mm, fs: obey gfp_mapping for add_to_page_cache()

Commit 6afdb859b710 ("mm: do not ignore mapping_gfp_mask in page cache
allocation paths") has caught some users of hardcoded GFP_KERNEL used in
the page cache allocation paths.  This, however, wasn't complete and
there were others which went unnoticed.

Dave Chinner has reported the following deadlock for xfs on loop device:
: With the recent merge of the loop device changes, I'm now seeing
: XFS deadlock on my single CPU, 1GB RAM VM running xfs/073.
:
: The deadlocked is as follows:
:
: kloopd1: loop_queue_read_work
:       xfs_file_iter_read
:       lock XFS inode XFS_IOLOCK_SHARED (on image file)
:       page cache read (GFP_KERNEL)
:       radix tree alloc
:       memory reclaim
:       reclaim XFS inodes
:       log force to unpin inodes
:       <wait for log IO completion>
:
: xfs-cil/loop1: <does log force IO work>
:       xlog_cil_push
:       xlog_write
:       <loop issuing log writes>
:               xlog_state_get_iclog_space()
:               <blocks due to all log buffers under write io>
:               <waits for IO completion>
:
: kloopd1: loop_queue_write_work
:       xfs_file_write_iter
:       lock XFS inode XFS_IOLOCK_EXCL (on image file)
:       <wait for inode to be unlocked>
:
: i.e. the kloopd, with it's split read and write work queues, has
: introduced a dependency through memory reclaim. i.e. that writes
: need to be able to progress for reads make progress.
:
: The problem, fundamentally, is that mpage_readpages() does a
: GFP_KERNEL allocation, rather than paying attention to the inode's
: mapping gfp mask, which is set to GFP_NOFS.
:
: The didn't used to happen, because the loop device used to issue
: reads through the splice path and that does:
:
:       error = add_to_page_cache_lru(page, mapping, index,
:                       GFP_KERNEL & mapping_gfp_mask(mapping));

This has changed by commit aa4d86163e4 ("block: loop: switch to VFS
ITER_BVEC").

This patch changes mpage_readpage{s} to follow gfp mask set for the
mapping.  There are, however, other places which are doing basically the
same.

lustre:ll_dir_filler is doing GFP_KERNEL from the function which
apparently uses GFP_NOFS for other allocations so let's make this
consistent.

cifs:readpages_get_pages is called from cifs_readpages and
__cifs_readpages_from_fscache called from the same path obeys mapping
gfp.

ramfs_nommu_expand_for_mapping is hardcoding GFP_KERNEL as well
regardless it uses mapping_gfp_mask for the page allocation.

ext4_mpage_readpages is the called from the page cache allocation path
same as read_pages and read_cache_pages

As I've noticed in my previous post I cannot say I would be happy about
sprinkling mapping_gfp_mask all over the place and it sounds like we
should drop gfp_mask argument altogether and use it internally in
__add_to_page_cache_locked that would require all the filesystems to use
mapping gfp consistently which I am not sure is the case here.  From a
quick glance it seems that some file system use it all the time while
others are selective.

Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Dave Chinner <david@fromorbit.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Ming Lei <ming.lei@canonical.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Oleg Drokin <oleg.drokin@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c
index 769b61193d87ef29c7868465c50e9b8ab87ee045..a9bc6e23fc2582f39c5a753638979fba15451e61 100644 (file)
--- a/drivers/staging/lustre/lustre/llite/dir.c
+++ b/drivers/staging/lustre/lustre/llite/dir.c
@@ -224,7 +224,7 @@ static int ll_dir_filler(void *_hash, struct page *page0)
 
                prefetchw(&page->flags);
                ret = add_to_page_cache_lru(page, inode->i_mapping, offset,
-                                           GFP_KERNEL);
+                                           GFP_NOFS);
                if (ret == 0) {
                        unlock_page(page);
                } else {

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index e2a6af1508af2aef789d0caab21fedfa91d49c60..62203c387db45a23b05c1cadcc0946843ea5332f 100644 (file)
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3380,6 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
        struct page *page, *tpage;
        unsigned int expected_index;
        int rc;
+       gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping);
 
        INIT_LIST_HEAD(tmplist);
 
@@ -3392,7 +3393,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
         */
        __set_page_locked(page);
        rc = add_to_page_cache_locked(page, mapping,
-                                     page->index, GFP_KERNEL);
+                                     page->index, gfp);
 
        /* give up if we can't stick it in the cache */
        if (rc) {
@@ -3418,8 +3419,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
                        break;
 
                __set_page_locked(page);
-               if (add_to_page_cache_locked(page, mapping, page->index,
-                                                               GFP_KERNEL)) {
+               if (add_to_page_cache_locked(page, mapping, page->index, gfp)) {
                        __clear_page_locked(page);
                        break;
                }

diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index e26803fb210d3bf1134f500b85f43802b2ce7e58..560af043770462df6170acd4d523f9d0385884a3 100644 (file)
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -165,8 +165,8 @@ int ext4_mpage_readpages(struct address_space *mapping,
                if (pages) {
                        page = list_entry(pages->prev, struct page, lru);
                        list_del(&page->lru);
-                       if (add_to_page_cache_lru(page, mapping,
-                                                 page->index, GFP_KERNEL))
+                       if (add_to_page_cache_lru(page, mapping, page->index,
+                                       GFP_KERNEL & mapping_gfp_mask(mapping)))
                                goto next_page;
                }
 

diff --git a/fs/mpage.c b/fs/mpage.c
index 778a4ddef77a21844b08af82058d3b188371dc01..a7c34274f2076bc36e9cb9797f682988e617417f 100644 (file)
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -139,7 +139,8 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
 static struct bio *
 do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
                sector_t *last_block_in_bio, struct buffer_head *map_bh,
-               unsigned long *first_logical_block, get_block_t get_block)
+               unsigned long *first_logical_block, get_block_t get_block,
+               gfp_t gfp)
 {
        struct inode *inode = page->mapping->host;
        const unsigned blkbits = inode->i_blkbits;
@@ -277,8 +278,7 @@ alloc_new:
                                goto out;
                }
                bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
-                               min_t(int, nr_pages, BIO_MAX_PAGES),
-                               GFP_KERNEL);
+                               min_t(int, nr_pages, BIO_MAX_PAGES), gfp);
                if (bio == NULL)
                        goto confused;
        }
@@ -361,6 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
        sector_t last_block_in_bio = 0;
        struct buffer_head map_bh;
        unsigned long first_logical_block = 0;
+       gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping);
 
        map_bh.b_state = 0;
        map_bh.b_size = 0;
@@ -370,12 +371,13 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
                prefetchw(&page->flags);
                list_del(&page->lru);
                if (!add_to_page_cache_lru(page, mapping,
-                                       page->index, GFP_KERNEL)) {
+                                       page->index,
+                                       gfp)) {
                        bio = do_mpage_readpage(bio, page,
                                        nr_pages - page_idx,
                                        &last_block_in_bio, &map_bh,
                                        &first_logical_block,
-                                       get_block);
+                                       get_block, gfp);
                }
                page_cache_release(page);
        }
@@ -395,11 +397,12 @@ int mpage_readpage(struct page *page, get_block_t get_block)
        sector_t last_block_in_bio = 0;
        struct buffer_head map_bh;
        unsigned long first_logical_block = 0;
+       gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping);
 
        map_bh.b_state = 0;
        map_bh.b_size = 0;
        bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
-                       &map_bh, &first_logical_block, get_block);
+                       &map_bh, &first_logical_block, get_block, gfp);
        if (bio)
                mpage_bio_submit(READ, bio);
        return 0;

diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index ba1323a94924962299d27cbe67d76ff4e0056bb9..a586467f6ff6c73a4f31234fd96fce0a7b0dc34b 100644 (file)
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -70,6 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
        unsigned order;
        void *data;
        int ret;
+       gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
 
        /* make various checks */
        order = get_order(newsize);
@@ -84,7 +85,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 
        /* allocate enough contiguous pages to be able to satisfy the
         * request */
-       pages = alloc_pages(mapping_gfp_mask(inode->i_mapping), order);
+       pages = alloc_pages(gfp, order);
        if (!pages)
                return -ENOMEM;
 
@@ -108,7 +109,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
                struct page *page = pages + loop;
 
                ret = add_to_page_cache_lru(page, inode->i_mapping, loop,
-                                       GFP_KERNEL);
+                                       gfp);
                if (ret < 0)
                        goto add_error;
 

diff --git a/mm/readahead.c b/mm/readahead.c
index 60cd846a9a4401f73a6a51539507ecc22fb308d4..24682f6f4cfd1d84d7245faea0da78e7fd17e716 100644 (file)
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -89,8 +89,8 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
        while (!list_empty(pages)) {
                page = list_to_page(pages);
                list_del(&page->lru);
-               if (add_to_page_cache_lru(page, mapping,
-                                       page->index, GFP_KERNEL)) {
+               if (add_to_page_cache_lru(page, mapping, page->index,
+                               GFP_KERNEL & mapping_gfp_mask(mapping))) {
                        read_cache_pages_invalidate_page(mapping, page);
                        continue;
                }
@@ -127,8 +127,8 @@ static int read_pages(struct address_space *mapping, struct file *filp,
        for (page_idx = 0; page_idx < nr_pages; page_idx++) {
                struct page *page = list_to_page(pages);
                list_del(&page->lru);
-               if (!add_to_page_cache_lru(page, mapping,
-                                       page->index, GFP_KERNEL)) {
+               if (!add_to_page_cache_lru(page, mapping, page->index,
+                               GFP_KERNEL & mapping_gfp_mask(mapping))) {
                        mapping->a_ops->readpage(filp, page);
                }
                page_cache_release(page);