summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/vm/unevictable-lru.txt61
-rw-r--r--mm/rmap.c36
2 files changed, 27 insertions, 70 deletions
diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.txt
index e983ee4e2758..fa3b527086fa 100644
--- a/Documentation/vm/unevictable-lru.txt
+++ b/Documentation/vm/unevictable-lru.txt
@@ -531,37 +531,20 @@ map.
try_to_unmap() is always called, by either vmscan for reclaim or for page
migration, with the argument page locked and isolated from the LRU. Separate
-functions handle anonymous and mapped file pages, as these types of pages have
-different reverse map mechanisms.
+functions handle anonymous and mapped file and KSM pages, as these types of
+pages have different reverse map lookup mechanisms, with different locking.
+In each case, whether rmap_walk_anon() or rmap_walk_file() or rmap_walk_ksm(),
+it will call try_to_unmap_one() for every VMA which might contain the page.
- (*) try_to_unmap_anon()
+When trying to reclaim, if try_to_unmap_one() finds the page in a VM_LOCKED
+VMA, it will then mlock the page via mlock_vma_page() instead of unmapping it,
+and return SWAP_MLOCK to indicate that the page is unevictable: and the scan
+stops there.
- To unmap anonymous pages, each VMA in the list anchored in the anon_vma
- must be visited - at least until a VM_LOCKED VMA is encountered. If the
- page is being unmapped for migration, VM_LOCKED VMAs do not stop the
- process because mlocked pages are migratable. However, for reclaim, if
- the page is mapped into a VM_LOCKED VMA, the scan stops.
-
- try_to_unmap_anon() attempts to acquire in read mode the mmap semaphore of
- the mm_struct to which the VMA belongs. If this is successful, it will
- mlock the page via mlock_vma_page() - we wouldn't have gotten to
- try_to_unmap_anon() if the page were already mlocked - and will return
- SWAP_MLOCK, indicating that the page is unevictable.
-
- If the mmap semaphore cannot be acquired, we are not sure whether the page
- is really unevictable or not. In this case, try_to_unmap_anon() will
- return SWAP_AGAIN.
-
- (*) try_to_unmap_file()
-
- Unmapping of a mapped file page works the same as for anonymous mappings,
- except that the scan visits all VMAs that map the page's index/page offset
- in the page's mapping's reverse map interval search tree.
-
- As for anonymous pages, on encountering a VM_LOCKED VMA for a mapped file
- page, try_to_unmap_file() will attempt to acquire the associated
- mm_struct's mmap semaphore to mlock the page, returning SWAP_MLOCK if this
- is successful, and SWAP_AGAIN, if not.
+mlock_vma_page() is called while holding the page table's lock (in addition
+to the page lock, and the rmap lock): to serialize against concurrent mlock or
+munlock or munmap system calls, mm teardown (munlock_vma_pages_all), reclaim,
+holepunching, and truncation of file pages and their anonymous COWed pages.
try_to_munlock() REVERSE MAP SCAN
@@ -577,22 +560,15 @@ all PTEs from the page. For this purpose, the unevictable/mlock infrastructure
introduced a variant of try_to_unmap() called try_to_munlock().
try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
-mapped file pages with an additional argument specifying unlock versus unmap
+mapped file and KSM pages with a flag argument specifying unlock versus unmap
processing. Again, these functions walk the respective reverse maps looking
for VM_LOCKED VMAs. When such a VMA is found, as in the try_to_unmap() case,
-the functions attempt to acquire the associated mmap semaphore, mlock the page
-via mlock_vma_page() and return SWAP_MLOCK. This effectively undoes the
-pre-clearing of the page's PG_mlocked done by munlock_vma_page.
-
-If try_to_unmap() is unable to acquire a VM_LOCKED VMA's associated mmap
-semaphore, it will return SWAP_AGAIN. This will allow shrink_page_list() to
-recycle the page on the inactive list and hope that it has better luck with the
-page next time.
+the functions mlock the page via mlock_vma_page() and return SWAP_MLOCK. This
+undoes the pre-clearing of the page's PG_mlocked done by munlock_vma_page.
Note that try_to_munlock()'s reverse map walk must visit every VMA in a page's
reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA.
-However, the scan can terminate when it encounters a VM_LOCKED VMA and can
-successfully acquire the VMA's mmap semaphore for read and mlock the page.
+However, the scan can terminate when it encounters a VM_LOCKED VMA.
Although try_to_munlock() might be called a great many times when munlocking a
large region or tearing down a large address space that has been mlocked via
mlockall(), overall this is a fairly rare event.
@@ -620,11 +596,6 @@ Some examples of these unevictable pages on the LRU lists are:
(3) mlocked pages that could not be isolated from the LRU and moved to the
unevictable list in mlock_vma_page().
- (4) Pages mapped into multiple VM_LOCKED VMAs, but try_to_munlock() couldn't
- acquire the VMA's mmap semaphore to test the flags and set PageMlocked.
- munlock_vma_page() was forced to let the page back on to the normal LRU
- list for vmscan to handle.
-
shrink_inactive_list() also diverts any unevictable pages that it finds on the
inactive lists to the appropriate zone's unevictable list.
diff --git a/mm/rmap.c b/mm/rmap.c
index 78a692827a63..b93fb540c525 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1304,6 +1304,10 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
int ret = SWAP_AGAIN;
enum ttu_flags flags = (enum ttu_flags)arg;
+ /* munlock has nothing to gain from examining un-locked vmas */
+ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
+ goto out;
+
pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
goto out;
@@ -1314,9 +1318,12 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* skipped over this mm) then we should reactivate it.
*/
if (!(flags & TTU_IGNORE_MLOCK)) {
- if (vma->vm_flags & VM_LOCKED)
- goto out_mlock;
-
+ if (vma->vm_flags & VM_LOCKED) {
+ /* Holding pte lock, we do *not* need mmap_sem here */
+ mlock_vma_page(page);
+ ret = SWAP_MLOCK;
+ goto out_unmap;
+ }
if (flags & TTU_MUNLOCK)
goto out_unmap;
}
@@ -1421,31 +1428,10 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
out_unmap:
pte_unmap_unlock(pte, ptl);
- if (ret != SWAP_FAIL && !(flags & TTU_MUNLOCK))
+ if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK))
mmu_notifier_invalidate_page(mm, address);
out:
return ret;
-
-out_mlock:
- pte_unmap_unlock(pte, ptl);
-
-
- /*
- * 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->rwsem or mapping->i_mmap_rwsem.
- * 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.
- */
- if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
- if (vma->vm_flags & VM_LOCKED) {
- mlock_vma_page(page);
- ret = SWAP_MLOCK;
- }
- up_read(&vma->vm_mm->mmap_sem);
- }
- return ret;
}
bool is_vma_temporary_stack(struct vm_area_struct *vma)