From 19af395d7c0daaafdebd441a162128aaac575912 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 18 Dec 2012 14:21:25 -0800 Subject: irq: tsk->comm is an array The array check is useless so remove it. [akpm@linux-foundation.org: remove comment, per David] Signed-off-by: Alan Cox Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/irq/manage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 35c70c9e24d8..e49a288fa479 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -818,7 +818,7 @@ static void irq_thread_dtor(struct callback_head *unused) action = kthread_data(tsk); pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", - tsk->comm ? tsk->comm : "", tsk->pid, action->irq); + tsk->comm, tsk->pid, action->irq); desc = irq_to_desc(action->irq); -- cgit v1.2.3 From 50bdd430c20566b13d8bc59946184b08f5875de6 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Tue, 18 Dec 2012 14:22:04 -0800 Subject: res_counter: return amount of charges after res_counter_uncharge() It is useful to know how many charges are still left after a call to res_counter_uncharge. While it is possible to issue a res_counter_read after uncharge, this can be racy. If we need, for instance, to take some action when the counters drop down to 0, only one of the callers should see it. This is the same semantics as the atomic variables in the kernel. Since the current return value is void, we don't need to worry about anything breaking due to this change: nobody relied on that, and only users appearing from now on will be checking this value. Signed-off-by: Glauber Costa Reviewed-by: Michal Hocko Acked-by: Kamezawa Hiroyuki Acked-by: David Rientjes Cc: Johannes Weiner Cc: Suleiman Souhlal Cc: Tejun Heo Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Greg Thelen Cc: JoonSoo Kim Cc: Mel Gorman Cc: Pekka Enberg Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/resource_counter.txt | 7 ++++--- include/linux/res_counter.h | 12 +++++++----- kernel/res_counter.c | 20 +++++++++++++------- 3 files changed, 24 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt index 0c4a344e78fa..c4d99ed0b418 100644 --- a/Documentation/cgroups/resource_counter.txt +++ b/Documentation/cgroups/resource_counter.txt @@ -83,16 +83,17 @@ to work with it. res_counter->lock internally (it must be called with res_counter->lock held). The force parameter indicates whether we can bypass the limit. - e. void res_counter_uncharge[_locked] + e. u64 res_counter_uncharge[_locked] (struct res_counter *rc, unsigned long val) When a resource is released (freed) it should be de-accounted from the resource counter it was accounted to. This is called - "uncharging". + "uncharging". The return value of this function indicate the amount + of charges still present in the counter. The _locked routines imply that the res_counter->lock is taken. - f. void res_counter_uncharge_until + f. u64 res_counter_uncharge_until (struct res_counter *rc, struct res_counter *top, unsinged long val) diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 6f54e40fa218..5ae8456d9670 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -125,14 +125,16 @@ int res_counter_charge_nofail(struct res_counter *counter, * * these calls check for usage underflow and show a warning on the console * _locked call expects the counter->lock to be taken + * + * returns the total charges still present in @counter. */ -void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); -void res_counter_uncharge(struct res_counter *counter, unsigned long val); +u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); +u64 res_counter_uncharge(struct res_counter *counter, unsigned long val); -void res_counter_uncharge_until(struct res_counter *counter, - struct res_counter *top, - unsigned long val); +u64 res_counter_uncharge_until(struct res_counter *counter, + struct res_counter *top, + unsigned long val); /** * res_counter_margin - calculate chargeable space of a counter * @cnt: the counter diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 3920d593e63c..ff55247e7049 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -86,33 +86,39 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, return __res_counter_charge(counter, val, limit_fail_at, true); } -void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) +u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) { if (WARN_ON(counter->usage < val)) val = counter->usage; counter->usage -= val; + return counter->usage; } -void res_counter_uncharge_until(struct res_counter *counter, - struct res_counter *top, - unsigned long val) +u64 res_counter_uncharge_until(struct res_counter *counter, + struct res_counter *top, + unsigned long val) { unsigned long flags; struct res_counter *c; + u64 ret = 0; local_irq_save(flags); for (c = counter; c != top; c = c->parent) { + u64 r; spin_lock(&c->lock); - res_counter_uncharge_locked(c, val); + r = res_counter_uncharge_locked(c, val); + if (c == counter) + ret = r; spin_unlock(&c->lock); } local_irq_restore(flags); + return ret; } -void res_counter_uncharge(struct res_counter *counter, unsigned long val) +u64 res_counter_uncharge(struct res_counter *counter, unsigned long val) { - res_counter_uncharge_until(counter, NULL, val); + return res_counter_uncharge_until(counter, NULL, val); } static inline unsigned long long * -- cgit v1.2.3 From 2ad306b17c0ac5a1b1f250d5f772aeb87fdf1eba Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Tue, 18 Dec 2012 14:22:18 -0800 Subject: fork: protect architectures where THREAD_SIZE >= PAGE_SIZE against fork bombs Because those architectures will draw their stacks directly from the page allocator, rather than the slab cache, we can directly pass __GFP_KMEMCG flag, and issue the corresponding free_pages. This code path is taken when the architecture doesn't define CONFIG_ARCH_THREAD_INFO_ALLOCATOR (only ia64 seems to), and has THREAD_SIZE >= PAGE_SIZE. Luckily, most - if not all - of the remaining architectures fall in this category. This will guarantee that every stack page is accounted to the memcg the process currently lives on, and will have the allocations to fail if they go over limit. For the time being, I am defining a new variant of THREADINFO_GFP, not to mess with the other path. Once the slab is also tracked by memcg, we can get rid of that flag. Tested to successfully protect against :(){ :|:& };: Signed-off-by: Glauber Costa Acked-by: Frederic Weisbecker Acked-by: Kamezawa Hiroyuki Reviewed-by: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Cc: Greg Thelen Cc: Johannes Weiner Cc: JoonSoo Kim Cc: Mel Gorman Cc: Pekka Enberg Cc: Rik van Riel Cc: Suleiman Souhlal Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thread_info.h | 2 ++ kernel/fork.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ccc1899bd62e..e7e04736802f 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -61,6 +61,8 @@ extern long do_no_restart_syscall(struct restart_block *parm); # define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK) #endif +#define THREADINFO_GFP_ACCOUNTED (THREADINFO_GFP | __GFP_KMEMCG) + /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions diff --git a/kernel/fork.c b/kernel/fork.c index c36c4e301efe..85f6d536608d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -146,7 +146,7 @@ void __weak arch_release_thread_info(struct thread_info *ti) static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) { - struct page *page = alloc_pages_node(node, THREADINFO_GFP, + struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED, THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; @@ -154,7 +154,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, static inline void free_thread_info(struct thread_info *ti) { - free_pages((unsigned long)ti, THREAD_SIZE_ORDER); + free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_info_cache; -- cgit v1.2.3