From 36ac26171afa8dbf29226199699fe955d4a0b6f6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 26 Jul 2008 11:22:33 +0200 Subject: crashdump: fix undefined reference to `elfcorehdr_addr' fix build bug introduced by 95b68dec0d5 "calgary iommu: use the first kernels TCE tables in kdump": arch/x86/kernel/built-in.o: In function `calgary_iommu_init': (.init.text+0x8399): undefined reference to `elfcorehdr_addr' arch/x86/kernel/built-in.o: In function `calgary_iommu_init': (.init.text+0x856c): undefined reference to `elfcorehdr_addr' arch/x86/kernel/built-in.o: In function `detect_calgary': (.init.text+0x8c68): undefined reference to `elfcorehdr_addr' arch/x86/kernel/built-in.o: In function `detect_calgary': (.init.text+0x8d0c): undefined reference to `elfcorehdr_addr' make elfcorehdr_addr a generally available symbol. Signed-off-by: Ingo Molnar --- include/linux/crash_dump.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 6cd39a927e1f..025e4f575103 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -8,7 +8,13 @@ #include #define ELFCORE_ADDR_MAX (-1ULL) + +#ifdef CONFIG_PROC_VMCORE extern unsigned long long elfcorehdr_addr; +#else +static const unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; +#endif + extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); extern const struct file_operations proc_vmcore_operations; -- cgit v1.2.2 From 16d69265b930f7e2fa9eea381715696f780718f4 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 25 Jul 2008 19:44:36 -0700 Subject: uninline arch_pick_mmap_layout() Fix this, on avr32: include/linux/utsname.h:35, from init/main.c:20: include/linux/sched.h: In function 'arch_pick_mmap_layout': include/linux/sched.h:2149: error: implicit declaration of function 'PAGE_ALIGN' Reported-by: Adrian Bunk Cc: Haavard Skinnemoen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 42036ffe6b00..3260a5c42b91 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2139,16 +2139,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ -#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT extern void arch_pick_mmap_layout(struct mm_struct *mm); -#else -static inline void arch_pick_mmap_layout(struct mm_struct *mm) -{ - mm->mmap_base = TASK_UNMAPPED_BASE; - mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; -} -#endif #ifdef CONFIG_TRACING extern void -- cgit v1.2.2 From 8d8bb39b9eba32dd70e87fd5ad5c5dd4ba118e06 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 25 Jul 2008 19:44:49 -0700 Subject: dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori Cc: Muli Ben-Yehuda Cc: Andi Kleen Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Avi Kivity Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2o.h | 2 +- include/linux/ssb/ssb.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 7d51cbca49ab..75ae6d8aba4f 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -758,7 +758,7 @@ static inline dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr, } dma_addr = dma_map_single(&c->pdev->dev, ptr, size, direction); - if (!dma_mapping_error(dma_addr)) { + if (!dma_mapping_error(&c->pdev->dev, dma_addr)) { #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64 if ((sizeof(dma_addr_t) > 4) && c->pae_support) { *mptr++ = cpu_to_le32(0x7C020002); diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 4bf8cade9dbc..e530026eedf7 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -427,9 +427,9 @@ static inline int ssb_dma_mapping_error(struct ssb_device *dev, dma_addr_t addr) { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: - return pci_dma_mapping_error(addr); + return pci_dma_mapping_error(dev->bus->host_pci, addr); case SSB_BUSTYPE_SSB: - return dma_mapping_error(addr); + return dma_mapping_error(dev->dev, addr); default: __ssb_dma_not_implemented(dev); } -- cgit v1.2.2 From 929dfb24fbcd60e2544b2de7bfb4a68da4dfc747 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:44:54 -0700 Subject: parport/share.c: proper externs This patch adds proper externs for parport_default_timeslice and parport_default_spintime in include/linux/parport.h Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/parport.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index dcb9e01a69ca..6a0d7cdb5774 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -560,5 +560,8 @@ extern int parport_device_proc_unregister(struct pardevice *device); #endif /* !CONFIG_PARPORT_NOT_PC */ +extern unsigned long parport_default_timeslice; +extern int parport_default_spintime; + #endif /* __KERNEL__ */ #endif /* _PARPORT_H_ */ -- cgit v1.2.2 From b77899985bdfd85a8e5a6e485033a9b4713d2471 Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Fri, 25 Jul 2008 19:45:00 -0700 Subject: memstick: allow "set_param" method to return an error code Some controllers (Jmicron, for instance) can report temporal failure condition during power-on. It is desirable to account for this using a return value of "set_param" device method. The return value can also be handy to distinguish between supported and unsupported device parameters in run time. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memstick.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index 37a5cdb03918..2fe599c66d52 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -284,7 +284,7 @@ struct memstick_host { /* Notify the host that some requests are pending. */ void (*request)(struct memstick_host *host); /* Set host IO parameters (power, clock, etc). */ - void (*set_param)(struct memstick_host *host, + int (*set_param)(struct memstick_host *host, enum memstick_param param, int value); unsigned long private[0] ____cacheline_aligned; -- cgit v1.2.2 From 17017d8d2c005734d7088d8281ce2daab8fcb097 Mon Sep 17 00:00:00 2001 From: Alex Dubov Date: Fri, 25 Jul 2008 19:45:01 -0700 Subject: memstick: add "start" and "stop" methods to memstick device In some cases it may be desirable to ensure that associated driver is not going to access the media in some period of time. "start" and "stop" methods are provided therefore to allow it. Signed-off-by: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memstick.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memstick.h b/include/linux/memstick.h index 2fe599c66d52..a9f998a3f48b 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -263,6 +263,10 @@ struct memstick_dev { /* Get next request from the media driver. */ int (*next_request)(struct memstick_dev *card, struct memstick_request **mrq); + /* Tell the media driver to stop doing things */ + void (*stop)(struct memstick_dev *card); + /* Allow the media driver to continue */ + void (*start)(struct memstick_dev *card); struct device dev; }; -- cgit v1.2.2 From 3ab83521378268044a448113c6aa9a9e245f4d2f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 25 Jul 2008 19:45:07 -0700 Subject: kexec jump This patch provides an enhancement to kexec/kdump. It implements the following features: - Backup/restore memory used by the original kernel before/after kexec. - Save/restore CPU state before/after kexec. The features of this patch can be used as a general method to call program in physical mode (paging turning off). This can be used to call BIOS code under Linux. kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 Usage example of calling some physical mode code and return: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_KEXEC=y CONFIG_PM=y CONFIG_KEXEC_JUMP=y 2. Build patched kexec-tool or download the pre-built one. 3. Build some physical mode executable named such as "phy_mode" 4. Boot kernel compiled in step 1. 5. Load physical mode executable with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context --args-none phy_mode 6. Call physical mode executable with following shell command line: /sbin/kexec -e Implementation point: To support jumping without reserving memory. One shadow backup page (source page) is allocated for each page used by kexeced code image (destination page). When do kexec_load, the image of kexeced code is loaded into source pages, and before executing, the destination pages and the source pages are swapped, so the contents of destination pages are backupped. Before jumping to the kexeced code image and after jumping back to the original kernel, the destination pages and the source pages are swapped too. C ABI (calling convention) is used as communication protocol between kernel and called code. A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to indicate that the loaded kernel image is used for jumping back. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying Acked-by: Vivek Goyal Cc: "Eric W. Biederman" Cc: Pavel Machek Cc: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 3265968cd2cd..82f88a8a827b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -83,6 +83,7 @@ struct kimage { unsigned long start; struct page *control_code_page; + struct page *swap_page; unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -98,18 +99,20 @@ struct kimage { unsigned int type : 1; #define KEXEC_TYPE_DEFAULT 0 #define KEXEC_TYPE_CRASH 1 + unsigned int preserve_context : 1; }; /* kexec interface functions */ -extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET; +extern void machine_kexec(struct kimage *image); extern int machine_kexec_prepare(struct kimage *image); extern void machine_kexec_cleanup(struct kimage *image); extern asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment __user *segments, unsigned long flags); +extern int kernel_kexec(void); #ifdef CONFIG_COMPAT extern asmlinkage long compat_sys_kexec_load(unsigned long entry, unsigned long nr_segments, @@ -156,8 +159,9 @@ extern struct kimage *kexec_crash_image; #define kexec_flush_icache_page(page) #endif -#define KEXEC_ON_CRASH 0x00000001 -#define KEXEC_ARCH_MASK 0xffff0000 +#define KEXEC_ON_CRASH 0x00000001 +#define KEXEC_PRESERVE_CONTEXT 0x00000002 +#define KEXEC_ARCH_MASK 0xffff0000 /* These values match the ELF architecture values. * Unless there is a good reason that should continue to be the case. @@ -174,7 +178,12 @@ extern struct kimage *kexec_crash_image; #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) -#define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags */ +/* List of defined/legal kexec flags */ +#ifndef CONFIG_KEXEC_JUMP +#define KEXEC_FLAGS KEXEC_ON_CRASH +#else +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT) +#endif #define VMCOREINFO_BYTES (4096) #define VMCOREINFO_NOTE_NAME "VMCOREINFO" -- cgit v1.2.2 From 89081d17f7bb81d89fa1aa9b70f821c5cf4d39e9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 25 Jul 2008 19:45:10 -0700 Subject: kexec jump: save/restore device state This patch implements devices state save/restore before after kexec. This patch together with features in kexec_jump patch can be used for following: - A simple hibernation implementation without ACPI support. You can kexec a hibernating kernel, save the memory image of original system and shutdown the system. When resuming, you restore the memory image of original system via ordinary kexec load then jump back. - Kernel/system debug through making system snapshot. You can make system snapshot, jump back, do some thing and make another system snapshot. - Cooperative multi-kernel/system. With kexec jump, you can switch between several kernels/systems quickly without boot process except the first time. This appears like swap a whole kernel/system out/in. - A general method to call program in physical mode (paging turning off). This can be used to invoke BIOS code under Linux. The following user-space tools can be used with kexec jump: - kexec-tools needs to be patched to support kexec jump. The patches and the precompiled kexec can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10 - makedumpfile with patches are used as memory image saving tool, it can exclude free pages from original kernel memory image file. The patches and the precompiled makedumpfile can be download from the following URL: source: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-src_cvs_kh10.tar.bz2 patches: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile-patches_cvs_kh10.tar.bz2 binary: http://khibernation.sourceforge.net/download/release_v10/makedumpfile/makedumpfile_cvs_kh10 - An initramfs image can be used as the root file system of kexeced kernel. An initramfs image built with "BuildRoot" can be downloaded from the following URL: initramfs image: http://khibernation.sourceforge.net/download/release_v10/initramfs/rootfs_cvs_kh10.gz All user space tools above are included in the initramfs image. Usage example of simple hibernation: 1. Compile and install patched kernel with following options selected: CONFIG_X86_32=y CONFIG_RELOCATABLE=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y CONFIG_PM=y CONFIG_HIBERNATION=y CONFIG_KEXEC_JUMP=y 2. Build an initramfs image contains kexec-tool and makedumpfile, or download the pre-built initramfs image, called rootfs.gz in following text. 3. Prepare a partition to save memory image of original kernel, called hibernating partition in following text. 4. Boot kernel compiled in step 1 (kernel A). 5. In the kernel A, load kernel compiled in step 1 (kernel B) with /sbin/kexec. The shell command line can be as follow: /sbin/kexec --load-preserve-context /boot/bzImage --mem-min=0x100000 --mem-max=0xffffff --initrd=rootfs.gz 6. Boot the kernel B with following shell command line: /sbin/kexec -e 7. The kernel B will boot as normal kexec. In kernel B the memory image of kernel A can be saved into hibernating partition as follow: jump_back_entry=`cat /proc/cmdline | tr ' ' '\n' | grep kexec_jump_back_entry | cut -d '='` echo $jump_back_entry > kexec_jump_back_entry cp /proc/vmcore dump.elf Then you can shutdown the machine as normal. 8. Boot kernel compiled in step 1 (kernel C). Use the rootfs.gz as root file system. 9. In kernel C, load the memory image of kernel A as follow: /sbin/kexec -l --args-none --entry=`cat kexec_jump_back_entry` dump.elf 10. Jump back to the kernel A as follow: /sbin/kexec -e Then, kernel A is resumed. Implementation point: To support jumping between two kernels, before jumping to (executing) the new kernel and jumping back to the original kernel, the devices are put into quiescent state, and the state of devices and CPU is saved. After jumping back from kexeced kernel and jumping to the new kernel, the state of devices and CPU are restored accordingly. The devices/CPU state save/restore code of software suspend is called to implement corresponding function. Known issues: - Because the segment number supported by sys_kexec_load is limited, hibernation image with many segments may not be load. This is planned to be eliminated by adding a new flag to sys_kexec_load to make a image can be loaded with multiple sys_kexec_load invoking. Now, only the i386 architecture is supported. Signed-off-by: Huang Ying Acked-by: Vivek Goyal Cc: "Eric W. Biederman" Cc: Pavel Machek Cc: Nigel Cunningham Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index e8e69159af71..c63435095970 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -278,4 +278,6 @@ static inline void register_nosave_region_late(unsigned long b, unsigned long e) } #endif +extern struct mutex pm_mutex; + #endif /* _LINUX_SUSPEND_H */ -- cgit v1.2.2 From c2147a5092cfe13dbf3210e54e8a622015edeecc Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:11 -0700 Subject: Better interface for hooking early initcalls Added early initcall (pre-SMP) support, using an identical interface to that of regular initcalls. Functions called from do_pre_smp_initcalls() could be converted to use this cleaner interface. This is required by CPU hotplug, because early users have to register notifiers before going SMP. One such CPU hotplug user is the relay interface with buffer-only channels, which needs to register such a notifier, to be usable in early code. This in turn is used by kmemtrace. Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 42ae95411a93..11b84e106053 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -169,6 +169,13 @@ extern void (*late_time_init)(void); static initcall_t __initcall_##fn##id __used \ __attribute__((__section__(".initcall" level ".init"))) = fn +/* + * Early initcalls run before initializing SMP. + * + * Only for built-in code, not modules. + */ +#define early_initcall(fn) __define_initcall("early",fn,early) + /* * A "pure" initcall has no dependencies on anything else, and purely * initializes variables that couldn't be statically initialized. -- cgit v1.2.2 From 7babe8db99d305340cf4828ce1f5a1481d5622ef Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:11 -0700 Subject: Full conversion to early_initcall() interface, remove old interface A previous patch added the early_initcall(), to allow a cleaner hooking of pre-SMP initcalls. Now we remove the older interface, converting all existing users to the new one. [akpm@linux-foundation.org: cleanups] [akpm@linux-foundation.org: build fix] [kosaki.motohiro@jp.fujitsu.com: warning fix] [kosaki.motohiro@jp.fujitsu.com: warning fix] Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 --------- include/linux/smp.h | 5 ----- 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3260a5c42b91..adb8077dc463 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -292,7 +292,6 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_DETECT_SOFTLOCKUP extern void softlockup_tick(void); -extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; @@ -2222,14 +2221,6 @@ static inline void inc_syscw(struct task_struct *tsk) } #endif -#ifdef CONFIG_SMP -void migration_init(void); -#else -static inline void migration_init(void) -{ -} -#endif - #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif diff --git a/include/linux/smp.h b/include/linux/smp.h index 48262f86c969..66484d4a8459 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -74,15 +74,10 @@ void __smp_call_function_single(int cpuid, struct call_single_data *data); #ifdef CONFIG_USE_GENERIC_SMP_HELPERS void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); -void init_call_single_data(void); void ipi_call_lock(void); void ipi_call_unlock(void); void ipi_call_lock_irq(void); void ipi_call_unlock_irq(void); -#else -static inline void init_call_single_data(void) -{ -} #endif /* -- cgit v1.2.2 From 20d8b67c06fa5e74f44e80b0a0fd68c8327f7c6a Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:12 -0700 Subject: relay: add buffer-only channels; useful for early logging Allows one to create and use a channel with no associated files. Files can be initialized later. This is useful in scenarios such as logging in early code, before VFS is up. Therefore, such channels can be created and used as soon as kmem_cache_init() completed. This is needed by kmemtrace to do tracing in early kernel code. [kosaki.motohiro@jp.fujitsu.com: build fix] Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/relay.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h index 6cd8c4425fc7..953fc055e875 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -48,6 +48,7 @@ struct rchan_buf size_t *padding; /* padding counts per sub-buffer */ size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ + size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ } ____cacheline_aligned; @@ -68,6 +69,7 @@ struct rchan int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ struct dentry *parent; /* parent dentry passed to open */ + int has_base_filename; /* has a filename associated? */ char base_filename[NAME_MAX]; /* saved base filename */ }; @@ -169,6 +171,9 @@ struct rchan *relay_open(const char *base_filename, size_t n_subbufs, struct rchan_callbacks *cb, void *private_data); +extern int relay_late_setup_files(struct rchan *chan, + const char *base_filename, + struct dentry *parent); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); extern void relay_subbufs_consumed(struct rchan *chan, -- cgit v1.2.2 From 080ccd4573607a930367c2128fc709814b2ade5d Mon Sep 17 00:00:00 2001 From: Huang Weiyi Date: Fri, 25 Jul 2008 19:45:13 -0700 Subject: include/linux/aio.h: removed duplicated include Removed duplicated include in include/linux/aio.h Signed-off-by: Huang Weiyi Signed-off-by: Benjamin LaHaise Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index b51ddd28444e..09b276c35227 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -7,7 +7,6 @@ #include #include -#include #define AIO_MAXSEGS 4 #define AIO_KIOGRP_NR_ATOMIC 8 -- cgit v1.2.2 From 21cc199baa815d7b3f1ace4be20b9558cbddc00f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:22 -0700 Subject: mm: introduce get_user_pages_fast Introduce a new get_user_pages_fast mm API, which is basically a get_user_pages with a less general API (but still tends to be suited to the common case): - task and mm are always current and current->mm - force is always 0 - pages is always non-NULL - don't pass back vmas This restricted API can be implemented in a much more scalable way on many architectures when the ptes are present, by walking the page tables locklessly (no mmap_sem or page table locks). When the ptes are not populated, get_user_pages_fast() could be slower. This is implemented locklessly on x86, and used in some key direct IO call sites, in later patches, which provides nearly 10% performance improvement on a threaded database workload. Lots of other code could use this too, depending on use cases (eg. grep drivers/). And it might inspire some new and clever ways to use it. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Nick Piggin Cc: Dave Kleikamp Cc: Andy Whitcroft Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Andi Kleen Cc: Dave Kleikamp Cc: Badari Pulavarty Cc: Zach Brown Cc: Jens Axboe Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d87a5a5fe87d..f3fd70d6029f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -833,6 +833,39 @@ extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); +#ifdef CONFIG_HAVE_GET_USER_PAGES_FAST +/* + * get_user_pages_fast provides equivalent functionality to get_user_pages, + * operating on current and current->mm (force=0 and doesn't return any vmas). + * + * get_user_pages_fast may take mmap_sem and page tables, so no assumptions + * can be made about locking. get_user_pages_fast is to be implemented in a + * way that is advantageous (vs get_user_pages()) when the user memory area is + * already faulted in and present in ptes. However if the pages have to be + * faulted in, it may turn out to be slightly slower). + */ +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages); + +#else +/* + * Should probably be moved to asm-generic, and architectures can include it if + * they don't implement their own get_user_pages_fast. + */ +#define get_user_pages_fast(start, nr_pages, write, pages) \ +({ \ + struct mm_struct *mm = current->mm; \ + int ret; \ + \ + down_read(&mm->mmap_sem); \ + ret = get_user_pages(current, mm, start, nr_pages, \ + write, 0, pages, NULL); \ + up_read(&mm->mmap_sem); \ + \ + ret; \ +}) +#endif + /* * A callback you can register to apply pressure to ageable caches. * -- cgit v1.2.2 From 47feff2c8eefe85099f87c43d3096855f0085ca0 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:29 -0700 Subject: radix-tree: add gang_lookup_slot, gang_lookup_slot_tag Introduce gang_lookup_slot() and gang_lookup_slot_tag() functions, which are used by lockless pagecache. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index b8ce2b444bb5..a916c6660dfa 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -99,12 +99,15 @@ do { \ * * The notable exceptions to this rule are the following functions: * radix_tree_lookup + * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup + * radix_tree_gang_lookup_slot * radix_tree_gang_lookup_tag + * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * - * The first 4 functions are able to be called locklessly, using RCU. The + * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. @@ -159,6 +162,9 @@ void *radix_tree_delete(struct radix_tree_root *, unsigned long); unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items); +unsigned int +radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items); unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); @@ -173,6 +179,10 @@ unsigned int radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag); +unsigned int +radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, + unsigned long first_index, unsigned int max_items, + unsigned int tag); int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); static inline void radix_tree_preload_end(void) -- cgit v1.2.2 From e286781d5f2e9c846e012a39653a166e9d31777d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:30 -0700 Subject: mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin Cc: Jeff Garzik Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: KOSAKI Motohiro Signed-off-by: Hugh Dickins Acked-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 111 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 110 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee1ec2c7723c..a81d81890422 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -12,6 +12,7 @@ #include #include #include +#include /* for in_interrupt() */ /* * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page @@ -62,6 +63,98 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_release(page) put_page(page) void release_pages(struct page **pages, int nr, int cold); +/* + * speculatively take a reference to a page. + * If the page is free (_count == 0), then _count is untouched, and 0 + * is returned. Otherwise, _count is incremented by 1 and 1 is returned. + * + * This function must be called inside the same rcu_read_lock() section as has + * been used to lookup the page in the pagecache radix-tree (or page table): + * this allows allocators to use a synchronize_rcu() to stabilize _count. + * + * Unless an RCU grace period has passed, the count of all pages coming out + * of the allocator must be considered unstable. page_count may return higher + * than expected, and put_page must be able to do the right thing when the + * page has been finished with, no matter what it is subsequently allocated + * for (because put_page is what is used here to drop an invalid speculative + * reference). + * + * This is the interesting part of the lockless pagecache (and lockless + * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) + * has the following pattern: + * 1. find page in radix tree + * 2. conditionally increment refcount + * 3. check the page is still in pagecache (if no, goto 1) + * + * Remove-side that cares about stability of _count (eg. reclaim) has the + * following (with tree_lock held for write): + * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) + * B. remove page from pagecache + * C. free the page + * + * There are 2 critical interleavings that matter: + * - 2 runs before A: in this case, A sees elevated refcount and bails out + * - A runs before 2: in this case, 2 sees zero refcount and retries; + * subsequently, B will complete and 1 will find no page, causing the + * lookup to return NULL. + * + * It is possible that between 1 and 2, the page is removed then the exact same + * page is inserted into the same position in pagecache. That's OK: the + * old find_get_page using tree_lock could equally have run before or after + * such a re-insertion, depending on order that locks are granted. + * + * Lookups racing against pagecache insertion isn't a big problem: either 1 + * will find the page or it will not. Likewise, the old find_get_page could run + * either before the insertion or afterwards, depending on timing. + */ +static inline int page_cache_get_speculative(struct page *page) +{ + VM_BUG_ON(in_interrupt()); + +#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU) +# ifdef CONFIG_PREEMPT + VM_BUG_ON(!in_atomic()); +# endif + /* + * Preempt must be disabled here - we rely on rcu_read_lock doing + * this for us. + * + * Pagecache won't be truncated from interrupt context, so if we have + * found a page in the radix tree here, we have pinned its refcount by + * disabling preempt, and hence no need for the "speculative get" that + * SMP requires. + */ + VM_BUG_ON(page_count(page) == 0); + atomic_inc(&page->_count); + +#else + if (unlikely(!get_page_unless_zero(page))) { + /* + * Either the page has been freed, or will be freed. + * In either case, retry here and the caller should + * do the right thing (see comments above). + */ + return 0; + } +#endif + VM_BUG_ON(PageTail(page)); + + return 1; +} + +static inline int page_freeze_refs(struct page *page, int count) +{ + return likely(atomic_cmpxchg(&page->_count, count, 0) == count); +} + +static inline void page_unfreeze_refs(struct page *page, int count) +{ + VM_BUG_ON(page_count(page) != 0); + VM_BUG_ON(count == 0); + + atomic_set(&page->_count, count); +} + #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else @@ -133,13 +226,29 @@ static inline struct page *read_mapping_page(struct address_space *mapping, return read_cache_page(mapping, index, filler, data); } -int add_to_page_cache(struct page *page, struct address_space *mapping, +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void remove_from_page_cache(struct page *page); extern void __remove_from_page_cache(struct page *page); +/* + * Like add_to_page_cache_locked, but used to add newly allocated pages: + * the page is new, so we can just run SetPageLocked() against it. + */ +static inline int add_to_page_cache(struct page *page, + struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) +{ + int error; + + SetPageLocked(page); + error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); + if (unlikely(error)) + ClearPageLocked(page); + return error; +} + /* * Return byte-offset into filesystem object for page. */ -- cgit v1.2.2 From 19fd6231279be3c3bdd02ed99f9b0eb195978064 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:32 -0700 Subject: mm: spinlock tree_lock mapping->tree_lock has no read lockers. convert the lock from an rwlock to a spinlock. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 49d8eb7a71be..53d2edb709b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -499,7 +499,7 @@ struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ - rwlock_t tree_lock; /* and rwlock protecting it */ + spinlock_t tree_lock; /* and lock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ -- cgit v1.2.2 From 51cc50685a4275c6a02653670af9f108a64e01cf Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 25 Jul 2008 19:45:34 -0700 Subject: SL*B: drop kmem cache argument from constructor Kmem cache passed to constructor is only needed for constructors that are themselves multiplexeres. Nobody uses this "feature", nor does anybody uses passed kmem cache in non-trivial way, so pass only pointer to object. Non-trivial places are: arch/powerpc/mm/init_64.c arch/powerpc/mm/hugetlbpage.c This is flag day, yes. Signed-off-by: Alexey Dobriyan Acked-by: Pekka Enberg Acked-by: Christoph Lameter Cc: Jon Tollefson Cc: Nick Piggin Cc: Matt Mackall [akpm@linux-foundation.org: fix arch/powerpc/mm/hugetlbpage.c] [akpm@linux-foundation.org: fix mm/slab.c] [akpm@linux-foundation.org: fix ubifs] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 +- include/linux/slub_def.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 41103910f8a2..9ff8e8499403 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -58,7 +58,7 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, - void (*)(struct kmem_cache *, void *)); + void (*)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index d117ea2825a9..5bad61a93f65 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -85,7 +85,7 @@ struct kmem_cache { struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ - void (*ctor)(struct kmem_cache *, void *); + void (*ctor)(void *); int inuse; /* Offset to metadata */ int align; /* Alignment */ const char *name; /* Name (only for display!) */ -- cgit v1.2.2 From 88ac2921a71f788ed693bcd44731dd6bc1994640 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:43 -0700 Subject: tracehook: add linux/tracehook.h This patch series introduces the "tracehook" interface layer of inlines in . There are more details in the log entry for patch 01/23 and in the header file comments inside that patch. Most of these changes move code around with little or no change, and they should not break anything or change any behavior. This sets a new standard for uniform arch support to enable clean arch-independent implementations of new debugging and tracing stuff, denoted by CONFIG_HAVE_ARCH_TRACEHOOK. Patch 20/23 adds that symbol to arch/Kconfig, with comments listing everything an arch has to do before setting "select HAVE_ARCH_TRACEHOOK". These are elaborted a bit at: http://sourceware.org/systemtap/wiki/utrace/arch/HowTo The new inlines that arch code must define or call have detailed kerneldoc comments in the generic header files that say what is required. No arch is obligated to do any work, and no arch's build should be broken by these changes. There are several steps that each arch should take so it can set HAVE_ARCH_TRACEHOOK. Most of these are simple. Providing this support will let new things people add for doing debugging and tracing of user-level threads "just work" for your arch in the future. For an arch that does not provide HAVE_ARCH_TRACEHOOK, some new options for such features will not be available for config. I have done some arch work and will submit this to the arch maintainers after the generic tracehook series settles in. For now, that work is available in my GIT repositories, and in patch and mbox-of-patches form at http://people.redhat.com/roland/utrace/2.6-current/ This paves the way for my "utrace" work, to be submitted later. But it is not innately tied to that. I hope that the tracehook series can go in soon regardless of what eventually does or doesn't go on top of it. For anyone implementing any kind of new tracing/debugging plan, or just understanding all the context of the existing ptrace implementation, having tracehook.h makes things much easier to find and understand. This patch: This adds the new kernel-internal header file . This is not yet used at all. The comments in the header introduce what the following series of patches is about. The aim is to formalize and consolidate all the places that the core kernel code and the arch code now ties into the ptrace implementation. These patches mostly don't cause any functional change. They just move the details of ptrace logic out of core code into tracehook.h inlines, where they are mostly compiled away to the same as before. All that changes is that everything is thoroughly documented and any future reworking of ptrace, or addition of something new, would not have to touch core code all over, just change the tracehook.h inlines. The new linux/ptrace.h inlines are used by the following patches in the new tracehook_*() inlines. Using these helpers for the ptrace event stops makes it simple to change or disable the old ptrace implementation of these stops conditionally later. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 33 ++++++++++++++++++++++++++++++ include/linux/tracehook.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 85 insertions(+) create mode 100644 include/linux/tracehook.h (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index c6f5f9dd0cee..c74abfc4c7e8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -121,6 +121,39 @@ static inline void ptrace_unlink(struct task_struct *child) int generic_ptrace_peekdata(struct task_struct *tsk, long addr, long data); int generic_ptrace_pokedata(struct task_struct *tsk, long addr, long data); +/** + * task_ptrace - return %PT_* flags that apply to a task + * @task: pointer to &task_struct in question + * + * Returns the %PT_* flags that apply to @task. + */ +static inline int task_ptrace(struct task_struct *task) +{ + return task->ptrace; +} + +/** + * ptrace_event - possibly stop for a ptrace event notification + * @mask: %PT_* bit to check in @current->ptrace + * @event: %PTRACE_EVENT_* value to report if @mask is set + * @message: value for %PTRACE_GETEVENTMSG to return + * + * This checks the @mask bit to see if ptrace wants stops for this event. + * If so we stop, reporting @event and @message to the ptrace parent. + * + * Returns nonzero if we did a ptrace notification, zero if not. + * + * Called without locks. + */ +static inline int ptrace_event(int mask, int event, unsigned long message) +{ + if (mask && likely(!(current->ptrace & mask))) + return 0; + current->ptrace_message = message; + ptrace_notify((event << 8) | SIGTRAP); + return 1; +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h new file mode 100644 index 000000000000..bea0f3eeff54 --- /dev/null +++ b/include/linux/tracehook.h @@ -0,0 +1,52 @@ +/* + * Tracing hooks + * + * Copyright (C) 2008 Red Hat, Inc. All rights reserved. + * + * This copyrighted material is made available to anyone wishing to use, + * modify, copy, or redistribute it subject to the terms and conditions + * of the GNU General Public License v.2. + * + * This file defines hook entry points called by core code where + * user tracing/debugging support might need to do something. These + * entry points are called tracehook_*(). Each hook declared below + * has a detailed kerneldoc comment giving the context (locking et + * al) from which it is called, and the meaning of its return value. + * + * Each function here typically has only one call site, so it is ok + * to have some nontrivial tracehook_*() inlines. In all cases, the + * fast path when no tracing is enabled should be very short. + * + * The purpose of this file and the tracehook_* layer is to consolidate + * the interface that the kernel core and arch code uses to enable any + * user debugging or tracing facility (such as ptrace). The interfaces + * here are carefully documented so that maintainers of core and arch + * code do not need to think about the implementation details of the + * tracing facilities. Likewise, maintainers of the tracing code do not + * need to understand all the calling core or arch code in detail, just + * documented circumstances of each call, such as locking conditions. + * + * If the calling core code changes so that locking is different, then + * it is ok to change the interface documented here. The maintainer of + * core code changing should notify the maintainers of the tracing code + * that they need to work out the change. + * + * Some tracehook_*() inlines take arguments that the current tracing + * implementations might not necessarily use. These function signatures + * are chosen to pass in all the information that is on hand in the + * caller and might conceivably be relevant to a tracer, so that the + * core code won't have to be updated when tracing adds more features. + * If a call site changes so that some of those parameters are no longer + * already on hand without extra work, then the tracehook_* interface + * can change so there is no make-work burden on the core code. The + * maintainer of core code changing should notify the maintainers of the + * tracing code that they need to work out the change. + */ + +#ifndef _LINUX_TRACEHOOK_H +#define _LINUX_TRACEHOOK_H 1 + +#include +#include + +#endif /* */ -- cgit v1.2.2 From 6341c393fcc37d58727865f1ee2f65e632e9d4f0 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:44 -0700 Subject: tracehook: exec This moves all the ptrace hooks related to exec into tracehook.h inlines. This also lifts the calls for tracing out of the binfmt load_binary hooks into search_binary_handler() after it calls into the binfmt module. This change has no effect, since all the binfmt modules' load_binary functions did the call at the end on success, and now search_binary_handler() does it immediately after return if successful. We consolidate the repeated code, and binfmt modules no longer need to import ptrace_notify(). Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index bea0f3eeff54..6276353709c1 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -48,5 +48,51 @@ #include #include +#include +struct linux_binprm; + +/** + * tracehook_unsafe_exec - check for exec declared unsafe due to tracing + * @task: current task doing exec + * + * Return %LSM_UNSAFE_* bits applied to an exec because of tracing. + * + * Called with task_lock() held on @task. + */ +static inline int tracehook_unsafe_exec(struct task_struct *task) +{ + int unsafe = 0; + int ptrace = task_ptrace(task); + if (ptrace & PT_PTRACED) { + if (ptrace & PT_PTRACE_CAP) + unsafe |= LSM_UNSAFE_PTRACE_CAP; + else + unsafe |= LSM_UNSAFE_PTRACE; + } + return unsafe; +} + +/** + * tracehook_report_exec - a successful exec was completed + * @fmt: &struct linux_binfmt that performed the exec + * @bprm: &struct linux_binprm containing exec details + * @regs: user-mode register state + * + * An exec just completed, we are shortly going to return to user mode. + * The freshly initialized register state can be seen and changed in @regs. + * The name, file and other pointers in @bprm are still on hand to be + * inspected, but will be freed as soon as this returns. + * + * Called with no locks, but with some kernel resources held live + * and a reference on @fmt->module. + */ +static inline void tracehook_report_exec(struct linux_binfmt *fmt, + struct linux_binprm *bprm, + struct pt_regs *regs) +{ + if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) && + unlikely(task_ptrace(current) & PT_PTRACED)) + send_sig(SIGTRAP, current, 0); +} #endif /* */ -- cgit v1.2.2 From 30199f5a46aee204bf437a4f5b0740f3efe448b7 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:46 -0700 Subject: tracehook: exit This moves the PTRACE_EVENT_EXIT tracing into a tracehook.h inline, tracehook_report_exec(). The change has no effect, just clean-up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6276353709c1..967ab473afbc 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -95,4 +95,19 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt, send_sig(SIGTRAP, current, 0); } +/** + * tracehook_report_exit - task has begun to exit + * @exit_code: pointer to value destined for @current->exit_code + * + * @exit_code points to the value passed to do_exit(), which tracing + * might change here. This is almost the first thing in do_exit(), + * before freeing any resources or setting the %PF_EXITING flag. + * + * Called with no locks held. + */ +static inline void tracehook_report_exit(long *exit_code) +{ + ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); +} + #endif /* */ -- cgit v1.2.2 From 09a05394fe2448a4139b014936330af23fa7ec83 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: clone This moves all the ptrace initialization and tracing logic for task creation into tracehook.h and ptrace.h inlines. It reorganizes the code slightly, but should not change any behavior. There are four tracehook entry points, at each important stage of task creation. This keeps the interface from the core fork.c code fairly clean, while supporting the complex setup required for ptrace or something like it. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 22 ++++++++++ include/linux/tracehook.h | 100 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 122 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index c74abfc4c7e8..dae6d85520fb 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -154,6 +154,28 @@ static inline int ptrace_event(int mask, int event, unsigned long message) return 1; } +/** + * ptrace_init_task - initialize ptrace state for a new child + * @child: new child task + * @ptrace: true if child should be ptrace'd by parent's tracer + * + * This is called immediately after adding @child to its parent's children + * list. @ptrace is false in the normal case, and true to ptrace @child. + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void ptrace_init_task(struct task_struct *child, bool ptrace) +{ + INIT_LIST_HEAD(&child->ptrace_entry); + INIT_LIST_HEAD(&child->ptraced); + child->parent = child->real_parent; + child->ptrace = 0; + if (unlikely(ptrace)) { + child->ptrace = current->ptrace; + __ptrace_link(child, current->parent); + } +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 967ab473afbc..3ebc58b59766 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -110,4 +110,104 @@ static inline void tracehook_report_exit(long *exit_code) ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code); } +/** + * tracehook_prepare_clone - prepare for new child to be cloned + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * + * This is called before a new user task is to be cloned. + * Its return value will be passed to tracehook_finish_clone(). + * + * Called with no locks held. + */ +static inline int tracehook_prepare_clone(unsigned clone_flags) +{ + if (clone_flags & CLONE_UNTRACED) + return 0; + + if (clone_flags & CLONE_VFORK) { + if (current->ptrace & PT_TRACE_VFORK) + return PTRACE_EVENT_VFORK; + } else if ((clone_flags & CSIGNAL) != SIGCHLD) { + if (current->ptrace & PT_TRACE_CLONE) + return PTRACE_EVENT_CLONE; + } else if (current->ptrace & PT_TRACE_FORK) + return PTRACE_EVENT_FORK; + + return 0; +} + +/** + * tracehook_finish_clone - new child created and being attached + * @child: new child task + * @clone_flags: %CLONE_* flags from clone/fork/vfork system call + * @trace: return value from tracehook_clone_prepare() + * + * This is called immediately after adding @child to its parent's children list. + * The @trace value is that returned by tracehook_prepare_clone(). + * + * Called with current's siglock and write_lock_irq(&tasklist_lock) held. + */ +static inline void tracehook_finish_clone(struct task_struct *child, + unsigned long clone_flags, int trace) +{ + ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace); +} + +/** + * tracehook_report_clone - in parent, new child is about to start running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: new child task + * + * Called after a child is set up, but before it has been started running. + * The @trace value is that returned by tracehook_clone_prepare(). + * This is not a good place to block, because the child has not started yet. + * Suspend the child here if desired, and block in tracehook_clone_complete(). + * This must prevent the child from self-reaping if tracehook_clone_complete() + * uses the @child pointer; otherwise it might have died and been released by + * the time tracehook_report_clone_complete() is called. + * + * Called with no locks held, but the child cannot run until this returns. + */ +static inline void tracehook_report_clone(int trace, struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, struct task_struct *child) +{ + if (unlikely(trace)) { + /* + * The child starts up with an immediate SIGSTOP. + */ + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); + } +} + +/** + * tracehook_report_clone_complete - new child is running + * @trace: return value from tracehook_clone_prepare() + * @regs: parent's user register state + * @clone_flags: flags from parent's system call + * @pid: new child's PID in the parent's namespace + * @child: child task, already running + * + * This is called just after the child has started running. This is + * just before the clone/fork syscall returns, or blocks for vfork + * child completion if @clone_flags has the %CLONE_VFORK bit set. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_clone_complete(int trace, + struct pt_regs *regs, + unsigned long clone_flags, + pid_t pid, + struct task_struct *child) +{ + if (unlikely(trace)) + ptrace_event(0, trace, pid); +} + #endif /* */ -- cgit v1.2.2 From daded34be96b1975ff8539ff62ad8b158ce7d842 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:47 -0700 Subject: tracehook: vfork-done This moves the PTRACE_EVENT_VFORK_DONE tracing into a tracehook.h inline, tracehook_report_vfork_done(). The change has no effect, just clean-up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3ebc58b59766..830e6e16097d 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -210,4 +210,22 @@ static inline void tracehook_report_clone_complete(int trace, ptrace_event(0, trace, pid); } +/** + * tracehook_report_vfork_done - vfork parent's child has exited or exec'd + * @child: child task, already running + * @pid: new child's PID in the parent's namespace + * + * Called after a %CLONE_VFORK parent has waited for the child to complete. + * The clone/vfork system call will return immediately after this. + * The @child pointer may be invalid if a self-reaping child died and + * tracehook_report_clone() took no action to prevent it from self-reaping. + * + * Called with no locks held. + */ +static inline void tracehook_report_vfork_done(struct task_struct *child, + pid_t pid) +{ + ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); +} + #endif /* */ -- cgit v1.2.2 From dae33574dcf5211e1f43c7e45fa29f73ba3e00cb Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:48 -0700 Subject: tracehook: release_task This moves the ptrace-related logic from release_task into tracehook.h and ptrace.h inlines. It provides clean hooks both before and after locking tasklist_lock, for future tracing logic to do more cleanup without the lock. This also changes release_task() itself in the rare "zap_leader" case to set the leader to EXIT_DEAD before iterating. This maintains the invariant that release_task() only ever handles a task in EXIT_DEAD. This is a common-sense invariant that is already always true except in this one arcane case of zombie leader whose parent ignores SIGCHLD. This change is harmless and only costs one store in this one rare case. It keeps the expected state more consisently sane, which is nicer when debugging weirdness in release_task(). It also lets some future code in the tracehook entry points rely on this invariant for bookkeeping. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 13 +++++++++++++ include/linux/tracehook.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index dae6d85520fb..ed69c03692d9 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -176,6 +176,19 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) } } +/** + * ptrace_release_task - final ptrace-related cleanup of a zombie being reaped + * @task: task in %EXIT_DEAD state + * + * Called with write_lock(&tasklist_lock) held. + */ +static inline void ptrace_release_task(struct task_struct *task) +{ + BUG_ON(!list_empty(&task->ptraced)); + ptrace_unlink(task); + BUG_ON(!list_empty(&task->ptrace_entry)); +} + #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 830e6e16097d..9a5b3be2503a 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -228,4 +228,32 @@ static inline void tracehook_report_vfork_done(struct task_struct *child, ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid); } +/** + * tracehook_prepare_release_task - task is being reaped, clean up tracing + * @task: task in %EXIT_DEAD state + * + * This is called in release_task() just before @task gets finally reaped + * and freed. This would be the ideal place to remove and clean up any + * tracing-related state for @task. + * + * Called with no locks held. + */ +static inline void tracehook_prepare_release_task(struct task_struct *task) +{ +} + +/** + * tracehook_finish_release_task - task is being reaped, clean up tracing + * @task: task in %EXIT_DEAD state + * + * This is called in release_task() when @task is being in the middle of + * being reaped. After this, there must be no tracing entanglements. + * + * Called with write_lock_irq(&tasklist_lock) held. + */ +static inline void tracehook_finish_release_task(struct task_struct *task) +{ + ptrace_release_task(task); +} + #endif /* */ -- cgit v1.2.2 From 0d094efeb1e98010c6b99923f1eb7e17bf1e3a74 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:49 -0700 Subject: tracehook: tracehook_tracer_task This adds the tracehook_tracer_task() hook to consolidate all forms of "Who is using ptrace on me?" logic. This is used for "TracerPid:" in /proc and for permission checks. We also clean up the selinux code the called an identical accessor. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 9a5b3be2503a..6468ca0fe69b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -72,6 +72,24 @@ static inline int tracehook_unsafe_exec(struct task_struct *task) return unsafe; } +/** + * tracehook_tracer_task - return the task that is tracing the given task + * @tsk: task to consider + * + * Returns NULL if noone is tracing @task, or the &struct task_struct + * pointer to its tracer. + * + * Must called under rcu_read_lock(). The pointer returned might be kept + * live only by RCU. During exec, this may be called with task_lock() + * held on @task, still held from when tracehook_unsafe_exec() was called. + */ +static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) +{ + if (task_ptrace(tsk) & PT_PTRACED) + return rcu_dereference(tsk->parent); + return NULL; +} + /** * tracehook_report_exec - a successful exec was completed * @fmt: &struct linux_binfmt that performed the exec -- cgit v1.2.2 From fa8e26ccd485216fc45c8c2dd1ec3b7ef1a0a2f8 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:50 -0700 Subject: tracehook: tracehook_expect_breakpoints This adds tracehook_expect_breakpoints() as a formal hook for the nommu code to use for its, "Is text-poking likely?" check at mmap time. This names the actual semantics the code means to test, and documents it. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6468ca0fe69b..e113e09b0341 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -51,6 +51,21 @@ #include struct linux_binprm; +/** + * tracehook_expect_breakpoints - guess if task memory might be touched + * @task: current task, making a new mapping + * + * Return nonzero if @task is expected to want breakpoint insertion in + * its memory at some point. A zero return is no guarantee it won't + * be done, but this is a hint that it's known to be likely. + * + * May be called with @task->mm->mmap_sem held for writing. + */ +static inline int tracehook_expect_breakpoints(struct task_struct *task) +{ + return (task_ptrace(task) & PT_PTRACED) != 0; +} + /** * tracehook_unsafe_exec - check for exec declared unsafe due to tracing * @task: current task doing exec -- cgit v1.2.2 From c45aea27617d6a1e0aacddc3b0233f704222fcbd Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:50 -0700 Subject: tracehook: tracehook_signal_handler This defines tracehook_signal_handler() as a hook for the arch signal handling code to call. It gives ptrace the opportunity to stop for a pseudo-single-step trap immediately after signal handler setup is done. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index e113e09b0341..2d1426f8e33b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -289,4 +289,27 @@ static inline void tracehook_finish_release_task(struct task_struct *task) ptrace_release_task(task); } +/** + * tracehook_signal_handler - signal handler setup is complete + * @sig: number of signal being delivered + * @info: siginfo_t of signal being delivered + * @ka: sigaction setting that chose the handler + * @regs: user register state + * @stepping: nonzero if debugger single-step or block-step in use + * + * Called by the arch code after a signal handler has been set up. + * Register and stack state reflects the user handler about to run. + * Signal mask changes have already been made. + * + * Called without locks, shortly before returning to user mode + * (or handling more signals). + */ +static inline void tracehook_signal_handler(int sig, siginfo_t *info, + const struct k_sigaction *ka, + struct pt_regs *regs, int stepping) +{ + if (stepping) + ptrace_notify(SIGTRAP); +} + #endif /* */ -- cgit v1.2.2 From 35de254dc60f91004b3b5ebb1fc7b2c3093d6032 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:51 -0700 Subject: tracehook: tracehook_consider_ignored_signal This defines tracehook_consider_ignored_signal() has a fine-grained hook for deciding to prevent the normal short-circuit of sending an ignored signal, as ptrace does. There is no change, only cleanup. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 2d1426f8e33b..8cffd34f88d5 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -312,4 +312,23 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info, ptrace_notify(SIGTRAP); } +/** + * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal + * @task: task receiving the signal + * @sig: signal number being sent + * @handler: %SIG_IGN or %SIG_DFL + * + * Return zero iff tracing doesn't care to examine this ignored signal, + * so it can short-circuit normal delivery and never even get queued. + * Either @handler is %SIG_DFL and @sig's default is ignore, or it's %SIG_IGN. + * + * Called with @task->sighand->siglock held. + */ +static inline int tracehook_consider_ignored_signal(struct task_struct *task, + int sig, + void __user *handler) +{ + return (task_ptrace(task) & PT_PTRACED) != 0; +} + #endif /* */ -- cgit v1.2.2 From 445a91d2fe3667fb8fc251433645f686933cf56a Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:52 -0700 Subject: tracehook: tracehook_consider_fatal_signal This defines tracehook_consider_fatal_signal() has a fine-grained hook for deciding to skip the special cases for a fatal signal, as ptrace does. There is no change, only cleanup. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8cffd34f88d5..8b4c15e208fe 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -331,4 +331,25 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } +/** + * tracehook_consider_fatal_signal - suppress special handling of fatal signal + * @task: task receiving the signal + * @sig: signal number being sent + * @handler: %SIG_DFL or %SIG_IGN + * + * Return nonzero to prevent special handling of this termination signal. + * Normally @handler is %SIG_DFL. It can be %SIG_IGN if @sig is ignored, + * in which case force_sig() is about to reset it to %SIG_DFL. + * When this returns zero, this signal might cause a quick termination + * that does not give the debugger a chance to intercept the signal. + * + * Called with or without @task->sighand->siglock held. + */ +static inline int tracehook_consider_fatal_signal(struct task_struct *task, + int sig, + void __user *handler) +{ + return (task_ptrace(task) & PT_PTRACED) != 0; +} + #endif /* */ -- cgit v1.2.2 From 283d7559e7712f95a05331eb0a85394c6368101b Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:52 -0700 Subject: tracehook: syscall This adds standard tracehook.h inlines for arch code to call when TIF_SYSCALL_TRACE has been set. This replaces having each arch implement the ptrace guts for its syscall tracing support. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8b4c15e208fe..3548694a24db 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -66,6 +66,76 @@ static inline int tracehook_expect_breakpoints(struct task_struct *task) return (task_ptrace(task) & PT_PTRACED) != 0; } +/* + * ptrace report for syscall entry and exit looks identical. + */ +static inline void ptrace_report_syscall(struct pt_regs *regs) +{ + int ptrace = task_ptrace(current); + + if (!(ptrace & PT_PTRACED)) + return; + + ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } +} + +/** + * tracehook_report_syscall_entry - task is about to attempt a system call + * @regs: user register state of current task + * + * This will be called if %TIF_SYSCALL_TRACE has been set, when the + * current task has just entered the kernel for a system call. + * Full user register state is available here. Changing the values + * in @regs can affect the system call number and arguments to be tried. + * It is safe to block here, preventing the system call from beginning. + * + * Returns zero normally, or nonzero if the calling arch code should abort + * the system call. That must prevent normal entry so no system call is + * made. If @task ever returns to user mode after this, its register state + * is unspecified, but should be something harmless like an %ENOSYS error + * return. + * + * Called without locks, just after entering kernel mode. + */ +static inline __must_check int tracehook_report_syscall_entry( + struct pt_regs *regs) +{ + ptrace_report_syscall(regs); + return 0; +} + +/** + * tracehook_report_syscall_exit - task has just finished a system call + * @regs: user register state of current task + * @step: nonzero if simulating single-step or block-step + * + * This will be called if %TIF_SYSCALL_TRACE has been set, when the + * current task has just finished an attempted system call. Full + * user register state is available here. It is safe to block here, + * preventing signals from being processed. + * + * If @step is nonzero, this report is also in lieu of the normal + * trap that would follow the system call instruction because + * user_enable_block_step() or user_enable_single_step() was used. + * In this case, %TIF_SYSCALL_TRACE might not be set. + * + * Called without locks, just before checking for pending signals. + */ +static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) +{ + ptrace_report_syscall(regs); +} + /** * tracehook_unsafe_exec - check for exec declared unsafe due to tracing * @task: current task doing exec -- cgit v1.2.2 From 7bcf6a2ca5f639b038c48711ebe6c4eca2036641 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:53 -0700 Subject: tracehook: get_signal_to_deliver This defines the tracehook_get_signal() hook to allow tracing code to slip in before normal signal dequeuing. This lays the groundwork for new tracing features that can inject synthetic signals outside the normal queue or control the disposition of delivered signals. The calling convention lets tracehook_get_signal() decide both exactly what will happen and what signal number to report in the handler/exit. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3548694a24db..42a0d7b11959 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -422,4 +422,33 @@ static inline int tracehook_consider_fatal_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } +/** + * tracehook_get_signal - deliver synthetic signal to traced task + * @task: @current + * @regs: task_pt_regs(@current) + * @info: details of synthetic signal + * @return_ka: sigaction for synthetic signal + * + * Return zero to check for a real pending signal normally. + * Return -1 after releasing the siglock to repeat the check. + * Return a signal number to induce an artifical signal delivery, + * setting *@info and *@return_ka to specify its details and behavior. + * + * The @return_ka->sa_handler value controls the disposition of the + * signal, no matter the signal number. For %SIG_DFL, the return value + * is a representative signal to indicate the behavior (e.g. %SIGTERM + * for death, %SIGQUIT for core dump, %SIGSTOP for job control stop, + * %SIGTSTP for stop unless in an orphaned pgrp), but the signal number + * reported will be @info->si_signo instead. + * + * Called with @task->sighand->siglock held, before dequeuing pending signals. + */ +static inline int tracehook_get_signal(struct task_struct *task, + struct pt_regs *regs, + siginfo_t *info, + struct k_sigaction *return_ka) +{ + return 0; +} + #endif /* */ -- cgit v1.2.2 From fa00b80b3c41a845b3d56f866fb40a2e98754c51 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:54 -0700 Subject: tracehook: job control This defines the tracehook_notify_jctl() hook to formalize the ptrace effects on the job control notifications. There is no change, only cleanup. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 42a0d7b11959..6dc428dd2f38 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -451,4 +451,24 @@ static inline int tracehook_get_signal(struct task_struct *task, return 0; } +/** + * tracehook_notify_jctl - report about job control stop/continue + * @notify: nonzero if this is the last thread in the group to stop + * @why: %CLD_STOPPED or %CLD_CONTINUED + * + * This is called when we might call do_notify_parent_cldstop(). + * It's called when about to stop for job control; we are already in + * %TASK_STOPPED state, about to call schedule(). It's also called when + * a delayed %CLD_STOPPED or %CLD_CONTINUED report is ready to be made. + * + * Return nonzero to generate a %SIGCHLD with @why, which is + * normal if @notify is nonzero. + * + * Called with no locks held. + */ +static inline int tracehook_notify_jctl(int notify, int why) +{ + return notify || (current->ptrace & PT_PTRACED); +} + #endif /* */ -- cgit v1.2.2 From 2b2a1ff64afbadac842bbc58c5166962cf4f7664 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:54 -0700 Subject: tracehook: death This moves the ptrace logic in task death (exit_notify) into tracehook.h inlines. Some code is rearranged slightly to make things nicer. There is no change, only cleanup. There is one hook called with the tasklist_lock write-locked, as ptrace needs. There is also a new hook called after exit_state changes and without locks. This is a better place for tracing work to be in the future, since it doesn't delay the whole system with locking. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- include/linux/tracehook.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index adb8077dc463..a95d84d0da95 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1796,7 +1796,7 @@ extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_ extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); -extern void do_notify_parent(struct task_struct *, int); +extern int do_notify_parent(struct task_struct *, int); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6dc428dd2f38..4c50e1b57349 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -471,4 +471,56 @@ static inline int tracehook_notify_jctl(int notify, int why) return notify || (current->ptrace & PT_PTRACED); } +/** + * tracehook_notify_death - task is dead, ready to notify parent + * @task: @current task now exiting + * @death_cookie: value to pass to tracehook_report_death() + * @group_dead: nonzero if this was the last thread in the group to die + * + * Return the signal number to send our parent with do_notify_parent(), or + * zero to send no signal and leave a zombie, or -1 to self-reap right now. + * + * Called with write_lock_irq(&tasklist_lock) held. + */ +static inline int tracehook_notify_death(struct task_struct *task, + void **death_cookie, int group_dead) +{ + if (task->exit_signal == -1) + return task->ptrace ? SIGCHLD : -1; + + /* + * If something other than our normal parent is ptracing us, then + * send it a SIGCHLD instead of honoring exit_signal. exit_signal + * only has special meaning to our real parent. + */ + if (thread_group_empty(task) && !ptrace_reparented(task)) + return task->exit_signal; + + return task->ptrace ? SIGCHLD : 0; +} + +/** + * tracehook_report_death - task is dead and ready to be reaped + * @task: @current task now exiting + * @signal: signal number sent to parent, or 0 or -1 + * @death_cookie: value passed back from tracehook_notify_death() + * @group_dead: nonzero if this was the last thread in the group to die + * + * Thread has just become a zombie or is about to self-reap. If positive, + * @signal is the signal number just sent to the parent (usually %SIGCHLD). + * If @signal is -1, this thread will self-reap. If @signal is 0, this is + * a delayed_group_leader() zombie. The @death_cookie was passed back by + * tracehook_notify_death(). + * + * If normal reaping is not inhibited, @task->exit_state might be changing + * in parallel. + * + * Called without locks. + */ +static inline void tracehook_report_death(struct task_struct *task, + int signal, void *death_cookie, + int group_dead) +{ +} + #endif /* */ -- cgit v1.2.2 From b787f7ba677840da16a2228c16571ce8a1fcb799 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:55 -0700 Subject: tracehook: force signal_pending() This defines a new hook tracehook_force_sigpending() that lets tracing code decide to force TIF_SIGPENDING on in recalc_sigpending(). This is not used yet, so it compiles away to nothing for now. It lays the groundwork for new tracing code that can interrupt a task synthetically without actually sending a signal. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 4c50e1b57349..43bc51b6bd33 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -422,6 +422,20 @@ static inline int tracehook_consider_fatal_signal(struct task_struct *task, return (task_ptrace(task) & PT_PTRACED) != 0; } +/** + * tracehook_force_sigpending - let tracing force signal_pending(current) on + * + * Called when recomputing our signal_pending() flag. Return nonzero + * to force the signal_pending() flag on, so that tracehook_get_signal() + * will be called before the next return to user mode. + * + * Called with @current->sighand->siglock held. + */ +static inline int tracehook_force_sigpending(void) +{ + return 0; +} + /** * tracehook_get_signal - deliver synthetic signal to traced task * @task: @current -- cgit v1.2.2 From 64b1208d5b0ef8859fd52ea7ae286a3eb994669b Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:56 -0700 Subject: tracehook: TIF_NOTIFY_RESUME This adds tracehook.h inlines to enable a new arch feature in support of user debugging/tracing. This is not used yet, but it lays the groundwork for a debugger to be able to wrangle a task that's possibly running, without interrupting its syscalls in progress. Each arch should define TIF_NOTIFY_RESUME, and in their entry.S code treat it much like TIF_SIGPENDING. That is, it causes you to take the slow path when returning to user mode, where you get the full user-mode state accessible as for signal handling or ptrace. The arch code should check TIF_NOTIFY_RESUME after handling TIF_SIGPENDING. When it's set, clear it and then call tracehook_notify_resume(). In future, tracing code will call set_notify_resume() when it wants to get a callback in tracehook_notify_resume(). Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 43bc51b6bd33..32867ab86c70 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -537,4 +537,38 @@ static inline void tracehook_report_death(struct task_struct *task, { } +#ifdef TIF_NOTIFY_RESUME +/** + * set_notify_resume - cause tracehook_notify_resume() to be called + * @task: task that will call tracehook_notify_resume() + * + * Calling this arranges that @task will call tracehook_notify_resume() + * before returning to user mode. If it's already running in user mode, + * it will enter the kernel and call tracehook_notify_resume() soon. + * If it's blocked, it will not be woken. + */ +static inline void set_notify_resume(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) + kick_process(task); +} + +/** + * tracehook_notify_resume - report when about to return to user mode + * @regs: user-mode registers of @current task + * + * This is called when %TIF_NOTIFY_RESUME has been set. Now we are + * about to return to user mode, and the user state in @regs can be + * inspected or adjusted. The caller in arch code has cleared + * %TIF_NOTIFY_RESUME before the call. If the flag gets set again + * asynchronously, this will be called again before we return to + * user mode. + * + * Called without locks. + */ +static inline void tracehook_notify_resume(struct pt_regs *regs) +{ +} +#endif /* TIF_NOTIFY_RESUME */ + #endif /* */ -- cgit v1.2.2 From 828c365cc8b8d38c346fccb19fa80d28f2240831 Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:57 -0700 Subject: tracehook: asm/syscall.h This adds asm-generic/syscall.h, which documents what a real asm-ARCH/syscall.h file should define. This is not used yet, but will provide all the machine-dependent details of examining a user system call about to begin, in progress, or just ended. Each arch should add an asm-ARCH/syscall.h that defines all the entry points documented in asm-generic/syscall.h, as short inlines if possible. This lets us write new tracing code that understands user system call registers, without any new arch-specific work. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tracehook.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 32867ab86c70..589f429619c9 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -103,7 +103,8 @@ static inline void ptrace_report_syscall(struct pt_regs *regs) * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error - * return. + * return. It should preserve enough information so that syscall_rollback() + * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ -- cgit v1.2.2 From 85ba2d862e521375a8ee01526c5c46b1f24bb4af Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:58 -0700 Subject: tracehook: wait_task_inactive This extends wait_task_inactive() with a new argument so it can be used in a "soft" mode where it will check for the task changing state unexpectedly and back off. There is no change to existing callers. This lays the groundwork to allow robust, noninvasive tracing that can try to sample a blocked thread but back off safely if it wakes up. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a95d84d0da95..f59318a0099b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1882,9 +1882,13 @@ extern void set_task_comm(struct task_struct *tsk, char *from); extern char *get_task_comm(char *to, struct task_struct *tsk); #ifdef CONFIG_SMP -extern void wait_task_inactive(struct task_struct * p); +extern unsigned long wait_task_inactive(struct task_struct *, long match_state); #else -#define wait_task_inactive(p) do { } while (0) +static inline unsigned long wait_task_inactive(struct task_struct *p, + long match_state) +{ + return 1; +} #endif #define next_task(p) list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks) -- cgit v1.2.2 From bbc698636ed48b6fcd323964e0f847a6a796325d Mon Sep 17 00:00:00 2001 From: Roland McGrath Date: Fri, 25 Jul 2008 19:45:59 -0700 Subject: task_current_syscall This adds the new function task_current_syscall() on machines where the asm/syscall.h interface is supported (CONFIG_HAVE_ARCH_TRACEHOOK). It's exported for modules to use in the future. This function safely samples the state of a blocked thread to collect what system call it is blocked in, and the six system call argument registers. Signed-off-by: Roland McGrath Cc: Oleg Nesterov Reviewed-by: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ptrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ed69c03692d9..fd31756e1a00 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -314,6 +314,10 @@ static inline void user_enable_block_step(struct task_struct *task) #define arch_ptrace_stop(code, info) do { } while (0) #endif +extern int task_current_syscall(struct task_struct *target, long *callno, + unsigned long args[6], unsigned int maxargs, + unsigned long *sp, unsigned long *pc); + #endif #endif -- cgit v1.2.2 From 9d8fddfb17aaee4ffc5e3d0560620d0fa8b50a42 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:23 -0700 Subject: mm/allocpercpu.c: make 4 functions static This patch makes the following needlessly global functions static: - percpu_depopulate() - __percpu_depopulate_mask() - percpu_populate() - __percpu_populate_mask() Signed-off-by: Adrian Bunk Acked-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 4cdd393e71e1..fac3337547eb 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -74,11 +74,6 @@ struct percpu_data { (__typeof__(ptr))__p->ptrs[(cpu)]; \ }) -extern void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu); -extern void percpu_depopulate(void *__pdata, int cpu); -extern int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, - cpumask_t *mask); -extern void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask); extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask); extern void percpu_free(void *__pdata); @@ -86,26 +81,6 @@ extern void percpu_free(void *__pdata); #define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static inline void percpu_depopulate(void *__pdata, int cpu) -{ -} - -static inline void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask) -{ -} - -static inline void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, - int cpu) -{ - return percpu_ptr(__pdata, cpu); -} - -static inline int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp, - cpumask_t *mask) -{ - return 0; -} - static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask) { return kzalloc(size, gfp); @@ -118,10 +93,6 @@ static inline void percpu_free(void *__pdata) #endif /* CONFIG_SMP */ -#define percpu_populate_mask(__pdata, size, gfp, mask) \ - __percpu_populate_mask((__pdata), (size), (gfp), &(mask)) -#define percpu_depopulate_mask(__pdata, mask) \ - __percpu_depopulate_mask((__pdata), &(mask)) #define percpu_alloc_mask(size, gfp, mask) \ __percpu_alloc_mask((size), (gfp), &(mask)) -- cgit v1.2.2 From 15f59adae001766a2c7f7fe4f196387bb04bcff5 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:23 -0700 Subject: make mm/memory.c:print_bad_pte() static This patch makes the needlessly global print_bad_pte() static. Signed-off-by: Adrian Bunk Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3fd70d6029f..6e695eaab4ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -810,7 +810,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); -void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned long offset); -- cgit v1.2.2 From 7c363b8c6536f26934172d3c46f0bbec01a97c61 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:24 -0700 Subject: mm/swapfile.c: make code static This patch makes the following needlessly global code static: - swap_lock - nr_swapfiles - struct swap_list Signed-off-by: Adrian Bunk Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0b3377650c85..de40f169a4e4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -237,7 +237,6 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, /* linux/mm/swapfile.c */ extern long total_swap_pages; -extern unsigned int nr_swapfiles; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); @@ -254,8 +253,6 @@ extern int can_share_swap_page(struct page *); extern int remove_exclusive_swap_page(struct page *); struct backing_dev_info; -extern spinlock_t swap_lock; - /* linux/mm/thrash.c */ extern struct mm_struct * swap_token_mm; extern void grab_swap_token(void); -- cgit v1.2.2 From 9580d85f9cdb076c4bfb467bc6c0d3c5e499957a Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:25 -0700 Subject: drivers/char/rtc.c: make 2 functions static The following functions can now become static: - rtc_interrupt() - rtc_get_rtc_time() Signed-off-by: Adrian Bunk Acked-by: Bernhard Walle Acked-by: Paul Gortmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b01fe004cb5e..91f597ad6acc 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -225,8 +225,6 @@ typedef struct rtc_task { int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); -void rtc_get_rtc_time(struct rtc_time *rtc_tm); -irqreturn_t rtc_interrupt(int irq, void *dev_id); #endif /* __KERNEL__ */ -- cgit v1.2.2