Subject: [folded-merged] mm-per-thread-vma-caching-fix-4.patch removed from -mm tree To: davidlohr@xxxxxx,oleg@xxxxxxxxxx,riel@xxxxxxxxxx,torvalds@xxxxxxxxxxxxxxxxxxxx,walken@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Mon, 07 Apr 2014 15:04:40 -0700 The patch titled Subject: mm,vmacache: also flush cache for VM_CLONE has been removed from the -mm tree. Its filename was mm-per-thread-vma-caching-fix-4.patch This patch was dropped because it was folded into mm-per-thread-vma-caching.patch ------------------------------------------------------ From: Davidlohr Bueso <davidlohr@xxxxxx> Subject: mm,vmacache: also flush cache for VM_CLONE Oleg found that there is a potential race if we don't flush the task for threads (VM_CLONE): "Suppose we have a task T1 which has the valid vmacache, T1->vmacache_seqnum == T1->mm->vmacache_seqnum == 0. Suppose it sleeps a lot. Suppose that its subthread T2 does a lot munmap's, finally mm->vmacache_seqnum becomes zero again and T2 calls vmacache_flush_all(). T1 wakes up and does clone(CLONE_VM). The new thread T3 gets the copy of T2's ->vmacache_seqnum and ->vmacache[]. T2 continues, vmacache_flush_all() finds T1 and does vmacache_flush(T1). But the new thread T3 is not on the list yet, vmacache_flush_all() can't find it. So T3 will run with vmacache_valid() == T (till the next invalidate(mm) of course) but its ->vmacache[] points to nowhere." Address this by moving the flush call into copy_mm(), instead of only having it in dup_mm(). Signed-off-by: Davidlohr Bueso <davidlohr@xxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Michel Lespinasse <walken@xxxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Oleg Nesterov <oleg@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- kernel/fork.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff -puN kernel/fork.c~mm-per-thread-vma-caching-fix-4 kernel/fork.c --- a/kernel/fork.c~mm-per-thread-vma-caching-fix-4 +++ a/kernel/fork.c @@ -840,9 +840,6 @@ static struct mm_struct *dup_mm(struct t if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; - /* initialize the new vmacache entries */ - vmacache_flush(tsk); - return mm; free_pt: @@ -886,6 +883,9 @@ static int copy_mm(unsigned long clone_f if (!oldmm) return 0; + /* initialize the new vmacache entries */ + vmacache_flush(tsk); + if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; _ Patches currently in -mm which might be from davidlohr@xxxxxx are origin.patch mm-memoryc-update-comment-in-unmap_single_vma.patch mm-per-thread-vma-caching.patch mm-per-thread-vma-caching-fix-5.patch mm-per-thread-vma-caching-fix-6.patch mm-per-thread-vma-caching-fix-6-fix.patch ipccompat-remove-sc_semopm-macro.patch ipc-use-device_initcall.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html