From 7c8265f51073bc8632a99de78d5fd19117ed78b7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 24 Jun 2006 14:50:29 -0700 Subject: Suspend infrastructure cleanup and extension Allow devices to participate in the suspend process more intimately, in particular, allow the final phase (with interrupts disabled) to also be open to normal devices, not just system devices. Also, allow classes to participate in device suspend. Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/power/main.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/power/main.c b/kernel/power/main.c index 6d295c776794..0c3ed6ac938e 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -57,6 +57,10 @@ static int suspend_prepare(suspend_state_t state) if (!pm_ops || !pm_ops->enter) return -EPERM; + error = device_prepare_suspend(PMSG_SUSPEND); + if (error) + return error; + pm_prepare_console(); disable_nonboot_cpus(); -- cgit v1.2.2 From f1cc0a894c963923b766eb2d455747495e6e982d Mon Sep 17 00:00:00 2001 From: David Brownell Date: Mon, 14 Aug 2006 23:11:08 -0700 Subject: PM: issue PM_EVENT_PRETHAW This patch is the first of this series that should actually change any behavior ... by issuing the new event, now tha the rest of the kernel is prepared to receive it. This converts the PM core to issue the new PRETHAW message, which the rest of the kernel is now ready to receive. Signed-off-by: David Brownell Cc: "Rafael J. Wysocki" Cc: Pavel Machek Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/power/disk.c | 4 ++-- kernel/power/swsusp.c | 9 ++++++++- kernel/power/user.c | 2 +- 3 files changed, 11 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index e13e74067845..a3c34fb14321 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -98,7 +98,7 @@ static void unprepare_processes(void) } /** - * pm_suspend_disk - The granpappy of power management. + * pm_suspend_disk - The granpappy of hibernation power management. * * If we're going through the firmware, then get it over with quickly. * @@ -207,7 +207,7 @@ static int software_resume(void) pr_debug("PM: Preparing devices for restore.\n"); - if ((error = device_suspend(PMSG_FREEZE))) { + if ((error = device_suspend(PMSG_PRETHAW))) { printk("Some devices failed to suspend\n"); swsusp_free(); goto Thaw; diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 17f669c83012..62752899b1a1 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -248,6 +248,9 @@ int swsusp_suspend(void) restore_processor_state(); Restore_highmem: restore_highmem(); + /* NOTE: device_power_up() is just a resume() for devices + * that suspended with irqs off ... no overall powerup. + */ device_power_up(); Enable_irqs: local_irq_enable(); @@ -257,8 +260,12 @@ Enable_irqs: int swsusp_resume(void) { int error; + local_irq_disable(); - if (device_power_down(PMSG_FREEZE)) + /* NOTE: device_power_down() is just a suspend() with irqs off; + * it has no special "power things down" semantics + */ + if (device_power_down(PMSG_PRETHAW)) printk(KERN_ERR "Some devices failed to power down, very bad\n"); /* We'll ignore saved state, but this gets preempt count (etc) right */ save_processor_state(); diff --git a/kernel/power/user.c b/kernel/power/user.c index 3f1539fbe48a..5a8d060d7909 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -191,7 +191,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, } down(&pm_sem); pm_prepare_console(); - error = device_suspend(PMSG_FREEZE); + error = device_suspend(PMSG_PRETHAW); if (!error) { error = swsusp_resume(); device_resume(); -- cgit v1.2.2 From 2bca293e56b6a8cd16bb6e70a09b2adac9c723b5 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 30 Aug 2006 13:54:36 -0700 Subject: PM: add kconfig option for deprecated .../power/state files Add a new PM_SYSFS_DEPRECATED config option to control whether or not the /sys/devices/.../power/state files are provided. This will make it easier to get rid of that mechanism when the time comes, and to verify that userspace tools work right without it. Signed-off-by: David Brownell Acked-by: Pavel Machek Signed-off-by: Greg Kroah-Hartman --- kernel/power/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel') diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 619ecabf7c58..1ed972070d19 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -53,6 +53,17 @@ config PM_TRACE CAUTION: this option will cause your machine's real-time clock to be set to an invalid time after a resume. +config PM_SYSFS_DEPRECATED + bool "Driver model /sys/devices/.../power/state files (DEPRECATED)" + depends on PM && SYSFS + default n + help + The driver model started out with a sysfs file intended to provide + a userspace hook for device power management. This feature has never + worked very well, except for limited testing purposes, and so it will + be removed. It's not clear that a generic mechanism could really + handle the wide variability of device power states; any replacements + are likely to be bus or driver specific. config SOFTWARE_SUSPEND bool "Software Suspend" -- cgit v1.2.2 From 1d3a82af45428c5e8deaa119cdeb79611ae46371 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 30 Aug 2006 14:09:47 -0700 Subject: PM: no suspend_prepare() phase Remove the new suspend_prepare() phase. It doesn't seem very usable, has never been tested, doesn't address fault cleanup, and would need a sibling resume_complete(); plus there are no real use cases. It could be restored later if those issues get resolved. Signed-off-by: David Brownell Cc: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- kernel/power/main.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/power/main.c b/kernel/power/main.c index 0c3ed6ac938e..6d295c776794 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -57,10 +57,6 @@ static int suspend_prepare(suspend_state_t state) if (!pm_ops || !pm_ops->enter) return -EPERM; - error = device_prepare_suspend(PMSG_SUSPEND); - if (error) - return error; - pm_prepare_console(); disable_nonboot_cpus(); -- cgit v1.2.2 From 2fbe7b25c8edaf2d10e6c1a4cc9f8afe714c4764 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 26 Sep 2006 10:52:27 +0200 Subject: [PATCH] i386/x86-64: Remove un/set_nmi_callback and reserve/release_lapic_nmi functions Removes the un/set_nmi_callback and reserve/release_lapic_nmi functions as they are no longer needed. The various subsystems are modified to register with the die_notifier instead. Also includes compile fixes by Andrew Morton. Signed-off-by: Don Zickus Signed-off-by: Andi Kleen --- kernel/sysctl.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 362a0cc37138..83f168361624 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -76,8 +76,6 @@ extern int compat_log; #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) int unknown_nmi_panic; -extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *, - void __user *, size_t *, loff_t *); #endif /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -628,7 +626,7 @@ static ctl_table kern_table[] = { .data = &unknown_nmi_panic, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = &proc_unknown_nmi_panic, + .proc_handler = &proc_dointvec, }, #endif #if defined(CONFIG_X86) -- cgit v1.2.2 From 407984f1af259b31957c7c05075a454a751bb801 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 26 Sep 2006 10:52:27 +0200 Subject: [PATCH] x86: Add abilty to enable/disable nmi watchdog with sysctl Adds a new /proc/sys/kernel/nmi call that will enable/disable the nmi watchdog. Signed-off-by: Don Zickus Signed-off-by: Andi Kleen --- kernel/sysctl.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 83f168361624..040de6bd74dd 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -76,6 +76,9 @@ extern int compat_log; #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) int unknown_nmi_panic; +int nmi_watchdog_enabled; +extern int proc_nmi_enabled(struct ctl_table *, int , struct file *, + void __user *, size_t *, loff_t *); #endif /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -628,6 +631,14 @@ static ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, + { + .ctl_name = KERN_NMI_WATCHDOG, + .procname = "nmi_watchdog", + .data = &nmi_watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_nmi_enabled, + }, #endif #if defined(CONFIG_X86) { -- cgit v1.2.2 From 8da5adda91df3d2fcc5300e68da491694c9af019 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Tue, 26 Sep 2006 10:52:27 +0200 Subject: [PATCH] x86: Allow users to force a panic on NMI To quote Alan Cox: The default Linux behaviour on an NMI of either memory or unknown is to continue operation. For many environments such as scientific computing it is preferable that the box is taken out and the error dealt with than an uncorrected parity/ECC error get propogated. A small number of systems do generate NMI's for bizarre random reasons such as power management so the default is unchanged. In other respects the new proc/sys entry works like the existing panic controls already in that directory. This is separate to the edac support - EDAC allows supported chipsets to handle ECC errors well, this change allows unsupported cases to at least panic rather than cause problems further down the line. Signed-off-by: Don Zickus Signed-off-by: Andi Kleen --- kernel/panic.c | 1 + kernel/sysctl.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 8010b9b17aca..d2db3e2209e0 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -21,6 +21,7 @@ #include int panic_on_oops; +int panic_on_unrecovered_nmi; int tainted; static int pause_on_oops; static int pause_on_oops_flag; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 040de6bd74dd..220e20564124 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -641,6 +641,14 @@ static ctl_table kern_table[] = { }, #endif #if defined(CONFIG_X86) + { + .ctl_name = KERN_PANIC_ON_NMI, + .procname = "panic_on_unrecovered_nmi", + .data = &panic_on_unrecovered_nmi, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, { .ctl_name = KERN_BOOTLOADER_TYPE, .procname = "bootloader_type", -- cgit v1.2.2 From 3cfc348bf90ffaa777c188652aa297f04eb94de8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 26 Sep 2006 10:52:28 +0200 Subject: [PATCH] x86: Add portable getcpu call For NUMA optimization and some other algorithms it is useful to have a fast to get the current CPU and node numbers in user space. x86-64 added a fast way to do this in a vsyscall. This adds a generic syscall for other architectures to make it a generic portable facility. I expect some of them will also implement it as a faster vsyscall. The cache is an optimization for the x86-64 vsyscall optimization. Since what the syscall returns is an approximation anyways and user space often wants very fast results it can be cached for some time. The norma methods to get this information in user space are relatively slow The vsyscall is in a better position to manage the cache because it has direct access to a fast time stamp (jiffies). For the generic syscall optimization it doesn't help much, but enforce a valid argument to keep programs portable I only added an i386 syscall entry for now. Other architectures can follow as needed. AK: Also added some cleanups from Andrew Morton Signed-off-by: Andi Kleen --- kernel/sys.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index e236f98f7ec5..3f894775488d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -2062,3 +2063,33 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, } return error; } + +asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep, + struct getcpu_cache __user *cache) +{ + int err = 0; + int cpu = raw_smp_processor_id(); + if (cpup) + err |= put_user(cpu, cpup); + if (nodep) + err |= put_user(cpu_to_node(cpu), nodep); + if (cache) { + /* + * The cache is not needed for this implementation, + * but make sure user programs pass something + * valid. vsyscall implementations can instead make + * good use of the cache. Only use t0 and t1 because + * these are available in both 32bit and 64bit ABI (no + * need for a compat_getcpu). 32bit has enough + * padding + */ + unsigned long t0, t1; + get_user(t0, &cache->t0); + get_user(t1, &cache->t1); + t0++; + t1++; + put_user(t0, &cache->t0); + put_user(t1, &cache->t1); + } + return err ? -EFAULT : 0; +} -- cgit v1.2.2 From 0cb91a2293648507886563ccb91979cfc94d6a4b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 26 Sep 2006 10:52:28 +0200 Subject: [PATCH] i386: Account spinlocks to the caller during profiling for !FP kernels This ports the algorithm from x86-64 (with improvements) to i386. Previously this only worked for frame pointer enabled kernels. But spinlocks have a very simple stack frame that can be manually analyzed. Do this. Signed-off-by: Andi Kleen --- kernel/spinlock.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/spinlock.c b/kernel/spinlock.c index fb524b009eef..9644a41e0bef 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -7,6 +7,11 @@ * * This file contains the spinlock/rwlock implementations for the * SMP and the DEBUG_SPINLOCK cases. (UP-nondebug inlines them) + * + * Note that some architectures have special knowledge about the + * stack frames of these functions in their profile_pc. If you + * change anything significant here that could change the stack + * frame contact the architecture maintainers. */ #include -- cgit v1.2.2 From 5a1b3999d6cb7ab87f1f3b1700bc91839fd6fa29 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 26 Sep 2006 10:52:34 +0200 Subject: [PATCH] x86: Some preparationary cleanup for stack trace - Remove unused all_contexts parameter No caller used it - Move skip argument into the structure (needed for followon patches) Cc: mingo@elte.hu Signed-off-by: Andi Kleen --- kernel/lockdep.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 9bad17884513..900b4cb1a024 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -224,7 +224,10 @@ static int save_trace(struct stack_trace *trace) trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; trace->entries = stack_trace + nr_stack_trace_entries; - save_stack_trace(trace, NULL, 0, 3); + trace->skip = 3; + trace->all_contexts = 0; + + save_stack_trace(trace, NULL); trace->max_entries = trace->nr_entries; -- cgit v1.2.2 From 3fa7c794fe4dc127f7fac3fad4d13628e68f89ce Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 26 Sep 2006 10:52:34 +0200 Subject: [PATCH] Avoid recursion in lockdep when stack tracer takes locks The new dwarf2 unwinder needs to take locks to do backtraces inside modules. This patch makes sure lockdep which calls stacktrace is not reentered. Thanks to Ingo for suggesting this simpler approach. Cc: mingo@elte.hu Signed-off-by: Andi Kleen --- kernel/lockdep.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 900b4cb1a024..c088e5542e84 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -227,7 +227,11 @@ static int save_trace(struct stack_trace *trace) trace->skip = 3; trace->all_contexts = 0; + /* Make sure to not recurse in case the the unwinder needs to tak +e locks. */ + lockdep_off(); save_stack_trace(trace, NULL); + lockdep_on(); trace->max_entries = trace->nr_entries; -- cgit v1.2.2 From 0a4254058037eb172758961d0a5b94f4320a1425 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 26 Sep 2006 10:52:38 +0200 Subject: [PATCH] Add the canary field to the PDA area and the task struct This patch adds the per thread cookie field to the task struct and the PDA. Also it makes sure that the PDA value gets the new cookie value at context switch, and that a new task gets a new cookie at task creation time. Signed-off-by: Arjan van Ven Signed-off-by: Ingo Molnar Signed-off-by: Andi Kleen CC: Andi Kleen --- kernel/fork.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index f9b014e3e700..a0dad84567c9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -175,6 +176,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->thread_info = ti; setup_thread_stack(tsk, orig); +#ifdef CONFIG_CC_STACKPROTECTOR + tsk->stack_canary = get_random_int(); +#endif + /* One for us, one for whoever does the "release_task()" (usually parent) */ atomic_set(&tsk->usage,2); atomic_set(&tsk->fs_excl, 0); -- cgit v1.2.2 From 3162f751d04086a9d006342de63ac8f44fe0f72a Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Tue, 26 Sep 2006 10:52:39 +0200 Subject: [PATCH] Add the __stack_chk_fail() function GCC emits a call to a __stack_chk_fail() function when the stack canary is not matching the expected value. Since this is a bad security issue; lets panic the kernel rather than limping along; the kernel really can't be trusted anymore when this happens. Signed-off-by: Arjan van de Ven Signed-off-by: Ingo Molnar Signed-off-by: Andi Kleen CC: Andi Kleen --- kernel/panic.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index d2db3e2209e0..6ceb664fb52a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -271,3 +271,15 @@ void oops_exit(void) { do_oops_enter_exit(); } + +#ifdef CONFIG_CC_STACKPROTECTOR +/* + * Called when gcc's -fstack-protector feature is used, and + * gcc detects corruption of the on-stack canary value + */ +void __stack_chk_fail(void) +{ + panic("stack-protector: Kernel stack is corrupted"); +} +EXPORT_SYMBOL(__stack_chk_fail); +#endif -- cgit v1.2.2 From adf1423698f00d00b267f7dca8231340ce7d65ef Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 26 Sep 2006 10:52:41 +0200 Subject: [PATCH] i386/x86-64: Work around gcc bug with noreturn functions in unwinder Current gcc generates calls not jumps to noreturn functions. When that happens the return address can point to the next function, which confuses the unwinder. This patch works around it by marking asynchronous exception frames in contrast normal call frames in the unwind information. Then teach the unwinder to decode this. For normal call frames the unwinder now subtracts one from the address which avoids this problem. The standard libgcc unwinder uses the same trick. It doesn't include adjustment of the printed address (i.e. for the original example, it'd still be kernel_math_error+0 that gets displayed, but the unwinder wouldn't get confused anymore. This only works with binutils 2.6.17+ and some versions of H.J.Lu's 2.6.16 unfortunately because earlier binutils don't support .cfi_signal_frame [AK: added automatic detection of the new binutils and wrote description] Signed-off-by: Jan Beulich Signed-off-by: Andi Kleen --- kernel/unwind.c | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/unwind.c b/kernel/unwind.c index f69c804c8e62..3430475fcd88 100644 --- a/kernel/unwind.c +++ b/kernel/unwind.c @@ -603,6 +603,7 @@ int unwind(struct unwind_frame_info *frame) #define FRAME_REG(r, t) (((t *)frame)[reg_info[r].offs]) const u32 *fde = NULL, *cie = NULL; const u8 *ptr = NULL, *end = NULL; + unsigned long pc = UNW_PC(frame) - frame->call_frame; unsigned long startLoc = 0, endLoc = 0, cfa; unsigned i; signed ptrType = -1; @@ -612,7 +613,7 @@ int unwind(struct unwind_frame_info *frame) if (UNW_PC(frame) == 0) return -EINVAL; - if ((table = find_table(UNW_PC(frame))) != NULL + if ((table = find_table(pc)) != NULL && !(table->size & (sizeof(*fde) - 1))) { unsigned long tableSize = table->size; @@ -647,7 +648,7 @@ int unwind(struct unwind_frame_info *frame) ptrType & DW_EH_PE_indirect ? ptrType : ptrType & (DW_EH_PE_FORM|DW_EH_PE_signed)); - if (UNW_PC(frame) >= startLoc && UNW_PC(frame) < endLoc) + if (pc >= startLoc && pc < endLoc) break; cie = NULL; } @@ -657,16 +658,28 @@ int unwind(struct unwind_frame_info *frame) state.cieEnd = ptr; /* keep here temporarily */ ptr = (const u8 *)(cie + 2); end = (const u8 *)(cie + 1) + *cie; + frame->call_frame = 1; if ((state.version = *ptr) != 1) cie = NULL; /* unsupported version */ else if (*++ptr) { /* check if augmentation size is first (and thus present) */ if (*ptr == 'z') { - /* check for ignorable (or already handled) - * nul-terminated augmentation string */ - while (++ptr < end && *ptr) - if (strchr("LPR", *ptr) == NULL) + while (++ptr < end && *ptr) { + switch(*ptr) { + /* check for ignorable (or already handled) + * nul-terminated augmentation string */ + case 'L': + case 'P': + case 'R': + continue; + case 'S': + frame->call_frame = 0; + continue; + default: break; + } + break; + } } if (ptr >= end || *ptr) cie = NULL; @@ -755,7 +768,7 @@ int unwind(struct unwind_frame_info *frame) state.org = startLoc; memcpy(&state.cfa, &badCFA, sizeof(state.cfa)); /* process instructions */ - if (!processCFI(ptr, end, UNW_PC(frame), ptrType, &state) + if (!processCFI(ptr, end, pc, ptrType, &state) || state.loc > endLoc || state.regs[retAddrReg].where == Nowhere || state.cfa.reg >= ARRAY_SIZE(reg_info) @@ -763,6 +776,11 @@ int unwind(struct unwind_frame_info *frame) || state.cfa.offs % sizeof(unsigned long)) return -EIO; /* update frame */ +#ifndef CONFIG_AS_CFI_SIGNAL_FRAME + if(frame->call_frame + && !UNW_DEFAULT_RA(state.regs[retAddrReg], state.dataAlign)) + frame->call_frame = 0; +#endif cfa = FRAME_REG(state.cfa.reg, unsigned long) + state.cfa.offs; startLoc = min((unsigned long)UNW_SP(frame), cfa); endLoc = max((unsigned long)UNW_SP(frame), cfa); @@ -866,6 +884,7 @@ int unwind_init_frame_info(struct unwind_frame_info *info, /*const*/ struct pt_regs *regs) { info->task = tsk; + info->call_frame = 0; arch_unw_init_frame_info(info, regs); return 0; @@ -879,6 +898,7 @@ int unwind_init_blocked(struct unwind_frame_info *info, struct task_struct *tsk) { info->task = tsk; + info->call_frame = 0; arch_unw_init_blocked(info); return 0; @@ -894,6 +914,7 @@ int unwind_init_running(struct unwind_frame_info *info, void *arg) { info->task = current; + info->call_frame = 0; return arch_unwind_init_running(info, callback, arg); } -- cgit v1.2.2 From d33b6fba2c4350651f3f61ff2ab858a2f116e9a4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 30 Jun 2006 02:31:24 -0700 Subject: Resources: insert identical resources above existing resources If you have two resources which aree exactly the same size, insert_resource() currently inserts the new one below the existing one. This is wrong because there's no way to insert a resource of the same size above an existing one. I took this opportunity to rewrite the initial loop to be a for-loop instead of a goto-loop and fix the documentation. Signed-off-by: Matthew Wilcox Cc: Ivan Kokshaysky Cc: Dominik Brodowski Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- kernel/resource.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/resource.c b/kernel/resource.c index 46286434af80..9db38a1a7520 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -344,12 +344,11 @@ EXPORT_SYMBOL(allocate_resource); * * Returns 0 on success, -EBUSY if the resource can't be inserted. * - * This function is equivalent of request_resource when no conflict + * This function is equivalent to request_resource when no conflict * happens. If a conflict happens, and the conflicting resources * entirely fit within the range of the new resource, then the new - * resource is inserted and the conflicting resources become childs of - * the new resource. Otherwise the new resource becomes the child of - * the conflicting resource + * resource is inserted and the conflicting resources become children of + * the new resource. */ int insert_resource(struct resource *parent, struct resource *new) { @@ -357,20 +356,21 @@ int insert_resource(struct resource *parent, struct resource *new) struct resource *first, *next; write_lock(&resource_lock); - begin: - result = 0; - first = __request_resource(parent, new); - if (!first) - goto out; - result = -EBUSY; - if (first == parent) - goto out; + for (;; parent = first) { + result = 0; + first = __request_resource(parent, new); + if (!first) + goto out; - /* Resource fully contained by the clashing resource? Recurse into it */ - if (first->start <= new->start && first->end >= new->end) { - parent = first; - goto begin; + result = -EBUSY; + if (first == parent) + goto out; + + if ((first->start > new->start) || (first->end < new->end)) + break; + if ((first->start == new->start) && (first->end == new->end)) + break; } for (next = first; ; next = next->sibling) { -- cgit v1.2.2 From 0ec76a110f432e98277e464b82ace8dd66571689 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:15 -0700 Subject: [PATCH] NOMMU: Check that access_process_vm() has a valid target Check that access_process_vm() is accessing a valid mapping in the target process. This limits ptrace() accesses and accesses through /proc//maps to only those regions actually mapped by a program. Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 54 ------------------------------------------------------ 1 file changed, 54 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 9a111f70145c..8aad0331d82e 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -241,60 +241,6 @@ int ptrace_detach(struct task_struct *child, unsigned int data) return 0; } -/* - * Access another process' address space. - * Source/target buffer must be kernel space, - * Do not walk the page table directly, use get_user_pages - */ - -int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write) -{ - struct mm_struct *mm; - struct vm_area_struct *vma; - struct page *page; - void *old_buf = buf; - - mm = get_task_mm(tsk); - if (!mm) - return 0; - - down_read(&mm->mmap_sem); - /* ignore errors, just check how much was sucessfully transfered */ - while (len) { - int bytes, ret, offset; - void *maddr; - - ret = get_user_pages(tsk, mm, addr, 1, - write, 1, &page, &vma); - if (ret <= 0) - break; - - bytes = len; - offset = addr & (PAGE_SIZE-1); - if (bytes > PAGE_SIZE-offset) - bytes = PAGE_SIZE-offset; - - maddr = kmap(page); - if (write) { - copy_to_user_page(vma, page, addr, - maddr + offset, buf, bytes); - set_page_dirty_lock(page); - } else { - copy_from_user_page(vma, page, addr, - buf, maddr + offset, bytes); - } - kunmap(page); - page_cache_release(page); - len -= bytes; - buf += bytes; - addr += bytes; - } - up_read(&mm->mmap_sem); - mmput(mm); - - return buf - old_buf; -} - int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; -- cgit v1.2.2 From f269fdd1829acc5e53bf57b145003e5733133f2b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 27 Sep 2006 01:50:23 -0700 Subject: [PATCH] NOMMU: move the fallback arch_vma_name() to a sensible place Move the fallback arch_vma_name() to a sensible place (kernel/signal.c). Currently it's in fs/proc/task_mmu.c, a file that is dependent on both CONFIG_PROC_FS and CONFIG_MMU being enabled, but it's used from kernel/signal.c from where it is called unconditionally. [akpm@osdl.org: build fix] Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/signal.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index bfdb5686fa3e..05853a7337e3 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2577,6 +2577,11 @@ asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize) } #endif /* __ARCH_WANT_SYS_RT_SIGSUSPEND */ +__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + void __init signals_init(void) { sigqueue_cachep = -- cgit v1.2.2 From 8e18e2941c53416aa219708e7dcad21fb4bd6794 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:46 -0700 Subject: [PATCH] inode_diet: Replace inode.u.generic_ip with inode.i_private The following patches reduce the size of the VFS inode structure by 28 bytes on a UP x86. (It would be more on an x86_64 system). This is a 10% reduction in the inode size on a UP kernel that is configured in a production mode (i.e., with no spinlock or other debugging functions enabled; if you want to save memory taken up by in-core inodes, the first thing you should do is disable the debugging options; they are responsible for a huge amount of bloat in the VFS inode structure). This patch: The filesystem or device-specific pointer in the inode is inside a union, which is pretty pointless given that all 30+ users of this field have been using the void pointer. Get rid of the union and rename it to i_private, with a comment to explain who is allowed to use the void pointer. This is just a cleanup, but it allows us to reuse the union 'u' for something something where the union will actually be used. [judith@osdl.org: powerpc build fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Judith Lebzelter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/relay.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/relay.c b/kernel/relay.c index 33345e73485c..85786ff2a4f9 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -669,7 +669,7 @@ EXPORT_SYMBOL_GPL(relay_flush); */ static int relay_file_open(struct inode *inode, struct file *filp) { - struct rchan_buf *buf = inode->u.generic_ip; + struct rchan_buf *buf = inode->i_private; kref_get(&buf->kref); filp->private_data = buf; -- cgit v1.2.2 From ba52de123d454b57369f291348266d86f4b35070 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 27 Sep 2006 01:50:49 -0700 Subject: [PATCH] inode-diet: Eliminate i_blksize from the inode structure This eliminates the i_blksize field from struct inode. Filesystems that want to provide a per-inode st_blksize can do so by providing their own getattr routine instead of using the generic_fillattr() function. Note that some filesystems were providing pretty much random (and incorrect) values for i_blksize. [bunk@stusta.de: cleanup] [akpm@osdl.org: generic_fillattr() fix] Signed-off-by: "Theodore Ts'o" Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index cff41511269f..1b32c2c04c15 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -289,7 +289,6 @@ static struct inode *cpuset_new_inode(mode_t mode) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info; -- cgit v1.2.2 From b89a81712f486e4f7a606987413e387605fdeaf4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:04 -0700 Subject: [PATCH] sysctl: Allow /proc/sys without sys_sysctl Since sys_sysctl is deprecated start allow it to be compiled out. This should catch any remaining user space code that cares, and paves the way for further sysctl cleanups. [akpm@osdl.org: If sys_sysctl() is not compiled-in, emit a warning] Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 113 +++++++++++++++++++------------------------------------- 1 file changed, 38 insertions(+), 75 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index bcb3a181dbb2..8bfa7d117c54 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -137,8 +137,11 @@ extern int no_unaligned_warning; extern int max_lock_depth; #endif -static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t, - ctl_table *, void **); +#ifdef CONFIG_SYSCTL_SYSCALL +static int parse_table(int __user *, int, void __user *, size_t __user *, + void __user *, size_t, ctl_table *, void **); +#endif + static int proc_doutsstring(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos); @@ -165,7 +168,7 @@ int sysctl_legacy_va_layout; /* /proc declarations: */ -#ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_SYSCTL static ssize_t proc_readsys(struct file *, char __user *, size_t, loff_t *); static ssize_t proc_writesys(struct file *, const char __user *, size_t, loff_t *); @@ -1166,12 +1169,13 @@ static void start_unregistering(struct ctl_table_header *p) void __init sysctl_init(void) { -#ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_SYSCTL register_proc_table(root_table, proc_sys_root, &root_table_header); init_irq_proc(); #endif } +#ifdef CONFIG_SYSCTL_SYSCALL int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen) { @@ -1225,6 +1229,7 @@ asmlinkage long sys_sysctl(struct __sysctl_args __user *args) unlock_kernel(); return error; } +#endif /* CONFIG_SYSCTL_SYSCALL */ /* * ctl_perm does NOT grant the superuser all rights automatically, because @@ -1251,6 +1256,7 @@ static inline int ctl_perm(ctl_table *table, int op) return test_perm(table->mode, op); } +#ifdef CONFIG_SYSCTL_SYSCALL static int parse_table(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen, @@ -1340,6 +1346,7 @@ int do_sysctl_strategy (ctl_table *table, } return 0; } +#endif /* CONFIG_SYSCTL_SYSCALL */ /** * register_sysctl_table - register a sysctl hierarchy @@ -1427,7 +1434,7 @@ struct ctl_table_header *register_sysctl_table(ctl_table * table, else list_add_tail(&tmp->ctl_entry, &root_table_header.ctl_entry); spin_unlock(&sysctl_lock); -#ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_SYSCTL register_proc_table(table, proc_sys_root, tmp); #endif return tmp; @@ -1445,18 +1452,31 @@ void unregister_sysctl_table(struct ctl_table_header * header) might_sleep(); spin_lock(&sysctl_lock); start_unregistering(header); -#ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_SYSCTL unregister_proc_table(header->ctl_table, proc_sys_root); #endif spin_unlock(&sysctl_lock); kfree(header); } +#else /* !CONFIG_SYSCTL */ +struct ctl_table_header * register_sysctl_table(ctl_table * table, + int insert_at_head) +{ + return NULL; +} + +void unregister_sysctl_table(struct ctl_table_header * table) +{ +} + +#endif /* CONFIG_SYSCTL */ + /* * /proc/sys support */ -#ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_SYSCTL /* Scan the sysctl entries in table and add them all into /proc */ static void register_proc_table(ctl_table * table, struct proc_dir_entry *root, void *set) @@ -2318,6 +2338,7 @@ int proc_doulongvec_ms_jiffies_minmax(ctl_table *table, int write, #endif /* CONFIG_PROC_FS */ +#ifdef CONFIG_SYSCTL_SYSCALL /* * General sysctl support routines */ @@ -2460,11 +2481,19 @@ int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen, return 1; } -#else /* CONFIG_SYSCTL */ +#else /* CONFIG_SYSCTL_SYSCALL */ asmlinkage long sys_sysctl(struct __sysctl_args __user *args) { + static int msg_count; + + if (msg_count < 5) { + msg_count++; + printk(KERN_INFO + "warning: process `%s' used the removed sysctl " + "system call\n", current->comm); + } return -ENOSYS; } @@ -2496,73 +2525,7 @@ int sysctl_ms_jiffies(ctl_table *table, int __user *name, int nlen, return -ENOSYS; } -int proc_dostring(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_bset(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_minmax(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_userhz_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_dointvec_ms_jiffies(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_doulongvec_minmax(ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -int proc_doulongvec_ms_jiffies_minmax(ctl_table *table, int write, - struct file *filp, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - -struct ctl_table_header * register_sysctl_table(ctl_table * table, - int insert_at_head) -{ - return NULL; -} - -void unregister_sysctl_table(struct ctl_table_header * table) -{ -} - -#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_SYSCTL_SYSCALL */ /* * No sense putting this after each symbol definition, twice, -- cgit v1.2.2 From c18258c6f0848f97e85287f6271c511a092bb784 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:06 -0700 Subject: [PATCH] pid: Implement transfer_pid and use it to simplify de_thread In de_thread we move pids from one process to another, a rather ugly case. The function transfer_pid makes it clear what we are doing, and makes the action atomic. This is useful we ever want to atomically traverse the process group and session lists, in a rcu safe manner. Even if the atomic properties this change should be a win as transfer_pid should be less code to execute than executing both attach_pid and detach_pid, and this should make de_thread slightly smaller as only a single function call needs to be emitted. The only downside is that the code might be slower to execute as the odds are against transfer_pid being in cache. Signed-off-by: Eric W. Biederman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/pid.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/pid.c b/kernel/pid.c index 93e212f20671..6db82b68e2f8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -252,6 +252,15 @@ void fastcall detach_pid(struct task_struct *task, enum pid_type type) free_pid(pid); } +/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ +void fastcall transfer_pid(struct task_struct *old, struct task_struct *new, + enum pid_type type) +{ + new->pids[type].pid = old->pids[type].pid; + hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node); + old->pids[type].pid = NULL; +} + struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; -- cgit v1.2.2 From 65800ac77e080cf159d6c1207b6886e18f22bc08 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 27 Sep 2006 01:51:11 -0700 Subject: [PATCH] pid: remove temporary debug code in attach_pid With the patches flying between Oleg and myself somehow this temporary debug code got left in pid.c. It was never intended to make it to the stable kernel. Signed-off-by: Eric W. Biederman Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/pid.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel') diff --git a/kernel/pid.c b/kernel/pid.c index 6db82b68e2f8..8387e8c68193 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -223,9 +223,6 @@ int fastcall attach_pid(struct task_struct *task, enum pid_type type, int nr) struct pid_link *link; struct pid *pid; - WARN_ON(!task->pid); /* to be removed soon */ - WARN_ON(!nr); /* to be removed soon */ - link = &task->pids[type]; link->pid = pid = find_pid(nr); hlist_add_head_rcu(&link->node, &pid->tasks[type]); -- cgit v1.2.2