diff options
94 files changed, 2033 insertions, 1338 deletions
@@ -84,6 +84,7 @@ Mayuresh Janorkar <mayur@ti.com> Michael Buesch <m@bues.ch> Michel Dänzer <michel@tungstengraphics.com> Mitesh shah <mshah@teja.com> +Mohit Kumar <mohit.kumar@st.com> <mohit.kumar.dhaka@gmail.com> Morten Welinder <terra@gnome.org> Morten Welinder <welinder@anemone.rentec.com> Morten Welinder <welinder@darter.rentec.com> @@ -95,10 +96,12 @@ Patrick Mochel <mochel@digitalimplant.org> Peter A Jonsson <pj@ludd.ltu.se> Peter Oruba <peter@oruba.de> Peter Oruba <peter.oruba@amd.com> +Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com> Praveen BP <praveenbp@ti.com> Rajesh Shah <rajesh.shah@intel.com> Ralf Baechle <ralf@linux-mips.org> Ralf Wildenhues <Ralf.Wildenhues@gmx.de> +Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net> Rémi Denis-Courmont <rdenis@simphalempin.com> Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com> Rudolf Marek <R.Marek@sh.cvut.cz> diff --git a/Documentation/ABI/testing/configfs-spear-pcie-gadget b/Documentation/ABI/testing/configfs-spear-pcie-gadget index 8759881..840c324 100644 --- a/Documentation/ABI/testing/configfs-spear-pcie-gadget +++ b/Documentation/ABI/testing/configfs-spear-pcie-gadget @@ -1,7 +1,7 @@ What: /config/pcie-gadget Date: Feb 2011 KernelVersion: 2.6.37 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Interface is used to configure selected dual mode PCIe controller diff --git a/Documentation/ABI/testing/dev-kmsg b/Documentation/ABI/testing/dev-kmsg index bb820be..fff817e 100644 --- a/Documentation/ABI/testing/dev-kmsg +++ b/Documentation/ABI/testing/dev-kmsg @@ -98,4 +98,13 @@ Description: The /dev/kmsg character device node provides userspace access logic is used internally when messages are printed to the console, /proc/kmsg or the syslog() syscall. + By default, kernel tries to avoid fragments by concatenating + when it can and fragments are rare; however, when extended + console support is enabled, the in-kernel concatenation is + disabled and /dev/kmsg output will contain more fragments. If + the log consumer performs concatenation, the end result + should be the same. In the future, the in-kernel concatenation + may be removed entirely and /dev/kmsg users are recommended to + implement fragment handling. + Users: dmesg(1), userspace kernel log consumers diff --git a/Documentation/ABI/testing/sysfs-bus-usb-lvstest b/Documentation/ABI/testing/sysfs-bus-usb-lvstest index aae68fc..5151290 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb-lvstest +++ b/Documentation/ABI/testing/sysfs-bus-usb-lvstest @@ -4,14 +4,14 @@ driver is bound with root hub device. What: /sys/bus/usb/devices/.../get_dev_desc Date: March 2014 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Write to this node to issue "Get Device Descriptor" for Link Layer Validation device. It is needed for TD.7.06. What: /sys/bus/usb/devices/.../u1_timeout Date: March 2014 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Set "U1 timeout" for the downstream port where Link Layer Validation device is connected. Timeout value must be between 0 @@ -19,7 +19,7 @@ Description: What: /sys/bus/usb/devices/.../u2_timeout Date: March 2014 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Set "U2 timeout" for the downstream port where Link Layer Validation device is connected. Timeout value must be between 0 @@ -27,21 +27,21 @@ Description: What: /sys/bus/usb/devices/.../hot_reset Date: March 2014 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Write to this node to issue "Reset" for Link Layer Validation device. It is needed for TD.7.29, TD.7.31, TD.7.34 and TD.7.35. What: /sys/bus/usb/devices/.../u3_entry Date: March 2014 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Write to this node to issue "U3 entry" for Link Layer Validation device. It is needed for TD.7.35 and TD.7.36. What: /sys/bus/usb/devices/.../u3_exit Date: March 2014 -Contact: Pratyush Anand <pratyush.anand@st.com> +Contact: Pratyush Anand <pratyush.anand@gmail.com> Description: Write to this node to issue "U3 exit" for Link Layer Validation device. It is needed for TD.7.36. diff --git a/Documentation/ABI/testing/sysfs-class-zram b/Documentation/ABI/testing/sysfs-class-zram new file mode 100644 index 0000000..48ddacb --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-zram @@ -0,0 +1,24 @@ +What: /sys/class/zram-control/ +Date: August 2015 +KernelVersion: 4.2 +Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> +Description: + The zram-control/ class sub-directory belongs to zram + device class + +What: /sys/class/zram-control/hot_add +Date: August 2015 +KernelVersion: 4.2 +Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> +Description: + RO attribute. Read operation will cause zram to add a new + device and return its device id back to user (so one can + use /dev/zram<id>), or error code. + +What: /sys/class/zram-control/hot_remove +Date: August 2015 +KernelVersion: 4.2 +Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> +Description: + WO attribute. Remove a specific /dev/zramX device, where X + is a device_id provided by user. diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 48a183e..c4de576 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -19,7 +19,9 @@ Following shows a typical sequence of steps for using zram. 1) Load Module: modprobe zram num_devices=4 This creates 4 devices: /dev/zram{0,1,2,3} - (num_devices parameter is optional. Default: 1) + +num_devices parameter is optional and tells zram how many devices should be +pre-created. Default: 1. 2) Set max number of compression streams Compression backend may use up to max_comp_streams compression streams, @@ -97,7 +99,24 @@ size of the disk when not in use so a huge zram is wasteful. mkfs.ext4 /dev/zram1 mount /dev/zram1 /tmp -7) Stats: +7) Add/remove zram devices + +zram provides a control interface, which enables dynamic (on-demand) device +addition and removal. + +In order to add a new /dev/zramX device, perform read operation on hot_add +attribute. This will return either new device's device id (meaning that you +can use /dev/zram<id>) or error code. + +Example: + cat /sys/class/zram-control/hot_add + 1 + +To remove the existing /dev/zramX device (where X is a device id) +execute + echo X > /sys/class/zram-control/hot_remove + +8) Stats: Per-device statistics are exported as various nodes under /sys/block/zram<id>/ A brief description of exported device attritbutes. For more details please @@ -126,7 +145,7 @@ mem_used_max RW the maximum amount memory zram have consumed to mem_limit RW the maximum amount of memory ZRAM can use to store the compressed data num_migrated RO the number of objects migrated migrated by compaction - +compact WO trigger memory compaction WARNING ======= @@ -172,11 +191,11 @@ line of text and contains the following stats separated by whitespace: zero_pages num_migrated -8) Deactivate: +9) Deactivate: swapoff /dev/zram0 umount /dev/zram1 -9) Reset: +10) Reset: Write any positive value to 'reset' sysfs node echo 1 > /sys/block/zram0/reset echo 1 > /sys/block/zram1/reset diff --git a/Documentation/misc-devices/spear-pcie-gadget.txt b/Documentation/misc-devices/spear-pcie-gadget.txt index 02c13ef..89b88de 100644 --- a/Documentation/misc-devices/spear-pcie-gadget.txt +++ b/Documentation/misc-devices/spear-pcie-gadget.txt @@ -2,7 +2,7 @@ Spear PCIe Gadget Driver: Author ============= -Pratyush Anand (pratyush.anand@st.com) +Pratyush Anand (pratyush.anand@gmail.com) Location ============ diff --git a/Documentation/networking/netconsole.txt b/Documentation/networking/netconsole.txt index a5d574a..30409a3 100644 --- a/Documentation/networking/netconsole.txt +++ b/Documentation/networking/netconsole.txt @@ -2,6 +2,7 @@ started by Ingo Molnar <mingo@redhat.com>, 2001.09.17 2.6 port and netpoll api by Matt Mackall <mpm@selenic.com>, Sep 9 2003 IPv6 support by Cong Wang <xiyou.wangcong@gmail.com>, Jan 1 2013 +Extended console support by Tejun Heo <tj@kernel.org>, May 1 2015 Please send bug reports to Matt Mackall <mpm@selenic.com> Satyam Sharma <satyam.sharma@gmail.com>, and Cong Wang <xiyou.wangcong@gmail.com> @@ -24,9 +25,10 @@ Sender and receiver configuration: It takes a string configuration parameter "netconsole" in the following format: - netconsole=[src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr] + netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr] where + + if present, enable extended console support src-port source for UDP packets (defaults to 6665) src-ip source IP to use (interface address) dev network interface (eth0) @@ -107,6 +109,7 @@ To remove a target: The interface exposes these parameters of a netconsole target to userspace: enabled Is this target currently enabled? (read-write) + extended Extended mode enabled (read-write) dev_name Local network interface name (read-write) local_port Source UDP port to use (read-write) remote_port Remote agent's UDP port (read-write) @@ -132,6 +135,36 @@ You can also update the local interface dynamically. This is especially useful if you want to use interfaces that have newly come up (and may not have existed when netconsole was loaded / initialized). +Extended console: +================= + +If '+' is prefixed to the configuration line or "extended" config file +is set to 1, extended console support is enabled. An example boot +param follows. + + linux netconsole=+4444@10.0.0.1/eth1,9353@10.0.0.2/12:34:56:78:9a:bc + +Log messages are transmitted with extended metadata header in the +following format which is the same as /dev/kmsg. + + <level>,<sequnum>,<timestamp>,<contflag>;<message text> + +Non printable characters in <message text> are escaped using "\xff" +notation. If the message contains optional dictionary, verbatim +newline is used as the delimeter. + +If a message doesn't fit in certain number of bytes (currently 1000), +the message is split into multiple fragments by netconsole. These +fragments are transmitted with "ncfrag" header field added. + + ncfrag=<byte-offset>/<total-bytes> + +For example, assuming a lot smaller chunk size, a message "the first +chunk, the 2nd chunk." may be split as follows. + + 6,416,1758426,-,ncfrag=0/31;the first chunk, + 6,416,1758426,-,ncfrag=16/31; the 2nd chunk. + Miscellaneous notes: ==================== diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index e5d528e..6fccb69 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -197,8 +197,8 @@ core_pattern is used to specify a core dumpfile pattern name. %P global pid (init PID namespace) %i tid %I global tid (init PID namespace) - %u uid - %g gid + %u uid (in initial user namespace) + %g gid (in initial user namespace) %d dump mode, matches PR_SET_DUMPABLE and /proc/sys/fs/suid_dumpable %s signal number diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt index 00c3d31..8458c08 100644 --- a/Documentation/vm/zswap.txt +++ b/Documentation/vm/zswap.txt @@ -26,8 +26,22 @@ Zswap evicts pages from compressed cache on an LRU basis to the backing swap device when the compressed pool reaches its size limit. This requirement had been identified in prior community discussions. -To enabled zswap, the "enabled" attribute must be set to 1 at boot time. e.g. -zswap.enabled=1 +Zswap is disabled by default but can be enabled at boot time by setting +the "enabled" attribute to 1 at boot time. ie: zswap.enabled=1. Zswap +can also be enabled and disabled at runtime using the sysfs interface. +An example command to enable zswap at runtime, assuming sysfs is mounted +at /sys, is: + +echo 1 > /sys/modules/zswap/parameters/enabled + +When zswap is disabled at runtime it will stop storing pages that are +being swapped out. However, it will _not_ immediately write out or fault +back into memory all of the pages stored in the compressed pool. The +pages stored in zswap will remain in the compressed pool until they are +either invalidated or faulted back into memory. In order to force all +pages out of the compressed pool, a swapoff on the swap device(s) will +fault back into memory all swapped out pages, including those in the +compressed pool. Design: diff --git a/MAINTAINERS b/MAINTAINERS index a01df30..5f2956c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -259,7 +259,7 @@ S: Maintained F: drivers/platform/x86/acer-wmi.c ACPI -M: Rafael J. Wysocki <rjw@rjwysocki.net> +M: "Rafael J. Wysocki" <rjw@rjwysocki.net> M: Len Brown <lenb@kernel.org> L: linux-acpi@vger.kernel.org W: https://01.org/linux-acpi @@ -280,7 +280,7 @@ F: tools/power/acpi/ ACPI COMPONENT ARCHITECTURE (ACPICA) M: Robert Moore <robert.moore@intel.com> M: Lv Zheng <lv.zheng@intel.com> -M: Rafael J. Wysocki <rafael.j.wysocki@intel.com> +M: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> L: linux-acpi@vger.kernel.org L: devel@acpica.org W: https://acpica.org/ @@ -2515,7 +2515,7 @@ F: arch/powerpc/oprofile/*cell* F: arch/powerpc/platforms/cell/ CEPH DISTRIBUTED FILE SYSTEM CLIENT -M: Yan, Zheng <zyan@redhat.com> +M: "Yan, Zheng" <zyan@redhat.com> M: Sage Weil <sage@redhat.com> L: ceph-devel@vger.kernel.org W: http://ceph.com/ @@ -2829,7 +2829,7 @@ S: Maintained F: drivers/net/ethernet/ti/cpmac.c CPU FREQUENCY DRIVERS -M: Rafael J. Wysocki <rjw@rjwysocki.net> +M: "Rafael J. Wysocki" <rjw@rjwysocki.net> M: Viresh Kumar <viresh.kumar@linaro.org> L: linux-pm@vger.kernel.org S: Maintained @@ -2868,7 +2868,7 @@ F: drivers/cpuidle/cpuidle-exynos.c F: arch/arm/mach-exynos/pm.c CPUIDLE DRIVERS -M: Rafael J. Wysocki <rjw@rjwysocki.net> +M: "Rafael J. Wysocki" <rjw@rjwysocki.net> M: Daniel Lezcano <daniel.lezcano@linaro.org> L: linux-pm@vger.kernel.org S: Maintained @@ -4103,7 +4103,7 @@ F: include/uapi/scsi/fc/ FILE LOCKING (flock() and fcntl()/lockf()) M: Jeff Layton <jlayton@poochiereds.net> -M: J. Bruce Fields <bfields@fieldses.org> +M: "J. Bruce Fields" <bfields@fieldses.org> L: linux-fsdevel@vger.kernel.org S: Maintained F: include/linux/fcntl.h @@ -4299,7 +4299,7 @@ F: sound/soc/fsl/imx* F: sound/soc/fsl/mpc8610_hpcd.c FREESCALE QORIQ MANAGEMENT COMPLEX DRIVER -M: J. German Rivera <German.Rivera@freescale.com> +M: "J. German Rivera" <German.Rivera@freescale.com> L: linux-kernel@vger.kernel.org S: Maintained F: drivers/staging/fsl-mc/ @@ -4581,7 +4581,7 @@ S: Maintained F: drivers/media/usb/gspca/ GUID PARTITION TABLE (GPT) -M: Davidlohr Bueso <davidlohr@hp.com> +M: Davidlohr Bueso <dave@stgolabs.net> L: linux-efi@vger.kernel.org S: Maintained F: block/partitions/efi.* @@ -4871,7 +4871,7 @@ S: Maintained F: fs/hugetlbfs/ Hyper-V CORE AND DRIVERS -M: K. Y. Srinivasan <kys@microsoft.com> +M: "K. Y. Srinivasan" <kys@microsoft.com> M: Haiyang Zhang <haiyangz@microsoft.com> L: devel@linuxdriverproject.org S: Maintained @@ -5233,7 +5233,7 @@ K: \b(ABS|SYN)_MT_ INTEL ASoC BDW/HSW DRIVERS M: Jie Yang <yang.jie@linux.intel.com> -L: alsa-devel@alsa-project.org +L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/intel/sst-haswell* F: sound/soc/intel/sst-dsp* @@ -6825,7 +6825,7 @@ F: drivers/net/ethernet/natsemi/natsemi.c NATIVE INSTRUMENTS USB SOUND INTERFACE DRIVER M: Daniel Mack <zonque@gmail.com> S: Maintained -L: alsa-devel@alsa-project.org +L: alsa-devel@alsa-project.org (moderated for non-subscribers) W: http://www.native-instruments.com F: sound/usb/caiaq/ @@ -7243,7 +7243,7 @@ F: arch/arm/mach-omap2/prm* OMAP AUDIO SUPPORT M: Peter Ujfalusi <peter.ujfalusi@ti.com> M: Jarkko Nikula <jarkko.nikula@bitmer.com> -L: alsa-devel@alsa-project.org (subscribers-only) +L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: linux-omap@vger.kernel.org S: Maintained F: sound/soc/omap/ @@ -7945,7 +7945,7 @@ F: include/linux/power_supply.h F: drivers/power/ PNP SUPPORT -M: Rafael J. Wysocki <rafael.j.wysocki@intel.com> +M: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> S: Maintained F: drivers/pnp/ @@ -8951,7 +8951,7 @@ F: drivers/mmc/host/sdhci-spear.c SECURITY SUBSYSTEM M: James Morris <james.l.morris@oracle.com> -M: Serge E. Hallyn <serge@hallyn.com> +M: "Serge E. Hallyn" <serge@hallyn.com> L: linux-security-module@vger.kernel.org (suggested Cc:) T: git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git W: http://kernsec.org/ @@ -9171,7 +9171,7 @@ F: arch/arm/mach-davinci/ F: drivers/i2c/busses/i2c-davinci.c TI DAVINCI SERIES MEDIA DRIVER -M: Lad, Prabhakar <prabhakar.csengg@gmail.com> +M: "Lad, Prabhakar" <prabhakar.csengg@gmail.com> L: linux-media@vger.kernel.org W: http://linuxtv.org/ Q: http://patchwork.linuxtv.org/project/linux-media/list/ @@ -9181,7 +9181,7 @@ F: drivers/media/platform/davinci/ F: include/media/davinci/ TI AM437X VPFE DRIVER -M: Lad, Prabhakar <prabhakar.csengg@gmail.com> +M: "Lad, Prabhakar" <prabhakar.csengg@gmail.com> L: linux-media@vger.kernel.org W: http://linuxtv.org/ Q: http://patchwork.linuxtv.org/project/linux-media/list/ @@ -9190,7 +9190,7 @@ S: Maintained F: drivers/media/platform/am437x/ OV2659 OMNIVISION SENSOR DRIVER -M: Lad, Prabhakar <prabhakar.csengg@gmail.com> +M: "Lad, Prabhakar" <prabhakar.csengg@gmail.com> L: linux-media@vger.kernel.org W: http://linuxtv.org/ Q: http://patchwork.linuxtv.org/project/linux-media/list/ @@ -9755,7 +9755,7 @@ F: fs/sysv/ F: include/linux/sysv_fs.h TARGET SUBSYSTEM -M: Nicholas A. Bellinger <nab@linux-iscsi.org> +M: "Nicholas A. Bellinger" <nab@linux-iscsi.org> L: linux-scsi@vger.kernel.org L: target-devel@vger.kernel.org W: http://www.linux-iscsi.org @@ -9897,7 +9897,7 @@ F: include/linux/if_team.h F: include/uapi/linux/if_team.h TECHNOLOGIC SYSTEMS TS-5500 PLATFORM SUPPORT -M: Savoir-faire Linux Inc. <kernel@savoirfairelinux.com> +M: "Savoir-faire Linux Inc." <kernel@savoirfairelinux.com> S: Maintained F: arch/x86/platform/ts5500/ diff --git a/arch/Kconfig b/arch/Kconfig index a65eafb..bec6666 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -499,6 +499,13 @@ config ARCH_HAS_ELF_RANDOMIZE - arch_mmap_rnd() - arch_randomize_brk() +config HAVE_COPY_THREAD_TLS + bool + help + Architecture provides copy_thread_tls to accept tls argument via + normal C parameter passing, rather than extracting the syscall + argument from pt_regs. + # # ABI hall of shame # diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index 31bb7dc..7d26f6c 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -63,15 +63,6 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 734c17e..2fd9b14 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -96,15 +96,6 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h index b3d18f9..ae7ac92 100644 --- a/arch/avr32/include/asm/dma-mapping.h +++ b/arch/avr32/include/asm/dma-mapping.h @@ -209,17 +209,18 @@ dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, * the same here. */ static inline int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) { int i; + struct scatterlist *sg; - for (i = 0; i < nents; i++) { + for_each_sg(sglist, sg, nents, i) { char *virt; - sg[i].dma_address = page_to_bus(sg_page(&sg[i])) + sg[i].offset; - virt = sg_virt(&sg[i]); - dma_cache_sync(dev, virt, sg[i].length, direction); + sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset; + virt = sg_virt(sg); + dma_cache_sync(dev, virt, sg->length, direction); } return nents; @@ -321,14 +322,14 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, } static inline void -dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) { int i; + struct scatterlist *sg; - for (i = 0; i < nents; i++) { - dma_cache_sync(dev, sg_virt(&sg[i]), sg[i].length, direction); - } + for_each_sg(sglist, sg, nents, i) + dma_cache_sync(dev, sg_virt(sg), sg->length, direction); } /* Now for the API extensions over the pci_ one */ diff --git a/arch/frv/include/asm/sections.h b/arch/frv/include/asm/sections.h index 17d0fb1..d03fb64 100644 --- a/arch/frv/include/asm/sections.h +++ b/arch/frv/include/asm/sections.h @@ -35,12 +35,6 @@ extern unsigned long __nongprelbss memory_start; extern unsigned long __nongprelbss memory_end; extern unsigned long __nongprelbss rom_length; -/* determine if we're running from ROM */ -static inline int is_in_rom(unsigned long addr) -{ - return 0; /* default case: not in ROM */ -} - #endif #endif #endif /* _ASM_SECTIONS_H */ diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c index b99c2a7..8eeea0d 100644 --- a/arch/frv/mb93090-mb00/pci-dma-nommu.c +++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c @@ -119,14 +119,16 @@ dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, EXPORT_SYMBOL(dma_map_single); -int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) { int i; + struct scatterlist *sg; - for (i=0; i<nents; i++) - frv_cache_wback_inv(sg_dma_address(&sg[i]), - sg_dma_address(&sg[i]) + sg_dma_len(&sg[i])); + for_each_sg(sglist, sg, nents, i) { + frv_cache_wback_inv(sg_dma_address(sg), + sg_dma_address(sg) + sg_dma_len(sg)); + } BUG_ON(direction == DMA_NONE); diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c index 8247897..4d1f01d 100644 --- a/arch/frv/mb93090-mb00/pci-dma.c +++ b/arch/frv/mb93090-mb00/pci-dma.c @@ -50,19 +50,20 @@ dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size, EXPORT_SYMBOL(dma_map_single); -int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction) { unsigned long dampr2; void *vaddr; int i; + struct scatterlist *sg; BUG_ON(direction == DMA_NONE); dampr2 = __get_DAMPR(2); - for (i = 0; i < nents; i++) { - vaddr = kmap_atomic_primary(sg_page(&sg[i])); + for_each_sg(sglist, sg, nents, i) { + vaddr = kmap_atomic_primary(sg_page(sg)); frv_dcache_writeback((unsigned long) vaddr, (unsigned long) vaddr + PAGE_SIZE); diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h index ff1377b..ef65f02 100644 --- a/arch/ia64/include/asm/hugetlb.h +++ b/arch/ia64/include/asm/hugetlb.h @@ -65,15 +65,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/metag/include/asm/hugetlb.h b/arch/metag/include/asm/hugetlb.h index f730b39..905ed42 100644 --- a/arch/metag/include/asm/hugetlb.h +++ b/arch/metag/include/asm/hugetlb.h @@ -67,15 +67,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index 4a5bb54..982bc06 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -110,15 +110,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 4bbd3c8..7eac89b 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -168,15 +168,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index dfb542a..0130d03 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -37,9 +37,6 @@ static inline int prepare_hugepage_range(struct file *file, #define arch_clear_hugepage_flags(page) do { } while (0) -int arch_prepare_hugepage(struct page *page); -void arch_release_hugepage(struct page *page); - static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 53eacbd..dd34523 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -17,7 +17,10 @@ #define PAGE_DEFAULT_ACC 0 #define PAGE_DEFAULT_KEY (PAGE_DEFAULT_ACC << 4) -#define HPAGE_SHIFT 20 +#include <asm/setup.h> +#ifndef __ASSEMBLY__ + +extern int HPAGE_SHIFT; #define HPAGE_SIZE (1UL << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) @@ -27,9 +30,6 @@ #define ARCH_HAS_PREPARE_HUGEPAGE #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH -#include <asm/setup.h> -#ifndef __ASSEMBLY__ - static inline void storage_key_init_range(unsigned long start, unsigned long end) { #if PAGE_DEFAULT_KEY diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index d7fa2f0..f8498dd 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -202,7 +202,7 @@ COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags); COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig); COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig); COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags); -COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val); +COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls); COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags); COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim); COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index af4f41d..73941bf 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -880,6 +880,8 @@ void __init setup_arch(char **cmdline_p) */ setup_hwcaps(); + HPAGE_SHIFT = MACHINE_HAS_HPAGE ? 20 : 0; + /* * Create kernel page tables and switch to virtual addressing. */ diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c3f8e3d..fb4bf2c 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -86,31 +86,16 @@ static inline pte_t __pmd_to_pte(pmd_t pmd) void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - pmd_t pmd; + pmd_t pmd = __pte_to_pmd(pte); - pmd = __pte_to_pmd(pte); - if (!MACHINE_HAS_HPAGE) { - /* Emulated huge ptes loose the dirty and young bit */ - pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN; - pmd_val(pmd) |= pte_page(pte)[1].index; - } else - pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; + pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; *(pmd_t *) ptep = pmd; } pte_t huge_ptep_get(pte_t *ptep) { - unsigned long origin; - pmd_t pmd; + pmd_t pmd = *(pmd_t *) ptep; - pmd = *(pmd_t *) ptep; - if (!MACHINE_HAS_HPAGE && pmd_present(pmd)) { - origin = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN; - pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN; - pmd_val(pmd) |= *(unsigned long *) origin; - /* Emulated huge ptes are young and dirty by definition */ - pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG | _SEGMENT_ENTRY_DIRTY; - } return __pmd_to_pte(pmd); } @@ -125,45 +110,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, return pte; } -int arch_prepare_hugepage(struct page *page) -{ - unsigned long addr = page_to_phys(page); - pte_t pte; - pte_t *ptep; - int i; - - if (MACHINE_HAS_HPAGE) - return 0; - - ptep = (pte_t *) pte_alloc_one(&init_mm, addr); - if (!ptep) - return -ENOMEM; - - pte_val(pte) = addr; - for (i = 0; i < PTRS_PER_PTE; i++) { - set_pte_at(&init_mm, addr + i * PAGE_SIZE, ptep + i, pte); - pte_val(pte) += PAGE_SIZE; - } - page[1].index = (unsigned long) ptep; - return 0; -} - -void arch_release_hugepage(struct page *page) -{ - pte_t *ptep; - - if (MACHINE_HAS_HPAGE) - return; - - ptep = (pte_t *) page[1].index; - if (!ptep) - return; - clear_table((unsigned long *) ptep, _PAGE_INVALID, - PTRS_PER_PTE * sizeof(pte_t)); - page_table_free(&init_mm, (unsigned long *) ptep); - page[1].index = 0; -} - pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { @@ -195,10 +141,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) int pmd_huge(pmd_t pmd) { - if (!MACHINE_HAS_HPAGE) - return 0; - - return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE); + return pmd_large(pmd); } int pud_huge(pud_t pud) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index b33f661..33082d0 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -31,6 +31,8 @@ #define ALLOC_ORDER 2 #define FRAG_MASK 0x03 +int HPAGE_SHIFT; + unsigned long *crst_table_alloc(struct mm_struct *mm) { struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER); diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index b788a9b..ef489a5 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -79,15 +79,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { clear_bit(PG_dcache_clean, &page->flags); diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 3130d76..139e711 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -78,15 +78,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/tile/include/asm/hugetlb.h b/arch/tile/include/asm/hugetlb.h index 1abd00c..2fac5be 100644 --- a/arch/tile/include/asm/hugetlb.h +++ b/arch/tile/include/asm/hugetlb.h @@ -94,15 +94,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index dab7a3a..f8a29d2 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -80,15 +80,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/drivers/base/core.c b/drivers/base/core.c index 21d1303..dafae6d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1303,12 +1303,11 @@ const char *device_get_devnode(struct device *dev, return dev_name(dev); /* replace '!' in the name with '/' */ - *tmp = kstrdup(dev_name(dev), GFP_KERNEL); - if (!*tmp) + s = kstrdup(dev_name(dev), GFP_KERNEL); + if (!s) return NULL; - while ((s = strchr(*tmp, '!'))) - s[0] = '/'; - return *tmp; + strreplace(s, '!', '/'); + return *tmp = s; } /** diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 6489c0f..386ba3d 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -23,12 +23,4 @@ config ZRAM_LZ4_COMPRESS default n help This option enables LZ4 compression algorithm support. Compression - algorithm can be changed using `comp_algorithm' device attribute. - -config ZRAM_DEBUG - bool "Compressed RAM block device debug support" - depends on ZRAM - default n - help - This option adds additional debugging code to the compressed - RAM block device driver. + algorithm can be changed using `comp_algorithm' device attribute.
\ No newline at end of file diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index f1ff39a..965d1af 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -274,7 +274,7 @@ ssize_t zcomp_available_show(const char *comp, char *buf) int i = 0; while (backends[i]) { - if (sysfs_streq(comp, backends[i]->name)) + if (!strcmp(comp, backends[i]->name)) sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2, "[%s] ", backends[i]->name); else @@ -286,6 +286,11 @@ ssize_t zcomp_available_show(const char *comp, char *buf) return sz; } +bool zcomp_available_algorithm(const char *comp) +{ + return find_backend(comp) != NULL; +} + bool zcomp_set_max_streams(struct zcomp *comp, int num_strm) { return comp->set_max_streams(comp, num_strm); diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h index c59d1fc..46e2b9f 100644 --- a/drivers/block/zram/zcomp.h +++ b/drivers/block/zram/zcomp.h @@ -51,6 +51,7 @@ struct zcomp { }; ssize_t zcomp_available_show(const char *comp, char *buf); +bool zcomp_available_algorithm(const char *comp); struct zcomp *zcomp_create(const char *comp, int max_strm); void zcomp_destroy(struct zcomp *comp); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6e134f4..fb655e8 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -15,10 +15,6 @@ #define KMSG_COMPONENT "zram" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt -#ifdef CONFIG_ZRAM_DEBUG -#define DEBUG -#endif - #include <linux/module.h> #include <linux/kernel.h> #include <linux/bio.h> @@ -32,12 +28,16 @@ #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/err.h> +#include <linux/idr.h> +#include <linux/sysfs.h> #include "zram_drv.h" -/* Globals */ +static DEFINE_IDR(zram_index_idr); +/* idr index must be protected */ +static DEFINE_MUTEX(zram_index_mutex); + static int zram_major; -static struct zram *zram_devices; static const char *default_compressor = "lzo"; /* Module params (documentation at end) */ @@ -53,7 +53,7 @@ static inline void deprecated_attr_warn(const char *name) } #define ZRAM_ATTR_RO(name) \ -static ssize_t name##_show(struct device *d, \ +static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *b) \ { \ struct zram *zram = dev_to_zram(d); \ @@ -74,33 +74,117 @@ static inline struct zram *dev_to_zram(struct device *dev) return (struct zram *)dev_to_disk(dev)->private_data; } -static ssize_t compact_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t len) +/* flag operations require table entry bit_spin_lock() being held */ +static int zram_test_flag(struct zram_meta *meta, u32 index, + enum zram_pageflags flag) { - unsigned long nr_migrated; - struct zram *zram = dev_to_zram(dev); - struct zram_meta *meta; + return meta->table[index].value & BIT(flag); +} - down_read(&zram->init_lock); - if (!init_done(zram)) { - up_read(&zram->init_lock); - return -EINVAL; - } +static void zram_set_flag(struct zram_meta *meta, u32 index, + enum zram_pageflags flag) +{ + meta->table[index].value |= BIT(flag); +} - meta = zram->meta; - nr_migrated = zs_compact(meta->mem_pool); - atomic64_add(nr_migrated, &zram->stats.num_migrated); - up_read(&zram->init_lock); +static void zram_clear_flag(struct zram_meta *meta, u32 index, + enum zram_pageflags flag) +{ + meta->table[index].value &= ~BIT(flag); +} - return len; +static size_t zram_get_obj_size(struct zram_meta *meta, u32 index) +{ + return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1); } -static ssize_t disksize_show(struct device *dev, - struct device_attribute *attr, char *buf) +static void zram_set_obj_size(struct zram_meta *meta, + u32 index, size_t size) { - struct zram *zram = dev_to_zram(dev); + unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT; - return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize); + meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size; +} + +static inline int is_partial_io(struct bio_vec *bvec) +{ + return bvec->bv_len != PAGE_SIZE; +} + +/* + * Check if request is within bounds and aligned on zram logical blocks. + */ +static inline int valid_io_request(struct zram *zram, + sector_t start, unsigned int size) +{ + u64 end, bound; + + /* unaligned request */ + if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1))) + return 0; + if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1))) + return 0; + + end = start + (size >> SECTOR_SHIFT); + bound = zram->disksize >> SECTOR_SHIFT; + /* out of range range */ + if (unlikely(start >= bound || end > bound || start > end)) + return 0; + + /* I/O request is valid */ + return 1; +} + +static void update_position(u32 *index, int *offset, struct bio_vec *bvec) +{ + if (*offset + bvec->bv_len >= PAGE_SIZE) + (*index)++; + *offset = (*offset + bvec->bv_len) % PAGE_SIZE; +} + +static inline void update_used_max(struct zram *zram, + const unsigned long pages) +{ + unsigned long old_max, cur_max; + + old_max = atomic_long_read(&zram->stats.max_used_pages); + + do { + cur_max = old_max; + if (pages > cur_max) + old_max = atomic_long_cmpxchg( + &zram->stats.max_used_pages, cur_max, pages); + } while (old_max != cur_max); +} + +static int page_zero_filled(void *ptr) +{ + unsigned int pos; + unsigned long *page; + + page = (unsigned long *)ptr; + + for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) { + if (page[pos]) + return 0; + } + + return 1; +} + +static void handle_zero_page(struct bio_vec *bvec) +{ + struct page *page = bvec->bv_page; + void *user_mem; + + user_mem = kmap_atomic(page); + if (is_partial_io(bvec)) + memset(user_mem + bvec->bv_offset, 0, bvec->bv_len); + else + clear_page(user_mem); + kunmap_atomic(user_mem); + + flush_dcache_page(page); } static ssize_t initstate_show(struct device *dev, @@ -116,6 +200,14 @@ static ssize_t initstate_show(struct device *dev, return scnprintf(buf, PAGE_SIZE, "%u\n", val); } +static ssize_t disksize_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize); +} + static ssize_t orig_data_size_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -143,19 +235,6 @@ static ssize_t mem_used_total_show(struct device *dev, return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); } -static ssize_t max_comp_streams_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - int val; - struct zram *zram = dev_to_zram(dev); - - down_read(&zram->init_lock); - val = zram->max_comp_streams; - up_read(&zram->init_lock); - - return scnprintf(buf, PAGE_SIZE, "%d\n", val); -} - static ssize_t mem_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -225,6 +304,19 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } +static ssize_t max_comp_streams_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + val = zram->max_comp_streams; + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%d\n", val); +} + static ssize_t max_comp_streams_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -271,6 +363,8 @@ static ssize_t comp_algorithm_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct zram *zram = dev_to_zram(dev); + size_t sz; + down_write(&zram->init_lock); if (init_done(zram)) { up_write(&zram->init_lock); @@ -278,69 +372,108 @@ static ssize_t comp_algorithm_store(struct device *dev, return -EBUSY; } strlcpy(zram->compressor, buf, sizeof(zram->compressor)); + + /* ignore trailing newline */ + sz = strlen(zram->compressor); + if (sz > 0 && zram->compressor[sz - 1] == '\n') + zram->compressor[sz - 1] = 0x00; + + if (!zcomp_available_algorithm(zram->compressor)) + len = -EINVAL; + up_write(&zram->init_lock); return len; } -/* flag operations needs meta->tb_lock */ -static int zram_test_flag(struct zram_meta *meta, u32 index, - enum zram_pageflags flag) +static ssize_t compact_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) { - return meta->table[index].value & BIT(flag); -} + unsigned long nr_migrated; + struct zram *zram = dev_to_zram(dev); + struct zram_meta *meta; -static void zram_set_flag(struct zram_meta *meta, u32 index, - enum zram_pageflags flag) -{ - meta->table[index].value |= BIT(flag); -} + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + return -EINVAL; + } -static void zram_clear_flag(struct zram_meta *meta, u32 index, - enum zram_pageflags flag) -{ - meta->table[index].value &= ~BIT(flag); + meta = zram->meta; + nr_migrated = zs_compact(meta->mem_pool); + atomic64_add(nr_migrated, &zram->stats.num_migrated); + up_read(&zram->init_lock); + + return len; } -static size_t zram_get_obj_size(struct zram_meta *meta, u32 index) +static ssize_t io_stat_show(struct device *dev, + struct device_attribute *attr, char *buf) { - return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1); + struct zram *zram = dev_to_zram(dev); + ssize_t ret; + + down_read(&zram->init_lock); + ret = scnprintf(buf, PAGE_SIZE, + "%8llu %8llu %8llu %8llu\n", + (u64)atomic64_read(&zram->stats.failed_reads), + (u64)atomic64_read(&zram->stats.failed_writes), + (u64)atomic64_read(&zram->stats.invalid_io), + (u64)atomic64_read(&zram->stats.notify_free)); + up_read(&zram->init_lock); + + return ret; } -static void zram_set_obj_size(struct zram_meta *meta, - u32 index, size_t size) +static ssize_t mm_stat_show(struct device *dev, + struct device_attribute *attr, char *buf) { - unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT; + struct zram *zram = dev_to_zram(dev); + u64 orig_size, mem_used = 0; + long max_used; + ssize_t ret; - meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size; + down_read(&zram->init_lock); + if (init_done(zram)) + mem_used = zs_get_total_pages(zram->meta->mem_pool); + + orig_size = atomic64_read(&zram->stats.pages_stored); + max_used = atomic_long_read(&zram->stats.max_used_pages); + + ret = scnprintf(buf, PAGE_SIZE, + "%8llu %8llu %8llu %8lu %8ld %8llu %8llu\n", + orig_size << PAGE_SHIFT, + (u64)atomic64_read(&zram->stats.compr_data_size), + mem_used << PAGE_SHIFT, + zram->limit_pages << PAGE_SHIFT, + max_used << PAGE_SHIFT, + (u64)atomic64_read(&zram->stats.zero_pages), + (u64)atomic64_read(&zram->stats.num_migrated)); + up_read(&zram->init_lock); + + return ret; } -static inline int is_partial_io(struct bio_vec *bvec) +static DEVICE_ATTR_RO(io_stat); +static DEVICE_ATTR_RO(mm_stat); +ZRAM_ATTR_RO(num_reads); +ZRAM_ATTR_RO(num_writes); +ZRAM_ATTR_RO(failed_reads); +ZRAM_ATTR_RO(failed_writes); +ZRAM_ATTR_RO(invalid_io); +ZRAM_ATTR_RO(notify_free); +ZRAM_ATTR_RO(zero_pages); +ZRAM_ATTR_RO(compr_data_size); + +static inline bool zram_meta_get(struct zram *zram) { - return bvec->bv_len != PAGE_SIZE; + if (atomic_inc_not_zero(&zram->refcount)) + return true; + return false; } -/* - * Check if request is within bounds and aligned on zram logical blocks. - */ -static inline int valid_io_request(struct zram *zram, - sector_t start, unsigned int size) +static inline void zram_meta_put(struct zram *zram) { - u64 end, bound; - - /* unaligned request */ - if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1))) - return 0; - if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1))) - return 0; - - end = start + (size >> SECTOR_SHIFT); - bound = zram->disksize >> SECTOR_SHIFT; - /* out of range range */ - if (unlikely(start >= bound || end > bound || start > end)) - return 0; - - /* I/O request is valid */ - return 1; + atomic_dec(&zram->refcount); } static void zram_meta_free(struct zram_meta *meta, u64 disksize) @@ -394,56 +527,6 @@ out_error: return NULL; } -static inline bool zram_meta_get(struct zram *zram) -{ - if (atomic_inc_not_zero(&zram->refcount)) - return true; - return false; -} - -static inline void zram_meta_put(struct zram *zram) -{ - atomic_dec(&zram->refcount); -} - -static void update_position(u32 *index, int *offset, struct bio_vec *bvec) -{ - if (*offset + bvec->bv_len >= PAGE_SIZE) - (*index)++; - *offset = (*offset + bvec->bv_len) % PAGE_SIZE; -} - -static int page_zero_filled(void *ptr) -{ - unsigned int pos; - unsigned long *page; - - page = (unsigned long *)ptr; - - for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) { - if (page[pos]) - return 0; - } - - return 1; -} - -static void handle_zero_page(struct bio_vec *bvec) -{ - struct page *page = bvec->bv_page; - void *user_mem; - - user_mem = kmap_atomic(page); - if (is_partial_io(bvec)) - memset(user_mem + bvec->bv_offset, 0, bvec->bv_len); - else - clear_page(user_mem); - kunmap_atomic(user_mem); - - flush_dcache_page(page); -} - - /* * To protect concurrent access to the same index entry, * caller should hold this table index entry's bit_spinlock to @@ -561,21 +644,6 @@ out_cleanup: return ret; } -static inline void update_used_max(struct zram *zram, - const unsigned long pages) -{ - unsigned long old_max, cur_max; - - old_max = atomic_long_read(&zram->stats.max_used_pages); - - do { - cur_max = old_max; - if (pages > cur_max) - old_max = atomic_long_cmpxchg( - &zram->stats.max_used_pages, cur_max, pages); - } while (old_max != cur_max); -} - static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, int offset) { @@ -585,8 +653,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, struct page *page; unsigned char *user_mem, *cmem, *src, *uncmem = NULL; struct zram_meta *meta = zram->meta; - struct zcomp_strm *zstrm; - bool locked = false; + struct zcomp_strm *zstrm = NULL; unsigned long alloced_pages; page = bvec->bv_page; @@ -606,7 +673,6 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } zstrm = zcomp_strm_find(zram->comp); - locked = true; user_mem = kmap_atomic(page); if (is_partial_io(bvec)) { @@ -678,7 +744,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } zcomp_strm_release(zram->comp, zstrm); - locked = false; + zstrm = NULL; zs_unmap_object(meta->mem_pool, handle); /* @@ -696,42 +762,13 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, atomic64_add(clen, &zram->stats.compr_data_size); atomic64_inc(&zram->stats.pages_stored); out: - if (locked) + if (zstrm) zcomp_strm_release(zram->comp, zstrm); if (is_partial_io(bvec)) kfree(uncmem); return ret; } -static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, - int offset, int rw) -{ - unsigned long start_time = jiffies; - int ret; - - generic_start_io_acct(rw, bvec->bv_len >> SECTOR_SHIFT, - &zram->disk->part0); - - if (rw == READ) { - atomic64_inc(&zram->stats.num_reads); - ret = zram_bvec_read(zram, bvec, index, offset); - } else { - atomic64_inc(&zram->stats.num_writes); - ret = zram_bvec_write(zram, bvec, index, offset); - } - - generic_end_io_acct(rw, &zram->disk->part0, start_time); - - if (unlikely(ret)) { - if (rw == READ) - atomic64_inc(&zram->stats.failed_reads); - else - atomic64_inc(&zram->stats.failed_writes); - } - - return ret; -} - /* * zram_bio_discard - handler on discard request * @index: physical block index in PAGE_SIZE units @@ -771,151 +808,32 @@ static void zram_bio_discard(struct zram *zram, u32 index, } } -static void zram_reset_device(struct zram *zram) -{ - struct zram_meta *meta; - struct zcomp *comp; - u64 disksize; - - down_write(&zram->init_lock); - - zram->limit_pages = 0; - - if (!init_done(zram)) { - up_write(&zram->init_lock); - return; - } - - meta = zram->meta; - comp = zram->comp; - disksize = zram->disksize; - /* - * Refcount will go down to 0 eventually and r/w handler - * cannot handle further I/O so it will bail out by - * check zram_meta_get. - */ - zram_meta_put(zram); - /* - * We want to free zram_meta in process context to avoid - * deadlock between reclaim path and any other locks. - */ - wait_event(zram->io_done, atomic_read(&zram->refcount) == 0); - - /* Reset stats */ - memset(&zram->stats, 0, sizeof(zram->stats)); - zram->disksize = 0; - zram->max_comp_streams = 1; - - set_capacity(zram->disk, 0); - part_stat_set_all(&zram->disk->part0, 0); - - up_write(&zram->init_lock); - /* I/O operation under all of CPU are done so let's free */ - zram_meta_free(meta, disksize); - zcomp_destroy(comp); -} - -static ssize_t disksize_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t len) -{ - u64 disksize; - struct zcomp *comp; - struct zram_meta *meta; - struct zram *zram = dev_to_zram(dev); - int err; - - disksize = memparse(buf, NULL); - if (!disksize) - return -EINVAL; - - disksize = PAGE_ALIGN(disksize); - meta = zram_meta_alloc(zram->disk->first_minor, disksize); - if (!meta) - return -ENOMEM; - - comp = zcomp_create(zram->compressor, zram->max_comp_streams); - if (IS_ERR(comp)) { - pr_info("Cannot initialise %s compressing backend\n", - zram->compressor); - err = PTR_ERR(comp); - goto out_free_meta; - } - - down_write(&zram->init_lock); - if (init_done(zram)) { - pr_info("Cannot change disksize for initialized device\n"); - err = -EBUSY; - goto out_destroy_comp; - } - - init_waitqueue_head(&zram->io_done); - atomic_set(&zram->refcount, 1); - zram->meta = meta; - zram->comp = comp; - zram->disksize = disksize; - set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); - up_write(&zram->init_lock); - - /* - * Revalidate disk out of the init_lock to avoid lockdep splat. - * It's okay because disk's capacity is protected by init_lock - * so that revalidate_disk always sees up-to-date capacity. - */ - revalidate_disk(zram->disk); - - return len; - -out_destroy_comp: - up_write(&zram->init_lock); - zcomp_destroy(comp); -out_free_meta: - zram_meta_free(meta, disksize); - return err; -} - -static ssize_t reset_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t len) +static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, + int offset, int rw) { + unsigned long start_time = jiffies; int ret; - unsigned short do_reset; - struct zram *zram; - struct block_device *bdev; - zram = dev_to_zram(dev); - bdev = bdget_disk(zram->disk, 0); - - if (!bdev) - return -ENOMEM; + generic_start_io_acct(rw, bvec->bv_len >> SECTOR_SHIFT, + &zram->disk->part0); - mutex_lock(&bdev->bd_mutex); - /* Do not reset an active device! */ - if (bdev->bd_openers) { - ret = -EBUSY; - goto out; + if (rw == READ) { + atomic64_inc(&zram->stats.num_reads); + ret = zram_bvec_read(zram, bvec, index, offset); + } else { + atomic64_inc(&zram->stats.num_writes); + ret = zram_bvec_write(zram, bvec, index, offset); } - ret = kstrtou16(buf, 10, &do_reset); - if (ret) - goto out; + generic_end_io_acct(rw, &zram->disk->part0, start_time); - if (!do_reset) { - ret = -EINVAL; - goto out; + if (unlikely(ret)) { + if (rw == READ) + atomic64_inc(&zram->stats.failed_reads); + else + atomic64_inc(&zram->stats.failed_writes); } - /* Make sure all pending I/O is finished */ - fsync_bdev(bdev); - zram_reset_device(zram); - - mutex_unlock(&bdev->bd_mutex); - revalidate_disk(zram->disk); - bdput(bdev); - - return len; - -out: - mutex_unlock(&bdev->bd_mutex); - bdput(bdev); return ret; } @@ -1055,80 +973,185 @@ out: return err; } -static const struct block_device_operations zram_devops = { - .swap_slot_free_notify = zram_slot_free_notify, - .rw_page = zram_rw_page, - .owner = THIS_MODULE -}; +static void zram_reset_device(struct zram *zram) +{ + struct zram_meta *meta; + struct zcomp *comp; + u64 disksize; -static DEVICE_ATTR_WO(compact); -static DEVICE_ATTR_RW(disksize); -static DEVICE_ATTR_RO(initstate); -static DEVICE_ATTR_WO(reset); -static DEVICE_ATTR_RO(orig_data_size); -static DEVICE_ATTR_RO(mem_used_total); -static DEVICE_ATTR_RW(mem_limit); -static DEVICE_ATTR_RW(mem_used_max); -static DEVICE_ATTR_RW(max_comp_streams); -static DEVICE_ATTR_RW(comp_algorithm); + down_write(&zram->init_lock); -static ssize_t io_stat_show(struct device *dev, - struct device_attribute *attr, char *buf) + zram->limit_pages = 0; + + if (!init_done(zram)) { + up_write(&zram->init_lock); + return; + } + + meta = zram->meta; + comp = zram->comp; + disksize = zram->disksize; + /* + * Refcount will go down to 0 eventually and r/w handler + * cannot handle further I/O so it will bail out by + * check zram_meta_get. + */ + zram_meta_put(zram); + /* + * We want to free zram_meta in process context to avoid + * deadlock between reclaim path and any other locks. + */ + wait_event(zram->io_done, atomic_read(&zram->refcount) == 0); + + /* Reset stats */ + memset(&zram->stats, 0, sizeof(zram->stats)); + zram->disksize = 0; + zram->max_comp_streams = 1; + + set_capacity(zram->disk, 0); + part_stat_set_all(&zram->disk->part0, 0); + + up_write(&zram->init_lock); + /* I/O operation under all of CPU are done so let's free */ + zram_meta_free(meta, disksize); + zcomp_destroy(comp); +} + +static ssize_t disksize_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) { + u64 disksize; + struct zcomp *comp; + struct zram_meta *meta; struct zram *zram = dev_to_zram(dev); - ssize_t ret; + int err; - down_read(&zram->init_lock); - ret = scnprintf(buf, PAGE_SIZE, - "%8llu %8llu %8llu %8llu\n", - (u64)atomic64_read(&zram->stats.failed_reads), - (u64)atomic64_read(&zram->stats.failed_writes), - (u64)atomic64_read(&zram->stats.invalid_io), - (u64)atomic64_read(&zram->stats.notify_free)); - up_read(&zram->init_lock); + disksize = memparse(buf, NULL); + if (!disksize) + return -EINVAL; - return ret; + disksize = PAGE_ALIGN(disksize); + meta = zram_meta_alloc(zram->disk->first_minor, disksize); + if (!meta) + return -ENOMEM; + + comp = zcomp_create(zram->compressor, zram->max_comp_streams); + if (IS_ERR(comp)) { + pr_info("Cannot initialise %s compressing backend\n", + zram->compressor); + err = PTR_ERR(comp); + goto out_free_meta; + } + + down_write(&zram->init_lock); + if (init_done(zram)) { + pr_info("Cannot change disksize for initialized device\n"); + err = -EBUSY; + goto out_destroy_comp; + } + + init_waitqueue_head(&zram->io_done); + atomic_set(&zram->refcount, 1); + zram->meta = meta; + zram->comp = comp; + zram->disksize = disksize; + set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); + up_write(&zram->init_lock); + + /* + * Revalidate disk out of the init_lock to avoid lockdep splat. + * It's okay because disk's capacity is protected by init_lock + * so that revalidate_disk always sees up-to-date capacity. + */ + revalidate_disk(zram->disk); + + return len; + +out_destroy_comp: + up_write(&zram->init_lock); + zcomp_destroy(comp); +out_free_meta: + zram_meta_free(meta, disksize); + return err; } -static ssize_t mm_stat_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t reset_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) { - struct zram *zram = dev_to_zram(dev); - u64 orig_size, mem_used = 0; - long max_used; - ssize_t ret; + int ret; + unsigned short do_reset; + struct zram *zram; + struct block_device *bdev; - down_read(&zram->init_lock); - if (init_done(zram)) - mem_used = zs_get_total_pages(zram->meta->mem_pool); + ret = kstrtou16(buf, 10, &do_reset); + if (ret) + return ret; - orig_size = atomic64_read(&zram->stats.pages_stored); - max_used = atomic_long_read(&zram->stats.max_used_pages); + if (!do_reset) + return -EINVAL; - ret = scnprintf(buf, PAGE_SIZE, - "%8llu %8llu %8llu %8lu %8ld %8llu %8llu\n", - orig_size << PAGE_SHIFT, - (u64)atomic64_read(&zram->stats.compr_data_size), - mem_used << PAGE_SHIFT, - zram->limit_pages << PAGE_SHIFT, - max_used << PAGE_SHIFT, - (u64)atomic64_read(&zram->stats.zero_pages), - (u64)atomic64_read(&zram->stats.num_migrated)); - up_read(&zram->init_lock); + zram = dev_to_zram(dev); + bdev = bdget_disk(zram->disk, 0); + if (!bdev) + return -ENOMEM; + + mutex_lock(&bdev->bd_mutex); + /* Do not reset an active device or claimed device */ + if (bdev->bd_openers || zram->claim) { + mutex_unlock(&bdev->bd_mutex); + bdput(bdev); + return -EBUSY; + } + + /* From now on, anyone can't open /dev/zram[0-9] */ + zram->claim = true; + mutex_unlock(&bdev->bd_mutex); + + /* Make sure all the pending I/O are finished */ + fsync_bdev(bdev); + zram_reset_device(zram); + revalidate_disk(zram->disk); + bdput(bdev); + + mutex_lock(&bdev->bd_mutex); + zram->claim = false; + mutex_unlock(&bdev->bd_mutex); + + return len; +} + +static int zram_open(struct block_device *bdev, fmode_t mode) +{ + int ret = 0; + struct zram *zram; + + WARN_ON(!mutex_is_locked(&bdev->bd_mutex)); + + zram = bdev->bd_disk->private_data; + /* zram was claimed to reset so open request fails */ + if (zram->claim) + ret = -EBUSY; return ret; } -static DEVICE_ATTR_RO(io_stat); -static DEVICE_ATTR_RO(mm_stat); -ZRAM_ATTR_RO(num_reads); -ZRAM_ATTR_RO(num_writes); -ZRAM_ATTR_RO(failed_reads); -ZRAM_ATTR_RO(failed_writes); -ZRAM_ATTR_RO(invalid_io); -ZRAM_ATTR_RO(notify_free); -ZRAM_ATTR_RO(zero_pages); -ZRAM_ATTR_RO(compr_data_size); +static const struct block_device_operations zram_devops = { + .open = zram_open, + .swap_slot_free_notify = zram_slot_free_notify, + .rw_page = zram_rw_page, + .owner = THIS_MODULE +}; + +static DEVICE_ATTR_WO(compact); +static DEVICE_ATTR_RW(disksize); +static DEVICE_ATTR_RO(initstate); +static DEVICE_ATTR_WO(reset); +static DEVICE_ATTR_RO(orig_data_size); +static DEVICE_ATTR_RO(mem_used_total); +static DEVICE_ATTR_RW(mem_limit); +static DEVICE_ATTR_RW(mem_used_max); +static DEVICE_ATTR_RW(max_comp_streams); +static DEVICE_ATTR_RW(comp_algorithm); static struct attribute *zram_disk_attrs[] = { &dev_attr_disksize.attr, @@ -1158,10 +1181,24 @@ static struct attribute_group zram_disk_attr_group = { .attrs = zram_disk_attrs, }; -static int create_device(struct zram *zram, int device_id) +/* + * Allocate and initialize new zram device. the function returns + * '>= 0' device_id upon success, and negative value otherwise. + */ +static int zram_add(void) { + struct zram *zram; struct request_queue *queue; - int ret = -ENOMEM; + int ret, device_id; + + zram = kzalloc(sizeof(struct zram), GFP_KERNEL); + if (!zram) + return -ENOMEM; + + ret = idr_alloc(&zram_index_idr, zram, 0, 0, GFP_KERNEL); + if (ret < 0) + goto out_free_dev; + device_id = ret; init_rwsem(&zram->init_lock); @@ -1169,12 +1206,13 @@ static int create_device(struct zram *zram, int device_id) if (!queue) { pr_err("Error allocating disk queue for device %d\n", device_id); - goto out; + ret = -ENOMEM; + goto out_free_idr; } blk_queue_make_request(queue, zram_make_request); - /* gendisk structure */ + /* gendisk structure */ zram->disk = alloc_disk(1); if (!zram->disk) { pr_warn("Error allocating disk structure for device %d\n", @@ -1232,90 +1270,177 @@ static int create_device(struct zram *zram, int device_id) strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); zram->meta = NULL; zram->max_comp_streams = 1; - return 0; + + pr_info("Added device: %s\n", zram->disk->disk_name); + return device_id; out_free_disk: del_gendisk(zram->disk); put_disk(zram->disk); out_free_queue: blk_cleanup_queue(queue); -out: +out_free_idr: + idr_remove(&zram_index_idr, device_id); +out_free_dev: + kfree(zram); return ret; } -static void destroy_devices(unsigned int nr) +static int zram_remove(struct zram *zram) +{ + struct block_device *bdev; + + bdev = bdget_disk(zram->disk, 0); + if (!bdev) + return -ENOMEM; + + mutex_lock(&bdev->bd_mutex); + if (bdev->bd_openers || zram->claim) { + mutex_unlock(&bdev->bd_mutex); + bdput(bdev); + return -EBUSY; + } + + zram->claim = true; + mutex_unlock(&bdev->bd_mutex); + + /* + * Remove sysfs first, so no one will perform a disksize + * store while we destroy the devices. This also helps during + * hot_remove -- zram_reset_device() is the last holder of + * ->init_lock, no later/concurrent disksize_store() or any + * other sysfs handlers are possible. + */ + sysfs_remove_group(&disk_to_dev(zram->disk)->kobj, + &zram_disk_attr_group); + + /* Make sure all the pending I/O are finished */ + fsync_bdev(bdev); + zram_reset_device(zram); + bdput(bdev); + + pr_info("Removed device: %s\n", zram->disk->disk_name); + + idr_remove(&zram_index_idr, zram->disk->first_minor); + blk_cleanup_queue(zram->disk->queue); + del_gendisk(zram->disk); + put_disk(zram->disk); + kfree(zram); + return 0; +} + +/* zram-control sysfs attributes */ +static ssize_t hot_add_show(struct class *class, + struct class_attribute *attr, + char *buf) +{ + int ret; + + mutex_lock(&zram_index_mutex); + ret = zram_add(); + mutex_unlock(&zram_index_mutex); + + if (ret < 0) + return ret; + return scnprintf(buf, PAGE_SIZE, "%d\n", ret); +} + +static ssize_t hot_remove_store(struct class *class, + struct class_attribute *attr, + const char *buf, + size_t count) { struct zram *zram; - unsigned int i; + int ret, dev_id; - for (i = 0; i < nr; i++) { - zram = &zram_devices[i]; - /* - * Remove sysfs first, so no one will perform a disksize - * store while we destroy the devices - */ - sysfs_remove_group(&disk_to_dev(zram->disk)->kobj, - &zram_disk_attr_group); + /* dev_id is gendisk->first_minor, which is `int' */ + ret = kstrtoint(buf, 10, &dev_id); + if (ret) + return ret; + if (dev_id < 0) + return -EINVAL; - zram_reset_device(zram); + mutex_lock(&zram_index_mutex); - blk_cleanup_queue(zram->disk->queue); - del_gendisk(zram->disk); - put_disk(zram->disk); - } + zram = idr_find(&zram_index_idr, dev_id); + if (zram) + ret = zram_remove(zram); + else + ret = -ENODEV; - kfree(zram_devices); + mutex_unlock(&zram_index_mutex); + return ret ? ret : count; +} + +static struct class_attribute zram_control_class_attrs[] = { + __ATTR_RO(hot_add), + __ATTR_WO(hot_remove), + __ATTR_NULL, +}; + +static struct class zram_control_class = { + .name = "zram-control", + .owner = THIS_MODULE, + .class_attrs = zram_control_class_attrs, +}; + +static int zram_remove_cb(int id, void *ptr, void *data) +{ + zram_remove(ptr); + return 0; +} + +static void destroy_devices(void) +{ + class_unregister(&zram_control_class); + idr_for_each(&zram_index_idr, &zram_remove_cb, NULL); + idr_destroy(&zram_index_idr); unregister_blkdev(zram_major, "zram"); - pr_info("Destroyed %u device(s)\n", nr); } static int __init zram_init(void) { - int ret, dev_id; + int ret; - if (num_devices > max_num_devices) { - pr_warn("Invalid value for num_devices: %u\n", - num_devices); - return -EINVAL; + ret = class_register(&zram_control_class); + if (ret) { + pr_warn("Unable to register zram-control class\n"); + return ret; } zram_major = register_blkdev(0, "zram"); if (zram_major <= 0) { pr_warn("Unable to get major number\n"); + class_unregister(&zram_control_class); return -EBUSY; } - /* Allocate the device array and initialize each one */ - zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL); - if (!zram_devices) { - unregister_blkdev(zram_major, "zram"); - return -ENOMEM; - } - - for (dev_id = 0; dev_id < num_devices; dev_id++) { - ret = create_device(&zram_devices[dev_id], dev_id); - if (ret) + while (num_devices != 0) { + mutex_lock(&zram_index_mutex); + ret = zram_add(); + mutex_unlock(&zram_index_mutex); + if (ret < 0) goto out_error; + num_devices--; } - pr_info("Created %u device(s)\n", num_devices); return 0; out_error: - destroy_devices(dev_id); + destroy_devices(); return ret; } static void __exit zram_exit(void) { - destroy_devices(num_devices); + destroy_devices(); } module_init(zram_init); module_exit(zram_exit); module_param(num_devices, uint, 0); -MODULE_PARM_DESC(num_devices, "Number of zram devices"); +MODULE_PARM_DESC(num_devices, "Number of pre-created zram devices"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 570c598..6dbe2df 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -20,12 +20,6 @@ #include "zcomp.h" -/* - * Some arbitrary value. This is just to catch - * invalid value for num_devices module parameter. - */ -static const unsigned max_num_devices = 32; - /*-- Configurable parameters */ /* @@ -121,5 +115,9 @@ struct zram { */ u64 disksize; /* bytes */ char compressor[10]; + /* + * zram is claimed so open request will be failed + */ + bool claim; /* Protected by bdev->bd_mutex */ }; #endif diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index cc016c6..5de3ed2 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -144,7 +144,9 @@ static struct kobj_type __refdata memmap_ktype = { * * Common implementation of firmware_map_add() and firmware_map_add_early() * which expects a pre-allocated struct firmware_map_entry. - **/ + * + * Return: 0 always + */ static int firmware_map_add_entry(u64 start, u64 end, const char *type, struct firmware_map_entry *entry) @@ -170,7 +172,7 @@ static int firmware_map_add_entry(u64 start, u64 end, * @entry: removed entry. * * The caller must hold map_entries_lock, and release it properly. - **/ + */ static inline void firmware_map_remove_entry(struct firmware_map_entry *entry) { list_del(&entry->list); @@ -208,7 +210,7 @@ static inline void remove_sysfs_fw_map_entry(struct firmware_map_entry *entry) kobject_put(&entry->kobj); } -/* +/** * firmware_map_find_entry_in_list() - Search memmap entry in a given list. * @start: Start of the memory range. * @end: End of the memory range (exclusive). @@ -236,7 +238,7 @@ firmware_map_find_entry_in_list(u64 start, u64 end, const char *type, return NULL; } -/* +/** * firmware_map_find_entry() - Search memmap entry in map_entries. * @start: Start of the memory range. * @end: End of the memory range (exclusive). @@ -254,7 +256,7 @@ firmware_map_find_entry(u64 start, u64 end, const char *type) return firmware_map_find_entry_in_list(start, end, type, &map_entries); } -/* +/** * firmware_map_find_entry_bootmem() - Search memmap entry in map_entries_bootmem. * @start: Start of the memory range. * @end: End of the memory range (exclusive). @@ -283,8 +285,8 @@ firmware_map_find_entry_bootmem(u64 start, u64 end, const char *type) * similar to function firmware_map_add_early(). The only difference is that * it will create the syfs entry dynamically. * - * Returns 0 on success, or -ENOMEM if no memory could be allocated. - **/ + * Return: 0 on success, or -ENOMEM if no memory could be allocated. + */ int __meminit firmware_map_add_hotplug(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; @@ -325,8 +327,8 @@ int __meminit firmware_map_add_hotplug(u64 start, u64 end, const char *type) * * That function must be called before late_initcall. * - * Returns 0 on success, or -ENOMEM if no memory could be allocated. - **/ + * Return: 0 on success, or -ENOMEM if no memory could be allocated. + */ int __init firmware_map_add_early(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; @@ -346,8 +348,8 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type) * * removes a firmware mapping entry. * - * Returns 0 on success, or -EINVAL if no entry. - **/ + * Return: 0 on success, or -EINVAL if no entry. + */ int __meminit firmware_map_remove(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; diff --git a/drivers/md/md.c b/drivers/md/md.c index 4dbed4a..8d9f89b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2024,7 +2024,6 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) { char b[BDEVNAME_SIZE]; struct kobject *ko; - char *s; int err; /* prevent duplicates */ @@ -2070,8 +2069,7 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) return -EBUSY; } bdevname(rdev->bdev,b); - while ( (s=strchr(b, '/')) != NULL) - *s = '!'; + strreplace(b, '/', '!'); rdev->mddev = mddev; printk(KERN_INFO "md: bind<%s>\n", b); diff --git a/drivers/misc/altera-stapl/altera.c b/drivers/misc/altera-stapl/altera.c index bca2630..f53e217 100644 --- a/drivers/misc/altera-stapl/altera.c +++ b/drivers/misc/altera-stapl/altera.c @@ -2451,7 +2451,7 @@ int altera_init(struct altera_config *config, const struct firmware *fw) astate->config = config; if (!astate->config->jtag_io) { - dprintk(KERN_INFO "%s: using byteblaster!\n", __func__); + dprintk("%s: using byteblaster!\n", __func__); astate->config->jtag_io = netup_jtag_io_lpt; } diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index 36f5d52..9a60bd4 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -220,7 +220,7 @@ static unsigned long lookup_addr(char *arg) else if (!strcmp(arg, "sys_open")) addr = (unsigned long)do_sys_open; else if (!strcmp(arg, "do_fork")) - addr = (unsigned long)do_fork; + addr = (unsigned long)_do_fork; else if (!strcmp(arg, "hw_break_val")) addr = (unsigned long)&hw_break_val; addr = (unsigned long) dereference_function_descriptor((void *)addr); diff --git a/drivers/misc/spear13xx_pcie_gadget.c b/drivers/misc/spear13xx_pcie_gadget.c index fe3ad0c..b8374cd 100644 --- a/drivers/misc/spear13xx_pcie_gadget.c +++ b/drivers/misc/spear13xx_pcie_gadget.c @@ -2,7 +2,7 @@ * drivers/misc/spear13xx_pcie_gadget.c * * Copyright (C) 2010 ST Microelectronics - * Pratyush Anand<pratyush.anand@st.com> + * Pratyush Anand<pratyush.anand@gmail.com> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 15731d1..97f3acd 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -79,6 +79,12 @@ static LIST_HEAD(target_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); +/* + * Console driver for extended netconsoles. Registered on the first use to + * avoid unnecessarily enabling ext message formatting. + */ +static struct console netconsole_ext; + /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. @@ -104,14 +110,15 @@ struct netconsole_target { #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_item item; #endif - int enabled; - struct mutex mutex; + bool enabled; + bool extended; struct netpoll np; }; #ifdef CONFIG_NETCONSOLE_DYNAMIC static struct configfs_subsystem netconsole_subsys; +static DEFINE_MUTEX(dynamic_netconsole_mutex); static int __init dynamic_netconsole_init(void) { @@ -185,9 +192,13 @@ static struct netconsole_target *alloc_param_target(char *target_config) strlcpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; - mutex_init(&nt->mutex); eth_broadcast_addr(nt->np.remote_mac); + if (*target_config == '+') { + nt->extended = true; + target_config++; + } + /* Parse parameters and setup netpoll */ err = netpoll_parse_options(&nt->np, target_config); if (err) @@ -197,7 +208,7 @@ static struct netconsole_target *alloc_param_target(char *target_config) if (err) goto fail; - nt->enabled = 1; + nt->enabled = true; return nt; @@ -258,6 +269,11 @@ static ssize_t show_enabled(struct netconsole_target *nt, char *buf) return snprintf(buf, PAGE_SIZE, "%d\n", nt->enabled); } +static ssize_t show_extended(struct netconsole_target *nt, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", nt->extended); +} + static ssize_t show_dev_name(struct netconsole_target *nt, char *buf) { return snprintf(buf, PAGE_SIZE, "%s\n", nt->np.dev_name); @@ -322,13 +338,18 @@ static ssize_t store_enabled(struct netconsole_target *nt, return err; if (enabled < 0 || enabled > 1) return -EINVAL; - if (enabled == nt->enabled) { + if ((bool)enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); return -EINVAL; } - if (enabled) { /* 1 */ + if (enabled) { /* true */ + if (nt->extended && !(netconsole_ext.flags & CON_ENABLED)) { + netconsole_ext.flags |= CON_ENABLED; + register_console(&netconsole_ext); + } + /* * Skip netpoll_parse_options() -- all the attributes are * already configured via configfs. Just print them out. @@ -340,13 +361,13 @@ static ssize_t store_enabled(struct netconsole_target *nt, return err; pr_info("netconsole: network logging started\n"); - } else { /* 0 */ + } else { /* false */ /* We need to disable the netconsole before cleaning it up * otherwise we might end up in write_msg() with - * nt->np.dev == NULL and nt->enabled == 1 + * nt->np.dev == NULL and nt->enabled == true */ spin_lock_irqsave(&target_list_lock, flags); - nt->enabled = 0; + nt->enabled = false; spin_unlock_irqrestore(&target_list_lock, flags); netpoll_cleanup(&nt->np); } @@ -356,6 +377,30 @@ static ssize_t store_enabled(struct netconsole_target *nt, return strnlen(buf, count); } +static ssize_t store_extended(struct netconsole_target *nt, + const char *buf, + size_t count) +{ + int extended; + int err; + + if (nt->enabled) { + pr_err("target (%s) is enabled, disable to update parameters\n", + config_item_name(&nt->item)); + return -EINVAL; + } + + err = kstrtoint(buf, 10, &extended); + if (err < 0) + return err; + if (extended < 0 || extended > 1) + return -EINVAL; + + nt->extended = extended; + + return strnlen(buf, count); +} + static ssize_t store_dev_name(struct netconsole_target *nt, const char *buf, size_t count) @@ -508,6 +553,7 @@ static struct netconsole_target_attr netconsole_target_##_name = \ __CONFIGFS_ATTR(_name, S_IRUGO | S_IWUSR, show_##_name, store_##_name) NETCONSOLE_TARGET_ATTR_RW(enabled); +NETCONSOLE_TARGET_ATTR_RW(extended); NETCONSOLE_TARGET_ATTR_RW(dev_name); NETCONSOLE_TARGET_ATTR_RW(local_port); NETCONSOLE_TARGET_ATTR_RW(remote_port); @@ -518,6 +564,7 @@ NETCONSOLE_TARGET_ATTR_RW(remote_mac); static struct configfs_attribute *netconsole_target_attrs[] = { &netconsole_target_enabled.attr, + &netconsole_target_extended.attr, &netconsole_target_dev_name.attr, &netconsole_target_local_port.attr, &netconsole_target_remote_port.attr, @@ -562,10 +609,10 @@ static ssize_t netconsole_target_attr_store(struct config_item *item, struct netconsole_target_attr *na = container_of(attr, struct netconsole_target_attr, attr); - mutex_lock(&nt->mutex); + mutex_lock(&dynamic_netconsole_mutex); if (na->store) ret = na->store(nt, buf, count); - mutex_unlock(&nt->mutex); + mutex_unlock(&dynamic_netconsole_mutex); return ret; } @@ -594,7 +641,7 @@ static struct config_item *make_netconsole_target(struct config_group *group, /* * Allocate and initialize with defaults. - * Target is disabled at creation (enabled == 0). + * Target is disabled at creation (!enabled). */ nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) @@ -604,7 +651,6 @@ static struct config_item *make_netconsole_target(struct config_group *group, strlcpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; - mutex_init(&nt->mutex); eth_broadcast_addr(nt->np.remote_mac); /* Initialize the config_item member */ @@ -695,7 +741,7 @@ restart: spin_lock_irqsave(&target_list_lock, flags); dev_put(nt->np.dev); nt->np.dev = NULL; - nt->enabled = 0; + nt->enabled = false; stopped = true; netconsole_target_put(nt); goto restart; @@ -729,6 +775,82 @@ static struct notifier_block netconsole_netdev_notifier = { .notifier_call = netconsole_netdev_event, }; +/** + * send_ext_msg_udp - send extended log message to target + * @nt: target to send message to + * @msg: extended log message to send + * @msg_len: length of message + * + * Transfer extended log @msg to @nt. If @msg is longer than + * MAX_PRINT_CHUNK, it'll be split and transmitted in multiple chunks with + * ncfrag header field added to identify them. + */ +static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, + int msg_len) +{ + static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */ + const char *header, *body; + int offset = 0; + int header_len, body_len; + + if (msg_len <= MAX_PRINT_CHUNK) { + netpoll_send_udp(&nt->np, msg, msg_len); + return; + } + + /* need to insert extra header fields, detect header and body */ + header = msg; + body = memchr(msg, ';', msg_len); + if (WARN_ON_ONCE(!body)) + return; + + header_len = body - header; + body_len = msg_len - header_len - 1; + body++; + + /* + * Transfer multiple chunks with the following extra header. + * "ncfrag=<byte-offset>/<total-bytes>" + */ + memcpy(buf, header, header_len); + + while (offset < body_len) { + int this_header = header_len; + int this_chunk; + + this_header += scnprintf(buf + this_header, + sizeof(buf) - this_header, + ",ncfrag=%d/%d;", offset, body_len); + + this_chunk = min(body_len - offset, + MAX_PRINT_CHUNK - this_header); + if (WARN_ON_ONCE(this_chunk <= 0)) + return; + + memcpy(buf + this_header, body + offset, this_chunk); + + netpoll_send_udp(&nt->np, buf, this_header + this_chunk); + + offset += this_chunk; + } +} + +static void write_ext_msg(struct console *con, const char *msg, + unsigned int len) +{ + struct netconsole_target *nt; + unsigned long flags; + + if ((oops_only && !oops_in_progress) || list_empty(&target_list)) + return; + + spin_lock_irqsave(&target_list_lock, flags); + list_for_each_entry(nt, &target_list, list) + if (nt->extended && nt->enabled && netif_running(nt->np.dev)) + send_ext_msg_udp(nt, msg, len); + spin_unlock_irqrestore(&target_list_lock, flags); +} + static void write_msg(struct console *con, const char *msg, unsigned int len) { int frag, left; @@ -744,8 +866,7 @@ static void write_msg(struct console *con, const char *msg, unsigned int len) spin_lock_irqsave(&target_list_lock, flags); list_for_each_entry(nt, &target_list, list) { - netconsole_target_get(nt); - if (nt->enabled && netif_running(nt->np.dev)) { + if (!nt->extended && nt->enabled && netif_running(nt->np.dev)) { /* * We nest this inside the for-each-target loop above * so that we're able to get as much logging out to @@ -760,11 +881,16 @@ static void write_msg(struct console *con, const char *msg, unsigned int len) left -= frag; } } - netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); } +static struct console netconsole_ext = { + .name = "netcon_ext", + .flags = CON_EXTENDED, /* starts disabled, registered on first use */ + .write = write_ext_msg, +}; + static struct console netconsole = { .name = "netcon", .flags = CON_ENABLED, @@ -787,7 +913,11 @@ static int __init init_netconsole(void) goto fail; } /* Dump existing printks when we register */ - netconsole.flags |= CON_PRINTBUFFER; + if (nt->extended) + netconsole_ext.flags |= CON_PRINTBUFFER | + CON_ENABLED; + else + netconsole.flags |= CON_PRINTBUFFER; spin_lock_irqsave(&target_list_lock, flags); list_add(&nt->list, &target_list); @@ -803,6 +933,8 @@ static int __init init_netconsole(void) if (err) goto undonotifier; + if (netconsole_ext.flags & CON_ENABLED) + register_console(&netconsole_ext); register_console(&netconsole); pr_info("network logging started\n"); @@ -831,6 +963,7 @@ static void __exit cleanup_netconsole(void) { struct netconsole_target *nt, *tmp; + unregister_console(&netconsole_ext); unregister_console(&netconsole); dynamic_netconsole_exit(); unregister_netdevice_notifier(&netconsole_netdev_notifier); diff --git a/drivers/pci/host/pcie-spear13xx.c b/drivers/pci/host/pcie-spear13xx.c index dfec428..c49fbdc 100644 --- a/drivers/pci/host/pcie-spear13xx.c +++ b/drivers/pci/host/pcie-spear13xx.c @@ -4,8 +4,8 @@ * SPEAr13xx PCIe Glue Layer Source Code * * Copyright (C) 2010-2014 ST Microelectronics - * Pratyush Anand <pratyush.anand@st.com> - * Mohit Kumar <mohit.kumar@st.com> + * Pratyush Anand <pratyush.anand@gmail.com> + * Mohit Kumar <mohit.kumar.dhaka@gmail.com> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any @@ -386,5 +386,5 @@ static int __init spear13xx_pcie_init(void) module_init(spear13xx_pcie_init); MODULE_DESCRIPTION("ST Microelectronics SPEAr13xx PCIe host controller driver"); -MODULE_AUTHOR("Pratyush Anand <pratyush.anand@st.com>"); +MODULE_AUTHOR("Pratyush Anand <pratyush.anand@gmail.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/phy-spear1310-miphy.c b/drivers/phy/phy-spear1310-miphy.c index 65ae640..45d0005 100644 --- a/drivers/phy/phy-spear1310-miphy.c +++ b/drivers/phy/phy-spear1310-miphy.c @@ -2,8 +2,8 @@ * ST SPEAr1310-miphy driver * * Copyright (C) 2014 ST Microelectronics - * Pratyush Anand <pratyush.anand@st.com> - * Mohit Kumar <mohit.kumar@st.com> + * Pratyush Anand <pratyush.anand@gmail.com> + * Mohit Kumar <mohit.kumar.dhaka@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -257,5 +257,5 @@ static struct platform_driver spear1310_miphy_driver = { module_platform_driver(spear1310_miphy_driver); MODULE_DESCRIPTION("ST SPEAR1310-MIPHY driver"); -MODULE_AUTHOR("Pratyush Anand <pratyush.anand@st.com>"); +MODULE_AUTHOR("Pratyush Anand <pratyush.anand@gmail.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/phy-spear1340-miphy.c b/drivers/phy/phy-spear1340-miphy.c index 1a00c28..494240d 100644 --- a/drivers/phy/phy-spear1340-miphy.c +++ b/drivers/phy/phy-spear1340-miphy.c @@ -2,8 +2,8 @@ * ST spear1340-miphy driver * * Copyright (C) 2014 ST Microelectronics - * Pratyush Anand <pratyush.anand@st.com> - * Mohit Kumar <mohit.kumar@st.com> + * Pratyush Anand <pratyush.anand@gmail.com> + * Mohit Kumar <mohit.kumar.dhaka@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -290,5 +290,5 @@ static struct platform_driver spear1340_miphy_driver = { module_platform_driver(spear1340_miphy_driver); MODULE_DESCRIPTION("ST SPEAR1340-MIPHY driver"); -MODULE_AUTHOR("Pratyush Anand <pratyush.anand@st.com>"); +MODULE_AUTHOR("Pratyush Anand <pratyush.anand@gmail.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/usb/misc/lvstest.c b/drivers/usb/misc/lvstest.c index 62cb8cd..86b4e4b 100644 --- a/drivers/usb/misc/lvstest.c +++ b/drivers/usb/misc/lvstest.c @@ -4,7 +4,7 @@ * Test pattern generation for Link Layer Validation System Tests * * Copyright (C) 2014 ST Microelectronics - * Pratyush Anand <pratyush.anand@st.com> + * Pratyush Anand <pratyush.anand@gmail.com> * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any diff --git a/fs/befs/btree.c b/fs/befs/btree.c index 0826e91..22c16628 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -137,8 +137,8 @@ static int befs_bt_read_super(struct super_block *sb, befs_data_stream * ds, befs_btree_super * sup) { - struct buffer_head *bh = NULL; - befs_disk_btree_super *od_sup = NULL; + struct buffer_head *bh; + befs_disk_btree_super *od_sup; befs_debug(sb, "---> %s", __func__); @@ -250,7 +250,7 @@ int befs_btree_find(struct super_block *sb, befs_data_stream * ds, const char *key, befs_off_t * value) { - struct befs_btree_node *this_node = NULL; + struct befs_btree_node *this_node; befs_btree_super bt_super; befs_off_t node_off; int res; diff --git a/fs/coredump.c b/fs/coredump.c index bbbe139..e52e006 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -70,7 +70,8 @@ static int expand_corename(struct core_name *cn, int size) return 0; } -static int cn_vprintf(struct core_name *cn, const char *fmt, va_list arg) +static __printf(2, 0) int cn_vprintf(struct core_name *cn, const char *fmt, + va_list arg) { int free, need; va_list arg_copy; @@ -93,7 +94,7 @@ again: return -ENOMEM; } -static int cn_printf(struct core_name *cn, const char *fmt, ...) +static __printf(2, 3) int cn_printf(struct core_name *cn, const char *fmt, ...) { va_list arg; int ret; @@ -105,7 +106,8 @@ static int cn_printf(struct core_name *cn, const char *fmt, ...) return ret; } -static int cn_esc_printf(struct core_name *cn, const char *fmt, ...) +static __printf(2, 3) +int cn_esc_printf(struct core_name *cn, const char *fmt, ...) { int cur = cn->used; va_list arg; @@ -209,11 +211,15 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) break; /* uid */ case 'u': - err = cn_printf(cn, "%d", cred->uid); + err = cn_printf(cn, "%u", + from_kuid(&init_user_ns, + cred->uid)); break; /* gid */ case 'g': - err = cn_printf(cn, "%d", cred->gid); + err = cn_printf(cn, "%u", + from_kgid(&init_user_ns, + cred->gid)); break; case 'd': err = cn_printf(cn, "%d", @@ -221,7 +227,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) break; /* signal that caused the coredump */ case 's': - err = cn_printf(cn, "%ld", cprm->siginfo->si_signo); + err = cn_printf(cn, "%d", + cprm->siginfo->si_signo); break; /* UNIX time of coredump */ case 't': { diff --git a/fs/efs/super.c b/fs/efs/super.c index 7fca462..c8411a3 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -67,7 +67,7 @@ static struct kmem_cache * efs_inode_cachep; static struct inode *efs_alloc_inode(struct super_block *sb) { struct efs_inode_info *ei; - ei = (struct efs_inode_info *)kmem_cache_alloc(efs_inode_cachep, GFP_KERNEL); + ei = kmem_cache_alloc(efs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a7b4b6e..5c78764 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3446,7 +3446,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) unsigned long journal_devnum = 0; unsigned long def_mount_opts; struct inode *root; - char *cp; const char *descr; int ret = -ENOMEM; int blocksize, clustersize; @@ -3477,8 +3476,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) part_stat_read(sb->s_bdev->bd_part, sectors[1]); /* Cleanup superblock name */ - for (cp = sb->s_id; (cp = strchr(cp, '/'));) - *cp = '!'; + strreplace(sb->s_id, '/', '!'); /* -EINVAL is default */ ret = -EINVAL; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 179d7d8..4ff3fad 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1135,7 +1135,6 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, { journal_t *journal = journal_init_common(); struct buffer_head *bh; - char *p; int n; if (!journal) @@ -1148,9 +1147,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, journal->j_blk_offset = start; journal->j_maxlen = len; bdevname(journal->j_dev, journal->j_devname); - p = journal->j_devname; - while ((p = strchr(p, '/'))) - *p = '!'; + strreplace(journal->j_devname, '/', '!'); jbd2_stats_proc_init(journal); n = journal->j_blocksize / sizeof(journal_block_tag_t); journal->j_wbufsize = n; @@ -1202,10 +1199,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode) journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev; journal->j_inode = inode; bdevname(journal->j_dev, journal->j_devname); - p = journal->j_devname; - while ((p = strchr(p, '/'))) - *p = '!'; - p = journal->j_devname + strlen(journal->j_devname); + p = strreplace(journal->j_devname, '/', '!'); sprintf(p, "-%lu", journal->j_inode->i_ino); jbd_debug(1, "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n", diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 1182d1e..086cd0a 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -62,7 +62,7 @@ static struct kmem_cache * minix_inode_cachep; static struct inode *minix_alloc_inode(struct super_block *sb) { struct minix_inode_info *ei; - ei = (struct minix_inode_info *)kmem_cache_alloc(minix_inode_cachep, GFP_KERNEL); + ei = kmem_cache_alloc(minix_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 2218083..37dd6b0 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -496,8 +496,7 @@ static struct dentry *nilfs_fh_to_dentry(struct super_block *sb, struct fid *fh, { struct nilfs_fid *fid = (struct nilfs_fid *)fh; - if ((fh_len != NILFS_FID_SIZE_NON_CONNECTABLE && - fh_len != NILFS_FID_SIZE_CONNECTABLE) || + if (fh_len < NILFS_FID_SIZE_NON_CONNECTABLE || (fh_type != FILEID_NILFS_WITH_PARENT && fh_type != FILEID_NILFS_WITHOUT_PARENT)) return NULL; @@ -510,7 +509,7 @@ static struct dentry *nilfs_fh_to_parent(struct super_block *sb, struct fid *fh, { struct nilfs_fid *fid = (struct nilfs_fid *)fh; - if (fh_len != NILFS_FID_SIZE_CONNECTABLE || + if (fh_len < NILFS_FID_SIZE_CONNECTABLE || fh_type != FILEID_NILFS_WITH_PARENT) return NULL; diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 2183fcf..d751fcb 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -71,3 +71,7 @@ config PROC_PAGE_MONITOR /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap, /proc/kpagecount, and /proc/kpageflags. Disabling these interfaces will reduce the size of the kernel by approximately 4kb. + +config PROC_CHILDREN + bool "Include /proc/<pid>/task/<tid>/children file" + default n diff --git a/fs/proc/array.c b/fs/proc/array.c index 3f57dac..ce065cf 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -577,7 +577,7 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, return 0; } -#ifdef CONFIG_CHECKPOINT_RESTORE +#ifdef CONFIG_PROC_CHILDREN static struct pid * get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos) { @@ -700,4 +700,4 @@ const struct file_operations proc_tid_children_operations = { .llseek = seq_lseek, .release = children_seq_release, }; -#endif /* CONFIG_CHECKPOINT_RESTORE */ +#endif /* CONFIG_PROC_CHILDREN */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 286a422..1d540b3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -196,18 +196,205 @@ static int proc_root_link(struct dentry *dentry, struct path *path) return result; } -static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns, - struct pid *pid, struct task_struct *task) +static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, + size_t _count, loff_t *pos) { + struct task_struct *tsk; + struct mm_struct *mm; + char *page; + unsigned long count = _count; + unsigned long arg_start, arg_end, env_start, env_end; + unsigned long len1, len2, len; + unsigned long p; + char c; + ssize_t rv; + + BUG_ON(*pos < 0); + + tsk = get_proc_task(file_inode(file)); + if (!tsk) + return -ESRCH; + mm = get_task_mm(tsk); + put_task_struct(tsk); + if (!mm) + return 0; + /* Check if process spawned far enough to have cmdline. */ + if (!mm->env_end) { + rv = 0; + goto out_mmput; + } + + page = (char *)__get_free_page(GFP_TEMPORARY); + if (!page) { + rv = -ENOMEM; + goto out_mmput; + } + + down_read(&mm->mmap_sem); + arg_start = mm->arg_start; + arg_end = mm->arg_end; + env_start = mm->env_start; + env_end = mm->env_end; + up_read(&mm->mmap_sem); + + BUG_ON(arg_start > arg_end); + BUG_ON(env_start > env_end); + + len1 = arg_end - arg_start; + len2 = env_end - env_start; + /* - * Rely on struct seq_operations::show() being called once - * per internal buffer allocation. See single_open(), traverse(). + * Inherently racy -- command line shares address space + * with code and data. */ - BUG_ON(m->size < PAGE_SIZE); - m->count += get_cmdline(task, m->buf, PAGE_SIZE); - return 0; + rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); + if (rv <= 0) + goto out_free_page; + + rv = 0; + + if (c == '\0') { + /* Command line (set of strings) occupies whole ARGV. */ + if (len1 <= *pos) + goto out_free_page; + + p = arg_start + *pos; + len = len1 - *pos; + while (count > 0 && len > 0) { + unsigned int _count; + int nr_read; + + _count = min3(count, len, PAGE_SIZE); + nr_read = access_remote_vm(mm, p, page, _count, 0); + if (nr_read < 0) + rv = nr_read; + if (nr_read <= 0) + goto out_free_page; + + if (copy_to_user(buf, page, nr_read)) { + rv = -EFAULT; + goto out_free_page; + } + + p += nr_read; + len -= nr_read; + buf += nr_read; + count -= nr_read; + rv += nr_read; + } + } else { + /* + * Command line (1 string) occupies ARGV and maybe + * extends into ENVP. + */ + if (len1 + len2 <= *pos) + goto skip_argv_envp; + if (len1 <= *pos) + goto skip_argv; + + p = arg_start + *pos; + len = len1 - *pos; + while (count > 0 && len > 0) { + unsigned int _count, l; + int nr_read; + bool final; + + _count = min3(count, len, PAGE_SIZE); + nr_read = access_remote_vm(mm, p, page, _count, 0); + if (nr_read < 0) + rv = nr_read; + if (nr_read <= 0) + goto out_free_page; + + /* + * Command line can be shorter than whole ARGV + * even if last "marker" byte says it is not. + */ + final = false; + l = strnlen(page, nr_read); + if (l < nr_read) { + nr_read = l; + final = true; + } + + if (copy_to_user(buf, page, nr_read)) { + rv = -EFAULT; + goto out_free_page; + } + + p += nr_read; + len -= nr_read; + buf += nr_read; + count -= nr_read; + rv += nr_read; + + if (final) + goto out_free_page; + } +skip_argv: + /* + * Command line (1 string) occupies ARGV and + * extends into ENVP. + */ + if (len1 <= *pos) { + p = env_start + *pos - len1; + len = len1 + len2 - *pos; + } else { + p = env_start; + len = len2; + } + while (count > 0 && len > 0) { + unsigned int _count, l; + int nr_read; + bool final; + + _count = min3(count, len, PAGE_SIZE); + nr_read = access_remote_vm(mm, p, page, _count, 0); + if (nr_read < 0) + rv = nr_read; + if (nr_read <= 0) + goto out_free_page; + + /* Find EOS. */ + final = false; + l = strnlen(page, nr_read); + if (l < nr_read) { + nr_read = l; + final = true; + } + + if (copy_to_user(buf, page, nr_read)) { + rv = -EFAULT; + goto out_free_page; + } + + p += nr_read; + len -= nr_read; + buf += nr_read; + count -= nr_read; + rv += nr_read; + + if (final) + goto out_free_page; + } +skip_argv_envp: + ; + } + +out_free_page: + free_page((unsigned long)page); +out_mmput: + mmput(mm); + if (rv > 0) + *pos += rv; + return rv; } +static const struct file_operations proc_pid_cmdline_ops = { + .read = proc_pid_cmdline_read, + .llseek = generic_file_llseek, +}; + static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -2572,7 +2759,7 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif - ONE("cmdline", S_IRUGO, proc_pid_cmdline), + REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tgid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_pid_maps_operations), @@ -2918,11 +3105,11 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_HAVE_ARCH_TRACEHOOK ONE("syscall", S_IRUSR, proc_pid_syscall), #endif - ONE("cmdline", S_IRUGO, proc_pid_cmdline), + REG("cmdline", S_IRUGO, proc_pid_cmdline_ops), ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_tid_maps_operations), -#ifdef CONFIG_CHECKPOINT_RESTORE +#ifdef CONFIG_PROC_CHILDREN REG("children", S_IRUGO, proc_tid_children_operations), #endif #ifdef CONFIG_NUMA diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 3e0af31..0e4cf72 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -589,8 +589,7 @@ static struct kmem_cache *reiserfs_inode_cachep; static struct inode *reiserfs_alloc_inode(struct super_block *sb) { struct reiserfs_inode_info *ei; - ei = (struct reiserfs_inode_info *) - kmem_cache_alloc(reiserfs_inode_cachep, GFP_KERNEL); + ei = kmem_cache_alloc(reiserfs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; atomic_set(&ei->openers, 0); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 371e560..dfaa7b3 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -5,9 +5,9 @@ /* * Common definitions for all gcc versions go here. */ -#define GCC_VERSION (__GNUC__ * 10000 \ - + __GNUC_MINOR__ * 100 \ - + __GNUC_PATCHLEVEL__) +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) /* Optimization barrier */ @@ -46,55 +46,63 @@ * the inline assembly constraint from =g to =r, in this particular * case either is valid. */ -#define RELOC_HIDE(ptr, off) \ - ({ unsigned long __ptr; \ - __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ - (typeof(ptr)) (__ptr + (off)); }) +#define RELOC_HIDE(ptr, off) \ +({ \ + unsigned long __ptr; \ + __asm__ ("" : "=r"(__ptr) : "0"(ptr)); \ + (typeof(ptr)) (__ptr + (off)); \ +}) /* Make the optimizer believe the variable can be manipulated arbitrarily. */ -#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var)) +#define OPTIMIZER_HIDE_VAR(var) \ + __asm__ ("" : "=r" (var) : "0" (var)) #ifdef __CHECKER__ -#define __must_be_array(arr) 0 +#define __must_be_array(a) 0 #else /* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #endif /* * Force always-inline if the user requests it so via the .config, * or if gcc is too old: */ -#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ +#if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4) -# define inline inline __attribute__((always_inline)) notrace -# define __inline__ __inline__ __attribute__((always_inline)) notrace -# define __inline __inline __attribute__((always_inline)) notrace +#define inline inline __attribute__((always_inline)) notrace +#define __inline__ __inline__ __attribute__((always_inline)) notrace +#define __inline __inline __attribute__((always_inline)) notrace #else /* A lot of inline functions can cause havoc with function tracing */ -# define inline inline notrace -# define __inline__ __inline__ notrace -# define __inline __inline notrace +#define inline inline notrace +#define __inline__ __inline__ notrace +#define __inline __inline notrace #endif -#define __deprecated __attribute__((deprecated)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) +#define __always_inline inline __attribute__((always_inline)) +#define noinline __attribute__((noinline)) + +#define __deprecated __attribute__((deprecated)) +#define __packed __attribute__((packed)) +#define __weak __attribute__((weak)) +#define __alias(symbol) __attribute__((alias(#symbol))) /* - * it doesn't make sense on ARM (currently the only user of __naked) to trace - * naked functions because then mcount is called without stack and frame pointer - * being set up and there is no chance to restore the lr register to the value - * before mcount was called. + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + * + * The asm() bodies of naked functions often depend on standard calling + * conventions, therefore they must be noinline and noclone. * - * The asm() bodies of naked functions often depend on standard calling conventions, - * therefore they must be noinline and noclone. GCC 4.[56] currently fail to enforce - * this, so we must do so ourselves. See GCC PR44290. + * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. + * See GCC PR44290. */ -#define __naked __attribute__((naked)) noinline __noclone notrace +#define __naked __attribute__((naked)) noinline __noclone notrace -#define __noreturn __attribute__((noreturn)) +#define __noreturn __attribute__((noreturn)) /* * From the GCC manual: @@ -106,19 +114,130 @@ * would be. * [...] */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define noinline __attribute__((noinline)) -#define __attribute_const__ __attribute__((__const__)) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) - -#define __gcc_header(x) #x -#define _gcc_header(x) __gcc_header(linux/compiler-gcc##x.h) -#define gcc_header(x) _gcc_header(x) -#include gcc_header(__GNUC__) +#define __pure __attribute__((pure)) +#define __aligned(x) __attribute__((aligned(x))) +#define __printf(a, b) __attribute__((format(printf, a, b))) +#define __scanf(a, b) __attribute__((format(scanf, a, b))) +#define __attribute_const__ __attribute__((__const__)) +#define __maybe_unused __attribute__((unused)) +#define __always_unused __attribute__((unused)) + +/* gcc version specific checks */ + +#if GCC_VERSION < 30200 +# error Sorry, your compiler is too old - please upgrade it. +#endif + +#if GCC_VERSION < 30300 +# define __used __attribute__((__unused__)) +#else +# define __used __attribute__((__used__)) +#endif + +#ifdef CONFIG_GCOV_KERNEL +# if GCC_VERSION < 30400 +# error "GCOV profiling support for gcc versions below 3.4 not included" +# endif /* __GNUC_MINOR__ */ +#endif /* CONFIG_GCOV_KERNEL */ + +#if GCC_VERSION >= 30400 +#define __must_check __attribute__((warn_unused_result)) +#endif + +#if GCC_VERSION >= 40000 + +/* GCC 4.1.[01] miscompiles __weak */ +#ifdef __KERNEL__ +# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 +# error Your version of gcc miscompiles the __weak directive +# endif +#endif + +#define __used __attribute__((__used__)) +#define __compiler_offsetof(a, b) \ + __builtin_offsetof(a, b) + +#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) +#endif + +#if GCC_VERSION >= 40300 +/* Mark functions as cold. gcc will assume any path leading to a call + * to them will be unlikely. This means a lot of manual unlikely()s + * are unnecessary now for any paths leading to the usual suspects + * like BUG(), printk(), panic() etc. [but let's keep them for now for + * older compilers] + * + * Early snapshots of gcc 4.3 don't support this and we can't detect this + * in the preprocessor, but we can live with this because they're unreleased. + * Maketime probing would be overkill here. + * + * gcc also has a __attribute__((__hot__)) to move hot functions into + * a special section, but I don't see any sense in this right now in + * the kernel context + */ +#define __cold __attribute__((__cold__)) + +#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) + +#ifndef __CHECKER__ +# define __compiletime_warning(message) __attribute__((warning(message))) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* __CHECKER__ */ +#endif /* GCC_VERSION >= 40300 */ + +#if GCC_VERSION >= 40500 +/* + * Mark a position in code as unreachable. This can be used to + * suppress control flow warnings after asm blocks that transfer + * control elsewhere. + * + * Early snapshots of gcc 4.5 don't support this and we can't detect + * this in the preprocessor, but we can live with this because they're + * unreleased. Really, we need to have autoconf for the kernel. + */ +#define unreachable() __builtin_unreachable() + +/* Mark a function definition as prohibited from being cloned. */ +#define __noclone __attribute__((__noclone__)) + +#endif /* GCC_VERSION >= 40500 */ + +#if GCC_VERSION >= 40600 +/* + * Tell the optimizer that something else uses this function or variable. + */ +#define __visible __attribute__((externally_visible)) +#endif + +/* + * GCC 'asm goto' miscompiles certain code sequences: + * + * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. + * + * (asm goto is automatically volatile - the naming reflects this.) + */ +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) + +#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +#if GCC_VERSION >= 40400 +#define __HAVE_BUILTIN_BSWAP32__ +#define __HAVE_BUILTIN_BSWAP64__ +#endif +#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) +#define __HAVE_BUILTIN_BSWAP16__ +#endif +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#if GCC_VERSION >= 50000 +#define KASAN_ABI_VERSION 4 +#elif GCC_VERSION >= 40902 +#define KASAN_ABI_VERSION 3 +#endif + +#endif /* gcc version >= 40000 specific checks */ #if !defined(__noclone) #define __noclone /* not needed */ @@ -129,5 +248,3 @@ * code */ #define uninitialized_var(x) x = x - -#define __always_inline inline __attribute__((always_inline)) diff --git a/include/linux/compiler-gcc3.h b/include/linux/compiler-gcc3.h deleted file mode 100644 index 7d89feb..0000000 --- a/include/linux/compiler-gcc3.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc3.h> directly, include <linux/compiler.h> instead." -#endif - -#if GCC_VERSION < 30200 -# error Sorry, your compiler is too old - please upgrade it. -#endif - -#if GCC_VERSION >= 30300 -# define __used __attribute__((__used__)) -#else -# define __used __attribute__((__unused__)) -#endif - -#if GCC_VERSION >= 30400 -#define __must_check __attribute__((warn_unused_result)) -#endif - -#ifdef CONFIG_GCOV_KERNEL -# if GCC_VERSION < 30400 -# error "GCOV profiling support for gcc versions below 3.4 not included" -# endif /* __GNUC_MINOR__ */ -#endif /* CONFIG_GCOV_KERNEL */ diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h deleted file mode 100644 index 769e198..0000000 --- a/include/linux/compiler-gcc4.h +++ /dev/null @@ -1,91 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc4.h> directly, include <linux/compiler.h> instead." -#endif - -/* GCC 4.1.[01] miscompiles __weak */ -#ifdef __KERNEL__ -# if GCC_VERSION >= 40100 && GCC_VERSION <= 40101 -# error Your version of gcc miscompiles the __weak directive -# endif -#endif - -#define __used __attribute__((__used__)) -#define __must_check __attribute__((warn_unused_result)) -#define __compiler_offsetof(a,b) __builtin_offsetof(a,b) - -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 -# define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#endif - -#if GCC_VERSION >= 40300 -/* Mark functions as cold. gcc will assume any path leading to a call - to them will be unlikely. This means a lot of manual unlikely()s - are unnecessary now for any paths leading to the usual suspects - like BUG(), printk(), panic() etc. [but let's keep them for now for - older compilers] - - Early snapshots of gcc 4.3 don't support this and we can't detect this - in the preprocessor, but we can live with this because they're unreleased. - Maketime probing would be overkill here. - - gcc also has a __attribute__((__hot__)) to move hot functions into - a special section, but I don't see any sense in this right now in - the kernel context */ -#define __cold __attribute__((__cold__)) - -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ -#endif /* GCC_VERSION >= 40300 */ - -#if GCC_VERSION >= 40500 -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. - */ -#define unreachable() __builtin_unreachable() - -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) - -#endif /* GCC_VERSION >= 40500 */ - -#if GCC_VERSION >= 40600 -/* - * Tell the optimizer that something else uses this function or variable. - */ -#define __visible __attribute__((externally_visible)) -#endif - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#if GCC_VERSION >= 40400 -#define __HAVE_BUILTIN_BSWAP32__ -#define __HAVE_BUILTIN_BSWAP64__ -#endif -#if GCC_VERSION >= 40800 || (defined(__powerpc__) && GCC_VERSION >= 40600) -#define __HAVE_BUILTIN_BSWAP16__ -#endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ - -#if GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 -#endif diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h deleted file mode 100644 index efee493..0000000 --- a/include/linux/compiler-gcc5.h +++ /dev/null @@ -1,67 +0,0 @@ -#ifndef __LINUX_COMPILER_H -#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead." -#endif - -#define __used __attribute__((__used__)) -#define __must_check __attribute__((warn_unused_result)) -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - -/* Mark functions as cold. gcc will assume any path leading to a call - to them will be unlikely. This means a lot of manual unlikely()s - are unnecessary now for any paths leading to the usual suspects - like BUG(), printk(), panic() etc. [but let's keep them for now for - older compilers] - - Early snapshots of gcc 4.3 don't support this and we can't detect this - in the preprocessor, but we can live with this because they're unreleased. - Maketime probing would be overkill here. - - gcc also has a __attribute__((__hot__)) to move hot functions into - a special section, but I don't see any sense in this right now in - the kernel context */ -#define __cold __attribute__((__cold__)) - -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) - -#ifndef __CHECKER__ -# define __compiletime_warning(message) __attribute__((warning(message))) -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* __CHECKER__ */ - -/* - * Mark a position in code as unreachable. This can be used to - * suppress control flow warnings after asm blocks that transfer - * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. - */ -#define unreachable() __builtin_unreachable() - -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__)) - -/* - * Tell the optimizer that something else uses this function or variable. - */ -#define __visible __attribute__((externally_visible)) - -/* - * GCC 'asm goto' miscompiles certain code sequences: - * - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 - * - * Work it around via a compiler barrier quirk suggested by Jakub Jelinek. - * - * (asm goto is automatically volatile - the naming reflects this.) - */ -#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) - -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP -#define __HAVE_BUILTIN_BSWAP32__ -#define __HAVE_BUILTIN_BSWAP64__ -#define __HAVE_BUILTIN_BSWAP16__ -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ - -#define KASAN_ABI_VERSION 4 diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 0c9a2f2..d4c7113 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -13,10 +13,12 @@ /* Intel ECC compiler doesn't support gcc specific asm stmts. * It uses intrinsics to do the equivalent things. */ +#undef barrier #undef barrier_data #undef RELOC_HIDE #undef OPTIMIZER_HIDE_VAR +#define barrier() __memory_barrier() #define barrier_data(ptr) barrier() #define RELOC_HIDE(ptr, off) \ diff --git a/include/linux/console.h b/include/linux/console.h index 9f50fb4..bd19434 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -115,6 +115,7 @@ static inline int con_debug_leave(void) #define CON_BOOT (8) #define CON_ANYTIME (16) /* Safe to call when cpu is offline */ #define CON_BRL (32) /* Used for a braille device */ +#define CON_EXTENDED (64) /* Use the extended output format a la /dev/kmsg */ struct console { char name[16]; diff --git a/include/linux/printk.h b/include/linux/printk.h index 9b30871..58b1fec 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -30,6 +30,8 @@ static inline const char *printk_skip_level(const char *buffer) return buffer; } +#define CONSOLE_EXT_LOG_MAX 8192 + /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT diff --git a/include/linux/sched.h b/include/linux/sched.h index 6633e83..93ed0b6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2556,8 +2556,22 @@ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct */ extern void mm_release(struct task_struct *, struct mm_struct *); +#ifdef CONFIG_HAVE_COPY_THREAD_TLS +extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, + struct task_struct *, unsigned long); +#else extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *); + +/* Architectures that haven't opted into copy_thread_tls get the tls argument + * via pt_regs, so ignore the tls argument passed via C. */ +static inline int copy_thread_tls( + unsigned long clone_flags, unsigned long sp, unsigned long arg, + struct task_struct *p, unsigned long tls) +{ + return copy_thread(clone_flags, sp, arg, p); +} +#endif extern void flush_thread(void); extern void exit_thread(void); @@ -2576,6 +2590,7 @@ extern int do_execveat(int, struct filename *, const char __user * const __user *, const char __user * const __user *, int); +extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 076af43..9c61c7c 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -3,7 +3,6 @@ #include <uapi/linux/stddef.h> - #undef NULL #define NULL ((void *)0) @@ -14,10 +13,9 @@ enum { #undef offsetof #ifdef __compiler_offsetof -#define offsetof(TYPE,MEMBER) __compiler_offsetof(TYPE,MEMBER) +#define offsetof(TYPE, MEMBER) __compiler_offsetof(TYPE, MEMBER) #else -#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) -#endif +#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) #endif /** @@ -28,3 +26,5 @@ enum { */ #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof(((TYPE *)0)->MEMBER)) + +#endif diff --git a/include/linux/string.h b/include/linux/string.h index e40099e..a8d90db 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -111,6 +111,7 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif void *memchr_inv(const void *s, int c, size_t n); +char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 76d1e38..bb51bec 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -827,15 +827,15 @@ asmlinkage long sys_syncfs(int fd); asmlinkage long sys_fork(void); asmlinkage long sys_vfork(void); #ifdef CONFIG_CLONE_BACKWARDS -asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int, +asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long, int __user *); #else #ifdef CONFIG_CLONE_BACKWARDS3 asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *, - int __user *, int); + int __user *, unsigned long); #else asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, - int __user *, int); + int __user *, unsigned long); #endif #endif diff --git a/include/linux/syslog.h b/include/linux/syslog.h index 4b7b875..c3a7f0c 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -47,12 +47,12 @@ #define SYSLOG_FROM_READER 0 #define SYSLOG_FROM_PROC 1 -int do_syslog(int type, char __user *buf, int count, bool from_file); +int do_syslog(int type, char __user *buf, int count, int source); #ifdef CONFIG_PRINTK -int check_syslog_permissions(int type, bool from_file); +int check_syslog_permissions(int type, int source); #else -static inline int check_syslog_permissions(int type, bool from_file) +static inline int check_syslog_permissions(int type, int source) { return 0; } diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 56529b3..d30eff3 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -81,7 +81,8 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops); + void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops, + struct zpool *zpool); void (*destroy)(void *pool); int (*malloc)(void *pool, size_t size, gfp_t gfp, @@ -102,6 +103,4 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); -int zpool_evict(void *pool, unsigned long handle); - #endif diff --git a/init/Kconfig b/init/Kconfig index 7260b27..f0c2e68 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1136,6 +1136,7 @@ endif # CGROUPS config CHECKPOINT_RESTORE bool "Checkpoint/restore support" if EXPERT + select PROC_CHILDREN default n help Enables additional kernel features in a sake of checkpoint/restore. diff --git a/init/do_mounts.c b/init/do_mounts.c index a95bbdb..dea5de9 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -533,8 +533,13 @@ void __init mount_root(void) } #endif #ifdef CONFIG_BLOCK - create_dev("/dev/root", ROOT_DEV); - mount_block_root("/dev/root", root_mountflags); + { + int err = create_dev("/dev/root", ROOT_DEV); + + if (err < 0) + pr_emerg("Failed to create /dev/root: %d\n", err); + mount_block_root("/dev/root", root_mountflags); + } #endif } diff --git a/kernel/exit.c b/kernel/exit.c index 185752a..031325e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -711,10 +711,10 @@ void do_exit(long code) current->comm, task_pid_nr(current), preempt_count()); - acct_update_integrals(tsk); /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm); + acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { hrtimer_cancel(&tsk->signal->real_timer); diff --git a/kernel/fork.c b/kernel/fork.c index 0bb88b5..4c95cb3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1238,7 +1238,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, unsigned long stack_size, int __user *child_tidptr, struct pid *pid, - int trace) + int trace, + unsigned long tls) { int retval; struct task_struct *p; @@ -1447,7 +1448,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; - retval = copy_thread(clone_flags, stack_start, stack_size, p); + retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls); if (retval) goto bad_fork_cleanup_io; @@ -1659,7 +1660,7 @@ static inline void init_idle_pids(struct pid_link *links) struct task_struct *fork_idle(int cpu) { struct task_struct *task; - task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0); + task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0); if (!IS_ERR(task)) { init_idle_pids(task->pids); init_idle(task, cpu); @@ -1674,11 +1675,12 @@ struct task_struct *fork_idle(int cpu) * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. */ -long do_fork(unsigned long clone_flags, +long _do_fork(unsigned long clone_flags, unsigned long stack_start, unsigned long stack_size, int __user *parent_tidptr, - int __user *child_tidptr) + int __user *child_tidptr, + unsigned long tls) { struct task_struct *p; int trace = 0; @@ -1703,7 +1705,7 @@ long do_fork(unsigned long clone_flags, } p = copy_process(clone_flags, stack_start, stack_size, - child_tidptr, NULL, trace); + child_tidptr, NULL, trace, tls); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. @@ -1744,20 +1746,34 @@ long do_fork(unsigned long clone_flags, return nr; } +#ifndef CONFIG_HAVE_COPY_THREAD_TLS +/* For compatibility with architectures that call do_fork directly rather than + * using the syscall entry points below. */ +long do_fork(unsigned long clone_flags, + unsigned long stack_start, + unsigned long stack_size, + int __user *parent_tidptr, + int __user *child_tidptr) +{ + return _do_fork(clone_flags, stack_start, stack_size, + parent_tidptr, child_tidptr, 0); +} +#endif + /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { - return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, - (unsigned long)arg, NULL, NULL); + return _do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, + (unsigned long)arg, NULL, NULL, 0); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU - return do_fork(SIGCHLD, 0, 0, NULL, NULL); + return _do_fork(SIGCHLD, 0, 0, NULL, NULL, 0); #else /* can not support in nommu mode */ return -EINVAL; @@ -1768,8 +1784,8 @@ SYSCALL_DEFINE0(fork) #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, - 0, NULL, NULL); + return _do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0, + 0, NULL, NULL, 0); } #endif @@ -1777,27 +1793,27 @@ SYSCALL_DEFINE0(vfork) #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, - int, tls_val, + unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, - int, tls_val) + unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, - int, tls_val) + unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, - int, tls_val) + unsigned long, tls) #endif { - return do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr); + return _do_fork(clone_flags, newsp, 0, parent_tidptr, child_tidptr, tls); } #endif diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index c099b08..de55384 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -85,6 +85,18 @@ static struct lockdep_map console_lock_dep_map = { #endif /* + * Number of registered extended console drivers. + * + * If extended consoles are present, in-kernel cont reassembly is disabled + * and each fragment is stored as a separate log entry with proper + * continuation flag so that every emitted message has full metadata. This + * doesn't change the result for regular consoles or /proc/kmsg. For + * /dev/kmsg, as long as the reader concatenates messages according to + * consecutive continuation flags, the end result should be the same too. + */ +static int nr_ext_console_drivers; + +/* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ @@ -195,7 +207,7 @@ static int console_may_schedule; * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: - * "level,sequnum,timestamp;<message text>\n" + * "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n" * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible @@ -477,18 +489,18 @@ static int syslog_action_restricted(int type) type != SYSLOG_ACTION_SIZE_BUFFER; } -int check_syslog_permissions(int type, bool from_file) +int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ - if (from_file && type != SYSLOG_ACTION_OPEN) - return 0; + if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) + goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) - return 0; + goto ok; /* * For historical reasons, accept CAP_SYS_ADMIN too, with * a warning. @@ -498,13 +510,94 @@ int check_syslog_permissions(int type, bool from_file) "CAP_SYS_ADMIN but no CAP_SYSLOG " "(deprecated).\n", current->comm, task_pid_nr(current)); - return 0; + goto ok; } return -EPERM; } +ok: return security_syslog(type); } +static void append_char(char **pp, char *e, char c) +{ + if (*pp < e) + *(*pp)++ = c; +} + +static ssize_t msg_print_ext_header(char *buf, size_t size, + struct printk_log *msg, u64 seq, + enum log_flags prev_flags) +{ + u64 ts_usec = msg->ts_nsec; + char cont = '-'; + + do_div(ts_usec, 1000); + + /* + * If we couldn't merge continuation line fragments during the print, + * export the stored flags to allow an optional external merge of the + * records. Merging the records isn't always neccessarily correct, like + * when we hit a race during printing. In most cases though, it produces + * better readable output. 'c' in the record flags mark the first + * fragment of a line, '+' the following. + */ + if (msg->flags & LOG_CONT && !(prev_flags & LOG_CONT)) + cont = 'c'; + else if ((msg->flags & LOG_CONT) || + ((prev_flags & LOG_CONT) && !(msg->flags & LOG_PREFIX))) + cont = '+'; + + return scnprintf(buf, size, "%u,%llu,%llu,%c;", + (msg->facility << 3) | msg->level, seq, ts_usec, cont); +} + +static ssize_t msg_print_ext_body(char *buf, size_t size, + char *dict, size_t dict_len, + char *text, size_t text_len) +{ + char *p = buf, *e = buf + size; + size_t i; + + /* escape non-printable characters */ + for (i = 0; i < text_len; i++) { + unsigned char c = text[i]; + + if (c < ' ' || c >= 127 || c == '\\') + p += scnprintf(p, e - p, "\\x%02x", c); + else + append_char(&p, e, c); + } + append_char(&p, e, '\n'); + + if (dict_len) { + bool line = true; + + for (i = 0; i < dict_len; i++) { + unsigned char c = dict[i]; + + if (line) { + append_char(&p, e, ' '); + line = false; + } + + if (c == '\0') { + append_char(&p, e, '\n'); + line = true; + continue; + } + + if (c < ' ' || c >= 127 || c == '\\') { + p += scnprintf(p, e - p, "\\x%02x", c); + continue; + } + + append_char(&p, e, c); + } + append_char(&p, e, '\n'); + } + + return p - buf; +} /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { @@ -512,7 +605,7 @@ struct devkmsg_user { u32 idx; enum log_flags prev; struct mutex lock; - char buf[8192]; + char buf[CONSOLE_EXT_LOG_MAX]; }; static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) @@ -570,9 +663,6 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, { struct devkmsg_user *user = file->private_data; struct printk_log *msg; - u64 ts_usec; - size_t i; - char cont = '-'; size_t len; ssize_t ret; @@ -608,66 +698,13 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, } msg = log_from_idx(user->idx); - ts_usec = msg->ts_nsec; - do_div(ts_usec, 1000); + len = msg_print_ext_header(user->buf, sizeof(user->buf), + msg, user->seq, user->prev); + len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len, + log_dict(msg), msg->dict_len, + log_text(msg), msg->text_len); - /* - * If we couldn't merge continuation line fragments during the print, - * export the stored flags to allow an optional external merge of the - * records. Merging the records isn't always neccessarily correct, like - * when we hit a race during printing. In most cases though, it produces - * better readable output. 'c' in the record flags mark the first - * fragment of a line, '+' the following. - */ - if (msg->flags & LOG_CONT && !(user->prev & LOG_CONT)) - cont = 'c'; - else if ((msg->flags & LOG_CONT) || - ((user->prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))) - cont = '+'; - - len = sprintf(user->buf, "%u,%llu,%llu,%c;", - (msg->facility << 3) | msg->level, - user->seq, ts_usec, cont); user->prev = msg->flags; - - /* escape non-printable characters */ - for (i = 0; i < msg->text_len; i++) { - unsigned char c = log_text(msg)[i]; - - if (c < ' ' || c >= 127 || c == '\\') - len += sprintf(user->buf + len, "\\x%02x", c); - else - user->buf[len++] = c; - } - user->buf[len++] = '\n'; - - if (msg->dict_len) { - bool line = true; - - for (i = 0; i < msg->dict_len; i++) { - unsigned char c = log_dict(msg)[i]; - - if (line) { - user->buf[len++] = ' '; - line = false; - } - - if (c == '\0') { - user->buf[len++] = '\n'; - line = true; - continue; - } - - if (c < ' ' || c >= 127 || c == '\\') { - len += sprintf(user->buf + len, "\\x%02x", c); - continue; - } - - user->buf[len++] = c; - } - user->buf[len++] = '\n'; - } - user->idx = log_next(user->idx); user->seq++; raw_spin_unlock_irq(&logbuf_lock); @@ -1253,20 +1290,16 @@ static int syslog_print_all(char __user *buf, int size, bool clear) return len; } -int do_syslog(int type, char __user *buf, int len, bool from_file) +int do_syslog(int type, char __user *buf, int len, int source) { bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; - error = check_syslog_permissions(type, from_file); + error = check_syslog_permissions(type, source); if (error) goto out; - error = security_syslog(type); - if (error) - return error; - switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; @@ -1346,7 +1379,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) syslog_prev = 0; syslog_partial = 0; } - if (from_file) { + if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of @@ -1393,7 +1426,9 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) * log_buf[start] to log_buf[end - 1]. * The console_lock must be held. */ -static void call_console_drivers(int level, const char *text, size_t len) +static void call_console_drivers(int level, + const char *ext_text, size_t ext_len, + const char *text, size_t len) { struct console *con; @@ -1414,7 +1449,10 @@ static void call_console_drivers(int level, const char *text, size_t len) if (!cpu_online(smp_processor_id()) && !(con->flags & CON_ANYTIME)) continue; - con->write(con, text, len); + if (con->flags & CON_EXTENDED) + con->write(con, ext_text, ext_len); + else + con->write(con, text, len); } } @@ -1557,8 +1595,12 @@ static bool cont_add(int facility, int level, const char *text, size_t len) if (cont.len && cont.flushed) return false; - if (cont.len + len > sizeof(cont.buf)) { - /* the line gets too long, split it up in separate records */ + /* + * If ext consoles are present, flush and skip in-kernel + * continuation. See nr_ext_console_drivers definition. Also, if + * the line gets too long, split it up in separate records. + */ + if (nr_ext_console_drivers || cont.len + len > sizeof(cont.buf)) { cont_flush(LOG_CONT); return false; } @@ -1893,9 +1935,19 @@ static struct cont { u8 level; bool flushed:1; } cont; +static char *log_text(const struct printk_log *msg) { return NULL; } +static char *log_dict(const struct printk_log *msg) { return NULL; } static struct printk_log *log_from_idx(u32 idx) { return NULL; } static u32 log_next(u32 idx) { return 0; } -static void call_console_drivers(int level, const char *text, size_t len) {} +static ssize_t msg_print_ext_header(char *buf, size_t size, + struct printk_log *msg, u64 seq, + enum log_flags prev_flags) { return 0; } +static ssize_t msg_print_ext_body(char *buf, size_t size, + char *dict, size_t dict_len, + char *text, size_t text_len) { return 0; } +static void call_console_drivers(int level, + const char *ext_text, size_t ext_len, + const char *text, size_t len) {} static size_t msg_print_text(const struct printk_log *msg, enum log_flags prev, bool syslog, char *buf, size_t size) { return 0; } static size_t cont_print_text(char *text, size_t size) { return 0; } @@ -2148,7 +2200,7 @@ static void console_cont_flush(char *text, size_t size) len = cont_print_text(text, size); raw_spin_unlock(&logbuf_lock); stop_critical_timings(); - call_console_drivers(cont.level, text, len); + call_console_drivers(cont.level, NULL, 0, text, len); start_critical_timings(); local_irq_restore(flags); return; @@ -2172,6 +2224,7 @@ out: */ void console_unlock(void) { + static char ext_text[CONSOLE_EXT_LOG_MAX]; static char text[LOG_LINE_MAX + PREFIX_MAX]; static u64 seen_seq; unsigned long flags; @@ -2190,6 +2243,7 @@ void console_unlock(void) again: for (;;) { struct printk_log *msg; + size_t ext_len = 0; size_t len; int level; @@ -2235,13 +2289,22 @@ skip: level = msg->level; len += msg_print_text(msg, console_prev, false, text + len, sizeof(text) - len); + if (nr_ext_console_drivers) { + ext_len = msg_print_ext_header(ext_text, + sizeof(ext_text), + msg, console_seq, console_prev); + ext_len += msg_print_ext_body(ext_text + ext_len, + sizeof(ext_text) - ext_len, + log_dict(msg), msg->dict_len, + log_text(msg), msg->text_len); + } console_idx = log_next(console_idx); console_seq++; console_prev = msg->flags; raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ - call_console_drivers(level, text, len); + call_console_drivers(level, ext_text, ext_len, text, len); start_critical_timings(); local_irq_restore(flags); } @@ -2497,6 +2560,11 @@ void register_console(struct console *newcon) newcon->next = console_drivers->next; console_drivers->next = newcon; } + + if (newcon->flags & CON_EXTENDED) + if (!nr_ext_console_drivers++) + pr_info("printk: continuation disabled due to ext consoles, expect more fragments in /dev/kmsg\n"); + if (newcon->flags & CON_PRINTBUFFER) { /* * console_unlock(); will print out the buffered messages @@ -2569,6 +2637,9 @@ int unregister_console(struct console *console) } } + if (!res && (console->flags & CON_EXTENDED)) + nr_ext_console_drivers--; + /* * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. diff --git a/kernel/sys.c b/kernel/sys.c index 8571296..259fda2 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1722,7 +1722,6 @@ exit_err: goto exit; } -#ifdef CONFIG_CHECKPOINT_RESTORE /* * WARNING: we don't require any capability here so be very careful * in what is allowed for modification from userspace. @@ -1818,6 +1817,7 @@ out: return error; } +#ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) { struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; @@ -1902,10 +1902,41 @@ out: } #endif /* CONFIG_CHECKPOINT_RESTORE */ +static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, + unsigned long len) +{ + /* + * This doesn't move the auxiliary vector itself since it's pinned to + * mm_struct, but it permits filling the vector with new values. It's + * up to the caller to provide sane values here, otherwise userspace + * tools which use this vector might be unhappy. + */ + unsigned long user_auxv[AT_VECTOR_SIZE]; + + if (len > sizeof(user_auxv)) + return -EINVAL; + + if (copy_from_user(user_auxv, (const void __user *)addr, len)) + return -EFAULT; + + /* Make sure the last entry is always AT_NULL */ + user_auxv[AT_VECTOR_SIZE - 2] = 0; + user_auxv[AT_VECTOR_SIZE - 1] = 0; + + BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); + + task_lock(current); + memcpy(mm->saved_auxv, user_auxv, len); + task_unlock(current); + + return 0; +} + static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; + struct prctl_mm_map prctl_map; struct vm_area_struct *vma; int error; @@ -1925,6 +1956,9 @@ static int prctl_set_mm(int opt, unsigned long addr, if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); + if (opt == PR_SET_MM_AUXV) + return prctl_set_auxv(mm, addr, arg4); + if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; @@ -1933,42 +1967,64 @@ static int prctl_set_mm(int opt, unsigned long addr, down_read(&mm->mmap_sem); vma = find_vma(mm, addr); + prctl_map.start_code = mm->start_code; + prctl_map.end_code = mm->end_code; + prctl_map.start_data = mm->start_data; + prctl_map.end_data = mm->end_data; + prctl_map.start_brk = mm->start_brk; + prctl_map.brk = mm->brk; + prctl_map.start_stack = mm->start_stack; + prctl_map.arg_start = mm->arg_start; + prctl_map.arg_end = mm->arg_end; + prctl_map.env_start = mm->env_start; + prctl_map.env_end = mm->env_end; + prctl_map.auxv = NULL; + prctl_map.auxv_size = 0; + prctl_map.exe_fd = -1; + switch (opt) { case PR_SET_MM_START_CODE: - mm->start_code = addr; + prctl_map.start_code = addr; break; case PR_SET_MM_END_CODE: - mm->end_code = addr; + prctl_map.end_code = addr; break; case PR_SET_MM_START_DATA: - mm->start_data = addr; + prctl_map.start_data = addr; break; case PR_SET_MM_END_DATA: - mm->end_data = addr; + prctl_map.end_data = addr; + break; + case PR_SET_MM_START_STACK: + prctl_map.start_stack = addr; break; - case PR_SET_MM_START_BRK: - if (addr <= mm->end_data) - goto out; - - if (check_data_rlimit(rlimit(RLIMIT_DATA), mm->brk, addr, - mm->end_data, mm->start_data)) - goto out; - - mm->start_brk = addr; + prctl_map.start_brk = addr; break; - case PR_SET_MM_BRK: - if (addr <= mm->end_data) - goto out; - - if (check_data_rlimit(rlimit(RLIMIT_DATA), addr, mm->start_brk, - mm->end_data, mm->start_data)) - goto out; - - mm->brk = addr; + prctl_map.brk = addr; break; + case PR_SET_MM_ARG_START: + prctl_map.arg_start = addr; + break; + case PR_SET_MM_ARG_END: + prctl_map.arg_end = addr; + break; + case PR_SET_MM_ENV_START: + prctl_map.env_start = addr; + break; + case PR_SET_MM_ENV_END: + prctl_map.env_end = addr; + break; + default: + goto out; + } + + error = validate_prctl_map(&prctl_map); + if (error) + goto out; + switch (opt) { /* * If command line arguments and environment * are placed somewhere else on stack, we can @@ -1985,52 +2041,20 @@ static int prctl_set_mm(int opt, unsigned long addr, error = -EFAULT; goto out; } - if (opt == PR_SET_MM_START_STACK) - mm->start_stack = addr; - else if (opt == PR_SET_MM_ARG_START) - mm->arg_start = addr; - else if (opt == PR_SET_MM_ARG_END) - mm->arg_end = addr; - else if (opt == PR_SET_MM_ENV_START) - mm->env_start = addr; - else if (opt == PR_SET_MM_ENV_END) - mm->env_end = addr; - break; - - /* - * This doesn't move auxiliary vector itself - * since it's pinned to mm_struct, but allow - * to fill vector with new values. It's up - * to a caller to provide sane values here - * otherwise user space tools which use this - * vector might be unhappy. - */ - case PR_SET_MM_AUXV: { - unsigned long user_auxv[AT_VECTOR_SIZE]; - - if (arg4 > sizeof(user_auxv)) - goto out; - up_read(&mm->mmap_sem); - - if (copy_from_user(user_auxv, (const void __user *)addr, arg4)) - return -EFAULT; - - /* Make sure the last entry is always AT_NULL */ - user_auxv[AT_VECTOR_SIZE - 2] = 0; - user_auxv[AT_VECTOR_SIZE - 1] = 0; - - BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); - - task_lock(current); - memcpy(mm->saved_auxv, user_auxv, arg4); - task_unlock(current); - - return 0; - } - default: - goto out; } + mm->start_code = prctl_map.start_code; + mm->end_code = prctl_map.end_code; + mm->start_data = prctl_map.start_data; + mm->end_data = prctl_map.end_data; + mm->start_brk = prctl_map.start_brk; + mm->brk = prctl_map.brk; + mm->start_stack = prctl_map.start_stack; + mm->arg_start = prctl_map.arg_start; + mm->arg_end = prctl_map.arg_end; + mm->env_start = prctl_map.env_start; + mm->env_end = prctl_map.env_end; + error = 0; out: up_read(&mm->mmap_sem); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 483cecf..4eeae46 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -439,7 +439,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, { struct blk_trace *old_bt, *bt = NULL; struct dentry *dir = NULL; - int ret, i; + int ret; if (!buts->buf_size || !buts->buf_nr) return -EINVAL; @@ -451,9 +451,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, * some device names have larger paths - convert the slashes * to underscores for this to work as expected */ - for (i = 0; i < strlen(buts->name); i++) - if (buts->name[i] == '/') - buts->name[i] = '_'; + strreplace(buts->name, '/', '_'); bt = kzalloc(sizeof(*bt), GFP_KERNEL); if (!bt) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 7f2e97c..9d4a78f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2082,7 +2082,7 @@ struct function_filter_data { static char ** ftrace_function_filter_re(char *buf, int len, int *count) { - char *str, *sep, **re; + char *str, **re; str = kstrndup(buf, len, GFP_KERNEL); if (!str) @@ -2092,8 +2092,7 @@ ftrace_function_filter_re(char *buf, int len, int *count) * The argv_split function takes white space * as a separator, so convert ',' into spaces. */ - while ((sep = strchr(str, ','))) - *sep = ' '; + strreplace(str, ',', ' '); re = argv_split(GFP_KERNEL, str, count); kfree(str); diff --git a/lib/bitmap.c b/lib/bitmap.c index 64c0926..a578a01 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -462,19 +462,20 @@ EXPORT_SYMBOL(bitmap_parse_user); * Output format is a comma-separated list of decimal numbers and * ranges if list is specified or hex digits grouped into comma-separated * sets of 8 digits/set. Returns the number of characters written to buf. + * + * It is assumed that @buf is a pointer into a PAGE_SIZE area and that + * sufficient storage remains at @buf to accommodate the + * bitmap_print_to_pagebuf() output. */ int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits) { - ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf - 2; + ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf; int n = 0; - if (len > 1) { - n = list ? scnprintf(buf, len, "%*pbl", nmaskbits, maskp) : - scnprintf(buf, len, "%*pb", nmaskbits, maskp); - buf[n++] = '\n'; - buf[n] = '\0'; - } + if (len > 1) + n = list ? scnprintf(buf, len, "%*pbl\n", nmaskbits, maskp) : + scnprintf(buf, len, "%*pb\n", nmaskbits, maskp); return n; } EXPORT_SYMBOL(bitmap_print_to_pagebuf); @@ -506,12 +507,12 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, unsigned a, b; int c, old_c, totaldigits; const char __user __force *ubuf = (const char __user __force *)buf; - int exp_digit, in_range; + int at_start, in_range; totaldigits = c = 0; bitmap_zero(maskp, nmaskbits); do { - exp_digit = 1; + at_start = 1; in_range = 0; a = b = 0; @@ -540,11 +541,10 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, break; if (c == '-') { - if (exp_digit || in_range) + if (at_start || in_range) return -EINVAL; b = 0; in_range = 1; - exp_digit = 1; continue; } @@ -554,16 +554,18 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, b = b * 10 + (c - '0'); if (!in_range) a = b; - exp_digit = 0; + at_start = 0; totaldigits++; } if (!(a <= b)) return -EINVAL; if (b >= nmaskbits) return -ERANGE; - while (a <= b) { - set_bit(a, maskp); - a++; + if (!at_start) { + while (a <= b) { + set_bit(a, maskp); + a++; + } } } while (buflen && c == ','); return 0; diff --git a/lib/kobject.c b/lib/kobject.c index 3b841b9..75ee638 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -257,23 +257,20 @@ static int kobject_add_internal(struct kobject *kobj) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { - const char *old_name = kobj->name; char *s; if (kobj->name && !fmt) return 0; - kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs); - if (!kobj->name) { - kobj->name = old_name; + s = kvasprintf(GFP_KERNEL, fmt, vargs); + if (!s) return -ENOMEM; - } /* ewww... some of these buggers have '/' in the name ... */ - while ((s = strchr(kobj->name, '/'))) - s[0] = '!'; + strreplace(s, '/', '!'); + kfree(kobj->name); + kobj->name = s; - kfree(old_name); return 0; } diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 061550d..f9ebe1c 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -65,7 +65,8 @@ static struct kmem_cache *radix_tree_node_cachep; */ struct radix_tree_preload { int nr; - struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_SIZE]; + /* nodes->private_data points to next preallocated node */ + struct radix_tree_node *nodes; }; static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; @@ -197,8 +198,9 @@ radix_tree_node_alloc(struct radix_tree_root *root) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { - ret = rtp->nodes[rtp->nr - 1]; - rtp->nodes[rtp->nr - 1] = NULL; + ret = rtp->nodes; + rtp->nodes = ret->private_data; + ret->private_data = NULL; rtp->nr--; } /* @@ -257,17 +259,20 @@ static int __radix_tree_preload(gfp_t gfp_mask) preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); - while (rtp->nr < ARRAY_SIZE(rtp->nodes)) { + while (rtp->nr < RADIX_TREE_PRELOAD_SIZE) { preempt_enable(); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); - if (rtp->nr < ARRAY_SIZE(rtp->nodes)) - rtp->nodes[rtp->nr++] = node; - else + if (rtp->nr < RADIX_TREE_PRELOAD_SIZE) { + node->private_data = rtp->nodes; + rtp->nodes = node; + rtp->nr++; + } else { kmem_cache_free(radix_tree_node_cachep, node); + } } ret = 0; out: @@ -1463,15 +1468,16 @@ static int radix_tree_callback(struct notifier_block *nfb, { int cpu = (long)hcpu; struct radix_tree_preload *rtp; + struct radix_tree_node *node; /* Free per-cpu pool of perloaded nodes */ if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { - kmem_cache_free(radix_tree_node_cachep, - rtp->nodes[rtp->nr-1]); - rtp->nodes[rtp->nr-1] = NULL; - rtp->nr--; + node = rtp->nodes; + rtp->nodes = node->private_data; + kmem_cache_free(radix_tree_node_cachep, node); + rtp->nr--; } } return NOTIFY_OK; @@ -8,6 +8,12 @@ #include <linux/export.h> #include <linux/sort.h> +static int alignment_ok(const void *base, int align) +{ + return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + ((unsigned long)base & (align - 1)) == 0; +} + static void u32_swap(void *a, void *b, int size) { u32 t = *(u32 *)a; @@ -15,6 +21,13 @@ static void u32_swap(void *a, void *b, int size) *(u32 *)b = t; } +static void u64_swap(void *a, void *b, int size) +{ + u64 t = *(u64 *)a; + *(u64 *)a = *(u64 *)b; + *(u64 *)b = t; +} + static void generic_swap(void *a, void *b, int size) { char t; @@ -50,8 +63,14 @@ void sort(void *base, size_t num, size_t size, /* pre-scale counters for performance */ int i = (num/2 - 1) * size, n = num * size, c, r; - if (!swap_func) - swap_func = (size == 4 ? u32_swap : generic_swap); + if (!swap_func) { + if (size == 4 && alignment_ok(base, 4)) + swap_func = u32_swap; + else if (size == 8 && alignment_ok(base, 8)) + swap_func = u64_swap; + else + swap_func = generic_swap; + } /* heapify */ for ( ; i >= 0; i -= size) { diff --git a/lib/string.c b/lib/string.c index bb3d4b6..13d1e84 100644 --- a/lib/string.c +++ b/lib/string.c @@ -849,3 +849,20 @@ void *memchr_inv(const void *start, int c, size_t bytes) return check_bytes8(start, value, bytes % 8); } EXPORT_SYMBOL(memchr_inv); + +/** + * strreplace - Replace all occurrences of character in string. + * @s: The string to operate on. + * @old: The character being replaced. + * @new: The character @old is replaced with. + * + * Returns pointer to the nul byte at the end of @s. + */ +char *strreplace(char *s, char old, char new) +{ + for (; *s; ++s) + if (*s == old) + *s = new; + return s; +} +EXPORT_SYMBOL(strreplace); diff --git a/lib/test-hexdump.c b/lib/test-hexdump.c index c227cc4..5241df3 100644 --- a/lib/test-hexdump.c +++ b/lib/test-hexdump.c @@ -25,19 +25,19 @@ static const char * const test_data_1_le[] __initconst = { "4c", "d1", "19", "99", "43", "b1", "af", "0c", }; -static const char *test_data_2_le[] __initdata = { +static const char * const test_data_2_le[] __initconst = { "32be", "7bdb", "180a", "b293", "ba70", "24c4", "837d", "9b34", "9ca6", "ad31", "0f9c", "e9ac", "d14c", "9919", "b143", "0caf", }; -static const char *test_data_4_le[] __initdata = { +static const char * const test_data_4_le[] __initconst = { "7bdb32be", "b293180a", "24c4ba70", "9b34837d", "ad319ca6", "e9ac0f9c", "9919d14c", "0cafb143", }; -static const char *test_data_8_le[] __initdata = { +static const char * const test_data_8_le[] __initconst = { "b293180a7bdb32be", "9b34837d24c4ba70", "e9ac0f9cad319ca6", "0cafb1439919d14c", }; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 75c0eef..a8c3087 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -975,7 +975,6 @@ static void update_and_free_page(struct hstate *h, struct page *page) destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); } else { - arch_release_hugepage(page); __free_pages(page, huge_page_order(h)); } } @@ -1160,10 +1159,6 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); if (page) { - if (arch_prepare_hugepage(page)) { - __free_pages(page, huge_page_order(h)); - return NULL; - } prep_new_huge_page(h, page, nid); } @@ -1315,11 +1310,6 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); - if (page && arch_prepare_hugepage(page)) { - __free_pages(page, huge_page_order(h)); - page = NULL; - } - spin_lock(&hugetlb_lock); if (page) { INIT_LIST_HEAD(&page->lru); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 4986b0a..c242adf 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -7,7 +7,6 @@ #define KASAN_SHADOW_MASK (KASAN_SHADOW_SCALE_SIZE - 1) #define KASAN_FREE_PAGE 0xFF /* page was freed */ -#define KASAN_FREE_PAGE 0xFF /* page was freed */ #define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ #define KASAN_KMALLOC_REDZONE 0xFC /* redzone inside slub object */ #define KASAN_KMALLOC_FREE 0xFB /* object was freed (kmem_cache_free/kfree) */ @@ -97,6 +97,10 @@ struct zbud_pool { struct list_head lru; u64 pages_nr; struct zbud_ops *ops; +#ifdef CONFIG_ZPOOL + struct zpool *zpool; + struct zpool_ops *zpool_ops; +#endif }; /* @@ -123,7 +127,10 @@ struct zbud_header { static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) { - return zpool_evict(pool, handle); + if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) + return pool->zpool_ops->evict(pool->zpool, handle); + else + return -ENOENT; } static struct zbud_ops zbud_zpool_ops = { @@ -131,9 +138,17 @@ static struct zbud_ops zbud_zpool_ops = { }; static void *zbud_zpool_create(char *name, gfp_t gfp, - struct zpool_ops *zpool_ops) + struct zpool_ops *zpool_ops, + struct zpool *zpool) { - return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + struct zbud_pool *pool; + + pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + return pool; } static void zbud_zpool_destroy(void *pool) @@ -292,7 +307,7 @@ struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops) struct zbud_pool *pool; int i; - pool = kmalloc(sizeof(struct zbud_pool), gfp); + pool = kzalloc(sizeof(struct zbud_pool), gfp); if (!pool) return NULL; spin_lock_init(&pool->lock); @@ -73,33 +73,6 @@ int zpool_unregister_driver(struct zpool_driver *driver) } EXPORT_SYMBOL(zpool_unregister_driver); -/** - * zpool_evict() - evict callback from a zpool implementation. - * @pool: pool to evict from. - * @handle: handle to evict. - * - * This can be used by zpool implementations to call the - * user's evict zpool_ops struct evict callback. - */ -int zpool_evict(void *pool, unsigned long handle) -{ - struct zpool *zpool; - - spin_lock(&pools_lock); - list_for_each_entry(zpool, &pools_head, list) { - if (zpool->pool == pool) { - spin_unlock(&pools_lock); - if (!zpool->ops || !zpool->ops->evict) - return -EINVAL; - return zpool->ops->evict(zpool, handle); - } - } - spin_unlock(&pools_lock); - - return -ENOENT; -} -EXPORT_SYMBOL(zpool_evict); - static struct zpool_driver *zpool_get_driver(char *type) { struct zpool_driver *driver; @@ -147,7 +120,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, struct zpool_driver *driver; struct zpool *zpool; - pr_info("creating pool type %s\n", type); + pr_debug("creating pool type %s\n", type); driver = zpool_get_driver(type); @@ -170,7 +143,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, zpool->type = driver->type; zpool->driver = driver; - zpool->pool = driver->create(name, gfp, ops); + zpool->pool = driver->create(name, gfp, ops, zpool); zpool->ops = ops; if (!zpool->pool) { @@ -180,7 +153,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, return NULL; } - pr_info("created %s pool\n", type); + pr_debug("created pool type %s\n", type); spin_lock(&pools_lock); list_add(&zpool->list, &pools_head); @@ -202,7 +175,7 @@ struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, */ void zpool_destroy_pool(struct zpool *zpool) { - pr_info("destroying pool type %s\n", zpool->type); + pr_debug("destroying pool type %s\n", zpool->type); spin_lock(&pools_lock); list_del(&zpool->list); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index a8b5e74..0a7f81a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -45,10 +45,6 @@ * */ -#ifdef CONFIG_ZSMALLOC_DEBUG -#define DEBUG -#endif - #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -313,7 +309,8 @@ static void record_obj(unsigned long handle, unsigned long obj) #ifdef CONFIG_ZPOOL -static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops) +static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops, + struct zpool *zpool) { return zs_create_pool(name, gfp); } @@ -75,9 +75,10 @@ static u64 zswap_duplicate_entry; /********************************* * tunables **********************************/ -/* Enable/disable zswap (disabled by default, fixed at boot for now) */ -static bool zswap_enabled __read_mostly; -module_param_named(enabled, zswap_enabled, bool, 0444); + +/* Enable/disable zswap (disabled by default) */ +static bool zswap_enabled; +module_param_named(enabled, zswap_enabled, bool, 0644); /* Compressor to be used by zswap (fixed at boot for now) */ #define ZSWAP_COMPRESSOR_DEFAULT "lzo" @@ -648,7 +649,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, u8 *src, *dst; struct zswap_header *zhdr; - if (!tree) { + if (!zswap_enabled || !tree) { ret = -ENODEV; goto reject; } @@ -901,9 +902,6 @@ static int __init init_zswap(void) { gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN; - if (!zswap_enabled) - return 0; - pr_info("loading zswap\n"); zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp, diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index c5ec977..90e1edc 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -9,6 +9,7 @@ use strict; use POSIX; use File::Basename; use Cwd 'abs_path'; +use Term::ANSIColor qw(:constants); my $P = $0; my $D = dirname(abs_path($P)); @@ -24,6 +25,7 @@ my $chk_patch = 1; my $tst_only; my $emacs = 0; my $terse = 0; +my $showfile = 0; my $file = 0; my $check = 0; my $check_orig = 0; @@ -48,7 +50,8 @@ my $minimum_perl_version = 5.10.0; my $min_conf_desc_length = 4; my $spelling_file = "$D/spelling.txt"; my $codespell = 0; -my $codespellfile = "/usr/local/share/codespell/dictionary.txt"; +my $codespellfile = "/usr/share/codespell/dictionary.txt"; +my $color = 1; sub help { my ($exitcode) = @_; @@ -64,6 +67,7 @@ Options: --patch treat FILE as patchfile (default) --emacs emacs compile window format --terse one line per report + --showfile emit diffed file position, not input file position -f, --file treat FILE as regular source file --subjective, --strict enable more subjective tests --types TYPE(,TYPE2...) show only these comma separated message types @@ -91,8 +95,9 @@ Options: --ignore-perl-version override checking of perl version. expect runtime errors. --codespell Use the codespell dictionary for spelling/typos - (default:/usr/local/share/codespell/dictionary.txt) + (default:/usr/share/codespell/dictionary.txt) --codespellfile Use this codespell dictionary + --color Use colors when output is STDOUT (default: on) -h, --help, --version display this help and exit When FILE is - read standard input. @@ -134,6 +139,7 @@ GetOptions( 'patch!' => \$chk_patch, 'emacs!' => \$emacs, 'terse!' => \$terse, + 'showfile!' => \$showfile, 'f|file!' => \$file, 'subjective!' => \$check, 'strict!' => \$check, @@ -153,6 +159,7 @@ GetOptions( 'test-only=s' => \$tst_only, 'codespell!' => \$codespell, 'codespellfile=s' => \$codespellfile, + 'color!' => \$color, 'h|help' => \$help, 'version' => \$help ) or help(1); @@ -196,12 +203,12 @@ sub hash_save_array_words { sub hash_show_words { my ($hashRef, $prefix) = @_; - if ($quiet == 0 && keys %$hashRef) { - print "NOTE: $prefix message types:"; + if (keys %$hashRef) { + print "\nNOTE: $prefix message types:"; foreach my $word (sort keys %$hashRef) { print " $word"; } - print "\n\n"; + print "\n"; } } @@ -347,15 +354,20 @@ our $UTF8 = qr{ | $NON_ASCII_UTF8 }x; +our $typeC99Typedefs = qr{(?:__)?(?:[us]_?)?int_?(?:8|16|32|64)_t}; our $typeOtherOSTypedefs = qr{(?x: u_(?:char|short|int|long) | # bsd u(?:nchar|short|int|long) # sysv )}; - -our $typeTypedefs = qr{(?x: +our $typeKernelTypedefs = qr{(?x: (?:__)?(?:u|s|be|le)(?:8|16|32|64)| atomic_t )}; +our $typeTypedefs = qr{(?x: + $typeC99Typedefs\b| + $typeOtherOSTypedefs\b| + $typeKernelTypedefs\b +)}; our $logFunctions = qr{(?x: printk(?:_ratelimited|_once|)| @@ -418,6 +430,7 @@ our @typeList = ( qr{${Ident}_handler_fn}, @typeListMisordered, ); +our @typeListFile = (); our @typeListWithAttr = ( @typeList, qr{struct\s+$InitAttribute\s+$Ident}, @@ -427,6 +440,7 @@ our @typeListWithAttr = ( our @modifierList = ( qr{fastcall}, ); +our @modifierListFile = (); our @mode_permission_funcs = ( ["module_param", 3], @@ -510,13 +524,12 @@ if ($codespell) { $misspellings = join("|", sort keys %spelling_fix) if keys %spelling_fix; sub build_types { - my $mods = "(?x: \n" . join("|\n ", @modifierList) . "\n)"; - my $all = "(?x: \n" . join("|\n ", @typeList) . "\n)"; + my $mods = "(?x: \n" . join("|\n ", (@modifierList, @modifierListFile)) . "\n)"; + my $all = "(?x: \n" . join("|\n ", (@typeList, @typeListFile)) . "\n)"; my $Misordered = "(?x: \n" . join("|\n ", @typeListMisordered) . "\n)"; my $allWithAttr = "(?x: \n" . join("|\n ", @typeListWithAttr) . "\n)"; $Modifier = qr{(?:$Attribute|$Sparse|$mods)}; $BasicType = qr{ - (?:$typeOtherOSTypedefs\b)| (?:$typeTypedefs\b)| (?:${all}\b) }x; @@ -524,7 +537,6 @@ sub build_types { (?:$Modifier\s+|const\s+)* (?: (?:typeof|__typeof__)\s*\([^\)]*\)| - (?:$typeOtherOSTypedefs\b)| (?:$typeTypedefs\b)| (?:${all}\b) ) @@ -542,7 +554,6 @@ sub build_types { (?: (?:typeof|__typeof__)\s*\([^\)]*\)| (?:$typeTypedefs\b)| - (?:$typeOtherOSTypedefs\b)| (?:${allWithAttr}\b) ) (?:\s+$Modifier|\s+const)* @@ -737,6 +748,13 @@ for my $filename (@ARGV) { push(@rawlines, $_); } close($FILE); + + if ($#ARGV > 0 && $quiet == 0) { + print '-' x length($vname) . "\n"; + print "$vname\n"; + print '-' x length($vname) . "\n"; + } + if (!process($filename)) { $exit = 1; } @@ -746,6 +764,29 @@ for my $filename (@ARGV) { @fixed_inserted = (); @fixed_deleted = (); $fixlinenr = -1; + @modifierListFile = (); + @typeListFile = (); + build_types(); +} + +if (!$quiet) { + hash_show_words(\%use_type, "Used"); + hash_show_words(\%ignore_type, "Ignored"); + + if ($^V lt 5.10.0) { + print << "EOM" + +NOTE: perl $^V is not modern enough to detect all possible issues. + An upgrade to at least perl v5.10.0 is suggested. +EOM + } + if ($exit) { + print << "EOM" + +NOTE: If any of the errors are false positives, please report + them to the maintainer, see CHECKPATCH in MAINTAINERS. +EOM + } } exit($exit); @@ -1001,7 +1042,7 @@ sub sanitise_line { sub get_quoted_string { my ($line, $rawline) = @_; - return "" if ($line !~ m/(\"[X\t]+\")/g); + return "" if ($line !~ m/($String)/g); return substr($rawline, $-[0], $+[0] - $-[0]); } @@ -1610,13 +1651,13 @@ sub possible { for my $modifier (split(' ', $possible)) { if ($modifier !~ $notPermitted) { warn "MODIFIER: $modifier ($possible) ($line)\n" if ($dbg_possible); - push(@modifierList, $modifier); + push(@modifierListFile, $modifier); } } } else { warn "POSSIBLE: $possible ($line)\n" if ($dbg_possible); - push(@typeList, $possible); + push(@typeListFile, $possible); } build_types(); } else { @@ -1641,15 +1682,32 @@ sub report { (defined $tst_only && $msg !~ /\Q$tst_only\E/)) { return 0; } - my $line; + my $output = ''; + if (-t STDOUT && $color) { + if ($level eq 'ERROR') { + $output .= RED; + } elsif ($level eq 'WARNING') { + $output .= YELLOW; + } else { + $output .= GREEN; + } + } + $output .= $prefix . $level . ':'; if ($show_types) { - $line = "$prefix$level:$type: $msg\n"; - } else { - $line = "$prefix$level: $msg\n"; + $output .= BLUE if (-t STDOUT && $color); + $output .= "$type:"; } - $line = (split('\n', $line))[0] . "\n" if ($terse); + $output .= RESET if (-t STDOUT && $color); + $output .= ' ' . $msg . "\n"; - push(our @report, $line); + if ($showfile) { + my @lines = split("\n", $output, -1); + splice(@lines, 1, 1); + $output = join("\n", @lines); + } + $output = (split('\n', $output))[0] . "\n" if ($terse); + + push(our @report, $output); return 1; } @@ -1899,6 +1957,7 @@ sub process { my $in_header_lines = $file ? 0 : 1; my $in_commit_log = 0; #Scanning lines before patch my $commit_log_long_line = 0; + my $commit_log_has_diff = 0; my $reported_maintainer_file = 0; my $non_utf8_charset = 0; @@ -2032,7 +2091,8 @@ sub process { my $rawline = $rawlines[$linenr - 1]; #extract the line range in the file after the patch is applied - if ($line=~/^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { + if (!$in_commit_log && + $line =~ /^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { $is_patch = 1; $first_line = $linenr + 1; $realline=$1-1; @@ -2073,10 +2133,6 @@ sub process { my $hunk_line = ($realcnt != 0); -#make up the handle for any error we report on this line - $prefix = "$filename:$realline: " if ($emacs && $file); - $prefix = "$filename:$linenr: " if ($emacs && !$file); - $here = "#$linenr: " if (!$file); $here = "#$realline: " if ($file); @@ -2106,6 +2162,13 @@ sub process { $found_file = 1; } +#make up the handle for any error we report on this line + if ($showfile) { + $prefix = "$realfile:$realline: " + } elsif ($emacs) { + $prefix = "$filename:$linenr: "; + } + if ($found_file) { if ($realfile =~ m@^(drivers/net/|net/)@) { $check = 1; @@ -2123,6 +2186,17 @@ sub process { $cnt_lines++ if ($realcnt != 0); +# Check if the commit log has what seems like a diff which can confuse patch + if ($in_commit_log && !$commit_log_has_diff && + (($line =~ m@^\s+diff\b.*a/[\w/]+@ && + $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) || + $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ || + $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) { + ERROR("DIFF_IN_COMMIT_MSG", + "Avoid using diff content in the commit message - patch(1) might not work\n" . $herecurr); + $commit_log_has_diff = 1; + } + # Check for incorrect file permissions if ($line =~ /^new (file )?mode.*[7531]\d{0,2}$/) { my $permhere = $here . "FILE: $realfile\n"; @@ -2510,16 +2584,56 @@ sub process { # check we are in a valid source file if not then ignore this hunk next if ($realfile !~ /\.(h|c|s|S|pl|sh|dtsi|dts)$/); -#line length limit - if ($line =~ /^\+/ && $prevrawline !~ /\/\*\*/ && - $rawline !~ /^.\s*\*\s*\@$Ident\s/ && - !($line =~ /^\+\s*$logFunctions\s*\(\s*(?:(KERN_\S+\s*|[^"]*))?$String\s*(?:|,|\)\s*;)\s*$/ || - $line =~ /^\+\s*$String\s*(?:\s*|,|\)\s*;)\s*$/ || - $line =~ /^\+\s*#\s*define\s+\w+\s+$String$/) && - $length > $max_line_length) - { - WARN("LONG_LINE", - "line over $max_line_length characters\n" . $herecurr); +# line length limit (with some exclusions) +# +# There are a few types of lines that may extend beyond $max_line_length: +# logging functions like pr_info that end in a string +# lines with a single string +# #defines that are a single string +# +# There are 3 different line length message types: +# LONG_LINE_COMMENT a comment starts before but extends beyond $max_linelength +# LONG_LINE_STRING a string starts before but extends beyond $max_line_length +# LONG_LINE all other lines longer than $max_line_length +# +# if LONG_LINE is ignored, the other 2 types are also ignored +# + + if ($length > $max_line_length) { + my $msg_type = "LONG_LINE"; + + # Check the allowed long line types first + + # logging functions that end in a string that starts + # before $max_line_length + if ($line =~ /^\+\s*$logFunctions\s*\(\s*(?:(?:KERN_\S+\s*|[^"]*))?($String\s*(?:|,|\)\s*;)\s*)$/ && + length(expand_tabs(substr($line, 1, length($line) - length($1) - 1))) <= $max_line_length) { + $msg_type = ""; + + # lines with only strings (w/ possible termination) + # #defines with only strings + } elsif ($line =~ /^\+\s*$String\s*(?:\s*|,|\)\s*;)\s*$/ || + $line =~ /^\+\s*#\s*define\s+\w+\s+$String$/) { + $msg_type = ""; + + # Otherwise set the alternate message types + + # a comment starts before $max_line_length + } elsif ($line =~ /($;[\s$;]*)$/ && + length(expand_tabs(substr($line, 1, length($line) - length($1) - 1))) <= $max_line_length) { + $msg_type = "LONG_LINE_COMMENT" + + # a quoted string starts before $max_line_length + } elsif ($sline =~ /\s*($String(?:\s*(?:\\|,\s*|\)\s*;\s*))?)$/ && + length(expand_tabs(substr($line, 1, length($line) - length($1) - 1))) <= $max_line_length) { + $msg_type = "LONG_LINE_STRING" + } + + if ($msg_type ne "" && + (show_type("LONG_LINE") || show_type($msg_type))) { + WARN($msg_type, + "line over $max_line_length characters\n" . $herecurr); + } } # check for adding lines without a newline. @@ -3264,7 +3378,6 @@ sub process { $line !~ /\btypedef\s+$Type\s*\(\s*\*?$Ident\s*\)\s*\(/ && $line !~ /\btypedef\s+$Type\s+$Ident\s*\(/ && $line !~ /\b$typeTypedefs\b/ && - $line !~ /\b$typeOtherOSTypedefs\b/ && $line !~ /\b__bitwise(?:__|)\b/) { WARN("NEW_TYPEDEFS", "do not add new typedefs\n" . $herecurr); @@ -4337,8 +4450,8 @@ sub process { } # Flatten any obvious string concatentation. - while ($dstat =~ s/("X*")\s*$Ident/$1/ || - $dstat =~ s/$Ident\s*("X*")/$1/) + while ($dstat =~ s/($String)\s*$Ident/$1/ || + $dstat =~ s/$Ident\s*($String)/$1/) { } @@ -4619,7 +4732,7 @@ sub process { # to grep for the string. Make exceptions when the previous string ends in a # newline (multiple lines in one string constant) or '\t', '\r', ';', or '{' # (common in inline assembly) or is a octal \123 or hexadecimal \xaf value - if ($line =~ /^\+\s*"[X\t]*"/ && + if ($line =~ /^\+\s*$String/ && $prevline =~ /"\s*$/ && $prevrawline !~ /(?:\\(?:[ntr]|[0-7]{1,3}|x[0-9a-fA-F]{1,2})|;\s*|\{\s*)"\s*$/) { if (WARN("SPLIT_STRING", @@ -4665,13 +4778,13 @@ sub process { } # concatenated string without spaces between elements - if ($line =~ /"X+"[A-Z_]+/ || $line =~ /[A-Z_]+"X+"/) { + if ($line =~ /$String[A-Z_]/ || $line =~ /[A-Za-z0-9_]$String/) { CHK("CONCATENATED_STRING", "Concatenated strings should use spaces between elements\n" . $herecurr); } # uncoalesced string fragments - if ($line =~ /"X*"\s*"/) { + if ($line =~ /$String\s*"/) { WARN("STRING_FRAGMENTS", "Consecutive strings are generally better as a single string\n" . $herecurr); } @@ -4898,6 +5011,13 @@ sub process { "memory barrier without comment\n" . $herecurr); } } +# check for waitqueue_active without a comment. + if ($line =~ /\bwaitqueue_active\s*\(/) { + if (!ctx_has_comment($first_line, $linenr)) { + WARN("WAITQUEUE_ACTIVE", + "waitqueue_active without comment\n" . $herecurr); + } + } # check of hardware specific defines if ($line =~ m@^.\s*\#\s*if.*\b(__i386__|__powerpc64__|__sun__|__s390x__)\b@ && $realfile !~ m@include/asm-@) { CHK("ARCH_DEFINES", @@ -4973,6 +5093,24 @@ sub process { "Using weak declarations can have unintended link defects\n" . $herecurr); } +# check for c99 types like uint8_t used outside of uapi/ + if ($realfile !~ m@\binclude/uapi/@ && + $line =~ /\b($Declare)\s*$Ident\s*[=;,\[]/) { + my $type = $1; + if ($type =~ /\b($typeC99Typedefs)\b/) { + $type = $1; + my $kernel_type = 'u'; + $kernel_type = 's' if ($type =~ /^_*[si]/); + $type =~ /(\d+)/; + $kernel_type .= $1; + if (CHK("PREFER_KERNEL_TYPES", + "Prefer kernel type '$kernel_type' over '$type'\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\b$type\b/$kernel_type/; + } + } + } + # check for sizeof(&) if ($line =~ /\bsizeof\s*\(\s*\&/) { WARN("SIZEOF_ADDRESS", @@ -5010,7 +5148,7 @@ sub process { # Check for misused memsets if ($^V && $^V ge 5.10.0 && defined $stat && - $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*$FuncArg\s*\)/s) { + $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*$FuncArg\s*\)/) { my $ms_addr = $2; my $ms_val = $7; @@ -5027,14 +5165,46 @@ sub process { # Check for memcpy(foo, bar, ETH_ALEN) that could be ether_addr_copy(foo, bar) if ($^V && $^V ge 5.10.0 && - $line =~ /^\+(?:.*?)\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/s) { + defined $stat && + $stat =~ /^\+(?:.*?)\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { if (WARN("PREFER_ETHER_ADDR_COPY", - "Prefer ether_addr_copy() over memcpy() if the Ethernet addresses are __aligned(2)\n" . $herecurr) && + "Prefer ether_addr_copy() over memcpy() if the Ethernet addresses are __aligned(2)\n" . "$here\n$stat\n") && $fix) { $fixed[$fixlinenr] =~ s/\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/ether_addr_copy($2, $7)/; } } +# Check for memcmp(foo, bar, ETH_ALEN) that could be ether_addr_equal*(foo, bar) + if ($^V && $^V ge 5.10.0 && + defined $stat && + $stat =~ /^\+(?:.*?)\bmemcmp\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { + WARN("PREFER_ETHER_ADDR_EQUAL", + "Prefer ether_addr_equal() or ether_addr_equal_unaligned() over memcmp()\n" . "$here\n$stat\n") + } + +# check for memset(foo, 0x0, ETH_ALEN) that could be eth_zero_addr +# check for memset(foo, 0xFF, ETH_ALEN) that could be eth_broadcast_addr + if ($^V && $^V ge 5.10.0 && + defined $stat && + $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { + + my $ms_val = $7; + + if ($ms_val =~ /^(?:0x|)0+$/i) { + if (WARN("PREFER_ETH_ZERO_ADDR", + "Prefer eth_zero_addr over memset()\n" . "$here\n$stat\n") && + $fix) { + $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_zero_addr($2)/; + } + } elsif ($ms_val =~ /^(?:0xff|255)$/i) { + if (WARN("PREFER_ETH_BROADCAST_ADDR", + "Prefer eth_broadcast_addr() over memset()\n" . "$here\n$stat\n") && + $fix) { + $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_broadcast_addr($2)/; + } + } + } + # typecasts on min/max could be min_t/max_t if ($^V && $^V ge 5.10.0 && defined $stat && @@ -5472,6 +5642,24 @@ sub process { } } } + +# validate content of MODULE_LICENSE against list from include/linux/module.h + if ($line =~ /\bMODULE_LICENSE\s*\(\s*($String)\s*\)/) { + my $extracted_string = get_quoted_string($line, $rawline); + my $valid_licenses = qr{ + GPL| + GPL\ v2| + GPL\ and\ additional\ rights| + Dual\ BSD/GPL| + Dual\ MIT/GPL| + Dual\ MPL/GPL| + Proprietary + }x; + if ($extracted_string !~ /^"(?:$valid_licenses)"$/x) { + WARN("MODULE_LICENSE", + "unknown module license " . $extracted_string . "\n" . $herecurr); + } + } } # If we have no input at all, then there is nothing to report on @@ -5492,11 +5680,11 @@ sub process { exit(0); } - if (!$is_patch) { + if (!$is_patch && $file !~ /cover-letter\.patch$/) { ERROR("NOT_UNIFIED_DIFF", "Does not appear to be a unified-diff format patch\n"); } - if ($is_patch && $chk_signoff && $signoff == 0) { + if ($is_patch && $filename ne '-' && $chk_signoff && $signoff == 0) { ERROR("MISSING_SIGN_OFF", "Missing Signed-off-by: line(s)\n"); } @@ -5507,28 +5695,21 @@ sub process { print "total: $cnt_error errors, $cnt_warn warnings, " . (($check)? "$cnt_chk checks, " : "") . "$cnt_lines lines checked\n"; - print "\n" if ($quiet == 0); } if ($quiet == 0) { - - if ($^V lt 5.10.0) { - print("NOTE: perl $^V is not modern enough to detect all possible issues.\n"); - print("An upgrade to at least perl v5.10.0 is suggested.\n\n"); - } - # If there were whitespace errors which cleanpatch can fix # then suggest that. if ($rpt_cleaners) { - print "NOTE: whitespace errors detected, you may wish to use scripts/cleanpatch or\n"; - print " scripts/cleanfile\n\n"; $rpt_cleaners = 0; + print << "EOM" + +NOTE: Whitespace errors detected. + You may wish to use scripts/cleanpatch or scripts/cleanfile +EOM } } - hash_show_words(\%use_type, "Used"); - hash_show_words(\%ignore_type, "Ignored"); - if ($clean == 0 && $fix && ("@rawlines" ne "@fixed" || $#fixed_inserted >= 0 || $#fixed_deleted >= 0)) { @@ -5556,6 +5737,7 @@ sub process { if (!$quiet) { print << "EOM"; + Wrote EXPERIMENTAL --fix correction(s) to '$newfile' Do _NOT_ trust the results written to this file. @@ -5563,22 +5745,17 @@ Do _NOT_ submit these changes without inspecting them for correctness. This EXPERIMENTAL file is simply a convenience to help rewrite patches. No warranties, expressed or implied... - EOM } } - if ($clean == 1 && $quiet == 0) { - print "$vname has no obvious style problems and is ready for submission.\n" - } - if ($clean == 0 && $quiet == 0) { - print << "EOM"; -$vname has style problems, please review. - -If any of these errors are false positives, please report -them to the maintainer, see CHECKPATCH in MAINTAINERS. -EOM + if ($quiet == 0) { + print "\n"; + if ($clean == 1) { + print "$vname has no obvious style problems and is ready for submission.\n"; + } else { + print "$vname has style problems, please review.\n"; + } } - return $clean; } diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index d701627..98bae86 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -42,6 +42,7 @@ my $output_multiline = 1; my $output_separator = ", "; my $output_roles = 0; my $output_rolestats = 1; +my $output_section_maxlen = 50; my $scm = 0; my $web = 0; my $subsystem = 0; @@ -186,6 +187,27 @@ if (-f $conf) { unshift(@ARGV, @conf_args) if @conf_args; } +my @ignore_emails = (); +my $ignore_file = which_conf(".get_maintainer.ignore"); +if (-f $ignore_file) { + open(my $ignore, '<', "$ignore_file") + or warn "$P: Can't find a readable .get_maintainer.ignore file $!\n"; + while (<$ignore>) { + my $line = $_; + + $line =~ s/\s*\n?$//; + $line =~ s/^\s*//; + $line =~ s/\s+$//; + $line =~ s/#.*$//; + + next if ($line =~ m/^\s*$/); + if (rfc822_valid($line)) { + push(@ignore_emails, $line); + } + } + close($ignore); +} + if (!GetOptions( 'email!' => \$email, 'git!' => \$email_git, @@ -283,7 +305,7 @@ open (my $maint, '<', "${lk_path}MAINTAINERS") while (<$maint>) { my $line = $_; - if ($line =~ m/^(\C):\s*(.*)/) { + if ($line =~ m/^([A-Z]):\s*(.*)/) { my $type = $1; my $value = $2; @@ -513,12 +535,22 @@ if ($web) { exit($exit); +sub ignore_email_address { + my ($address) = @_; + + foreach my $ignore (@ignore_emails) { + return 1 if ($ignore eq $address); + } + + return 0; +} + sub range_is_maintained { my ($start, $end) = @_; for (my $i = $start; $i < $end; $i++) { my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { + if ($line =~ m/^([A-Z]):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'S') { @@ -536,7 +568,7 @@ sub range_has_maintainer { for (my $i = $start; $i < $end; $i++) { my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { + if ($line =~ m/^([A-Z]):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'M') { @@ -585,7 +617,7 @@ sub get_maintainers { for ($i = $start; $i < $end; $i++) { my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { + if ($line =~ m/^([A-Z]):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'X') { @@ -600,7 +632,7 @@ sub get_maintainers { if (!$exclude) { for ($i = $start; $i < $end; $i++) { my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { + if ($line =~ m/^([A-Z]):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'F') { @@ -901,7 +933,7 @@ sub find_first_section { while ($index < @typevalue) { my $tv = $typevalue[$index]; - if (($tv =~ m/^(\C):\s*(.*)/)) { + if (($tv =~ m/^([A-Z]):\s*(.*)/)) { last; } $index++; @@ -915,7 +947,7 @@ sub find_starting_index { while ($index > 0) { my $tv = $typevalue[$index]; - if (!($tv =~ m/^(\C):\s*(.*)/)) { + if (!($tv =~ m/^([A-Z]):\s*(.*)/)) { last; } $index--; @@ -929,7 +961,7 @@ sub find_ending_index { while ($index < @typevalue) { my $tv = $typevalue[$index]; - if (!($tv =~ m/^(\C):\s*(.*)/)) { + if (!($tv =~ m/^([A-Z]):\s*(.*)/)) { last; } $index++; @@ -947,15 +979,15 @@ sub get_maintainer_role { my $role = "unknown"; my $subsystem = $typevalue[$start]; - if (length($subsystem) > 20) { - $subsystem = substr($subsystem, 0, 17); + if ($output_section_maxlen && length($subsystem) > $output_section_maxlen) { + $subsystem = substr($subsystem, 0, $output_section_maxlen - 3); $subsystem =~ s/\s*$//; $subsystem = $subsystem . "..."; } for ($i = $start + 1; $i < $end; $i++) { my $tv = $typevalue[$i]; - if ($tv =~ m/^(\C):\s*(.*)/) { + if ($tv =~ m/^([A-Z]):\s*(.*)/) { my $ptype = $1; my $pvalue = $2; if ($ptype eq "S") { @@ -990,8 +1022,8 @@ sub get_list_role { my $end = find_ending_index($index); my $subsystem = $typevalue[$start]; - if (length($subsystem) > 20) { - $subsystem = substr($subsystem, 0, 17); + if ($output_section_maxlen && length($subsystem) > $output_section_maxlen) { + $subsystem = substr($subsystem, 0, $output_section_maxlen - 3); $subsystem =~ s/\s*$//; $subsystem = $subsystem . "..."; } @@ -1014,7 +1046,7 @@ sub add_categories { for ($i = $start + 1; $i < $end; $i++) { my $tv = $typevalue[$i]; - if ($tv =~ m/^(\C):\s*(.*)/) { + if ($tv =~ m/^([A-Z]):\s*(.*)/) { my $ptype = $1; my $pvalue = $2; if ($ptype eq "L") { @@ -1056,7 +1088,7 @@ sub add_categories { if ($name eq "") { if ($i > 0) { my $tv = $typevalue[$i - 1]; - if ($tv =~ m/^(\C):\s*(.*)/) { + if ($tv =~ m/^([A-Z]):\s*(.*)/) { if ($1 eq "P") { $name = $2; $pvalue = format_email($name, $address, $email_usename); @@ -1073,7 +1105,7 @@ sub add_categories { if ($name eq "") { if ($i > 0) { my $tv = $typevalue[$i - 1]; - if ($tv =~ m/^(\C):\s*(.*)/) { + if ($tv =~ m/^([A-Z]):\s*(.*)/) { if ($1 eq "P") { $name = $2; $pvalue = format_email($name, $address, $email_usename); @@ -1868,6 +1900,7 @@ sub vcs_assign { my $percent = $sign_offs * 100 / $divisor; $percent = 100 if ($percent > 100); + next if (ignore_email_address($line)); $count++; last if ($sign_offs < $email_git_min_signatures || $count > $email_git_max_maintainers || |