From d05f0cdcbe6388723f1900c549b4850360545201 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 23 Jun 2014 13:22:07 -0700 Subject: mm: fix crashes from mbind() merging vmas In v2.6.34 commit 9d8cebd4bcd7 ("mm: fix mbind vma merge problem") introduced vma merging to mbind(), but it should have also changed the convention of passing start vma from queue_pages_range() (formerly check_range()) to new_vma_page(): vma merging may have already freed that structure, resulting in BUG at mm/mempolicy.c:1738 and probably worse crashes. Fixes: 9d8cebd4bcd7 ("mm: fix mbind vma merge problem") Reported-by: Naoya Horiguchi Tested-by: Naoya Horiguchi Signed-off-by: Hugh Dickins Acked-by: Christoph Lameter Cc: KOSAKI Motohiro Cc: Minchan Kim Cc: [2.6.34+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 46 ++++++++++++++++++++-------------------------- 1 file changed, 20 insertions(+), 26 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 284974230459..eb58de19f815 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -656,19 +656,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private.) */ -static struct vm_area_struct * +static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, const nodemask_t *nodes, unsigned long flags, void *private) { - int err; - struct vm_area_struct *first, *vma, *prev; - + int err = 0; + struct vm_area_struct *vma, *prev; - first = find_vma(mm, start); - if (!first) - return ERR_PTR(-EFAULT); + vma = find_vma(mm, start); + if (!vma) + return -EFAULT; prev = NULL; - for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { + for (; vma && vma->vm_start < end; vma = vma->vm_next) { unsigned long endvma = vma->vm_end; if (endvma > end) @@ -678,9 +677,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, if (!(flags & MPOL_MF_DISCONTIG_OK)) { if (!vma->vm_next && vma->vm_end < end) - return ERR_PTR(-EFAULT); + return -EFAULT; if (prev && prev->vm_end < vma->vm_start) - return ERR_PTR(-EFAULT); + return -EFAULT; } if (flags & MPOL_MF_LAZY) { @@ -694,15 +693,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, err = queue_pages_pgd_range(vma, start, endvma, nodes, flags, private); - if (err) { - first = ERR_PTR(err); + if (err) break; - } } next: prev = vma; } - return first; + return err; } /* @@ -1156,16 +1153,17 @@ out: /* * Allocate a new page for page migration based on vma policy. - * Start assuming that page is mapped by vma pointed to by @private. + * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { - struct vm_area_struct *vma = (struct vm_area_struct *)private; + struct vm_area_struct *vma; unsigned long uninitialized_var(address); + vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) @@ -1195,7 +1193,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +static struct page *new_page(struct page *page, unsigned long start, int **x) { return NULL; } @@ -1205,7 +1203,6 @@ static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { - struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; @@ -1271,11 +1268,9 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - vma = queue_pages_range(mm, start, end, nmask, + err = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - - err = PTR_ERR(vma); /* maybe ... */ - if (!IS_ERR(vma)) + if (!err) err = mbind_range(mm, start, end, new); if (!err) { @@ -1283,9 +1278,8 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); - nr_failed = migrate_pages(&pagelist, new_vma_page, - NULL, (unsigned long)vma, - MIGRATE_SYNC, MR_MEMPOLICY_MBIND); + nr_failed = migrate_pages(&pagelist, new_page, NULL, + start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } -- cgit v1.2.3 From 391acf970d21219a2a5446282d3b20eace0c0d7a Mon Sep 17 00:00:00 2001 From: Gu Zheng Date: Wed, 25 Jun 2014 09:57:18 +0800 Subject: cpuset,mempolicy: fix sleeping function called from invalid context When runing with the kernel(3.15-rc7+), the follow bug occurs: [ 9969.258987] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 [ 9969.359906] in_atomic(): 1, irqs_disabled(): 0, pid: 160655, name: python [ 9969.441175] INFO: lockdep is turned off. [ 9969.488184] CPU: 26 PID: 160655 Comm: python Tainted: G A 3.15.0-rc7+ #85 [ 9969.581032] Hardware name: FUJITSU-SV PRIMEQUEST 1800E/SB, BIOS PRIMEQUEST 1000 Series BIOS Version 1.39 11/16/2012 [ 9969.706052] ffffffff81a20e60 ffff8803e941fbd0 ffffffff8162f523 ffff8803e941fd18 [ 9969.795323] ffff8803e941fbe0 ffffffff8109995a ffff8803e941fc58 ffffffff81633e6c [ 9969.884710] ffffffff811ba5dc ffff880405c6b480 ffff88041fdd90a0 0000000000002000 [ 9969.974071] Call Trace: [ 9970.003403] [] dump_stack+0x4d/0x66 [ 9970.065074] [] __might_sleep+0xfa/0x130 [ 9970.130743] [] mutex_lock_nested+0x3c/0x4f0 [ 9970.200638] [] ? kmem_cache_alloc+0x1bc/0x210 [ 9970.272610] [] cpuset_mems_allowed+0x27/0x140 [ 9970.344584] [] ? __mpol_dup+0x63/0x150 [ 9970.409282] [] __mpol_dup+0xe5/0x150 [ 9970.471897] [] ? __mpol_dup+0x63/0x150 [ 9970.536585] [] ? copy_process.part.23+0x606/0x1d40 [ 9970.613763] [] ? trace_hardirqs_on+0xd/0x10 [ 9970.683660] [] ? monotonic_to_bootbased+0x2f/0x50 [ 9970.759795] [] copy_process.part.23+0x670/0x1d40 [ 9970.834885] [] do_fork+0xd8/0x380 [ 9970.894375] [] ? __audit_syscall_entry+0x9c/0xf0 [ 9970.969470] [] SyS_clone+0x16/0x20 [ 9971.030011] [] stub_clone+0x69/0x90 [ 9971.091573] [] ? system_call_fastpath+0x16/0x1b The cause is that cpuset_mems_allowed() try to take mutex_lock(&callback_mutex) under the rcu_read_lock(which was hold in __mpol_dup()). And in cpuset_mems_allowed(), the access to cpuset is under rcu_read_lock, so in __mpol_dup, we can reduce the rcu_read_lock protection region to protect the access to cpuset only in current_cpuset_is_being_rebound(). So that we can avoid this bug. This patch is a temporary solution that just addresses the bug mentioned above, can not fix the long-standing issue about cpuset.mems rebinding on fork(): "When the forker's task_struct is duplicated (which includes ->mems_allowed) and it races with an update to cpuset_being_rebound in update_tasks_nodemask() then the task's mems_allowed doesn't get updated. And the child task's mems_allowed can be wrong if the cpuset's nodemask changes before the child has been added to the cgroup's tasklist." Signed-off-by: Gu Zheng Acked-by: Li Zefan Signed-off-by: Tejun Heo Cc: stable --- mm/mempolicy.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 284974230459..9a3783ccff67 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2145,7 +2145,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) } else *new = *old; - rcu_read_lock(); if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); if (new->flags & MPOL_F_REBINDING) @@ -2153,7 +2152,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old) else mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE); } - rcu_read_unlock(); atomic_set(&new->refcnt, 1); return new; } -- cgit v1.2.3