From a50527b19c62c808a7fca022816fff88a50b948d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 2 Dec 2011 09:17:02 +0800 Subject: fs: Make write(2) interruptible by a fatal signal Currently write(2) to a file is not interruptible by any signal. Sometimes this is desirable, e.g. when you want to quickly kill a process hogging your disk. Also, with commit 499d05ecf990 ("mm: Make task in balance_dirty_pages() killable"), it's necessary to abort the current write accordingly to avoid it quickly dirtying lots more pages at unthrottled rate. This patch makes write interruptible by SIGKILL. We do not allow write to be interruptible by any other signal because that has larger potential of screwing some badly written applications. Reported-by: Kazuya Mio Tested-by: Kazuya Mio Acked-by: Matthew Wilcox Signed-off-by: Jan Kara Signed-off-by: Wu Fengguang --- mm/filemap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index c0018f2d50e0..c106d3b3cc64 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2407,7 +2407,6 @@ static ssize_t generic_perform_write(struct file *file, iov_iter_count(i)); again: - /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the @@ -2463,7 +2462,10 @@ again: written += copied; balance_dirty_pages_ratelimited(mapping); - + if (fatal_signal_pending(current)) { + status = -EINTR; + break; + } } while (iov_iter_count(i)); return written ? written : status; -- cgit v1.2.3 From e6f67b8c05f5e129e126f4409ddac6f25f58ffcb Mon Sep 17 00:00:00 2001 From: Dave Kleikamp Date: Wed, 21 Dec 2011 11:05:48 -0600 Subject: vfs: __read_cache_page should use gfp argument rather than GFP_KERNEL lockdep reports a deadlock in jfs because a special inode's rw semaphore is taken recursively. The mapping's gfp mask is GFP_NOFS, but is not used when __read_cache_page() calls add_to_page_cache_lru(). Signed-off-by: Dave Kleikamp Acked-by: Hugh Dickins Acked-by: Al Viro Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- mm/filemap.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index c106d3b3cc64..5f0a3c91fdac 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1828,7 +1828,7 @@ repeat: page = __page_cache_alloc(gfp | __GFP_COLD); if (!page) return ERR_PTR(-ENOMEM); - err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); + err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { page_cache_release(page); if (err == -EEXIST) @@ -1925,10 +1925,7 @@ static struct page *wait_on_page_read(struct page *page) * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with - * any new page allocations done using the specified allocation flags. Note - * that the Radix tree operations will still use GFP_KERNEL, so you can't - * expect to do this atomically or anything like that - but you can pass in - * other page requirements. + * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. */ -- cgit v1.2.3 From 649fc7b1b046eb98bf9e3fe20c9d11f629293140 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 26 Jul 2011 04:31:05 -0400 Subject: should_remove_suid(): inode->i_mode is umode_t Signed-off-by: Al Viro --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 5f0a3c91fdac..a0701e6eec10 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1968,7 +1968,7 @@ EXPORT_SYMBOL(read_cache_page); */ int should_remove_suid(struct dentry *dentry) { - mode_t mode = dentry->d_inode->i_mode; + umode_t mode = dentry->d_inode->i_mode; int kill = 0; /* suid always must be killed */ -- cgit v1.2.3 From 0faa70cb0180d45a06208e54b552a538aabb8a30 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 10 Jan 2012 15:07:53 -0800 Subject: mm: filemap: pass __GFP_WRITE from grab_cache_page_write_begin() Tell the page allocator that pages allocated through grab_cache_page_write_begin() are expected to become dirty soon. Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Acked-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: Michal Hocko Cc: KAMEZAWA Hiroyuki Cc: Christoph Hellwig Cc: Wu Fengguang Cc: Dave Chinner Cc: Jan Kara Cc: Shaohua Li Cc: Chris Mason Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index a0701e6eec10..c4ee2e918bea 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2351,8 +2351,11 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { int status; + gfp_t gfp_mask; struct page *page; gfp_t gfp_notmask = 0; + + gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE; if (flags & AOP_FLAG_NOFS) gfp_notmask = __GFP_FS; repeat: @@ -2360,7 +2363,7 @@ repeat: if (page) goto found; - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask); + page = __page_cache_alloc(gfp_mask & ~gfp_notmask); if (!page) return NULL; status = add_to_page_cache_lru(page, mapping, index, -- cgit v1.2.3 From ab936cbcd02072a34b60d268f94440fd5cf1970b Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 12 Jan 2012 17:17:44 -0800 Subject: memcg: add mem_cgroup_replace_page_cache() to fix LRU issue Commit ef6a3c6311 ("mm: add replace_page_cache_page() function") added a function replace_page_cache_page(). This function replaces a page in the radix-tree with a new page. WHen doing this, memory cgroup needs to fix up the accounting information. memcg need to check PCG_USED bit etc. In some(many?) cases, 'newpage' is on LRU before calling replace_page_cache(). So, memcg's LRU accounting information should be fixed, too. This patch adds mem_cgroup_replace_page_cache() and removes the old hooks. In that function, old pages will be unaccounted without touching res_counter and new page will be accounted to the memcg (of old page). WHen overwriting pc->mem_cgroup of newpage, take zone->lru_lock and avoid races with LRU handling. Background: replace_page_cache_page() is called by FUSE code in its splice() handling. Here, 'newpage' is replacing oldpage but this newpage is not a newly allocated page and may be on LRU. LRU mis-accounting will be critical for memory cgroup because rmdir() checks the whole LRU is empty and there is no account leak. If a page is on the other LRU than it should be, rmdir() will fail. This bug was added in March 2011, but no bug report yet. I guess there are not many people who use memcg and FUSE at the same time with upstream kernels. The result of this bug is that admin cannot destroy a memcg because of account leak. So, no panic, no deadlock. And, even if an active cgroup exist, umount can succseed. So no problem at shutdown. Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Miklos Szeredi Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index c4ee2e918bea..97f49ed35bd2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -393,24 +393,11 @@ EXPORT_SYMBOL(filemap_write_and_wait_range); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { int error; - struct mem_cgroup *memcg = NULL; VM_BUG_ON(!PageLocked(old)); VM_BUG_ON(!PageLocked(new)); VM_BUG_ON(new->mapping); - /* - * This is not page migration, but prepare_migration and - * end_migration does enough work for charge replacement. - * - * In the longer term we probably want a specialized function - * for moving the charge from old to new in a more efficient - * manner. - */ - error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask); - if (error) - return error; - error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); if (!error) { struct address_space *mapping = old->mapping; @@ -432,13 +419,12 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) if (PageSwapBacked(new)) __inc_zone_page_state(new, NR_SHMEM); spin_unlock_irq(&mapping->tree_lock); + /* mem_cgroup codes must not be called under tree_lock */ + mem_cgroup_replace_page_cache(old, new); radix_tree_preload_end(); if (freepage) freepage(old); page_cache_release(old); - mem_cgroup_end_migration(memcg, old, new, true); - } else { - mem_cgroup_end_migration(memcg, old, new, false); } return error; -- cgit v1.2.3 From 3deaa7190a8da38453c4fabd9dec7f66d17fff67 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 3 Feb 2012 15:37:17 -0800 Subject: readahead: fix pipeline break caused by block plug Herbert Poetzl reported a performance regression since 2.6.39. The test is a simple dd read, but with big block size. The reason is: T1: ra (A, A+128k), (A+128k, A+256k) T2: lock_page for page A, submit the 256k T3: hit page A+128K, ra (A+256k, A+384). the range isn't submitted because of plug and there isn't any lock_page till we hit page A+256k because all pages from A to A+256k is in memory T4: hit page A+256k, ra (A+384, A+ 512). Because of plug, the range isn't submitted again. T5: lock_page A+256k, so (A+256k, A+512k) will be submitted. The task is waitting for (A+256k, A+512k) finish. There is no request to disk in T3 and T4, so readahead pipeline breaks. We really don't need block plug for generic_file_aio_read() for buffered I/O. The readahead already has plug and has fine grained control when I/O should be submitted. Deleting plug for buffered I/O fixes the regression. One side effect is plug makes the request size 256k, the size is 128k without it. This is because default ra size is 128k and not a reason we need plug here. Vivek said: : We submit some readahead IO to device request queue but because of nested : plug, queue never gets unplugged. When read logic reaches a page which is : not in page cache, it waits for page to be read from the disk : (lock_page_killable()) and that time we flush the plug list. : : So effectively read ahead logic is kind of broken in parts because of : nested plugging. Removing top level plug (generic_file_aio_read()) for : buffered reads, will allow unplugging queue earlier for readahead. Signed-off-by: Shaohua Li Signed-off-by: Wu Fengguang Reported-by: Herbert Poetzl Tested-by: Eric Dumazet Cc: Christoph Hellwig Cc: Jens Axboe Cc: Vivek Goyal Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 97f49ed35bd2..b66275757c28 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1400,15 +1400,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long seg = 0; size_t count; loff_t *ppos = &iocb->ki_pos; - struct blk_plug plug; count = 0; retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); if (retval) return retval; - blk_start_plug(&plug); - /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { loff_t size; @@ -1424,8 +1421,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); if (!retval) { + struct blk_plug plug; + + blk_start_plug(&plug); retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); + blk_finish_plug(&plug); } if (retval > 0) { *ppos = pos + retval; @@ -1481,7 +1482,6 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, break; } out: - blk_finish_plug(&plug); return retval; } EXPORT_SYMBOL(generic_file_aio_read); -- cgit v1.2.3