summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2012-05-29 15:06:42 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-05-29 16:22:23 -0700
commit1635f6a74152f1dcd1b888231609d64875f0a81a (patch)
treea2919520e0a8fead3930d23136ca30829f0fc64a
parente2d12e22c59ce714008aa5266d769f8568d74eac (diff)
tmpfs: undo fallocation on failure
In the previous episode, we left the already-fallocated pages attached to the file when shmem_fallocate() fails part way through. Now try to do better, by extending the earlier optimization of !Uptodate pages (then always under page lock) to !Uptodate pages (outside of page lock), representing fallocated pages. And don't waste time clearing them at the time of fallocate(), leave that until later if necessary. Adapt shmem_truncate_range() to shmem_undo_range(), so that a failing fallocate can recognize and remove precisely those !Uptodate allocations which it added (and were not independently allocated by racing tasks). But unless we start playing with swapfile.c and memcontrol.c too, once one of our fallocated pages reaches shmem_writepage(), we do then have to instantiate it as an ordinarily allocated page, before swapping out. This is unsatisfactory, but improved in the next episode. Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Cong Wang <amwang@redhat.com> Cc: Kay Sievers <kay@vrfy.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/shmem.c105
1 files changed, 72 insertions, 33 deletions
diff --git a/mm/shmem.c b/mm/shmem.c
index 9b90d89e54ce..793dcd1bac8b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -89,7 +89,8 @@ enum sgp_type {
SGP_READ, /* don't exceed i_size, don't allocate page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */
- SGP_WRITE, /* may exceed i_size, may allocate page */
+ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
+ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
};
#ifdef CONFIG_TMPFS
@@ -427,8 +428,10 @@ void shmem_unlock_mapping(struct address_space *mapping)
/*
* Remove range of pages and swap entries from radix tree, and free them.
+ * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
*/
-void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
+ bool unfalloc)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
@@ -462,6 +465,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
break;
if (radix_tree_exceptional_entry(page)) {
+ if (unfalloc)
+ continue;
nr_swaps_freed += !shmem_free_swap(mapping,
index, page);
continue;
@@ -469,9 +474,11 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
if (!trylock_page(page))
continue;
- if (page->mapping == mapping) {
- VM_BUG_ON(PageWriteback(page));
- truncate_inode_page(mapping, page);
+ if (!unfalloc || !PageUptodate(page)) {
+ if (page->mapping == mapping) {
+ VM_BUG_ON(PageWriteback(page));
+ truncate_inode_page(mapping, page);
+ }
}
unlock_page(page);
}
@@ -517,12 +524,12 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr) {
- if (index == start)
+ if (index == start || unfalloc)
break;
index = start;
continue;
}
- if (index == start && indices[0] >= end) {
+ if ((index == start || unfalloc) && indices[0] >= end) {
shmem_deswap_pagevec(&pvec);
pagevec_release(&pvec);
break;
@@ -536,15 +543,19 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
break;
if (radix_tree_exceptional_entry(page)) {
+ if (unfalloc)
+ continue;
nr_swaps_freed += !shmem_free_swap(mapping,
index, page);
continue;
}
lock_page(page);
- if (page->mapping == mapping) {
- VM_BUG_ON(PageWriteback(page));
- truncate_inode_page(mapping, page);
+ if (!unfalloc || !PageUptodate(page)) {
+ if (page->mapping == mapping) {
+ VM_BUG_ON(PageWriteback(page));
+ truncate_inode_page(mapping, page);
+ }
}
unlock_page(page);
}
@@ -558,7 +569,11 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
info->swapped -= nr_swaps_freed;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
+}
+void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+ shmem_undo_range(inode, lstart, lend, false);
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
@@ -771,6 +786,18 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
goto redirty;
}
+
+ /*
+ * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC
+ * value into swapfile.c, the only way we can correctly account for a
+ * fallocated page arriving here is now to initialize it and write it.
+ */
+ if (!PageUptodate(page)) {
+ clear_highpage(page);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ }
+
swap = get_swap_page();
if (!swap.val)
goto redirty;
@@ -994,6 +1021,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
swp_entry_t swap;
int error;
int once = 0;
+ int alloced = 0;
if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))
return -EFBIG;
@@ -1005,19 +1033,21 @@ repeat:
page = NULL;
}
- if (sgp != SGP_WRITE &&
+ if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
goto failed;
}
+ /* fallocated page? */
+ if (page && !PageUptodate(page)) {
+ if (sgp != SGP_READ)
+ goto clear;
+ unlock_page(page);
+ page_cache_release(page);
+ page = NULL;
+ }
if (page || (sgp == SGP_READ && !swap.val)) {
- /*
- * Once we can get the page lock, it must be uptodate:
- * if there were an error in reading back from swap,
- * the page would not be inserted into the filecache.
- */
- BUG_ON(page && !PageUptodate(page));
*pagep = page;
return 0;
}
@@ -1114,9 +1144,18 @@ repeat:
inode->i_blocks += BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
+ alloced = true;
/*
- * Let SGP_WRITE caller clear ends if write does not fill page
+ * Let SGP_FALLOC use the SGP_WRITE optimization on a new page.
+ */
+ if (sgp == SGP_FALLOC)
+ sgp = SGP_WRITE;
+clear:
+ /*
+ * Let SGP_WRITE caller clear ends if write does not fill page;
+ * but SGP_FALLOC on a page fallocated earlier must initialize
+ * it now, lest undo on failure cancel our earlier guarantee.
*/
if (sgp != SGP_WRITE) {
clear_highpage(page);
@@ -1128,10 +1167,13 @@ repeat:
}
/* Perhaps the file has been truncated since we checked */
- if (sgp != SGP_WRITE &&
+ if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
- goto trunc;
+ if (alloced)
+ goto trunc;
+ else
+ goto failed;
}
*pagep = page;
return 0;
@@ -1140,6 +1182,7 @@ repeat:
* Error recovery.
*/
trunc:
+ info = SHMEM_I(inode);
ClearPageDirty(page);
delete_from_page_cache(page);
spin_lock(&info->lock);
@@ -1147,6 +1190,7 @@ trunc:
inode->i_blocks -= BLOCKS_PER_PAGE;
spin_unlock(&info->lock);
decused:
+ sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -1);
unacct:
@@ -1645,25 +1689,20 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
if (signal_pending(current))
error = -EINTR;
else
- error = shmem_getpage(inode, index, &page, SGP_WRITE,
+ error = shmem_getpage(inode, index, &page, SGP_FALLOC,
NULL);
if (error) {
- /*
- * We really ought to free what we allocated so far,
- * but it would be wrong to free pages allocated
- * earlier, or already now in use: i_mutex does not
- * exclude all cases. We do not know what to free.
- */
+ /* Remove the !PageUptodate pages we added */
+ shmem_undo_range(inode,
+ (loff_t)start << PAGE_CACHE_SHIFT,
+ (loff_t)index << PAGE_CACHE_SHIFT, true);
goto ctime;
}
- if (!PageUptodate(page)) {
- clear_highpage(page);
- flush_dcache_page(page);
- SetPageUptodate(page);
- }
/*
- * set_page_dirty so that memory pressure will swap rather
+ * If !PageUptodate, leave it that way so that freeable pages
+ * can be recognized if we need to rollback on error later.
+ * But set_page_dirty so that memory pressure will swap rather
* than free the pages we are allocating (and SGP_CACHE pages
* might still be clean: we now need to mark those dirty too).
*/