mm: Convert i_mmap_lock to a mutex
Straightforward conversion of i_mmap_lock to a mutex.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Miller <davem@davemloft.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Tony Luck <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
index 65f4c79..9c0a80d 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/lockstat.txt
@@ -136,7 +136,7 @@
dcache_lock: 1037 1161 0.38 45.32 774.51 6611 243371 0.15 306.48 77387.24
&inode->i_mutex: 161 286 18446744073709 62882.54 1244614.55 3653 20598 18446744073709 62318.60 1693822.74
&zone->lru_lock: 94 94 0.53 7.33 92.10 4366 32690 0.29 59.81 16350.06
- &inode->i_data.i_mmap_lock: 79 79 0.40 3.77 53.03 11779 87755 0.28 116.93 29898.44
+ &inode->i_data.i_mmap_mutex: 79 79 0.40 3.77 53.03 11779 87755 0.28 116.93 29898.44
&q->__queue_lock: 48 50 0.52 31.62 86.31 774 13131 0.17 113.08 12277.52
&rq->rq_lock_key: 43 47 0.74 68.50 170.63 3706 33929 0.22 107.99 17460.62
&rq->rq_lock_key#2: 39 46 0.75 6.68 49.03 2979 32292 0.17 125.17 17137.63
diff --git a/Documentation/vm/locking b/Documentation/vm/locking
index 25fadb4..f61228b 100644
--- a/Documentation/vm/locking
+++ b/Documentation/vm/locking
@@ -66,7 +66,7 @@
expand_stack(), it is hard to come up with a destructive scenario without
having the vmlist protection in this case.
-The page_table_lock nests with the inode i_mmap_lock and the kmem cache
+The page_table_lock nests with the inode i_mmap_mutex and the kmem cache
c_spinlock spinlocks. This is okay, since the kmem code asks for pages after
dropping c_spinlock. The page_table_lock also nests with pagecache_lock and
pagemap_lru_lock spinlocks, and no code asks for memory with these locks
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index d420398..f581a18 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -72,7 +72,7 @@
if (!vma_shareable(vma, addr))
return;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
if (svma == vma)
continue;
@@ -97,7 +97,7 @@
put_page(virt_to_page(spte));
spin_unlock(&mm->page_table_lock);
out:
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/*
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b9eeb1c..e7a0357 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -412,10 +412,10 @@
pgoff = offset >> PAGE_SHIFT;
i_size_write(inode, offset);
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
if (!prio_tree_empty(&mapping->i_mmap))
hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
truncate_hugepages(inode, offset);
return 0;
}
diff --git a/fs/inode.c b/fs/inode.c
index 7a7284c..88aa3bc 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -326,7 +326,7 @@
memset(mapping, 0, sizeof(*mapping));
INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
spin_lock_init(&mapping->tree_lock);
- spin_lock_init(&mapping->i_mmap_lock);
+ mutex_init(&mapping->i_mmap_mutex);
INIT_LIST_HEAD(&mapping->private_list);
spin_lock_init(&mapping->private_lock);
INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5d2c86b..5bb9e82 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -634,7 +634,7 @@
unsigned int i_mmap_writable;/* count VM_SHARED mappings */
struct prio_tree_root i_mmap; /* tree of private and shared mappings */
struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
- spinlock_t i_mmap_lock; /* protect tree, count, list */
+ struct mutex i_mmap_mutex; /* protect tree, count, list */
unsigned long nrpages; /* number of total pages */
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index cc2e7df..a877dfc 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -150,7 +150,7 @@
* Therefore notifier chains can only be traversed when either
*
* 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock).
+ * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->lock).
* 3. No other concurrent thread can access the list (release)
*/
struct mmu_notifier {
diff --git a/kernel/fork.c b/kernel/fork.c
index 4eef925..9276927 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -383,14 +383,14 @@
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
if (tmp->vm_flags & VM_SHARED)
mapping->i_mmap_writable++;
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
vma_prio_tree_add(tmp, mpnt);
flush_dcache_mmap_unlock(mapping);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/*
diff --git a/mm/filemap.c b/mm/filemap.c
index 8144f87..88354ae 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -58,16 +58,16 @@
/*
* Lock ordering:
*
- * ->i_mmap_lock (truncate_pagecache)
+ * ->i_mmap_mutex (truncate_pagecache)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
*
* ->i_mutex
- * ->i_mmap_lock (truncate->unmap_mapping_range)
+ * ->i_mmap_mutex (truncate->unmap_mapping_range)
*
* ->mmap_sem
- * ->i_mmap_lock
+ * ->i_mmap_mutex
* ->page_table_lock or pte_lock (various, mainly in memory.c)
* ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock)
*
@@ -84,7 +84,7 @@
* sb_lock (fs/fs-writeback.c)
* ->mapping->tree_lock (__sync_single_inode)
*
- * ->i_mmap_lock
+ * ->i_mmap_mutex
* ->anon_vma.lock (vma_adjust)
*
* ->anon_vma.lock
@@ -106,7 +106,7 @@
*
* (code doesn't rely on that order, so you could switch it around)
* ->tasklist_lock (memory_failure, collect_procs_ao)
- * ->i_mmap_lock
+ * ->i_mmap_mutex
*/
/*
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 83364df..93356cd 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -183,7 +183,7 @@
return;
retry:
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
mm = vma->vm_mm;
address = vma->vm_start +
@@ -201,7 +201,7 @@
page_cache_release(page);
}
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
if (locked) {
mutex_unlock(&xip_sparse_mutex);
diff --git a/mm/fremap.c b/mm/fremap.c
index ec520c7..7f41230 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -211,13 +211,13 @@
}
goto out;
}
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
vma->vm_flags |= VM_NONLINEAR;
vma_prio_tree_remove(vma, &mapping->i_mmap);
vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
flush_dcache_mmap_unlock(mapping);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
if (vma->vm_flags & VM_LOCKED) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bbb4a5b..5fd68b9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2205,7 +2205,7 @@
unsigned long sz = huge_page_size(h);
/*
- * A page gathering list, protected by per file i_mmap_lock. The
+ * A page gathering list, protected by per file i_mmap_mutex. The
* lock is used to avoid list corruption from multiple unmapping
* of the same page since we are using page->lru.
*/
@@ -2274,9 +2274,9 @@
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
- spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
__unmap_hugepage_range(vma, start, end, ref_page);
- spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
}
/*
@@ -2308,7 +2308,7 @@
* this mapping should be shared between all the VMAs,
* __unmap_hugepage_range() is called as the lock is already held
*/
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
/* Do not unmap the current VMA */
if (iter_vma == vma)
@@ -2326,7 +2326,7 @@
address, address + huge_page_size(h),
page);
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return 1;
}
@@ -2810,7 +2810,7 @@
BUG_ON(address >= end);
flush_cache_range(vma, address, end);
- spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
spin_lock(&mm->page_table_lock);
for (; address < end; address += huge_page_size(h)) {
ptep = huge_pte_offset(mm, address);
@@ -2825,7 +2825,7 @@
}
}
spin_unlock(&mm->page_table_lock);
- spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+ mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
flush_tlb_range(vma, start, end);
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2b9a5ee..12178ec 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -429,7 +429,7 @@
*/
read_lock(&tasklist_lock);
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
for_each_process(tsk) {
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -449,7 +449,7 @@
add_to_kill(tsk, page, vma, to_kill, tkc);
}
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
read_unlock(&tasklist_lock);
}
diff --git a/mm/memory.c b/mm/memory.c
index 1865587..7bbe4d3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2667,12 +2667,12 @@
details.last_index = ULONG_MAX;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
EXPORT_SYMBOL(unmap_mapping_range);
diff --git a/mm/mmap.c b/mm/mmap.c
index 50cb04b..26efbfc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -194,7 +194,7 @@
}
/*
- * Requires inode->i_mapping->i_mmap_lock
+ * Requires inode->i_mapping->i_mmap_mutex
*/
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
struct file *file, struct address_space *mapping)
@@ -222,9 +222,9 @@
if (file) {
struct address_space *mapping = file->f_mapping;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
__remove_shared_vm_struct(vma, file, mapping);
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
}
@@ -446,13 +446,13 @@
mapping = vma->vm_file->f_mapping;
if (mapping)
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
__vma_link(mm, vma, prev, rb_link, rb_parent);
__vma_link_file(vma);
if (mapping)
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
mm->map_count++;
validate_mm(mm);
@@ -555,7 +555,7 @@
mapping = file->f_mapping;
if (!(vma->vm_flags & VM_NONLINEAR))
root = &mapping->i_mmap;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
if (insert) {
/*
* Put into prio_tree now, so instantiated pages
@@ -622,7 +622,7 @@
if (anon_vma)
anon_vma_unlock(anon_vma);
if (mapping)
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
if (remove_next) {
if (file) {
@@ -2290,7 +2290,7 @@
/* Insert vm structure into process list sorted by address
* and into the inode's i_mmap tree. If vm_file is non-NULL
- * then i_mmap_lock is taken here.
+ * then i_mmap_mutex is taken here.
*/
int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
@@ -2532,7 +2532,7 @@
*/
if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
BUG();
- spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
+ mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem);
}
}
@@ -2559,7 +2559,7 @@
* vma in this mm is backed by the same anon_vma or address_space.
*
* We can take all the locks in random order because the VM code
- * taking i_mmap_lock or anon_vma->lock outside the mmap_sem never
+ * taking i_mmap_mutex or anon_vma->lock outside the mmap_sem never
* takes more than one of them in a row. Secondly we're protected
* against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
*
@@ -2631,7 +2631,7 @@
* AS_MM_ALL_LOCKS can't change to 0 from under us
* because we hold the mm_all_locks_mutex.
*/
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
&mapping->flags))
BUG();
diff --git a/mm/mremap.c b/mm/mremap.c
index 909e1e1..506fa44 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -93,7 +93,7 @@
* and we propagate stale pages into the dst afterward.
*/
mapping = vma->vm_file->f_mapping;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
}
/*
@@ -122,7 +122,7 @@
pte_unmap(new_pte - 1);
pte_unmap_unlock(old_pte - 1, old_ptl);
if (mapping)
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 522e4a9..f0ef7ea 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -24,7 +24,7 @@
* inode->i_alloc_sem (vmtruncate_range)
* mm->mmap_sem
* page->flags PG_locked (lock_page)
- * mapping->i_mmap_lock
+ * mapping->i_mmap_mutex
* anon_vma->lock
* mm->page_table_lock or pte_lock
* zone->lru_lock (in mark_page_accessed, isolate_lru_page)
@@ -646,14 +646,14 @@
* The page lock not only makes sure that page->mapping cannot
* suddenly be NULLified by truncation, it makes sure that the
* structure at mapping cannot be freed and reused yet,
- * so we can safely take mapping->i_mmap_lock.
+ * so we can safely take mapping->i_mmap_mutex.
*/
BUG_ON(!PageLocked(page));
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
/*
- * i_mmap_lock does not stabilize mapcount at all, but mapcount
+ * i_mmap_mutex does not stabilize mapcount at all, but mapcount
* is more likely to be accurate if we note it after spinning.
*/
mapcount = page_mapcount(page);
@@ -675,7 +675,7 @@
break;
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return referenced;
}
@@ -762,7 +762,7 @@
BUG_ON(PageAnon(page));
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
if (vma->vm_flags & VM_SHARED) {
unsigned long address = vma_address(page, vma);
@@ -771,7 +771,7 @@
ret += page_mkclean_one(page, vma, address);
}
}
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return ret;
}
@@ -1119,7 +1119,7 @@
/*
* We need mmap_sem locking, Otherwise VM_LOCKED check makes
* unstable result and race. Plus, We can't wait here because
- * we now hold anon_vma->lock or mapping->i_mmap_lock.
+ * we now hold anon_vma->lock or mapping->i_mmap_mutex.
* if trylock failed, the page remain in evictable lru and later
* vmscan could retry to move the page to unevictable lru if the
* page is actually mlocked.
@@ -1345,7 +1345,7 @@
unsigned long max_nl_size = 0;
unsigned int mapcount;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
unsigned long address = vma_address(page, vma);
if (address == -EFAULT)
@@ -1391,7 +1391,7 @@
mapcount = page_mapcount(page);
if (!mapcount)
goto out;
- cond_resched_lock(&mapping->i_mmap_lock);
+ cond_resched();
max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
if (max_nl_cursor == 0)
@@ -1413,7 +1413,7 @@
}
vma->vm_private_data = (void *) max_nl_cursor;
}
- cond_resched_lock(&mapping->i_mmap_lock);
+ cond_resched();
max_nl_cursor += CLUSTER_SIZE;
} while (max_nl_cursor <= max_nl_size);
@@ -1425,7 +1425,7 @@
list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
vma->vm_private_data = NULL;
out:
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return ret;
}
@@ -1544,7 +1544,7 @@
if (!mapping)
return ret;
- spin_lock(&mapping->i_mmap_lock);
+ mutex_lock(&mapping->i_mmap_mutex);
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
unsigned long address = vma_address(page, vma);
if (address == -EFAULT)
@@ -1558,7 +1558,7 @@
* never contain migration ptes. Decide what to do about this
* limitation to linear when we need rmap_walk() on nonlinear.
*/
- spin_unlock(&mapping->i_mmap_lock);
+ mutex_unlock(&mapping->i_mmap_mutex);
return ret;
}