From 7906d00cd1f687268f0a3599442d113767795ae6 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Mon, 28 Jul 2008 15:46:26 -0700 Subject: mmu-notifiers: add mm_take_all_locks() operation mm_take_all_locks holds off reclaim from an entire mm_struct. This allows mmu notifiers to register into the mm at any time with the guarantee that no mmu operation is in progress on the mm. This operation locks against the VM for all pte/vma/mm related operations that could ever happen on a certain mm. This includes vmtruncate, try_to_unmap, and all page faults. The caller must take the mmap_sem in write mode before calling mm_take_all_locks(). The caller isn't allowed to release the mmap_sem until mm_drop_all_locks() returns. mmap_sem in write mode is required in order to block all operations that could modify pagetables and free pages without need of altering the vma layout (for example populate_range() with nonlinear vmas). It's also needed in write mode to avoid new anon_vmas to be associated with existing vmas. A single task can't take more than one mm_take_all_locks() in a row or it would deadlock. mm_take_all_locks() and mm_drop_all_locks are expensive operations that may have to take thousand of locks. mm_take_all_locks() can fail if it's interrupted by signals. When mmu_notifier_register returns, we must be sure that the driver is notified if some task is in the middle of a vmtruncate for the 'mm' where the mmu notifier was registered (mmu_notifier_invalidate_range_start/end is run around the vmtruncation but mmu_notifier_register can run after mmu_notifier_invalidate_range_start and before mmu_notifier_invalidate_range_end). Same problem for rmap paths. And we've to remove page pinning to avoid replicating the tlb_gather logic inside KVM (and GRU doesn't work well with page pinning regardless of needing tlb_gather), so without mm_take_all_locks when vmtruncate frees the page, kvm would have no way to notice that it mapped into sptes a page that is going into the freelist without a chance of any further mmu_notifier notification. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andrea Arcangeli Acked-by: Linus Torvalds Cc: Christoph Lameter Cc: Jack Steiner Cc: Robin Holt Cc: Nick Piggin Cc: Peter Zijlstra Cc: Kanoj Sarcar Cc: Roland Dreier Cc: Steve Wise Cc: Avi Kivity Cc: Hugh Dickins Cc: Rusty Russell Cc: Anthony Liguori Cc: Chris Wright Cc: Marcelo Tosatti Cc: Eric Dumazet Cc: "Paul E. McKenney" Cc: Izik Eidus Cc: Anthony Liguori Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ include/linux/pagemap.h | 1 + include/linux/rmap.h | 8 ++++++++ 3 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e695eaab4c..866a3dbe5c7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1104,6 +1104,9 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff); extern void exit_mmap(struct mm_struct *); +extern int mm_take_all_locks(struct mm_struct *mm); +extern void mm_drop_all_locks(struct mm_struct *mm); + #ifdef CONFIG_PROC_FS /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ extern void added_exe_file_vma(struct mm_struct *mm); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a81d8189042..a39b38ccdc9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -20,6 +20,7 @@ */ #define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */ #define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */ +#define AS_MM_ALL_LOCKS (__GFP_BITS_SHIFT + 2) /* under mm_take_all_locks() */ static inline void mapping_set_error(struct address_space *mapping, int error) { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 1383692ac5b..69407f85e10 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -26,6 +26,14 @@ */ struct anon_vma { spinlock_t lock; /* Serialize access to vma list */ + /* + * NOTE: the LSB of the head.next is set by + * mm_take_all_locks() _after_ taking the above lock. So the + * head must only be read/written after taking the above lock + * to be sure to see a valid next pointer. The LSB bit itself + * is serialized by a system wide lock only visible to + * mm_take_all_locks() (mm_all_locks_mutex). + */ struct list_head head; /* List of private "related" vmas */ }; -- cgit v1.2.3-70-g09d2