From 112bc2e120a94a511858918d6866a4978f9c500e Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 24 Nov 2010 12:56:58 -0800 Subject: memcg: fix false positive VM_BUG on non-SMP Fix this: kernel BUG at mm/memcontrol.c:2155! invalid opcode: 0000 [#1] last sysfs file: Pid: 18, comm: sh Not tainted 2.6.37-rc3 #3 /Bochs EIP: 0060:[] EFLAGS: 00000246 CPU: 0 EIP is at mem_cgroup_move_account+0xe2/0xf0 EAX: 00000004 EBX: c6f931d4 ECX: c681c300 EDX: c681c000 ESI: c681c300 EDI: ffffffea EBP: c681c000 ESP: c46f3e30 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sh (pid: 18, ti=c46f2000 task=c6826e60 task.ti=c46f2000) Stack: 00000155 c681c000 0805f000 c46ee180 c46f3e5c c7058820 c1074d37 00000000 08060000 c46db9a0 c46ec080 c7058820 0805f000 08060000 c46f3e98 c1074c50 c106c75e c46f3e98 c46ec080 08060000 0805ffff c46db9a0 c46f3e98 c46e0340 Call Trace: [] ? mem_cgroup_move_charge_pte_range+0xe7/0x130 [] ? mem_cgroup_move_charge_pte_range+0x0/0x130 [] ? walk_page_range+0xee/0x1d0 [] ? mem_cgroup_move_task+0x66/0x90 [] ? mem_cgroup_move_charge_pte_range+0x0/0x130 [] ? mem_cgroup_move_task+0x0/0x90 [] ? cgroup_attach_task+0x136/0x200 [] ? cgroup_tasks_write+0x48/0xc0 [] ? cgroup_file_write+0xde/0x220 [] ? do_page_fault+0x17d/0x3f0 [] ? alloc_fd+0x2d/0xd0 [] ? cgroup_file_write+0x0/0x220 [] ? vfs_write+0x92/0xc0 [] ? sys_write+0x41/0x70 [] ? syscall_call+0x7/0xb Code: 03 00 74 09 8b 44 24 04 e8 1c f1 ff ff 89 73 04 8d 86 b0 00 00 00 b9 01 00 00 00 89 da 31 ff e8 65 f5 ff ff e9 4d ff ff ff 0f 0b <0f> 0b 0f 0b 0f 0b 90 8d b4 26 00 00 00 00 83 ec 10 8b 0d f4 e3 EIP: [] mem_cgroup_move_account+0xe2/0xf0 SS:ESP 0068:c46f3e30 ---[ end trace 7daa1582159b6532 ]--- lock_page_cgroup and unlock_page_cgroup are implemented using bit_spinlock. bit_spinlock doesn't touch the bit if we are on non-SMP machine, so we can't use the bit to check whether the lock was taken. Let's introduce is_page_cgroup_locked based on bit_spin_is_locked instead of PageCgroupLocked to fix it. [akpm@linux-foundation.org: s/is_page_cgroup_locked/page_is_cgroup_locked/] Signed-off-by: Kirill A. Shutemov Reviewed-by: Johannes Weiner Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2efa8ea07ff7..62d1880f6992 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2152,7 +2152,7 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc, { VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(pc->page)); - VM_BUG_ON(!PageCgroupLocked(pc)); + VM_BUG_ON(!page_is_cgroup_locked(pc)); VM_BUG_ON(!PageCgroupUsed(pc)); VM_BUG_ON(pc->mem_cgroup != from); -- cgit v1.2.2 From b1dd693e5b9348bd68a80e679e03cf9c0973b01b Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Wed, 24 Nov 2010 12:57:06 -0800 Subject: memcg: avoid deadlock between move charge and try_charge() __mem_cgroup_try_charge() can be called under down_write(&mmap_sem)(e.g. mlock does it). This means it can cause deadlock if it races with move charge: Ex.1) move charge | try charge --------------------------------------+------------------------------ mem_cgroup_can_attach() | down_write(&mmap_sem) mc.moving_task = current | .. mem_cgroup_precharge_mc() | __mem_cgroup_try_charge() mem_cgroup_count_precharge() | prepare_to_wait() down_read(&mmap_sem) | if (mc.moving_task) -> cannot aquire the lock | -> true | schedule() Ex.2) move charge | try charge --------------------------------------+------------------------------ mem_cgroup_can_attach() | mc.moving_task = current | mem_cgroup_precharge_mc() | mem_cgroup_count_precharge() | down_read(&mmap_sem) | .. | up_read(&mmap_sem) | | down_write(&mmap_sem) mem_cgroup_move_task() | .. mem_cgroup_move_charge() | __mem_cgroup_try_charge() down_read(&mmap_sem) | prepare_to_wait() -> cannot aquire the lock | if (mc.moving_task) | -> true | schedule() To avoid this deadlock, we do all the move charge works (both can_attach() and attach()) under one mmap_sem section. And after this patch, we set/clear mc.moving_task outside mc.lock, because we use the lock only to check mc.from/to. Signed-off-by: Daisuke Nishimura Cc: Balbir Singh Acked-by: KAMEZAWA Hiroyuki Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 43 ++++++++++++++++++++++++++----------------- 1 file changed, 26 insertions(+), 17 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 62d1880f6992..26218df8d19d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -278,13 +278,14 @@ enum move_type { /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { - spinlock_t lock; /* for from, to, moving_task */ + spinlock_t lock; /* for from, to */ struct mem_cgroup *from; struct mem_cgroup *to; unsigned long precharge; unsigned long moved_charge; unsigned long moved_swap; struct task_struct *moving_task; /* a task moving charges */ + struct mm_struct *mm; wait_queue_head_t waitq; /* a waitq for other context */ } mc = { .lock = __SPIN_LOCK_UNLOCKED(mc.lock), @@ -4631,7 +4632,7 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) unsigned long precharge; struct vm_area_struct *vma; - down_read(&mm->mmap_sem); + /* We've already held the mmap_sem */ for (vma = mm->mmap; vma; vma = vma->vm_next) { struct mm_walk mem_cgroup_count_precharge_walk = { .pmd_entry = mem_cgroup_count_precharge_pte_range, @@ -4643,7 +4644,6 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) walk_page_range(vma->vm_start, vma->vm_end, &mem_cgroup_count_precharge_walk); } - up_read(&mm->mmap_sem); precharge = mc.precharge; mc.precharge = 0; @@ -4694,11 +4694,16 @@ static void mem_cgroup_clear_mc(void) mc.moved_swap = 0; } + if (mc.mm) { + up_read(&mc.mm->mmap_sem); + mmput(mc.mm); + } spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; - mc.moving_task = NULL; spin_unlock(&mc.lock); + mc.moving_task = NULL; + mc.mm = NULL; mem_cgroup_end_move(from); memcg_oom_recover(from); memcg_oom_recover(to); @@ -4724,12 +4729,21 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, return 0; /* We move charges only when we move a owner of the mm */ if (mm->owner == p) { + /* + * We do all the move charge works under one mmap_sem to + * avoid deadlock with down_write(&mmap_sem) + * -> try_charge() -> if (mc.moving_task) -> sleep. + */ + down_read(&mm->mmap_sem); + VM_BUG_ON(mc.from); VM_BUG_ON(mc.to); VM_BUG_ON(mc.precharge); VM_BUG_ON(mc.moved_charge); VM_BUG_ON(mc.moved_swap); VM_BUG_ON(mc.moving_task); + VM_BUG_ON(mc.mm); + mem_cgroup_start_move(from); spin_lock(&mc.lock); mc.from = from; @@ -4737,14 +4751,16 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, mc.precharge = 0; mc.moved_charge = 0; mc.moved_swap = 0; - mc.moving_task = current; spin_unlock(&mc.lock); + mc.moving_task = current; + mc.mm = mm; ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); - } - mmput(mm); + /* We call up_read() and mmput() in clear_mc(). */ + } else + mmput(mm); } return ret; } @@ -4832,7 +4848,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) struct vm_area_struct *vma; lru_add_drain_all(); - down_read(&mm->mmap_sem); + /* We've already held the mmap_sem */ for (vma = mm->mmap; vma; vma = vma->vm_next) { int ret; struct mm_walk mem_cgroup_move_charge_walk = { @@ -4851,7 +4867,6 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) */ break; } - up_read(&mm->mmap_sem); } static void mem_cgroup_move_task(struct cgroup_subsys *ss, @@ -4860,17 +4875,11 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, struct task_struct *p, bool threadgroup) { - struct mm_struct *mm; - - if (!mc.to) + if (!mc.mm) /* no need to move charge */ return; - mm = get_task_mm(p); - if (mm) { - mem_cgroup_move_charge(mm); - mmput(mm); - } + mem_cgroup_move_charge(mc.mm); mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -- cgit v1.2.2 From a42c390cfa0c2612459d7226ba11612847ca3a64 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 24 Nov 2010 12:57:08 -0800 Subject: cgroups: make swap accounting default behavior configurable Swap accounting can be configured by CONFIG_CGROUP_MEM_RES_CTLR_SWAP configuration option and then it is turned on by default. There is a boot option (noswapaccount) which can disable this feature. This makes it hard for distributors to enable the configuration option as this feature leads to a bigger memory consumption and this is a no-go for general purpose distribution kernel. On the other hand swap accounting may be very usuful for some workloads. This patch adds a new configuration option which controls the default behavior (CGROUP_MEM_RES_CTLR_SWAP_ENABLED). If the option is selected then the feature is turned on by default. It also adds a new boot parameter swapaccount[=1|0] which enhances the original noswapaccount parameter semantic by means of enable/disable logic (defaults to 1 if no value is provided to be still consistent with noswapaccount). The default behavior is unchanged (if CONFIG_CGROUP_MEM_RES_CTLR_SWAP is enabled then CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED is enabled as well) Signed-off-by: Michal Hocko Acked-by: Daisuke Nishimura Cc: Balbir Singh Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 26218df8d19d..7a22b4129211 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -61,7 +61,14 @@ struct mem_cgroup *root_mem_cgroup __read_mostly; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; -static int really_do_swap_account __initdata = 1; /* for remember boot option*/ + +/* for remember boot option*/ +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED +static int really_do_swap_account __initdata = 1; +#else +static int really_do_swap_account __initdata = 0; +#endif + #else #define do_swap_account (0) #endif @@ -4920,10 +4927,20 @@ struct cgroup_subsys mem_cgroup_subsys = { }; #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +static int __init enable_swap_account(char *s) +{ + /* consider enabled if no parameter or 1 is given */ + if (!s || !strcmp(s, "1")) + really_do_swap_account = 1; + else if (!strcmp(s, "0")) + really_do_swap_account = 0; + return 1; +} +__setup("swapaccount", enable_swap_account); static int __init disable_swap_account(char *s) { - really_do_swap_account = 0; + enable_swap_account("0"); return 1; } __setup("noswapaccount", disable_swap_account); -- cgit v1.2.2