[GIT PULL] late cgroup fixes for v3.17-rc6

From: Tejun Heo
Date: Sat Sep 27 2014 - 10:01:17 EST

Next message: Peter Hurley: "Re: page allocator bug in 3.16?"
Previous message: Fabio Estevam: "Re: [PATCH v2 1/3] drivers: of: add return value to of_reserved_mem_device_init (fixup)"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Hello, Linus.

This is quite late but these need to be backported anyway. This is
the fix for a long-standing cpuset bug which existed from 2009.
cpuset makes use of PF_SPREAD_{PAGE|SLAB} flags to modify the task's
memory allocation behavior according to the settings of the cpuset it
belongs to; unfortunately, when those flags have to be changed, cpuset
did so directly even whlie the target task is running, which is
obviously racy as task->flags may be modified by the task itself at
any time. This obscure bug manifested as corrupt PF_USED_MATH flag
leading to a weird crash.

The bug is fixed by moving the flag to task->atomic_flags. The first
two are prepatory ones to help defining atomic_flags accessors and the
third one is the actual fix.

Thanks.

The following changes since commit eb4aec84d6bdf98d00cedb41c18000f7a31e648a:

cgroup: fix unbalanced locking (2014-09-18 12:32:52 -0400)

are available in the git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git for-3.17-fixes

for you to fetch changes up to 2ad654bc5e2b211e92f66da1d819e47d79a866f0:

cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags (2014-09-24 22:16:06 -0400)

----------------------------------------------------------------
Zefan Li (3):
sched: fix confusing PFA_NO_NEW_PRIVS constant
sched: add macros to define bitops for task atomic flags
cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags

Documentation/cgroups/cpusets.txt | 6 +++---
include/linux/cpuset.h | 4 ++--
include/linux/sched.h | 38 +++++++++++++++++++++++++-------------
kernel/cpuset.c | 9 +++++----
mm/slab.c | 4 ++--
scripts/tags.sh | 6 ++++++
6 files changed, 43 insertions(+), 24 deletions(-)

diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 7740038..3c94ff3 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 ade2390..6e39c9b 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 5c2c885..7b1cafe 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 */
@@ -1957,17 +1955,31 @@ static inline void memalloc_noio_restore(unsigned int flags)
}

/* Per-process atomic flags. */
-#define PFA_NO_NEW_PRIVS 0x00000001 /* 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);
-}
-
-static inline void task_set_no_new_privs(struct task_struct *p)
-{
- set_bit(PFA_NO_NEW_PRIVS, &p->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) \
+ { 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); }
+
+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 22874d7..52cb04c 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 a467b30..881951e 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;
diff --git a/scripts/tags.sh b/scripts/tags.sh
index cbfd269..293828b 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/'\

--
tejun
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Peter Hurley: "Re: page allocator bug in 3.16?"
Previous message: Fabio Estevam: "Re: [PATCH v2 1/3] drivers: of: add return value to of_reserved_mem_device_init (fixup)"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]