +#endif + + +/** Code indicating translation services required within the RPC path. + * These indicate whether there is a translatable struct at the start + * of the RPC buffer and what information that struct contains. + */ +enum iorpc_format_e +{ + /** No translation required, no prefix struct. */ + IORPC_FORMAT_NONE, + + /** No translation required, no prefix struct, no access to this + * operation from user space. */ + IORPC_FORMAT_NONE_NOUSER, + + /** Prefix struct contains user VA and size. */ + IORPC_FORMAT_USER_MEM, + + /** Prefix struct contains CPA, size, and homing bits. */ + IORPC_FORMAT_KERNEL_MEM, + + /** Prefix struct contains interrupt. */ + IORPC_FORMAT_KERNEL_INTERRUPT, + + /** Prefix struct contains user-level interrupt. */ + IORPC_FORMAT_USER_INTERRUPT, + + /** Prefix struct contains pollfd_setup (interrupt information). */ + IORPC_FORMAT_KERNEL_POLLFD_SETUP, + + /** Prefix struct contains user-level pollfd_setup (file descriptor). */ + IORPC_FORMAT_USER_POLLFD_SETUP, + + /** Prefix struct contains pollfd (interrupt cookie). */ + IORPC_FORMAT_KERNEL_POLLFD, + + /** Prefix struct contains user-level pollfd (file descriptor). */ + IORPC_FORMAT_USER_POLLFD, +}; + + +/** Generate an opcode given format and code. */ +#define IORPC_OPCODE(FORMAT, CODE) (((FORMAT) << 16) | (CODE)) + +/** The offset passed through the read() and write() system calls + combines an opcode with 32 bits of user-specified offset. */ +union iorpc_offset +{ +#ifndef __BIG_ENDIAN__ + uint64_t offset; /**< All bits. */ + + struct + { + uint16_t code; /**< RPC code. */ + uint16_t format; /**< iorpc_format_e */ + uint32_t sub_offset; /**< caller-specified offset. */ + }; + + uint32_t opcode; /**< Opcode combines code & format. */ +#else + uint64_t offset; /**< All bits. */ + + struct + { + uint32_t sub_offset; /**< caller-specified offset. */ + uint16_t format; /**< iorpc_format_e */ + uint16_t code; /**< RPC code. */ + }; + + struct + { + uint32_t padding; + uint32_t opcode; /**< Opcode combines code & format. */ + }; +#endif +}; + + +/** Homing and cache hinting bits that can be used by IO devices. */ +struct iorpc_mem_attr +{ + unsigned int lotar_x:4; /**< lotar X bits (or Gx page_mask). */ + unsigned int lotar_y:4; /**< lotar Y bits (or Gx page_offset). */ + unsigned int hfh:1; /**< Uses hash-for-home. */ + unsigned int nt_hint:1; /**< Non-temporal hint. */ + unsigned int io_pin:1; /**< Only fill 'IO' cache ways. */ +}; + +/** Set the nt_hint bit. */ +#define IORPC_MEM_BUFFER_FLAG_NT_HINT (1 << 0) + +/** Set the IO pin bit. */ +#define IORPC_MEM_BUFFER_FLAG_IO_PIN (1 << 1) + + +/** A structure used to describe memory registration. Different + protection levels describe memory differently, so this union + contains all the different possible descriptions. As a request + moves up the call chain, each layer translates from one + description format to the next. In particular, the Linux iorpc + driver translates user VAs into CPAs and homing parameters. */ +union iorpc_mem_buffer +{ + struct + { + uint64_t va; /**< User virtual address. */ + uint64_t size; /**< Buffer size. */ + unsigned int flags; /**< nt_hint, IO pin. */ + } + user; /**< Buffer as described by user apps. */ + + struct + { + unsigned long long cpa; /**< Client physical address. */ +#if defined(__KERNEL__) || defined(__HV__) + size_t size; /**< Buffer size. */ + HV_PTE pte; /**< PTE describing memory homing. */ +#else + uint64_t size; + uint64_t pte; +#endif + unsigned int flags; /**< nt_hint, IO pin. */ + } + kernel; /**< Buffer as described by kernel. */ + + struct + { + unsigned long long pa; /**< Physical address. */ + size_t size; /**< Buffer size. */ + struct iorpc_mem_attr attr; /**< Homing and locality hint bits. */ + } + hv; /**< Buffer parameters for HV driver. */ +}; + + +/** A structure used to describe interrupts. The format differs slightly + * for user and kernel interrupts. As with the mem_buffer_t, translation + * between the formats is done at each level. */ +union iorpc_interrupt +{ + struct + { + int cpu; /**< CPU. */ + int event; /**< evt_num */ + } + user; /**< Interrupt as described by user applications. */ + + struct + { + int x; /**< X coord. */ + int y; /**< Y coord. */ + int ipi; /**< int_num */ + int event; /**< evt_num */ + } + kernel; /**< Interrupt as described by the kernel. */ + +}; + + +/** A structure used to describe interrupts used with poll(). The format + * differs significantly for requests from user to kernel, and kernel to + * hypervisor. As with the mem_buffer_t, translation between the formats + * is done at each level. */ +union iorpc_pollfd_setup +{ + struct + { + int fd; /**< Pollable file descriptor. */ + } + user; /**< pollfd_setup as described by user applications. */ + + struct + { + int x; /**< X coord. */ + int y; /**< Y coord. */ + int ipi; /**< int_num */ + int event; /**< evt_num */ + } + kernel; /**< pollfd_setup as described by the kernel. */ + +}; + + +/** A structure used to describe previously set up interrupts used with + * poll(). The format differs significantly for requests from user to + * kernel, and kernel to hypervisor. As with the mem_buffer_t, translation + * between the formats is done at each level. */ +union iorpc_pollfd +{ + struct + { + int fd; /**< Pollable file descriptor. */ + } + user; /**< pollfd as described by user applications. */ + + struct + { + int cookie; /**< hv cookie returned by the pollfd_setup operation. */ + } + kernel; /**< pollfd as described by the kernel. */ + +}; + + +/** The various iorpc devices use error codes from -1100 to -1299. + * + * This range is distinct from netio (-700 to -799), the hypervisor + * (-800 to -899), tilepci (-900 to -999), ilib (-1000 to -1099), + * gxcr (-1300 to -1399) and gxpci (-1400 to -1499). + */ +enum gxio_err_e { + + /** Largest iorpc error number. */ + GXIO_ERR_MAX = -1101, + + + /********************************************************/ + /* Generic Error Codes */ + /********************************************************/ + + /** Bad RPC opcode - possible version incompatibility. */ + GXIO_ERR_OPCODE = -1101, + + /** Invalid parameter. */ + GXIO_ERR_INVAL = -1102, + + /** Memory buffer did not meet alignment requirements. */ + GXIO_ERR_ALIGNMENT = -1103, + + /** Memory buffers must be coherent and cacheable. */ + GXIO_ERR_COHERENCE = -1104, + + /** Resource already initialized. */ + GXIO_ERR_ALREADY_INIT = -1105, + + /** No service domains available. */ + GXIO_ERR_NO_SVC_DOM = -1106, + + /** Illegal service domain number. */ + GXIO_ERR_INVAL_SVC_DOM = -1107, + + /** Illegal MMIO address. */ + GXIO_ERR_MMIO_ADDRESS = -1108, + + /** Illegal interrupt binding. */ + GXIO_ERR_INTERRUPT = -1109, + + /** Unreasonable client memory. */ + GXIO_ERR_CLIENT_MEMORY = -1110, + + /** No more IOTLB entries. */ + GXIO_ERR_IOTLB_ENTRY = -1111, + + /** Invalid memory size. */ + GXIO_ERR_INVAL_MEMORY_SIZE = -1112, + + /** Unsupported operation. */ + GXIO_ERR_UNSUPPORTED_OP = -1113, + + /** Insufficient DMA credits. */ + GXIO_ERR_DMA_CREDITS = -1114, + + /** Operation timed out. */ + GXIO_ERR_TIMEOUT = -1115, + + /** No such device or object. */ + GXIO_ERR_NO_DEVICE = -1116, + + /** Device or resource busy. */ + GXIO_ERR_BUSY = -1117, + + /** I/O error. */ + GXIO_ERR_IO = -1118, + + /** Permissions error. */ + GXIO_ERR_PERM = -1119, + + + + /********************************************************/ + /* Test Device Error Codes */ + /********************************************************/ + + /** Illegal register number. */ + GXIO_TEST_ERR_REG_NUMBER = -1120, + + /** Illegal buffer slot. */ + GXIO_TEST_ERR_BUFFER_SLOT = -1121, + + + /********************************************************/ + /* MPIPE Error Codes */ + /********************************************************/ + + + /** Invalid buffer size. */ + GXIO_MPIPE_ERR_INVAL_BUFFER_SIZE = -1131, + + /** Cannot allocate buffer stack. */ + GXIO_MPIPE_ERR_NO_BUFFER_STACK = -1140, + + /** Invalid buffer stack number. */ + GXIO_MPIPE_ERR_BAD_BUFFER_STACK = -1141, + + /** Cannot allocate NotifRing. */ + GXIO_MPIPE_ERR_NO_NOTIF_RING = -1142, + + /** Invalid NotifRing number. */ + GXIO_MPIPE_ERR_BAD_NOTIF_RING = -1143, + + /** Cannot allocate NotifGroup. */ + GXIO_MPIPE_ERR_NO_NOTIF_GROUP = -1144, + + /** Invalid NotifGroup number. */ + GXIO_MPIPE_ERR_BAD_NOTIF_GROUP = -1145, + + /** Cannot allocate bucket. */ + GXIO_MPIPE_ERR_NO_BUCKET = -1146, + + /** Invalid bucket number. */ + GXIO_MPIPE_ERR_BAD_BUCKET = -1147, + + /** Cannot allocate eDMA ring. */ + GXIO_MPIPE_ERR_NO_EDMA_RING = -1148, + + /** Invalid eDMA ring number. */ + GXIO_MPIPE_ERR_BAD_EDMA_RING = -1149, + + /** Invalid channel number. */ + GXIO_MPIPE_ERR_BAD_CHANNEL = -1150, + + /** Bad configuration. */ + GXIO_MPIPE_ERR_BAD_CONFIG = -1151, + + /** Empty iqueue. */ + GXIO_MPIPE_ERR_IQUEUE_EMPTY = -1152, + + /** Empty rules. */ + GXIO_MPIPE_ERR_RULES_EMPTY = -1160, + + /** Full rules. */ + GXIO_MPIPE_ERR_RULES_FULL = -1161, + + /** Corrupt rules. */ + GXIO_MPIPE_ERR_RULES_CORRUPT = -1162, + + /** Invalid rules. */ + GXIO_MPIPE_ERR_RULES_INVALID = -1163, + + /** Classifier is too big. */ + GXIO_MPIPE_ERR_CLASSIFIER_TOO_BIG = -1170, + + /** Classifier is too complex. */ + GXIO_MPIPE_ERR_CLASSIFIER_TOO_COMPLEX = -1171, + + /** Classifier has bad header. */ + GXIO_MPIPE_ERR_CLASSIFIER_BAD_HEADER = -1172, + + /** Classifier has bad contents. */ + GXIO_MPIPE_ERR_CLASSIFIER_BAD_CONTENTS = -1173, + + /** Classifier encountered invalid symbol. */ + GXIO_MPIPE_ERR_CLASSIFIER_INVAL_SYMBOL = -1174, + + /** Classifier encountered invalid bounds. */ + GXIO_MPIPE_ERR_CLASSIFIER_INVAL_BOUNDS = -1175, + + /** Classifier encountered invalid relocation. */ + GXIO_MPIPE_ERR_CLASSIFIER_INVAL_RELOCATION = -1176, + + /** Classifier encountered undefined symbol. */ + GXIO_MPIPE_ERR_CLASSIFIER_UNDEF_SYMBOL = -1177, + + + /********************************************************/ + /* TRIO Error Codes */ + /********************************************************/ + + /** Cannot allocate memory map region. */ + GXIO_TRIO_ERR_NO_MEMORY_MAP = -1180, + + /** Invalid memory map region number. */ + GXIO_TRIO_ERR_BAD_MEMORY_MAP = -1181, + + /** Cannot allocate scatter queue. */ + GXIO_TRIO_ERR_NO_SCATTER_QUEUE = -1182, + + /** Invalid scatter queue number. */ + GXIO_TRIO_ERR_BAD_SCATTER_QUEUE = -1183, + + /** Cannot allocate push DMA ring. */ + GXIO_TRIO_ERR_NO_PUSH_DMA_RING = -1184, + + /** Invalid push DMA ring index. */ + GXIO_TRIO_ERR_BAD_PUSH_DMA_RING = -1185, + + /** Cannot allocate pull DMA ring. */ + GXIO_TRIO_ERR_NO_PULL_DMA_RING = -1186, + + /** Invalid pull DMA ring index. */ + GXIO_TRIO_ERR_BAD_PULL_DMA_RING = -1187, + + /** Cannot allocate PIO region. */ + GXIO_TRIO_ERR_NO_PIO = -1188, + + /** Invalid PIO region index. */ + GXIO_TRIO_ERR_BAD_PIO = -1189, + + /** Cannot allocate ASID. */ + GXIO_TRIO_ERR_NO_ASID = -1190, + + /** Invalid ASID. */ + GXIO_TRIO_ERR_BAD_ASID = -1191, + + + /********************************************************/ + /* MICA Error Codes */ + /********************************************************/ + + /** No such accelerator type. */ + GXIO_MICA_ERR_BAD_ACCEL_TYPE = -1220, + + /** Cannot allocate context. */ + GXIO_MICA_ERR_NO_CONTEXT = -1221, + + /** PKA command queue is full, can't add another command. */ + GXIO_MICA_ERR_PKA_CMD_QUEUE_FULL = -1222, + + /** PKA result queue is empty, can't get a result from the queue. */ + GXIO_MICA_ERR_PKA_RESULT_QUEUE_EMPTY = -1223, + + /********************************************************/ + /* GPIO Error Codes */ + /********************************************************/ + + /** Pin not available. Either the physical pin does not exist, or + * it is reserved by the hypervisor for system usage. */ + GXIO_GPIO_ERR_PIN_UNAVAILABLE = -1240, + + /** Pin busy. The pin exists, and is available for use via GXIO, but + * it has been attached by some other process or driver. */ + GXIO_GPIO_ERR_PIN_BUSY = -1241, + + /** Cannot access unattached pin. One or more of the pins being + * manipulated by this call are not attached to the requesting + * context. */ + GXIO_GPIO_ERR_PIN_UNATTACHED = -1242, + + /** Invalid I/O mode for pin. The wiring of the pin in the system + * is such that the I/O mode or electrical control parameters + * requested could cause damage. */ + GXIO_GPIO_ERR_PIN_INVALID_MODE = -1243, + + /** Smallest iorpc error number. */ + GXIO_ERR_MIN = -1299 +}; + + +#endif /* !_HV_IORPC_H_ */ diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile index 5de9924..5334be8 100644 --- a/arch/tile/kernel/Makefile +++ b/arch/tile/kernel/Makefile @@ -14,4 +14,9 @@ obj-$(CONFIG_SMP) += smpboot.o smp.o tlb.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel_$(BITS).o +ifdef CONFIG_TILEGX +obj-$(CONFIG_PCI) += pci_gx.o +else obj-$(CONFIG_PCI) += pci.o +endif +obj-$(CONFIG_TILE_USB) += usb.o diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c index b3ed19f..b9fe80e 100644 --- a/arch/tile/kernel/pci-dma.c +++ b/arch/tile/kernel/pci-dma.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/dma-mapping.h> +#include <linux/swiotlb.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <asm/tlbflush.h> @@ -22,13 +23,18 @@ /* Generic DMA mapping functions: */ /* - * Allocate what Linux calls "coherent" memory, which for us just - * means uncached. + * Allocate what Linux calls "coherent" memory. On TILEPro this is + * uncached memory; on TILE-Gx it is hash-for-home memory. */ -void *dma_alloc_coherent(struct device *dev, - size_t size, - dma_addr_t *dma_handle, - gfp_t gfp) +#ifdef __tilepro__ +#define PAGE_HOME_DMA PAGE_HOME_UNCACHED +#else +#define PAGE_HOME_DMA PAGE_HOME_HASH +#endif + +static void *tile_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + struct dma_attrs *attrs) { u64 dma_mask = dev->coherent_dma_mask ?: DMA_BIT_MASK(32); int node = dev_to_node(dev); @@ -39,39 +45,42 @@ void *dma_alloc_coherent(struct device *dev, gfp |= __GFP_ZERO; /* - * By forcing NUMA node 0 for 32-bit masks we ensure that the - * high 32 bits of the resulting PA will be zero. If the mask - * size is, e.g., 24, we may still not be able to guarantee a - * suitable memory address, in which case we will return NULL. - * But such devices are uncommon. + * If the mask specifies that the memory be in the first 4 GB, then + * we force the allocation to come from the DMA zone. We also + * force the node to 0 since that's the only node where the DMA + * zone isn't empty. If the mask size is smaller than 32 bits, we + * may still not be able to guarantee a suitable memory address, in + * which case we will return NULL. But such devices are uncommon. */ - if (dma_mask <= DMA_BIT_MASK(32)) + if (dma_mask <= DMA_BIT_MASK(32)) { + gfp |= GFP_DMA; node = 0; + } - pg = homecache_alloc_pages_node(node, gfp, order, PAGE_HOME_UNCACHED); + pg = homecache_alloc_pages_node(node, gfp, order, PAGE_HOME_DMA); if (pg == NULL) return NULL; addr = page_to_phys(pg); if (addr + size > dma_mask) { - homecache_free_pages(addr, order); + __homecache_free_pages(pg, order); return NULL; } *dma_handle = addr; + return page_address(pg); } -EXPORT_SYMBOL(dma_alloc_coherent); /* - * Free memory that was allocated with dma_alloc_coherent. + * Free memory that was allocated with tile_dma_alloc_coherent. */ -void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) +static void tile_dma_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) { homecache_free_pages((unsigned long)vaddr, get_order(size)); } -EXPORT_SYMBOL(dma_free_coherent); /* * The map routines "map" the specified address range for DMA @@ -87,52 +96,285 @@ EXPORT_SYMBOL(dma_free_coherent); * can count on nothing having been touched. */ -/* Flush a PA range from cache page by page. */ -static void __dma_map_pa_range(dma_addr_t dma_addr, size_t size) +/* Set up a single page for DMA access. */ +static void __dma_prep_page(struct page *page, unsigned long offset, + size_t size, enum dma_data_direction direction) +{ + /* + * Flush the page from cache if necessary. + * On tilegx, data is delivered to hash-for-home L3; on tilepro, + * data is delivered direct to memory. + * + * NOTE: If we were just doing DMA_TO_DEVICE we could optimize + * this to be a "flush" not a "finv" and keep some of the + * state in cache across the DMA operation, but it doesn't seem + * worth creating the necessary flush_buffer_xxx() infrastructure. + */ + int home = page_home(page); + switch (home) { + case PAGE_HOME_HASH: +#ifdef __tilegx__ + return; +#endif + break; + case PAGE_HOME_UNCACHED: +#ifdef __tilepro__ + return; +#endif + break; + case PAGE_HOME_IMMUTABLE: + /* Should be going to the device only. */ + BUG_ON(direction == DMA_FROM_DEVICE || + direction == DMA_BIDIRECTIONAL); + return; + case PAGE_HOME_INCOHERENT: + /* Incoherent anyway, so no need to work hard here. */ + return; + default: + BUG_ON(home < 0 || home >= NR_CPUS); + break; + } + homecache_finv_page(page); + +#ifdef DEBUG_ALIGNMENT + /* Warn if the region isn't cacheline aligned. */ + if (offset & (L2_CACHE_BYTES - 1) || (size & (L2_CACHE_BYTES - 1))) + pr_warn("Unaligned DMA to non-hfh memory: PA %#llx/%#lx\n", + PFN_PHYS(page_to_pfn(page)) + offset, size); +#endif +} + +/* Make the page ready to be read by the core. */ +static void __dma_complete_page(struct page *page, unsigned long offset, + size_t size, enum dma_data_direction direction) +{ +#ifdef __tilegx__ + switch (page_home(page)) { + case PAGE_HOME_HASH: + /* I/O device delivered data the way the cpu wanted it. */ + break; + case PAGE_HOME_INCOHERENT: + /* Incoherent anyway, so no need to work hard here. */ + break; + case PAGE_HOME_IMMUTABLE: + /* Extra read-only copies are not a problem. */ + break; + default: + /* Flush the bogus hash-for-home I/O entries to memory. */ + homecache_finv_map_page(page, PAGE_HOME_HASH); + break; + } +#endif +} + +static void __dma_prep_pa_range(dma_addr_t dma_addr, size_t size, + enum dma_data_direction direction) { struct page *page = pfn_to_page(PFN_DOWN(dma_addr)); - size_t bytesleft = PAGE_SIZE - (dma_addr & (PAGE_SIZE - 1)); + unsigned long offset = dma_addr & (PAGE_SIZE - 1); + size_t bytes = min(size, (size_t)(PAGE_SIZE - offset)); + + while (size != 0) { + __dma_prep_page(page, offset, bytes, direction); + size -= bytes; + ++page; + offset = 0; + bytes = min((size_t)PAGE_SIZE, size); + } +} - while ((ssize_t)size > 0) { - /* Flush the page. */ - homecache_flush_cache(page++, 0); +static void __dma_complete_pa_range(dma_addr_t dma_addr, size_t size, + enum dma_data_direction direction) +{ + struct page *page = pfn_to_page(PFN_DOWN(dma_addr)); + unsigned long offset = dma_addr & (PAGE_SIZE - 1); + size_t bytes = min(size, (size_t)(PAGE_SIZE - offset)); + + while (size != 0) { + __dma_complete_page(page, offset, bytes, direction); + size -= bytes; + ++page; + offset = 0; + bytes = min((size_t)PAGE_SIZE, size); + } +} + +static int tile_dma_map_sg(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + struct scatterlist *sg; + int i; + + BUG_ON(!valid_dma_direction(direction)); + + WARN_ON(nents == 0 || sglist->length == 0); - /* Figure out if we need to continue on the next page. */ - size -= bytesleft; - bytesleft = PAGE_SIZE; + for_each_sg(sglist, sg, nents, i) { + sg->dma_address = sg_phys(sg); + __dma_prep_pa_range(sg->dma_address, sg->length, direction); +#ifdef CONFIG_NEED_SG_DMA_LENGTH + sg->dma_length = sg->length; +#endif } + + return nents; } -/* - * dma_map_single can be passed any memory address, and there appear - * to be no alignment constraints. - * - * There is a chance that the start of the buffer will share a cache - * line with some other data that has been touched in the meantime. - */ -dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction direction) +static void tile_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + struct scatterlist *sg; + int i; + + BUG_ON(!valid_dma_direction(direction)); + for_each_sg(sglist, sg, nents, i) { + sg->dma_address = sg_phys(sg); + __dma_complete_pa_range(sg->dma_address, sg->length, + direction); + } +} + +static dma_addr_t tile_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { - dma_addr_t dma_addr = __pa(ptr); + BUG_ON(!valid_dma_direction(direction)); + + BUG_ON(offset + size > PAGE_SIZE); + __dma_prep_page(page, offset, size, direction); + return page_to_pa(page) + offset; +} + +static void tile_dma_unmap_page(struct device *dev, dma_addr_t dma_address, + size_t size, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ BUG_ON(!valid_dma_direction(direction)); - WARN_ON(size == 0); - __dma_map_pa_range(dma_addr, size); + __dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)), + dma_address & PAGE_OFFSET, size, direction); +} - return dma_addr; +static void tile_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, + size_t size, + enum dma_data_direction direction) +{ + BUG_ON(!valid_dma_direction(direction)); + + __dma_complete_pa_range(dma_handle, size, direction); +} + +static void tile_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ + __dma_prep_pa_range(dma_handle, size, direction); } -EXPORT_SYMBOL(dma_map_single); -void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction direction) +static void tile_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sglist, int nelems, + enum dma_data_direction direction) { + struct scatterlist *sg; + int i; + + BUG_ON(!valid_dma_direction(direction)); + WARN_ON(nelems == 0 || sglist->length == 0); + + for_each_sg(sglist, sg, nelems, i) { + dma_sync_single_for_cpu(dev, sg->dma_address, + sg_dma_len(sg), direction); + } +} + +static void tile_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sglist, int nelems, + enum dma_data_direction direction) +{ + struct scatterlist *sg; + int i; + BUG_ON(!valid_dma_direction(direction)); + WARN_ON(nelems == 0 || sglist->length == 0); + + for_each_sg(sglist, sg, nelems, i) { + dma_sync_single_for_device(dev, sg->dma_address, + sg_dma_len(sg), direction); + } +} + +static inline int +tile_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return 0; +} + +static inline int +tile_dma_supported(struct device *dev, u64 mask) +{ + return 1; +} + +static struct dma_map_ops tile_default_dma_map_ops = { + .alloc = tile_dma_alloc_coherent, + .free = tile_dma_free_coherent, + .map_page = tile_dma_map_page, + .unmap_page = tile_dma_unmap_page, + .map_sg = tile_dma_map_sg, + .unmap_sg = tile_dma_unmap_sg, + .sync_single_for_cpu = tile_dma_sync_single_for_cpu, + .sync_single_for_device = tile_dma_sync_single_for_device, + .sync_sg_for_cpu = tile_dma_sync_sg_for_cpu, + .sync_sg_for_device = tile_dma_sync_sg_for_device, + .mapping_error = tile_dma_mapping_error, + .dma_supported = tile_dma_supported +}; + +struct dma_map_ops *tile_dma_map_ops = &tile_default_dma_map_ops; +EXPORT_SYMBOL(tile_dma_map_ops); + +/* Generic PCI DMA mapping functions */ + +static void *tile_pci_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + struct dma_attrs *attrs) +{ + int node = dev_to_node(dev); + int order = get_order(size); + struct page *pg; + dma_addr_t addr; + + gfp |= __GFP_ZERO; + + pg = homecache_alloc_pages_node(node, gfp, order, PAGE_HOME_DMA); + if (pg == NULL) + return NULL; + + addr = page_to_phys(pg); + + *dma_handle = phys_to_dma(dev, addr); + + return page_address(pg); +} + +/* + * Free memory that was allocated with tile_pci_dma_alloc_coherent. + */ +static void tile_pci_dma_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + homecache_free_pages((unsigned long)vaddr, get_order(size)); } -EXPORT_SYMBOL(dma_unmap_single); -int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, - enum dma_data_direction direction) +static int tile_pci_dma_map_sg(struct device *dev, struct scatterlist *sglist, + int nents, enum dma_data_direction direction, + struct dma_attrs *attrs) { struct scatterlist *sg; int i; @@ -143,73 +385,103 @@ int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, for_each_sg(sglist, sg, nents, i) { sg->dma_address = sg_phys(sg); - __dma_map_pa_range(sg->dma_address, sg->length); + __dma_prep_pa_range(sg->dma_address, sg->length, direction); + + sg->dma_address = phys_to_dma(dev, sg->dma_address); +#ifdef CONFIG_NEED_SG_DMA_LENGTH + sg->dma_length = sg->length; +#endif } return nents; } -EXPORT_SYMBOL(dma_map_sg); -void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries, - enum dma_data_direction direction) +static void tile_pci_dma_unmap_sg(struct device *dev, + struct scatterlist *sglist, int nents, + enum dma_data_direction direction, + struct dma_attrs *attrs) { + struct scatterlist *sg; + int i; + BUG_ON(!valid_dma_direction(direction)); + for_each_sg(sglist, sg, nents, i) { + sg->dma_address = sg_phys(sg); + __dma_complete_pa_range(sg->dma_address, sg->length, + direction); + } } -EXPORT_SYMBOL(dma_unmap_sg); -dma_addr_t dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction) +static dma_addr_t tile_pci_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { BUG_ON(!valid_dma_direction(direction)); BUG_ON(offset + size > PAGE_SIZE); - homecache_flush_cache(page, 0); + __dma_prep_page(page, offset, size, direction); - return page_to_pa(page) + offset; + return phys_to_dma(dev, page_to_pa(page) + offset); } -EXPORT_SYMBOL(dma_map_page); -void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, - enum dma_data_direction direction) +static void tile_pci_dma_unmap_page(struct device *dev, dma_addr_t dma_address, + size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) { BUG_ON(!valid_dma_direction(direction)); + + dma_address = dma_to_phys(dev, dma_address); + + __dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)), + dma_address & PAGE_OFFSET, size, direction); } -EXPORT_SYMBOL(dma_unmap_page); -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction direction) +static void tile_pci_dma_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, + size_t size, + enum dma_data_direction direction) { BUG_ON(!valid_dma_direction(direction)); + + dma_handle = dma_to_phys(dev, dma_handle); + + __dma_complete_pa_range(dma_handle, size, direction); } -EXPORT_SYMBOL(dma_sync_single_for_cpu); -void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction direction) +static void tile_pci_dma_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, + size_t size, + enum dma_data_direction + direction) { - unsigned long start = PFN_DOWN(dma_handle); - unsigned long end = PFN_DOWN(dma_handle + size - 1); - unsigned long i; + dma_handle = dma_to_phys(dev, dma_handle); - BUG_ON(!valid_dma_direction(direction)); - for (i = start; i <= end; ++i) - homecache_flush_cache(pfn_to_page(i), 0); + __dma_prep_pa_range(dma_handle, size, direction); } -EXPORT_SYMBOL(dma_sync_single_for_device); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction direction) +static void tile_pci_dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sglist, + int nelems, + enum dma_data_direction direction) { + struct scatterlist *sg; + int i; + BUG_ON(!valid_dma_direction(direction)); - WARN_ON(nelems == 0 || sg[0].length == 0); + WARN_ON(nelems == 0 || sglist->length == 0); + + for_each_sg(sglist, sg, nelems, i) { + dma_sync_single_for_cpu(dev, sg->dma_address, + sg_dma_len(sg), direction); + } } -EXPORT_SYMBOL(dma_sync_sg_for_cpu); -/* - * Flush and invalidate cache for scatterlist. - */ -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, - int nelems, enum dma_data_direction direction) +static void tile_pci_dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sglist, + int nelems, + enum dma_data_direction direction) { struct scatterlist *sg; int i; @@ -222,31 +494,93 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, sg_dma_len(sg), direction); } } -EXPORT_SYMBOL(dma_sync_sg_for_device); -void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle, - unsigned long offset, size_t size, - enum dma_data_direction direction) +static inline int +tile_pci_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - dma_sync_single_for_cpu(dev, dma_handle + offset, size, direction); + return 0; } -EXPORT_SYMBOL(dma_sync_single_range_for_cpu); -void dma_sync_single_range_for_device(struct device *dev, - dma_addr_t dma_handle, - unsigned long offset, size_t size, - enum dma_data_direction direction) +static inline int +tile_pci_dma_supported(struct device *dev, u64 mask) { - dma_sync_single_for_device(dev, dma_handle + offset, size, direction); + return 1; } -EXPORT_SYMBOL(dma_sync_single_range_for_device); -/* - * dma_alloc_noncoherent() returns non-cacheable memory, so there's no - * need to do any flushing here. - */ -void dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction direction) +static struct dma_map_ops tile_pci_default_dma_map_ops = { + .alloc = tile_pci_dma_alloc_coherent, + .free = tile_pci_dma_free_coherent, + .map_page = tile_pci_dma_map_page, + .unmap_page = tile_pci_dma_unmap_page, + .map_sg = tile_pci_dma_map_sg, + .unmap_sg = tile_pci_dma_unmap_sg, + .sync_single_for_cpu = tile_pci_dma_sync_single_for_cpu, + .sync_single_for_device = tile_pci_dma_sync_single_for_device, + .sync_sg_for_cpu = tile_pci_dma_sync_sg_for_cpu, + .sync_sg_for_device = tile_pci_dma_sync_sg_for_device, + .mapping_error = tile_pci_dma_mapping_error, + .dma_supported = tile_pci_dma_supported +}; + +struct dma_map_ops *gx_pci_dma_map_ops = &tile_pci_default_dma_map_ops; +EXPORT_SYMBOL(gx_pci_dma_map_ops); + +/* PCI DMA mapping functions for legacy PCI devices */ + +#ifdef CONFIG_SWIOTLB +static void *tile_swiotlb_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, + struct dma_attrs *attrs) { + gfp |= GFP_DMA; + return swiotlb_alloc_coherent(dev, size, dma_handle, gfp); +} + +static void tile_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs) +{ + swiotlb_free_coherent(dev, size, vaddr, dma_addr); +} + +static struct dma_map_ops pci_swiotlb_dma_ops = { + .alloc = tile_swiotlb_alloc_coherent, + .free = tile_swiotlb_free_coherent, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, + .sync_single_for_cpu = swiotlb_sync_single_for_cpu, + .sync_single_for_device = swiotlb_sync_single_for_device, + .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = swiotlb_sync_sg_for_device, + .dma_supported = swiotlb_dma_supported, + .mapping_error = swiotlb_dma_mapping_error, +}; + +struct dma_map_ops *gx_legacy_pci_dma_map_ops = &pci_swiotlb_dma_ops; +#else +struct dma_map_ops *gx_legacy_pci_dma_map_ops; +#endif +EXPORT_SYMBOL(gx_legacy_pci_dma_map_ops); + +#ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + /* Handle legacy PCI devices with limited memory addressability. */ + if (((dma_ops == gx_pci_dma_map_ops) || + (dma_ops == gx_legacy_pci_dma_map_ops)) && + (mask <= DMA_BIT_MASK(32))) { + if (mask > dev->archdata.max_direct_dma_addr) + mask = dev->archdata.max_direct_dma_addr; + } + + if (!dma_supported(dev, mask)) + return -EIO; + dev->coherent_dma_mask = mask; + return 0; } -EXPORT_SYMBOL(dma_cache_sync); +EXPORT_SYMBOL(dma_set_coherent_mask); +#endif diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c index b56d12b..0fdd99d 100644 --- a/arch/tile/kernel/pci.c +++ b/arch/tile/kernel/pci.c @@ -310,6 +310,7 @@ int __init pcibios_init(void) if (pci_scan_flags[i] == 0 && controllers[i].ops != NULL) { struct pci_controller *controller = &controllers[i]; struct pci_bus *bus; + LIST_HEAD(resources); if (tile_init_irqs(i, controller)) { pr_err("PCI: Could not initialize IRQs\n"); @@ -327,9 +328,11 @@ int __init pcibios_init(void) * This is inlined in linux/pci.h and calls into * pci_scan_bus_parented() in probe.c. */ - bus = pci_scan_bus(0, controller->ops, controller); + pci_add_resource(&resources, &ioport_resource); + pci_add_resource(&resources, &iomem_resource); + bus = pci_scan_root_bus(NULL, 0, controller->ops, controller, &resources); controller->root_bus = bus; - controller->last_busno = bus->subordinate; + controller->last_busno = bus->busn_res.end; } } @@ -366,7 +369,7 @@ int __init pcibios_init(void) */ if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && (PCI_SLOT(dev->devfn) == 0)) { - next_bus = dev->subordinate; + next_bus = dev->busn_res.end; controllers[i].mem_resources[0] = *next_bus->resource[0]; controllers[i].mem_resources[1] = @@ -401,16 +404,6 @@ void pcibios_set_master(struct pci_dev *dev) } /* - * This can be called from the generic PCI layer, but doesn't need to - * do anything. - */ -char __devinit *pcibios_setup(char *str) -{ - /* Nothing needs to be done. */ - return str; -} - -/* * This is called from the generic Linux layer. */ void __devinit pcibios_update_irq(struct pci_dev *dev, int irq) diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c new file mode 100644 index 0000000..fa75264 --- /dev/null +++ b/arch/tile/kernel/pci_gx.c @@ -0,0 +1,1543 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#include <linux/kernel.h> +#include <linux/mmzone.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/string.h> +#include <linux/init.h> +#include <linux/capability.h> +#include <linux/sched.h> +#include <linux/errno.h> +#include <linux/irq.h> +#include <linux/msi.h> +#include <linux/io.h> +#include <linux/uaccess.h> +#include <linux/ctype.h> + +#include <asm/processor.h> +#include <asm/sections.h> +#include <asm/byteorder.h> + +#include <gxio/iorpc_globals.h> +#include <gxio/kiorpc.h> +#include <gxio/trio.h> +#include <gxio/iorpc_trio.h> +#include <hv/drv_trio_intf.h> + +#include <arch/sim.h> + +/* + * This file containes the routines to search for PCI buses, + * enumerate the buses, and configure any attached devices. + */ + +#define DEBUG_PCI_CFG 0 + +#if DEBUG_PCI_CFG +#define TRACE_CFG_WR(size, val, bus, dev, func, offset) \ + pr_info("CFG WR %d-byte VAL %#x to bus %d dev %d func %d addr %u\n", \ + size, val, bus, dev, func, offset & 0xFFF); +#define TRACE_CFG_RD(size, val, bus, dev, func, offset) \ + pr_info("CFG RD %d-byte VAL %#x from bus %d dev %d func %d addr %u\n", \ + size, val, bus, dev, func, offset & 0xFFF); +#else +#define TRACE_CFG_WR(...) +#define TRACE_CFG_RD(...) +#endif + +static int __devinitdata pci_probe = 1; + +/* Information on the PCIe RC ports configuration. */ +static int __devinitdata pcie_rc[TILEGX_NUM_TRIO][TILEGX_TRIO_PCIES]; + +/* + * On some platforms with one or more Gx endpoint ports, we need to + * delay the PCIe RC port probe for a few seconds to work around + * a HW PCIe link-training bug. The exact delay is specified with + * a kernel boot argument in the form of "pcie_rc_delay=T,P,S", + * where T is the TRIO instance number, P is the port number and S is + * the delay in seconds. If the delay is not provided, the value + * will be DEFAULT_RC_DELAY. + */ +static int __devinitdata rc_delay[TILEGX_NUM_TRIO][TILEGX_TRIO_PCIES]; + +/* Default number of seconds that the PCIe RC port probe can be delayed. */ +#define DEFAULT_RC_DELAY 10 + +/* Max number of seconds that the PCIe RC port probe can be delayed. */ +#define MAX_RC_DELAY 20 + +/* Array of the PCIe ports configuration info obtained from the BIB. */ +struct pcie_port_property pcie_ports[TILEGX_NUM_TRIO][TILEGX_TRIO_PCIES]; + +/* All drivers share the TRIO contexts defined here. */ +gxio_trio_context_t trio_contexts[TILEGX_NUM_TRIO]; + +/* Pointer to an array of PCIe RC controllers. */ +struct pci_controller pci_controllers[TILEGX_NUM_TRIO * TILEGX_TRIO_PCIES]; +int num_rc_controllers; +static int num_ep_controllers; + +static struct pci_ops tile_cfg_ops; + +/* Mask of CPUs that should receive PCIe interrupts. */ +static struct cpumask intr_cpus_map; + +/* + * We don't need to worry about the alignment of resources. + */ +resource_size_t pcibios_align_resource(void *data, const struct resource *res, + resource_size_t size, resource_size_t align) +{ + return res->start; +} +EXPORT_SYMBOL(pcibios_align_resource); + + +/* + * Pick a CPU to receive and handle the PCIe interrupts, based on the IRQ #. + * For now, we simply send interrupts to non-dataplane CPUs. + * We may implement methods to allow user to specify the target CPUs, + * e.g. via boot arguments. + */ +static int tile_irq_cpu(int irq) +{ + unsigned int count; + int i = 0; + int cpu; + + count = cpumask_weight(&intr_cpus_map); + if (unlikely(count == 0)) { + pr_warning("intr_cpus_map empty, interrupts will be" + " delievered to dataplane tiles\n"); + return irq % (smp_height * smp_width); + } + + count = irq % count; + for_each_cpu(cpu, &intr_cpus_map) { + if (i++ == count) + break; + } + return cpu; +} + +/* + * Open a file descriptor to the TRIO shim. + */ +static int __devinit tile_pcie_open(int trio_index) +{ + gxio_trio_context_t *context = &trio_contexts[trio_index]; + int ret; + + /* + * This opens a file descriptor to the TRIO shim. + */ + ret = gxio_trio_init(context, trio_index); + if (ret < 0) + return ret; + + /* + * Allocate an ASID for the kernel. + */ + ret = gxio_trio_alloc_asids(context, 1, 0, 0); + if (ret < 0) { + pr_err("PCI: ASID alloc failure on TRIO %d, give up\n", + trio_index); + goto asid_alloc_failure; + } + + context->asid = ret; + +#ifdef USE_SHARED_PCIE_CONFIG_REGION + /* + * Alloc a PIO region for config access, shared by all MACs per TRIO. + * This shouldn't fail since the kernel is supposed to the first + * client of the TRIO's PIO regions. + */ + ret = gxio_trio_alloc_pio_regions(context, 1, 0, 0); + if (ret < 0) { + pr_err("PCI: CFG PIO alloc failure on TRIO %d, give up\n", + trio_index); + goto pio_alloc_failure; + } + + context->pio_cfg_index = ret; + + /* + * For PIO CFG, the bus_address_hi parameter is 0. The mac parameter + * is also 0 because it is specified in PIO_REGION_SETUP_CFG_ADDR. + */ + ret = gxio_trio_init_pio_region_aux(context, context->pio_cfg_index, + 0, 0, HV_TRIO_PIO_FLAG_CONFIG_SPACE); + if (ret < 0) { + pr_err("PCI: CFG PIO init failure on TRIO %d, give up\n", + trio_index); + goto pio_alloc_failure; + } +#endif + + return ret; + +asid_alloc_failure: +#ifdef USE_SHARED_PCIE_CONFIG_REGION +pio_alloc_failure: +#endif + hv_dev_close(context->fd); + + return ret; +} + +static void +tilegx_legacy_irq_ack(struct irq_data *d) +{ + __insn_mtspr(SPR_IPI_EVENT_RESET_K, 1UL << d->irq); +} + +static void +tilegx_legacy_irq_mask(struct irq_data *d) +{ + __insn_mtspr(SPR_IPI_MASK_SET_K, 1UL << d->irq); +} + +static void +tilegx_legacy_irq_unmask(struct irq_data *d) +{ + __insn_mtspr(SPR_IPI_MASK_RESET_K, 1UL << d->irq); +} + +static struct irq_chip tilegx_legacy_irq_chip = { + .name = "tilegx_legacy_irq", + .irq_ack = tilegx_legacy_irq_ack, + .irq_mask = tilegx_legacy_irq_mask, + .irq_unmask = tilegx_legacy_irq_unmask, + + /* TBD: support set_affinity. */ +}; + +/* + * This is a wrapper function of the kernel level-trigger interrupt + * handler handle_level_irq() for PCI legacy interrupts. The TRIO + * is configured such that only INTx Assert interrupts are proxied + * to Linux which just calls handle_level_irq() after clearing the + * MAC INTx Assert status bit associated with this interrupt. + */ +static void +trio_handle_level_irq(unsigned int irq, struct irq_desc *desc) +{ + struct pci_controller *controller = irq_desc_get_handler_data(desc); + gxio_trio_context_t *trio_context = controller->trio; + uint64_t intx = (uint64_t)irq_desc_get_chip_data(desc); + int mac = controller->mac; + unsigned int reg_offset; + uint64_t level_mask; + + handle_level_irq(irq, desc); + + /* + * Clear the INTx Level status, otherwise future interrupts are + * not sent. + */ + reg_offset = (TRIO_PCIE_INTFC_MAC_INT_STS << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + level_mask = TRIO_PCIE_INTFC_MAC_INT_STS__INT_LEVEL_MASK << intx; + + __gxio_mmio_write(trio_context->mmio_base_mac + reg_offset, level_mask); +} + +/* + * Create kernel irqs and set up the handlers for the legacy interrupts. + * Also some minimum initialization for the MSI support. + */ +static int __devinit tile_init_irqs(struct pci_controller *controller) +{ + int i; + int j; + int irq; + int result; + + cpumask_copy(&intr_cpus_map, cpu_online_mask); + + + for (i = 0; i < 4; i++) { + gxio_trio_context_t *context = controller->trio; + int cpu; + + /* Ask the kernel to allocate an IRQ. */ + irq = create_irq(); + if (irq < 0) { + pr_err("PCI: no free irq vectors, failed for %d\n", i); + + goto free_irqs; + } + controller->irq_intx_table[i] = irq; + + /* Distribute the 4 IRQs to different tiles. */ + cpu = tile_irq_cpu(irq); + + /* Configure the TRIO intr binding for this IRQ. */ + result = gxio_trio_config_legacy_intr(context, cpu_x(cpu), + cpu_y(cpu), KERNEL_PL, + irq, controller->mac, i); + if (result < 0) { + pr_err("PCI: MAC intx config failed for %d\n", i); + + goto free_irqs; + } + + /* + * Register the IRQ handler with the kernel. + */ + irq_set_chip_and_handler(irq, &tilegx_legacy_irq_chip, + trio_handle_level_irq); + irq_set_chip_data(irq, (void *)(uint64_t)i); + irq_set_handler_data(irq, controller); + } + + return 0; + +free_irqs: + for (j = 0; j < i; j++) + destroy_irq(controller->irq_intx_table[j]); + + return -1; +} + +/* + * Find valid controllers and fill in pci_controller structs for each + * of them. + * + * Returns the number of controllers discovered. + */ +int __init tile_pci_init(void) +{ + int num_trio_shims = 0; + int ctl_index = 0; + int i, j; + + if (!pci_probe) { + pr_info("PCI: disabled by boot argument\n"); + return 0; + } + + pr_info("PCI: Searching for controllers...\n"); + + /* + * We loop over all the TRIO shims. + */ + for (i = 0; i < TILEGX_NUM_TRIO; i++) { + int ret; + + ret = tile_pcie_open(i); + if (ret < 0) + continue; + + num_trio_shims++; + } + + if (num_trio_shims == 0 || sim_is_simulator()) + return 0; + + /* + * Now determine which PCIe ports are configured to operate in RC mode. + * We look at the Board Information Block first and then see if there + * are any overriding configuration by the HW strapping pin. + */ + for (i = 0; i < TILEGX_NUM_TRIO; i++) { + gxio_trio_context_t *context = &trio_contexts[i]; + int ret; + + if (context->fd < 0) + continue; + + ret = hv_dev_pread(context->fd, 0, + (HV_VirtAddr)&pcie_ports[i][0], + sizeof(struct pcie_port_property) * TILEGX_TRIO_PCIES, + GXIO_TRIO_OP_GET_PORT_PROPERTY); + if (ret < 0) { + pr_err("PCI: PCIE_GET_PORT_PROPERTY failure, error %d," + " on TRIO %d\n", ret, i); + continue; + } + + for (j = 0; j < TILEGX_TRIO_PCIES; j++) { + if (pcie_ports[i][j].allow_rc) { + pcie_rc[i][j] = 1; + num_rc_controllers++; + } + else if (pcie_ports[i][j].allow_ep) { + num_ep_controllers++; + } + } + } + + /* + * Return if no PCIe ports are configured to operate in RC mode. + */ + if (num_rc_controllers == 0) + return 0; + + /* + * Set the TRIO pointer and MAC index for each PCIe RC port. + */ + for (i = 0; i < TILEGX_NUM_TRIO; i++) { + for (j = 0; j < TILEGX_TRIO_PCIES; j++) { + if (pcie_rc[i][j]) { + pci_controllers[ctl_index].trio = + &trio_contexts[i]; + pci_controllers[ctl_index].mac = j; + pci_controllers[ctl_index].trio_index = i; + ctl_index++; + if (ctl_index == num_rc_controllers) + goto out; + } + } + } + +out: + /* + * Configure each PCIe RC port. + */ + for (i = 0; i < num_rc_controllers; i++) { + /* + * Configure the PCIe MAC to run in RC mode. + */ + + struct pci_controller *controller = &pci_controllers[i]; + + controller->index = i; + controller->ops = &tile_cfg_ops; + + /* + * The PCI memory resource is located above the PA space. + * For every host bridge, the BAR window or the MMIO aperture + * is in range [3GB, 4GB - 1] of a 4GB space beyond the + * PA space. + */ + + controller->mem_offset = TILE_PCI_MEM_START + + (i * TILE_PCI_BAR_WINDOW_TOP); + controller->mem_space.start = controller->mem_offset + + TILE_PCI_BAR_WINDOW_TOP - TILE_PCI_BAR_WINDOW_SIZE; + controller->mem_space.end = controller->mem_offset + + TILE_PCI_BAR_WINDOW_TOP - 1; + controller->mem_space.flags = IORESOURCE_MEM; + snprintf(controller->mem_space_name, + sizeof(controller->mem_space_name), + "PCI mem domain %d", i); + controller->mem_space.name = controller->mem_space_name; + } + + return num_rc_controllers; +} + +/* + * (pin - 1) converts from the PCI standard's [1:4] convention to + * a normal [0:3] range. + */ +static int tile_map_irq(const struct pci_dev *dev, u8 device, u8 pin) +{ + struct pci_controller *controller = + (struct pci_controller *)dev->sysdata; + return controller->irq_intx_table[pin - 1]; +} + + +static void __devinit fixup_read_and_payload_sizes(struct pci_controller * + controller) +{ + gxio_trio_context_t *trio_context = controller->trio; + struct pci_bus *root_bus = controller->root_bus; + TRIO_PCIE_RC_DEVICE_CONTROL_t dev_control; + TRIO_PCIE_RC_DEVICE_CAP_t rc_dev_cap; + unsigned int reg_offset; + struct pci_bus *child; + int mac; + int err; + + mac = controller->mac; + + /* + * Set our max read request size to be 4KB. + */ + reg_offset = + (TRIO_PCIE_RC_DEVICE_CONTROL << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_STANDARD << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + dev_control.word = __gxio_mmio_read32(trio_context->mmio_base_mac + + reg_offset); + dev_control.max_read_req_sz = 5; + __gxio_mmio_write32(trio_context->mmio_base_mac + reg_offset, + dev_control.word); + + /* + * Set the max payload size supported by this Gx PCIe MAC. + * Though Gx PCIe supports Max Payload Size of up to 1024 bytes, + * experiments have shown that setting MPS to 256 yields the + * best performance. + */ + reg_offset = + (TRIO_PCIE_RC_DEVICE_CAP << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_STANDARD << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + rc_dev_cap.word = __gxio_mmio_read32(trio_context->mmio_base_mac + + reg_offset); + rc_dev_cap.mps_sup = 1; + __gxio_mmio_write32(trio_context->mmio_base_mac + reg_offset, + rc_dev_cap.word); + + /* Configure PCI Express MPS setting. */ + list_for_each_entry(child, &root_bus->children, node) { + struct pci_dev *self = child->self; + if (!self) + continue; + + pcie_bus_configure_settings(child, self->pcie_mpss); + } + + /* + * Set the mac_config register in trio based on the MPS/MRS of the link. + */ + reg_offset = + (TRIO_PCIE_RC_DEVICE_CONTROL << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_STANDARD << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + dev_control.word = __gxio_mmio_read32(trio_context->mmio_base_mac + + reg_offset); + + err = gxio_trio_set_mps_mrs(trio_context, + dev_control.max_payload_size, + dev_control.max_read_req_sz, + mac); + if (err < 0) { + pr_err("PCI: PCIE_CONFIGURE_MAC_MPS_MRS failure, " + "MAC %d on TRIO %d\n", + mac, controller->trio_index); + } +} + +static int __devinit setup_pcie_rc_delay(char *str) +{ + unsigned long delay = 0; + unsigned long trio_index; + unsigned long mac; + + if (str == NULL || !isdigit(*str)) + return -EINVAL; + trio_index = simple_strtoul(str, (char **)&str, 10); + if (trio_index >= TILEGX_NUM_TRIO) + return -EINVAL; + + if (*str != ',') + return -EINVAL; + + str++; + if (!isdigit(*str)) + return -EINVAL; + mac = simple_strtoul(str, (char **)&str, 10); + if (mac >= TILEGX_TRIO_PCIES) + return -EINVAL; + + if (*str != '\0') { + if (*str != ',') + return -EINVAL; + + str++; + if (!isdigit(*str)) + return -EINVAL; + delay = simple_strtoul(str, (char **)&str, 10); + if (delay > MAX_RC_DELAY) + return -EINVAL; + } + + rc_delay[trio_index][mac] = delay ? : DEFAULT_RC_DELAY; + pr_info("Delaying PCIe RC link training for %u sec" + " on MAC %lu on TRIO %lu\n", rc_delay[trio_index][mac], + mac, trio_index); + return 0; +} +early_param("pcie_rc_delay", setup_pcie_rc_delay); + +/* + * PCI initialization entry point, called by subsys_initcall. + */ +int __init pcibios_init(void) +{ + resource_size_t offset; + LIST_HEAD(resources); + int next_busno; + int i; + + tile_pci_init(); + + if (num_rc_controllers == 0 && num_ep_controllers == 0) + return 0; + + /* + * We loop over all the TRIO shims and set up the MMIO mappings. + */ + for (i = 0; i < TILEGX_NUM_TRIO; i++) { + gxio_trio_context_t *context = &trio_contexts[i]; + + if (context->fd < 0) + continue; + + /* + * Map in the MMIO space for the MAC. + */ + offset = 0; + context->mmio_base_mac = + iorpc_ioremap(context->fd, offset, + HV_TRIO_CONFIG_IOREMAP_SIZE); + if (context->mmio_base_mac == NULL) { + pr_err("PCI: MAC map failure on TRIO %d\n", i); + + hv_dev_close(context->fd); + context->fd = -1; + continue; + } + } + + /* + * Delay a bit in case devices aren't ready. Some devices are + * known to require at least 20ms here, but we use a more + * conservative value. + */ + msleep(250); + + /* Scan all of the recorded PCI controllers. */ + for (next_busno = 0, i = 0; i < num_rc_controllers; i++) { + struct pci_controller *controller = &pci_controllers[i]; + gxio_trio_context_t *trio_context = controller->trio; + TRIO_PCIE_INTFC_PORT_CONFIG_t port_config; + TRIO_PCIE_INTFC_PORT_STATUS_t port_status; + TRIO_PCIE_INTFC_TX_FIFO_CTL_t tx_fifo_ctl; + struct pci_bus *bus; + unsigned int reg_offset; + unsigned int class_code_revision; + int trio_index; + int mac; + int ret; + + if (trio_context->fd < 0) + continue; + + trio_index = controller->trio_index; + mac = controller->mac; + + /* + * Check the port strap state which will override the BIB + * setting. + */ + + reg_offset = + (TRIO_PCIE_INTFC_PORT_CONFIG << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + port_config.word = + __gxio_mmio_read(trio_context->mmio_base_mac + + reg_offset); + + if ((port_config.strap_state != + TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC) && + (port_config.strap_state != + TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_RC_G1)) { + /* + * If this is really intended to be an EP port, + * record it so that the endpoint driver will know about it. + */ + if (port_config.strap_state == + TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT || + port_config.strap_state == + TRIO_PCIE_INTFC_PORT_CONFIG__STRAP_STATE_VAL_AUTO_CONFIG_ENDPOINT_G1) + pcie_ports[trio_index][mac].allow_ep = 1; + + continue; + } + + /* + * Delay the RC link training if needed. + */ + if (rc_delay[trio_index][mac]) + msleep(rc_delay[trio_index][mac] * 1000); + + ret = gxio_trio_force_rc_link_up(trio_context, mac); + if (ret < 0) + pr_err("PCI: PCIE_FORCE_LINK_UP failure, " + "MAC %d on TRIO %d\n", mac, trio_index); + + pr_info("PCI: Found PCI controller #%d on TRIO %d MAC %d\n", i, + trio_index, controller->mac); + + /* + * Wait a bit here because some EP devices take longer + * to come up. + */ + msleep(1000); + + /* + * Check for PCIe link-up status. + */ + + reg_offset = + (TRIO_PCIE_INTFC_PORT_STATUS << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + port_status.word = + __gxio_mmio_read(trio_context->mmio_base_mac + + reg_offset); + if (!port_status.dl_up) { + pr_err("PCI: link is down, MAC %d on TRIO %d\n", + mac, trio_index); + continue; + } + + /* + * Ensure that the link can come out of L1 power down state. + * Strictly speaking, this is needed only in the case of + * heavy RC-initiated DMAs. + */ + reg_offset = + (TRIO_PCIE_INTFC_TX_FIFO_CTL << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_INTERFACE << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + tx_fifo_ctl.word = + __gxio_mmio_read(trio_context->mmio_base_mac + + reg_offset); + tx_fifo_ctl.min_p_credits = 0; + __gxio_mmio_write(trio_context->mmio_base_mac + reg_offset, + tx_fifo_ctl.word); + + /* + * Change the device ID so that Linux bus crawl doesn't confuse + * the internal bridge with any Tilera endpoints. + */ + + reg_offset = + (TRIO_PCIE_RC_DEVICE_ID_VEN_ID << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_STANDARD << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + __gxio_mmio_write32(trio_context->mmio_base_mac + reg_offset, + (TILERA_GX36_RC_DEV_ID << + TRIO_PCIE_RC_DEVICE_ID_VEN_ID__DEV_ID_SHIFT) | + TILERA_VENDOR_ID); + + /* + * Set the internal P2P bridge class code. + */ + + reg_offset = + (TRIO_PCIE_RC_REVISION_ID << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_STANDARD << + TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (mac << TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + class_code_revision = + __gxio_mmio_read32(trio_context->mmio_base_mac + + reg_offset); + class_code_revision = (class_code_revision & 0xff ) | + (PCI_CLASS_BRIDGE_PCI << 16); + + __gxio_mmio_write32(trio_context->mmio_base_mac + + reg_offset, class_code_revision); + +#ifdef USE_SHARED_PCIE_CONFIG_REGION + + /* + * Map in the MMIO space for the PIO region. + */ + offset = HV_TRIO_PIO_OFFSET(trio_context->pio_cfg_index) | + (((unsigned long long)mac) << + TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT); + +#else + + /* + * Alloc a PIO region for PCI config access per MAC. + */ + ret = gxio_trio_alloc_pio_regions(trio_context, 1, 0, 0); + if (ret < 0) { + pr_err("PCI: PCI CFG PIO alloc failure for mac %d " + "on TRIO %d, give up\n", mac, trio_index); + + continue; + } + + trio_context->pio_cfg_index[mac] = ret; + + /* + * For PIO CFG, the bus_address_hi parameter is 0. + */ + ret = gxio_trio_init_pio_region_aux(trio_context, + trio_context->pio_cfg_index[mac], + mac, 0, HV_TRIO_PIO_FLAG_CONFIG_SPACE); + if (ret < 0) { + pr_err("PCI: PCI CFG PIO init failure for mac %d " + "on TRIO %d, give up\n", mac, trio_index); + + continue; + } + + offset = HV_TRIO_PIO_OFFSET(trio_context->pio_cfg_index[mac]) | + (((unsigned long long)mac) << + TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT); + +#endif + + trio_context->mmio_base_pio_cfg[mac] = + iorpc_ioremap(trio_context->fd, offset, + (1 << TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR__MAC_SHIFT)); + if (trio_context->mmio_base_pio_cfg[mac] == NULL) { + pr_err("PCI: PIO map failure for mac %d on TRIO %d\n", + mac, trio_index); + + continue; + } + + /* + * Initialize the PCIe interrupts. + */ + if (tile_init_irqs(controller)) { + pr_err("PCI: IRQs init failure for mac %d on TRIO %d\n", + mac, trio_index); + + continue; + } + + /* + * The PCI memory resource is located above the PA space. + * The memory range for the PCI root bus should not overlap + * with the physical RAM + */ + pci_add_resource_offset(&resources, &controller->mem_space, + controller->mem_offset); + + controller->first_busno = next_busno; + bus = pci_scan_root_bus(NULL, next_busno, controller->ops, + controller, &resources); + controller->root_bus = bus; + next_busno = bus->subordinate + 1; + + } + + /* Do machine dependent PCI interrupt routing */ + pci_fixup_irqs(pci_common_swizzle, tile_map_irq); + + /* + * This comes from the generic Linux PCI driver. + * + * It allocates all of the resources (I/O memory, etc) + * associated with the devices read in above. + */ + + pci_assign_unassigned_resources(); + + /* Record the I/O resources in the PCI controller structure. */ + for (i = 0; i < num_rc_controllers; i++) { + struct pci_controller *controller = &pci_controllers[i]; + gxio_trio_context_t *trio_context = controller->trio; + struct pci_bus *root_bus = pci_controllers[i].root_bus; + struct pci_bus *next_bus; + uint32_t bus_address_hi; + struct pci_dev *dev; + int ret; + int j; + + /* + * Skip controllers that are not properly initialized or + * have down links. + */ + if (root_bus == NULL) + continue; + + /* Configure the max_payload_size values for this domain. */ + fixup_read_and_payload_sizes(controller); + + list_for_each_entry(dev, &root_bus->devices, bus_list) { + /* Find the PCI host controller, ie. the 1st bridge. */ + if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && + (PCI_SLOT(dev->devfn) == 0)) { + next_bus = dev->subordinate; + pci_controllers[i].mem_resources[0] = + *next_bus->resource[0]; + pci_controllers[i].mem_resources[1] = + *next_bus->resource[1]; + pci_controllers[i].mem_resources[2] = + *next_bus->resource[2]; + + break; + } + } + + if (pci_controllers[i].mem_resources[1].flags & IORESOURCE_MEM) + bus_address_hi = + pci_controllers[i].mem_resources[1].start >> 32; + else if (pci_controllers[i].mem_resources[2].flags & IORESOURCE_PREFETCH) + bus_address_hi = + pci_controllers[i].mem_resources[2].start >> 32; + else { + /* This is unlikely. */ + pr_err("PCI: no memory resources on TRIO %d mac %d\n", + controller->trio_index, controller->mac); + continue; + } + + /* + * Alloc a PIO region for PCI memory access for each RC port. + */ + ret = gxio_trio_alloc_pio_regions(trio_context, 1, 0, 0); + if (ret < 0) { + pr_err("PCI: MEM PIO alloc failure on TRIO %d mac %d, " + "give up\n", controller->trio_index, + controller->mac); + + continue; + } + + controller->pio_mem_index = ret; + + /* + * For PIO MEM, the bus_address_hi parameter is hard-coded 0 + * because we always assign 32-bit PCI bus BAR ranges. + */ + ret = gxio_trio_init_pio_region_aux(trio_context, + controller->pio_mem_index, + controller->mac, + 0, + 0); + if (ret < 0) { + pr_err("PCI: MEM PIO init failure on TRIO %d mac %d, " + "give up\n", controller->trio_index, + controller->mac); + + continue; + } + + /* + * Configure a Mem-Map region for each memory controller so + * that Linux can map all of its PA space to the PCI bus. + * Use the IOMMU to handle hash-for-home memory. + */ + for_each_online_node(j) { + unsigned long start_pfn = node_start_pfn[j]; + unsigned long end_pfn = node_end_pfn[j]; + unsigned long nr_pages = end_pfn - start_pfn; + + ret = gxio_trio_alloc_memory_maps(trio_context, 1, 0, + 0); + if (ret < 0) { + pr_err("PCI: Mem-Map alloc failure on TRIO %d " + "mac %d for MC %d, give up\n", + controller->trio_index, + controller->mac, j); + + goto alloc_mem_map_failed; + } + + controller->mem_maps[j] = ret; + + /* + * Initialize the Mem-Map and the I/O MMU so that all + * the physical memory can be accessed by the endpoint + * devices. The base bus address is set to the base CPA + * of this memory controller plus an offset (see pci.h). + * The region's base VA is set to the base CPA. The + * I/O MMU table essentially translates the CPA to + * the real PA. Implicitly, for node 0, we create + * a separate Mem-Map region that serves as the inbound + * window for legacy 32-bit devices. This is a direct + * map of the low 4GB CPA space. + */ + ret = gxio_trio_init_memory_map_mmu_aux(trio_context, + controller->mem_maps[j], + start_pfn << PAGE_SHIFT, + nr_pages << PAGE_SHIFT, + trio_context->asid, + controller->mac, + (start_pfn << PAGE_SHIFT) + + TILE_PCI_MEM_MAP_BASE_OFFSET, + j, + GXIO_TRIO_ORDER_MODE_UNORDERED); + if (ret < 0) { + pr_err("PCI: Mem-Map init failure on TRIO %d " + "mac %d for MC %d, give up\n", + controller->trio_index, + controller->mac, j); + + goto alloc_mem_map_failed; + } + continue; + +alloc_mem_map_failed: + break; + } + + } + + return 0; +} +subsys_initcall(pcibios_init); + +/* Note: to be deleted after Linux 3.6 merge. */ +void __devinit pcibios_fixup_bus(struct pci_bus *bus) +{ +} + +/* + * This can be called from the generic PCI layer, but doesn't need to + * do anything. + */ +char __devinit *pcibios_setup(char *str) +{ + if (!strcmp(str, "off")) { + pci_probe = 0; + return NULL; + } + return str; +} + +/* + * This is called from the generic Linux layer. + */ +void __devinit pcibios_update_irq(struct pci_dev *dev, int irq) +{ + pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq); +} + +/* + * Enable memory address decoding, as appropriate, for the + * device described by the 'dev' struct. The I/O decoding + * is disabled, though the TILE-Gx supports I/O addressing. + * + * This is called from the generic PCI layer, and can be called + * for bridges or endpoints. + */ +int pcibios_enable_device(struct pci_dev *dev, int mask) +{ + return pci_enable_resources(dev, mask); +} + +/* Called for each device after PCI setup is done. */ +static void __init +pcibios_fixup_final(struct pci_dev *pdev) +{ + set_dma_ops(&pdev->dev, gx_pci_dma_map_ops); + set_dma_offset(&pdev->dev, TILE_PCI_MEM_MAP_BASE_OFFSET); + pdev->dev.archdata.max_direct_dma_addr = + TILE_PCI_MAX_DIRECT_DMA_ADDRESS; +} +DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_final); + +/* Map a PCI MMIO bus address into VA space. */ +void __iomem *ioremap(resource_size_t phys_addr, unsigned long size) +{ + struct pci_controller *controller = NULL; + resource_size_t bar_start; + resource_size_t bar_end; + resource_size_t offset; + resource_size_t start; + resource_size_t end; + int trio_fd; + int i, j; + + start = phys_addr; + end = phys_addr + size - 1; + + /* + * In the following, each PCI controller's mem_resources[1] + * represents its (non-prefetchable) PCI memory resource and + * mem_resources[2] refers to its prefetchable PCI memory resource. + * By searching phys_addr in each controller's mem_resources[], we can + * determine the controller that should accept the PCI memory access. + */ + + for (i = 0; i < num_rc_controllers; i++) { + /* + * Skip controllers that are not properly initialized or + * have down links. + */ + if (pci_controllers[i].root_bus == NULL) + continue; + + for (j = 1; j < 3; j++) { + bar_start = + pci_controllers[i].mem_resources[j].start; + bar_end = + pci_controllers[i].mem_resources[j].end; + + if ((start >= bar_start) && (end <= bar_end)) { + + controller = &pci_controllers[i]; + + goto got_it; + } + } + } + + if (controller == NULL) + return NULL; + +got_it: + trio_fd = controller->trio->fd; + + /* Convert the resource start to the bus address offset. */ + start = phys_addr - controller->mem_offset; + + offset = HV_TRIO_PIO_OFFSET(controller->pio_mem_index) + start; + + /* + * We need to keep the PCI bus address's in-page offset in the VA. + */ + return iorpc_ioremap(trio_fd, offset, size) + + (phys_addr & (PAGE_SIZE - 1)); +} +EXPORT_SYMBOL(ioremap); + +void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ + iounmap(addr); +} +EXPORT_SYMBOL(pci_iounmap); + +/**************************************************************** + * + * Tile PCI config space read/write routines + * + ****************************************************************/ + +/* + * These are the normal read and write ops + * These are expanded with macros from pci_bus_read_config_byte() etc. + * + * devfn is the combined PCI device & function. + * + * offset is in bytes, from the start of config space for the + * specified bus & device. + */ + +static int __devinit tile_cfg_read(struct pci_bus *bus, + unsigned int devfn, + int offset, + int size, + u32 *val) +{ + struct pci_controller *controller = bus->sysdata; + gxio_trio_context_t *trio_context = controller->trio; + int busnum = bus->number & 0xff; + int device = PCI_SLOT(devfn); + int function = PCI_FUNC(devfn); + int config_type = 1; + TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR_t cfg_addr; + void *mmio_addr; + + /* + * Map all accesses to the local device on root bus into the + * MMIO space of the MAC. Accesses to the downstream devices + * go to the PIO space. + */ + if (pci_is_root_bus(bus)) { + if (device == 0) { + /* + * This is the internal downstream P2P bridge, + * access directly. + */ + unsigned int reg_offset; + + reg_offset = ((offset & 0xFFF) << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_PROTECTED + << TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (controller->mac << + TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + mmio_addr = trio_context->mmio_base_mac + reg_offset; + + goto valid_device; + + } else { + /* + * We fake an empty device for (device > 0), + * since there is only one device on bus 0. + */ + goto invalid_device; + } + } + + /* + * Accesses to the directly attached device have to be + * sent as type-0 configs. + */ + + if (busnum == (controller->first_busno + 1)) { + /* + * There is only one device off of our built-in P2P bridge. + */ + if (device != 0) + goto invalid_device; + + config_type = 0; + } + + cfg_addr.word = 0; + cfg_addr.reg_addr = (offset & 0xFFF); + cfg_addr.fn = function; + cfg_addr.dev = device; + cfg_addr.bus = busnum; + cfg_addr.type = config_type; + + /* + * Note that we don't set the mac field in cfg_addr because the + * mapping is per port. + */ + + mmio_addr = trio_context->mmio_base_pio_cfg[controller->mac] + + cfg_addr.word; + +valid_device: + + switch (size) { + case 4: + *val = __gxio_mmio_read32(mmio_addr); + break; + + case 2: + *val = __gxio_mmio_read16(mmio_addr); + break; + + case 1: + *val = __gxio_mmio_read8(mmio_addr); + break; + + default: + return PCIBIOS_FUNC_NOT_SUPPORTED; + } + + TRACE_CFG_RD(size, *val, busnum, device, function, offset); + + return 0; + +invalid_device: + + switch (size) { + case 4: + *val = 0xFFFFFFFF; + break; + + case 2: + *val = 0xFFFF; + break; + + case 1: + *val = 0xFF; + break; + + default: + return PCIBIOS_FUNC_NOT_SUPPORTED; + } + + return 0; +} + + +/* + * See tile_cfg_read() for relevent comments. + * Note that "val" is the value to write, not a pointer to that value. + */ +static int __devinit tile_cfg_write(struct pci_bus *bus, + unsigned int devfn, + int offset, + int size, + u32 val) +{ + struct pci_controller *controller = bus->sysdata; + gxio_trio_context_t *trio_context = controller->trio; + int busnum = bus->number & 0xff; + int device = PCI_SLOT(devfn); + int function = PCI_FUNC(devfn); + int config_type = 1; + TRIO_TILE_PIO_REGION_SETUP_CFG_ADDR_t cfg_addr; + void *mmio_addr; + u32 val_32 = (u32)val; + u16 val_16 = (u16)val; + u8 val_8 = (u8)val; + + /* + * Map all accesses to the local device on root bus into the + * MMIO space of the MAC. Accesses to the downstream devices + * go to the PIO space. + */ + if (pci_is_root_bus(bus)) { + if (device == 0) { + /* + * This is the internal downstream P2P bridge, + * access directly. + */ + unsigned int reg_offset; + + reg_offset = ((offset & 0xFFF) << + TRIO_CFG_REGION_ADDR__REG_SHIFT) | + (TRIO_CFG_REGION_ADDR__INTFC_VAL_MAC_PROTECTED + << TRIO_CFG_REGION_ADDR__INTFC_SHIFT ) | + (controller->mac << + TRIO_CFG_REGION_ADDR__MAC_SEL_SHIFT); + + mmio_addr = trio_context->mmio_base_mac + reg_offset; + + goto valid_device; + + } else { + /* + * We fake an empty device for (device > 0), + * since there is only one device on bus 0. + */ + goto invalid_device; + } + } + + /* + * Accesses to the directly attached device have to be + * sent as type-0 configs. + */ + + if (busnum == (controller->first_busno + 1)) { + /* + * There is only one device off of our built-in P2P bridge. + */ + if (device != 0) + goto invalid_device; + + config_type = 0; + } + + cfg_addr.word = 0; + cfg_addr.reg_addr = (offset & 0xFFF); + cfg_addr.fn = function; + cfg_addr.dev = device; + cfg_addr.bus = busnum; + cfg_addr.type = config_type; + + /* + * Note that we don't set the mac field in cfg_addr because the + * mapping is per port. + */ + + mmio_addr = trio_context->mmio_base_pio_cfg[controller->mac] + + cfg_addr.word; + +valid_device: + + switch (size) { + case 4: + __gxio_mmio_write32(mmio_addr, val_32); + TRACE_CFG_WR(size, val_32, busnum, device, function, offset); + break; + + case 2: + __gxio_mmio_write16(mmio_addr, val_16); + TRACE_CFG_WR(size, val_16, busnum, device, function, offset); + break; + + case 1: + __gxio_mmio_write8(mmio_addr, val_8); + TRACE_CFG_WR(size, val_8, busnum, device, function, offset); + break; + + default: + return PCIBIOS_FUNC_NOT_SUPPORTED; + } + +invalid_device: + + return 0; +} + + +static struct pci_ops tile_cfg_ops = { + .read = tile_cfg_read, + .write = tile_cfg_write, +}; + + +/* + * MSI support starts here. + */ +static unsigned int +tilegx_msi_startup(struct irq_data *d) +{ + if (d->msi_desc) + unmask_msi_irq(d); + + return 0; +} + +static void +tilegx_msi_ack(struct irq_data *d) +{ + __insn_mtspr(SPR_IPI_EVENT_RESET_K, 1UL << d->irq); +} + +static void +tilegx_msi_mask(struct irq_data *d) +{ + mask_msi_irq(d); + __insn_mtspr(SPR_IPI_MASK_SET_K, 1UL << d->irq); +} + +static void +tilegx_msi_unmask(struct irq_data *d) +{ + __insn_mtspr(SPR_IPI_MASK_RESET_K, 1UL << d->irq); + unmask_msi_irq(d); +} + +static struct irq_chip tilegx_msi_chip = { + .name = "tilegx_msi", + .irq_startup = tilegx_msi_startup, + .irq_ack = tilegx_msi_ack, + .irq_mask = tilegx_msi_mask, + .irq_unmask = tilegx_msi_unmask, + + /* TBD: support set_affinity. */ +}; + +int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) +{ + struct pci_controller *controller; + gxio_trio_context_t *trio_context; + struct msi_msg msg; + int default_irq; + uint64_t mem_map_base; + uint64_t mem_map_limit; + u64 msi_addr; + int mem_map; + int cpu; + int irq; + int ret; + + irq = create_irq(); + if (irq < 0) + return irq; + + /* + * Since we use a 64-bit Mem-Map to accept the MSI write, we fail + * devices that are not capable of generating a 64-bit message address. + * These devices will fall back to using the legacy interrupts. + * Most PCIe endpoint devices do support 64-bit message addressing. + */ + if (desc->msi_attrib.is_64 == 0) { + dev_printk(KERN_INFO, &pdev->dev, + "64-bit MSI message address not supported, " + "falling back to legacy interrupts.\n"); + + ret = -ENOMEM; + goto is_64_failure; + } + + default_irq = desc->msi_attrib.default_irq; + controller = irq_get_handler_data(default_irq); + + BUG_ON(!controller); + + trio_context = controller->trio; + + /* + * Allocate the Mem-Map that will accept the MSI write and + * trigger the TILE-side interrupts. + */ + mem_map = gxio_trio_alloc_memory_maps(trio_context, 1, 0, 0); + if (mem_map < 0) { + dev_printk(KERN_INFO, &pdev->dev, + "%s Mem-Map alloc failure. " + "Failed to initialize MSI interrupts. " + "Falling back to legacy interrupts.\n", + desc->msi_attrib.is_msix ? "MSI-X" : "MSI"); + + ret = -ENOMEM; + goto msi_mem_map_alloc_failure; + } + + /* We try to distribute different IRQs to different tiles. */ + cpu = tile_irq_cpu(irq); + + /* + * Now call up to the HV to configure the Mem-Map interrupt and + * set up the IPI binding. + */ + mem_map_base = MEM_MAP_INTR_REGIONS_BASE + + mem_map * MEM_MAP_INTR_REGION_SIZE; + mem_map_limit = mem_map_base + MEM_MAP_INTR_REGION_SIZE - 1; + + ret = gxio_trio_config_msi_intr(trio_context, cpu_x(cpu), cpu_y(cpu), + KERNEL_PL, irq, controller->mac, + mem_map, mem_map_base, mem_map_limit, + trio_context->asid); + if (ret < 0) { + dev_printk(KERN_INFO, &pdev->dev, "HV MSI config failed.\n"); + + goto hv_msi_config_failure; + } + + irq_set_msi_desc(irq, desc); + + msi_addr = mem_map_base + TRIO_MAP_MEM_REG_INT3 - TRIO_MAP_MEM_REG_INT0; + + msg.address_hi = msi_addr >> 32; + msg.address_lo = msi_addr & 0xffffffff; + + msg.data = mem_map; + + write_msi_msg(irq, &msg); + irq_set_chip_and_handler(irq, &tilegx_msi_chip, handle_level_irq); + irq_set_handler_data(irq, controller); + + return 0; + +hv_msi_config_failure: + /* Free mem-map */ +msi_mem_map_alloc_failure: +is_64_failure: + destroy_irq(irq); + return ret; +} + +void arch_teardown_msi_irq(unsigned int irq) +{ + destroy_irq(irq); +} diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index dd87f34..6a649a4 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -23,6 +23,7 @@ #include <linux/irq.h> #include <linux/kexec.h> #include <linux/pci.h> +#include <linux/swiotlb.h> #include <linux/initrd.h> #include <linux/io.h> #include <linux/highmem.h> @@ -109,7 +110,7 @@ static unsigned int __initdata maxnodemem_pfn[MAX_NUMNODES] = { }; static nodemask_t __initdata isolnodes; -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) enum { DEFAULT_PCI_RESERVE_MB = 64 }; static unsigned int __initdata pci_reserve_mb = DEFAULT_PCI_RESERVE_MB; unsigned long __initdata pci_reserve_start_pfn = -1U; @@ -160,7 +161,7 @@ static int __init setup_isolnodes(char *str) } early_param("isolnodes", setup_isolnodes); -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) static int __init setup_pci_reserve(char* str) { unsigned long mb; @@ -171,7 +172,7 @@ static int __init setup_pci_reserve(char* str) pci_reserve_mb = mb; pr_info("Reserving %dMB for PCIE root complex mappings\n", - pci_reserve_mb); + pci_reserve_mb); return 0; } early_param("pci_reserve", setup_pci_reserve); @@ -411,7 +412,7 @@ static void __init setup_memory(void) continue; } #endif -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) /* * Blocks that overlap the pci reserved region must * have enough space to hold the maximum percpu data @@ -604,11 +605,9 @@ static void __init setup_bootmem_allocator_node(int i) /* Free all the space back into the allocator. */ free_bootmem(PFN_PHYS(start), PFN_PHYS(end - start)); -#if defined(CONFIG_PCI) +#if defined(CONFIG_PCI) && !defined(__tilegx__) /* - * Throw away any memory aliased by the PCI region. FIXME: this - * is a temporary hack to work around bug 10502, and needs to be - * fixed properly. + * Throw away any memory aliased by the PCI region. */ if (pci_reserve_start_pfn < end && pci_reserve_end_pfn > start) reserve_bootmem(PFN_PHYS(pci_reserve_start_pfn), @@ -658,6 +657,8 @@ static void __init zone_sizes_init(void) unsigned long zones_size[MAX_NR_ZONES] = { 0 }; int size = percpu_size(); int num_cpus = smp_height * smp_width; + const unsigned long dma_end = (1UL << (32 - PAGE_SHIFT)); + int i; for (i = 0; i < num_cpus; ++i) @@ -729,6 +730,14 @@ static void __init zone_sizes_init(void) zones_size[ZONE_NORMAL] = end - start; #endif + if (start < dma_end) { + zones_size[ZONE_DMA] = min(zones_size[ZONE_NORMAL], + dma_end - start); + zones_size[ZONE_NORMAL] -= zones_size[ZONE_DMA]; + } else { + zones_size[ZONE_DMA] = 0; + } + /* Take zone metadata from controller 0 if we're isolnode. */ if (node_isset(i, isolnodes)) NODE_DATA(i)->bdata = &bootmem_node_data[0]; @@ -738,7 +747,7 @@ static void __init zone_sizes_init(void) PFN_UP(node_percpu[i])); /* Track the type of memory on each node */ - if (zones_size[ZONE_NORMAL]) + if (zones_size[ZONE_NORMAL] || zones_size[ZONE_DMA]) node_set_state(i, N_NORMAL_MEMORY); #ifdef CONFIG_HIGHMEM if (end != start) @@ -1343,7 +1352,7 @@ void __init setup_arch(char **cmdline_p) setup_cpu_maps(); -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) /* * Initialize the PCI structures. This is done before memory * setup so that we know whether or not a pci_reserve region @@ -1372,6 +1381,10 @@ void __init setup_arch(char **cmdline_p) * any memory using the bootmem allocator. */ +#ifdef CONFIG_SWIOTLB + swiotlb_init(0); +#endif + paging_init(); setup_numa_mapping(); zone_sizes_init(); @@ -1522,11 +1535,10 @@ static struct resource code_resource = { }; /* - * We reserve all resources above 4GB so that PCI won't try to put - * mappings above 4GB; the standard allows that for some devices but - * the probing code trunates values to 32 bits. + * On Pro, we reserve all resources above 4GB so that PCI won't try to put + * mappings above 4GB. */ -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) static struct resource* __init insert_non_bus_resource(void) { @@ -1571,8 +1583,7 @@ static int __init request_standard_resources(void) int i; enum { CODE_DELTA = MEM_SV_INTRPT - PAGE_OFFSET }; - iomem_resource.end = -1LL; -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) insert_non_bus_resource(); #endif @@ -1580,7 +1591,7 @@ static int __init request_standard_resources(void) u64 start_pfn = node_start_pfn[i]; u64 end_pfn = node_end_pfn[i]; -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && !defined(__tilegx__) if (start_pfn <= pci_reserve_start_pfn && end_pfn > pci_reserve_start_pfn) { if (end_pfn > pci_reserve_end_pfn) diff --git a/arch/tile/kernel/usb.c b/arch/tile/kernel/usb.c new file mode 100644 index 0000000..5af8deb --- /dev/null +++ b/arch/tile/kernel/usb.c @@ -0,0 +1,69 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * 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, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + * + * Register the Tile-Gx USB interfaces as platform devices. + * + * The actual USB driver is just some glue (in + * drivers/usb/host/[eo]hci-tilegx.c) which makes the registers available + * to the standard kernel EHCI and OHCI drivers. + */ + +#include <linux/dma-mapping.h> +#include <linux/platform_device.h> +#include <linux/usb/tilegx.h> +#include <linux/types.h> + +static u64 ehci_dmamask = DMA_BIT_MASK(32); + +#define USB_HOST_DEF(unit, type, dmamask) \ + static struct \ + tilegx_usb_platform_data tilegx_usb_platform_data_ ## type ## \ + hci ## unit = { \ + .dev_index = unit, \ + }; \ + \ + static struct platform_device tilegx_usb_ ## type ## hci ## unit = { \ + .name = "tilegx-" #type "hci", \ + .id = unit, \ + .dev = { \ + .dma_mask = dmamask, \ + .coherent_dma_mask = DMA_BIT_MASK(32), \ + .platform_data = \ + &tilegx_usb_platform_data_ ## type ## hci ## \ + unit, \ + }, \ + }; + +USB_HOST_DEF(0, e, &ehci_dmamask) +USB_HOST_DEF(0, o, NULL) +USB_HOST_DEF(1, e, &ehci_dmamask) +USB_HOST_DEF(1, o, NULL) + +#undef USB_HOST_DEF + +static struct platform_device *tilegx_usb_devices[] __initdata = { + &tilegx_usb_ehci0, + &tilegx_usb_ehci1, + &tilegx_usb_ohci0, + &tilegx_usb_ohci1, +}; + +/** Add our set of possible USB devices. */ +static int __init tilegx_usb_init(void) +{ + platform_add_devices(tilegx_usb_devices, + ARRAY_SIZE(tilegx_usb_devices)); + + return 0; +} +arch_initcall(tilegx_usb_init); diff --git a/arch/tile/lib/checksum.c b/arch/tile/lib/checksum.c index e4bab5b..c3ca3e6 100644 --- a/arch/tile/lib/checksum.c +++ b/arch/tile/lib/checksum.c @@ -16,19 +16,6 @@ #include <net/checksum.h> #include <linux/module.h> -static inline unsigned int longto16(unsigned long x) -{ - unsigned long ret; -#ifdef __tilegx__ - ret = __insn_v2sadu(x, 0); - ret = __insn_v2sadu(ret, 0); -#else - ret = __insn_sadh_u(x, 0); - ret = __insn_sadh_u(ret, 0); -#endif - return ret; -} - __wsum do_csum(const unsigned char *buff, int len) { int odd, count; @@ -94,7 +81,7 @@ __wsum do_csum(const unsigned char *buff, int len) } if (len & 1) result += *buff; - result = longto16(result); + result = csum_long(result); if (odd) result = swab16(result); out: diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c index dbcbdf7..5f7868d 100644 --- a/arch/tile/mm/homecache.c +++ b/arch/tile/mm/homecache.c @@ -64,10 +64,6 @@ early_param("noallocl2", set_noallocl2); #endif -/* Provide no-op versions of these routines to keep flush_remote() cleaner. */ -#define mark_caches_evicted_start() 0 -#define mark_caches_evicted_finish(mask, timestamp) do {} while (0) - /* * Update the irq_stat for cpus that we are going to interrupt @@ -107,7 +103,6 @@ static void hv_flush_update(const struct cpumask *cache_cpumask, * there's never any good reason for hv_flush_remote() to fail. * - Accepts a 32-bit PFN rather than a 64-bit PA, which generally * is the type that Linux wants to pass around anyway. - * - Centralizes the mark_caches_evicted() handling. * - Canonicalizes that lengths of zero make cpumasks NULL. * - Handles deferring TLB flushes for dataplane tiles. * - Tracks remote interrupts in the per-cpu irq_cpustat_t. @@ -126,7 +121,6 @@ void flush_remote(unsigned long cache_pfn, unsigned long cache_control, HV_Remote_ASID *asids, int asidcount) { int rc; - int timestamp = 0; /* happy compiler */ struct cpumask cache_cpumask_copy, tlb_cpumask_copy; struct cpumask *cache_cpumask, *tlb_cpumask; HV_PhysAddr cache_pa; @@ -157,15 +151,11 @@ void flush_remote(unsigned long cache_pfn, unsigned long cache_control, hv_flush_update(cache_cpumask, tlb_cpumask, tlb_va, tlb_length, asids, asidcount); cache_pa = (HV_PhysAddr)cache_pfn << PAGE_SHIFT; - if (cache_control & HV_FLUSH_EVICT_L2) - timestamp = mark_caches_evicted_start(); rc = hv_flush_remote(cache_pa, cache_control, cpumask_bits(cache_cpumask), tlb_va, tlb_length, tlb_pgsize, cpumask_bits(tlb_cpumask), asids, asidcount); - if (cache_control & HV_FLUSH_EVICT_L2) - mark_caches_evicted_finish(cache_cpumask, timestamp); if (rc == 0) return; cpumask_scnprintf(cache_buf, sizeof(cache_buf), &cache_cpumask_copy); @@ -180,85 +170,86 @@ void flush_remote(unsigned long cache_pfn, unsigned long cache_control, panic("Unsafe to continue."); } -void flush_remote_page(struct page *page, int order) +static void homecache_finv_page_va(void* va, int home) { - int i, pages = (1 << order); - for (i = 0; i < pages; ++i, ++page) { - void *p = kmap_atomic(page); - int hfh = 0; - int home = page_home(page); -#if CHIP_HAS_CBOX_HOME_MAP() - if (home == PAGE_HOME_HASH) - hfh = 1; - else -#endif - BUG_ON(home < 0 || home >= NR_CPUS); - finv_buffer_remote(p, PAGE_SIZE, hfh); - kunmap_atomic(p); + if (home == smp_processor_id()) { + finv_buffer_local(va, PAGE_SIZE); + } else if (home == PAGE_HOME_HASH) { + finv_buffer_remote(va, PAGE_SIZE, 1); + } else { + BUG_ON(home < 0 || home >= NR_CPUS); + finv_buffer_remote(va, PAGE_SIZE, 0); } } -void homecache_evict(const struct cpumask *mask) +void homecache_finv_map_page(struct page *page, int home) { - flush_remote(0, HV_FLUSH_EVICT_L2, mask, 0, 0, 0, NULL, NULL, 0); + unsigned long flags; + unsigned long va; + pte_t *ptep; + pte_t pte; + + if (home == PAGE_HOME_UNCACHED) + return; + local_irq_save(flags); +#ifdef CONFIG_HIGHMEM + va = __fix_to_virt(FIX_KMAP_BEGIN + kmap_atomic_idx_push() + + (KM_TYPE_NR * smp_processor_id())); +#else + va = __fix_to_virt(FIX_HOMECACHE_BEGIN + smp_processor_id()); +#endif + ptep = virt_to_pte(NULL, (unsigned long)va); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); + __set_pte(ptep, pte_set_home(pte, home)); + homecache_finv_page_va((void *)va, home); + __pte_clear(ptep); + hv_flush_page(va, PAGE_SIZE); +#ifdef CONFIG_HIGHMEM + kmap_atomic_idx_pop(); +#endif + local_irq_restore(flags); } -/* - * Return a mask of the cpus whose caches currently own these pages. - * The return value is whether the pages are all coherently cached - * (i.e. none are immutable, incoherent, or uncached). - */ -static int homecache_mask(struct page *page, int pages, - struct cpumask *home_mask) +static void homecache_finv_page_home(struct page *page, int home) { - int i; - int cached_coherently = 1; - cpumask_clear(home_mask); - for (i = 0; i < pages; ++i) { - int home = page_home(&page[i]); - if (home == PAGE_HOME_IMMUTABLE || - home == PAGE_HOME_INCOHERENT) { - cpumask_copy(home_mask, cpu_possible_mask); - return 0; - } -#if CHIP_HAS_CBOX_HOME_MAP() - if (home == PAGE_HOME_HASH) { - cpumask_or(home_mask, home_mask, &hash_for_home_map); - continue; - } -#endif - if (home == PAGE_HOME_UNCACHED) { - cached_coherently = 0; - continue; - } - BUG_ON(home < 0 || home >= NR_CPUS); - cpumask_set_cpu(home, home_mask); - } - return cached_coherently; + if (!PageHighMem(page) && home == page_home(page)) + homecache_finv_page_va(page_address(page), home); + else + homecache_finv_map_page(page, home); } -/* - * Return the passed length, or zero if it's long enough that we - * believe we should evict the whole L2 cache. - */ -static unsigned long cache_flush_length(unsigned long length) +static inline bool incoherent_home(int home) { - return (length >= CHIP_L2_CACHE_SIZE()) ? HV_FLUSH_EVICT_L2 : length; + return home == PAGE_HOME_IMMUTABLE || home == PAGE_HOME_INCOHERENT; } -/* Flush a page out of whatever cache(s) it is in. */ -void homecache_flush_cache(struct page *page, int order) +static void homecache_finv_page_internal(struct page *page, int force_map) { - int pages = 1 << order; - int length = cache_flush_length(pages * PAGE_SIZE); - unsigned long pfn = page_to_pfn(page); - struct cpumask home_mask; - - homecache_mask(page, pages, &home_mask); - flush_remote(pfn, length, &home_mask, 0, 0, 0, NULL, NULL, 0); - sim_validate_lines_evicted(PFN_PHYS(pfn), pages * PAGE_SIZE); + int home = page_home(page); + if (home == PAGE_HOME_UNCACHED) + return; + if (incoherent_home(home)) { + int cpu; + for_each_cpu(cpu, &cpu_cacheable_map) + homecache_finv_map_page(page, cpu); + } else if (force_map) { + /* Force if, e.g., the normal mapping is migrating. */ + homecache_finv_map_page(page, home); + } else { + homecache_finv_page_home(page, home); + } + sim_validate_lines_evicted(PFN_PHYS(page_to_pfn(page)), PAGE_SIZE); } +void homecache_finv_page(struct page *page) +{ + homecache_finv_page_internal(page, 0); +} + +void homecache_evict(const struct cpumask *mask) +{ + flush_remote(0, HV_FLUSH_EVICT_L2, mask, 0, 0, 0, NULL, NULL, 0); +} /* Report the home corresponding to a given PTE. */ static int pte_to_home(pte_t pte) @@ -441,15 +432,8 @@ struct page *homecache_alloc_pages_node(int nid, gfp_t gfp_mask, return page; } -void homecache_free_pages(unsigned long addr, unsigned int order) +void __homecache_free_pages(struct page *page, unsigned int order) { - struct page *page; - - if (addr == 0) - return; - - VM_BUG_ON(!virt_addr_valid((void *)addr)); - page = virt_to_page((void *)addr); if (put_page_testzero(page)) { homecache_change_page_home(page, order, initial_page_home()); if (order == 0) { @@ -460,3 +444,13 @@ void homecache_free_pages(unsigned long addr, unsigned int order) } } } +EXPORT_SYMBOL(__homecache_free_pages); + +void homecache_free_pages(unsigned long addr, unsigned int order) +{ + if (addr != 0) { + VM_BUG_ON(!virt_addr_valid((void *)addr)); + __homecache_free_pages(virt_to_page((void *)addr), order); + } +} +EXPORT_SYMBOL(homecache_free_pages); diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index 630dd2c..ef29d6c 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -150,7 +150,21 @@ void __init shatter_pmd(pmd_t *pmd) assign_pte(pmd, pte); } -#ifdef CONFIG_HIGHMEM +#ifdef __tilegx__ +static pmd_t *__init get_pmd(pgd_t pgtables[], unsigned long va) +{ + pud_t *pud = pud_offset(&pgtables[pgd_index(va)], va); + if (pud_none(*pud)) + assign_pmd(pud, alloc_pmd()); + return pmd_offset(pud, va); +} +#else +static pmd_t *__init get_pmd(pgd_t pgtables[], unsigned long va) +{ + return pmd_offset(pud_offset(&pgtables[pgd_index(va)], va), va); +} +#endif + /* * This function initializes a certain range of kernel virtual memory * with new bootmem page tables, everywhere page tables are missing in @@ -163,24 +177,17 @@ void __init shatter_pmd(pmd_t *pmd) * checking the pgd every time. */ static void __init page_table_range_init(unsigned long start, - unsigned long end, pgd_t *pgd_base) + unsigned long end, pgd_t *pgd) { - pgd_t *pgd; - int pgd_idx; unsigned long vaddr; - - vaddr = start; - pgd_idx = pgd_index(vaddr); - pgd = pgd_base + pgd_idx; - - for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) { - pmd_t *pmd = pmd_offset(pud_offset(pgd, vaddr), vaddr); + start = round_down(start, PMD_SIZE); + end = round_up(end, PMD_SIZE); + for (vaddr = start; vaddr < end; vaddr += PMD_SIZE) { + pmd_t *pmd = get_pmd(pgd, vaddr); if (pmd_none(*pmd)) assign_pte(pmd, alloc_pte()); - vaddr += PMD_SIZE; } } -#endif /* CONFIG_HIGHMEM */ #if CHIP_HAS_CBOX_HOME_MAP() @@ -404,21 +411,6 @@ static inline pgprot_t ktext_set_nocache(pgprot_t prot) return prot; } -#ifndef __tilegx__ -static pmd_t *__init get_pmd(pgd_t pgtables[], unsigned long va) -{ - return pmd_offset(pud_offset(&pgtables[pgd_index(va)], va), va); -} -#else -static pmd_t *__init get_pmd(pgd_t pgtables[], unsigned long va) -{ - pud_t *pud = pud_offset(&pgtables[pgd_index(va)], va); - if (pud_none(*pud)) - assign_pmd(pud, alloc_pmd()); - return pmd_offset(pud, va); -} -#endif - /* Temporary page table we use for staging. */ static pgd_t pgtables[PTRS_PER_PGD] __attribute__((aligned(HV_PAGE_TABLE_ALIGN))); @@ -741,16 +733,15 @@ static void __init set_non_bootmem_pages_init(void) for_each_zone(z) { unsigned long start, end; int nid = z->zone_pgdat->node_id; +#ifdef CONFIG_HIGHMEM int idx = zone_idx(z); +#endif start = z->zone_start_pfn; - if (start == 0) - continue; /* bootmem */ end = start + z->spanned_pages; - if (idx == ZONE_NORMAL) { - BUG_ON(start != node_start_pfn[nid]); - start = node_free_pfn[nid]; - } + start = max(start, node_free_pfn[nid]); + start = max(start, max_low_pfn); + #ifdef CONFIG_HIGHMEM if (idx == ZONE_HIGHMEM) totalhigh_pages += z->spanned_pages; @@ -779,9 +770,6 @@ static void __init set_non_bootmem_pages_init(void) */ void __init paging_init(void) { -#ifdef CONFIG_HIGHMEM - unsigned long vaddr, end; -#endif #ifdef __tilegx__ pud_t *pud; #endif @@ -789,14 +777,14 @@ void __init paging_init(void) kernel_physical_mapping_init(pgd_base); -#ifdef CONFIG_HIGHMEM /* * Fixed mappings, only the page table structure has to be * created - mappings will be set by set_fixmap(): */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK; - page_table_range_init(vaddr, end, pgd_base); + page_table_range_init(fix_to_virt(__end_of_fixed_addresses - 1), + FIXADDR_TOP, pgd_base); + +#ifdef CONFIG_HIGHMEM permanent_kmaps_init(pgd_base); #endif diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index 345edfe..de0de0c 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -575,13 +575,6 @@ void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, } EXPORT_SYMBOL(ioremap_prot); -/* Map a PCI MMIO bus address into VA space. */ -void __iomem *ioremap(resource_size_t phys_addr, unsigned long size) -{ - panic("ioremap for PCI MMIO is not supported"); -} -EXPORT_SYMBOL(ioremap); - /* Unmap an MMIO VA mapping. */ void iounmap(volatile void __iomem *addr_in) { diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 0d60c56..458d324 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -339,7 +339,7 @@ static int setup_etheraddr(char *str, unsigned char *addr, char *name) random: printk(KERN_INFO "Choosing a random ethernet address for device %s\n", name); - random_ether_addr(addr); + eth_random_addr(addr); return 1; } diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 03c9ff8..b0a4743 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -238,7 +238,6 @@ config I2C_BATTERY_BQ27200 config I2C_EEPROM_AT24 tristate "I2C EEPROMs AT24 support" select I2C_PUV3 - select MISC_DEVICES select EEPROM_AT24 config LCD_BACKLIGHT diff --git a/arch/unicore32/kernel/pci.c b/arch/unicore32/kernel/pci.c index 2fc2b1b..46cb6c9 100644 --- a/arch/unicore32/kernel/pci.c +++ b/arch/unicore32/kernel/pci.c @@ -296,7 +296,7 @@ static int __init pci_common_init(void) } subsys_initcall(pci_common_init); -char * __devinit pcibios_setup(char *str) +char * __init pcibios_setup(char *str) { if (!strcmp(str, "debug")) { debug_pci = 1; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 88093c1..3ea51a8 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -465,6 +465,8 @@ static inline u32 safe_apic_wait_icr_idle(void) return apic->safe_wait_icr_idle(); } +extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)); + #else /* CONFIG_X86_LOCAL_APIC */ static inline u32 apic_read(u32 reg) { return 0; } @@ -474,6 +476,7 @@ static inline u64 apic_icr_read(void) { return 0; } static inline void apic_icr_write(u32 low, u32 high) { } static inline void apic_wait_icr_idle(void) { } static inline u32 safe_apic_wait_icr_idle(void) { return 0; } +static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {} #endif /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index a6983b2..72f5009 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -264,6 +264,13 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) * This operation is non-atomic and can be reordered. * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. + * + * Note: the operation is performed atomically with respect to + * the local CPU, but not other CPUs. Portable code should not + * rely on this behaviour. + * KVM relies on this behaviour on x86 for modifying memory that is also + * accessed from a hypervisor on the same CPU if running in a VM: don't change + * this without also updating arch/x86/kernel/kvm.c */ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) { diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 7a15153..b518c75 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -49,6 +49,7 @@ extern const struct hypervisor_x86 *x86_hyper; extern const struct hypervisor_x86 x86_hyper_vmware; 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) { diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index dffc38e..345c99c 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -5,7 +5,6 @@ extern struct dma_map_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; extern int iommu_pass_through; -extern int iommu_group_mf; /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index e7d1c19..246617e 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -12,6 +12,7 @@ /* Select x86 specific features in <linux/kvm.h> */ #define __KVM_HAVE_PIT #define __KVM_HAVE_IOAPIC +#define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_DEVICE_ASSIGNMENT #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 1ac46c22..c764f43 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -192,8 +192,8 @@ struct x86_emulate_ops { struct x86_instruction_info *info, enum x86_intercept_stage stage); - bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); + void (*get_cpuid)(struct x86_emulate_ctxt *ctxt, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); }; typedef u32 __attribute__((vector_size(16))) sse128_t; @@ -280,9 +280,9 @@ struct x86_emulate_ctxt { u8 modrm_seg; bool rip_relative; unsigned long _eip; + struct operand memop; /* Fields above regs are cleared together. */ unsigned long regs[NR_VCPU_REGS]; - struct operand memop; struct operand *memopp; struct fetch_cache fetch; struct read_cache io_read; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2da88c0..09155d6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -48,12 +48,13 @@ #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) +#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ 0xFFFFFF0000000000ULL) #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ - | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ + | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_RDWRGSFS \ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) @@ -175,6 +176,13 @@ enum { /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 +/* + * The following bit is set with PV-EOI, unset on EOI. + * We detect PV-EOI changes by guest by comparing + * this bit with PV-EOI in guest memory. + * See the implementation in apic_update_pv_eoi. + */ +#define KVM_APIC_PV_EOI_PENDING 1 /* * We don't want allocation failures within the mmu code, so we preallocate @@ -484,6 +492,11 @@ struct kvm_vcpu_arch { u64 length; u64 status; } osvw; + + struct { + u64 msr_val; + struct gfn_to_hva_cache data; + } pv_eoi; }; struct kvm_lpage_info { @@ -661,6 +674,7 @@ struct kvm_x86_ops { u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); + bool (*invpcid_supported)(void); void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -802,7 +816,20 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); -int kvm_pic_set_irq(void *opaque, int irq, int level); +static inline int __kvm_irq_line_state(unsigned long *irq_state, + int irq_source_id, int level) +{ + /* Logical OR for level trig interrupt */ + if (level) + __set_bit(irq_source_id, irq_state); + else + __clear_bit(irq_source_id, irq_state); + + return !!(*irq_state); +} + +int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); +void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 63ab166..2f7712e 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -22,6 +22,7 @@ #define KVM_FEATURE_CLOCKSOURCE2 3 #define KVM_FEATURE_ASYNC_PF 4 #define KVM_FEATURE_STEAL_TIME 5 +#define KVM_FEATURE_PV_EOI 6 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. @@ -37,6 +38,7 @@ #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02 #define MSR_KVM_STEAL_TIME 0x4b564d03 +#define MSR_KVM_PV_EOI_EN 0x4b564d04 struct kvm_steal_time { __u64 steal; @@ -89,6 +91,11 @@ struct kvm_vcpu_pv_apf_data { __u32 enabled; }; +#define KVM_PV_EOI_BIT 0 +#define KVM_PV_EOI_MASK (0x1 << KVM_PV_EOI_BIT) +#define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK +#define KVM_PV_EOI_DISABLED 0x0 + #ifdef __KERNEL__ #include <asm/processor.h> diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 5ad24a8..73e8eef 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -104,6 +104,7 @@ struct pci_raw_ops { extern const struct pci_raw_ops *raw_pci_ops; extern const struct pci_raw_ops *raw_pci_ext_ops; +extern const struct pci_raw_ops pci_mmcfg; extern const struct pci_raw_ops pci_direct_conf1; extern bool port_cf9_safe; @@ -139,6 +140,12 @@ struct pci_mmcfg_region { extern int __init pci_mmcfg_arch_init(void); extern void __init pci_mmcfg_arch_free(void); +extern int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg); +extern void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg); +extern int __devinit pci_mmconfig_insert(struct device *dev, + u16 seg, u8 start, + u8 end, phys_addr_t addr); +extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end); extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus); extern struct list_head pci_mmcfg_list; diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index f8ab3ea..aea1d1d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -44,6 +44,7 @@ */ #define X86_CR3_PWT 0x00000008 /* Page Write Through */ #define X86_CR3_PCD 0x00000010 /* Page Cache Disable */ +#define X86_CR3_PCID_MASK 0x00000fff /* PCID Mask */ /* * Intel CPU features in CR4 @@ -61,6 +62,7 @@ #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */ #define X86_CR4_VMXE 0x00002000 /* enable VMX virtualization */ #define X86_CR4_RDWRGSFS 0x00010000 /* enable RDWRGSFS support */ +#define X86_CR4_PCIDE 0x00020000 /* enable PCID support */ #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */ #define X86_CR4_SMEP 0x00100000 /* enable SMEP support */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 31f180c..74fcb96 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -60,6 +60,7 @@ #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 +#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -281,6 +282,7 @@ enum vmcs_field { #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 +#define EXIT_REASON_INVPCID 58 /* * Interruption-information format @@ -404,6 +406,7 @@ enum vmcs_field { #define VMX_EPTP_WB_BIT (1ull << 14) #define VMX_EPT_2MB_PAGE_BIT (1ull << 16) #define VMX_EPT_1GB_PAGE_BIT (1ull << 17) +#define VMX_EPT_AD_BIT (1ull << 21) #define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24) #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) @@ -415,11 +418,14 @@ enum vmcs_field { #define VMX_EPT_MAX_GAW 0x4 #define VMX_EPT_MT_EPTE_SHIFT 3 #define VMX_EPT_GAW_EPTP_SHIFT 3 +#define VMX_EPT_AD_ENABLE_BIT (1ull << 6) #define VMX_EPT_DEFAULT_MT 0x6ull #define VMX_EPT_READABLE_MASK 0x1ull #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull #define VMX_EPT_IPAT_BIT (1ull << 6) +#define VMX_EPT_ACCESS_BIT (1ull << 8) +#define VMX_EPT_DIRTY_BIT (1ull << 9) #define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 5728852..59c226d 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -48,6 +48,7 @@ #include <xen/interface/sched.h> #include <xen/interface/physdev.h> #include <xen/interface/platform.h> +#include <xen/interface/xen-mca.h> /* * The hypercall asms have to meet several constraints: @@ -302,6 +303,13 @@ HYPERVISOR_set_timer_op(u64 timeout) } static inline int +HYPERVISOR_mca(struct xen_mc *mc_op) +{ + mc_op->interface_version = XEN_MCA_INTERFACE_VERSION; + return _hypercall1(int, mca, mc_op); +} + +static inline int HYPERVISOR_dom0_op(struct xen_platform_op *platform_op) { platform_op->interface_version = XENPF_INTERFACE_VERSION; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c421512..98e2413 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2143,6 +2143,23 @@ int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, } /* + * Override the generic EOI implementation with an optimized version. + * Only called during early boot when only one CPU is active and with + * interrupts disabled, so we know this does not race with actual APIC driver + * use. + */ +void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) +{ + struct apic **drv; + + for (drv = __apicdrivers; drv < __apicdrivers_end; drv++) { + /* Should happen once for each apic */ + WARN_ON((*drv)->eoi_write == eoi_write); + (*drv)->eoi_write = eoi_write; + } +} + +/* * Power management */ #ifdef CONFIG_PM diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 755f64f..a8f8fa9 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -37,6 +37,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = #endif &x86_hyper_vmware, &x86_hyper_ms_hyperv, +#ifdef CONFIG_KVM_GUEST + &x86_hyper_kvm, +#endif }; const struct hypervisor_x86 *x86_hyper; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9473e87..5e095f8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); int mce_disabled __read_mostly; -#define MISC_MCELOG_MINOR 227 - #define SPINUNIT 100 /* 100ns */ atomic_t mce_entry; @@ -2346,7 +2344,7 @@ static __init int mcheck_init_device(void) return err; } -device_initcall(mcheck_init_device); +device_initcall_sync(mcheck_init_device); /* * Old style boot options parsing. Only for compatibility. diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 671b95a..c4e916d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -759,4 +759,24 @@ static __init int threshold_init_device(void) return 0; } -device_initcall(threshold_init_device); +/* + * there are 3 funcs which need to be _initcalled in a logic sequence: + * 1. xen_late_init_mcelog + * 2. mcheck_init_device + * 3. threshold_init_device + * + * xen_late_init_mcelog must register xen_mce_chrdev_device before + * native mce_chrdev_device registration if running under xen platform; + * + * mcheck_init_device should be inited before threshold_init_device to + * initialize mce_device, otherwise a NULL ptr dereference will cause panic. + * + * so we use following _initcalls + * 1. device_initcall(xen_late_init_mcelog); + * 2. device_initcall_sync(mcheck_init_device); + * 3. late_initcall(threshold_init_device); + * + * when running under xen, the initcall order is 1,2,3; + * on baremetal, we skip 1 and we do only 2 and 3. + */ +late_initcall(threshold_init_device); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e554e5a..c1d61ee 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -39,6 +39,9 @@ #include <asm/desc.h> #include <asm/tlbflush.h> #include <asm/idle.h> +#include <asm/apic.h> +#include <asm/apicdef.h> +#include <asm/hypervisor.h> static int kvmapf = 1; @@ -283,6 +286,22 @@ static void kvm_register_steal_time(void) cpu, __pa(st)); } +static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; + +static void kvm_guest_apic_eoi_write(u32 reg, u32 val) +{ + /** + * This relies on __test_and_clear_bit to modify the memory + * in a way that is atomic with respect to the local CPU. + * The hypervisor only accesses this memory from the local CPU so + * there's no need for lock or memory barriers. + * An optimization barrier is implied in apic write. + */ + if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi))) + return; + apic_write(APIC_EOI, APIC_EOI_ACK); +} + void __cpuinit kvm_guest_cpu_init(void) { if (!kvm_para_available()) @@ -300,11 +319,20 @@ void __cpuinit kvm_guest_cpu_init(void) smp_processor_id()); } + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { + unsigned long pa; + /* Size alignment is implied but just to make it explicit. */ + BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); + __get_cpu_var(kvm_apic_eoi) = 0; + pa = __pa(&__get_cpu_var(kvm_apic_eoi)) | KVM_MSR_ENABLED; + wrmsrl(MSR_KVM_PV_EOI_EN, pa); + } + if (has_steal_clock) kvm_register_steal_time(); } -static void kvm_pv_disable_apf(void *unused) +static void kvm_pv_disable_apf(void) { if (!__get_cpu_var(apf_reason).enabled) return; @@ -316,11 +344,23 @@ static void kvm_pv_disable_apf(void *unused) smp_processor_id()); } +static void kvm_pv_guest_cpu_reboot(void *unused) +{ + /* + * We disable PV EOI before we load a new kernel by kexec, + * since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory. + * New kernel can re-enable when it boots. + */ + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); +} + static int kvm_pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused) { if (code == SYS_RESTART) - on_each_cpu(kvm_pv_disable_apf, NULL, 1); + on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); return NOTIFY_DONE; } @@ -371,7 +411,9 @@ static void __cpuinit kvm_guest_cpu_online(void *dummy) static void kvm_guest_cpu_offline(void *dummy) { kvm_disable_steal_time(); - kvm_pv_disable_apf(NULL); + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); apf_task_wake_all(); } @@ -424,6 +466,9 @@ void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + apic_set_eoi_write(kvm_guest_apic_eoi_write); + #ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; register_cpu_notifier(&kvm_cpu_notifier); @@ -432,6 +477,19 @@ void __init kvm_guest_init(void) #endif } +static bool __init kvm_detect(void) +{ + if (!kvm_para_available()) + return false; + return true; +} + +const struct hypervisor_x86 x86_hyper_kvm __refconst = { + .name = "KVM", + .detect = kvm_detect, +}; +EXPORT_SYMBOL_GPL(x86_hyper_kvm); + static __init int activate_jump_labels(void) { if (has_steal_clock) { diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 202494d..216a4d7 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -81,7 +81,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value; break; case R_386_PC32: - /* Add the value, subtract its postition */ + /* Add the value, subtract its position */ *location += sym->st_value - (uint32_t)location; break; default: diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index c0f420f..de2b7ad 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -45,15 +45,6 @@ int iommu_detected __read_mostly = 0; */ int iommu_pass_through __read_mostly; -/* - * Group multi-function PCI devices into a single device-group for the - * iommu_device_group interface. This tells the iommu driver to pretend - * it cannot distinguish between functions of a device, exposing only one - * group for the device. Useful for disallowing use of individual PCI - * functions from userspace drivers. - */ -int iommu_group_mf __read_mostly; - extern struct iommu_table_entry __iommu_table[], __iommu_table_end[]; /* Dummy device used for NULL arguments (normally ISA). */ @@ -194,8 +185,6 @@ static __init int iommu_setup(char *p) #endif if (!strncmp(p, "pt", 2)) iommu_pass_through = 1; - if (!strncmp(p, "group_mf", 8)) - iommu_group_mf = 1; gart_parse_options(p); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 03920a1..1b27de5 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -512,7 +512,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, #if defined(CONFIG_PCI) && defined(CONFIG_NUMA) /* Set correct numa_node information for AMD NB functions */ -static void __init quirk_amd_nb_node(struct pci_dev *dev) +static void __devinit quirk_amd_nb_node(struct pci_dev *dev) { struct pci_dev *nb_ht; unsigned int devfn; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7df1c6d..0595f13 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -201,6 +201,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_lm = 0; #endif unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; + unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; /* cpuid 1.edx */ const u32 kvm_supported_word0_x86_features = @@ -228,7 +229,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | - 0 /* Reserved, DCA */ | F(XMM4_1) | + F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | F(F16C) | F(RDRAND); @@ -248,7 +249,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ebx */ const u32 kvm_supported_word9_x86_features = F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | F(RTM); + F(BMI2) | F(ERMS) | f_invpcid | F(RTM); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -409,6 +410,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_NOP_IO_DELAY) | (1 << KVM_FEATURE_CLOCKSOURCE2) | (1 << KVM_FEATURE_ASYNC_PF) | + (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); if (sched_info_on()) @@ -639,33 +641,37 @@ static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); } -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) { - u32 function, index; + u32 function = *eax, index = *ecx; struct kvm_cpuid_entry2 *best; - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); best = kvm_find_cpuid_entry(vcpu, function, index); if (!best) best = check_cpuid_limit(vcpu, function, index); if (best) { - kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); - kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); - kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); - } + *eax = best->eax; + *ebx = best->ebx; + *ecx = best->ecx; + *edx = best->edx; + } else + *eax = *ebx = *ecx = *edx = 0; +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 function, eax, ebx, ecx, edx; + + function = eax = kvm_register_read(vcpu, VCPU_REGS_RAX); + ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx); + kvm_register_write(vcpu, VCPU_REGS_RAX, eax); + kvm_register_write(vcpu, VCPU_REGS_RBX, ebx); + kvm_register_write(vcpu, VCPU_REGS_RCX, ecx); + kvm_register_write(vcpu, VCPU_REGS_RDX, edx); kvm_x86_ops->skip_emulated_instruction(vcpu); - trace_kvm_cpuid(function, - kvm_register_read(vcpu, VCPU_REGS_RAX), - kvm_register_read(vcpu, VCPU_REGS_RBX), - kvm_register_read(vcpu, VCPU_REGS_RCX), - kvm_register_read(vcpu, VCPU_REGS_RDX)); + trace_kvm_cpuid(function, eax, ebx, ecx, edx); } EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 26d1fb4..a10e460 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -17,6 +17,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) @@ -51,4 +52,12 @@ static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_OSVW)); } +static inline bool guest_cpuid_has_pcid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & bit(X86_FEATURE_PCID)); +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f95d242..97d9a99 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -433,11 +433,32 @@ static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt, return ctxt->ops->intercept(ctxt, &info, stage); } +static void assign_masked(ulong *dest, ulong src, ulong mask) +{ + *dest = (*dest & ~mask) | (src & mask); +} + static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; } +static ulong stack_mask(struct x86_emulate_ctxt *ctxt) +{ + u16 sel; + struct desc_struct ss; + + if (ctxt->mode == X86EMUL_MODE_PROT64) + return ~0UL; + ctxt->ops->get_segment(ctxt, &sel, &ss, NULL, VCPU_SREG_SS); + return ~0U >> ((ss.d ^ 1) * 16); /* d=0: 0xffff; d=1: 0xffffffff */ +} + +static int stack_size(struct x86_emulate_ctxt *ctxt) +{ + return (__fls(stack_mask(ctxt)) + 1) >> 3; +} + /* Access/update address held in a register, based on addressing mode. */ static inline unsigned long address_mask(struct x86_emulate_ctxt *ctxt, unsigned long reg) @@ -958,6 +979,12 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt, op->orig_val = op->val; } +static void adjust_modrm_seg(struct x86_emulate_ctxt *ctxt, int base_reg) +{ + if (base_reg == VCPU_REGS_RSP || base_reg == VCPU_REGS_RBP) + ctxt->modrm_seg = VCPU_SREG_SS; +} + static int decode_modrm(struct x86_emulate_ctxt *ctxt, struct operand *op) { @@ -1061,15 +1088,20 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0) modrm_ea += insn_fetch(s32, ctxt); - else + else { modrm_ea += ctxt->regs[base_reg]; + adjust_modrm_seg(ctxt, base_reg); + } if (index_reg != 4) modrm_ea += ctxt->regs[index_reg] << scale; } else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) { if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->rip_relative = 1; - } else - modrm_ea += ctxt->regs[ctxt->modrm_rm]; + } else { + base_reg = ctxt->modrm_rm; + modrm_ea += ctxt->regs[base_reg]; + adjust_modrm_seg(ctxt, base_reg); + } switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 5) @@ -1264,7 +1296,8 @@ static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, /* allowed just for 8 bytes segments */ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, - u16 selector, struct desc_struct *desc) + u16 selector, struct desc_struct *desc, + ulong *desc_addr_p) { struct desc_ptr dt; u16 index = selector >> 3; @@ -1275,7 +1308,7 @@ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (dt.size < index * 8 + 7) return emulate_gp(ctxt, selector & 0xfffc); - addr = dt.address + index * 8; + *desc_addr_p = addr = dt.address + index * 8; return ctxt->ops->read_std(ctxt, addr, desc, sizeof *desc, &ctxt->exception); } @@ -1302,11 +1335,12 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg) { - struct desc_struct seg_desc; + struct desc_struct seg_desc, old_desc; u8 dpl, rpl, cpl; unsigned err_vec = GP_VECTOR; u32 err_code = 0; bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ + ulong desc_addr; int ret; memset(&seg_desc, 0, sizeof seg_desc); @@ -1324,8 +1358,14 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto load; } - /* NULL selector is not valid for TR, CS and SS */ - if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) + rpl = selector & 3; + cpl = ctxt->ops->cpl(ctxt); + + /* NULL selector is not valid for TR, CS and SS (except for long mode) */ + if ((seg == VCPU_SREG_CS + || (seg == VCPU_SREG_SS + && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)) + || seg == VCPU_SREG_TR) && null_selector) goto exception; @@ -1336,7 +1376,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (null_selector) /* for NULL selector skip all following checks */ goto load; - ret = read_segment_descriptor(ctxt, selector, &seg_desc); + ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; @@ -1352,9 +1392,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; } - rpl = selector & 3; dpl = seg_desc.dpl; - cpl = ctxt->ops->cpl(ctxt); switch (seg) { case VCPU_SREG_SS: @@ -1384,6 +1422,12 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_TR: if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) goto exception; + old_desc = seg_desc; + seg_desc.type |= 2; /* busy */ + ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, + sizeof(seg_desc), &ctxt->exception); + if (ret != X86EMUL_CONTINUE) + return ret; break; case VCPU_SREG_LDTR: if (seg_desc.s || seg_desc.type != 2) @@ -1474,17 +1518,22 @@ static int writeback(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_push(struct x86_emulate_ctxt *ctxt) +static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -ctxt->op_bytes); + register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes); addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); addr.seg = VCPU_SREG_SS; + return segmented_write(ctxt, addr, data, bytes); +} + +static int em_push(struct x86_emulate_ctxt *ctxt) +{ /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return segmented_write(ctxt, addr, &ctxt->src.val, ctxt->op_bytes); + return push(ctxt, &ctxt->src.val, ctxt->op_bytes); } static int emulate_pop(struct x86_emulate_ctxt *ctxt, @@ -1556,6 +1605,33 @@ static int em_popf(struct x86_emulate_ctxt *ctxt) return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes); } +static int em_enter(struct x86_emulate_ctxt *ctxt) +{ + int rc; + unsigned frame_size = ctxt->src.val; + unsigned nesting_level = ctxt->src2.val & 31; + + if (nesting_level) + return X86EMUL_UNHANDLEABLE; + + rc = push(ctxt, &ctxt->regs[VCPU_REGS_RBP], stack_size(ctxt)); + if (rc != X86EMUL_CONTINUE) + return rc; + assign_masked(&ctxt->regs[VCPU_REGS_RBP], ctxt->regs[VCPU_REGS_RSP], + stack_mask(ctxt)); + assign_masked(&ctxt->regs[VCPU_REGS_RSP], + ctxt->regs[VCPU_REGS_RSP] - frame_size, + stack_mask(ctxt)); + return X86EMUL_CONTINUE; +} + +static int em_leave(struct x86_emulate_ctxt *ctxt) +{ + assign_masked(&ctxt->regs[VCPU_REGS_RSP], ctxt->regs[VCPU_REGS_RBP], + stack_mask(ctxt)); + return emulate_pop(ctxt, &ctxt->regs[VCPU_REGS_RBP], ctxt->op_bytes); +} + static int em_push_sreg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; @@ -1993,8 +2069,8 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt) u32 eax, ebx, ecx, edx; eax = ecx = 0; - return ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx) - && ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; } @@ -2013,32 +2089,31 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) eax = 0x00000000; ecx = 0x00000000; - if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) { - /* - * Intel ("GenuineIntel") - * remark: Intel CPUs only support "syscall" in 64bit - * longmode. Also an 64bit guest with a - * 32bit compat-app running will #UD !! While this - * behaviour can be fixed (by emulating) into AMD - * response - CPUs of AMD can't behave like Intel. - */ - if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && - ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && - edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) - return false; + ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + /* + * Intel ("GenuineIntel") + * remark: Intel CPUs only support "syscall" in 64bit + * longmode. Also an 64bit guest with a + * 32bit compat-app running will #UD !! While this + * behaviour can be fixed (by emulating) into AMD + * response - CPUs of AMD can't behave like Intel. + */ + if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && + ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && + edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) + return false; - /* AMD ("AuthenticAMD") */ - if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && - ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && - edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) - return true; - - /* AMD ("AMDisbetter!") */ - if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && - ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && - edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) - return true; - } + /* AMD ("AuthenticAMD") */ + if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && + ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && + edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return true; + + /* AMD ("AMDisbetter!") */ + if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && + ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && + edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) + return true; /* default: (not Intel, not AMD), apply Intel's stricter rules... */ return false; @@ -2547,13 +2622,14 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ulong old_tss_base = ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; + ulong desc_addr; /* FIXME: old_tss_base == ~0 ? */ - ret = read_segment_descriptor(ctxt, tss_selector, &next_tss_desc); + ret = read_segment_descriptor(ctxt, tss_selector, &next_tss_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; - ret = read_segment_descriptor(ctxt, old_tss_sel, &curr_tss_desc); + ret = read_segment_descriptor(ctxt, old_tss_sel, &curr_tss_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; @@ -2948,6 +3024,24 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg); } +static int em_lldt(struct x86_emulate_ctxt *ctxt) +{ + u16 sel = ctxt->src.val; + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return load_segment_descriptor(ctxt, sel, VCPU_SREG_LDTR); +} + +static int em_ltr(struct x86_emulate_ctxt *ctxt) +{ + u16 sel = ctxt->src.val; + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return load_segment_descriptor(ctxt, sel, VCPU_SREG_TR); +} + static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; @@ -2989,11 +3083,42 @@ static int em_vmcall(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, + void (*get)(struct x86_emulate_ctxt *ctxt, + struct desc_ptr *ptr)) +{ + struct desc_ptr desc_ptr; + + if (ctxt->mode == X86EMUL_MODE_PROT64) + ctxt->op_bytes = 8; + get(ctxt, &desc_ptr); + if (ctxt->op_bytes == 2) { + ctxt->op_bytes = 4; + desc_ptr.address &= 0x00ffffff; + } + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return segmented_write(ctxt, ctxt->dst.addr.mem, + &desc_ptr, 2 + ctxt->op_bytes); +} + +static int em_sgdt(struct x86_emulate_ctxt *ctxt) +{ + return emulate_store_desc_ptr(ctxt, ctxt->ops->get_gdt); +} + +static int em_sidt(struct x86_emulate_ctxt *ctxt) +{ + return emulate_store_desc_ptr(ctxt, ctxt->ops->get_idt); +} + static int em_lgdt(struct x86_emulate_ctxt *ctxt) { struct desc_ptr desc_ptr; int rc; + if (ctxt->mode == X86EMUL_MODE_PROT64) + ctxt->op_bytes = 8; rc = read_descriptor(ctxt, ctxt->src.addr.mem, &desc_ptr.size, &desc_ptr.address, ctxt->op_bytes); @@ -3021,6 +3146,8 @@ static int em_lidt(struct x86_emulate_ctxt *ctxt) struct desc_ptr desc_ptr; int rc; + if (ctxt->mode == X86EMUL_MODE_PROT64) + ctxt->op_bytes = 8; rc = read_descriptor(ctxt, ctxt->src.addr.mem, &desc_ptr.size, &desc_ptr.address, ctxt->op_bytes); @@ -3143,6 +3270,42 @@ static int em_bsr(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_cpuid(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = ctxt->regs[VCPU_REGS_RAX]; + ecx = ctxt->regs[VCPU_REGS_RCX]; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + ctxt->regs[VCPU_REGS_RAX] = eax; + ctxt->regs[VCPU_REGS_RBX] = ebx; + ctxt->regs[VCPU_REGS_RCX] = ecx; + ctxt->regs[VCPU_REGS_RDX] = edx; + return X86EMUL_CONTINUE; +} + +static int em_lahf(struct x86_emulate_ctxt *ctxt) +{ + ctxt->regs[VCPU_REGS_RAX] &= ~0xff00UL; + ctxt->regs[VCPU_REGS_RAX] |= (ctxt->eflags & 0xff) << 8; + return X86EMUL_CONTINUE; +} + +static int em_bswap(struct x86_emulate_ctxt *ctxt) +{ + switch (ctxt->op_bytes) { +#ifdef CONFIG_X86_64 + case 8: + asm("bswap %0" : "+r"(ctxt->dst.val)); + break; +#endif + default: + asm("bswap %0" : "+r"(*(u32 *)&ctxt->dst.val)); + break; + } + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -3424,14 +3587,14 @@ static struct opcode group5[] = { static struct opcode group6[] = { DI(Prot, sldt), DI(Prot, str), - DI(Prot | Priv, lldt), - DI(Prot | Priv, ltr), + II(Prot | Priv | SrcMem16, em_lldt, lldt), + II(Prot | Priv | SrcMem16, em_ltr, ltr), N, N, N, N, }; static struct group_dual group7 = { { - DI(Mov | DstMem | Priv, sgdt), - DI(Mov | DstMem | Priv, sidt), + II(Mov | DstMem | Priv, em_sgdt, sgdt), + II(Mov | DstMem | Priv, em_sidt, sidt), II(SrcMem | Priv, em_lgdt, lgdt), II(SrcMem | Priv, em_lidt, lidt), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, @@ -3538,7 +3701,7 @@ static struct opcode opcode_table[256] = { D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), I(SrcImmFAddr | No64, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), - II(ImplicitOps | Stack, em_popf, popf), N, N, + II(ImplicitOps | Stack, em_popf, popf), N, I(ImplicitOps, em_lahf), /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), @@ -3561,7 +3724,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ - N, N, N, I(ImplicitOps | Stack, em_ret_far), + I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave), + N, I(ImplicitOps | Stack, em_ret_far), D(ImplicitOps), DI(SrcImmByte, intn), D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret), /* 0xD0 - 0xD7 */ @@ -3635,7 +3799,7 @@ static struct opcode twobyte_table[256] = { X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), - DI(ImplicitOps, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), + II(ImplicitOps, em_cpuid, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ @@ -3658,11 +3822,12 @@ static struct opcode twobyte_table[256] = { I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), - /* 0xC0 - 0xCF */ + /* 0xC0 - 0xC7 */ D2bv(DstMem | SrcReg | ModRM | Lock), N, D(DstMem | SrcReg | ModRM | Mov), N, N, N, GD(0, &group9), - N, N, N, N, N, N, N, N, + /* 0xC8 - 0xCF */ + X8(I(DstReg, em_bswap)), /* 0xD0 - 0xDF */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, /* 0xE0 - 0xEF */ @@ -4426,12 +4591,12 @@ twobyte_insn: break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; - ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val + ctxt->dst.val = (ctxt->src.bytes == 1) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; case 0xbe ... 0xbf: /* movsx */ ctxt->dst.bytes = ctxt->op_bytes; - ctxt->dst.val = (ctxt->d & ByteOp) ? (s8) ctxt->src.val : + ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val : (s16) ctxt->src.val; break; case 0xc0 ... 0xc1: /* xadd */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 81cf4fa..1df8fb9 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -188,14 +188,15 @@ void kvm_pic_update_irq(struct kvm_pic *s) pic_unlock(s); } -int kvm_pic_set_irq(void *opaque, int irq, int level) +int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level) { - struct kvm_pic *s = opaque; int ret = -1; pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { - ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); + int irq_level = __kvm_irq_line_state(&s->irq_states[irq], + irq_source_id, level); + ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, irq_level); pic_update_irq(s); trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr, s->pics[irq >> 3].imr, ret == 0); @@ -205,6 +206,16 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) return ret; } +void kvm_pic_clear_all(struct kvm_pic *s, int irq_source_id) +{ + int i; + + pic_lock(s); + for (i = 0; i < PIC_NUM_PINS; i++) + __clear_bit(irq_source_id, &s->irq_states[i]); + pic_unlock(s); +} + /* * acknowledge interrupt 'irq' */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 93c1574..ce87878 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -107,6 +107,16 @@ static inline void apic_clear_vector(int vec, void *bitmap) clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } +static inline int __apic_test_and_set_vector(int vec, void *bitmap) +{ + return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline int __apic_test_and_clear_vector(int vec, void *bitmap) +{ + return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + static inline int apic_hw_enabled(struct kvm_lapic *apic) { return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE; @@ -210,6 +220,16 @@ static int find_highest_vector(void *bitmap) return fls(word[word_offset << 2]) - 1 + (word_offset << 5); } +static u8 count_vectors(void *bitmap) +{ + u32 *word = bitmap; + int word_offset; + u8 count = 0; + for (word_offset = 0; word_offset < MAX_APIC_VECTOR >> 5; ++word_offset) + count += hweight32(word[word_offset << 2]); + return count; +} + static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) { apic->irr_pending = true; @@ -242,6 +262,27 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) apic->irr_pending = true; } +static inline void apic_set_isr(int vec, struct kvm_lapic *apic) +{ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + ++apic->isr_count; + BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + /* + * ISR (in service register) bit is set when injecting an interrupt. + * The highest vector is injected. Thus the latest bit set matches + * the highest bit in ISR. + */ + apic->highest_isr_cache = vec; +} + +static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) +{ + if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + --apic->isr_count; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; +} + int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -270,9 +311,61 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq) irq->level, irq->trig_mode); } +static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) +{ + + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &val, + sizeof(val)); +} + +static int pv_eoi_get_user(struct kvm_vcpu *vcpu, u8 *val) +{ + + return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, val, + sizeof(*val)); +} + +static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; +} + +static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) +{ + u8 val; + if (pv_eoi_get_user(vcpu, &val) < 0) + apic_debug("Can't read EOI MSR value: 0x%llx\n", + (unsigned long long)vcpi->arch.pv_eoi.msr_val); + return val & 0x1; +} + +static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) +{ + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { + apic_debug("Can't set EOI MSR value: 0x%llx\n", + (unsigned long long)vcpi->arch.pv_eoi.msr_val); + return; + } + __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); +} + +static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) +{ + if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { + apic_debug("Can't clear EOI MSR value: 0x%llx\n", + (unsigned long long)vcpi->arch.pv_eoi.msr_val); + return; + } + __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); +} + static inline int apic_find_highest_isr(struct kvm_lapic *apic) { int result; + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; result = find_highest_vector(apic->regs + APIC_ISR); ASSERT(result == -1 || result >= 16); @@ -482,17 +575,20 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } -static void apic_set_eoi(struct kvm_lapic *apic) +static int apic_set_eoi(struct kvm_lapic *apic) { int vector = apic_find_highest_isr(apic); + + trace_kvm_eoi(apic, vector); + /* * Not every write EOI will has corresponding ISR, * one example is when Kernel check timer on setup_IO_APIC */ if (vector == -1) - return; + return vector; - apic_clear_vector(vector, apic->regs + APIC_ISR); + apic_clear_isr(vector, apic); apic_update_ppr(apic); if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && @@ -505,6 +601,7 @@ static void apic_set_eoi(struct kvm_lapic *apic) kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); } kvm_make_request(KVM_REQ_EVENT, apic->vcpu); + return vector; } static void apic_send_ipi(struct kvm_lapic *apic) @@ -1081,10 +1178,13 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } apic->irr_pending = false; + apic->isr_count = 0; + apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); if (kvm_vcpu_is_bsp(vcpu)) vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP; + vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); vcpu->arch.apic_arb_prio = 0; @@ -1248,7 +1348,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) if (vector == -1) return -1; - apic_set_vector(vector, apic->regs + APIC_ISR); + apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); return vector; @@ -1267,6 +1367,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu) update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; + apic->isr_count = count_vectors(apic->regs + APIC_ISR); + apic->highest_isr_cache = -1; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -1283,11 +1385,51 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } +/* + * apic_sync_pv_eoi_from_guest - called on vmexit or cancel interrupt + * + * Detect whether guest triggered PV EOI since the + * last entry. If yes, set EOI on guests's behalf. + * Clear PV EOI in guest memory in any case. + */ +static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, + struct kvm_lapic *apic) +{ + bool pending; + int vector; + /* + * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host + * and KVM_PV_EOI_ENABLED in guest memory as follows: + * + * KVM_APIC_PV_EOI_PENDING is unset: + * -> host disabled PV EOI. + * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is set: + * -> host enabled PV EOI, guest did not execute EOI yet. + * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is unset: + * -> host enabled PV EOI, guest executed EOI. + */ + BUG_ON(!pv_eoi_enabled(vcpu)); + pending = pv_eoi_get_pending(vcpu); + /* + * Clear pending bit in any case: it will be set again on vmentry. + * While this might not be ideal from performance point of view, + * this makes sure pv eoi is only enabled when we know it's safe. + */ + pv_eoi_clr_pending(vcpu); + if (pending) + return; + vector = apic_set_eoi(apic); + trace_kvm_pv_eoi(apic, vector); +} + void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) { u32 data; void *vapic; + if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention)) + apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic); + if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; @@ -1298,17 +1440,44 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) apic_set_tpr(vcpu->arch.apic, data & 0xff); } +/* + * apic_sync_pv_eoi_to_guest - called before vmentry + * + * Detect whether it's safe to enable PV EOI and + * if yes do so. + */ +static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu, + struct kvm_lapic *apic) +{ + if (!pv_eoi_enabled(vcpu) || + /* IRR set or many bits in ISR: could be nested. */ + apic->irr_pending || + /* Cache not set: could be safe but we don't bother. */ + apic->highest_isr_cache == -1 || + /* Need EOI to update ioapic. */ + kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) { + /* + * PV EOI was disabled by apic_sync_pv_eoi_from_guest + * so we need not do anything here. + */ + return; + } + + pv_eoi_set_pending(apic->vcpu); +} + void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) { u32 data, tpr; int max_irr, max_isr; - struct kvm_lapic *apic; + struct kvm_lapic *apic = vcpu->arch.apic; void *vapic; + apic_sync_pv_eoi_to_guest(vcpu, apic); + if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - apic = vcpu->arch.apic; tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff; max_irr = apic_find_highest_irr(apic); if (max_irr < 0) @@ -1394,3 +1563,16 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) return 0; } + +int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) +{ + u64 addr = data & ~KVM_MSR_ENABLED; + if (!IS_ALIGNED(addr, 4)) + return 1; + + vcpu->arch.pv_eoi.msr_val = data; + if (!pv_eoi_enabled(vcpu)) + return 0; + return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, + addr); +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 6f4ce25..4af5405 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -13,6 +13,15 @@ struct kvm_lapic { u32 divide_count; struct kvm_vcpu *vcpu; bool irr_pending; + /* Number of bits set in ISR. */ + s16 isr_count; + /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ + int highest_isr_cache; + /** + * APIC register page. The layout matches the register layout seen by + * the guest 1:1, because it is accessed by the vmx microcode. + * Note: Only one register, the TPR, is used by the microcode. + */ void *regs; gpa_t vapic_addr; struct page *vapic_page; @@ -60,4 +69,6 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) { return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; } + +int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 57e168e..01ca004 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -90,7 +90,7 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 -#define PT_FIRST_AVAIL_BITS_SHIFT 9 +#define PT_FIRST_AVAIL_BITS_SHIFT 10 #define PT64_SECOND_AVAIL_BITS_SHIFT 52 #define PT64_LEVEL_BITS 9 @@ -145,7 +145,8 @@ module_param(dbg, bool, 0644); #define CREATE_TRACE_POINTS #include "mmutrace.h" -#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) +#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) +#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1)) #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) @@ -188,6 +189,7 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static void mmu_spte_set(u64 *sptep, u64 spte); +static void mmu_free_roots(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) { @@ -444,8 +446,22 @@ static bool __check_direct_spte_mmio_pf(u64 spte) } #endif +static bool spte_is_locklessly_modifiable(u64 spte) +{ + return !(~spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)); +} + static bool spte_has_volatile_bits(u64 spte) { + /* + * Always atomicly update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (spte_is_locklessly_modifiable(spte)) + return true; + if (!shadow_accessed_mask) return false; @@ -478,34 +494,47 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte) /* Rules for using mmu_spte_update: * Update the state bits, it means the mapped pfn is not changged. + * + * Whenever we overwrite a writable spte with a read-only one we + * should flush remote TLBs. Otherwise rmap_write_protect + * will find a read-only spte, even though the writable spte + * might be cached on a CPU's TLB, the return value indicates this + * case. */ -static void mmu_spte_update(u64 *sptep, u64 new_spte) +static bool mmu_spte_update(u64 *sptep, u64 new_spte) { - u64 mask, old_spte = *sptep; + u64 old_spte = *sptep; + bool ret = false; WARN_ON(!is_rmap_spte(new_spte)); - if (!is_shadow_present_pte(old_spte)) - return mmu_spte_set(sptep, new_spte); - - new_spte |= old_spte & shadow_dirty_mask; - - mask = shadow_accessed_mask; - if (is_writable_pte(old_spte)) - mask |= shadow_dirty_mask; + if (!is_shadow_present_pte(old_spte)) { + mmu_spte_set(sptep, new_spte); + return ret; + } - if (!spte_has_volatile_bits(old_spte) || (new_spte & mask) == mask) + if (!spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, new_spte); else old_spte = __update_clear_spte_slow(sptep, new_spte); + /* + * For the spte updated out of mmu-lock is safe, since + * we always atomicly update it, see the comments in + * spte_has_volatile_bits(). + */ + if (is_writable_pte(old_spte) && !is_writable_pte(new_spte)) + ret = true; + if (!shadow_accessed_mask) - return; + return ret; if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask)) kvm_set_pfn_accessed(spte_to_pfn(old_spte)); if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask)) kvm_set_pfn_dirty(spte_to_pfn(old_spte)); + + return ret; } /* @@ -652,8 +681,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) mmu_page_header_cache); } -static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, - size_t size) +static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { void *p; @@ -664,8 +692,7 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu) { - return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache, - sizeof(struct pte_list_desc)); + return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache); } static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc) @@ -1051,35 +1078,82 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) rmap_remove(kvm, sptep); } -static int __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level) + +static bool __drop_large_spte(struct kvm *kvm, u64 *sptep) +{ + if (is_large_pte(*sptep)) { + WARN_ON(page_header(__pa(sptep))->role.level == + PT_PAGE_TABLE_LEVEL); + drop_spte(kvm, sptep); + --kvm->stat.lpages; + return true; + } + + return false; +} + +static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) +{ + if (__drop_large_spte(vcpu->kvm, sptep)) + kvm_flush_remote_tlbs(vcpu->kvm); +} + +/* + * Write-protect on the specified @sptep, @pt_protect indicates whether + * spte writ-protection is caused by protecting shadow page table. + * @flush indicates whether tlb need be flushed. + * + * Note: write protection is difference between drity logging and spte + * protection: + * - for dirty logging, the spte can be set to writable at anytime if + * its dirty bitmap is properly set. + * - for spte protection, the spte can be writable only after unsync-ing + * shadow page. + * + * Return true if the spte is dropped. + */ +static bool +spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) +{ + u64 spte = *sptep; + + if (!is_writable_pte(spte) && + !(pt_protect && spte_is_locklessly_modifiable(spte))) + return false; + + rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); + + if (__drop_large_spte(kvm, sptep)) { + *flush |= true; + return true; + } + + if (pt_protect) + spte &= ~SPTE_MMU_WRITEABLE; + spte = spte & ~PT_WRITABLE_MASK; + + *flush |= mmu_spte_update(sptep, spte); + return false; +} + +static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, + int level, bool pt_protect) { u64 *sptep; struct rmap_iterator iter; - int write_protected = 0; + bool flush = false; for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); - - if (!is_writable_pte(*sptep)) { - sptep = rmap_get_next(&iter); - continue; - } - - if (level == PT_PAGE_TABLE_LEVEL) { - mmu_spte_update(sptep, *sptep & ~PT_WRITABLE_MASK); - sptep = rmap_get_next(&iter); - } else { - BUG_ON(!is_large_pte(*sptep)); - drop_spte(kvm, sptep); - --kvm->stat.lpages; + if (spte_write_protect(kvm, sptep, &flush, pt_protect)) { sptep = rmap_get_first(*rmapp, &iter); + continue; } - write_protected = 1; + sptep = rmap_get_next(&iter); } - return write_protected; + return flush; } /** @@ -1100,26 +1174,26 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, while (mask) { rmapp = &slot->rmap[gfn_offset + __ffs(mask)]; - __rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL); + __rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false); /* clear the first set bit */ mask &= mask - 1; } } -static int rmap_write_protect(struct kvm *kvm, u64 gfn) +static bool rmap_write_protect(struct kvm *kvm, u64 gfn) { struct kvm_memory_slot *slot; unsigned long *rmapp; int i; - int write_protected = 0; + bool write_protected = false; slot = gfn_to_memslot(kvm, gfn); for (i = PT_PAGE_TABLE_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmapp, i); + write_protected |= __rmap_write_protect(kvm, rmapp, i, true); } return write_protected; @@ -1238,11 +1312,12 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, unsigned long data) { u64 *sptep; - struct rmap_iterator iter; + struct rmap_iterator uninitialized_var(iter); int young = 0; /* - * Emulate the accessed bit for EPT, by checking if this page has + * In case of absence of EPT Access and Dirty Bits supports, + * emulate the accessed bit for EPT, by checking if this page has * an EPT mapping, and clearing it if it does. On the next access, * a new EPT mapping will be established. * This has some overhead, but not as much as the cost of swapping @@ -1253,11 +1328,12 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, for (sptep = rmap_get_first(*rmapp, &iter); sptep; sptep = rmap_get_next(&iter)) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + BUG_ON(!is_shadow_present_pte(*sptep)); - if (*sptep & PT_ACCESSED_MASK) { + if (*sptep & shadow_accessed_mask) { young = 1; - clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)sptep); + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); } } @@ -1281,9 +1357,9 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, for (sptep = rmap_get_first(*rmapp, &iter); sptep; sptep = rmap_get_next(&iter)) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + BUG_ON(!is_shadow_present_pte(*sptep)); - if (*sptep & PT_ACCESSED_MASK) { + if (*sptep & shadow_accessed_mask) { young = 1; break; } @@ -1401,12 +1477,10 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, u64 *parent_pte, int direct) { struct kvm_mmu_page *sp; - sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, - sizeof *sp); - sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); + sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache); + sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); if (!direct) - sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, - PAGE_SIZE); + sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM); @@ -1701,7 +1775,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, kvm_mmu_pages_init(parent, &parents, &pages); while (mmu_unsync_walk(parent, &pages)) { - int protected = 0; + bool protected = false; for_each_sp(pages, sp, parents, i) protected |= rmap_write_protect(vcpu->kvm, sp->gfn); @@ -1866,15 +1940,6 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) mmu_spte_set(sptep, spte); } -static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) -{ - if (is_large_pte(*sptep)) { - drop_spte(vcpu->kvm, sptep); - --vcpu->kvm->stat.lpages; - kvm_flush_remote_tlbs(vcpu->kvm); - } -} - static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned direct_access) { @@ -2243,7 +2308,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { - u64 spte, entry = *sptep; + u64 spte; int ret = 0; if (set_mmio_spte(sptep, gfn, pfn, pte_access)) @@ -2257,8 +2322,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= shadow_x_mask; else spte |= shadow_nx_mask; + if (pte_access & ACC_USER_MASK) spte |= shadow_user_mask; + if (level > PT_PAGE_TABLE_LEVEL) spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) @@ -2283,7 +2350,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, goto done; } - spte |= PT_WRITABLE_MASK; + spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; if (!vcpu->arch.mmu.direct_map && !(pte_access & ACC_WRITE_MASK)) { @@ -2312,8 +2379,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, __func__, gfn); ret = 1; pte_access &= ~ACC_WRITE_MASK; - if (is_writable_pte(spte)) - spte &= ~PT_WRITABLE_MASK; + spte &= ~(PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE); } } @@ -2321,14 +2387,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, mark_page_dirty(vcpu->kvm, gfn); set_pte: - mmu_spte_update(sptep, spte); - /* - * If we overwrite a writable spte with a read-only one we - * should flush remote TLBs. Otherwise rmap_write_protect - * will find a read-only spte, even though the writable spte - * might be cached on a CPU's TLB. - */ - if (is_writable_pte(entry) && !is_writable_pte(*sptep)) + if (mmu_spte_update(sptep, spte)) kvm_flush_remote_tlbs(vcpu->kvm); done: return ret; @@ -2403,6 +2462,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { + mmu_free_roots(vcpu); } static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, @@ -2625,18 +2685,116 @@ exit: return ret; } +static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code) +{ + /* + * #PF can be fast only if the shadow page table is present and it + * is caused by write-protect, that means we just need change the + * W bit of the spte which can be done out of mmu-lock. + */ + if (!(error_code & PFERR_PRESENT_MASK) || + !(error_code & PFERR_WRITE_MASK)) + return false; + + return true; +} + +static bool +fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte) +{ + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + gfn_t gfn; + + WARN_ON(!sp->role.direct); + + /* + * The gfn of direct spte is stable since it is calculated + * by sp->gfn. + */ + gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); + + if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) + mark_page_dirty(vcpu->kvm, gfn); + + return true; +} + +/* + * Return value: + * - true: let the vcpu to access on the same address again. + * - false: let the real page fault path to fix it. + */ +static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, + u32 error_code) +{ + struct kvm_shadow_walk_iterator iterator; + bool ret = false; + u64 spte = 0ull; + + if (!page_fault_can_be_fast(vcpu, error_code)) + return false; + + walk_shadow_page_lockless_begin(vcpu); + for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + if (!is_shadow_present_pte(spte) || iterator.level < level) + break; + + /* + * If the mapping has been changed, let the vcpu fault on the + * same address again. + */ + if (!is_rmap_spte(spte)) { + ret = true; + goto exit; + } + + if (!is_last_spte(spte, level)) + goto exit; + + /* + * Check if it is a spurious fault caused by TLB lazily flushed. + * + * Need not check the access of upper level table entries since + * they are always ACC_ALL. + */ + if (is_writable_pte(spte)) { + ret = true; + goto exit; + } + + /* + * Currently, to simplify the code, only the spte write-protected + * by dirty-log can be fast fixed. + */ + if (!spte_is_locklessly_modifiable(spte)) + goto exit; + + /* + * Currently, fast page fault only works for direct mapping since + * the gfn is not stable for indirect shadow page. + * See Documentation/virtual/kvm/locking.txt to get more detail. + */ + ret = fast_pf_fix_direct_spte(vcpu, iterator.sptep, spte); +exit: + trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, + spte, ret); + walk_shadow_page_lockless_end(vcpu); + + return ret; +} + static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable); -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn, - bool prefault) +static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, + gfn_t gfn, bool prefault) { int r; int level; int force_pt_level; pfn_t pfn; unsigned long mmu_seq; - bool map_writable; + bool map_writable, write = error_code & PFERR_WRITE_MASK; force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); if (likely(!force_pt_level)) { @@ -2653,6 +2811,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn, } else level = PT_PAGE_TABLE_LEVEL; + if (fast_page_fault(vcpu, v, level, error_code)) + return 0; + mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -3041,7 +3202,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, gfn = gva >> PAGE_SHIFT; return nonpaging_map(vcpu, gva & PAGE_MASK, - error_code & PFERR_WRITE_MASK, gfn, prefault); + error_code, gfn, prefault); } static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) @@ -3121,6 +3282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, } else level = PT_PAGE_TABLE_LEVEL; + if (fast_page_fault(vcpu, gpa, level, error_code)) + return 0; + mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -3885,6 +4049,7 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu) void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) { struct kvm_mmu_page *sp; + bool flush = false; list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) { int i; @@ -3899,16 +4064,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) !is_last_spte(pt[i], sp->role.level)) continue; - if (is_large_pte(pt[i])) { - drop_spte(kvm, &pt[i]); - --kvm->stat.lpages; - continue; - } - - /* avoid RMW */ - if (is_writable_pte(pt[i])) - mmu_spte_update(&pt[i], - pt[i] & ~PT_WRITABLE_MASK); + spte_write_protect(kvm, &pt[i], &flush, false); } } kvm_flush_remote_tlbs(kvm); @@ -3945,7 +4101,6 @@ static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) { struct kvm *kvm; - struct kvm *kvm_freed = NULL; int nr_to_scan = sc->nr_to_scan; if (nr_to_scan == 0) @@ -3957,22 +4112,30 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) int idx; LIST_HEAD(invalid_list); + /* + * n_used_mmu_pages is accessed without holding kvm->mmu_lock + * here. We may skip a VM instance errorneosly, but we do not + * want to shrink a VM that only started to populate its MMU + * anyway. + */ + if (kvm->arch.n_used_mmu_pages > 0) { + if (!nr_to_scan--) + break; + continue; + } + idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); - if (!kvm_freed && nr_to_scan > 0 && - kvm->arch.n_used_mmu_pages > 0) { - kvm_mmu_remove_some_alloc_mmu_pages(kvm, - &invalid_list); - kvm_freed = kvm; - } - nr_to_scan--; + kvm_mmu_remove_some_alloc_mmu_pages(kvm, &invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); + spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); + + list_move_tail(&kvm->vm_list, &vm_list); + break; } - if (kvm_freed) - list_move_tail(&kvm_freed->vm_list, &vm_list); raw_spin_unlock(&kvm_lock); diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 89fb0e8..cd6e983 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -54,8 +54,8 @@ */ TRACE_EVENT( kvm_mmu_pagetable_walk, - TP_PROTO(u64 addr, int write_fault, int user_fault, int fetch_fault), - TP_ARGS(addr, write_fault, user_fault, fetch_fault), + TP_PROTO(u64 addr, u32 pferr), + TP_ARGS(addr, pferr), TP_STRUCT__entry( __field(__u64, addr) @@ -64,8 +64,7 @@ TRACE_EVENT( TP_fast_assign( __entry->addr = addr; - __entry->pferr = (!!write_fault << 1) | (!!user_fault << 2) - | (!!fetch_fault << 4); + __entry->pferr = pferr; ), TP_printk("addr %llx pferr %x %s", __entry->addr, __entry->pferr, @@ -243,6 +242,44 @@ TRACE_EVENT( TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn, __entry->access) ); + +#define __spte_satisfied(__spte) \ + (__entry->retry && is_writable_pte(__entry->__spte)) + +TRACE_EVENT( + fast_page_fault, + TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, + u64 *sptep, u64 old_spte, bool retry), + TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(gva_t, gva) + __field(u32, error_code) + __field(u64 *, sptep) + __field(u64, old_spte) + __field(u64, new_spte) + __field(bool, retry) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->gva = gva; + __entry->error_code = error_code; + __entry->sptep = sptep; + __entry->old_spte = old_spte; + __entry->new_spte = *sptep; + __entry->retry = retry; + ), + + TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx" + " new %llx spurious %d fixed %d", __entry->vcpu_id, + __entry->gva, __print_flags(__entry->error_code, "|", + kvm_mmu_trace_pferr_flags), __entry->sptep, + __entry->old_spte, __entry->new_spte, + __spte_satisfied(old_spte), __spte_satisfied(new_spte) + ) +); #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 34f9709..bb7cf01 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -154,8 +154,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, const int fetch_fault = access & PFERR_FETCH_MASK; u16 errcode = 0; - trace_kvm_mmu_pagetable_walk(addr, write_fault, user_fault, - fetch_fault); + trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: eperm = false; walker->level = mmu->root_level; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f75af40..baead95 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3185,8 +3185,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) break; case MSR_IA32_DEBUGCTLMSR: if (!boot_cpu_has(X86_FEATURE_LBRV)) { - pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", + __func__, data); break; } if (data & DEBUGCTL_RESERVED_BITS) @@ -3205,7 +3205,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; default: return kvm_set_msr_common(vcpu, ecx, data); @@ -4044,6 +4044,11 @@ static bool svm_rdtscp_supported(void) return false; } +static bool svm_invpcid_supported(void) +{ + return false; +} + static bool svm_has_wbinvd_exit(void) { return true; @@ -4312,6 +4317,7 @@ static struct kvm_x86_ops svm_x86_ops = { .cpuid_update = svm_cpuid_update, .rdtscp_supported = svm_rdtscp_supported, + .invpcid_supported = svm_invpcid_supported, .set_supported_cpuid = svm_set_supported_cpuid, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 62d02e3..a71faf7 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -517,6 +517,40 @@ TRACE_EVENT(kvm_apic_accept_irq, __entry->coalesced ? " (coalesced)" : "") ); +TRACE_EVENT(kvm_eoi, + TP_PROTO(struct kvm_lapic *apic, int vector), + TP_ARGS(apic, vector), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( int, vector ) + ), + + TP_fast_assign( + __entry->apicid = apic->vcpu->vcpu_id; + __entry->vector = vector; + ), + + TP_printk("apicid %x vector %d", __entry->apicid, __entry->vector) +); + +TRACE_EVENT(kvm_pv_eoi, + TP_PROTO(struct kvm_lapic *apic, int vector), + TP_ARGS(apic, vector), + + TP_STRUCT__entry( + __field( __u32, apicid ) + __field( int, vector ) + ), + + TP_fast_assign( + __entry->apicid = apic->vcpu->vcpu_id; + __entry->vector = vector; + ), + + TP_printk("apicid %x vector %d", __entry->apicid, __entry->vector) +); + /* * Tracepoint for nested VMRUN */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32eb588..c39b607 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -71,7 +71,10 @@ static bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, S_IRUGO); -static bool __read_mostly emulate_invalid_guest_state = 0; +static bool __read_mostly enable_ept_ad_bits = 1; +module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); + +static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly vmm_exclusive = 1; @@ -615,6 +618,10 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); +static void vmx_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); +static void vmx_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -789,6 +796,11 @@ static inline bool cpu_has_vmx_ept_4levels(void) return vmx_capability.ept & VMX_EPT_PAGE_WALK_4_BIT; } +static inline bool cpu_has_vmx_ept_ad_bits(void) +{ + return vmx_capability.ept & VMX_EPT_AD_BIT; +} + static inline bool cpu_has_vmx_invept_individual_addr(void) { return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT; @@ -849,6 +861,12 @@ static inline bool cpu_has_vmx_rdtscp(void) SECONDARY_EXEC_RDTSCP; } +static inline bool cpu_has_vmx_invpcid(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_ENABLE_INVPCID; +} + static inline bool cpu_has_virtual_nmis(void) { return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; @@ -1739,6 +1757,11 @@ static bool vmx_rdtscp_supported(void) return cpu_has_vmx_rdtscp(); } +static bool vmx_invpcid_supported(void) +{ + return cpu_has_vmx_invpcid() && enable_ept; +} + /* * Swap MSR entry in host/guest MSR entry array. */ @@ -2458,7 +2481,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_ENABLE_EPT | SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_PAUSE_LOOP_EXITING | - SECONDARY_EXEC_RDTSCP; + SECONDARY_EXEC_RDTSCP | + SECONDARY_EXEC_ENABLE_INVPCID; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -2645,8 +2669,12 @@ static __init int hardware_setup(void) !cpu_has_vmx_ept_4levels()) { enable_ept = 0; enable_unrestricted_guest = 0; + enable_ept_ad_bits = 0; } + if (!cpu_has_vmx_ept_ad_bits()) + enable_ept_ad_bits = 0; + if (!cpu_has_vmx_unrestricted_guest()) enable_unrestricted_guest = 0; @@ -2770,6 +2798,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) { unsigned long flags; struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_segment var; if (enable_unrestricted_guest) return; @@ -2813,20 +2842,23 @@ static void enter_rmode(struct kvm_vcpu *vcpu) if (emulate_invalid_guest_state) goto continue_rmode; - vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4); - vmcs_write32(GUEST_SS_LIMIT, 0xffff); - vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + vmx_get_segment(vcpu, &var, VCPU_SREG_SS); + vmx_set_segment(vcpu, &var, VCPU_SREG_SS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_CS); + vmx_set_segment(vcpu, &var, VCPU_SREG_CS); + + vmx_get_segment(vcpu, &var, VCPU_SREG_ES); + vmx_set_segment(vcpu, &var, VCPU_SREG_ES); + + vmx_get_segment(vcpu, &var, VCPU_SREG_DS); + vmx_set_segment(vcpu, &var, VCPU_SREG_DS); - vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); - vmcs_write32(GUEST_CS_LIMIT, 0xffff); - if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) - vmcs_writel(GUEST_CS_BASE, 0xf0000); - vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); + vmx_get_segment(vcpu, &var, VCPU_SREG_GS); + vmx_set_segment(vcpu, &var, VCPU_SREG_GS); - fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); - fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); - fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); - fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); + vmx_get_segment(vcpu, &var, VCPU_SREG_FS); + vmx_set_segment(vcpu, &var, VCPU_SREG_FS); continue_rmode: kvm_mmu_reset_context(vcpu); @@ -3027,6 +3059,8 @@ static u64 construct_eptp(unsigned long root_hpa) /* TODO write the value reading from MSR */ eptp = VMX_EPT_DEFAULT_MT | VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; + if (enable_ept_ad_bits) + eptp |= VMX_EPT_AD_ENABLE_BIT; eptp |= (root_hpa & PAGE_MASK); return eptp; @@ -3153,11 +3187,22 @@ static int __vmx_get_cpl(struct kvm_vcpu *vcpu) static int vmx_get_cpl(struct kvm_vcpu *vcpu) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * If we enter real mode with cs.sel & 3 != 0, the normal CPL calculations + * fail; use the cache instead. + */ + if (unlikely(vmx->emulation_required && emulate_invalid_guest_state)) { + return vmx->cpl; + } + if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - to_vmx(vcpu)->cpl = __vmx_get_cpl(vcpu); + vmx->cpl = __vmx_get_cpl(vcpu); } - return to_vmx(vcpu)->cpl; + + return vmx->cpl; } @@ -3165,7 +3210,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable) + if (var->unusable || !var->present) ar = 1 << 16; else { ar = var->type & 15; @@ -3177,8 +3222,6 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) ar |= (var->db & 1) << 14; ar |= (var->g & 1) << 15; } - if (ar == 0) /* a 0 value means unusable */ - ar = AR_UNUSABLE_MASK; return ar; } @@ -3229,6 +3272,44 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, vmcs_write32(sf->ar_bytes, ar); __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); + + /* + * Fix segments for real mode guest in hosts that don't have + * "unrestricted_mode" or it was disabled. + * This is done to allow migration of the guests from hosts with + * unrestricted guest like Westmere to older host that don't have + * unrestricted guest like Nehelem. + */ + if (!enable_unrestricted_guest && vmx->rmode.vm86_active) { + switch (seg) { + case VCPU_SREG_CS: + vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); + vmcs_write32(GUEST_CS_LIMIT, 0xffff); + if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) + vmcs_writel(GUEST_CS_BASE, 0xf0000); + vmcs_write16(GUEST_CS_SELECTOR, + vmcs_readl(GUEST_CS_BASE) >> 4); + break; + case VCPU_SREG_ES: + fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es); + break; + case VCPU_SREG_DS: + fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds); + break; + case VCPU_SREG_GS: + fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs); + break; + case VCPU_SREG_FS: + fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs); + break; + case VCPU_SREG_SS: + vmcs_write16(GUEST_SS_SELECTOR, + vmcs_readl(GUEST_SS_BASE) >> 4); + vmcs_write32(GUEST_SS_LIMIT, 0xffff); + vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); + break; + } + } } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) @@ -3731,6 +3812,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; enable_unrestricted_guest = 0; + /* Enable INVPCID for non-ept guests may cause performance regression. */ + exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -4489,7 +4572,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; } vcpu->run->exit_reason = 0; - pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", + vcpu_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } @@ -4769,6 +4852,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; gpa_t gpa; + u32 error_code; int gla_validity; exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -4793,7 +4877,13 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3, NULL, 0); + + /* It is a write fault? */ + error_code = exit_qualification & (1U << 1); + /* ept page table is present? */ + error_code |= (exit_qualification >> 3) & 0x1; + + return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } static u64 ept_rsvd_mask(u64 spte, int level) @@ -4908,15 +4998,18 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) int ret = 1; u32 cpu_exec_ctrl; bool intr_window_requested; + unsigned count = 130; cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING; - while (!guest_state_valid(vcpu)) { - if (intr_window_requested - && (kvm_get_rflags(&vmx->vcpu) & X86_EFLAGS_IF)) + while (!guest_state_valid(vcpu) && count-- != 0) { + if (intr_window_requested && vmx_interrupt_allowed(vcpu)) return handle_interrupt_window(&vmx->vcpu); + if (test_bit(KVM_REQ_EVENT, &vcpu->requests)) + return 1; + err = emulate_instruction(vcpu, 0); if (err == EMULATE_DO_MMIO) { @@ -4924,8 +5017,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) goto out; } - if (err != EMULATE_DONE) + if (err != EMULATE_DONE) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; + } if (signal_pending(current)) goto out; @@ -4933,7 +5030,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) schedule(); } - vmx->emulation_required = 0; + vmx->emulation_required = !guest_state_valid(vcpu); out: return ret; } @@ -6467,6 +6564,23 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) } } } + + exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + /* Exposing INVPCID only when PCID is exposed */ + best = kvm_find_cpuid_entry(vcpu, 0x7, 0); + if (vmx_invpcid_supported() && + best && (best->ecx & bit(X86_FEATURE_INVPCID)) && + guest_cpuid_has_pcid(vcpu)) { + exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + exec_control); + } else { + exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + exec_control); + if (best) + best->ecx &= ~bit(X86_FEATURE_INVPCID); + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -7201,6 +7315,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .cpuid_update = vmx_cpuid_update, .rdtscp_supported = vmx_rdtscp_supported, + .invpcid_supported = vmx_invpcid_supported, .set_supported_cpuid = vmx_set_supported_cpuid, @@ -7230,23 +7345,21 @@ static int __init vmx_init(void) if (!vmx_io_bitmap_a) return -ENOMEM; + r = -ENOMEM; + vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_io_bitmap_b) { - r = -ENOMEM; + if (!vmx_io_bitmap_b) goto out; - } vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_legacy) { - r = -ENOMEM; + if (!vmx_msr_bitmap_legacy) goto out1; - } + vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_longmode) { - r = -ENOMEM; + if (!vmx_msr_bitmap_longmode) goto out2; - } + /* * Allow direct access to the PC debug port (it is often used for I/O @@ -7275,8 +7388,10 @@ static int __init vmx_init(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); if (enable_ept) { - kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull, - VMX_EPT_EXECUTABLE_MASK); + kvm_mmu_set_mask_ptes(0ull, + (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, + (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK); ept_set_mmio_spte_mask(); kvm_enable_tdp(); } else diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index be6d549..59b5950 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -528,6 +528,9 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) return 1; } + if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + return 1; + kvm_x86_ops->set_cr0(vcpu, cr0); if ((cr0 ^ old_cr0) & X86_CR0_PG) { @@ -604,10 +607,20 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_read_cr3(vcpu))) return 1; + if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { + if (!guest_cpuid_has_pcid(vcpu)) + return 1; + + /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ + if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) + return 1; + } + if (kvm_x86_ops->set_cr4(vcpu, cr4)) return 1; - if ((cr4 ^ old_cr4) & pdptr_bits) + if (((cr4 ^ old_cr4) & pdptr_bits) || + (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) @@ -626,8 +639,12 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu)) { - if (cr3 & CR3_L_MODE_RESERVED_BITS) - return 1; + if (kvm_read_cr4(vcpu) & X86_CR4_PCIDE) { + if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS) + return 1; + } else + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; } else { if (is_pae(vcpu)) { if (cr3 & CR3_PAE_RESERVED_BITS) @@ -795,6 +812,7 @@ static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1437,8 +1455,8 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; } default: - pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); return 1; } return 0; @@ -1470,8 +1488,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); default: - pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); return 1; } @@ -1551,15 +1569,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ if (data != 0) { - pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", + data); return 1; } break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { - pr_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " + "0x%llx\n", data); return 1; } break; @@ -1574,8 +1592,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) thus reserved and should throw a #GP */ return 1; } - pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: @@ -1653,6 +1671,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; + case MSR_KVM_PV_EOI_EN: + if (kvm_lapic_enable_pv_eoi(vcpu, data)) + return 1; + break; case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: @@ -1671,8 +1693,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_K7_EVNTSEL2: case MSR_K7_EVNTSEL3: if (data != 0) - pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); break; /* at least RHEL 4 unconditionally writes to the perfctr registers, * so we ignore writes to make it happy. @@ -1681,8 +1703,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_K7_PERFCTR1: case MSR_K7_PERFCTR2: case MSR_K7_PERFCTR3: - pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: @@ -1693,8 +1715,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) return kvm_pmu_set_msr(vcpu, msr, data); if (pr || data != 0) - pr_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " + "0x%x data 0x%llx\n", msr, data); break; case MSR_K7_CLK_CTL: /* @@ -1720,7 +1742,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has_osvw(vcpu)) @@ -1738,12 +1760,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (kvm_pmu_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr, data); if (!ignore_msrs) { - pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", - msr, data); + vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", + msr, data); return 1; } else { - pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", - msr, data); + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", + msr, data); break; } } @@ -1846,7 +1868,7 @@ static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = kvm->arch.hv_hypercall; break; default: - pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; } @@ -1877,7 +1899,7 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = vcpu->arch.hv_vapic; break; default: - pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; } *pdata = data; @@ -2030,10 +2052,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) if (kvm_pmu_msr(vcpu, msr)) return kvm_pmu_get_msr(vcpu, msr, pdata); if (!ignore_msrs) { - pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); return 1; } else { - pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); data = 0; } break; @@ -4116,7 +4138,7 @@ static unsigned long emulator_get_cr(struct x86_emulate_ctxt *ctxt, int cr) value = kvm_get_cr8(vcpu); break; default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + kvm_err("%s: unexpected cr %u\n", __func__, cr); return 0; } @@ -4145,7 +4167,7 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) res = kvm_set_cr8(vcpu, val); break; default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + kvm_err("%s: unexpected cr %u\n", __func__, cr); res = -1; } @@ -4297,26 +4319,10 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage); } -static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, +static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) { - struct kvm_cpuid_entry2 *cpuid = NULL; - - if (eax && ecx) - cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt), - *eax, *ecx); - - if (cpuid) { - *eax = cpuid->eax; - *ecx = cpuid->ecx; - if (ebx) - *ebx = cpuid->ebx; - if (edx) - *edx = cpuid->edx; - return true; - } - - return false; + kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx); } static struct x86_emulate_ops emulate_ops = { @@ -5296,8 +5302,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = kvm_mmu_reload(vcpu); if (unlikely(r)) { - kvm_x86_ops->cancel_injection(vcpu); - goto out; + goto cancel_injection; } preempt_disable(); @@ -5322,9 +5327,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); - kvm_x86_ops->cancel_injection(vcpu); r = 1; - goto out; + goto cancel_injection; } srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -5388,9 +5392,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(vcpu->arch.tsc_always_catchup)) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); - kvm_lapic_sync_from_vapic(vcpu); + if (vcpu->arch.apic_attention) + kvm_lapic_sync_from_vapic(vcpu); r = kvm_x86_ops->handle_exit(vcpu); + return r; + +cancel_injection: + kvm_x86_ops->cancel_injection(vcpu); + if (unlikely(vcpu->arch.apic_attention)) + kvm_lapic_sync_from_vapic(vcpu); out: return r; } @@ -6304,7 +6315,7 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) { - vfree(free->arch.lpage_info[i]); + kvm_kvfree(free->arch.lpage_info[i]); free->arch.lpage_info[i] = NULL; } } @@ -6323,7 +6334,7 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) slot->base_gfn, level) + 1; slot->arch.lpage_info[i] = - vzalloc(lpages * sizeof(*slot->arch.lpage_info[i])); + kvm_kvzalloc(lpages * sizeof(*slot->arch.lpage_info[i])); if (!slot->arch.lpage_info[i]) goto out_free; @@ -6350,7 +6361,7 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) out_free: for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { - vfree(slot->arch.lpage_info[i]); + kvm_kvfree(slot->arch.lpage_info[i]); slot->arch.lpage_info[i] = NULL; } return -ENOMEM; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0597f95..33643a8 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -309,6 +309,10 @@ void bpf_jit_compile(struct sk_filter *fp) else EMIT1_off32(0x0d, K); /* or imm32,%eax */ break; + case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ + seen |= SEEN_XREG; + EMIT2(0x31, 0xd8); /* xor %ebx,%eax */ + break; case BPF_S_ALU_LSH_X: /* A <<= X; */ seen |= SEEN_XREG; EMIT4(0x89, 0xd9, 0xd3, 0xe0); /* mov %ebx,%ecx; shl %cl,%eax */ diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index fc09c27..505acdd 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -12,8 +12,13 @@ struct pci_root_info { char name[16]; unsigned int res_num; struct resource *res; - int busnum; struct pci_sysdata sd; +#ifdef CONFIG_PCI_MMCONFIG + bool mcfg_added; + u16 segment; + u8 start_bus; + u8 end_bus; +#endif }; static bool pci_use_crs = true; @@ -120,6 +125,81 @@ void __init pci_acpi_crs_quirks(void) pci_use_crs ? "nocrs" : "use_crs"); } +#ifdef CONFIG_PCI_MMCONFIG +static int __devinit check_segment(u16 seg, struct device *dev, char *estr) +{ + if (seg) { + dev_err(dev, + "%s can't access PCI configuration " + "space under this host bridge.\n", + estr); + return -EIO; + } + + /* + * Failure in adding MMCFG information is not fatal, + * just can't access extended configuration space of + * devices under this host bridge. + */ + dev_warn(dev, + "%s can't access extended PCI configuration " + "space under this bridge.\n", + estr); + + return 0; +} + +static int __devinit setup_mcfg_map(struct pci_root_info *info, + u16 seg, u8 start, u8 end, + phys_addr_t addr) +{ + int result; + struct device *dev = &info->bridge->dev; + + info->start_bus = start; + info->end_bus = end; + info->mcfg_added = false; + + /* return success if MMCFG is not in use */ + if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) + return 0; + + if (!(pci_probe & PCI_PROBE_MMCONF)) + return check_segment(seg, dev, "MMCONFIG is disabled,"); + + result = pci_mmconfig_insert(dev, seg, start, end, addr); + if (result == 0) { + /* enable MMCFG if it hasn't been enabled yet */ + if (raw_pci_ext_ops == NULL) + raw_pci_ext_ops = &pci_mmcfg; + info->mcfg_added = true; + } else if (result != -EEXIST) + return check_segment(seg, dev, + "fail to add MMCONFIG information,"); + + return 0; +} + +static void teardown_mcfg_map(struct pci_root_info *info) +{ + if (info->mcfg_added) { + pci_mmconfig_delete(info->segment, info->start_bus, + info->end_bus); + info->mcfg_added = false; + } +} +#else +static int __devinit setup_mcfg_map(struct pci_root_info *info, + u16 seg, u8 start, u8 end, + phys_addr_t addr) +{ + return 0; +} +static void teardown_mcfg_map(struct pci_root_info *info) +{ +} +#endif + static acpi_status resource_to_addr(struct acpi_resource *resource, struct acpi_resource_address64 *addr) @@ -234,13 +314,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data) } info->res_num++; - if (addr.translation_offset) - dev_info(&info->bridge->dev, "host bridge window %pR " - "(PCI address [%#llx-%#llx])\n", - res, res->start - addr.translation_offset, - res->end - addr.translation_offset); - else - dev_info(&info->bridge->dev, "host bridge window %pR\n", res); return AE_OK; } @@ -332,8 +405,11 @@ static void __release_pci_root_info(struct pci_root_info *info) free_pci_root_info_res(info); + teardown_mcfg_map(info); + kfree(info); } + static void release_pci_root_info(struct pci_host_bridge *bridge) { struct pci_root_info *info = bridge->release_data; @@ -347,7 +423,9 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, { size_t size; + sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); info->bridge = device; + info->res_num = 0; acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource, info); @@ -360,8 +438,6 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, if (!info->res) return; - sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); - acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, info); } @@ -373,7 +449,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) int domain = root->segment; int busnum = root->secondary.start; LIST_HEAD(resources); - struct pci_bus *bus; + struct pci_bus *bus = NULL; struct pci_sysdata *sd; int node; #ifdef CONFIG_ACPI_NUMA @@ -426,6 +502,8 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) } else { probe_pci_root_info(info, device, busnum, domain); + /* insert busn res at first */ + pci_add_resource(&resources, &root->secondary); /* * _CRS with no apertures is normal, so only fall back to * defaults or native bridge info if we're ignoring _CRS. @@ -437,10 +515,13 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) x86_pci_root_bus_resources(busnum, &resources); } - bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd, - &resources); + if (!setup_mcfg_map(info, domain, (u8)root->secondary.start, + (u8)root->secondary.end, root->mcfg_addr)) + bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, + sd, &resources); + if (bus) { - bus->subordinate = pci_scan_child_bus(bus); + pci_scan_child_bus(bus); pci_set_host_bridge_release( to_pci_host_bridge(bus->bridge), release_pci_root_info, info); diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index 5aed49b..e9e6ed5 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -121,7 +121,6 @@ static int __init early_fill_mp_bus_info(void) link = (reg >> 8) & 0x03; info = alloc_pci_root_info(min_bus, max_bus, node, link); - sprintf(info->name, "PCI Bus #%02x", min_bus); } /* get the default node and link for left over res */ @@ -300,9 +299,9 @@ static int __init early_fill_mp_bus_info(void) int busnum; struct pci_root_res *root_res; - busnum = info->bus_min; - printk(KERN_DEBUG "bus: [%02x, %02x] on node %x link %x\n", - info->bus_min, info->bus_max, info->node, info->link); + busnum = info->busn.start; + printk(KERN_DEBUG "bus: %pR on node %x link %x\n", + &info->busn, info->node, info->link); list_for_each_entry(root_res, &info->resources, list) printk(KERN_DEBUG "bus: %02x %pR\n", busnum, &root_res->res); diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 306579f..d37e2fe 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -14,7 +14,7 @@ static struct pci_root_info *x86_find_pci_root_info(int bus) return NULL; list_for_each_entry(info, &pci_root_infos, list) - if (info->bus_min == bus) + if (info->busn.start == bus) return info; return NULL; @@ -24,6 +24,8 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) { struct pci_root_info *info = x86_find_pci_root_info(bus); struct pci_root_res *root_res; + struct pci_host_bridge_window *window; + bool found = false; if (!info) goto default_resources; @@ -31,6 +33,16 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) printk(KERN_DEBUG "PCI: root bus %02x: hardware-probed resources\n", bus); + /* already added by acpi ? */ + list_for_each_entry(window, resources, list) + if (window->res->flags & IORESOURCE_BUS) { + found = true; + break; + } + + if (!found) + pci_add_resource(resources, &info->busn); + list_for_each_entry(root_res, &info->resources, list) { struct resource *res; struct resource *root; @@ -66,9 +78,13 @@ struct pci_root_info __init *alloc_pci_root_info(int bus_min, int bus_max, if (!info) return info; + sprintf(info->name, "PCI Bus #%02x", bus_min); + INIT_LIST_HEAD(&info->resources); - info->bus_min = bus_min; - info->bus_max = bus_max; + info->busn.name = info->name; + info->busn.start = bus_min; + info->busn.end = bus_max; + info->busn.flags = IORESOURCE_BUS; info->node = node; info->link = link; diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h index 226a466..ff8f65b 100644 --- a/arch/x86/pci/bus_numa.h +++ b/arch/x86/pci/bus_numa.h @@ -13,8 +13,7 @@ struct pci_root_info { struct list_head list; char name[12]; struct list_head resources; - int bus_min; - int bus_max; + struct resource busn; int node; int link; }; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 0ad990a..720e973f 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -494,7 +494,7 @@ int __init pcibios_init(void) return 0; } -char * __devinit pcibios_setup(char *str) +char * __init pcibios_setup(char *str) { if (!strcmp(str, "off")) { pci_probe = 0; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 301e325..937bcec 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -17,6 +17,8 @@ #include <linux/bitmap.h> #include <linux/dmi.h> #include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/rculist.h> #include <asm/e820.h> #include <asm/pci_x86.h> #include <asm/acpi.h> @@ -24,7 +26,9 @@ #define PREFIX "PCI: " /* Indicate if the mmcfg resources have been placed into the resource table. */ -static int __initdata pci_mmcfg_resources_inserted; +static bool pci_mmcfg_running_state; +static bool pci_mmcfg_arch_init_failed; +static DEFINE_MUTEX(pci_mmcfg_lock); LIST_HEAD(pci_mmcfg_list); @@ -45,24 +49,25 @@ static __init void free_all_mmcfg(void) pci_mmconfig_remove(cfg); } -static __init void list_add_sorted(struct pci_mmcfg_region *new) +static __devinit void list_add_sorted(struct pci_mmcfg_region *new) { struct pci_mmcfg_region *cfg; /* keep list sorted by segment and starting bus number */ - list_for_each_entry(cfg, &pci_mmcfg_list, list) { + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) { if (cfg->segment > new->segment || (cfg->segment == new->segment && cfg->start_bus >= new->start_bus)) { - list_add_tail(&new->list, &cfg->list); + list_add_tail_rcu(&new->list, &cfg->list); return; } } - list_add_tail(&new->list, &pci_mmcfg_list); + list_add_tail_rcu(&new->list, &pci_mmcfg_list); } -static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start, - int end, u64 addr) +static __devinit struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, + int start, + int end, u64 addr) { struct pci_mmcfg_region *new; struct resource *res; @@ -79,8 +84,6 @@ static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start, new->start_bus = start; new->end_bus = end; - list_add_sorted(new); - res = &new->res; res->start = addr + PCI_MMCFG_BUS_OFFSET(start); res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1; @@ -89,9 +92,25 @@ static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start, "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end); res->name = new->name; - printk(KERN_INFO PREFIX "MMCONFIG for domain %04x [bus %02x-%02x] at " - "%pR (base %#lx)\n", segment, start, end, &new->res, - (unsigned long) addr); + return new; +} + +static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start, + int end, u64 addr) +{ + struct pci_mmcfg_region *new; + + new = pci_mmconfig_alloc(segment, start, end, addr); + if (new) { + mutex_lock(&pci_mmcfg_lock); + list_add_sorted(new); + mutex_unlock(&pci_mmcfg_lock); + + pr_info(PREFIX + "MMCONFIG for domain %04x [bus %02x-%02x] at %pR " + "(base %#lx)\n", + segment, start, end, &new->res, (unsigned long)addr); + } return new; } @@ -100,7 +119,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus) { struct pci_mmcfg_region *cfg; - list_for_each_entry(cfg, &pci_mmcfg_list, list) + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) if (cfg->segment == segment && cfg->start_bus <= bus && bus <= cfg->end_bus) return cfg; @@ -343,8 +362,7 @@ static int __init pci_mmcfg_check_hostbridge(void) name = pci_mmcfg_probes[i].probe(); if (name) - printk(KERN_INFO PREFIX "%s with MMCONFIG support\n", - name); + pr_info(PREFIX "%s with MMCONFIG support\n", name); } /* some end_bus_number is crazy, fix it */ @@ -353,19 +371,8 @@ static int __init pci_mmcfg_check_hostbridge(void) return !list_empty(&pci_mmcfg_list); } -static void __init pci_mmcfg_insert_resources(void) -{ - struct pci_mmcfg_region *cfg; - - list_for_each_entry(cfg, &pci_mmcfg_list, list) - insert_resource(&iomem_resource, &cfg->res); - - /* Mark that the resources have been inserted. */ - pci_mmcfg_resources_inserted = 1; -} - -static acpi_status __init check_mcfg_resource(struct acpi_resource *res, - void *data) +static acpi_status __devinit check_mcfg_resource(struct acpi_resource *res, + void *data) { struct resource *mcfg_res = data; struct acpi_resource_address64 address; @@ -401,8 +408,8 @@ static acpi_status __init check_mcfg_resource(struct acpi_resource *res, return AE_OK; } -static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl, - void *context, void **rv) +static acpi_status __devinit find_mboard_resource(acpi_handle handle, u32 lvl, + void *context, void **rv) { struct resource *mcfg_res = context; @@ -415,7 +422,7 @@ static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl, return AE_OK; } -static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used) +static int __devinit is_acpi_reserved(u64 start, u64 end, unsigned not_used) { struct resource mcfg_res; @@ -434,13 +441,15 @@ static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used) typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type); -static int __init is_mmconf_reserved(check_reserved_t is_reserved, - struct pci_mmcfg_region *cfg, int with_e820) +static int __ref is_mmconf_reserved(check_reserved_t is_reserved, + struct pci_mmcfg_region *cfg, + struct device *dev, int with_e820) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); u64 old_size = size; - int valid = 0, num_buses; + int num_buses; + char *method = with_e820 ? "E820" : "ACPI motherboard resources"; while (!is_reserved(addr, addr + size, E820_RESERVED)) { size >>= 1; @@ -448,30 +457,76 @@ static int __init is_mmconf_reserved(check_reserved_t is_reserved, break; } - if (size >= (16UL<<20) || size == old_size) { - printk(KERN_INFO PREFIX "MMCONFIG at %pR reserved in %s\n", - &cfg->res, - with_e820 ? "E820" : "ACPI motherboard resources"); - valid = 1; - - if (old_size != size) { - /* update end_bus */ - cfg->end_bus = cfg->start_bus + ((size>>20) - 1); - num_buses = cfg->end_bus - cfg->start_bus + 1; - cfg->res.end = cfg->res.start + - PCI_MMCFG_BUS_OFFSET(num_buses) - 1; - snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN, - "PCI MMCONFIG %04x [bus %02x-%02x]", - cfg->segment, cfg->start_bus, cfg->end_bus); - printk(KERN_INFO PREFIX - "MMCONFIG for %04x [bus%02x-%02x] " - "at %pR (base %#lx) (size reduced!)\n", - cfg->segment, cfg->start_bus, cfg->end_bus, - &cfg->res, (unsigned long) cfg->address); - } + if (size < (16UL<<20) && size != old_size) + return 0; + + if (dev) + dev_info(dev, "MMCONFIG at %pR reserved in %s\n", + &cfg->res, method); + else + pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n", + &cfg->res, method); + + if (old_size != size) { + /* update end_bus */ + cfg->end_bus = cfg->start_bus + ((size>>20) - 1); + num_buses = cfg->end_bus - cfg->start_bus + 1; + cfg->res.end = cfg->res.start + + PCI_MMCFG_BUS_OFFSET(num_buses) - 1; + snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN, + "PCI MMCONFIG %04x [bus %02x-%02x]", + cfg->segment, cfg->start_bus, cfg->end_bus); + + if (dev) + dev_info(dev, + "MMCONFIG " + "at %pR (base %#lx) (size reduced!)\n", + &cfg->res, (unsigned long) cfg->address); + else + pr_info(PREFIX + "MMCONFIG for %04x [bus%02x-%02x] " + "at %pR (base %#lx) (size reduced!)\n", + cfg->segment, cfg->start_bus, cfg->end_bus, + &cfg->res, (unsigned long) cfg->address); } - return valid; + return 1; +} + +static int __ref pci_mmcfg_check_reserved(struct device *dev, + struct pci_mmcfg_region *cfg, int early) +{ + if (!early && !acpi_disabled) { + if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) + return 1; + + if (dev) + dev_info(dev, FW_INFO + "MMCONFIG at %pR not reserved in " + "ACPI motherboard resources\n", + &cfg->res); + else + pr_info(FW_INFO PREFIX + "MMCONFIG at %pR not reserved in " + "ACPI motherboard resources\n", + &cfg->res); + } + + /* + * e820_all_mapped() is marked as __init. + * All entries from ACPI MCFG table have been checked at boot time. + * For MCFG information constructed from hotpluggable host bridge's + * _CBA method, just assume it's reserved. + */ + if (pci_mmcfg_running_state) + return 1; + + /* Don't try to do this check unless configuration + type 1 is available. how about type 2 ?*/ + if (raw_pci_ops) + return is_mmconf_reserved(e820_all_mapped, cfg, dev, 1); + + return 0; } static void __init pci_mmcfg_reject_broken(int early) @@ -479,38 +534,14 @@ static void __init pci_mmcfg_reject_broken(int early) struct pci_mmcfg_region *cfg; list_for_each_entry(cfg, &pci_mmcfg_list, list) { - int valid = 0; - - if (!early && !acpi_disabled) { - valid = is_mmconf_reserved(is_acpi_reserved, cfg, 0); - - if (valid) - continue; - else - printk(KERN_ERR FW_BUG PREFIX - "MMCONFIG at %pR not reserved in " - "ACPI motherboard resources\n", - &cfg->res); + if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) { + pr_info(PREFIX "not using MMCONFIG\n"); + free_all_mmcfg(); + return; } - - /* Don't try to do this check unless configuration - type 1 is available. how about type 2 ?*/ - if (raw_pci_ops) - valid = is_mmconf_reserved(e820_all_mapped, cfg, 1); - - if (!valid) - goto reject; } - - return; - -reject: - printk(KERN_INFO PREFIX "not using MMCONFIG\n"); - free_all_mmcfg(); } -static int __initdata known_bridge; - static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg, struct acpi_mcfg_allocation *cfg) { @@ -529,7 +560,7 @@ static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg, return 0; } - printk(KERN_ERR PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx " + pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx " "is above 4GB, ignored\n", cfg->pci_segment, cfg->start_bus_number, cfg->end_bus_number, cfg->address); return -EINVAL; @@ -556,7 +587,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) i -= sizeof(struct acpi_mcfg_allocation); }; if (entries == 0) { - printk(KERN_ERR PREFIX "MMCONFIG has no entries\n"); + pr_err(PREFIX "MMCONFIG has no entries\n"); return -ENODEV; } @@ -570,8 +601,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number, cfg->end_bus_number, cfg->address) == NULL) { - printk(KERN_WARNING PREFIX - "no memory for MCFG entries\n"); + pr_warn(PREFIX "no memory for MCFG entries\n"); free_all_mmcfg(); return -ENOMEM; } @@ -582,28 +612,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) static void __init __pci_mmcfg_init(int early) { - /* MMCONFIG disabled */ - if ((pci_probe & PCI_PROBE_MMCONF) == 0) - return; - - /* MMCONFIG already enabled */ - if (!early && !(pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF)) - return; - - /* for late to exit */ - if (known_bridge) - return; - - if (early) { - if (pci_mmcfg_check_hostbridge()) - known_bridge = 1; - } - - if (!known_bridge) - acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); - pci_mmcfg_reject_broken(early); - if (list_empty(&pci_mmcfg_list)) return; @@ -620,33 +629,48 @@ static void __init __pci_mmcfg_init(int early) if (pci_mmcfg_arch_init()) pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; else { - /* - * Signal not to attempt to insert mmcfg resources because - * the architecture mmcfg setup could not initialize. - */ - pci_mmcfg_resources_inserted = 1; + free_all_mmcfg(); + pci_mmcfg_arch_init_failed = true; } } +static int __initdata known_bridge; + void __init pci_mmcfg_early_init(void) { - __pci_mmcfg_init(1); + if (pci_probe & PCI_PROBE_MMCONF) { + if (pci_mmcfg_check_hostbridge()) + known_bridge = 1; + else + acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); + __pci_mmcfg_init(1); + } } void __init pci_mmcfg_late_init(void) { - __pci_mmcfg_init(0); + /* MMCONFIG disabled */ + if ((pci_probe & PCI_PROBE_MMCONF) == 0) + return; + + if (known_bridge) + return; + + /* MMCONFIG hasn't been enabled yet, try again */ + if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) { + acpi_sfi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); + __pci_mmcfg_init(0); + } } static int __init pci_mmcfg_late_insert_resources(void) { - /* - * If resources are already inserted or we are not using MMCONFIG, - * don't insert the resources. - */ - if ((pci_mmcfg_resources_inserted == 1) || - (pci_probe & PCI_PROBE_MMCONF) == 0 || - list_empty(&pci_mmcfg_list)) + struct pci_mmcfg_region *cfg; + + pci_mmcfg_running_state = true; + + /* If we are not using MMCONFIG, don't insert the resources. */ + if ((pci_probe & PCI_PROBE_MMCONF) == 0) return 1; /* @@ -654,7 +678,9 @@ static int __init pci_mmcfg_late_insert_resources(void) * marked so it won't cause request errors when __request_region is * called. */ - pci_mmcfg_insert_resources(); + list_for_each_entry(cfg, &pci_mmcfg_list, list) + if (!cfg->res.parent) + insert_resource(&iomem_resource, &cfg->res); return 0; } @@ -665,3 +691,101 @@ static int __init pci_mmcfg_late_insert_resources(void) * with other system resources. */ late_initcall(pci_mmcfg_late_insert_resources); + +/* Add MMCFG information for host bridges */ +int __devinit pci_mmconfig_insert(struct device *dev, + u16 seg, u8 start, u8 end, + phys_addr_t addr) +{ + int rc; + struct resource *tmp = NULL; + struct pci_mmcfg_region *cfg; + + if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed) + return -ENODEV; + + if (start > end) + return -EINVAL; + + mutex_lock(&pci_mmcfg_lock); + cfg = pci_mmconfig_lookup(seg, start); + if (cfg) { + if (cfg->end_bus < end) + dev_info(dev, FW_INFO + "MMCONFIG for " + "domain %04x [bus %02x-%02x] " + "only partially covers this bridge\n", + cfg->segment, cfg->start_bus, cfg->end_bus); + mutex_unlock(&pci_mmcfg_lock); + return -EEXIST; + } + + if (!addr) { + mutex_unlock(&pci_mmcfg_lock); + return -EINVAL; + } + + rc = -EBUSY; + cfg = pci_mmconfig_alloc(seg, start, end, addr); + if (cfg == NULL) { + dev_warn(dev, "fail to add MMCONFIG (out of memory)\n"); + rc = -ENOMEM; + } else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) { + dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n", + &cfg->res); + } else { + /* Insert resource if it's not in boot stage */ + if (pci_mmcfg_running_state) + tmp = insert_resource_conflict(&iomem_resource, + &cfg->res); + + if (tmp) { + dev_warn(dev, + "MMCONFIG %pR conflicts with " + "%s %pR\n", + &cfg->res, tmp->name, tmp); + } else if (pci_mmcfg_arch_map(cfg)) { + dev_warn(dev, "fail to map MMCONFIG %pR.\n", + &cfg->res); + } else { + list_add_sorted(cfg); + dev_info(dev, "MMCONFIG at %pR (base %#lx)\n", + &cfg->res, (unsigned long)addr); + cfg = NULL; + rc = 0; + } + } + + if (cfg) { + if (cfg->res.parent) + release_resource(&cfg->res); + kfree(cfg); + } + + mutex_unlock(&pci_mmcfg_lock); + + return rc; +} + +/* Delete MMCFG information for host bridges */ +int pci_mmconfig_delete(u16 seg, u8 start, u8 end) +{ + struct pci_mmcfg_region *cfg; + + mutex_lock(&pci_mmcfg_lock); + list_for_each_entry_rcu(cfg, &pci_mmcfg_list, list) + if (cfg->segment == seg && cfg->start_bus == start && + cfg->end_bus == end) { + list_del_rcu(&cfg->list); + synchronize_rcu(); + pci_mmcfg_arch_unmap(cfg); + if (cfg->res.parent) + release_resource(&cfg->res); + mutex_unlock(&pci_mmcfg_lock); + kfree(cfg); + return 0; + } + mutex_unlock(&pci_mmcfg_lock); + + return -ENOENT; +} diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index 5372e86..db63ac2 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/init.h> +#include <linux/rcupdate.h> #include <asm/e820.h> #include <asm/pci_x86.h> #include <acpi/acpi.h> @@ -60,9 +61,12 @@ err: *value = -1; return -EINVAL; } + rcu_read_lock(); base = get_base_addr(seg, bus, devfn); - if (!base) + if (!base) { + rcu_read_unlock(); goto err; + } raw_spin_lock_irqsave(&pci_config_lock, flags); @@ -80,6 +84,7 @@ err: *value = -1; break; } raw_spin_unlock_irqrestore(&pci_config_lock, flags); + rcu_read_unlock(); return 0; } @@ -93,9 +98,12 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, if ((bus > 255) || (devfn > 255) || (reg > 4095)) return -EINVAL; + rcu_read_lock(); base = get_base_addr(seg, bus, devfn); - if (!base) + if (!base) { + rcu_read_unlock(); return -EINVAL; + } raw_spin_lock_irqsave(&pci_config_lock, flags); @@ -113,11 +121,12 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, break; } raw_spin_unlock_irqrestore(&pci_config_lock, flags); + rcu_read_unlock(); return 0; } -static const struct pci_raw_ops pci_mmcfg = { +const struct pci_raw_ops pci_mmcfg = { .read = pci_mmcfg_read, .write = pci_mmcfg_write, }; @@ -132,3 +141,18 @@ int __init pci_mmcfg_arch_init(void) void __init pci_mmcfg_arch_free(void) { } + +int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) +{ + return 0; +} + +void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg) +{ + unsigned long flags; + + /* Invalidate the cached mmcfg map entry. */ + raw_spin_lock_irqsave(&pci_config_lock, flags); + mmcfg_last_accessed_device = 0; + raw_spin_unlock_irqrestore(&pci_config_lock, flags); +} diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 915a493..d4ebd07 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/bitmap.h> +#include <linux/rcupdate.h> #include <asm/e820.h> #include <asm/pci_x86.h> @@ -34,9 +35,12 @@ err: *value = -1; return -EINVAL; } + rcu_read_lock(); addr = pci_dev_base(seg, bus, devfn); - if (!addr) + if (!addr) { + rcu_read_unlock(); goto err; + } switch (len) { case 1: @@ -49,6 +53,7 @@ err: *value = -1; *value = mmio_config_readl(addr + reg); break; } + rcu_read_unlock(); return 0; } @@ -62,9 +67,12 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, if (unlikely((bus > 255) || (devfn > 255) || (reg > 4095))) return -EINVAL; + rcu_read_lock(); addr = pci_dev_base(seg, bus, devfn); - if (!addr) + if (!addr) { + rcu_read_unlock(); return -EINVAL; + } switch (len) { case 1: @@ -77,16 +85,17 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, mmio_config_writel(addr + reg, value); break; } + rcu_read_unlock(); return 0; } -static const struct pci_raw_ops pci_mmcfg = { +const struct pci_raw_ops pci_mmcfg = { .read = pci_mmcfg_read, .write = pci_mmcfg_write, }; -static void __iomem * __init mcfg_ioremap(struct pci_mmcfg_region *cfg) +static void __iomem * __devinit mcfg_ioremap(struct pci_mmcfg_region *cfg) { void __iomem *addr; u64 start, size; @@ -105,16 +114,14 @@ int __init pci_mmcfg_arch_init(void) { struct pci_mmcfg_region *cfg; - list_for_each_entry(cfg, &pci_mmcfg_list, list) { - cfg->virt = mcfg_ioremap(cfg); - if (!cfg->virt) { - printk(KERN_ERR PREFIX "can't map MMCONFIG at %pR\n", - &cfg->res); + list_for_each_entry(cfg, &pci_mmcfg_list, list) + if (pci_mmcfg_arch_map(cfg)) { pci_mmcfg_arch_free(); return 0; } - } + raw_pci_ext_ops = &pci_mmcfg; + return 1; } @@ -122,10 +129,25 @@ void __init pci_mmcfg_arch_free(void) { struct pci_mmcfg_region *cfg; - list_for_each_entry(cfg, &pci_mmcfg_list, list) { - if (cfg->virt) { - iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus)); - cfg->virt = NULL; - } + list_for_each_entry(cfg, &pci_mmcfg_list, list) + pci_mmcfg_arch_unmap(cfg); +} + +int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) +{ + cfg->virt = mcfg_ioremap(cfg); + if (!cfg->virt) { + pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res); + return -ENOMEM; + } + + return 0; +} + +void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg) +{ + if (cfg && cfg->virt) { + iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus)); + cfg->virt = NULL; } } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 140942f..e14a2ff 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -264,7 +264,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup); static void __devinit mrst_power_off_unused_dev(struct pci_dev *dev) { - pci_set_power_state(dev, PCI_D3cold); + pci_set_power_state(dev, PCI_D3hot); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0801, mrst_power_off_unused_dev); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0809, mrst_power_off_unused_dev); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ed7d549..bf4bda6 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,6 +31,7 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/syscore_ops.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -38,6 +39,7 @@ #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> #include <xen/interface/memory.h> +#include <xen/interface/xen-mca.h> #include <xen/features.h> #include <xen/page.h> #include <xen/hvm.h> @@ -107,7 +109,7 @@ EXPORT_SYMBOL_GPL(xen_have_vector_callback); * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ -struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; +struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; /* * Flag to determine whether vcpu info placement is available on all @@ -124,6 +126,19 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; */ static int have_vcpu_info_placement = 1; +struct tls_descs { + struct desc_struct desc[3]; +}; + +/* + * Updating the 3 TLS descriptors in the GDT on every task switch is + * surprisingly expensive so we avoid updating them if they haven't + * changed. Since Xen writes different descriptors than the one + * passed in the update_descriptor hypercall we keep shadow copies to + * compare against. + */ +static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); + static void clamp_max_cpus(void) { #ifdef CONFIG_SMP @@ -341,9 +356,7 @@ static void __init xen_init_cpuid_mask(void) unsigned int xsave_mask; cpuid_leaf1_edx_mask = - ~((1 << X86_FEATURE_MCE) | /* disable MCE */ - (1 << X86_FEATURE_MCA) | /* disable MCA */ - (1 << X86_FEATURE_MTRR) | /* disable MTRR */ + ~((1 << X86_FEATURE_MTRR) | /* disable MTRR */ (1 << X86_FEATURE_ACC)); /* thermal monitoring */ if (!xen_initial_domain()) @@ -540,12 +553,28 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) BUG(); } +static inline bool desc_equal(const struct desc_struct *d1, + const struct desc_struct *d2) +{ + return d1->a == d2->a && d1->b == d2->b; +} + static void load_TLS_descriptor(struct thread_struct *t, unsigned int cpu, unsigned int i) { - struct desc_struct *gdt = get_cpu_gdt_table(cpu); - xmaddr_t maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); - struct multicall_space mc = __xen_mc_entry(0); + struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i]; + struct desc_struct *gdt; + xmaddr_t maddr; + struct multicall_space mc; + + if (desc_equal(shadow, &t->tls_array[i])) + return; + + *shadow = t->tls_array[i]; + + gdt = get_cpu_gdt_table(cpu); + maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); + mc = __xen_mc_entry(0); MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]); } @@ -627,8 +656,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, /* * Look for known traps using IST, and substitute them * appropriately. The debugger ones are the only ones we care - * about. Xen will handle faults like double_fault and - * machine_check, so we should never see them. Warn if + * about. Xen will handle faults like double_fault, + * so we should never see them. Warn if * there's an unexpected IST-using fault handler. */ if (addr == (unsigned long)debug) @@ -643,7 +672,11 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, return 0; #ifdef CONFIG_X86_MCE } else if (addr == (unsigned long)machine_check) { - return 0; + /* + * when xen hypervisor inject vMCE to guest, + * use native mce handler to handle it + */ + ; #endif } else { /* Some other trap using IST? */ @@ -1437,64 +1470,155 @@ asmlinkage void __init xen_start_kernel(void) #endif } -static int init_hvm_pv_info(int *major, int *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); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - - xen_setup_features(); - - pv_info.name = "Xen HVM"; - - xen_domain_type = XEN_HVM_DOMAIN; +#ifdef CONFIG_XEN_PVHVM +/* + * The pfn containing the shared_info is located somewhere in RAM. This + * will cause trouble if the current kernel is doing a kexec boot into a + * new kernel. The new kernel (and its startup code) can not know where + * the pfn is, so it can not reserve the page. The hypervisor will + * continue to update the pfn, and as a result memory corruption occours + * in the new kernel. + * + * One way to work around this issue is to allocate a page in the + * xen-platform pci device's BAR memory range. But pci init is done very + * late and the shared_info page is already in use very early to read + * the pvclock. So moving the pfn from RAM to MMIO is racy because some + * code paths on other vcpus could access the pfn during the small + * window when the old pfn is moved to the new pfn. There is even a + * small window were the old pfn is not backed by a mfn, and during that + * time all reads return -1. + * + * Because it is not known upfront where the MMIO region is located it + * can not be used right from the start in xen_hvm_init_shared_info. + * + * To minimise trouble the move of the pfn is done shortly before kexec. + * This does not eliminate the race because all vcpus are still online + * when the syscore_ops will be called. But hopefully there is no work + * pending at this point in time. Also the syscore_op is run last which + * reduces the risk further. + */ - return 0; -} +static struct shared_info *xen_hvm_shared_info; -void __ref xen_hvm_init_shared_info(void) +static void xen_hvm_connect_shared_info(unsigned long pfn) { - 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 = __pa(shared_info_page) >> PAGE_SHIFT; + xatp.gpfn = pfn; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); - HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; +} +static void xen_hvm_set_shared_info(struct shared_info *sip) +{ + int cpu; + + HYPERVISOR_shared_info = sip; /* 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. - * 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 + * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_set_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]; } } -#ifdef CONFIG_XEN_PVHVM +/* Reconnect the shared_info pfn to a mfn */ +void xen_hvm_resume_shared_info(void) +{ + xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); +} + +#ifdef CONFIG_KEXEC +static struct shared_info *xen_hvm_shared_info_kexec; +static unsigned long xen_hvm_shared_info_pfn_kexec; + +/* Remember a pfn in MMIO space for kexec reboot */ +void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn) +{ + xen_hvm_shared_info_kexec = sip; + xen_hvm_shared_info_pfn_kexec = pfn; +} + +static void xen_hvm_syscore_shutdown(void) +{ + struct xen_memory_reservation reservation = { + .domid = DOMID_SELF, + .nr_extents = 1, + }; + unsigned long prev_pfn; + int rc; + + if (!xen_hvm_shared_info_kexec) + return; + + prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT; + set_xen_guest_handle(reservation.extent_start, &prev_pfn); + + /* Move pfn to MMIO, disconnects previous pfn from mfn */ + xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec); + + /* Update pointers, following hypercall is also a memory barrier */ + xen_hvm_set_shared_info(xen_hvm_shared_info_kexec); + + /* Allocate new mfn for previous pfn */ + do { + rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); + if (rc == 0) + msleep(123); + } while (rc == 0); + + /* Make sure the previous pfn is really connected to a (new) mfn */ + BUG_ON(rc != 1); +} + +static struct syscore_ops xen_hvm_syscore_ops = { + .shutdown = xen_hvm_syscore_shutdown, +}; +#endif + +/* Use a pfn in RAM, may move to MMIO before kexec. */ +static void __init xen_hvm_init_shared_info(void) +{ + /* Remember pointer for resume */ + xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); + xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); + xen_hvm_set_shared_info(xen_hvm_shared_info); +} + +static void __init init_hvm_pv_info(void) +{ + 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); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + xen_setup_features(); + + pv_info.name = "Xen HVM"; + + xen_domain_type = XEN_HVM_DOMAIN; +} + static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -1517,14 +1641,12 @@ static struct notifier_block xen_hvm_cpu_notifier __cpuinitdata = { static void __init xen_hvm_guest_init(void) { - int r; - int major, minor; - - r = init_hvm_pv_info(&major, &minor); - if (r < 0) - return; + init_hvm_pv_info(); xen_hvm_init_shared_info(); +#ifdef CONFIG_KEXEC + register_syscore_ops(&xen_hvm_syscore_ops); +#endif if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3a73785..27336df 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -308,8 +308,20 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) static inline void __xen_set_pte(pte_t *ptep, pte_t pteval) { - if (!xen_batched_set_pte(ptep, pteval)) - native_set_pte(ptep, pteval); + if (!xen_batched_set_pte(ptep, pteval)) { + /* + * Could call native_set_pte() here and trap and + * emulate the PTE write but with 32-bit guests this + * needs two traps (one for each of the two 32-bit + * words in the PTE) so do one hypercall directly + * instead. + */ + struct mmu_update u; + + u.ptr = virt_to_machine(ptep).maddr | MMU_NORMAL_PT_UPDATE; + u.val = pte_val_ma(pteval); + HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF); + } } static void xen_set_pte(pte_t *ptep, pte_t pteval) @@ -1416,13 +1428,28 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) } #endif /* CONFIG_X86_64 */ -/* Init-time set_pte while constructing initial pagetables, which - doesn't allow RO pagetable pages to be remapped RW */ +/* + * Init-time set_pte while constructing initial pagetables, which + * doesn't allow RO page table pages to be remapped RW. + * + * If there is no MFN for this PFN then this page is initially + * ballooned out so clear the PTE (as in decrease_reservation() in + * drivers/xen/balloon.c). + * + * Many of these PTE updates are done on unpinned and writable pages + * and doing a hypercall for these is unnecessary and expensive. At + * this point it is not possible to tell if a page is pinned or not, + * so always write the PTE directly and rely on Xen trapping and + * emulating any updates as necessary. + */ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) { - pte = mask_rw_pte(ptep, pte); + if (pte_mfn(pte) != INVALID_P2M_ENTRY) + pte = mask_rw_pte(ptep, pte); + else + pte = __pte_ma(0); - xen_set_pte(ptep, pte); + native_set_pte(ptep, pte); } static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a4790bf..ead8557 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -157,25 +157,24 @@ static unsigned long __init xen_populate_chunk( unsigned long dest_pfn; for (i = 0, entry = list; i < map_size; i++, entry++) { - unsigned long credits = credits_left; unsigned long s_pfn; unsigned long e_pfn; unsigned long pfns; long capacity; - if (credits <= 0) + if (credits_left <= 0) break; if (entry->type != E820_RAM) continue; - e_pfn = PFN_UP(entry->addr + entry->size); + e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after the xen_start_info->nr_pages */ if (e_pfn <= max_pfn) continue; - s_pfn = PFN_DOWN(entry->addr); + s_pfn = PFN_UP(entry->addr); /* If the E820 falls within the nr_pages, we want to start * at the nr_pages PFN. * If that would mean going past the E820 entry, skip it @@ -184,23 +183,19 @@ static unsigned long __init xen_populate_chunk( capacity = e_pfn - max_pfn; dest_pfn = max_pfn; } else { - /* last_pfn MUST be within E820_RAM regions */ - if (*last_pfn && e_pfn >= *last_pfn) - s_pfn = *last_pfn; capacity = e_pfn - s_pfn; dest_pfn = s_pfn; } - /* If we had filled this E820_RAM entry, go to the next one. */ - if (capacity <= 0) - continue; - if (credits > capacity) - credits = capacity; + if (credits_left < capacity) + capacity = credits_left; - pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false); + pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false); done += pfns; - credits_left -= pfns; *last_pfn = (dest_pfn + pfns); + if (pfns < capacity) + break; + credits_left -= pfns; } return done; } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 45329c8..ae8a00c 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_init_shared_info(); + xen_hvm_resume_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 202d4c1..1e4329e 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -41,7 +41,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_init_shared_info(void); +void xen_hvm_resume_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c index eb30e35..69759e9 100644 --- a/arch/xtensa/kernel/pci.c +++ b/arch/xtensa/kernel/pci.c @@ -46,7 +46,6 @@ * pcibios_fixups * pcibios_align_resource * pcibios_fixup_bus - * pcibios_setup * pci_bus_add_device * pci_mmap_page_range */ @@ -187,7 +186,7 @@ static int __init pcibios_init(void) bus = pci_scan_root_bus(NULL, pci_ctrl->first_busno, pci_ctrl->ops, pci_ctrl, &resources); pci_ctrl->bus = bus; - pci_ctrl->last_busno = bus->subordinate; + pci_ctrl->last_busno = bus->busn_res.end; if (next_busno <= pci_ctrl->last_busno) next_busno = pci_ctrl->last_busno+1; } @@ -206,11 +205,6 @@ void __init pcibios_fixup_bus(struct pci_bus *bus) } } -char __init *pcibios_setup(char *str) -{ - return str; -} - void pcibios_set_master(struct pci_dev *dev) { /* No special bus mastering setup handling */ |