From 76f60268e70a700c04c85e1b0d520c94062a40a2 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 15 Apr 2014 16:04:15 +0900 Subject: f2fs: call redirty_page_for_writepage This patch replace some general codes with redirty_page_for_writepage, which can be enabled after consideration on additional procedure like counting dirty pages appropriately. Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a161e955c4c..f760793c1a6 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1227,10 +1227,7 @@ static int f2fs_write_node_page(struct page *page, return 0; redirty_out: - dec_page_count(sbi, F2FS_DIRTY_NODES); - wbc->pages_skipped++; - account_page_redirty(page); - set_page_dirty(page); + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; } -- cgit v1.2.3-70-g09d2 From b156d542415d88c265a0a579448a93e66aa18e33 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Tue, 15 Apr 2014 17:51:05 +0900 Subject: f2fs: make recover_inline_xattr() static Make recover_inline_xattr() static, because this function is used only in this file. Signed-off-by: Jingoo Han Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index f760793c1a6..38fe5f534e7 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1531,7 +1531,7 @@ void recover_node_page(struct f2fs_sb_info *sbi, struct page *page, clear_node_page_dirty(page); } -void recover_inline_xattr(struct inode *inode, struct page *page) +static void recover_inline_xattr(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); void *src_addr, *dst_addr; -- cgit v1.2.3-70-g09d2 From 94dac22e72e891b16e8e8abbdb6df10f322d20e0 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 17 Apr 2014 10:51:05 +0800 Subject: f2fs: introduce raw_nat_from_node_info() to simplfy codes This patch introduce raw_nat_from_node_info() to simplfy some codes, and also use exist function node_info_from_raw_nat() to do the same job. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 15 +++------------ fs/f2fs/node.h | 8 ++++++++ 2 files changed, 11 insertions(+), 12 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 38fe5f534e7..837f5fdabd1 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -179,9 +179,7 @@ retry: write_unlock(&nm_i->nat_tree_lock); goto retry; } - nat_set_blkaddr(e, le32_to_cpu(ne->block_addr)); - nat_set_ino(e, le32_to_cpu(ne->ino)); - nat_set_version(e, ne->version); + node_info_from_raw_nat(&e->ni, ne); } write_unlock(&nm_i->nat_tree_lock); } @@ -1755,9 +1753,7 @@ retry: write_unlock(&nm_i->nat_tree_lock); goto retry; } - nat_set_blkaddr(ne, le32_to_cpu(raw_ne.block_addr)); - nat_set_ino(ne, le32_to_cpu(raw_ne.ino)); - nat_set_version(ne, raw_ne.version); + node_info_from_raw_nat(&ne->ni, &raw_ne); __set_nat_cache_dirty(nm_i, ne); write_unlock(&nm_i->nat_tree_lock); } @@ -1790,7 +1786,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) nid_t nid; struct f2fs_nat_entry raw_ne; int offset = -1; - block_t new_blkaddr; if (nat_get_blkaddr(ne) == NEW_ADDR) continue; @@ -1826,11 +1821,7 @@ to_nat_page: f2fs_bug_on(!nat_blk); raw_ne = nat_blk->entries[nid - start_nid]; flush_now: - new_blkaddr = nat_get_blkaddr(ne); - - raw_ne.ino = cpu_to_le32(nat_get_ino(ne)); - raw_ne.block_addr = cpu_to_le32(new_blkaddr); - raw_ne.version = nat_get_version(ne); + raw_nat_from_node_info(&raw_ne, &ne->ni); if (offset < 0) { nat_blk->entries[nid - start_nid] = raw_ne; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 5decc1a375f..41bb65b1c97 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -75,6 +75,14 @@ static inline void node_info_from_raw_nat(struct node_info *ni, ni->version = raw_ne->version; } +static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne, + struct node_info *ni) +{ + raw_ne->ino = cpu_to_le32(ni->ino); + raw_ne->block_addr = cpu_to_le32(ni->blk_addr); + raw_ne->version = ni->version; +} + enum nid_type { FREE_NIDS, /* indicates the free nid list */ NAT_ENTRIES /* indicates the cached nat entry */ -- cgit v1.2.3-70-g09d2 From 7ee0eeabcdbb1610d7bc75d1132a43e0c7f7ef28 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 18 Apr 2014 11:14:37 +0900 Subject: f2fs: add available_nids to fix handling max_nid correctly This patch introduces available_nids for alloc_nids() and fixes max_nid for build_free_nids() and scan_nat_pages(). Signed-off-by: Chao Yu Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 1 + fs/f2fs/node.c | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 55152de1118..556d06b67e6 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -244,6 +244,7 @@ static inline void set_raw_extent(struct extent_info *ext, struct f2fs_nm_info { block_t nat_blkaddr; /* base disk address of NAT */ nid_t max_nid; /* maximum possible node ids */ + nid_t available_nids; /* maximum available node ids */ nid_t next_scan_nid; /* the next nid to be scanned */ unsigned int ram_thresh; /* control the memory footprint */ diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 837f5fdabd1..6ebdba151f1 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1447,7 +1447,7 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i = NULL; retry: - if (unlikely(sbi->total_valid_node_count + 1 >= nm_i->max_nid)) + if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids)) return false; spin_lock(&nm_i->free_nid_list_lock); @@ -1859,8 +1859,10 @@ static int init_node_manager(struct f2fs_sb_info *sbi) nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1; nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg); + nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks; + /* not used nids: 0, node, meta, (and root counted as valid node) */ - nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks - 3; + nm_i->available_nids = nm_i->max_nid - 3; nm_i->fcnt = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; -- cgit v1.2.3-70-g09d2 From e8271fa3908de52937d298b339f9f7984c491cc6 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 18 Apr 2014 15:21:04 +0900 Subject: f2fs: avoid BUG_ON when mouting corrupted image having garbage blocks If the disk has some garbage blocks, F2FS is able to face with BUG_ON when recovering direct node blocks. This patch detects the error case and avoids that prior to reaching BUG_ON. Alexey Khoroshilov addressed the potential security issues as follows. "An ability to trigger a BUG_ON assert by mounting a crafted image is usually considered as a local denial of service [1-3]. As far as I understand, the reason is that some kernel data may become inconsistent that can lead to further problems. [1] http://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2011-3353 [2] http://www.openwall.com/lists/oss-security/2011/06/24/4 [3] http://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2011-2928 etc." Reported-by: Andrey Tsyvarev Cc: Alexey Khoroshilov Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 6ebdba151f1..64755f49d6e 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1609,6 +1609,11 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) struct node_info old_ni, new_ni; struct page *ipage; + get_node_info(sbi, ino, &old_ni); + + if (unlikely(old_ni.blk_addr != NULL_ADDR)) + return -EINVAL; + ipage = grab_cache_page(NODE_MAPPING(sbi), ino); if (!ipage) return -ENOMEM; @@ -1616,7 +1621,6 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) /* Should not use this inode from free nid list */ remove_free_nid(NM_I(sbi), ino); - get_node_info(sbi, ino, &old_ni); SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); -- cgit v1.2.3-70-g09d2 From 6fb03f3a40805a412c9b285010ffdc2e7563f81b Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 16 Apr 2014 10:47:06 +0900 Subject: f2fs: adjust free mem size to flush dentry blocks If so many dirty dentry blocks are cached, not reached to the flush condition, we should fall into livelock in balance_dirty_pages. So, let's consider the mem size for the condition. Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 3 ++- fs/f2fs/f2fs.h | 1 + fs/f2fs/node.c | 44 ++++++++++++++++++++++++++------------------ fs/f2fs/node.h | 5 +++-- 4 files changed, 32 insertions(+), 21 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b5cd6d1c932..6b89b2517ed 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -863,7 +863,8 @@ static int f2fs_write_data_pages(struct address_space *mapping, return 0; if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && - get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA)) + get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) && + available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; diff = nr_pages_to_write(sbi, DATA, wbc); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 556d06b67e6..97da71d96ce 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1143,6 +1143,7 @@ f2fs_hash_t f2fs_dentry_hash(const char *, size_t); struct dnode_of_data; struct node_info; +bool available_free_memory(struct f2fs_sb_info *, int); int is_checkpointed_node(struct f2fs_sb_info *, nid_t); bool fsync_mark_done(struct f2fs_sb_info *, nid_t); void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 64755f49d6e..2803ef6cf53 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -26,20 +26,26 @@ static struct kmem_cache *nat_entry_slab; static struct kmem_cache *free_nid_slab; -static inline bool available_free_memory(struct f2fs_nm_info *nm_i, int type) +bool available_free_memory(struct f2fs_sb_info *sbi, int type) { + struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; unsigned long mem_size = 0; + bool res = false; si_meminfo(&val); - if (type == FREE_NIDS) - mem_size = nm_i->fcnt * sizeof(struct free_nid); - else if (type == NAT_ENTRIES) - mem_size += nm_i->nat_cnt * sizeof(struct nat_entry); - mem_size >>= 12; - - /* give 50:50 memory for free nids and nat caches respectively */ - return (mem_size < ((val.totalram * nm_i->ram_thresh) >> 11)); + /* give 25%, 25%, 50% memory for each components respectively */ + if (type == FREE_NIDS) { + mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12; + res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); + } else if (type == NAT_ENTRIES) { + mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12; + res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); + } else if (type == DIRTY_DENTS) { + mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); + res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1); + } + return res; } static void clear_node_page_dirty(struct page *page) @@ -241,7 +247,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); - if (available_free_memory(nm_i, NAT_ENTRIES)) + if (available_free_memory(sbi, NAT_ENTRIES)) return 0; write_lock(&nm_i->nat_tree_lock); @@ -1310,13 +1316,14 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i, radix_tree_delete(&nm_i->free_nid_root, i->nid); } -static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build) +static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) { + struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; struct nat_entry *ne; bool allocated = false; - if (!available_free_memory(nm_i, FREE_NIDS)) + if (!available_free_memory(sbi, FREE_NIDS)) return -1; /* 0 nid should not be used */ @@ -1369,9 +1376,10 @@ static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid) kmem_cache_free(free_nid_slab, i); } -static void scan_nat_page(struct f2fs_nm_info *nm_i, +static void scan_nat_page(struct f2fs_sb_info *sbi, struct page *nat_page, nid_t start_nid) { + struct f2fs_nm_info *nm_i = NM_I(sbi); struct f2fs_nat_block *nat_blk = page_address(nat_page); block_t blk_addr; int i; @@ -1386,7 +1394,7 @@ static void scan_nat_page(struct f2fs_nm_info *nm_i, blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); f2fs_bug_on(blk_addr == NEW_ADDR); if (blk_addr == NULL_ADDR) { - if (add_free_nid(nm_i, start_nid, true) < 0) + if (add_free_nid(sbi, start_nid, true) < 0) break; } } @@ -1410,7 +1418,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi) while (1) { struct page *page = get_current_nat_page(sbi, nid); - scan_nat_page(nm_i, page, nid); + scan_nat_page(sbi, page, nid); f2fs_put_page(page, 1); nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); @@ -1430,7 +1438,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi) block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr); nid = le32_to_cpu(nid_in_journal(sum, i)); if (addr == NULL_ADDR) - add_free_nid(nm_i, nid, true); + add_free_nid(sbi, nid, true); else remove_free_nid(nm_i, nid); } @@ -1507,7 +1515,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) spin_lock(&nm_i->free_nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(!i || i->state != NID_ALLOC); - if (!available_free_memory(nm_i, FREE_NIDS)) { + if (!available_free_memory(sbi, FREE_NIDS)) { __del_from_free_nid_list(nm_i, i); need_free = true; } else { @@ -1835,7 +1843,7 @@ flush_now: } if (nat_get_blkaddr(ne) == NULL_ADDR && - add_free_nid(NM_I(sbi), nid, false) <= 0) { + add_free_nid(sbi, nid, false) <= 0) { write_lock(&nm_i->nat_tree_lock); __del_from_nat_cache(nm_i, ne); write_unlock(&nm_i->nat_tree_lock); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 41bb65b1c97..a076c88bdca 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -83,9 +83,10 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne, raw_ne->version = ni->version; } -enum nid_type { +enum mem_type { FREE_NIDS, /* indicates the free nid list */ - NAT_ENTRIES /* indicates the cached nat entry */ + NAT_ENTRIES, /* indicates the cached nat entry */ + DIRTY_DENTS /* indicates dirty dentry pages */ }; /* -- cgit v1.2.3-70-g09d2 From 54b591dfda1f5ab0bc2a9ce1bee5364110168777 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 29 Apr 2014 17:28:32 +0900 Subject: f2fs: split grab_cache_page and wait_on_page_writeback for node pages This patch splits grab_cache_page_write_begin into grab_cache_page and wait_on_page_writeback for node pages. This patch intends to enhance the latency to get node pages by alleviating unnecessary wait_on_page_writeback. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/dir.c | 2 ++ fs/f2fs/inline.c | 6 ++++++ fs/f2fs/node.c | 8 ++++---- fs/f2fs/node.h | 2 +- fs/f2fs/xattr.c | 3 +++ 5 files changed, 16 insertions(+), 5 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 3581c2bde21..c3f148555c3 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -268,6 +268,8 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) { struct f2fs_inode *ri; + f2fs_wait_on_page_writeback(ipage, NODE); + /* copy name info. to this inode page */ ri = F2FS_INODE(ipage); ri->i_namelen = cpu_to_le32(name->len); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index d215dbb09f0..8bf34f052f6 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -156,6 +156,7 @@ int f2fs_write_inline_data(struct inode *inode, return err; ipage = dn.inode_page; + f2fs_wait_on_page_writeback(ipage, NODE); zero_user_segment(ipage, INLINE_DATA_OFFSET, INLINE_DATA_OFFSET + MAX_INLINE_DATA); src_addr = kmap(page); @@ -188,6 +189,8 @@ void truncate_inline_data(struct inode *inode, u64 from) if (IS_ERR(ipage)) return; + f2fs_wait_on_page_writeback(ipage, NODE); + zero_user_segment(ipage, INLINE_DATA_OFFSET + from, INLINE_DATA_OFFSET + MAX_INLINE_DATA); set_page_dirty(ipage); @@ -218,6 +221,8 @@ process_inline: ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(IS_ERR(ipage)); + f2fs_wait_on_page_writeback(ipage, NODE); + src_addr = inline_data_addr(npage); dst_addr = inline_data_addr(ipage); memcpy(dst_addr, src_addr, MAX_INLINE_DATA); @@ -229,6 +234,7 @@ process_inline: if (f2fs_has_inline_data(inode)) { ipage = get_node_page(sbi, inode->i_ino); f2fs_bug_on(IS_ERR(ipage)); + f2fs_wait_on_page_writeback(ipage, NODE); zero_user_segment(ipage, INLINE_DATA_OFFSET, INLINE_DATA_OFFSET + MAX_INLINE_DATA); clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 2803ef6cf53..059aaf5dda2 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -853,8 +853,7 @@ struct page *new_node_page(struct dnode_of_data *dn, if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) return ERR_PTR(-EPERM); - page = grab_cache_page_write_begin(NODE_MAPPING(sbi), - dn->nid, AOP_FLAG_NOFS); + page = grab_cache_page(NODE_MAPPING(sbi), dn->nid); if (!page) return ERR_PTR(-ENOMEM); @@ -871,6 +870,7 @@ struct page *new_node_page(struct dnode_of_data *dn, new_ni.ino = dn->inode->i_ino; set_node_addr(sbi, &new_ni, NEW_ADDR, false); + f2fs_wait_on_page_writeback(page, NODE); fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); set_cold_node(dn->inode, page); SetPageUptodate(page); @@ -950,8 +950,7 @@ struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) struct page *page; int err; repeat: - page = grab_cache_page_write_begin(NODE_MAPPING(sbi), - nid, AOP_FLAG_NOFS); + page = grab_cache_page(NODE_MAPPING(sbi), nid); if (!page) return ERR_PTR(-ENOMEM); @@ -1562,6 +1561,7 @@ static void recover_inline_xattr(struct inode *inode, struct page *page) src_addr = inline_xattr_addr(page); inline_size = inline_xattr_size(inode); + f2fs_wait_on_page_writeback(ipage, NODE); memcpy(dst_addr, src_addr, inline_size); update_inode(inode, ipage); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index a076c88bdca..4ee29d506f8 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -272,7 +272,7 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i) { struct f2fs_node *rn = F2FS_NODE(p); - wait_on_page_writeback(p); + f2fs_wait_on_page_writeback(p, NODE); if (i) rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 6073f9f8841..1f546b4b6b6 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -349,6 +349,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, if (ipage) { inline_addr = inline_xattr_addr(ipage); + f2fs_wait_on_page_writeback(ipage, NODE); } else { page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { @@ -356,6 +357,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, return PTR_ERR(page); } inline_addr = inline_xattr_addr(page); + f2fs_wait_on_page_writeback(page, NODE); } memcpy(inline_addr, txattr_addr, inline_size); f2fs_put_page(page, 1); @@ -376,6 +378,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, return PTR_ERR(xpage); } f2fs_bug_on(new_nid); + f2fs_wait_on_page_writeback(xpage, NODE); } else { struct dnode_of_data dn; set_new_dnode(&dn, inode, NULL, NULL, new_nid); -- cgit v1.2.3-70-g09d2 From ecda0de3430455378f1c02523bf3ad71d91d613a Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 6 May 2014 16:48:26 +0800 Subject: f2fs: add a tracepoint for f2fs_write_{meta,node,data}_page This patch adds a tracepoint for f2fs_write_{meta,node,data}_page to trace when page is writting out. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 2 ++ fs/f2fs/data.c | 2 ++ fs/f2fs/node.c | 2 ++ include/trace/events/f2fs.h | 7 +++++++ 4 files changed, 13 insertions(+) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 4206f1664be..c95d62281d7 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -157,6 +157,8 @@ static int f2fs_write_meta_page(struct page *page, struct inode *inode = page->mapping->host; struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + trace_f2fs_writepage(page, META); + if (unlikely(sbi->por_doing)) goto redirty_out; if (wbc->for_reclaim) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ea58fb698ac..b997d552880 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -788,6 +788,8 @@ static int f2fs_write_data_page(struct page *page, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, }; + trace_f2fs_writepage(page, DATA); + if (page->index < end_index) goto write; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 059aaf5dda2..49bdddbcade 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1199,6 +1199,8 @@ static int f2fs_write_node_page(struct page *page, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, }; + trace_f2fs_writepage(page, NODE); + if (unlikely(sbi->por_doing)) goto redirty_out; diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 483804b5574..d70991e69e5 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -751,6 +751,13 @@ DECLARE_EVENT_CLASS(f2fs__page, __entry->dirty) ); +DEFINE_EVENT(f2fs__page, f2fs_writepage, + + TP_PROTO(struct page *page, int type), + + TP_ARGS(page, type) +); + DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty, TP_PROTO(struct page *page, int type), -- cgit v1.2.3-70-g09d2 From e57484343898094bb8f72a2aa1a50929d27aa027 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 6 May 2014 16:51:24 +0800 Subject: f2fs: add a tracepoint for f2fs_write_{meta,node,data}_pages This patch adds a tracepoint for f2fs_write_{meta,node,data}_pages to trace when pages are fsyncing/flushing. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 2 ++ fs/f2fs/data.c | 2 ++ fs/f2fs/node.c | 2 ++ include/trace/events/f2fs.h | 64 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 70 insertions(+) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index c95d62281d7..fe968c7bfc9 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -186,6 +186,8 @@ static int f2fs_write_meta_pages(struct address_space *mapping, struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); long diff, written; + trace_f2fs_writepages(mapping->host, wbc, META); + /* collect a number of dirty meta pages and write together */ if (wbc->for_kupdate || get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b997d552880..21bfafaafe8 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -860,6 +860,8 @@ static int f2fs_write_data_pages(struct address_space *mapping, int ret; long diff; + trace_f2fs_writepages(mapping->host, wbc, DATA); + /* deal with chardevs and other special file */ if (!mapping->a_ops->writepage) return 0; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 49bdddbcade..3d60d3d34ed 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1242,6 +1242,8 @@ static int f2fs_write_node_pages(struct address_space *mapping, struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); long diff; + trace_f2fs_writepages(mapping->host, wbc, NODE); + /* balancing f2fs's metadata in background */ f2fs_balance_fs_bg(sbi); diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index d70991e69e5..91b1fcc5ec9 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -772,6 +772,70 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite, TP_ARGS(page, type) ); +TRACE_EVENT(f2fs_writepages, + + TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type), + + TP_ARGS(inode, wbc, type), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, type) + __field(int, dir) + __field(long, nr_to_write) + __field(long, pages_skipped) + __field(loff_t, range_start) + __field(loff_t, range_end) + __field(pgoff_t, writeback_index) + __field(int, sync_mode) + __field(char, for_kupdate) + __field(char, for_background) + __field(char, tagged_writepages) + __field(char, for_reclaim) + __field(char, range_cyclic) + __field(char, for_sync) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->type = type; + __entry->dir = S_ISDIR(inode->i_mode); + __entry->nr_to_write = wbc->nr_to_write; + __entry->pages_skipped = wbc->pages_skipped; + __entry->range_start = wbc->range_start; + __entry->range_end = wbc->range_end; + __entry->writeback_index = inode->i_mapping->writeback_index; + __entry->sync_mode = wbc->sync_mode; + __entry->for_kupdate = wbc->for_kupdate; + __entry->for_background = wbc->for_background; + __entry->tagged_writepages = wbc->tagged_writepages; + __entry->for_reclaim = wbc->for_reclaim; + __entry->range_cyclic = wbc->range_cyclic; + __entry->for_sync = wbc->for_sync; + ), + + TP_printk("dev = (%d,%d), ino = %lu, %s, %s, nr_to_write %ld, " + "skipped %ld, start %lld, end %lld, wb_idx %lu, sync_mode %d, " + "kupdate %u background %u tagged %u reclaim %u cyclic %u sync %u", + show_dev_ino(__entry), + show_block_type(__entry->type), + show_file_type(__entry->dir), + __entry->nr_to_write, + __entry->pages_skipped, + __entry->range_start, + __entry->range_end, + (unsigned long)__entry->writeback_index, + __entry->sync_mode, + __entry->for_kupdate, + __entry->for_background, + __entry->tagged_writepages, + __entry->for_reclaim, + __entry->range_cyclic, + __entry->for_sync) +); + TRACE_EVENT(f2fs_submit_page_mbio, TP_PROTO(struct page *page, int rw, int type, block_t blk_addr), -- cgit v1.2.3-70-g09d2 From bac4eef6537a663585f3fb3d633a629c72e3b73d Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 27 May 2014 08:41:07 +0800 Subject: f2fs: avoid crash when trace f2fs_submit_page_mbio event in ra_sum_pages Previously we allocate pages with no mapping in ra_sum_pages(), so we may encounter a crash in event trace of f2fs_submit_page_mbio where we access mapping data of the page. We'd better allocate pages in bd_inode mapping and invalidate these pages after we restore data from pages. It could avoid crash in above scenario. Changes from V1 o remove redundant code in ra_sum_pages() suggested by Jaegeuk Kim. Call Trace: [] ? ftrace_raw_event_f2fs_write_checkpoint+0x80/0x80 [f2fs] [] f2fs_submit_page_mbio+0x1cb/0x200 [f2fs] [] restore_node_summary+0x13a/0x280 [f2fs] [] build_curseg+0x2bd/0x620 [f2fs] [] build_segment_manager+0x1cb/0x920 [f2fs] [] f2fs_fill_super+0x535/0x8e0 [f2fs] [] mount_bdev+0x16a/0x1a0 [] f2fs_mount+0x1f/0x30 [f2fs] [] mount_fs+0x36/0x170 [] vfs_kern_mount+0x55/0xe0 [] do_mount+0x1e8/0x900 [] SyS_mount+0x82/0xc0 [] sysenter_do_call+0x12/0x22 Suggested-by: Jaegeuk Kim Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 52 ++++++++++++++++++++++++---------------------------- 1 file changed, 24 insertions(+), 28 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3d60d3d34ed..02a59e9027b 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1658,35 +1658,29 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) /* * ra_sum_pages() merge contiguous pages into one bio and submit. - * these pre-readed pages are linked in pages list. + * these pre-readed pages are alloced in bd_inode's mapping tree. */ -static int ra_sum_pages(struct f2fs_sb_info *sbi, struct list_head *pages, +static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages, int start, int nrpages) { - struct page *page; - int page_idx = start; + struct inode *inode = sbi->sb->s_bdev->bd_inode; + struct address_space *mapping = inode->i_mapping; + int i, page_idx = start; struct f2fs_io_info fio = { .type = META, .rw = READ_SYNC | REQ_META | REQ_PRIO }; - for (; page_idx < start + nrpages; page_idx++) { - /* alloc temporal page for read node summary info*/ - page = alloc_page(GFP_F2FS_ZERO); - if (!page) + for (i = 0; page_idx < start + nrpages; page_idx++, i++) { + /* alloc page in bd_inode for reading node summary info */ + pages[i] = grab_cache_page(mapping, page_idx); + if (!pages[i]) break; - - lock_page(page); - page->index = page_idx; - list_add_tail(&page->lru, pages); + f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio); } - list_for_each_entry(page, pages, lru) - f2fs_submit_page_mbio(sbi, page, page->index, &fio); - f2fs_submit_merged_bio(sbi, META, READ); - - return page_idx - start; + return i; } int restore_node_summary(struct f2fs_sb_info *sbi, @@ -1694,11 +1688,11 @@ int restore_node_summary(struct f2fs_sb_info *sbi, { struct f2fs_node *rn; struct f2fs_summary *sum_entry; - struct page *page, *tmp; + struct inode *inode = sbi->sb->s_bdev->bd_inode; block_t addr; int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi)); - int i, last_offset, nrpages, err = 0; - LIST_HEAD(page_list); + struct page *pages[bio_blocks]; + int i, idx, last_offset, nrpages, err = 0; /* scan the node segment */ last_offset = sbi->blocks_per_seg; @@ -1709,29 +1703,31 @@ int restore_node_summary(struct f2fs_sb_info *sbi, nrpages = min(last_offset - i, bio_blocks); /* read ahead node pages */ - nrpages = ra_sum_pages(sbi, &page_list, addr, nrpages); + nrpages = ra_sum_pages(sbi, pages, addr, nrpages); if (!nrpages) return -ENOMEM; - list_for_each_entry_safe(page, tmp, &page_list, lru) { + for (idx = 0; idx < nrpages; idx++) { if (err) goto skip; - lock_page(page); - if (unlikely(!PageUptodate(page))) { + lock_page(pages[idx]); + if (unlikely(!PageUptodate(pages[idx]))) { err = -EIO; } else { - rn = F2FS_NODE(page); + rn = F2FS_NODE(pages[idx]); sum_entry->nid = rn->footer.nid; sum_entry->version = 0; sum_entry->ofs_in_node = 0; sum_entry++; } - unlock_page(page); + unlock_page(pages[idx]); skip: - list_del(&page->lru); - __free_pages(page, 0); + page_cache_release(pages[idx]); } + + invalidate_mapping_pages(inode->i_mapping, addr, + addr + nrpages); } return err; } -- cgit v1.2.3-70-g09d2 From b6fe5873cb422417ae3fc914954bc5a10fd4e003 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 4 Jun 2014 00:39:42 +0900 Subject: f2fs: fix to recover data written by dio If data are overwritten through dio, previous f2fs doesn't remain the fsync mark due to no additional node writes. Note that this patch should resolve the xfstests:311. Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 3 +++ fs/f2fs/f2fs.h | 1 + fs/f2fs/node.c | 12 ++++++++++++ 3 files changed, 16 insertions(+) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8c250a5d6f2..39fe7d70791 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1041,6 +1041,9 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, if (check_direct_IO(inode, rw, iov, offset, nr_segs)) return 0; + /* clear fsync mark to recover these blocks */ + fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino); + return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, get_data_block); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9684b1f77a7..f628c3c5e63 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1168,6 +1168,7 @@ struct node_info; bool available_free_memory(struct f2fs_sb_info *, int); int is_checkpointed_node(struct f2fs_sb_info *, nid_t); bool fsync_mark_done(struct f2fs_sb_info *, nid_t); +void fsync_mark_clear(struct f2fs_sb_info *, nid_t); void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); int truncate_inode_blocks(struct inode *, pgoff_t); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 02a59e9027b..a0a1f25ed20 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -153,6 +153,18 @@ bool fsync_mark_done(struct f2fs_sb_info *sbi, nid_t nid) return fsync_done; } +void fsync_mark_clear(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; + + write_lock(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (e) + e->fsync_done = false; + write_unlock(&nm_i->nat_tree_lock); +} + static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) { struct nat_entry *new; -- cgit v1.2.3-70-g09d2 From 2457aec63745e235bcafb7ef312b182d8682f0fc Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:10:31 -0700 Subject: mm: non-atomically mark page accessed during page cache allocation where possible aops->write_begin may allocate a new page and make it visible only to have mark_page_accessed called almost immediately after. Once the page is visible the atomic operations are necessary which is noticable overhead when writing to an in-memory filesystem like tmpfs but should also be noticable with fast storage. The objective of the patch is to initialse the accessed information with non-atomic operations before the page is visible. The bulk of filesystems directly or indirectly use grab_cache_page_write_begin or find_or_create_page for the initial allocation of a page cache page. This patch adds an init_page_accessed() helper which behaves like the first call to mark_page_accessed() but may called before the page is visible and can be done non-atomically. The primary APIs of concern in this care are the following and are used by most filesystems. find_get_page find_lock_page find_or_create_page grab_cache_page_nowait grab_cache_page_write_begin All of them are very similar in detail to the patch creates a core helper pagecache_get_page() which takes a flags parameter that affects its behavior such as whether the page should be marked accessed or not. Then old API is preserved but is basically a thin wrapper around this core function. Each of the filesystems are then updated to avoid calling mark_page_accessed when it is known that the VM interfaces have already done the job. There is a slight snag in that the timing of the mark_page_accessed() has now changed so in rare cases it's possible a page gets to the end of the LRU as PageReferenced where as previously it might have been repromoted. This is expected to be rare but it's worth the filesystem people thinking about it in case they see a problem with the timing change. It is also the case that some filesystems may be marking pages accessed that previously did not but it makes sense that filesystems have consistent behaviour in this regard. The test case used to evaulate this is a simple dd of a large file done multiple times with the file deleted on each iterations. The size of the file is 1/10th physical memory to avoid dirty page balancing. In the async case it will be possible that the workload completes without even hitting the disk and will have variable results but highlight the impact of mark_page_accessed for async IO. The sync results are expected to be more stable. The exception is tmpfs where the normal case is for the "IO" to not hit the disk. The test machine was single socket and UMA to avoid any scheduling or NUMA artifacts. Throughput and wall times are presented for sync IO, only wall times are shown for async as the granularity reported by dd and the variability is unsuitable for comparison. As async results were variable do to writback timings, I'm only reporting the maximum figures. The sync results were stable enough to make the mean and stddev uninteresting. The performance results are reported based on a run with no profiling. Profile data is based on a separate run with oprofile running. async dd 3.15.0-rc3 3.15.0-rc3 vanilla accessed-v2 ext3 Max elapsed 13.9900 ( 0.00%) 11.5900 ( 17.16%) tmpfs Max elapsed 0.5100 ( 0.00%) 0.4900 ( 3.92%) btrfs Max elapsed 12.8100 ( 0.00%) 12.7800 ( 0.23%) ext4 Max elapsed 18.6000 ( 0.00%) 13.3400 ( 28.28%) xfs Max elapsed 12.5600 ( 0.00%) 2.0900 ( 83.36%) The XFS figure is a bit strange as it managed to avoid a worst case by sheer luck but the average figures looked reasonable. samples percentage ext3 86107 0.9783 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext3 23833 0.2710 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext3 5036 0.0573 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed ext4 64566 0.8961 vmlinux-3.15.0-rc4-vanilla mark_page_accessed ext4 5322 0.0713 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed ext4 2869 0.0384 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 62126 1.7675 vmlinux-3.15.0-rc4-vanilla mark_page_accessed xfs 1904 0.0554 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed xfs 103 0.0030 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed btrfs 10655 0.1338 vmlinux-3.15.0-rc4-vanilla mark_page_accessed btrfs 2020 0.0273 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed btrfs 587 0.0079 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed tmpfs 59562 3.2628 vmlinux-3.15.0-rc4-vanilla mark_page_accessed tmpfs 1210 0.0696 vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed tmpfs 94 0.0054 vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed [akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer] Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Jan Kara Cc: Michal Hocko Cc: Hugh Dickins Cc: Dave Hansen Cc: Theodore Ts'o Cc: "Paul E. McKenney" Cc: Oleg Nesterov Cc: Rik van Riel Cc: Peter Zijlstra Tested-by: Prabhakar Lad Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/extent_io.c | 11 +-- fs/btrfs/file.c | 5 +- fs/buffer.c | 7 +- fs/ext4/mballoc.c | 14 ++-- fs/f2fs/checkpoint.c | 3 - fs/f2fs/node.c | 2 - fs/fuse/file.c | 2 - fs/gfs2/aops.c | 1 - fs/gfs2/meta_io.c | 4 +- fs/ntfs/attrib.c | 1 - fs/ntfs/file.c | 1 - include/linux/page-flags.h | 1 + include/linux/pagemap.h | 107 ++++++++++++++++++++++-- include/linux/swap.h | 1 + mm/filemap.c | 202 +++++++++++++++++---------------------------- mm/shmem.c | 6 +- mm/swap.c | 11 +++ 17 files changed, 217 insertions(+), 162 deletions(-) (limited to 'fs/f2fs/node.c') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f29a54e454d..4cd0ac983f9 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4510,7 +4510,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb) spin_unlock(&eb->refs_lock); } -static void mark_extent_buffer_accessed(struct extent_buffer *eb) +static void mark_extent_buffer_accessed(struct extent_buffer *eb, + struct page *accessed) { unsigned long num_pages, i; @@ -4519,7 +4520,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb) num_pages = num_extent_pages(eb->start, eb->len); for (i = 0; i < num_pages; i++) { struct page *p = extent_buffer_page(eb, i); - mark_page_accessed(p); + if (p != accessed) + mark_page_accessed(p); } } @@ -4533,7 +4535,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, start >> PAGE_CACHE_SHIFT); if (eb && atomic_inc_not_zero(&eb->refs)) { rcu_read_unlock(); - mark_extent_buffer_accessed(eb); + mark_extent_buffer_accessed(eb, NULL); return eb; } rcu_read_unlock(); @@ -4581,7 +4583,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, spin_unlock(&mapping->private_lock); unlock_page(p); page_cache_release(p); - mark_extent_buffer_accessed(exists); + mark_extent_buffer_accessed(exists, p); goto free_eb; } @@ -4596,7 +4598,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, attach_extent_buffer_page(eb, p); spin_unlock(&mapping->private_lock); WARN_ON(PageDirty(p)); - mark_page_accessed(p); eb->pages[i] = p; if (!PageUptodate(p)) uptodate = 0; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ae6af072b63..74272a3f9d9 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -470,11 +470,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) for (i = 0; i < num_pages; i++) { /* page checked is some magic around finding pages that * have been modified without going through btrfs_set_page_dirty - * clear it here + * clear it here. There should be no need to mark the pages + * accessed as prepare_pages should have marked them accessed + * in prepare_pages via find_or_create_page() */ ClearPageChecked(pages[i]); unlock_page(pages[i]); - mark_page_accessed(pages[i]); page_cache_release(pages[i]); } } diff --git a/fs/buffer.c b/fs/buffer.c index 0d3e8d5a229..eba6e4f621c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) int all_mapped = 1; index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits); - page = find_get_page(bd_mapping, index); + page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; @@ -1366,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { + /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); - } - if (bh) + } else touch_buffer(bh); + return bh; } EXPORT_SYMBOL(__find_get_block); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c8238a26818..afe8a133e3d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy page to page cache. + * The call to ext4_mb_get_buddy_page_lock will mark the + * page accessed. */ ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { @@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); if (e4b.bd_buddy_page == NULL) { /* @@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group) ret = -EIO; goto err; } - mark_page_accessed(page); err: ext4_mb_put_buddy_page_lock(&e4b); return ret; @@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, /* we could use find_or_create_page(), but it locks page * what we'd like to avoid in fast path ... */ - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) /* @@ -1176,15 +1176,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_bitmap_page = page; e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); block++; pnum = block / blocks_per_page; poff = block % blocks_per_page; - page = find_get_page(inode->i_mapping, pnum); + page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED); if (page == NULL || !PageUptodate(page)) { if (page) page_cache_release(page); @@ -1209,9 +1210,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, ret = -EIO; goto err; } + + /* Pages marked accessed already */ e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - mark_page_accessed(page); BUG_ON(e4b->bd_bitmap_page == NULL); BUG_ON(e4b->bd_buddy_page == NULL); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 4aa521aa9bc..c405b8f1705 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -69,7 +69,6 @@ repeat: goto repeat; } out: - mark_page_accessed(page); return page; } @@ -137,13 +136,11 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, int start, int nrpages, int type) if (!page) continue; if (PageUptodate(page)) { - mark_page_accessed(page); f2fs_put_page(page, 1); continue; } f2fs_submit_page_mbio(sbi, page, blk_addr, &fio); - mark_page_accessed(page); f2fs_put_page(page, 0); } out: diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index a161e955c4c..57caa6eaf47 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -967,7 +967,6 @@ repeat: goto repeat; } got_it: - mark_page_accessed(page); return page; } @@ -1022,7 +1021,6 @@ page_hit: f2fs_put_page(page, 1); return ERR_PTR(-EIO); } - mark_page_accessed(page); return page; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f680d2c44e9..903cbc9cd6b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1089,8 +1089,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); - if (!tmp) { unlock_page(page); page_cache_release(page); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 5a49b037da8..492123cda64 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -577,7 +577,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, p = kmap_atomic(page); memcpy(buf + copied, p + offset, amt); kunmap_atomic(p); - mark_page_accessed(page); page_cache_release(page); copied += amt; index++; diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 2cf09b63a6b..b984a6e190b 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -136,7 +136,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) yield(); } } else { - page = find_lock_page(mapping, index); + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); if (!page) return NULL; } @@ -153,7 +154,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) map_bh(bh, sdp->sd_vfs, blkno); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); return bh; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index a27e3fecefa..250ed5b20c8 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size) if (page) { set_page_dirty(page); unlock_page(page); - mark_page_accessed(page); page_cache_release(page); } ntfs_debug("Done."); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a3172..86ddab916b6 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d4b39ab234..2093eb72785 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,6 +198,7 @@ struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) + __SETPAGEFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c16fb6d06e3..0a97b583ee8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -259,12 +259,109 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, pgoff_t page_cache_prev_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan); +#define FGP_ACCESSED 0x00000001 +#define FGP_LOCK 0x00000002 +#define FGP_CREAT 0x00000004 +#define FGP_WRITE 0x00000008 +#define FGP_NOFS 0x00000010 +#define FGP_NOWAIT 0x00000020 + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask); + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct page *find_get_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, 0, 0, 0); +} + +static inline struct page *find_get_page_flags(struct address_space *mapping, + pgoff_t offset, int fgp_flags) +{ + return pagecache_get_page(mapping, offset, fgp_flags, 0, 0); +} + +/** + * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +static inline struct page *find_lock_page(struct address_space *mapping, + pgoff_t offset) +{ + return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0); +} + +/** + * find_or_create_page - locate or add a pagecache page + * @mapping: the page's address_space + * @index: the page's index into the mapping + * @gfp_mask: page allocation mode + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. + * + * On memory exhaustion, %NULL is returned. + * + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! + */ +static inline struct page *find_or_create_page(struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return pagecache_get_page(mapping, offset, + FGP_LOCK|FGP_ACCESSED|FGP_CREAT, + gfp_mask, gfp_mask & GFP_RECLAIM_MASK); +} + +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * + * Same as grab_cache_page(), but do not wait if the page is unavailable. + * This is intended for speculative data generators, where the data can + * be regenerated if the page couldn't be grabbed. This routine should + * be safe to call while holding the lock for another page. + * + * Clear __GFP_FS when allocating the page to avoid recursion into the fs + * and deadlock against the caller's locked page. + */ +static inline struct page *grab_cache_page_nowait(struct address_space *mapping, + pgoff_t index) +{ + return pagecache_get_page(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping), + GFP_NOFS); +} + struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_get_page(struct address_space *mapping, pgoff_t offset); struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset); -struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, - gfp_t gfp_mask); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); @@ -287,8 +384,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * grab_cache_page_nowait(struct address_space *mapping, - pgoff_t index); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, diff --git a/include/linux/swap.h b/include/linux/swap.h index 97cf16164c4..4348d95e571 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -311,6 +311,7 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); +extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); diff --git a/mm/filemap.c b/mm/filemap.c index 47d235b357a..0fcd792103f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -981,26 +981,6 @@ out: } EXPORT_SYMBOL(find_get_entry); -/** - * find_get_page - find and get a page reference - * @mapping: the address_space to search - * @offset: the page index - * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned with an increased refcount. - * - * Otherwise, %NULL is returned. - */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_get_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_get_page); - /** * find_lock_entry - locate, pin and lock a page cache entry * @mapping: the address_space to search @@ -1038,66 +1018,84 @@ repeat: EXPORT_SYMBOL(find_lock_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * pagecache_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index + * @fgp_flags: PCG flags + * @gfp_mask: gfp mask to use if a page is to be allocated * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. - * - * Otherwise, %NULL is returned. - * - * find_lock_page() may sleep. - */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) -{ - struct page *page = find_lock_entry(mapping, offset); - - if (radix_tree_exceptional_entry(page)) - page = NULL; - return page; -} -EXPORT_SYMBOL(find_lock_page); - -/** - * find_or_create_page - locate or add a pagecache page - * @mapping: the page's address_space - * @index: the page's index into the mapping - * @gfp_mask: page allocation mode + * Looks up the page cache slot at @mapping & @offset. * - * Looks up the page cache slot at @mapping & @offset. If there is a - * page cache page, it is returned locked and with an increased - * refcount. + * PCG flags modify how the page is returned * - * If the page is not present, a new page is allocated using @gfp_mask - * and added to the page cache and the VM's LRU list. The page is - * returned locked and with an increased refcount. + * FGP_ACCESSED: the page will be marked accessed + * FGP_LOCK: Page is return locked + * FGP_CREAT: If page is not present then a new page is allocated using + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * - * On memory exhaustion, %NULL is returned. + * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even + * if the GFP flags specified for FGP_CREAT are atomic. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an - * atomic allocation! + * If there is a page cache page, it is returned with an increased refcount. */ -struct page *find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask) +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, + int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask) { struct page *page; - int err; + repeat: - page = find_lock_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp_mask); + page = find_get_entry(mapping, offset); + if (radix_tree_exceptional_entry(page)) + page = NULL; + if (!page) + goto no_page; + + if (fgp_flags & FGP_LOCK) { + if (fgp_flags & FGP_NOWAIT) { + if (!trylock_page(page)) { + page_cache_release(page); + return NULL; + } + } else { + lock_page(page); + } + + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; + } + VM_BUG_ON_PAGE(page->index != offset, page); + } + + if (page && (fgp_flags & FGP_ACCESSED)) + mark_page_accessed(page); + +no_page: + if (!page && (fgp_flags & FGP_CREAT)) { + int err; + if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) + cache_gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) { + cache_gfp_mask &= ~__GFP_FS; + radix_gfp_mask &= ~__GFP_FS; + } + + page = __page_cache_alloc(cache_gfp_mask); if (!page) return NULL; - /* - * We want a regular kernel memory (not highmem or DMA etc) - * allocation for the radix tree nodes, but we need to honour - * the context-specific requirements the caller has asked for. - * GFP_RECLAIM_MASK collects those requirements. - */ - err = add_to_page_cache_lru(page, mapping, index, - (gfp_mask & GFP_RECLAIM_MASK)); + + if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + fgp_flags |= FGP_LOCK; + + /* Init accessed so avoit atomic mark_page_accessed later */ + if (fgp_flags & FGP_ACCESSED) + init_page_accessed(page); + + err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -1105,9 +1103,10 @@ repeat: goto repeat; } } + return page; } -EXPORT_SYMBOL(find_or_create_page); +EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup @@ -1404,39 +1403,6 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); -/** - * grab_cache_page_nowait - returns locked page at given index in given cache - * @mapping: target address_space - * @index: the page index - * - * Same as grab_cache_page(), but do not wait if the page is unavailable. - * This is intended for speculative data generators, where the data can - * be regenerated if the page couldn't be grabbed. This routine should - * be safe to call while holding the lock for another page. - * - * Clear __GFP_FS when allocating the page to avoid recursion into the fs - * and deadlock against the caller's locked page. - */ -struct page * -grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) -{ - struct page *page = find_get_page(mapping, index); - - if (page) { - if (trylock_page(page)) - return page; - page_cache_release(page); - return NULL; - } - page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); - if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) { - page_cache_release(page); - page = NULL; - } - return page; -} -EXPORT_SYMBOL(grab_cache_page_nowait); - /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -2406,7 +2372,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - mark_page_accessed(page); return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2488,34 +2453,18 @@ EXPORT_SYMBOL(generic_file_direct_write); 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; + int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT; - gfp_mask = mapping_gfp_mask(mapping); - if (mapping_cap_account_dirty(mapping)) - gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) - gfp_notmask = __GFP_FS; -repeat: - page = find_lock_page(mapping, index); + fgp_flags |= FGP_NOFS; + + page = pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping), + GFP_KERNEL); if (page) - goto found; + wait_for_stable_page(page); - page = __page_cache_alloc(gfp_mask & ~gfp_notmask); - if (!page) - return NULL; - status = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL & ~gfp_notmask); - if (unlikely(status)) { - page_cache_release(page); - if (status == -EEXIST) - goto repeat; - return NULL; - } -found: - wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); @@ -2564,7 +2513,7 @@ again: status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); - if (unlikely(status)) + if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) @@ -2573,7 +2522,6 @@ again: copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); - mark_page_accessed(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) diff --git a/mm/shmem.c b/mm/shmem.c index f47fb38c488..5402481c28d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1372,9 +1372,13 @@ shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int ret; struct inode *inode = mapping->host; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL); + if (ret == 0 && *pagep) + init_page_accessed(*pagep); + return ret; } static int diff --git a/mm/swap.c b/mm/swap.c index 1fb25f8bb15..9e8e3472248 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -614,6 +614,17 @@ void mark_page_accessed(struct page *page) } EXPORT_SYMBOL(mark_page_accessed); +/* + * Used to mark_page_accessed(page) that is not visible yet and when it is + * still safe to use non-atomic ops + */ +void init_page_accessed(struct page *page) +{ + if (!PageReferenced(page)) + __SetPageReferenced(page); +} +EXPORT_SYMBOL(init_page_accessed); + static void __lru_cache_add(struct page *page) { struct pagevec *pvec = &get_cpu_var(lru_add_pvec); -- cgit v1.2.3-70-g09d2 From 2743f865543c0c4a5e12fc13edb2bf89a6e9687c Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Sat, 28 Jun 2014 01:00:41 +0900 Subject: f2fs: check bdi->dirty_exceeded when trying to skip data writes If we don't check the current backing device status, balance_dirty_pages can fall into infinite pausing routine. This can be occurred when a lot of directories make a small number of dirty dentry pages including files. Reported-by: Brian Chadwick Signed-off-by: Jaegeuk Kim --- fs/f2fs/node.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/f2fs/node.c') diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9dfb9a042fd..4b697ccc9b0 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -42,6 +42,8 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12; res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); } else if (type == DIRTY_DENTS) { + if (sbi->sb->s_bdi->dirty_exceeded) + return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1); } -- cgit v1.2.3-70-g09d2