Commit 5a720394 authored by Lukas Czerner's avatar Lukas Czerner Committed by Theodore Ts'o

mm: teach truncate_inode_pages_range() to handle non page aligned ranges

This commit changes truncate_inode_pages_range() so it can handle non
page aligned regions of the truncate. Currently we can hit BUG_ON when
the end of the range is not page aligned, but we can handle unaligned
start of the range.

Being able to handle non page aligned regions of the page can help file
system punch_hole implementations and save some work, because once we're
holding the page we might as well deal with it right away.

In previous commits we've changed ->invalidatepage() prototype to accept
'length' argument to be able to specify range to invalidate. No we can
use that new ability in truncate_inode_pages_range().
Signed-off-by: default avatarLukas Czerner <lczerner@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: default avatarTheodore Ts'o <tytso@mit.edu>
parent bad54831
...@@ -52,14 +52,6 @@ void do_invalidatepage(struct page *page, unsigned int offset, ...@@ -52,14 +52,6 @@ void do_invalidatepage(struct page *page, unsigned int offset,
(*invalidatepage)(page, offset, length); (*invalidatepage)(page, offset, length);
} }
static inline void truncate_partial_page(struct page *page, unsigned partial)
{
zero_user_segment(page, partial, PAGE_CACHE_SIZE);
cleancache_invalidate_page(page->mapping, page);
if (page_has_private(page))
do_invalidatepage(page, partial, PAGE_CACHE_SIZE - partial);
}
/* /*
* This cancels just the dirty bit on the kernel page itself, it * This cancels just the dirty bit on the kernel page itself, it
* does NOT actually remove dirty bits on any mmap's that may be * does NOT actually remove dirty bits on any mmap's that may be
...@@ -188,11 +180,11 @@ int invalidate_inode_page(struct page *page) ...@@ -188,11 +180,11 @@ int invalidate_inode_page(struct page *page)
* truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
* @mapping: mapping to truncate * @mapping: mapping to truncate
* @lstart: offset from which to truncate * @lstart: offset from which to truncate
* @lend: offset to which to truncate * @lend: offset to which to truncate (inclusive)
* *
* Truncate the page cache, removing the pages that are between * Truncate the page cache, removing the pages that are between
* specified offsets (and zeroing out partial page * specified offsets (and zeroing out partial pages
* (if lstart is not page aligned)). * if lstart or lend + 1 is not page aligned).
* *
* Truncate takes two passes - the first pass is nonblocking. It will not * Truncate takes two passes - the first pass is nonblocking. It will not
* block on page locks and it will not block on writeback. The second pass * block on page locks and it will not block on writeback. The second pass
...@@ -203,35 +195,58 @@ int invalidate_inode_page(struct page *page) ...@@ -203,35 +195,58 @@ int invalidate_inode_page(struct page *page)
* We pass down the cache-hot hint to the page freeing code. Even if the * We pass down the cache-hot hint to the page freeing code. Even if the
* mapping is large, it is probably the case that the final pages are the most * mapping is large, it is probably the case that the final pages are the most
* recently touched, and freeing happens in ascending file offset order. * recently touched, and freeing happens in ascending file offset order.
*
* Note that since ->invalidatepage() accepts range to invalidate
* truncate_inode_pages_range is able to handle cases where lend + 1 is not
* page aligned properly.
*/ */
void truncate_inode_pages_range(struct address_space *mapping, void truncate_inode_pages_range(struct address_space *mapping,
loff_t lstart, loff_t lend) loff_t lstart, loff_t lend)
{ {
const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; pgoff_t start; /* inclusive */
const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1); pgoff_t end; /* exclusive */
unsigned int partial_start; /* inclusive */
unsigned int partial_end; /* exclusive */
struct pagevec pvec; struct pagevec pvec;
pgoff_t index; pgoff_t index;
pgoff_t end;
int i; int i;
cleancache_invalidate_inode(mapping); cleancache_invalidate_inode(mapping);
if (mapping->nrpages == 0) if (mapping->nrpages == 0)
return; return;
BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1)); /* Offsets within partial pages */
end = (lend >> PAGE_CACHE_SHIFT); partial_start = lstart & (PAGE_CACHE_SIZE - 1);
partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
/*
* 'start' and 'end' always covers the range of pages to be fully
* truncated. Partial pages are covered with 'partial_start' at the
* start of the range and 'partial_end' at the end of the range.
* Note that 'end' is exclusive while 'lend' is inclusive.
*/
start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (lend == -1)
/*
* lend == -1 indicates end-of-file so we have to set 'end'
* to the highest possible pgoff_t and since the type is
* unsigned we're using -1.
*/
end = -1;
else
end = (lend + 1) >> PAGE_CACHE_SHIFT;
pagevec_init(&pvec, 0); pagevec_init(&pvec, 0);
index = start; index = start;
while (index <= end && pagevec_lookup(&pvec, mapping, index, while (index < end && pagevec_lookup(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
mem_cgroup_uncharge_start(); mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) { for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i]; struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */ /* We rely upon deletion not changing page->index */
index = page->index; index = page->index;
if (index > end) if (index >= end)
break; break;
if (!trylock_page(page)) if (!trylock_page(page))
...@@ -250,27 +265,56 @@ void truncate_inode_pages_range(struct address_space *mapping, ...@@ -250,27 +265,56 @@ void truncate_inode_pages_range(struct address_space *mapping,
index++; index++;
} }
if (partial) { if (partial_start) {
struct page *page = find_lock_page(mapping, start - 1); struct page *page = find_lock_page(mapping, start - 1);
if (page) { if (page) {
unsigned int top = PAGE_CACHE_SIZE;
if (start > end) {
/* Truncation within a single page */
top = partial_end;
partial_end = 0;
}
wait_on_page_writeback(page); wait_on_page_writeback(page);
truncate_partial_page(page, partial); zero_user_segment(page, partial_start, top);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, partial_start,
top - partial_start);
unlock_page(page); unlock_page(page);
page_cache_release(page); page_cache_release(page);
} }
} }
if (partial_end) {
struct page *page = find_lock_page(mapping, end);
if (page) {
wait_on_page_writeback(page);
zero_user_segment(page, 0, partial_end);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, 0,
partial_end);
unlock_page(page);
page_cache_release(page);
}
}
/*
* If the truncation happened within a single page no pages
* will be released, just zeroed, so we can bail out now.
*/
if (start >= end)
return;
index = start; index = start;
for ( ; ; ) { for ( ; ; ) {
cond_resched(); cond_resched();
if (!pagevec_lookup(&pvec, mapping, index, if (!pagevec_lookup(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
if (index == start) if (index == start)
break; break;
index = start; index = start;
continue; continue;
} }
if (index == start && pvec.pages[0]->index > end) { if (index == start && pvec.pages[0]->index >= end) {
pagevec_release(&pvec); pagevec_release(&pvec);
break; break;
} }
...@@ -280,7 +324,7 @@ void truncate_inode_pages_range(struct address_space *mapping, ...@@ -280,7 +324,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
/* We rely upon deletion not changing page->index */ /* We rely upon deletion not changing page->index */
index = page->index; index = page->index;
if (index > end) if (index >= end)
break; break;
lock_page(page); lock_page(page);
...@@ -601,10 +645,8 @@ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) ...@@ -601,10 +645,8 @@ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
* This rounding is currently just for example: unmap_mapping_range * This rounding is currently just for example: unmap_mapping_range
* expands its hole outwards, whereas we want it to contract the hole * expands its hole outwards, whereas we want it to contract the hole
* inwards. However, existing callers of truncate_pagecache_range are * inwards. However, existing callers of truncate_pagecache_range are
* doing their own page rounding first; and truncate_inode_pages_range * doing their own page rounding first. Note that unmap_mapping_range
* currently BUGs if lend is not pagealigned-1 (it handles partial * allows holelen 0 for all, and we allow lend -1 for end of file.
* page at start of hole, but not partial page at end of hole). Note
* unmap_mapping_range allows holelen 0 for all, and we allow lend -1.
*/ */
/* /*
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment