From a2b86f772227bcaf962c8b134f8d187046ac5f0e Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:40:17 +0800 Subject: [PATCH 1/3] sched: fix confusing PFA_NO_NEW_PRIVS constant Commit 1d4457f99928 ("sched: move no_new_privs into new atomic flags") defined PFA_NO_NEW_PRIVS as hexadecimal value, but it is confusing because it is used as bit number. Redefine it as decimal bit number. Note this changes the bit position of PFA_NOW_NEW_PRIVS from 1 to 0. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miao Xie Signed-off-by: Tetsuo Handa Acked-by: Kees Cook [ lizf: slightly modified subject and changelog ] Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 5c2c885ee52b..45577650f629 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1957,7 +1957,7 @@ static inline void memalloc_noio_restore(unsigned int flags) } /* Per-process atomic flags. */ -#define PFA_NO_NEW_PRIVS 0x00000001 /* May not gain new privileges. */ +#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ static inline bool task_no_new_privs(struct task_struct *p) { From e0e5070b20e01f0321f97db4e4e174f3f6b49e50 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:40:40 +0800 Subject: [PATCH 2/3] sched: add macros to define bitops for task atomic flags This will simplify code when we add new flags. v3: - Kees pointed out that no_new_privs should never be cleared, so we shouldn't define task_clear_no_new_privs(). we define 3 macros instead of a single one. v2: - updated scripts/tags.sh, suggested by Peter Cc: Ingo Molnar Cc: Miao Xie Cc: Tetsuo Handa Acked-by: Peter Zijlstra (Intel) Acked-by: Kees Cook Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- include/linux/sched.h | 19 +++++++++++-------- scripts/tags.sh | 6 ++++++ 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 45577650f629..5630763956d9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1959,15 +1959,18 @@ static inline void memalloc_noio_restore(unsigned int flags) /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ -static inline bool task_no_new_privs(struct task_struct *p) -{ - return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags); -} +#define TASK_PFA_TEST(name, func) \ + static inline bool task_##func(struct task_struct *p) \ + { return test_bit(PFA_##name, &p->atomic_flags); } +#define TASK_PFA_SET(name, func) \ + static inline void task_set_##func(struct task_struct *p) \ + { set_bit(PFA_##name, &p->atomic_flags); } +#define TASK_PFA_CLEAR(name, func) \ + static inline void task_clear_##func(struct task_struct *p) \ + { clear_bit(PFA_##name, &p->atomic_flags); } -static inline void task_set_no_new_privs(struct task_struct *p) -{ - set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags); -} +TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) +TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) /* * task->jobctl flags diff --git a/scripts/tags.sh b/scripts/tags.sh index cbfd269a6011..293828bfd4ac 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -197,6 +197,9 @@ exuberant() --regex-c++='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/' \ --regex-c++='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/' \ --regex-c++='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \ + --regex-c++='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/' \ + --regex-c++='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/' \ + --regex-c++='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/'\ --regex-c='/PCI_OP_READ\((\w*).*[1-4]\)/pci_bus_read_config_\1/' \ --regex-c='/PCI_OP_WRITE\((\w*).*[1-4]\)/pci_bus_write_config_\1/' \ --regex-c='/DEFINE_(MUTEX|SEMAPHORE|SPINLOCK)\((\w*)/\2/v/' \ @@ -260,6 +263,9 @@ emacs() --regex='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/' \ --regex='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/' \ --regex='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \ + --regex='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/' \ + --regex='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/' \ + --regex='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/' \ --regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/' \ --regex='/PCI_OP_READ(\([a-z]*[a-z]\).*[1-4])/pci_bus_read_config_\1/' \ --regex='/PCI_OP_WRITE(\([a-z]*[a-z]\).*[1-4])/pci_bus_write_config_\1/'\ From 2ad654bc5e2b211e92f66da1d819e47d79a866f0 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:41:02 +0800 Subject: [PATCH 3/3] cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags When we change cpuset.memory_spread_{page,slab}, cpuset will flip PF_SPREAD_{PAGE,SLAB} bit of tsk->flags for each task in that cpuset. This should be done using atomic bitops, but currently we don't, which is broken. Tetsuo reported a hard-to-reproduce kernel crash on RHEL6, which happened when one thread tried to clear PF_USED_MATH while at the same time another thread tried to flip PF_SPREAD_PAGE/PF_SPREAD_SLAB. They both operate on the same task. Here's the full report: https://lkml.org/lkml/2014/9/19/230 To fix this, we make PF_SPREAD_PAGE and PF_SPREAD_SLAB atomic flags. v4: - updated mm/slab.c. (Fengguang Wu) - updated Documentation. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miao Xie Cc: Kees Cook Fixes: 950592f7b991 ("cpusets: update tasks' page/slab spread flags in time") Cc: # 2.6.31+ Reported-by: Tetsuo Handa Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- Documentation/cgroups/cpusets.txt | 6 +++--- include/linux/cpuset.h | 4 ++-- include/linux/sched.h | 13 +++++++++++-- kernel/cpuset.c | 9 +++++---- mm/slab.c | 4 ++-- 5 files changed, 23 insertions(+), 13 deletions(-) diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 7740038d82bc..3c94ff3f9693 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -345,14 +345,14 @@ the named feature on. The implementation is simple. Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag -PF_SPREAD_PAGE for each task that is in that cpuset or subsequently +PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently joins that cpuset. The page allocation calls for the page cache -is modified to perform an inline check for this PF_SPREAD_PAGE task +is modified to perform an inline check for this PFA_SPREAD_PAGE task flag, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. Similarly, setting 'cpuset.memory_spread_slab' turns on the flag -PF_SPREAD_SLAB, and appropriately marked slab caches will allocate +PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate pages from the node returned by cpuset_mem_spread_node(). The cpuset_mem_spread_node() routine is also simple. It uses the diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index ade2390ffe92..6e39c9bb0dae 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -93,12 +93,12 @@ extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { - return current->flags & PF_SPREAD_PAGE; + return task_spread_page(current); } static inline int cpuset_do_slab_mem_spread(void) { - return current->flags & PF_SPREAD_SLAB; + return task_spread_slab(current); } extern int current_cpuset_is_being_rebound(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 5630763956d9..7b1cafefb05e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1903,8 +1903,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ -#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ @@ -1958,6 +1956,9 @@ static inline void memalloc_noio_restore(unsigned int flags) /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ +#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ +#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ + #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1972,6 +1973,14 @@ static inline void memalloc_noio_restore(unsigned int flags) TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) +TASK_PFA_TEST(SPREAD_PAGE, spread_page) +TASK_PFA_SET(SPREAD_PAGE, spread_page) +TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) + +TASK_PFA_TEST(SPREAD_SLAB, spread_slab) +TASK_PFA_SET(SPREAD_SLAB, spread_slab) +TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) + /* * task->jobctl flags */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 22874d7cf2c0..52cb04c993b7 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) - tsk->flags |= PF_SPREAD_PAGE; + task_set_spread_page(tsk); else - tsk->flags &= ~PF_SPREAD_PAGE; + task_clear_spread_page(tsk); + if (is_spread_slab(cs)) - tsk->flags |= PF_SPREAD_SLAB; + task_set_spread_slab(tsk); else - tsk->flags &= ~PF_SPREAD_SLAB; + task_clear_spread_slab(tsk); } /* diff --git a/mm/slab.c b/mm/slab.c index a467b308c682..881951e67f12 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2994,7 +2994,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. + * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3226,7 +3226,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { + if (current->mempolicy || cpuset_do_slab_mem_spread()) { objp = alternate_node_alloc(cache, flags); if (objp) goto out;