sched: Always check the integrity of the canary
Subsystems (8)
v4 cover sched: Always check the integrity of the canary
Hi Peter,
Please let me know if this iteration is satisfactory. Thanks.
Currently in the event of a stack overrun a call to schedule() does not check for this type of corruption. This corruption is often silent and can go unnoticed. However once the corrupted region is examined at a later stage, the outcome is undefined and often results in a sporadic page fault which cannot be handled.
The first patch adds a canary to init_task's end of stack. While the second patch provides a helper to determine the integrity of the canary. The third checks for a stack overrun and takes appropriate action since the damage is already done, there is no point in continuing.
Changes since v3:
* Add Michael Ellerman's Acked-by to first patch (for powerpc)
* Fix compiler error - Michael Ellerman
* Set default Kconfig option to n - Michael Ellerman
Changes since v2:
* Use BUG_ON in schedule_debug() - Peter Zijlstra
* Use a more explicit function
name for setting the canary - Chuck Ebbert
Changes since v1:
* Rebased against v3.17-rc4
* Add a canary to init_task - Oleg Nesterov
* Fix various code formatting issues - Peter Zijlstra
* Introduce Kconfig option - Peter Zijlstra
Aaron Tomlin (3):
init/main.c: Give init_task a canary
sched: Add helper for task stack page overrun checking
sched: BUG when stack end location is over written
arch/powerpc/mm/fault.c | 5 +---- arch/x86/mm/fault.c | 5 +---- include/linux/sched.h | 4 ++++ init/main.c | 1 + kernel/fork.c | 12 +++++++++--- kernel/sched/core.c | 3 +++ kernel/trace/trace_stack.c | 4 +--- lib/Kconfig.debug | 12 ++++++++++++ 8 files changed, 32 insertions(+), 14 deletions(-)
Signature · 1 line
1.9.3
PATCH v4 1/3 init/main.c: Give init_task a canary
Tasks get their end of stack set to STACK_END_MAGIC with the aim to catch stack overruns. Currently this feature does not apply to init_task. This patch removes this restriction.
Note that a similar patch was posted by Prarit Bhargava [1] some time ago but was never merged.
[1]: http://marc.info/?l=linux-kernel&m=127144305403241&w=2
--- arch/powerpc/mm/fault.c | 3 +-- arch/x86/mm/fault.c | 3 +-- include/linux/sched.h | 2 ++ init/main.c | 1 + kernel/fork.c | 12 +++++++++--- kernel/trace/trace_stack.c | 4 +--- 6 files changed, 15 insertions(+), 10 deletions(-)
arch/powerpc/mm/fault.c +1 -2
@@ -30,7 +30,6 @@#include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/perf_event.h> -#include <linux/magic.h> #include <linux/ratelimit.h> #include <linux/context_tracking.h>
@@ -538,7 +537,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) regs->nip); stackend =end_of_stack (current); -if (current != &init_task && *stackend !=STACK_END_MAGIC ) +if (*stackend !=STACK_END_MAGIC )printk (KERN_ALERT "Thread overran stack, or stack corrupted\n" );die ("Kernel access of bad area" , regs, sig);
arch/x86/mm/fault.c +1 -2
@@ -3,7 +3,6 @@* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ -#include <linux/magic.h> /* STACK_END_MAGIC */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/module.h> /* search_exception_table */
@@ -710,7 +709,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,show_fault_oops (regs, error_code, address); stackend =end_of_stack (tsk); -if (tsk != &init_task && *stackend !=STACK_END_MAGIC ) +if (*stackend !=STACK_END_MAGIC )printk (KERN_EMERG "Thread overran stack, or stack corrupted\n" ); tsk->thread.cr2 = address;
include/linux/sched.h +2 -0
@@ -57,6 +57,7 @@ struct sched_param {#include <linux/llist.h> #include <linux/uidgid.h> #include <linux/gfp.h> +#include <linux/magic.h> #include <asm/processor.h>
@@ -2636,6 +2637,7 @@ static inline unsigned long stack_not_used(struct task_struct *p) return (unsigned long)n - (unsigned long)end_of_stack(p); }#endif +extern void set_task_stack_end_magic (struct task_struct *tsk);/* set thread flags in other task's structures * - see asm/thread_info.h for TIF_xxxx flags available
init/main.c +1 -0
@@ -508,6 +508,7 @@ asmlinkage __visible void __init start_kernel(void)* lockdep hash: */ lockdep_init (); +set_task_stack_end_magic (&init_task);smp_setup_processor_id ();debug_objects_early_init ();
kernel/fork.c +9 -3
@@ -294,11 +294,18 @@ int __weak arch_dup_task_struct(struct task_struct *dst,return 0 ; } +void set_task_stack_end_magic (struct task_struct *tsk) +{ +unsigned long *stackend; + + stackend =end_of_stack (tsk); + *stackend =STACK_END_MAGIC ;/* for overflow detection */ +} +static struct task_struct *dup_task_struct (struct task_struct *orig) {struct task_struct *tsk;struct thread_info *ti; -unsigned long *stackend;int node =tsk_fork_get_node (orig);int err;
@@ -328,8 +335,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)setup_thread_stack (tsk, orig);clear_user_return_notifier (tsk);clear_tsk_need_resched (tsk); - stackend =end_of_stack (tsk); - *stackend =STACK_END_MAGIC ;/* for overflow detection */ +set_task_stack_end_magic (tsk);#ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary =get_random_int ();
kernel/trace/trace_stack.c +1 -3
@@ -13,7 +13,6 @@#include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> -#include <linux/magic.h> #include <asm/setup.h>
@@ -171,8 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } -if ((current != &init_task && - *(end_of_stack (current)) !=STACK_END_MAGIC )) { +if (*end_of_stack (current) !=STACK_END_MAGIC ) {print_max_stack ();BUG (); }
Signature · 1 line
1.9.3
Re: [PATCH v4 1/3] init/main.c: Give init_task a canary
Quoted 5 lines · Aaron Tomlin
Tasks get their end of stack set to
STACK_END_MAGICwith the aim to catch stack overruns. Currently this feature does not apply toinit_task. This patch removes this restriction.
Quoted 7 lines
Note that a similar patch was posted by Prarit Bhargava [1] some time ago but was never merged.
[1]: http://marc.info/?l=linux-kernel&m=127144305403241&w=2
Signed-off-by Aaron Tomlin <[email protected]>Acked-by Michael Ellerman <[email protected]>
tip-bot for Aaron Tomlin
merge bot[tip:sched/core] init/main.c: Give init_task a canary
In reply to Aaron Tomlininit/main.c: Give init_task a canary
Commit-ID: d4311ff1a8da48d609db9500f121c15580dfeeb7 Gitweb: http://git.kernel.org/tip/d4311ff1a8da48d609db9500f121c15580dfeeb7 Author: Aaron Tomlin <[email protected]> AuthorDate: Fri, 12 Sep 2014 14:16:17 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 19 Sep 2014 12:35:22 +0200
init/main.c: Give init_task a canary
Tasks get their end of stack set to STACK_END_MAGIC with the aim to catch stack overruns. Currently this feature does not apply to init_task. This patch removes this restriction.
Note that a similar patch was posted by Prarit Bhargava some time ago but was never merged:
http://marc.info/?l=linux-kernel&m=127144305403241&w=2
--- arch/powerpc/mm/fault.c | 3 +-- arch/x86/mm/fault.c | 3 +-- include/linux/sched.h | 2 ++ init/main.c | 1 + kernel/fork.c | 12 +++++++++--- kernel/trace/trace_stack.c | 4 +--- 6 files changed, 15 insertions(+), 10 deletions(-)
arch/powerpc/mm/fault.c +1 -2
@@ -30,7 +30,6 @@#include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/perf_event.h> -#include <linux/magic.h> #include <linux/ratelimit.h> #include <linux/context_tracking.h>
@@ -538,7 +537,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) regs->nip); stackend =end_of_stack (current); -if (current != &init_task && *stackend !=STACK_END_MAGIC ) +if (*stackend !=STACK_END_MAGIC )printk (KERN_ALERT "Thread overran stack, or stack corrupted\n" );die ("Kernel access of bad area" , regs, sig);
arch/x86/mm/fault.c +1 -2
@@ -3,7 +3,6 @@* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ -#include <linux/magic.h> /* STACK_END_MAGIC */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/module.h> /* search_exception_table */
@@ -710,7 +709,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,show_fault_oops (regs, error_code, address); stackend =end_of_stack (tsk); -if (tsk != &init_task && *stackend !=STACK_END_MAGIC ) +if (*stackend !=STACK_END_MAGIC )printk (KERN_EMERG "Thread overran stack, or stack corrupted\n" ); tsk->thread.cr2 = address;
include/linux/sched.h +2 -0
@@ -57,6 +57,7 @@ struct sched_param {#include <linux/llist.h> #include <linux/uidgid.h> #include <linux/gfp.h> +#include <linux/magic.h> #include <asm/processor.h>
@@ -2638,6 +2639,7 @@ static inline unsigned long stack_not_used(struct task_struct *p) return (unsigned long)n - (unsigned long)end_of_stack(p); }#endif +extern void set_task_stack_end_magic (struct task_struct *tsk);/* set thread flags in other task's structures * - see asm/thread_info.h for TIF_xxxx flags available
init/main.c +1 -0
@@ -508,6 +508,7 @@ asmlinkage __visible void __init start_kernel(void)* lockdep hash: */ lockdep_init (); +set_task_stack_end_magic (&init_task);smp_setup_processor_id ();debug_objects_early_init ();
kernel/fork.c +9 -3
@@ -294,11 +294,18 @@ int __weak arch_dup_task_struct(struct task_struct *dst,return 0 ; } +void set_task_stack_end_magic (struct task_struct *tsk) +{ +unsigned long *stackend; + + stackend =end_of_stack (tsk); + *stackend =STACK_END_MAGIC ;/* for overflow detection */ +} +static struct task_struct *dup_task_struct (struct task_struct *orig) {struct task_struct *tsk;struct thread_info *ti; -unsigned long *stackend;int node =tsk_fork_get_node (orig);int err;
@@ -328,8 +335,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)setup_thread_stack (tsk, orig);clear_user_return_notifier (tsk);clear_tsk_need_resched (tsk); - stackend =end_of_stack (tsk); - *stackend =STACK_END_MAGIC ;/* for overflow detection */ +set_task_stack_end_magic (tsk);#ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary =get_random_int ();
kernel/trace/trace_stack.c +1 -3
@@ -13,7 +13,6 @@#include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> -#include <linux/magic.h> #include <asm/setup.h>
@@ -171,8 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } -if ((current != &init_task && - *(end_of_stack (current)) !=STACK_END_MAGIC )) { +if (*end_of_stack (current) !=STACK_END_MAGIC ) {print_max_stack ();BUG (); }
PATCH v4 2/3 sched: Add helper for task stack page overrun checking
In reply to Aaron TomlinThis facility is used in a few places so let's introduce a helper function to improve code readability.
--- arch/powerpc/mm/fault.c | 4 +--- arch/x86/mm/fault.c | 4 +--- include/linux/sched.h | 2 ++ kernel/trace/trace_stack.c | 2 +- 4 files changed, 5 insertions(+), 7 deletions(-)
arch/powerpc/mm/fault.c +1 -3
@@ -507,7 +507,6 @@ bail:void bad_page_fault (struct pt_regs *regs,unsigned long address,int sig) {const struct exception_table_entry *entry; -unsigned long *stackend;/* Are we prepared to handle this fault? */ if ((entry =search_exception_tables (regs->nip)) !=NULL ) {
@@ -536,8 +535,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)printk (KERN_ALERT "Faulting instruction address: 0x%08lx\n" , regs->nip); - stackend =end_of_stack (current); -if (*stackend !=STACK_END_MAGIC ) +if (task_stack_end_corrupted (current))printk (KERN_ALERT "Thread overran stack, or stack corrupted\n" );die ("Kernel access of bad area" , regs, sig);
arch/x86/mm/fault.c +1 -3
@@ -648,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; -unsigned long *stackend;unsigned long flags;int sig;
@@ -708,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,show_fault_oops (regs, error_code, address); - stackend =end_of_stack (tsk); -if (*stackend !=STACK_END_MAGIC ) +if (task_stack_end_corrupted (tsk))printk (KERN_EMERG "Thread overran stack, or stack corrupted\n" ); tsk->thread.cr2 = address;
include/linux/sched.h +2 -0
@@ -2615,6 +2615,8 @@ static inline unsigned long *end_of_stack(struct task_struct *p) }#endif +#define task_stack_end_corrupted (task) \ + (*(end_of_stack(task)) != STACK_END_MAGIC)static inline int object_is_on_stack (void *obj) {
kernel/trace/trace_stack.c +1 -1
@@ -170,7 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } -if (*end_of_stack (current) !=STACK_END_MAGIC ) { +if (task_stack_end_corrupted (current)) {print_max_stack ();BUG (); }
Signature · 1 line
1.9.3
tip-bot for Aaron Tomlin
merge bot[tip:sched/core] sched: Add helper for task stack page overrun checking
sched: Add helper for task stack page overrun checking
Commit-ID: a70857e46dd13e87ae06bf0e64cb6a2d4f436265 Gitweb: http://git.kernel.org/tip/a70857e46dd13e87ae06bf0e64cb6a2d4f436265 Author: Aaron Tomlin <[email protected]> AuthorDate: Fri, 12 Sep 2014 14:16:18 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 19 Sep 2014 12:35:23 +0200
sched: Add helper for task stack page overrun checking
This facility is used in a few places so let's introduce a helper function to improve code readability.
--- arch/powerpc/mm/fault.c | 4 +--- arch/x86/mm/fault.c | 4 +--- include/linux/sched.h | 2 ++ kernel/trace/trace_stack.c | 2 +- 4 files changed, 5 insertions(+), 7 deletions(-)
arch/powerpc/mm/fault.c +1 -3
@@ -507,7 +507,6 @@ bail:void bad_page_fault (struct pt_regs *regs,unsigned long address,int sig) {const struct exception_table_entry *entry; -unsigned long *stackend;/* Are we prepared to handle this fault? */ if ((entry =search_exception_tables (regs->nip)) !=NULL ) {
@@ -536,8 +535,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)printk (KERN_ALERT "Faulting instruction address: 0x%08lx\n" , regs->nip); - stackend =end_of_stack (current); -if (*stackend !=STACK_END_MAGIC ) +if (task_stack_end_corrupted (current))printk (KERN_ALERT "Thread overran stack, or stack corrupted\n" );die ("Kernel access of bad area" , regs, sig);
arch/x86/mm/fault.c +1 -3
@@ -648,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; -unsigned long *stackend;unsigned long flags;int sig;
@@ -708,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,show_fault_oops (regs, error_code, address); - stackend =end_of_stack (tsk); -if (*stackend !=STACK_END_MAGIC ) +if (task_stack_end_corrupted (tsk))printk (KERN_EMERG "Thread overran stack, or stack corrupted\n" ); tsk->thread.cr2 = address;
include/linux/sched.h +2 -0
@@ -2617,6 +2617,8 @@ static inline unsigned long *end_of_stack(struct task_struct *p) }#endif +#define task_stack_end_corrupted (task) \ + (*(end_of_stack(task)) != STACK_END_MAGIC)static inline int object_is_on_stack (void *obj) {
kernel/trace/trace_stack.c +1 -1
@@ -170,7 +170,7 @@ check_stack(unsigned long ip, unsigned long *stack) i++; } -if (*end_of_stack (current) !=STACK_END_MAGIC ) { +if (task_stack_end_corrupted (current)) {print_max_stack ();BUG (); }
PATCH v4 3/3 sched: BUG when stack end location is over written
In reply to Aaron TomlinCurrently in the event of a stack overrun a call to schedule() does not check for this type of corruption. This corruption is often silent and can go unnoticed. However once the corrupted region is examined at a later stage, the outcome is undefined and often results in a sporadic page fault which cannot be handled.
This patch checks for a stack overrun and takes appropriate action since the damage is already done, there is no point in continuing.
--- kernel/sched/core.c | 3 +++ lib/Kconfig.debug | 12 ++++++++++++ 2 files changed, 15 insertions(+)
kernel/sched/core.c +3 -0
@@ -2660,6 +2660,9 @@ static noinline void __schedule_bug(struct task_struct *prev)*/ static inline void schedule_debug (struct task_struct *prev) { +#ifdef CONFIG_SCHED_STACK_END_CHECK +BUG_ON (unlikely (task_stack_end_corrupted (prev))); +#endif /* * Test if we are atomic. Since do_exit() needs to call into * schedule() atomically, we ignore that path. Otherwise whine
lib/Kconfig.debug +12 -0
@@ -824,6 +824,18 @@ config SCHEDSTATS application, you can say N to avoid the very slight overhead this adds. +config SCHED_STACK_END_CHECK + bool "Detect stack corruption on calls to schedule()" + depends on DEBUG_KERNEL + default n + help + This option checks for a stack overrun on calls to schedule(). + If the stack end location is found to be over written always panic as + the content of the corrupted region can no longer be trusted. + This is to ensure no erroneous behaviour occurs which could result in + data corruption or a sporadic crash at a later stage once the region + is examined. The runtime overhead introduced is minimal. + config TIMER_STATS bool "Collect kernel timers statistics" depends on DEBUG_KERNEL && PROC_FS
Signature · 1 line
1.9.3
tip-bot for Aaron Tomlin
merge bot[tip:sched/core] sched: Add default-disabled option to BUG() when stack end location is overwritten
sched: Add default-disabled option to BUG() when stack end location is overwritten
Commit-ID: 0d9e26329b0c9263d4d9e0422d80a0e73268c52f Gitweb: http://git.kernel.org/tip/0d9e26329b0c9263d4d9e0422d80a0e73268c52f Author: Aaron Tomlin <[email protected]> AuthorDate: Fri, 12 Sep 2014 14:16:19 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Fri, 19 Sep 2014 12:35:24 +0200
sched: Add default-disabled option to BUG() when stack end location is overwritten
Currently in the event of a stack overrun a call to schedule() does not check for this type of corruption. This corruption is often silent and can go unnoticed. However once the corrupted region is examined at a later stage, the outcome is undefined and often results in a sporadic page fault which cannot be handled.
This patch checks for a stack overrun and takes appropriate action since the damage is already done, there is no point in continuing.
--- kernel/sched/core.c | 3 +++ lib/Kconfig.debug | 12 ++++++++++++ 2 files changed, 15 insertions(+)
kernel/sched/core.c +3 -0
@@ -2693,6 +2693,9 @@ static noinline void __schedule_bug(struct task_struct *prev)*/ static inline void schedule_debug (struct task_struct *prev) { +#ifdef CONFIG_SCHED_STACK_END_CHECK +BUG_ON (unlikely (task_stack_end_corrupted (prev))); +#endif /* * Test if we are atomic. Since do_exit() needs to call into * schedule() atomically, we ignore that path. Otherwise whine
lib/Kconfig.debug +12 -0
@@ -824,6 +824,18 @@ config SCHEDSTATS application, you can say N to avoid the very slight overhead this adds. +config SCHED_STACK_END_CHECK + bool "Detect stack corruption on calls to schedule()" + depends on DEBUG_KERNEL + default n + help + This option checks for a stack overrun on calls to schedule(). + If the stack end location is found to be over written always panic as + the content of the corrupted region can no longer be trusted. + This is to ensure no erroneous behaviour occurs which could result in + data corruption or a sporadic crash at a later stage once the region + is examined. The runtime overhead introduced is minimal. + config TIMER_STATS bool "Collect kernel timers statistics" depends on DEBUG_KERNEL && PROC_FS