summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-06-02 12:21:36 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-02 12:21:36 -0700
commit94709049fb8442fb2f7b91fbec3c2897a75e18df (patch)
treef1d38ea6bc9db6d5a15ba4821c83abeb7ce7fd35 /fs
parent17839856fd588f4ab6b789f482ed3ffd7c403e1f (diff)
parent4fba37586e4e73f9f9a855e610e151ef7da2b481 (diff)
Merge branch 'akpm' (patches from Andrew)
Merge updates from Andrew Morton: "A few little subsystems and a start of a lot of MM patches. Subsystems affected by this patch series: squashfs, ocfs2, parisc, vfs. With mm subsystems: slab-generic, slub, debug, pagecache, gup, swap, memcg, pagemap, memory-failure, vmalloc, kasan" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (128 commits) kasan: move kasan_report() into report.c mm/mm_init.c: report kasan-tag information stored in page->flags ubsan: entirely disable alignment checks under UBSAN_TRAP kasan: fix clang compilation warning due to stack protector x86/mm: remove vmalloc faulting mm: remove vmalloc_sync_(un)mappings() x86/mm/32: implement arch_sync_kernel_mappings() x86/mm/64: implement arch_sync_kernel_mappings() mm/ioremap: track which page-table levels were modified mm/vmalloc: track which page-table levels were modified mm: add functions to track page directory modifications s390: use __vmalloc_node in stack_alloc powerpc: use __vmalloc_node in alloc_vm_stack arm64: use __vmalloc_node in arch_alloc_vmap_stack mm: remove vmalloc_user_node_flags mm: switch the test_vmalloc module to use __vmalloc_node mm: remove __vmalloc_node_flags_caller mm: remove both instances of __vmalloc_node_flags mm: remove the prot argument to __vmalloc_node mm: remove the pgprot argument to __vmalloc ...
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c7
-rw-r--r--fs/btrfs/disk-io.c4
-rw-r--r--fs/btrfs/extent_io.c64
-rw-r--r--fs/btrfs/extent_io.h3
-rw-r--r--fs/btrfs/inode.c39
-rw-r--r--fs/buffer.c23
-rw-r--r--fs/erofs/data.c39
-rw-r--r--fs/erofs/decompressor.c2
-rw-r--r--fs/erofs/zdata.c29
-rw-r--r--fs/exfat/inode.c7
-rw-r--r--fs/ext2/inode.c10
-rw-r--r--fs/ext4/ext4.h5
-rw-r--r--fs/ext4/inode.c21
-rw-r--r--fs/ext4/readpage.c25
-rw-r--r--fs/ext4/verity.c35
-rw-r--r--fs/f2fs/data.c50
-rw-r--r--fs/f2fs/f2fs.h14
-rw-r--r--fs/f2fs/verity.c35
-rw-r--r--fs/fat/inode.c7
-rw-r--r--fs/file_table.c1
-rw-r--r--fs/fs-writeback.c1
-rw-r--r--fs/fuse/file.c100
-rw-r--r--fs/gfs2/aops.c23
-rw-r--r--fs/gfs2/dir.c9
-rw-r--r--fs/gfs2/quota.c2
-rw-r--r--fs/hpfs/file.c7
-rw-r--r--fs/iomap/buffered-io.c111
-rw-r--r--fs/iomap/trace.h2
-rw-r--r--fs/isofs/inode.c7
-rw-r--r--fs/jfs/inode.c7
-rw-r--r--fs/mpage.c38
-rw-r--r--fs/nfs/blocklayout/extent_tree.c2
-rw-r--r--fs/nfs/internal.h10
-rw-r--r--fs/nfs/write.c4
-rw-r--r--fs/nfsd/vfs.c9
-rw-r--r--fs/nilfs2/inode.c15
-rw-r--r--fs/ntfs/aops.c2
-rw-r--r--fs/ntfs/malloc.h2
-rw-r--r--fs/ntfs/mft.c2
-rw-r--r--fs/ocfs2/aops.c34
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c1
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--fs/ocfs2/slot_map.c46
-rw-r--r--fs/ocfs2/super.c21
-rw-r--r--fs/omfs/file.c7
-rw-r--r--fs/open.c3
-rw-r--r--fs/orangefs/inode.c32
-rw-r--r--fs/proc/meminfo.c3
-rw-r--r--fs/proc/task_mmu.c16
-rw-r--r--fs/qnx6/inode.c7
-rw-r--r--fs/reiserfs/inode.c8
-rw-r--r--fs/squashfs/block.c273
-rw-r--r--fs/squashfs/decompressor.h5
-rw-r--r--fs/squashfs/decompressor_multi.c9
-rw-r--r--fs/squashfs/decompressor_multi_percpu.c8
-rw-r--r--fs/squashfs/decompressor_single.c9
-rw-r--r--fs/squashfs/lz4_wrapper.c17
-rw-r--r--fs/squashfs/lzo_wrapper.c17
-rw-r--r--fs/squashfs/squashfs.h4
-rw-r--r--fs/squashfs/xz_wrapper.c51
-rw-r--r--fs/squashfs/zlib_wrapper.c63
-rw-r--r--fs/squashfs/zstd_wrapper.c64
-rw-r--r--fs/sync.c6
-rw-r--r--fs/ubifs/debug.c2
-rw-r--r--fs/ubifs/lprops.c2
-rw-r--r--fs/ubifs/lpt_commit.c4
-rw-r--r--fs/ubifs/orphan.c2
-rw-r--r--fs/udf/inode.c7
-rw-r--r--fs/xfs/kmem.c2
-rw-r--r--fs/xfs/xfs_aops.c13
-rw-r--r--fs/xfs/xfs_buf.c2
-rw-r--r--fs/zonefs/super.c7
72 files changed, 642 insertions, 880 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 93672c3f1c78..f05e2f2c898d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -614,10 +614,9 @@ static int blkdev_readpage(struct file * file, struct page * page)
return block_read_full_page(page, blkdev_get_block);
}
-static int blkdev_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void blkdev_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
+ mpage_readahead(rac, blkdev_get_block);
}
static int blkdev_write_begin(struct file *file, struct address_space *mapping,
@@ -2085,7 +2084,7 @@ static int blkdev_writepages(struct address_space *mapping,
static const struct address_space_operations def_blk_aops = {
.readpage = blkdev_readpage,
- .readpages = blkdev_readpages,
+ .readahead = blkdev_readahead,
.writepage = blkdev_writepage,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d10c7be10f3b..7278789ff8a7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -980,9 +980,7 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
"page private not zero on page %llu",
(unsigned long long)page_offset(page));
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
+ detach_page_private(page);
}
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 39e45b8a5031..e12eb32d9e17 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3076,22 +3076,16 @@ static int submit_extent_page(unsigned int opf,
static void attach_extent_buffer_page(struct extent_buffer *eb,
struct page *page)
{
- if (!PagePrivate(page)) {
- SetPagePrivate(page);
- get_page(page);
- set_page_private(page, (unsigned long)eb);
- } else {
+ if (!PagePrivate(page))
+ attach_page_private(page, eb);
+ else
WARN_ON(page->private != (unsigned long)eb);
- }
}
void set_page_extent_mapped(struct page *page)
{
- if (!PagePrivate(page)) {
- SetPagePrivate(page);
- get_page(page);
- set_page_private(page, EXTENT_PAGE_PRIVATE);
- }
+ if (!PagePrivate(page))
+ attach_page_private(page, (void *)EXTENT_PAGE_PRIVATE);
}
static struct extent_map *
@@ -4367,51 +4361,32 @@ int extent_writepages(struct address_space *mapping,
return ret;
}
-int extent_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages)
+void extent_readahead(struct readahead_control *rac)
{
struct bio *bio = NULL;
unsigned long bio_flags = 0;
struct page *pagepool[16];
struct extent_map *em_cached = NULL;
- int nr = 0;
u64 prev_em_start = (u64)-1;
+ int nr;
- while (!list_empty(pages)) {
- u64 contig_end = 0;
-
- for (nr = 0; nr < ARRAY_SIZE(pagepool) && !list_empty(pages);) {
- struct page *page = lru_to_page(pages);
-
- prefetchw(&page->flags);
- list_del(&page->lru);
- if (add_to_page_cache_lru(page, mapping, page->index,
- readahead_gfp_mask(mapping))) {
- put_page(page);
- break;
- }
-
- pagepool[nr++] = page;
- contig_end = page_offset(page) + PAGE_SIZE - 1;
- }
+ while ((nr = readahead_page_batch(rac, pagepool))) {
+ u64 contig_start = page_offset(pagepool[0]);
+ u64 contig_end = page_offset(pagepool[nr - 1]) + PAGE_SIZE - 1;
- if (nr) {
- u64 contig_start = page_offset(pagepool[0]);
+ ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end);
- ASSERT(contig_start + nr * PAGE_SIZE - 1 == contig_end);
-
- contiguous_readpages(pagepool, nr, contig_start,
- contig_end, &em_cached, &bio, &bio_flags,
- &prev_em_start);
- }
+ contiguous_readpages(pagepool, nr, contig_start, contig_end,
+ &em_cached, &bio, &bio_flags, &prev_em_start);
}
if (em_cached)
free_extent_map(em_cached);
- if (bio)
- return submit_one_bio(bio, 0, bio_flags);
- return 0;
+ if (bio) {
+ if (submit_one_bio(bio, 0, bio_flags))
+ return;
+ }
}
/*
@@ -4929,10 +4904,7 @@ static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
* We need to make sure we haven't be attached
* to a new eb.
*/
- ClearPagePrivate(page);
- set_page_private(page, 0);
- /* One for the page private */
- put_page(page);
+ detach_page_private(page);
}
if (mapped)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 2ed65bd0760e..25594e09fdcd 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -198,8 +198,7 @@ int extent_writepages(struct address_space *mapping,
struct writeback_control *wbc);
int btree_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc);
-int extent_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages);
+void extent_readahead(struct readahead_control *rac);
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
void set_page_extent_mapped(struct page *page);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 320d1062068d..8b3489f229c7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4856,8 +4856,8 @@ static void evict_inode_truncate_pages(struct inode *inode)
/*
* Keep looping until we have no more ranges in the io tree.
- * We can have ongoing bios started by readpages (called from readahead)
- * that have their endio callback (extent_io.c:end_bio_extent_readpage)
+ * We can have ongoing bios started by readahead that have
+ * their endio callback (extent_io.c:end_bio_extent_readpage)
* still in progress (unlocked the pages in the bio but did not yet
* unlocked the ranges in the io tree). Therefore this means some
* ranges can still be locked and eviction started because before
@@ -7050,11 +7050,11 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
* for it to complete) and then invalidate the pages for
* this range (through invalidate_inode_pages2_range()),
* but that can lead us to a deadlock with a concurrent
- * call to readpages() (a buffered read or a defrag call
+ * call to readahead (a buffered read or a defrag call
* triggered a readahead) on a page lock due to an
* ordered dio extent we created before but did not have
* yet a corresponding bio submitted (whence it can not
- * complete), which makes readpages() wait for that
+ * complete), which makes readahead wait for that
* ordered extent to complete while holding a lock on
* that page.
*/
@@ -8293,21 +8293,16 @@ static int btrfs_writepages(struct address_space *mapping,
return extent_writepages(mapping, wbc);
}
-static int
-btrfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void btrfs_readahead(struct readahead_control *rac)
{
- return extent_readpages(mapping, pages, nr_pages);
+ extent_readahead(rac);
}
static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
int ret = try_release_extent_mapping(page, gfp_flags);
- if (ret == 1) {
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
- }
+ if (ret == 1)
+ detach_page_private(page);
return ret;
}
@@ -8329,14 +8324,8 @@ static int btrfs_migratepage(struct address_space *mapping,
if (ret != MIGRATEPAGE_SUCCESS)
return ret;
- if (page_has_private(page)) {
- ClearPagePrivate(page);
- get_page(newpage);
- set_page_private(newpage, page_private(page));
- set_page_private(page, 0);
- put_page(page);
- SetPagePrivate(newpage);
- }
+ if (page_has_private(page))
+ attach_page_private(newpage, detach_page_private(page));
if (PagePrivate2(page)) {
ClearPagePrivate2(page);
@@ -8458,11 +8447,7 @@ again:
}
ClearPageChecked(page);
- if (PagePrivate(page)) {
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
- }
+ detach_page_private(page);
}
/*
@@ -10553,7 +10538,7 @@ static const struct address_space_operations btrfs_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
- .readpages = btrfs_readpages,
+ .readahead = btrfs_readahead,
.direct_IO = btrfs_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
diff --git a/fs/buffer.c b/fs/buffer.c
index a60f60396cfa..64fe82ec65ff 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -123,14 +123,6 @@ void __wait_on_buffer(struct buffer_head * bh)
}
EXPORT_SYMBOL(__wait_on_buffer);
-static void
-__clear_page_buffers(struct page *page)
-{
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
-}
-
static void buffer_io_error(struct buffer_head *bh, char *msg)
{
if (!test_bit(BH_Quiet, &bh->b_state))
@@ -906,7 +898,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
- attach_page_buffers(page, head);
+ attach_page_private(page, head);
}
static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
@@ -1154,12 +1146,19 @@ EXPORT_SYMBOL(mark_buffer_dirty);
void mark_buffer_write_io_error(struct buffer_head *bh)
{
+ struct super_block *sb;
+
set_buffer_write_io_error(bh);
/* FIXME: do we need to set this in both places? */
if (bh->b_page && bh->b_page->mapping)
mapping_set_error(bh->b_page->mapping, -EIO);
if (bh->b_assoc_map)
mapping_set_error(bh->b_assoc_map, -EIO);
+ rcu_read_lock();
+ sb = READ_ONCE(bh->b_bdev->bd_super);
+ if (sb)
+ errseq_set(&sb->s_wb_err, -EIO);
+ rcu_read_unlock();
}
EXPORT_SYMBOL(mark_buffer_write_io_error);
@@ -1580,7 +1579,7 @@ void create_empty_buffers(struct page *page,
bh = bh->b_this_page;
} while (bh != head);
}
- attach_page_buffers(page, head);
+ attach_page_private(page, head);
spin_unlock(&page->mapping->private_lock);
}
EXPORT_SYMBOL(create_empty_buffers);
@@ -2567,7 +2566,7 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
bh->b_this_page = head;
bh = bh->b_this_page;
} while (bh != head);
- attach_page_buffers(page, head);
+ attach_page_private(page, head);
spin_unlock(&page->mapping->private_lock);
}
@@ -3227,7 +3226,7 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
bh = next;
} while (bh != head);
*buffers_to_free = head;
- __clear_page_buffers(page);
+ detach_page_private(page);
return 1;
failed:
return 0;
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index fc3a8d8064f8..d0542151e8c4 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -280,47 +280,36 @@ static int erofs_raw_access_readpage(struct file *file, struct page *page)
return 0;
}
-static int erofs_raw_access_readpages(struct file *filp,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned int nr_pages)
+static void erofs_raw_access_readahead(struct readahead_control *rac)
{
erofs_off_t last_block;
struct bio *bio = NULL;
- gfp_t gfp = readahead_gfp_mask(mapping);
- struct page *page = list_last_entry(pages, struct page, lru);
-
- trace_erofs_readpages(mapping->host, page, nr_pages, true);
+ struct page *page;
- for (; nr_pages; --nr_pages) {
- page = list_entry(pages->prev, struct page, lru);
+ trace_erofs_readpages(rac->mapping->host, readahead_index(rac),
+ readahead_count(rac), true);
+ while ((page = readahead_page(rac))) {
prefetchw(&page->flags);
- list_del(&page->lru);
- if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) {
- bio = erofs_read_raw_page(bio, mapping, page,
- &last_block, nr_pages, true);
+ bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
+ readahead_count(rac), true);
- /* all the page errors are ignored when readahead */
- if (IS_ERR(bio)) {
- pr_err("%s, readahead error at page %lu of nid %llu\n",
- __func__, page->index,
- EROFS_I(mapping->host)->nid);
+ /* all the page errors are ignored when readahead */
+ if (IS_ERR(bio)) {
+ pr_err("%s, readahead error at page %lu of nid %llu\n",
+ __func__, page->index,
+ EROFS_I(rac->mapping->host)->nid);
- bio = NULL;
- }
+ bio = NULL;
}
- /* pages could still be locked */
put_page(page);
}
- DBG_BUGON(!list_empty(pages));
/* the rare case (end in gaps) */
if (bio)
submit_bio(bio);
- return 0;
}
static int erofs_get_block(struct inode *inode, sector_t iblock,
@@ -358,7 +347,7 @@ static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
/* for uncompressed (aligned) files and raw access for other files */
const struct address_space_operations erofs_raw_access_aops = {
.readpage = erofs_raw_access_readpage,
- .readpages = erofs_raw_access_readpages,
+ .readahead = erofs_raw_access_readahead,
.bmap = erofs_bmap,
};
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 5d2d81940679..7628816f2453 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -274,7 +274,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq,
i = 0;
while (1) {
- dst = vm_map_ram(rq->out, nrpages_out, -1, PAGE_KERNEL);
+ dst = vm_map_ram(rq->out, nrpages_out, -1);
/* retry two more times (totally 3 times) */
if (dst || ++i >= 3)
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index c4b6c9aa87ec..187f93b4900e 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1305,28 +1305,23 @@ static bool should_decompress_synchronously(struct erofs_sb_info *sbi,
return nr <= sbi->max_sync_decompress_pages;
}
-static int z_erofs_readpages(struct file *filp, struct address_space *mapping,
- struct list_head *pages, unsigned int nr_pages)
+static void z_erofs_readahead(struct readahead_control *rac)
{
- struct inode *const inode = mapping->host;
+ struct inode *const inode = rac->mapping->host;
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
- bool sync = should_decompress_synchronously(sbi, nr_pages);
+ bool sync = should_decompress_synchronously(sbi, readahead_count(rac));
struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
- gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
- struct page *head = NULL;
+ struct page *page, *head = NULL;
LIST_HEAD(pagepool);
- trace_erofs_readpages(mapping->host, lru_to_page(pages),
- nr_pages, false);
+ trace_erofs_readpages(inode, readahead_index(rac),
+ readahead_count(rac), false);
- f.headoffset = (erofs_off_t)lru_to_page(pages)->index << PAGE_SHIFT;
-
- for (; nr_pages; --nr_pages) {
- struct page *page = lru_to_page(pages);
+ f.headoffset = readahead_pos(rac);
+ while ((page = readahead_page(rac))) {
prefetchw(&page->flags);
- list_del(&page->lru);
/*
* A pure asynchronous readahead is indicated if
@@ -1335,11 +1330,6 @@ static int z_erofs_readpages(struct file *filp, struct address_space *mapping,
*/
sync &= !(PageReadahead(page) && !head);
- if (add_to_page_cache_lru(page, mapping, page->index, gfp)) {
- list_add(&page->lru, &pagepool);
- continue;
- }
-
set_page_private(page, (unsigned long)head);
head = page;
}
@@ -1368,11 +1358,10 @@ static int z_erofs_readpages(struct file *filp, struct address_space *mapping,
/* clean up the remaining free pages */
put_pages_list(&pagepool);
- return 0;
}
const struct address_space_operations z_erofs_aops = {
.readpage = z_erofs_readpage,
- .readpages = z_erofs_readpages,
+ .readahead = z_erofs_readahead,
};
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index 06887492f54b..785ead346543 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -372,10 +372,9 @@ static int exfat_readpage(struct file *file, struct page *page)
return mpage_readpage(page, exfat_get_block);
}
-static int exfat_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned int nr_pages)
+static void exfat_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, exfat_get_block);
+ mpage_readahead(rac, exfat_get_block);
}
static int exfat_writepage(struct page *page, struct writeback_control *wbc)
@@ -502,7 +501,7 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from)
static const struct address_space_operations exfat_aops = {
.readpage = exfat_readpage,
- .readpages = exfat_readpages,
+ .readahead = exfat_readahead,
.writepage = exfat_writepage,
.writepages = exfat_writepages,
.write_begin = exfat_write_begin,
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index c885cf7d724b..2875c0a705b5 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -877,11 +877,9 @@ static int ext2_readpage(struct file *file, struct page *page)
return mpage_readpage(page, ext2_get_block);
}
-static int
-ext2_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void ext2_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
+ mpage_readahead(rac, ext2_get_block);
}
static int
@@ -967,7 +965,7 @@ ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc
const struct address_space_operations ext2_aops = {
.readpage = ext2_readpage,
- .readpages = ext2_readpages,
+ .readahead = ext2_readahead,
.writepage = ext2_writepage,
.write_begin = ext2_write_begin,
.write_end = ext2_write_end,
@@ -981,7 +979,7 @@ const struct address_space_operations ext2_aops = {
const struct address_space_operations ext2_nobh_aops = {
.readpage = ext2_readpage,
- .readpages = ext2_readpages,
+ .readahead = ext2_readahead,
.writepage = ext2_nobh_writepage,
.write_begin = ext2_nobh_write_begin,
.write_end = nobh_write_end,
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3147bb0cf82a..15b062efcff1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3317,9 +3317,8 @@ static inline void ext4_set_de_type(struct super_block *sb,
}
/* readpages.c */
-extern int ext4_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead);
+extern int ext4_mpage_readpages(struct inode *inode,
+ struct readahead_control *rac, struct page *page);
extern int __init ext4_init_post_read_processing(void);
extern void ext4_exit_post_read_processing(void);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2a4aae6acdcb..52be85f96159 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3224,23 +3224,20 @@ static int ext4_readpage(struct file *file, struct page *page)
ret = ext4_readpage_inline(inode, page);
if (ret == -EAGAIN)
- return ext4_mpage_readpages(page->mapping, NULL, page, 1,
- false);
+ return ext4_mpage_readpages(inode, NULL, page);
return ret;
}
-static int
-ext4_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void ext4_readahead(struct readahead_control *rac)
{
- struct inode *inode = mapping->host;
+ struct inode *inode = rac->mapping->host;
- /* If the file has inline data, no need to do readpages. */
+ /* If the file has inline data, no need to do readahead. */
if (ext4_has_inline_data(inode))
- return 0;
+ return;
- return ext4_mpage_readpages(mapping, pages, NULL, nr_pages, true);
+ ext4_mpage_readpages(inode, rac, NULL);
}
static void ext4_invalidatepage(struct page *page, unsigned int offset,
@@ -3605,7 +3602,7 @@ static int ext4_set_page_dirty(struct page *page)
static const struct address_space_operations ext4_aops = {
.readpage = ext4_readpage,
- .readpages = ext4_readpages,
+ .readahead = ext4_readahead,
.writepage = ext4_writepage,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
@@ -3622,7 +3619,7 @@ static const struct address_space_operations ext4_aops = {
static const struct address_space_operations ext4_journalled_aops = {
.readpage = ext4_readpage,
- .readpages = ext4_readpages,
+ .readahead = ext4_readahead,
.writepage = ext4_writepage,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
@@ -3638,7 +3635,7 @@ static const struct address_space_operations ext4_journalled_aops = {
static const struct address_space_operations ext4_da_aops = {
.readpage = ext4_readpage,
- .readpages = ext4_readpages,
+ .readahead = ext4_readahead,
.writepage = ext4_writepage,
.writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index c1769afbf799..5761e9961682 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -7,8 +7,8 @@
*
* This was originally taken from fs/mpage.c
*
- * The intent is the ext4_mpage_readpages() function here is intended
- * to replace mpage_readpages() in the general case, not just for
+ * The ext4_mpage_readpages() function here is intended to
+ * replace mpage_readahead() in the general case, not just for
* encrypted files. It has some limitations (see below), where it
* will fall back to read_block_full_page(), but these limitations
* should only be hit when page_size != block_size.
@@ -221,14 +221,12 @@ static inline loff_t ext4_readpage_limit(struct inode *inode)
return i_size_read(inode);
}
-int ext4_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead)
+int ext4_mpage_readpages(struct inode *inode,
+ struct readahead_control *rac, struct page *page)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
- struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
@@ -241,6 +239,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
int length;
unsigned relative_block = 0;
struct ext4_map_blocks map;
+ unsigned int nr_pages = rac ? readahead_count(rac) : 1;
map.m_pblk = 0;
map.m_lblk = 0;
@@ -251,14 +250,9 @@ int ext4_mpage_readpages(struct address_space *mapping,
int fully_mapped = 1;
unsigned first_hole = blocks_per_page;
- if (pages) {
- page = lru_to_page(pages);
-
+ if (rac) {
+ page = readahead_page(rac);
prefetchw(&page->flags);
- list_del(&page->lru);
- if (add_to_page_cache_lru(page, mapping, page->index,
- readahead_gfp_mask(mapping)))
- goto next_page;
}
if (page_has_buffers(page))
@@ -381,7 +375,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
bio_set_op_attrs(bio, REQ_OP_READ,
- is_readahead ? REQ_RAHEAD : 0);
+ rac ? REQ_RAHEAD : 0);
}
length = first_hole << blkbits;
@@ -406,10 +400,9 @@ int ext4_mpage_readpages(struct address_space *mapping,
else
unlock_page(page);
next_page:
- if (pages)
+ if (rac)
put_page(page);
}
- BUG_ON(pages && !list_empty(pages));
if (bio)
submit_bio(bio);
return 0;
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..dec1244dd062 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -342,37 +342,6 @@ static int ext4_get_verity_descriptor(struct inode *inode, void *buf,
return desc_size;
}
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void ext4_merkle_tree_readahead(struct address_space *mapping,
- pgoff_t start_index, unsigned long count)
-{
- LIST_HEAD(pages);
- unsigned int nr_pages = 0;
- struct page *page;
- pgoff_t index;
- struct blk_plug plug;
-
- for (index = start_index; index < start_index + count; index++) {
- page = xa_load(&mapping->i_pages, index);
- if (!page || xa_is_value(page)) {
- page = __page_cache_alloc(readahead_gfp_mask(mapping));
- if (!page)
- break;
- page->index = index;
- list_add(&page->lru, &pages);
- nr_pages++;
- }
- }
- blk_start_plug(&plug);
- ext4_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
- blk_finish_plug(&plug);
-}
-
static struct page *ext4_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
@@ -386,8 +355,8 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
if (page)
put_page(page);
else if (num_ra_pages > 1)
- ext4_merkle_tree_readahead(inode->i_mapping, index,
- num_ra_pages);
+ page_cache_readahead_unbounded(inode->i_mapping, NULL,
+ index, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index cdf2f626bea7..03ec97f28235 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2177,13 +2177,11 @@ out:
* use ->readpage() or do the necessary surgery to decouple ->readpages()
* from read-ahead.
*/
-int f2fs_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead)
+static int f2fs_mpage_readpages(struct inode *inode,
+ struct readahead_control *rac, struct page *page)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
- struct inode *inode = mapping->host;
struct f2fs_map_blocks map;
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct compress_ctx cc = {
@@ -2197,6 +2195,7 @@ int f2fs_mpage_readpages(struct address_space *mapping,
.nr_cpages = 0,
};
#endif
+ unsigned nr_pages = rac ? readahead_count(rac) : 1;
unsigned max_nr_pages = nr_pages;
int ret = 0;
@@ -2210,15 +2209,9 @@ int f2fs_mpage_readpages(struct address_space *mapping,
map.m_may_create = false;
for (; nr_pages; nr_pages--) {
- if (pages) {
- page = list_last_entry(pages, struct page, lru);
-
+ if (rac) {
+ page = readahead_page(rac);
prefetchw(&page->flags);
- list_del(&page->lru);
- if (add_to_page_cache_lru(page, mapping,
- page_index(page),
- readahead_gfp_mask(mapping)))
- goto next_page;
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -2228,7 +2221,7 @@ int f2fs_mpage_readpages(struct address_space *mapping,
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
- is_readahead, false);
+ rac != NULL, false);
f2fs_destroy_compress_ctx(&cc);
if (ret)
goto set_error_page;
@@ -2251,7 +2244,7 @@ read_single_page:
#endif
ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
- &bio, &last_block_in_bio, is_readahead);
+ &bio, &last_block_in_bio, rac);
if (ret) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
set_error_page:
@@ -2260,8 +2253,10 @@ set_error_page:
zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
}
+#ifdef CONFIG_F2FS_FS_COMPRESSION
next_page:
- if (pages)
+#endif
+ if (rac)
put_page(page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -2271,16 +2266,15 @@ next_page:
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
- is_readahead, false);
+ rac != NULL, false);
f2fs_destroy_compress_ctx(&cc);
}
}
#endif
}
- BUG_ON(pages && !list_empty(pages));
if (bio)
__submit_bio(F2FS_I_SB(inode), bio, DATA);
- return pages ? 0 : ret;
+ return ret;
}
static int f2fs_read_data_page(struct file *file, struct page *page)
@@ -2299,28 +2293,24 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
if (ret == -EAGAIN)
- ret = f2fs_mpage_readpages(page_file_mapping(page),
- NULL, page, 1, false);
+ ret = f2fs_mpage_readpages(inode, NULL, page);
return ret;
}
-static int f2fs_read_data_pages(struct file *file,
- struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void f2fs_readahead(struct readahead_control *rac)
{
- struct inode *inode = mapping->host;
- struct page *page = list_last_entry(pages, struct page, lru);
+ struct inode *inode = rac->mapping->host;
- trace_f2fs_readpages(inode, page, nr_pages);
+ trace_f2fs_readpages(inode, readahead_index(rac), readahead_count(rac));
if (!f2fs_is_compress_backend_ready(inode))
- return 0;
+ return;
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
- return 0;
+ return;
- return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
+ f2fs_mpage_readpages(inode, rac, NULL);
}
int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
@@ -3805,7 +3795,7 @@ static void f2fs_swap_deactivate(struct file *file)
const struct address_space_operations f2fs_dblock_aops = {
.readpage = f2fs_read_data_page,
- .readpages = f2fs_read_data_pages,
+ .readahead = f2fs_readahead,
.writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 157eec348970..5c0149d2f46a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3051,19 +3051,12 @@ static inline void f2fs_set_page_private(struct page *page,
if (PagePrivate(page))
return;
- get_page(page);
- SetPagePrivate(page);
- set_page_private(page, data);
+ attach_page_private(page, (void *)data);
}
static inline void f2fs_clear_page_private(struct page *page)
{
- if (!PagePrivate(page))
- return;
-
- set_page_private(page, 0);
- ClearPagePrivate(page);
- f2fs_put_page(page, 0);
+ detach_page_private(page);
}
/*
@@ -3373,9 +3366,6 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index d7d430a6f130..865c9fb774fb 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -222,37 +222,6 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
return size;
}
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void f2fs_merkle_tree_readahead(struct address_space *mapping,
- pgoff_t start_index, unsigned long count)
-{
- LIST_HEAD(pages);
- unsigned int nr_pages = 0;
- struct page *page;
- pgoff_t index;
- struct blk_plug plug;
-
- for (index = start_index; index < start_index + count; index++) {
- page = xa_load(&mapping->i_pages, index);
- if (!page || xa_is_value(page)) {
- page = __page_cache_alloc(readahead_gfp_mask(mapping));
- if (!page)
- break;
- page->index = index;
- list_add(&page->lru, &pages);
- nr_pages++;
- }
- }
- blk_start_plug(&plug);
- f2fs_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
- blk_finish_plug(&plug);
-}
-
static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
@@ -266,8 +235,8 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
if (page)
put_page(page);
else if (num_ra_pages > 1)
- f2fs_merkle_tree_readahead(inode->i_mapping, index,
- num_ra_pages);
+ page_cache_readahead_unbounded(inode->i_mapping, NULL,
+ index, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 71946da84388..e6e68b2274a5 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -210,10 +210,9 @@ static int fat_readpage(struct file *file, struct page *page)
return mpage_readpage(page, fat_get_block);
}
-static int fat_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void fat_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
+ mpage_readahead(rac, fat_get_block);
}
static void fat_write_failed(struct address_space *mapping, loff_t to)
@@ -344,7 +343,7 @@ int fat_block_truncate_page(struct inode *inode, loff_t from)
static const struct address_space_operations fat_aops = {
.readpage = fat_readpage,
- .readpages = fat_readpages,
+ .readahead = fat_readahead,
.writepage = fat_writepage,
.writepages = fat_writepages,
.write_begin = fat_write_begin,
diff --git a/fs/file_table.c b/fs/file_table.c
index 30d55c9a1744..676e620948d2 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -198,6 +198,7 @@ static struct file *alloc_file(const struct path *path, int flags,
file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
+ file->f_sb_err = file_sample_sb_err(file);
if ((file->f_mode & FMODE_READ) &&
likely(fop->read || fop->read_iter))
file->f_mode |= FMODE_CAN_READ;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 76ac9c7d32ec..c5bdf46e3b4b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1070,7 +1070,6 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
static unsigned long get_nr_dirty_pages(void)
{
return global_node_page_state(NR_FILE_DIRTY) +
- global_node_page_state(NR_UNSTABLE_NFS) +
get_nr_dirty_inodes();
}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9d67b830fb7a..bac51c32d660 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -915,84 +915,40 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
fuse_readpages_end(fc, &ap->args, err);
}
-struct fuse_fill_data {
- struct fuse_io_args *ia;
- struct file *file;
- struct inode *inode;
- unsigned int nr_pages;
- unsigned int max_pages;
-};
-
-static int fuse_readpages_fill(void *_data, struct page *page)
+static void fuse_readahead(struct readahead_control *rac)
{
- struct fuse_fill_data *data = _data;
- struct fuse_io_args *ia = data->ia;
- struct fuse_args_pages *ap = &ia->ap;
- struct inode *inode = data->inode;
+ struct inode *inode = rac->mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
+ unsigned int i, max_pages, nr_pages = 0;
- fuse_wait_on_page_writeback(inode, page->index);
-
- if (ap->num_pages &&
- (ap->num_pages == fc->max_pages ||
- (ap->num_pages + 1) * PAGE_SIZE > fc->max_read ||
- ap->pages[ap->num_pages - 1]->index + 1 != page->index)) {
- data->max_pages = min_t(unsigned int, data->nr_pages,
- fc->max_pages);
- fuse_send_readpages(ia, data->file);
- data->ia = ia = fuse_io_alloc(NULL, data->max_pages);
- if (!ia) {
- unlock_page(page);
- return -ENOMEM;
- }
- ap = &ia->ap;
- }
-
- if (WARN_ON(ap->num_pages >= data->max_pages)) {
- unlock_page(page);
- fuse_io_free(ia);
- return -EIO;
- }
-
- get_page(page);
- ap->pages[ap->num_pages] = page;
- ap->descs[ap->num_pages].length = PAGE_SIZE;
- ap->num_pages++;
- data->nr_pages--;
- return 0;
-}
-
-static int fuse_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
-{
- struct inode *inode = mapping->host;
- struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_fill_data data;
- int err;
-
- err = -EIO;
if (is_bad_inode(inode))
- goto out;
+ return;
- data.file = file;
- data.inode = inode;
- data.nr_pages = nr_pages;
- data.max_pages = min_t(unsigned int, nr_pages, fc->max_pages);
-;
- data.ia = fuse_io_alloc(NULL, data.max_pages);
- err = -ENOMEM;
- if (!data.ia)
- goto out;
+ max_pages = min_t(unsigned int, fc->max_pages,
+ fc->max_read / PAGE_SIZE);
- err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data);
- if (!err) {
- if (data.ia->ap.num_pages)
- fuse_send_readpages(data.ia, file);
- else
- fuse_io_free(data.ia);
+ for (;;) {
+ struct fuse_io_args *ia;
+ struct fuse_args_pages *ap;
+
+ nr_pages = readahead_count(rac) - nr_pages;
+ if (nr_pages > max_pages)
+ nr_pages = max_pages;
+ if (nr_pages == 0)
+ break;
+ ia = fuse_io_alloc(NULL, nr_pages);
+ if (!ia)
+ return;
+ ap = &ia->ap;
+ nr_pages = __readahead_batch(rac, ap->pages, nr_pages);
+ for (i = 0; i < nr_pages; i++) {
+ fuse_wait_on_page_writeback(inode,
+ readahead_index(rac) + i);
+ ap->descs[i].length = PAGE_SIZE;
+ }
+ ap->num_pages = nr_pages;
+ fuse_send_readpages(ia, rac->file);
}
-out:
- return err;
}
static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -3373,10 +3329,10 @@ static const struct file_operations fuse_file_operations = {
static const struct address_space_operations fuse_file_aops = {
.readpage = fuse_readpage,
+ .readahead = fuse_readahead,
.writepage = fuse_writepage,
.writepages = fuse_writepages,
.launder_page = fuse_launder_page,
- .readpages = fuse_readpages,
.set_page_dirty = __set_page_dirty_nobuffers,
.bmap = fuse_bmap,
.direct_IO = fuse_direct_IO,
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 786c1ce8f030..72c9560f4467 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -577,7 +577,7 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
}
/**
- * gfs2_readpages - Read a bunch of pages at once
+ * gfs2_readahead - Read a bunch of pages at once
* @file: The file to read from
* @mapping: Address space info
* @pages: List of pages to read
@@ -590,31 +590,24 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
* obviously not something we'd want to do on too regular a basis.
* Any I/O we ignore at this time will be done via readpage later.
* 2. We don't handle stuffed files here we let readpage do the honours.
- * 3. mpage_readpages() does most of the heavy lifting in the common case.
+ * 3. mpage_readahead() does most of the heavy lifting in the common case.
* 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places.
*/
-static int gfs2_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void gfs2_readahead(struct readahead_control *rac)
{
- struct inode *inode = mapping->host;
+ struct inode *inode = rac->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_holder gh;
- int ret;
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
- ret = gfs2_glock_nq(&gh);
- if (unlikely(ret))
+ if (gfs2_glock_nq(&gh))
goto out_uninit;
if (!gfs2_is_stuffed(ip))
- ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
+ mpage_readahead(rac, gfs2_block_map);
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
- if (unlikely(gfs2_withdrawn(sdp)))
- ret = -EIO;
- return ret;
}
/**
@@ -833,7 +826,7 @@ static const struct address_space_operations gfs2_aops = {
.writepage = gfs2_writepage,
.writepages = gfs2_writepages,
.readpage = gfs2_readpage,
- .readpages = gfs2_readpages,
+ .readahead = gfs2_readahead,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,
.releasepage = gfs2_releasepage,
@@ -847,7 +840,7 @@ static const struct address_space_operations gfs2_jdata_aops = {
.writepage = gfs2_jdata_writepage,
.writepages = gfs2_jdata_writepages,
.readpage = gfs2_readpage,
- .readpages = gfs2_readpages,
+ .readahead = gfs2_readahead,
.set_page_dirty = jdata_set_page_dirty,
.bmap = gfs2_bmap,
.invalidatepage = gfs2_invalidatepage,
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index c3f7732415be..c0f2875c946c 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -354,7 +354,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip)
hc = kmalloc(hsize, GFP_NOFS | __GFP_NOWARN);
if (hc == NULL)
- hc = __vmalloc(hsize, GFP_NOFS, PAGE_KERNEL);
+ hc = __vmalloc(hsize, GFP_NOFS);
if (hc == NULL)
return ERR_PTR(-ENOMEM);
@@ -1166,7 +1166,7 @@ static int dir_double_exhash(struct gfs2_inode *dip)
hc2 = kmalloc_array(hsize_bytes, 2, GFP_NOFS | __GFP_NOWARN);
if (hc2 == NULL)
- hc2 = __vmalloc(hsize_bytes * 2, GFP_NOFS, PAGE_KERNEL);
+ hc2 = __vmalloc(hsize_bytes * 2, GFP_NOFS);
if (!hc2)
return -ENOMEM;
@@ -1327,7 +1327,7 @@ static void *gfs2_alloc_sort_buffer(unsigned size)
if (size < KMALLOC_MAX_SIZE)
ptr = kmalloc(size, GFP_NOFS | __GFP_NOWARN);
if (!ptr)
- ptr = __vmalloc(size, GFP_NOFS, PAGE_KERNEL);
+ ptr = __vmalloc(size, GFP_NOFS);
return ptr;
}
@@ -1987,8 +1987,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
ht = kzalloc(size, GFP_NOFS | __GFP_NOWARN);
if (ht == NULL)
- ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO,
- PAGE_KERNEL);
+ ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO);
if (!ht)
return -ENOMEM;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 8259fef3f986..4b67d47a7e00 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1365,7 +1365,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
sdp->sd_quota_bitmap = kzalloc(bm_size, GFP_NOFS | __GFP_NOWARN);
if (sdp->sd_quota_bitmap == NULL)
sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS |
- __GFP_ZERO, PAGE_KERNEL);
+ __GFP_ZERO);
if (!sdp->sd_quota_bitmap)
return error;
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index b36abf9cb345..2de0d3492d15 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -125,10 +125,9 @@ static int hpfs_writepage(struct page *page, struct writeback_control *wbc)
return block_write_full_page(page, hpfs_get_block, wbc);
}
-static int hpfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void hpfs_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, hpfs_get_block);
+ mpage_readahead(rac, hpfs_get_block);
}
static int hpfs_writepages(struct address_space *mapping,
@@ -198,7 +197,7 @@ static int hpfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
const struct address_space_operations hpfs_aops = {
.readpage = hpfs_readpage,
.writepage = hpfs_writepage,
- .readpages = hpfs_readpages,
+ .readahead = hpfs_readahead,
.writepages = hpfs_writepages,
.write_begin = hpfs_write_begin,
.write_end = hpfs_write_end,
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 89e21961d1ad..a1ed7620fbac 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -59,24 +59,19 @@ iomap_page_create(struct inode *inode, struct page *page)
* migrate_page_move_mapping() assumes that pages with private data have
* their count elevated by 1.
*/
- get_page(page);
- set_page_private(page, (unsigned long)iop);
- SetPagePrivate(page);
+ attach_page_private(page, iop);
return iop;
}
static void
iomap_page_release(struct page *page)
{
- struct iomap_page *iop = to_iomap_page(page);
+ struct iomap_page *iop = detach_page_private(page);
if (!iop)
return;
WARN_ON_ONCE(atomic_read(&iop->read_count));
WARN_ON_ONCE(atomic_read(&iop->write_count));
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
kfree(iop);
}
@@ -214,9 +209,8 @@ iomap_read_end_io(struct bio *bio)
struct iomap_readpage_ctx {
struct page *cur_page;
bool cur_page_in_bio;
- bool is_readahead;
struct bio *bio;
- struct list_head *pages;
+ struct readahead_control *rac;
};
static void
@@ -308,7 +302,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
if (ctx->bio)
submit_bio(ctx->bio);
- if (ctx->is_readahead) /* same as readahead_gfp_mask */
+ if (ctx->rac) /* same as readahead_gfp_mask */
gfp |= __GFP_NORETRY | __GFP_NOWARN;
ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs));
/*
@@ -319,7 +313,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
if (!ctx->bio)
ctx->bio = bio_alloc(orig_gfp, 1);
ctx->bio->bi_opf = REQ_OP_READ;
- if (ctx->is_readahead)
+ if (ctx->rac)
ctx->bio->bi_opf |= REQ_RAHEAD;
ctx->bio->bi_iter.bi_sector = sector;
bio_set_dev(ctx->bio, iomap->bdev);
@@ -367,7 +361,7 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
}
/*
- * Just like mpage_readpages and block_read_full_page we always
+ * Just like mpage_readahead and block_read_full_page we always
* return 0 and just mark the page as PageError on errors. This
* should be cleaned up all through the stack eventually.
*/
@@ -375,36 +369,8 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
}
EXPORT_SYMBOL_GPL(iomap_readpage);
-static struct page *
-iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
- loff_t length, loff_t *done)
-{
- while (!list_empty(pages)) {
- struct page *page = lru_to_page(pages);
-
- if (page_offset(page) >= (u64)pos + length)
- break;
-
- list_del(&page->lru);
- if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
- GFP_NOFS))
- return page;
-
- /*
- * If we already have a page in the page cache at index we are
- * done. Upper layers don't care if it is uptodate after the
- * readpages call itself as every page gets checked again once
- * actually needed.
- */
- *done += PAGE_SIZE;
- put_page(page);
- }
-
- return NULL;
-}
-
static loff_t
-iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
+iomap_readahead_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap, struct iomap *srcmap)
{
struct iomap_readpage_ctx *ctx = data;
@@ -418,10 +384,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
ctx->cur_page = NULL;
}
if (!ctx->cur_page) {
- ctx->cur_page = iomap_next_page(inode, ctx->pages,
- pos, length, &done);
- if (!ctx->cur_page)
- break;
+ ctx->cur_page = readahead_page(ctx->rac);
ctx->cur_page_in_bio = false;
}
ret = iomap_readpage_actor(inode, pos + done, length - done,
@@ -431,32 +394,43 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
return done;
}
-int
-iomap_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages, const struct iomap_ops *ops)
+/**
+ * iomap_readahead - Attempt to read pages from a file.
+ * @rac: Describes the pages to be read.
+ * @ops: The operations vector for the filesystem.
+ *
+ * This function is for filesystems to call to implement their readahead
+ * address_space operation.
+ *
+ * Context: The @ops callbacks may submit I/O (eg to read the addresses of
+ * blocks from disc), and may wait for it. The caller may be trying to
+ * access a different page, and so sleeping excessively should be avoided.
+ * It may allocate memory, but should avoid costly allocations. This
+ * function is called with memalloc_nofs set, so allocations will not cause
+ * the filesystem to be reentered.
+ */
+void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
{
+ struct inode *inode = rac->mapping->host;
+ loff_t pos = readahead_pos(rac);
+ loff_t length = readahead_length(rac);
struct iomap_readpage_ctx ctx = {
- .pages = pages,
- .is_readahead = true,
+ .rac = rac,
};
- loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
- loff_t last = page_offset(list_entry(pages->next, struct page, lru));
- loff_t length = last - pos + PAGE_SIZE, ret = 0;
- trace_iomap_readpages(mapping->host, nr_pages);
+ trace_iomap_readahead(inode, readahead_count(rac));
while (length > 0) {
- ret = iomap_apply(mapping->host, pos, length, 0, ops,
- &ctx, iomap_readpages_actor);
+ loff_t ret = iomap_apply(inode, pos, length, 0, ops,
+ &ctx, iomap_readahead_actor);
if (ret <= 0) {
WARN_ON_ONCE(ret == 0);
- goto done;
+ break;
}
pos += ret;
length -= ret;
}
- ret = 0;
-done:
+
if (ctx.bio)
submit_bio(ctx.bio);
if (ctx.cur_page) {
@@ -464,15 +438,8 @@ done:
unlock_page(ctx.cur_page);
put_page(ctx.cur_page);
}
-
- /*
- * Check that we didn't lose a page due to the arcance calling
- * conventions..
- */
- WARN_ON_ONCE(!ret && !list_empty(ctx.pages));
- return ret;
}
-EXPORT_SYMBOL_GPL(iomap_readpages);
+EXPORT_SYMBOL_GPL(iomap_readahead);
/*
* iomap_is_partially_uptodate checks whether blocks within a page are
@@ -554,14 +521,8 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
if (ret != MIGRATEPAGE_SUCCESS)
return ret;
- if (page_has_private(page)) {
- ClearPagePrivate(page);
- get_page(newpage);
- set_page_private(newpage, page_private(page));
- set_page_private(page, 0);
- put_page(page);
- SetPagePrivate(newpage);
- }
+ if (page_has_private(page))
+ attach_page_private(newpage, detach_page_private(page));
if (mode != MIGRATE_SYNC_NO_COPY)
migrate_page_copy(newpage, page);
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 4df19c66f597..5693a39d52fb 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -39,7 +39,7 @@ DEFINE_EVENT(iomap_readpage_class, name, \
TP_PROTO(struct inode *inode, int nr_pages), \
TP_ARGS(inode, nr_pages))
DEFINE_READPAGE_EVENT(iomap_readpage);
-DEFINE_READPAGE_EVENT(iomap_readpages);
+DEFINE_READPAGE_EVENT(iomap_readahead);
DECLARE_EVENT_CLASS(iomap_range_class,
TP_PROTO(struct inode *inode, unsigned long off, unsigned int len),
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 62c0462dc89f..95b1f377ad09 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1185,10 +1185,9 @@ static int isofs_readpage(struct file *file, struct page *page)
return mpage_readpage(page, isofs_get_block);
}
-static int isofs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void isofs_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, isofs_get_block);
+ mpage_readahead(rac, isofs_get_block);
}
static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
@@ -1198,7 +1197,7 @@ static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
static const struct address_space_operations isofs_aops = {
.readpage = isofs_readpage,
- .readpages = isofs_readpages,
+ .readahead = isofs_readahead,
.bmap = _isofs_bmap
};
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 9486afcdac76..6f65bfa9f18d 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -296,10 +296,9 @@ static int jfs_readpage(struct file *file, struct page *page)
return mpage_readpage(page, jfs_get_block);
}
-static int jfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void jfs_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, jfs_get_block);
+ mpage_readahead(rac, jfs_get_block);
}
static void jfs_write_failed(struct address_space *mapping, loff_t to)
@@ -358,7 +357,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
const struct address_space_operations jfs_aops = {
.readpage = jfs_readpage,
- .readpages = jfs_readpages,
+ .readahead = jfs_readahead,
.writepage = jfs_writepage,
.writepages = jfs_writepages,
.write_begin = jfs_write_begin,
diff --git a/fs/mpage.c b/fs/mpage.c
index ccba3c4c4479..830e6cc2a9e7 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -91,7 +91,7 @@ mpage_alloc(struct block_device *bdev,
}
/*
- * support function for mpage_readpages. The fs supplied get_block might
+ * support function for mpage_readahead. The fs supplied get_block might
* return an up to date buffer. This is used to map that buffer into
* the page, which allows readpage to avoid triggering a duplicate call
* to get_block.
@@ -338,13 +338,8 @@ confused:
}
/**
- * mpage_readpages - populate an address space with some pages & start reads against them
- * @mapping: the address_space
- * @pages: The address of a list_head which contains the target pages. These
- * pages have their ->index populated and are otherwise uninitialised.
- * The page at @pages->prev has the lowest file offset, and reads should be
- * issued in @pages->prev to @pages->next order.
- * @nr_pages: The number of pages at *@pages
+ * mpage_readahead - start reads against pages
+ * @rac: Describes which pages to read.
* @get_block: The filesystem's block mapper function.
*
* This function walks the pages and the blocks within each page, building and
@@ -381,36 +376,25 @@ confused:
*
* This all causes the disk requests to be issued in the correct order.
*/
-int
-mpage_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages, get_block_t get_block)
+void mpage_readahead(struct readahead_control *rac, get_block_t get_block)
{
+ struct page *page;
struct mpage_readpage_args args = {
.get_block = get_block,
.is_readahead = true,
};
- unsigned page_idx;
-
- for (page_idx = 0; page_idx < nr_pages; page_idx++) {
- struct page *page = lru_to_page(pages);
+ while ((page = readahead_page(rac))) {
prefetchw(&page->flags);
- list_del(&page->lru);
- if (!add_to_page_cache_lru(page, mapping,
- page->index,
- readahead_gfp_mask(mapping))) {
- args.page = page;
- args.nr_pages = nr_pages - page_idx;
- args.bio = do_mpage_readpage(&args);
- }
+ args.page = page;
+ args.nr_pages = readahead_count(rac);
+ args.bio = do_mpage_readpage(&args);
put_page(page);
}
- BUG_ON(!list_empty(pages));
if (args.bio)
mpage_bio_submit(REQ_OP_READ, REQ_RAHEAD, args.bio);
- return 0;
}
-EXPORT_SYMBOL(mpage_readpages);
+EXPORT_SYMBOL(mpage_readahead);
/*
* This isn't called much at all
@@ -563,7 +547,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
* Page has buffers, but they are all unmapped. The page was
* created by pagein or read over a hole which was handled by
* block_read_full_page(). If this address_space is also
- * using mpage_readpages then this can rarely happen.
+ * using mpage_readahead then this can rarely happen.
*/
goto confused;
}
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index 7a57ff2528af..8f7cff7a4293 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -582,7 +582,7 @@ retry:
if (!arg->layoutupdate_pages)
return -ENOMEM;
- start_p = __vmalloc(buffer_size, GFP_NOFS, PAGE_KERNEL);
+ start_p = __vmalloc(buffer_size, GFP_NOFS);
if (!start_p) {
kfree(arg->layoutupdate_pages);
return -ENOMEM;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 1f32a9fbfdaf..6673a77884d9 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -668,7 +668,8 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize)
}
/*
- * Record the page as unstable and mark its inode as dirty.
+ * Record the page as unstable (an extra writeback period) and mark its
+ * inode as dirty.
*/
static inline
void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo)
@@ -676,8 +677,11 @@ void nfs_mark_page_unstable(struct page *page, struct nfs_commit_info *cinfo)
if (!cinfo->dreq) {
struct inode *inode = page_file_mapping(page)->host;
- inc_node_page_state(page, NR_UNSTABLE_NFS);
- inc_wb_stat(&inode_to_bdi(inode)->wb, WB_RECLAIMABLE);
+ /* This page is really still in write-back - just that the
+ * writeback is happening on the server now.
+ */
+ inc_node_page_state(page, NR_WRITEBACK);
+ inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 1e767f779c49..639c34fec04a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -946,9 +946,9 @@ nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
static void
nfs_clear_page_commit(struct page *page)
{
- dec_node_page_state(page, NR_UNSTABLE_NFS);
+ dec_node_page_state(page, NR_WRITEBACK);
dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
- WB_RECLAIMABLE);
+ WB_WRITEBACK);
}
/* Called holding the request lock on @req */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 0aa02eb18bd3..c3fbab1753ec 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -979,12 +979,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
/*
- * We want less throttling in balance_dirty_pages()
- * and shrink_inactive_list() so that nfs to
+ * We want throttling in balance_dirty_pages()
+ * and shrink_inactive_list() to only consider
+ * the backingdev we are writing to, so that nfs to
* localhost doesn't cause nfsd to lock up due to all
* the client's dirty pages or its congested queue.
*/
- current->flags |= PF_LESS_THROTTLE;
+ current->flags |= PF_LOCAL_THROTTLE;
exp = fhp->fh_export;
use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
@@ -1037,7 +1038,7 @@ out_nfserr:
nfserr = nfserrno(host_err);
}
if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
- current_restore_flags(pflags, PF_LESS_THROTTLE);
+ current_restore_flags(pflags, PF_LOCAL_THROTTLE);
return nfserr;
}
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 671085512e0f..ceeb3b441844 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -145,18 +145,9 @@ static int nilfs_readpage(struct file *file, struct page *page)
return mpage_readpage(page, nilfs_get_block);
}
-/**
- * nilfs_readpages() - implement readpages() method of nilfs_aops {}
- * address_space_operations.
- * @file - file struct of the file to be read
- * @mapping - address_space struct used for reading multiple pages
- * @pages - the pages to be read
- * @nr_pages - number of pages to be read
- */
-static int nilfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned int nr_pages)
+static void nilfs_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
+ mpage_readahead(rac, nilfs_get_block);
}
static int nilfs_writepages(struct address_space *mapping,
@@ -308,7 +299,7 @@ const struct address_space_operations nilfs_aops = {
.readpage = nilfs_readpage,
.writepages = nilfs_writepages,
.set_page_dirty = nilfs_set_page_dirty,
- .readpages = nilfs_readpages,
+ .readahead = nilfs_readahead,
.write_begin = nilfs_write_begin,
.write_end = nilfs_write_end,
/* .releasepage = nilfs_releasepage, */
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 554b744f41bf..bb0a43860ad2 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1732,7 +1732,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
- attach_page_buffers(page, head);
+ attach_page_private(page, head);
} else
buffers_to_free = bh;
}
diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h
index 842b0bfc3ac9..7068425735f1 100644
--- a/fs/ntfs/malloc.h
+++ b/fs/ntfs/malloc.h
@@ -34,7 +34,7 @@ static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)
/* return (void *)__get_free_page(gfp_mask); */
}
if (likely((size >> PAGE_SHIFT) < totalram_pages()))
- return __vmalloc(size, gfp_mask, PAGE_KERNEL);
+ return __vmalloc(size, gfp_mask);
return NULL;
}
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 3aac5c917afe..fbb9f1bc623d 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -504,7 +504,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
bh = bh->b_this_page;
} while (bh);
tail->b_this_page = head;
- attach_page_buffers(page, head);
+ attach_page_private(page, head);
}
bh = head = page_buffers(page);
BUG_ON(!bh);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3a67a6518ddf..3bfb4147895a 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -350,14 +350,11 @@ out:
* grow out to a tree. If need be, detecting boundary extents could
* trivially be added in a future version of ocfs2_get_block().
*/
-static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void ocfs2_readahead(struct readahead_control *rac)
{
- int ret, err = -EIO;
- struct inode *inode = mapping->host;
+ int ret;
+ struct inode *inode = rac->mapping->host;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
- loff_t start;
- struct page *last;
/*
* Use the nonblocking flag for the dlm code to avoid page
@@ -365,36 +362,31 @@ static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
*/
ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK);
if (ret)
- return err;
+ return;
- if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
- ocfs2_inode_unlock(inode, 0);
- return err;
- }
+ if (down_read_trylock(&oi->ip_alloc_sem) == 0)
+ goto out_unlock;
/*
* Don't bother with inline-data. There isn't anything
* to read-ahead in that case anyway...
*/
if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
- goto out_unlock;
+ goto out_up;
/*
* Check whether a remote node truncated this file - we just
* drop out in that case as it's not worth handling here.
*/
- last = lru_to_page(pages);
- start = (loff_t)last->index << PAGE_SHIFT;
- if (start >= i_size_read(inode))
- goto out_unlock;
+ if (readahead_pos(rac) >= i_size_read(inode))
+ goto out_up;
- err = mpage_readpages(mapping, pages, nr_pages, ocfs2_get_block);
+ mpage_readahead(rac, ocfs2_get_block);
-out_unlock:
+out_up:
up_read(&oi->ip_alloc_sem);
+out_unlock:
ocfs2_inode_unlock(inode, 0);
-
- return err;
}
/* Note: Because we don't support holes, our allocation has
@@ -2474,7 +2466,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
const struct address_space_operations ocfs2_aops = {
.readpage = ocfs2_readpage,
- .readpages = ocfs2_readpages,
+ .readahead = ocfs2_readahead,
.writepage = ocfs2_writepage,
.write_begin = ocfs2_write_begin,
.write_end = ocfs2_write_end,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 55a6512e9fde..f105746063ed 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2760,6 +2760,7 @@ leave:
* Returns: 1 if dlm->spinlock was dropped/retaken, 0 if never dropped
*/
int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
+ __must_hold(&dlm->spinlock)
{
int ret;
int lock_dropped = 0;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 9150cfa4df7d..ee5d98516212 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -279,6 +279,7 @@ enum ocfs2_mount_options
OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */
OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
+ OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
};
#define OCFS2_OSB_SOFT_RO 0x0001
@@ -673,7 +674,8 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
static inline int ocfs2_mount_local(struct ocfs2_super *osb)
{
- return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
+ return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
+ || (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
}
static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 8caeceeaeda7..4da0e4b1e79b 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -254,14 +254,16 @@ static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si,
int i, ret = -ENOSPC;
if ((preferred >= 0) && (preferred < si->si_num_slots)) {
- if (!si->si_slots[preferred].sl_valid) {
+ if (!si->si_slots[preferred].sl_valid ||
+ !si->si_slots[preferred].sl_node_num) {
ret = preferred;
goto out;
}
}
for(i = 0; i < si->si_num_slots; i++) {
- if (!si->si_slots[i].sl_valid) {
+ if (!si->si_slots[i].sl_valid ||
+ !si->si_slots[i].sl_node_num) {
ret = i;
break;
}
@@ -456,24 +458,30 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
spin_lock(&osb->osb_lock);
ocfs2_update_slot_info(si);
- /* search for ourselves first and take the slot if it already
- * exists. Perhaps we need to mark this in a variable for our
- * own journal recovery? Possibly not, though we certainly
- * need to warn to the user */
- slot = __ocfs2_node_num_to_slot(si, osb->node_num);
- if (slot < 0) {
- /* if no slot yet, then just take 1st available
- * one. */
- slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
+ if (ocfs2_mount_local(osb))
+ /* use slot 0 directly in local mode */
+ slot = 0;
+ else {
+ /* search for ourselves first and take the slot if it already
+ * exists. Perhaps we need to mark this in a variable for our
+ * own journal recovery? Possibly not, though we certainly
+ * need to warn to the user */
+ slot = __ocfs2_node_num_to_slot(si, osb->node_num);
if (slot < 0) {
- spin_unlock(&osb->osb_lock);
- mlog(ML_ERROR, "no free slots available!\n");
- status = -EINVAL;
- goto bail;
- }
- } else
- printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
- "allocated to this node!\n", slot, osb->dev_str);
+ /* if no slot yet, then just take 1st available
+ * one. */
+ slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
+ if (slot < 0) {
+ spin_unlock(&osb->osb_lock);
+ mlog(ML_ERROR, "no free slots available!\n");
+ status = -EINVAL;
+ goto bail;
+ }
+ } else
+ printk(KERN_INFO "ocfs2: Slot %d on device (%s) was "
+ "already allocated to this node!\n",
+ slot, osb->dev_str);
+ }
ocfs2_set_slot(si, slot, osb->node_num);
osb->slot_num = slot;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index ac61eeaf3837..71ea9ce71a6b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -175,6 +175,7 @@ enum {
Opt_dir_resv_level,
Opt_journal_async_commit,
Opt_err_cont,
+ Opt_nocluster,
Opt_err,
};
@@ -208,6 +209,7 @@ static const match_table_t tokens = {
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_err_cont, "errors=continue"},
+ {Opt_nocluster, "nocluster"},
{Opt_err, NULL}
};
@@ -619,6 +621,13 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
goto out;
}
+ tmp = OCFS2_MOUNT_NOCLUSTER;
+ if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
+ ret = -EINVAL;
+ mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
+ goto out;
+ }
+
tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
OCFS2_MOUNT_HB_NONE;
if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
@@ -859,6 +868,7 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
}
if (ocfs2_userspace_stack(osb) &&
+ !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
OCFS2_STACK_LABEL_LEN)) {
mlog(ML_ERROR,
@@ -1139,6 +1149,11 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
"ordered");
+ if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
+ !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
+ printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
+ "without cluster aware mode.\n", osb->dev_str);
+
atomic_set(&osb->vol_state, VOLUME_MOUNTED);
wake_up(&osb->osb_mount_event);
@@ -1445,6 +1460,9 @@ static int ocfs2_parse_options(struct super_block *sb,
case Opt_journal_async_commit:
mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
break;
+ case Opt_nocluster:
+ mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
+ break;
default:
mlog(ML_ERROR,
"Unrecognized mount option \"%s\" "
@@ -1556,6 +1574,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
seq_printf(s, ",journal_async_commit");
+ if (opts & OCFS2_MOUNT_NOCLUSTER)
+ seq_printf(s, ",nocluster");
+
return 0;
}
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index d640b9388238..d7b5f09d298c 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -289,10 +289,9 @@ static int omfs_readpage(struct file *file, struct page *page)
return block_read_full_page(page, omfs_get_block);
}
-static int omfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void omfs_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, omfs_get_block);
+ mpage_readahead(rac, omfs_get_block);
}
static int omfs_writepage(struct page *page, struct writeback_control *wbc)
@@ -373,7 +372,7 @@ const struct inode_operations omfs_file_inops = {
const struct address_space_operations omfs_aops = {
.readpage = omfs_readpage,
- .readpages = omfs_readpages,
+ .readahead = omfs_readahead,
.writepage = omfs_writepage,
.writepages = omfs_writepages,
.write_begin = omfs_write_begin,
diff --git a/fs/open.c b/fs/open.c
index e62b1db06638..6cd48a61cda3 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -775,9 +775,8 @@ static int do_dentry_open(struct file *f,
path_get(&f->f_path);
f->f_inode = inode;
f->f_mapping = inode->i_mapping;
-
- /* Ensure that we skip any errors that predate opening of the file */
f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
+ f->f_sb_err = file_sample_sb_err(f);
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH | FMODE_OPENED;
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 12ae630fbed7..48f0547d4850 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -62,12 +62,7 @@ static int orangefs_writepage_locked(struct page *page,
} else {
ret = 0;
}
- if (wr) {
- kfree(wr);
- set_page_private(page, 0);
- ClearPagePrivate(page);
- put_page(page);
- }
+ kfree(detach_page_private(page));
return ret;
}
@@ -409,9 +404,7 @@ static int orangefs_write_begin(struct file *file,
wr->len = len;
wr->uid = current_fsuid();
wr->gid = current_fsgid();
- SetPagePrivate(page);
- set_page_private(page, (unsigned long)wr);
- get_page(page);
+ attach_page_private(page, wr);
okay:
return 0;
}
@@ -459,18 +452,12 @@ static void orangefs_invalidatepage(struct page *page,
wr = (struct orangefs_write_range *)page_private(page);
if (offset == 0 && length == PAGE_SIZE) {
- kfree((struct orangefs_write_range *)page_private(page));
- set_page_private(page, 0);
- ClearPagePrivate(page);
- put_page(page);
+ kfree(detach_page_private(page));
return;
/* write range entirely within invalidate range (or equal) */
} else if (page_offset(page) + offset <= wr->pos &&
wr->pos + wr->len <= page_offset(page) + offset + length) {
- kfree((struct orangefs_write_range *)page_private(page));
- set_page_private(page, 0);
- ClearPagePrivate(page);
- put_page(page);
+ kfree(detach_page_private(page));
/* XXX is this right? only caller in fs */
cancel_dirty_page(page);
return;
@@ -535,12 +522,7 @@ static int orangefs_releasepage(struct page *page, gfp_t foo)
static void orangefs_freepage(struct page *page)
{
- if (PagePrivate(page)) {
- kfree((struct orangefs_write_range *)page_private(page));
- set_page_private(page, 0);
- ClearPagePrivate(page);
- put_page(page);
- }
+ kfree(detach_page_private(page));
}
static int orangefs_launder_page(struct page *page)
@@ -740,9 +722,7 @@ vm_fault_t orangefs_page_mkwrite(struct vm_fault *vmf)
wr->len = PAGE_SIZE;
wr->uid = current_fsuid();
wr->gid = current_fsgid();
- SetPagePrivate(page);
- set_page_private(page, (unsigned long)wr);
- get_page(page);
+ attach_page_private(page, wr);
okay:
file_update_time(vmf->vma->vm_file);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 09cd51c8d23d..ecc63ce01be7 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -110,8 +110,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
show_val_kb(m, "PageTables: ",
global_zone_page_state(NR_PAGETABLE));
- show_val_kb(m, "NFS_Unstable: ",
- global_node_page_state(NR_UNSTABLE_NFS));
+ show_val_kb(m, "NFS_Unstable: ", 0);
show_val_kb(m, "Bounce: ",
global_zone_page_state(NR_BOUNCE));
show_val_kb(m, "WritebackTmp: ",
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 10a6d472397f..6ad407d5efe2 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -546,10 +546,17 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
bool locked = !!(vma->vm_flags & VM_LOCKED);
- struct page *page;
+ struct page *page = NULL;
+
+ if (pmd_present(*pmd)) {
+ /* FOLL_DUMP will return -EFAULT on huge zero page */
+ page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+ } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
+ swp_entry_t entry = pmd_to_swp_entry(*pmd);
- /* FOLL_DUMP will return -EFAULT on huge zero page */
- page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+ if (is_migration_entry(entry))
+ page = migration_entry_to_page(entry);
+ }
if (IS_ERR_OR_NULL(page))
return;
if (PageAnon(page))
@@ -578,8 +585,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
- if (pmd_present(*pmd))
- smaps_pmd_entry(pmd, addr, walk);
+ smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
goto out;
}
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 345db56c98fd..755293c8c71a 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -99,10 +99,9 @@ static int qnx6_readpage(struct file *file, struct page *page)
return mpage_readpage(page, qnx6_get_block);
}
-static int qnx6_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void qnx6_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, qnx6_get_block);
+ mpage_readahead(rac, qnx6_get_block);
}
/*
@@ -499,7 +498,7 @@ static sector_t qnx6_bmap(struct address_space *mapping, sector_t block)
}
static const struct address_space_operations qnx6_aops = {
.readpage = qnx6_readpage,
- .readpages = qnx6_readpages,
+ .readahead = qnx6_readahead,
.bmap = qnx6_bmap
};
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 6419e6dacc39..0031070b3692 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1160,11 +1160,9 @@ failure:
return retval;
}
-static int
-reiserfs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void reiserfs_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, reiserfs_get_block);
+ mpage_readahead(rac, reiserfs_get_block);
}
/*
@@ -3434,7 +3432,7 @@ out:
const struct address_space_operations reiserfs_address_space_operations = {
.writepage = reiserfs_writepage,
.readpage = reiserfs_readpage,
- .readpages = reiserfs_readpages,
+ .readahead = reiserfs_readahead,
.releasepage = reiserfs_releasepage,
.invalidatepage = reiserfs_invalidatepage,
.write_begin = reiserfs_write_begin,
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 4f9b9fb59362..64f61330564a 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -13,6 +13,7 @@
* datablocks and metadata blocks.
*/
+#include <linux/blkdev.h>
#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/slab.h>
@@ -27,44 +28,103 @@
#include "page_actor.h"
/*
- * Read the metadata block length, this is stored in the first two
- * bytes of the metadata block.
+ * Returns the amount of bytes copied to the page actor.
*/
-static struct buffer_head *get_block_length(struct super_block *sb,
- u64 *cur_index, int *offset, int *length)
+static int copy_bio_to_actor(struct bio *bio,
+ struct squashfs_page_actor *actor,
+ int offset, int req_length)
+{
+ void *actor_addr = squashfs_first_page(actor);
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+ int copied_bytes = 0;
+ int actor_offset = 0;
+
+ if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all)))
+ return 0;
+
+ while (copied_bytes < req_length) {
+ int bytes_to_copy = min_t(int, bvec->bv_len - offset,
+ PAGE_SIZE - actor_offset);
+
+ bytes_to_copy = min_t(int, bytes_to_copy,
+ req_length - copied_bytes);
+ memcpy(actor_addr + actor_offset,
+ page_address(bvec->bv_page) + bvec->bv_offset + offset,
+ bytes_to_copy);
+
+ actor_offset += bytes_to_copy;
+ copied_bytes += bytes_to_copy;
+ offset += bytes_to_copy;
+
+ if (actor_offset >= PAGE_SIZE) {
+ actor_addr = squashfs_next_page(actor);
+ if (!actor_addr)
+ break;
+ actor_offset = 0;
+ }
+ if (offset >= bvec->bv_len) {
+ if (!bio_next_segment(bio, &iter_all))
+ break;
+ offset = 0;
+ }
+ }
+ squashfs_finish_page(actor);
+ return copied_bytes;
+}
+
+static int squashfs_bio_read(struct super_block *sb, u64 index, int length,
+ struct bio **biop, int *block_offset)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- struct buffer_head *bh;
-
- bh = sb_bread(sb, *cur_index);
- if (bh == NULL)
- return NULL;
-
- if (msblk->devblksize - *offset == 1) {
- *length = (unsigned char) bh->b_data[*offset];
- put_bh(bh);
- bh = sb_bread(sb, ++(*cur_index));
- if (bh == NULL)
- return NULL;
- *length |= (unsigned char) bh->b_data[0] << 8;
- *offset = 1;
- } else {
- *length = (unsigned char) bh->b_data[*offset] |
- (unsigned char) bh->b_data[*offset + 1] << 8;
- *offset += 2;
-
- if (*offset == msblk->devblksize) {
- put_bh(bh);
- bh = sb_bread(sb, ++(*cur_index));
- if (bh == NULL)
- return NULL;
- *offset = 0;
+ const u64 read_start = round_down(index, msblk->devblksize);
+ const sector_t block = read_start >> msblk->devblksize_log2;
+ const u64 read_end = round_up(index + length, msblk->devblksize);
+ const sector_t block_end = read_end >> msblk->devblksize_log2;
+ int offset = read_start - round_down(index, PAGE_SIZE);
+ int total_len = (block_end - block) << msblk->devblksize_log2;
+ const int page_count = DIV_ROUND_UP(total_len + offset, PAGE_SIZE);
+ int error, i;
+ struct bio *bio;
+
+ bio = bio_alloc(GFP_NOIO, page_count);
+ if (!bio)
+ return -ENOMEM;
+
+ bio_set_dev(bio, sb->s_bdev);
+ bio->bi_opf = READ;
+ bio->bi_iter.bi_sector = block * (msblk->devblksize >> SECTOR_SHIFT);
+
+ for (i = 0; i < page_count; ++i) {
+ unsigned int len =
+ min_t(unsigned int, PAGE_SIZE - offset, total_len);
+ struct page *page = alloc_page(GFP_NOIO);
+
+ if (!page) {
+ error = -ENOMEM;
+ goto out_free_bio;
+ }
+ if (!bio_add_page(bio, page, len, offset)) {
+ error = -EIO;
+ goto out_free_bio;
}
+ offset = 0;
+ total_len -= len;
}
- return bh;
-}
+ error = submit_bio_wait(bio);
+ if (error)
+ goto out_free_bio;
+ *biop = bio;
+ *block_offset = index & ((1 << msblk->devblksize_log2) - 1);
+ return 0;
+
+out_free_bio:
+ bio_free_pages(bio);
+ bio_put(bio);
+ return error;
+}
/*
* Read and decompress a metadata block or datablock. Length is non-zero
@@ -76,129 +136,88 @@ static struct buffer_head *get_block_length(struct super_block *sb,
* algorithms).
*/
int squashfs_read_data(struct super_block *sb, u64 index, int length,
- u64 *next_index, struct squashfs_page_actor *output)
+ u64 *next_index, struct squashfs_page_actor *output)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
- struct buffer_head **bh;
- int offset = index & ((1 << msblk->devblksize_log2) - 1);
- u64 cur_index = index >> msblk->devblksize_log2;
- int bytes, compressed, b = 0, k = 0, avail, i;
-
- bh = kcalloc(((output->length + msblk->devblksize - 1)
- >> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL);
- if (bh == NULL)
- return -ENOMEM;
+ struct bio *bio = NULL;
+ int compressed;
+ int res;
+ int offset;
if (length) {
/*
* Datablock.
*/
- bytes = -offset;
compressed = SQUASHFS_COMPRESSED_BLOCK(length);
length = SQUASHFS_COMPRESSED_SIZE_BLOCK(length);
- if (next_index)
- *next_index = index + length;
-
TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n",
index, compressed ? "" : "un", length, output->length);
-
- if (length < 0 || length > output->length ||
- (index + length) > msblk->bytes_used)
- goto read_failure;
-
- for (b = 0; bytes < length; b++, cur_index++) {
- bh[b] = sb_getblk(sb, cur_index);
- if (bh[b] == NULL)
- goto block_release;
- bytes += msblk->devblksize;
- }
- ll_rw_block(REQ_OP_READ, 0, b, bh);
} else {
/*
* Metadata block.
*/
- if ((index + 2) > msblk->bytes_used)
- goto read_failure;
+ const u8 *data;
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
- bh[0] = get_block_length(sb, &cur_index, &offset, &length);
- if (bh[0] == NULL)
- goto read_failure;
- b = 1;
+ if (index + 2 > msblk->bytes_used) {
+ res = -EIO;
+ goto out;
+ }
+ res = squashfs_bio_read(sb, index, 2, &bio, &offset);
+ if (res)
+ goto out;
+
+ if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) {
+ res = -EIO;
+ goto out_free_bio;
+ }
+ /* Extract the length of the metadata block */
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
+ length = data[offset];
+ if (offset <= bvec->bv_len - 1) {
+ length |= data[offset + 1] << 8;
+ } else {
+ if (WARN_ON_ONCE(!bio_next_segment(bio, &iter_all))) {
+ res = -EIO;
+ goto out_free_bio;
+ }
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
+ length |= data[0] << 8;
+ }
+ bio_free_pages(bio);
+ bio_put(bio);
- bytes = msblk->devblksize - offset;
compressed = SQUASHFS_COMPRESSED(length);
length = SQUASHFS_COMPRESSED_SIZE(length);
- if (next_index)
- *next_index = index + length + 2;
+ index += 2;
TRACE("Block @ 0x%llx, %scompressed size %d\n", index,
- compressed ? "" : "un", length);
-
- if (length < 0 || length > output->length ||
- (index + length) > msblk->bytes_used)
- goto block_release;
-
- for (; bytes < length; b++) {
- bh[b] = sb_getblk(sb, ++cur_index);
- if (bh[b] == NULL)
- goto block_release;
- bytes += msblk->devblksize;
- }
- ll_rw_block(REQ_OP_READ, 0, b - 1, bh + 1);
+ compressed ? "" : "un", length);
}
+ if (next_index)
+ *next_index = index + length;
- for (i = 0; i < b; i++) {
- wait_on_buffer(bh[i]);
- if (!buffer_uptodate(bh[i]))
- goto block_release;
- }
+ res = squashfs_bio_read(sb, index, length, &bio, &offset);
+ if (res)
+ goto out;
if (compressed) {
- if (!msblk->stream)
- goto read_failure;
- length = squashfs_decompress(msblk, bh, b, offset, length,
- output);
- if (length < 0)
- goto read_failure;
- } else {
- /*
- * Block is uncompressed.
- */
- int in, pg_offset = 0;
- void *data = squashfs_first_page(output);
-
- for (bytes = length; k < b; k++) {
- in = min(bytes, msblk->devblksize - offset);
- bytes -= in;
- while (in) {
- if (pg_offset == PAGE_SIZE) {
- data = squashfs_next_page(output);
- pg_offset = 0;
- }
- avail = min_t(int, in, PAGE_SIZE -
- pg_offset);
- memcpy(data + pg_offset, bh[k]->b_data + offset,
- avail);
- in -= avail;
- pg_offset += avail;
- offset += avail;
- }
- offset = 0;
- put_bh(bh[k]);
+ if (!msblk->stream) {
+ res = -EIO;
+ goto out_free_bio;
}
- squashfs_finish_page(output);
+ res = squashfs_decompress(msblk, bio, offset, length, output);
+ } else {
+ res = copy_bio_to_actor(bio, output, offset, length);
}
- kfree(bh);
- return length;
-
-block_release:
- for (; k < b; k++)
- put_bh(bh[k]);
+out_free_bio:
+ bio_free_pages(bio);
+ bio_put(bio);
+out:
+ if (res < 0)
+ ERROR("Failed to read block 0x%llx: %d\n", index, res);
-read_failure:
- ERROR("squashfs_read_data failed to read block 0x%llx\n",
- (unsigned long long) index);
- kfree(bh);
- return -EIO;
+ return res;
}
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index ec8617523e56..1b9ccfd0aa51 100644
--- a/fs/squashfs/decompressor.h
+++ b/fs/squashfs/decompressor.h
@@ -10,13 +10,14 @@
* decompressor.h
*/
+#include <linux/bio.h>
+
struct squashfs_decompressor {
void *(*init)(struct squashfs_sb_info *, void *);
void *(*comp_opts)(struct squashfs_sb_info *, void *, int);
void (*free)(void *);
int (*decompress)(struct squashfs_sb_info *, void *,
- struct buffer_head **, int, int, int,
- struct squashfs_page_actor *);
+ struct bio *, int, int, struct squashfs_page_actor *);
int id;
char *name;
int supported;
diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c
index c181dee235bb..db9f12a3ea05 100644
--- a/fs/squashfs/decompressor_multi.c
+++ b/fs/squashfs/decompressor_multi.c
@@ -6,7 +6,7 @@
#include <linux/types.h>
#include <linux/mutex.h>
#include <linux/slab.h>
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/cpumask.h>
@@ -180,14 +180,15 @@ wait:
}
-int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
- int b, int offset, int length, struct squashfs_page_actor *output)
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio,
+ int offset, int length,
+ struct squashfs_page_actor *output)
{
int res;
struct squashfs_stream *stream = msblk->stream;
struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream);
res = msblk->decompressor->decompress(msblk, decomp_stream->stream,
- bh, b, offset, length, output);
+ bio, offset, length, output);
put_decomp_stream(decomp_stream, stream);
if (res < 0)
ERROR("%s decompression failed, data probably corrupt\n",
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index e206ebfe003c..b881b9283b7f 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -75,8 +75,8 @@ void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
}
}
-int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
- int b, int offset, int length, struct squashfs_page_actor *output)
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio,
+ int offset, int length, struct squashfs_page_actor *output)
{
struct squashfs_stream *stream;
int res;
@@ -84,8 +84,8 @@ int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
local_lock(&msblk->stream->lock);
stream = this_cpu_ptr(msblk->stream);
- res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
- offset, length, output);
+ res = msblk->decompressor->decompress(msblk, stream->stream, bio,
+ offset, length, output);
local_unlock(&msblk->stream->lock);
diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c
index 550c3e592032..4eb3d083d45e 100644
--- a/fs/squashfs/decompressor_single.c
+++ b/fs/squashfs/decompressor_single.c
@@ -7,7 +7,7 @@
#include <linux/types.h>
#include <linux/mutex.h>
#include <linux/slab.h>
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include "squashfs_fs.h"
#include "squashfs_fs_sb.h"
@@ -59,14 +59,15 @@ void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk)
}
}
-int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
- int b, int offset, int length, struct squashfs_page_actor *output)
+int squashfs_decompress(struct squashfs_sb_info *msblk, struct bio *bio,
+ int offset, int length,
+ struct squashfs_page_actor *output)
{
int res;
struct squashfs_stream *stream = msblk->stream;
mutex_lock(&stream->mutex);
- res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+ res = msblk->decompressor->decompress(msblk, stream->stream, bio,
offset, length, output);
mutex_unlock(&stream->mutex);
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index c4e47e0588c7..233d5582fbee 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -4,7 +4,7 @@
* Phillip Lougher <phillip@squashfs.org.uk>
*/
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
@@ -89,20 +89,23 @@ static void lz4_free(void *strm)
static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
- struct buffer_head **bh, int b, int offset, int length,
+ struct bio *bio, int offset, int length,
struct squashfs_page_actor *output)
{
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
struct squashfs_lz4 *stream = strm;
void *buff = stream->input, *data;
- int avail, i, bytes = length, res;
+ int bytes = length, res;
- for (i = 0; i < b; i++) {
- avail = min(bytes, msblk->devblksize - offset);
- memcpy(buff, bh[i]->b_data + offset, avail);
+ while (bio_next_segment(bio, &iter_all)) {
+ int avail = min(bytes, ((int)bvec->bv_len) - offset);
+
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
+ memcpy(buff, data + offset, avail);
buff += avail;
bytes -= avail;
offset = 0;
- put_bh(bh[i]);
}
res = LZ4_decompress_safe(stream->input, stream->output,
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index aa3c3dafc33d..97bb7d92ddcd 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -9,7 +9,7 @@
*/
#include <linux/mutex.h>
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/lzo.h>
@@ -63,21 +63,24 @@ static void lzo_free(void *strm)
static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm,
- struct buffer_head **bh, int b, int offset, int length,
+ struct bio *bio, int offset, int length,
struct squashfs_page_actor *output)
{
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
struct squashfs_lzo *stream = strm;
void *buff = stream->input, *data;
- int avail, i, bytes = length, res;
+ int bytes = length, res;
size_t out_len = output->length;
- for (i = 0; i < b; i++) {
- avail = min(bytes, msblk->devblksize - offset);
- memcpy(buff, bh[i]->b_data + offset, avail);
+ while (bio_next_segment(bio, &iter_all)) {
+ int avail = min(bytes, ((int)bvec->bv_len) - offset);
+
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
+ memcpy(buff, data + offset, avail);
buff += avail;
bytes -= avail;
offset = 0;
- put_bh(bh[i]);
}
res = lzo1x_decompress_safe(stream->input, (size_t)length,
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 2797763ed046..9783e01c8100 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -40,8 +40,8 @@ extern void *squashfs_decompressor_setup(struct super_block *, unsigned short);
/* decompressor_xxx.c */
extern void *squashfs_decompressor_create(struct squashfs_sb_info *, void *);
extern void squashfs_decompressor_destroy(struct squashfs_sb_info *);
-extern int squashfs_decompress(struct squashfs_sb_info *, struct buffer_head **,
- int, int, int, struct squashfs_page_actor *);
+extern int squashfs_decompress(struct squashfs_sb_info *, struct bio *,
+ int, int, struct squashfs_page_actor *);
extern int squashfs_max_decompressors(void);
/* export.c */
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index 4b2f2051a6dc..e80419aed862 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -10,7 +10,7 @@
#include <linux/mutex.h>
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/xz.h>
#include <linux/bitops.h>
@@ -117,11 +117,12 @@ static void squashfs_xz_free(void *strm)
static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
- struct buffer_head **bh, int b, int offset, int length,
+ struct bio *bio, int offset, int length,
struct squashfs_page_actor *output)
{
- enum xz_ret xz_err;
- int avail, total = 0, k = 0;
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+ int total = 0, error = 0;
struct squashfs_xz *stream = strm;
xz_dec_reset(stream->state);
@@ -131,11 +132,23 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
stream->buf.out_size = PAGE_SIZE;
stream->buf.out = squashfs_first_page(output);
- do {
- if (stream->buf.in_pos == stream->buf.in_size && k < b) {
- avail = min(length, msblk->devblksize - offset);
+ for (;;) {
+ enum xz_ret xz_err;
+
+ if (stream->buf.in_pos == stream->buf.in_size) {
+ const void *data;
+ int avail;
+
+ if (!bio_next_segment(bio, &iter_all)) {
+ /* XZ_STREAM_END must be reached. */
+ error = -EIO;
+ break;
+ }
+
+ avail = min(length, ((int)bvec->bv_len) - offset);
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
length -= avail;
- stream->buf.in = bh[k]->b_data + offset;
+ stream->buf.in = data + offset;
stream->buf.in_size = avail;
stream->buf.in_pos = 0;
offset = 0;
@@ -150,23 +163,17 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm,
}
xz_err = xz_dec_run(stream->state, &stream->buf);
-
- if (stream->buf.in_pos == stream->buf.in_size && k < b)
- put_bh(bh[k++]);
- } while (xz_err == XZ_OK);
+ if (xz_err == XZ_STREAM_END)
+ break;
+ if (xz_err != XZ_OK) {
+ error = -EIO;
+ break;
+ }
+ }
squashfs_finish_page(output);
- if (xz_err != XZ_STREAM_END || k < b)
- goto out;
-
- return total + stream->buf.out_pos;
-
-out:
- for (; k < b; k++)
- put_bh(bh[k]);
-
- return -EIO;
+ return error ? error : total + stream->buf.out_pos;
}
const struct squashfs_decompressor squashfs_xz_comp_ops = {
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index f2226afa1625..bcb881ec47f2 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -10,7 +10,7 @@
#include <linux/mutex.h>
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/zlib.h>
#include <linux/vmalloc.h>
@@ -50,21 +50,35 @@ static void zlib_free(void *strm)
static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
- struct buffer_head **bh, int b, int offset, int length,
+ struct bio *bio, int offset, int length,
struct squashfs_page_actor *output)
{
- int zlib_err, zlib_init = 0, k = 0;
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
+ int zlib_init = 0, error = 0;
z_stream *stream = strm;
stream->avail_out = PAGE_SIZE;
stream->next_out = squashfs_first_page(output);
stream->avail_in = 0;
- do {
- if (stream->avail_in == 0 && k < b) {
- int avail = min(length, msblk->devblksize - offset);
+ for (;;) {
+ int zlib_err;
+
+ if (stream->avail_in == 0) {
+ const void *data;
+ int avail;
+
+ if (!bio_next_segment(bio, &iter_all)) {
+ /* Z_STREAM_END must be reached. */
+ error = -EIO;
+ break;
+ }
+
+ avail = min(length, ((int)bvec->bv_len) - offset);
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
length -= avail;
- stream->next_in = bh[k]->b_data + offset;
+ stream->next_in = data + offset;
stream->avail_in = avail;
offset = 0;
}
@@ -78,37 +92,28 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm,
if (!zlib_init) {
zlib_err = zlib_inflateInit(stream);
if (zlib_err != Z_OK) {
- squashfs_finish_page(output);
- goto out;
+ error = -EIO;
+ break;
}
zlib_init = 1;
}
zlib_err = zlib_inflate(stream, Z_SYNC_FLUSH);
-
- if (stream->avail_in == 0 && k < b)
- put_bh(bh[k++]);
- } while (zlib_err == Z_OK);
+ if (zlib_err == Z_STREAM_END)
+ break;
+ if (zlib_err != Z_OK) {
+ error = -EIO;
+ break;
+ }
+ }
squashfs_finish_page(output);
- if (zlib_err != Z_STREAM_END)
- goto out;
-
- zlib_err = zlib_inflateEnd(stream);
- if (zlib_err != Z_OK)
- goto out;
-
- if (k < b)
- goto out;
-
- return stream->total_out;
-
-out:
- for (; k < b; k++)
- put_bh(bh[k]);
+ if (!error)
+ if (zlib_inflateEnd(stream) != Z_OK)
+ error = -EIO;
- return -EIO;
+ return error ? error : stream->total_out;
}
const struct squashfs_decompressor squashfs_zlib_comp_ops = {
diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
index b448c2a1d0ed..b7cb1faa652d 100644
--- a/fs/squashfs/zstd_wrapper.c
+++ b/fs/squashfs/zstd_wrapper.c
@@ -9,7 +9,7 @@
*/
#include <linux/mutex.h>
-#include <linux/buffer_head.h>
+#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/zstd.h>
#include <linux/vmalloc.h>
@@ -59,33 +59,44 @@ static void zstd_free(void *strm)
static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
- struct buffer_head **bh, int b, int offset, int length,
+ struct bio *bio, int offset, int length,
struct squashfs_page_actor *output)
{
struct workspace *wksp = strm;
ZSTD_DStream *stream;
size_t total_out = 0;
- size_t zstd_err;
- int k = 0;
+ int error = 0;
ZSTD_inBuffer in_buf = { NULL, 0, 0 };
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
+ struct bvec_iter_all iter_all = {};
+ struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
stream = ZSTD_initDStream(wksp->window_size, wksp->mem, wksp->mem_size);
if (!stream) {
ERROR("Failed to initialize zstd decompressor\n");
- goto out;
+ return -EIO;
}
out_buf.size = PAGE_SIZE;
out_buf.dst = squashfs_first_page(output);
- do {
- if (in_buf.pos == in_buf.size && k < b) {
- int avail = min(length, msblk->devblksize - offset);
+ for (;;) {
+ size_t zstd_err;
+ if (in_buf.pos == in_buf.size) {
+ const void *data;
+ int avail;
+
+ if (!bio_next_segment(bio, &iter_all)) {
+ error = -EIO;
+ break;
+ }
+
+ avail = min(length, ((int)bvec->bv_len) - offset);
+ data = page_address(bvec->bv_page) + bvec->bv_offset;
length -= avail;
- in_buf.src = bh[k]->b_data + offset;
+ in_buf.src = data + offset;
in_buf.size = avail;
in_buf.pos = 0;
offset = 0;
@@ -97,8 +108,8 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
/* Shouldn't run out of pages
* before stream is done.
*/
- squashfs_finish_page(output);
- goto out;
+ error = -EIO;
+ break;
}
out_buf.pos = 0;
out_buf.size = PAGE_SIZE;
@@ -107,29 +118,20 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
total_out -= out_buf.pos;
zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf);
total_out += out_buf.pos; /* add the additional data produced */
-
- if (in_buf.pos == in_buf.size && k < b)
- put_bh(bh[k++]);
- } while (zstd_err != 0 && !ZSTD_isError(zstd_err));
-
- squashfs_finish_page(output);
-
- if (ZSTD_isError(zstd_err)) {
- ERROR("zstd decompression error: %d\n",
- (int)ZSTD_getErrorCode(zstd_err));
- goto out;
+ if (zstd_err == 0)
+ break;
+
+ if (ZSTD_isError(zstd_err)) {
+ ERROR("zstd decompression error: %d\n",
+ (int)ZSTD_getErrorCode(zstd_err));
+ error = -EIO;
+ break;
+ }
}
- if (k < b)
- goto out;
-
- return (int)total_out;
-
-out:
- for (; k < b; k++)
- put_bh(bh[k]);
+ squashfs_finish_page(output);
- return -EIO;
+ return error ? error : total_out;
}
const struct squashfs_decompressor squashfs_zstd_comp_ops = {
diff --git a/fs/sync.c b/fs/sync.c
index 4d1ff010bc5a..c6f6f5be5682 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -161,7 +161,7 @@ SYSCALL_DEFINE1(syncfs, int, fd)
{
struct fd f = fdget(fd);
struct super_block *sb;
- int ret;
+ int ret, ret2;
if (!f.file)
return -EBADF;
@@ -171,8 +171,10 @@ SYSCALL_DEFINE1(syncfs, int, fd)
ret = sync_filesystem(sb);
up_read(&sb->s_umount);
+ ret2 = errseq_check_and_advance(&sb->s_wb_err, &f.file->f_sb_err);
+
fdput(f);
- return ret;
+ return ret ? ret : ret2;
}
/**
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 0f5a480fe264..31288d8fa2ce 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -815,7 +815,7 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum)
pr_err("(pid %d) start dumping LEB %d\n", current->pid, lnum);
- buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+ buf = __vmalloc(c->leb_size, GFP_NOFS);
if (!buf) {
ubifs_err(c, "cannot allocate memory for dumping LEB %d", lnum);
return;
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 29826c51883a..22bfda158f7f 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -1095,7 +1095,7 @@ static int scan_check_cb(struct ubifs_info *c,
return LPT_SCAN_CONTINUE;
}
- buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+ buf = __vmalloc(c->leb_size, GFP_NOFS);
if (!buf)
return -ENOMEM;
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index ff5e0411cf2d..d76a19e460cd 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -1596,7 +1596,7 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum)
if (!dbg_is_chk_lprops(c))
return 0;
- buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+ buf = p = __vmalloc(c->leb_size, GFP_NOFS);
if (!buf) {
ubifs_err(c, "cannot allocate memory for ltab checking");
return 0;
@@ -1845,7 +1845,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum)
void *buf, *p;
pr_err("(pid %d) start dumping LEB %d\n", current->pid, lnum);
- buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+ buf = p = __vmalloc(c->leb_size, GFP_NOFS);
if (!buf) {
ubifs_err(c, "cannot allocate memory to dump LPT");
return;
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 283f9eb48410..2c294085ffed 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -977,7 +977,7 @@ static int dbg_scan_orphans(struct ubifs_info *c, struct check_info *ci)
if (c->no_orphs)
return 0;
- buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+ buf = __vmalloc(c->leb_size, GFP_NOFS);
if (!buf) {
ubifs_err(c, "cannot allocate memory to check orphans");
return 0;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index e875bc5668ee..adaba8e8b326 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -195,10 +195,9 @@ static int udf_readpage(struct file *file, struct page *page)
return mpage_readpage(page, udf_get_block);
}
-static int udf_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void udf_readahead(struct readahead_control *rac)
{
- return mpage_readpages(mapping, pages, nr_pages, udf_get_block);
+ mpage_readahead(rac, udf_get_block);
}
static int udf_write_begin(struct file *file, struct address_space *mapping,
@@ -234,7 +233,7 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block)
const struct address_space_operations udf_aops = {
.readpage = udf_readpage,
- .readpages = udf_readpages,
+ .readahead = udf_readahead,
.writepage = udf_writepage,
.writepages = udf_writepages,
.write_begin = udf_write_begin,
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 1da94237a8cf..f1366475c389 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -48,7 +48,7 @@ __kmem_vmalloc(size_t size, xfs_km_flags_t flags)
if (flags & KM_NOFS)
nofs_flag = memalloc_nofs_save();
- ptr = __vmalloc(size, lflags, PAGE_KERNEL);
+ ptr = __vmalloc(size, lflags);
if (flags & KM_NOFS)
memalloc_nofs_restore(nofs_flag);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 9d9cebf18726..1fd4fb7a607c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -621,14 +621,11 @@ xfs_vm_readpage(
return iomap_readpage(page, &xfs_read_iomap_ops);
}
-STATIC int
-xfs_vm_readpages(
- struct file *unused,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned nr_pages)
+STATIC void
+xfs_vm_readahead(
+ struct readahead_control *rac)
{
- return iomap_readpages(mapping, pages, nr_pages, &xfs_read_iomap_ops);
+ iomap_readahead(rac, &xfs_read_iomap_ops);
}
static int
@@ -644,7 +641,7 @@ xfs_iomap_swapfile_activate(
const struct address_space_operations xfs_address_space_operations = {
.readpage = xfs_vm_readpage,
- .readpages = xfs_vm_readpages,
+ .readahead = xfs_vm_readahead,
.writepage = xfs_vm_writepage,
.writepages = xfs_vm_writepages,
.set_page_dirty = iomap_set_page_dirty,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 9ec3eaf1c618..65538d18e64f 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -477,7 +477,7 @@ _xfs_buf_map_pages(
nofs_flag = memalloc_nofs_save();
do {
bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
- -1, PAGE_KERNEL);
+ -1);
if (bp->b_addr)
break;
vm_unmap_aliases();
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 3ce9829a6936..dba874a61fc5 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -78,10 +78,9 @@ static int zonefs_readpage(struct file *unused, struct page *page)
return iomap_readpage(page, &zonefs_iomap_ops);
}
-static int zonefs_readpages(struct file *unused, struct address_space *mapping,
- struct list_head *pages, unsigned int nr_pages)
+static void zonefs_readahead(struct readahead_control *rac)
{
- return iomap_readpages(mapping, pages, nr_pages, &zonefs_iomap_ops);
+ iomap_readahead(rac, &zonefs_iomap_ops);
}
/*
@@ -128,7 +127,7 @@ static int zonefs_writepages(struct address_space *mapping,
static const struct address_space_operations zonefs_file_aops = {
.readpage = zonefs_readpage,
- .readpages = zonefs_readpages,
+ .readahead = zonefs_readahead,
.writepage = zonefs_writepage,
.writepages = zonefs_writepages,
.set_page_dirty = iomap_set_page_dirty,