diff options
Diffstat (limited to 'fs')
113 files changed, 1330 insertions, 727 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index bb7991c7e5c7..53161ec058a7 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -451,7 +451,7 @@ void v9fs_evict_inode(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); - truncate_inode_pages(inode->i_mapping, 0); + truncate_inode_pages_final(inode->i_mapping); clear_inode(inode); filemap_fdatawrite(inode->i_mapping); diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 0e092d08680e..96df91e8c334 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -259,7 +259,7 @@ affs_evict_inode(struct inode *inode) { unsigned long cache_page; pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index ce25d755b7aa..294671288449 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -422,7 +422,7 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); afs_give_up_callback(vnode); diff --git a/fs/befs/Makefile b/fs/befs/Makefile index 2f370bd7a50d..8b9f66642a83 100644 --- a/fs/befs/Makefile +++ b/fs/befs/Makefile @@ -3,5 +3,5 @@ # obj-$(CONFIG_BEFS_FS) += befs.o - +ccflags-$(CONFIG_BEFS_DEBUG) += -DDEBUG befs-objs := datastream.o btree.o super.o inode.o debug.o io.o linuxvfs.o diff --git a/fs/befs/befs.h b/fs/befs/befs.h index b26642839156..3a7813ab8c95 100644 --- a/fs/befs/befs.h +++ b/fs/befs/befs.h @@ -88,8 +88,11 @@ enum befs_err { /****************************/ /* debug.c */ +__printf(2, 3) void befs_error(const struct super_block *sb, const char *fmt, ...); +__printf(2, 3) void befs_warning(const struct super_block *sb, const char *fmt, ...); +__printf(2, 3) void befs_debug(const struct super_block *sb, const char *fmt, ...); void befs_dump_super_block(const struct super_block *sb, befs_super_block *); diff --git a/fs/befs/btree.c b/fs/befs/btree.c index 74e397db0b8b..a2cd305a993a 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -137,7 +137,7 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds, struct buffer_head *bh = NULL; befs_disk_btree_super *od_sup = NULL; - befs_debug(sb, "---> befs_btree_read_super()"); + befs_debug(sb, "---> %s", __func__); bh = befs_read_datastream(sb, ds, 0, NULL); @@ -162,11 +162,11 @@ befs_bt_read_super(struct super_block *sb, befs_data_stream * ds, goto error; } - befs_debug(sb, "<--- befs_btree_read_super()"); + befs_debug(sb, "<--- %s", __func__); return BEFS_OK; error: - befs_debug(sb, "<--- befs_btree_read_super() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return BEFS_ERR; } @@ -195,16 +195,16 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds, { uint off = 0; - befs_debug(sb, "---> befs_bt_read_node()"); + befs_debug(sb, "---> %s", __func__); if (node->bh) brelse(node->bh); node->bh = befs_read_datastream(sb, ds, node_off, &off); if (!node->bh) { - befs_error(sb, "befs_bt_read_node() failed to read " - "node at %Lu", node_off); - befs_debug(sb, "<--- befs_bt_read_node() ERROR"); + befs_error(sb, "%s failed to read " + "node at %llu", __func__, node_off); + befs_debug(sb, "<--- %s ERROR", __func__); return BEFS_ERR; } @@ -221,7 +221,7 @@ befs_bt_read_node(struct super_block *sb, befs_data_stream * ds, node->head.all_key_length = fs16_to_cpu(sb, node->od_node->all_key_length); - befs_debug(sb, "<--- befs_btree_read_node()"); + befs_debug(sb, "<--- %s", __func__); return BEFS_OK; } @@ -252,7 +252,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds, befs_off_t node_off; int res; - befs_debug(sb, "---> befs_btree_find() Key: %s", key); + befs_debug(sb, "---> %s Key: %s", __func__, key); if (befs_bt_read_super(sb, ds, &bt_super) != BEFS_OK) { befs_error(sb, @@ -263,7 +263,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds, this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS); if (!this_node) { - befs_error(sb, "befs_btree_find() failed to allocate %u " + befs_error(sb, "befs_btree_find() failed to allocate %zu " "bytes of memory", sizeof (befs_btree_node)); goto error; } @@ -274,7 +274,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds, node_off = bt_super.root_node_ptr; if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) { befs_error(sb, "befs_btree_find() failed to read " - "node at %Lu", node_off); + "node at %llu", node_off); goto error_alloc; } @@ -285,7 +285,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds, /* if no match, go to overflow node */ if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) { befs_error(sb, "befs_btree_find() failed to read " - "node at %Lu", node_off); + "node at %llu", node_off); goto error_alloc; } } @@ -298,11 +298,11 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds, kfree(this_node); if (res != BEFS_BT_MATCH) { - befs_debug(sb, "<--- befs_btree_find() Key %s not found", key); + befs_debug(sb, "<--- %s Key %s not found", __func__, key); *value = 0; return BEFS_BT_NOT_FOUND; } - befs_debug(sb, "<--- befs_btree_find() Found key %s, value %Lu", + befs_debug(sb, "<--- %s Found key %s, value %llu", __func__, key, *value); return BEFS_OK; @@ -310,7 +310,7 @@ befs_btree_find(struct super_block *sb, befs_data_stream * ds, kfree(this_node); error: *value = 0; - befs_debug(sb, "<--- befs_btree_find() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return BEFS_ERR; } @@ -343,7 +343,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node, char *thiskey; fs64 *valarray; - befs_debug(sb, "---> befs_find_key() %s", findkey); + befs_debug(sb, "---> %s %s", __func__, findkey); *value = 0; @@ -355,7 +355,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node, eq = befs_compare_strings(thiskey, keylen, findkey, findkey_len); if (eq < 0) { - befs_debug(sb, "<--- befs_find_key() %s not found", findkey); + befs_debug(sb, "<--- %s %s not found", __func__, findkey); return BEFS_BT_NOT_FOUND; } @@ -373,8 +373,8 @@ befs_find_key(struct super_block *sb, befs_btree_node * node, findkey_len); if (eq == 0) { - befs_debug(sb, "<--- befs_find_key() found %s at %d", - thiskey, mid); + befs_debug(sb, "<--- %s found %s at %d", + __func__, thiskey, mid); *value = fs64_to_cpu(sb, valarray[mid]); return BEFS_BT_MATCH; @@ -388,7 +388,7 @@ befs_find_key(struct super_block *sb, befs_btree_node * node, *value = fs64_to_cpu(sb, valarray[mid + 1]); else *value = fs64_to_cpu(sb, valarray[mid]); - befs_debug(sb, "<--- befs_find_key() found %s at %d", thiskey, mid); + befs_debug(sb, "<--- %s found %s at %d", __func__, thiskey, mid); return BEFS_BT_PARMATCH; } @@ -428,7 +428,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, uint key_sum = 0; - befs_debug(sb, "---> befs_btree_read()"); + befs_debug(sb, "---> %s", __func__); if (befs_bt_read_super(sb, ds, &bt_super) != BEFS_OK) { befs_error(sb, @@ -437,7 +437,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, } if ((this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) { - befs_error(sb, "befs_btree_read() failed to allocate %u " + befs_error(sb, "befs_btree_read() failed to allocate %zu " "bytes of memory", sizeof (befs_btree_node)); goto error; } @@ -452,7 +452,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, kfree(this_node); *value = 0; *keysize = 0; - befs_debug(sb, "<--- befs_btree_read() Tree is EMPTY"); + befs_debug(sb, "<--- %s Tree is EMPTY", __func__); return BEFS_BT_EMPTY; } else if (res == BEFS_ERR) { goto error_alloc; @@ -467,7 +467,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, *keysize = 0; *value = 0; befs_debug(sb, - "<--- befs_btree_read() END of keys at %Lu", + "<--- %s END of keys at %llu", __func__, + (unsigned long long) key_sum + this_node->head.all_key_count); brelse(this_node->bh); kfree(this_node); @@ -478,8 +479,8 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, node_off = this_node->head.right; if (befs_bt_read_node(sb, ds, this_node, node_off) != BEFS_OK) { - befs_error(sb, "befs_btree_read() failed to read " - "node at %Lu", node_off); + befs_error(sb, "%s failed to read node at %llu", + __func__, (unsigned long long)node_off); goto error_alloc; } } @@ -492,11 +493,13 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, keystart = befs_bt_get_key(sb, this_node, cur_key, &keylen); - befs_debug(sb, "Read [%Lu,%d]: keysize %d", node_off, cur_key, keylen); + befs_debug(sb, "Read [%llu,%d]: keysize %d", + (long long unsigned int)node_off, (int)cur_key, + (int)keylen); if (bufsize < keylen + 1) { - befs_error(sb, "befs_btree_read() keybuf too small (%u) " - "for key of size %d", bufsize, keylen); + befs_error(sb, "%s keybuf too small (%zu) " + "for key of size %d", __func__, bufsize, keylen); brelse(this_node->bh); goto error_alloc; }; @@ -506,13 +509,13 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, *keysize = keylen; keybuf[keylen] = '\0'; - befs_debug(sb, "Read [%Lu,%d]: Key \"%.*s\", Value %Lu", node_off, + befs_debug(sb, "Read [%llu,%d]: Key \"%.*s\", Value %llu", node_off, cur_key, keylen, keybuf, *value); brelse(this_node->bh); kfree(this_node); - befs_debug(sb, "<--- befs_btree_read()"); + befs_debug(sb, "<--- %s", __func__); return BEFS_OK; @@ -522,7 +525,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds, error: *keysize = 0; *value = 0; - befs_debug(sb, "<--- befs_btree_read() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return BEFS_ERR; } @@ -547,26 +550,26 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds, befs_off_t * node_off) { - befs_debug(sb, "---> befs_btree_seekleaf()"); + befs_debug(sb, "---> %s", __func__); if (befs_bt_read_node(sb, ds, this_node, *node_off) != BEFS_OK) { - befs_error(sb, "befs_btree_seekleaf() failed to read " - "node at %Lu", *node_off); + befs_error(sb, "%s failed to read " + "node at %llu", __func__, *node_off); goto error; } - befs_debug(sb, "Seekleaf to root node %Lu", *node_off); + befs_debug(sb, "Seekleaf to root node %llu", *node_off); if (this_node->head.all_key_count == 0 && befs_leafnode(this_node)) { - befs_debug(sb, "<--- befs_btree_seekleaf() Tree is EMPTY"); + befs_debug(sb, "<--- %s Tree is EMPTY", __func__); return BEFS_BT_EMPTY; } while (!befs_leafnode(this_node)) { if (this_node->head.all_key_count == 0) { - befs_debug(sb, "befs_btree_seekleaf() encountered " - "an empty interior node: %Lu. Using Overflow " - "node: %Lu", *node_off, + befs_debug(sb, "%s encountered " + "an empty interior node: %llu. Using Overflow " + "node: %llu", __func__, *node_off, this_node->head.overflow); *node_off = this_node->head.overflow; } else { @@ -574,19 +577,19 @@ befs_btree_seekleaf(struct super_block *sb, befs_data_stream * ds, *node_off = fs64_to_cpu(sb, valarray[0]); } if (befs_bt_read_node(sb, ds, this_node, *node_off) != BEFS_OK) { - befs_error(sb, "befs_btree_seekleaf() failed to read " - "node at %Lu", *node_off); + befs_error(sb, "%s failed to read " + "node at %llu", __func__, *node_off); goto error; } - befs_debug(sb, "Seekleaf to child node %Lu", *node_off); + befs_debug(sb, "Seekleaf to child node %llu", *node_off); } - befs_debug(sb, "Node %Lu is a leaf node", *node_off); + befs_debug(sb, "Node %llu is a leaf node", *node_off); return BEFS_OK; error: - befs_debug(sb, "<--- befs_btree_seekleaf() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return BEFS_ERR; } diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c index 59096b5e0fc7..c467bebd50af 100644 --- a/fs/befs/datastream.c +++ b/fs/befs/datastream.c @@ -52,26 +52,25 @@ befs_read_datastream(struct super_block *sb, befs_data_stream * ds, befs_block_run run; befs_blocknr_t block; /* block coresponding to pos */ - befs_debug(sb, "---> befs_read_datastream() %Lu", pos); + befs_debug(sb, "---> %s %llu", __func__, pos); block = pos >> BEFS_SB(sb)->block_shift; if (off) *off = pos - (block << BEFS_SB(sb)->block_shift); if (befs_fblock2brun(sb, ds, block, &run) != BEFS_OK) { befs_error(sb, "BeFS: Error finding disk addr of block %lu", - block); - befs_debug(sb, "<--- befs_read_datastream() ERROR"); + (unsigned long)block); + befs_debug(sb, "<--- %s ERROR", __func__); return NULL; } bh = befs_bread_iaddr(sb, run); if (!bh) { befs_error(sb, "BeFS: Error reading block %lu from datastream", - block); + (unsigned long)block); return NULL; } - befs_debug(sb, "<--- befs_read_datastream() read data, starting at %Lu", - pos); + befs_debug(sb, "<--- %s read data, starting at %llu", __func__, pos); return bh; } @@ -106,7 +105,8 @@ befs_fblock2brun(struct super_block *sb, befs_data_stream * data, } else { befs_error(sb, "befs_fblock2brun() was asked to find block %lu, " - "which is not mapped by the datastream\n", fblock); + "which is not mapped by the datastream\n", + (unsigned long)fblock); err = BEFS_ERR; } return err; @@ -128,14 +128,14 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff, befs_off_t bytes_read = 0; /* bytes readed */ u16 plen; struct buffer_head *bh = NULL; - befs_debug(sb, "---> befs_read_lsymlink() length: %Lu", len); + befs_debug(sb, "---> %s length: %llu", __func__, len); while (bytes_read < len) { bh = befs_read_datastream(sb, ds, bytes_read, NULL); if (!bh) { befs_error(sb, "BeFS: Error reading datastream block " - "starting from %Lu", bytes_read); - befs_debug(sb, "<--- befs_read_lsymlink() ERROR"); + "starting from %llu", bytes_read); + befs_debug(sb, "<--- %s ERROR", __func__); return bytes_read; } @@ -146,7 +146,8 @@ befs_read_lsymlink(struct super_block * sb, befs_data_stream * ds, void *buff, bytes_read += plen; } - befs_debug(sb, "<--- befs_read_lsymlink() read %u bytes", bytes_read); + befs_debug(sb, "<--- %s read %u bytes", __func__, (unsigned int) + bytes_read); return bytes_read; } @@ -169,7 +170,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds) befs_blocknr_t metablocks; /* FS metadata blocks */ befs_sb_info *befs_sb = BEFS_SB(sb); - befs_debug(sb, "---> befs_count_blocks()"); + befs_debug(sb, "---> %s", __func__); datablocks = ds->size >> befs_sb->block_shift; if (ds->size & (befs_sb->block_size - 1)) @@ -206,7 +207,7 @@ befs_count_blocks(struct super_block * sb, befs_data_stream * ds) } blocks = datablocks + metablocks; - befs_debug(sb, "<--- befs_count_blocks() %u blocks", blocks); + befs_debug(sb, "<--- %s %u blocks", __func__, (unsigned int)blocks); return blocks; } @@ -251,11 +252,11 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data, befs_blocknr_t max_block = data->max_direct_range >> BEFS_SB(sb)->block_shift; - befs_debug(sb, "---> befs_find_brun_direct(), find %lu", blockno); + befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno); if (blockno > max_block) { - befs_error(sb, "befs_find_brun_direct() passed block outside of" - "direct region"); + befs_error(sb, "%s passed block outside of direct region", + __func__); return BEFS_ERR; } @@ -267,13 +268,14 @@ befs_find_brun_direct(struct super_block *sb, befs_data_stream * data, run->start = array[i].start + offset; run->len = array[i].len - offset; - befs_debug(sb, "---> befs_find_brun_direct(), " - "found %lu at direct[%d]", blockno, i); + befs_debug(sb, "---> %s, " + "found %lu at direct[%d]", __func__, + (unsigned long)blockno, i); return BEFS_OK; } } - befs_debug(sb, "---> befs_find_brun_direct() ERROR"); + befs_debug(sb, "---> %s ERROR", __func__); return BEFS_ERR; } @@ -316,7 +318,7 @@ befs_find_brun_indirect(struct super_block *sb, befs_blocknr_t indirblockno = iaddr2blockno(sb, &indirect); int arraylen = befs_iaddrs_per_block(sb); - befs_debug(sb, "---> befs_find_brun_indirect(), find %lu", blockno); + befs_debug(sb, "---> %s, find %lu", __func__, (unsigned long)blockno); indir_start_blk = data->max_direct_range >> BEFS_SB(sb)->block_shift; search_blk = blockno - indir_start_blk; @@ -325,10 +327,9 @@ befs_find_brun_indirect(struct super_block *sb, for (i = 0; i < indirect.len; i++) { indirblock = befs_bread(sb, indirblockno + i); if (indirblock == NULL) { - befs_debug(sb, - "---> befs_find_brun_indirect() failed to " - "read disk block %lu from the indirect brun", - indirblockno + i); + befs_debug(sb, "---> %s failed to read " + "disk block %lu from the indirect brun", + __func__, (unsigned long)indirblockno + i); return BEFS_ERR; } @@ -348,9 +349,10 @@ befs_find_brun_indirect(struct super_block *sb, brelse(indirblock); befs_debug(sb, - "<--- befs_find_brun_indirect() found " - "file block %lu at indirect[%d]", - blockno, j + (i * arraylen)); + "<--- %s found file block " + "%lu at indirect[%d]", __func__, + (unsigned long)blockno, + j + (i * arraylen)); return BEFS_OK; } sum += len; @@ -360,10 +362,10 @@ befs_find_brun_indirect(struct super_block *sb, } /* Only fallthrough is an error */ - befs_error(sb, "BeFS: befs_find_brun_indirect() failed to find " - "file block %lu", blockno); + befs_error(sb, "BeFS: %s failed to find " + "file block %lu", __func__, (unsigned long)blockno); - befs_debug(sb, "<--- befs_find_brun_indirect() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return BEFS_ERR; } @@ -444,7 +446,7 @@ befs_find_brun_dblindirect(struct super_block *sb, size_t diblklen = iblklen * befs_iaddrs_per_block(sb) * BEFS_DBLINDIR_BRUN_LEN; - befs_debug(sb, "---> befs_find_brun_dblindirect() find %lu", blockno); + befs_debug(sb, "---> %s find %lu", __func__, (unsigned long)blockno); /* First, discover which of the double_indir->indir blocks * contains pos. Then figure out how much of pos that @@ -460,8 +462,9 @@ befs_find_brun_dblindirect(struct super_block *sb, dbl_which_block = dblindir_indx / befs_iaddrs_per_block(sb); if (dbl_which_block > data->double_indirect.len) { befs_error(sb, "The double-indirect index calculated by " - "befs_read_brun_dblindirect(), %d, is outside the range " - "of the double-indirect block", dblindir_indx); + "%s, %d, is outside the range " + "of the double-indirect block", __func__, + dblindir_indx); return BEFS_ERR; } @@ -469,10 +472,10 @@ befs_find_brun_dblindirect(struct super_block *sb, befs_bread(sb, iaddr2blockno(sb, &data->double_indirect) + dbl_which_block); if (dbl_indir_block == NULL) { - befs_error(sb, "befs_read_brun_dblindirect() couldn't read the " - "double-indirect block at blockno %lu", - iaddr2blockno(sb, - &data->double_indirect) + + befs_error(sb, "%s couldn't read the " + "double-indirect block at blockno %lu", __func__, + (unsigned long) + iaddr2blockno(sb, &data->double_indirect) + dbl_which_block); brelse(dbl_indir_block); return BEFS_ERR; @@ -489,16 +492,16 @@ befs_find_brun_dblindirect(struct super_block *sb, which_block = indir_indx / befs_iaddrs_per_block(sb); if (which_block > indir_run.len) { befs_error(sb, "The indirect index calculated by " - "befs_read_brun_dblindirect(), %d, is outside the range " - "of the indirect block", indir_indx); + "%s, %d, is outside the range " + "of the indirect block", __func__, indir_indx); return BEFS_ERR; } indir_block = befs_bread(sb, iaddr2blockno(sb, &indir_run) + which_block); if (indir_block == NULL) { - befs_error(sb, "befs_read_brun_dblindirect() couldn't read the " - "indirect block at blockno %lu", + befs_error(sb, "%s couldn't read the indirect block " + "at blockno %lu", __func__, (unsigned long) iaddr2blockno(sb, &indir_run) + which_block); brelse(indir_block); return BEFS_ERR; @@ -519,7 +522,7 @@ befs_find_brun_dblindirect(struct super_block *sb, run->len -= offset; befs_debug(sb, "Found file block %lu in double_indirect[%d][%d]," - " double_indirect_leftover = %lu", + " double_indirect_leftover = %lu", (unsigned long) blockno, dblindir_indx, indir_indx, dblindir_leftover); return BEFS_OK; diff --git a/fs/befs/debug.c b/fs/befs/debug.c index 622e73775c83..4de7cffcd662 100644 --- a/fs/befs/debug.c +++ b/fs/befs/debug.c @@ -10,6 +10,7 @@ * debug functions */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #ifdef __KERNEL__ #include <stdarg.h> @@ -23,43 +24,30 @@ #include "befs.h" -#define ERRBUFSIZE 1024 - void befs_error(const struct super_block *sb, const char *fmt, ...) { + struct va_format vaf; va_list args; - char *err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL); - if (err_buf == NULL) { - printk(KERN_ERR "could not allocate %d bytes\n", ERRBUFSIZE); - return; - } va_start(args, fmt); - vsnprintf(err_buf, ERRBUFSIZE, fmt, args); + vaf.fmt = fmt; + vaf.va = &args; + pr_err("(%s): %pV\n", sb->s_id, &vaf); va_end(args); - - printk(KERN_ERR "BeFS(%s): %s\n", sb->s_id, err_buf); - kfree(err_buf); } void befs_warning(const struct super_block *sb, const char *fmt, ...) { + struct va_format vaf; va_list args; - char *err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL); - if (err_buf == NULL) { - printk(KERN_ERR "could not allocate %d bytes\n", ERRBUFSIZE); - return; - } va_start(args, fmt); - vsnprintf(err_buf, ERRBUFSIZE, fmt, args); + vaf.fmt = fmt; + vaf.va = &args; + pr_warn("(%s): %pV\n", sb->s_id, &vaf); va_end(args); - - printk(KERN_WARNING "BeFS(%s): %s\n", sb->s_id, err_buf); - - kfree(err_buf); } void @@ -67,25 +55,13 @@ befs_debug(const struct super_block *sb, const char *fmt, ...) { #ifdef CONFIG_BEFS_DEBUG + struct va_format vaf; va_list args; - char *err_buf = NULL; - - if (BEFS_SB(sb)->mount_opts.debug) { - err_buf = kmalloc(ERRBUFSIZE, GFP_KERNEL); - if (err_buf == NULL) { - printk(KERN_ERR "could not allocate %d bytes\n", - ERRBUFSIZE); - return; - } - - va_start(args, fmt); - vsnprintf(err_buf, ERRBUFSIZE, fmt, args); - va_end(args); - - printk(KERN_DEBUG "BeFS(%s): %s\n", sb->s_id, err_buf); - - kfree(err_buf); - } + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + pr_debug("(%s): %pV\n", sb->s_id, &vaf); + va_end(args); #endif //CONFIG_BEFS_DEBUG } @@ -109,9 +85,9 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode) befs_debug(sb, " gid %u", fs32_to_cpu(sb, inode->gid)); befs_debug(sb, " mode %08x", fs32_to_cpu(sb, inode->mode)); befs_debug(sb, " flags %08x", fs32_to_cpu(sb, inode->flags)); - befs_debug(sb, " create_time %Lu", + befs_debug(sb, " create_time %llu", fs64_to_cpu(sb, inode->create_time)); - befs_debug(sb, " last_modified_time %Lu", + befs_debug(sb, " last_modified_time %llu", fs64_to_cpu(sb, inode->last_modified_time)); tmp_run = fsrun_to_cpu(sb, inode->parent); @@ -137,7 +113,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode) tmp_run.allocation_group, tmp_run.start, tmp_run.len); } - befs_debug(sb, " max_direct_range %Lu", + befs_debug(sb, " max_direct_range %llu", fs64_to_cpu(sb, inode->data.datastream. max_direct_range)); @@ -147,7 +123,7 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode) tmp_run.allocation_group, tmp_run.start, tmp_run.len); - befs_debug(sb, " max_indirect_range %Lu", + befs_debug(sb, " max_indirect_range %llu", fs64_to_cpu(sb, inode->data.datastream. max_indirect_range)); @@ -158,12 +134,12 @@ befs_dump_inode(const struct super_block *sb, befs_inode * inode) tmp_run.allocation_group, tmp_run.start, tmp_run.len); - befs_debug(sb, " max_double_indirect_range %Lu", + befs_debug(sb, " max_double_indirect_range %llu", fs64_to_cpu(sb, inode->data.datastream. max_double_indirect_range)); - befs_debug(sb, " size %Lu", + befs_debug(sb, " size %llu", fs64_to_cpu(sb, inode->data.datastream.size)); } @@ -191,8 +167,8 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup) befs_debug(sb, " block_size %u", fs32_to_cpu(sb, sup->block_size)); befs_debug(sb, " block_shift %u", fs32_to_cpu(sb, sup->block_shift)); - befs_debug(sb, " num_blocks %Lu", fs64_to_cpu(sb, sup->num_blocks)); - befs_debug(sb, " used_blocks %Lu", fs64_to_cpu(sb, sup->used_blocks)); + befs_debug(sb, " num_blocks %llu", fs64_to_cpu(sb, sup->num_blocks)); + befs_debug(sb, " used_blocks %llu", fs64_to_cpu(sb, sup->used_blocks)); befs_debug(sb, " magic2 %08x", fs32_to_cpu(sb, sup->magic2)); befs_debug(sb, " blocks_per_ag %u", @@ -206,8 +182,8 @@ befs_dump_super_block(const struct super_block *sb, befs_super_block * sup) befs_debug(sb, " log_blocks %u, %hu, %hu", tmp_run.allocation_group, tmp_run.start, tmp_run.len); - befs_debug(sb, " log_start %Ld", fs64_to_cpu(sb, sup->log_start)); - befs_debug(sb, " log_end %Ld", fs64_to_cpu(sb, sup->log_end)); + befs_debug(sb, " log_start %lld", fs64_to_cpu(sb, sup->log_start)); + befs_debug(sb, " log_end %lld", fs64_to_cpu(sb, sup->log_end)); befs_debug(sb, " magic3 %08x", fs32_to_cpu(sb, sup->magic3)); diff --git a/fs/befs/inode.c b/fs/befs/inode.c index 94c17f9a9576..fa4b718de597 100644 --- a/fs/befs/inode.c +++ b/fs/befs/inode.c @@ -25,7 +25,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode, /* check magic header. */ if (magic1 != BEFS_INODE_MAGIC1) { befs_error(sb, - "Inode has a bad magic header - inode = %lu", inode); + "Inode has a bad magic header - inode = %lu", + (unsigned long)inode); return BEFS_BAD_INODE; } @@ -34,8 +35,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode, */ if (inode != iaddr2blockno(sb, &ino_num)) { befs_error(sb, "inode blocknr field disagrees with vfs " - "VFS: %lu, Inode %lu", - inode, iaddr2blockno(sb, &ino_num)); + "VFS: %lu, Inode %lu", (unsigned long) + inode, (unsigned long)iaddr2blockno(sb, &ino_num)); return BEFS_BAD_INODE; } @@ -44,7 +45,8 @@ befs_check_inode(struct super_block *sb, befs_inode * raw_inode, */ if (!(flags & BEFS_INODE_IN_USE)) { - befs_error(sb, "inode is not used - inode = %lu", inode); + befs_error(sb, "inode is not used - inode = %lu", + (unsigned long)inode); return BEFS_BAD_INODE; } diff --git a/fs/befs/io.c b/fs/befs/io.c index ddef98aa255d..0408a3d601d0 100644 --- a/fs/befs/io.c +++ b/fs/befs/io.c @@ -30,9 +30,9 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr) befs_blocknr_t block = 0; befs_sb_info *befs_sb = BEFS_SB(sb); - befs_debug(sb, "---> Enter befs_read_iaddr() " - "[%u, %hu, %hu]", - iaddr.allocation_group, iaddr.start, iaddr.len); + befs_debug(sb, "---> Enter %s " + "[%u, %hu, %hu]", __func__, iaddr.allocation_group, + iaddr.start, iaddr.len); if (iaddr.allocation_group > befs_sb->num_ags) { befs_error(sb, "BEFS: Invalid allocation group %u, max is %u", @@ -42,20 +42,21 @@ befs_bread_iaddr(struct super_block *sb, befs_inode_addr iaddr) block = iaddr2blockno(sb, &iaddr); - befs_debug(sb, "befs_read_iaddr: offset = %lu", block); + befs_debug(sb, "%s: offset = %lu", __func__, (unsigned long)block); bh = sb_bread(sb, block); if (bh == NULL) { - befs_error(sb, "Failed to read block %lu", block); + befs_error(sb, "Failed to read block %lu", + (unsigned long)block); goto error; } - befs_debug(sb, "<--- befs_read_iaddr()"); + befs_debug(sb, "<--- %s", __func__); return bh; error: - befs_debug(sb, "<--- befs_read_iaddr() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return NULL; } @@ -64,20 +65,21 @@ befs_bread(struct super_block *sb, befs_blocknr_t block) { struct buffer_head *bh = NULL; - befs_debug(sb, "---> Enter befs_read() %Lu", block); + befs_debug(sb, "---> Enter %s %lu", __func__, (unsigned long)block); bh = sb_bread(sb, block); if (bh == NULL) { - befs_error(sb, "Failed to read block %lu", block); + befs_error(sb, "Failed to read block %lu", + (unsigned long)block); goto error; } - befs_debug(sb, "<--- befs_read()"); + befs_debug(sb, "<--- %s", __func__); return bh; error: - befs_debug(sb, "<--- befs_read() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return NULL; } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 845d2d690ce2..5188f1222987 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -5,6 +5,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/fs.h> @@ -39,7 +41,6 @@ static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int) static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_destroy_inode(struct inode *inode); -static int befs_init_inodecache(void); static void befs_destroy_inodecache(void); static void *befs_follow_link(struct dentry *, struct nameidata *); static void *befs_fast_follow_link(struct dentry *, struct nameidata *); @@ -131,26 +132,28 @@ befs_get_block(struct inode *inode, sector_t block, ulong disk_off; befs_debug(sb, "---> befs_get_block() for inode %lu, block %ld", - inode->i_ino, block); + (unsigned long)inode->i_ino, (long)block); if (block < 0) { befs_error(sb, "befs_get_block() was asked for a block " "number less than zero: block %ld in inode %lu", - block, inode->i_ino); + (long)block, (unsigned long)inode->i_ino); return -EIO; } if (create) { befs_error(sb, "befs_get_block() was asked to write to " - "block %ld in inode %lu", block, inode->i_ino); + "block %ld in inode %lu", (long)block, + (unsigned long)inode->i_ino); return -EPERM; } res = befs_fblock2brun(sb, ds, block, &run); if (res != BEFS_OK) { befs_error(sb, - "<--- befs_get_block() for inode %lu, block " - "%ld ERROR", inode->i_ino, block); + "<--- %s for inode %lu, block %ld ERROR", + __func__, (unsigned long)inode->i_ino, + (long)block); return -EFBIG; } @@ -158,8 +161,9 @@ befs_get_block(struct inode *inode, sector_t block, map_bh(bh_result, inode->i_sb, disk_off); - befs_debug(sb, "<--- befs_get_block() for inode %lu, block %ld, " - "disk address %lu", inode->i_ino, block, disk_off); + befs_debug(sb, "<--- %s for inode %lu, block %ld, disk address %lu", + __func__, (unsigned long)inode->i_ino, (long)block, + (unsigned long)disk_off); return 0; } @@ -176,15 +180,15 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) char *utfname; const char *name = dentry->d_name.name; - befs_debug(sb, "---> befs_lookup() " - "name %s inode %ld", dentry->d_name.name, dir->i_ino); + befs_debug(sb, "---> %s name %s inode %ld", __func__, + dentry->d_name.name, dir->i_ino); /* Convert to UTF-8 */ if (BEFS_SB(sb)->nls) { ret = befs_nls2utf(sb, name, strlen(name), &utfname, &utfnamelen); if (ret < 0) { - befs_debug(sb, "<--- befs_lookup() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return ERR_PTR(ret); } ret = befs_btree_find(sb, ds, utfname, &offset); @@ -195,12 +199,12 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) } if (ret == BEFS_BT_NOT_FOUND) { - befs_debug(sb, "<--- befs_lookup() %s not found", + befs_debug(sb, "<--- %s %s not found", __func__, dentry->d_name.name); return ERR_PTR(-ENOENT); } else if (ret != BEFS_OK || offset == 0) { - befs_warning(sb, "<--- befs_lookup() Error"); + befs_warning(sb, "<--- %s Error", __func__); return ERR_PTR(-ENODATA); } @@ -210,7 +214,7 @@ befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) d_add(dentry, inode); - befs_debug(sb, "<--- befs_lookup()"); + befs_debug(sb, "<--- %s", __func__); return NULL; } @@ -228,26 +232,25 @@ befs_readdir(struct file *file, struct dir_context *ctx) char keybuf[BEFS_NAME_LEN + 1]; const char *dirname = file->f_path.dentry->d_name.name; - befs_debug(sb, "---> befs_readdir() " - "name %s, inode %ld, ctx->pos %Ld", - dirname, inode->i_ino, ctx->pos); + befs_debug(sb, "---> %s name %s, inode %ld, ctx->pos %lld", + __func__, dirname, inode->i_ino, ctx->pos); more: result = befs_btree_read(sb, ds, ctx->pos, BEFS_NAME_LEN + 1, keybuf, &keysize, &value); if (result == BEFS_ERR) { - befs_debug(sb, "<--- befs_readdir() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); befs_error(sb, "IO error reading %s (inode %lu)", dirname, inode->i_ino); return -EIO; } else if (result == BEFS_BT_END) { - befs_debug(sb, "<--- befs_readdir() END"); + befs_debug(sb, "<--- %s END", __func__); return 0; } else if (result == BEFS_BT_EMPTY) { - befs_debug(sb, "<--- befs_readdir() Empty directory"); + befs_debug(sb, "<--- %s Empty directory", __func__); return 0; } @@ -260,7 +263,7 @@ more: result = befs_utf2nls(sb, keybuf, keysize, &nlsname, &nlsnamelen); if (result < 0) { - befs_debug(sb, "<--- befs_readdir() ERROR"); + befs_debug(sb, "<--- %s ERROR", __func__); return result; } if (!dir_emit(ctx, nlsname, nlsnamelen, @@ -277,7 +280,7 @@ more: ctx->pos++; goto more; - befs_debug(sb, "<--- befs_readdir() pos %Ld", ctx->pos); + befs_debug(sb, "<--- %s pos %lld", __func__, ctx->pos); return 0; } @@ -321,7 +324,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) struct inode *inode; long ret = -EIO; - befs_debug(sb, "---> befs_read_inode() " "inode = %lu", ino); + befs_debug(sb, "---> %s inode = %lu", __func__, ino); inode = iget_locked(sb, ino); if (!inode) @@ -428,7 +431,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) } brelse(bh); - befs_debug(sb, "<--- befs_read_inode()"); + befs_debug(sb, "<--- %s", __func__); unlock_new_inode(inode); return inode; @@ -437,7 +440,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) unacquire_none: iget_failed(inode); - befs_debug(sb, "<--- befs_read_inode() - Bad inode"); + befs_debug(sb, "<--- %s - Bad inode", __func__); return ERR_PTR(ret); } @@ -445,7 +448,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) * * Taken from NFS implementation by Al Viro. */ -static int +static int __init befs_init_inodecache(void) { befs_inode_cachep = kmem_cache_create("befs_inode_cache", @@ -454,11 +457,9 @@ befs_init_inodecache(void) SLAB_MEM_SPREAD), init_once); if (befs_inode_cachep == NULL) { - printk(KERN_ERR "befs_init_inodecache: " - "Couldn't initialize inode slabcache\n"); + pr_err("%s: Couldn't initialize inode slabcache\n", __func__); return -ENOMEM; } - return 0; } @@ -544,16 +545,16 @@ befs_utf2nls(struct super_block *sb, const char *in, */ int maxlen = in_len + 1; - befs_debug(sb, "---> utf2nls()"); + befs_debug(sb, "---> %s", __func__); if (!nls) { - befs_error(sb, "befs_utf2nls called with no NLS table loaded"); + befs_error(sb, "%s called with no NLS table loaded", __func__); return -EINVAL; } *out = result = kmalloc(maxlen, GFP_NOFS); if (!*out) { - befs_error(sb, "befs_utf2nls() cannot allocate memory"); + befs_error(sb, "%s cannot allocate memory", __func__); *out_len = 0; return -ENOMEM; } @@ -575,14 +576,14 @@ befs_utf2nls(struct super_block *sb, const char *in, result[o] = '\0'; *out_len = o; - befs_debug(sb, "<--- utf2nls()"); + befs_debug(sb, "<--- %s", __func__); return o; conv_err: befs_error(sb, "Name using character set %s contains a character that " "cannot be converted to unicode.", nls->charset); - befs_debug(sb, "<--- utf2nls()"); + befs_debug(sb, "<--- %s", __func__); kfree(result); return -EILSEQ; } @@ -623,16 +624,17 @@ befs_nls2utf(struct super_block *sb, const char *in, * in special cases */ int maxlen = (3 * in_len) + 1; - befs_debug(sb, "---> nls2utf()\n"); + befs_debug(sb, "---> %s\n", __func__); if (!nls) { - befs_error(sb, "befs_nls2utf called with no NLS table loaded."); + befs_error(sb, "%s called with no NLS table loaded.", + __func__); return -EINVAL; } *out = result = kmalloc(maxlen, GFP_NOFS); if (!*out) { - befs_error(sb, "befs_nls2utf() cannot allocate memory"); + befs_error(sb, "%s cannot allocate memory", __func__); *out_len = 0; return -ENOMEM; } @@ -653,14 +655,14 @@ befs_nls2utf(struct super_block *sb, const char *in, result[o] = '\0'; *out_len = o; - befs_debug(sb, "<--- nls2utf()"); + befs_debug(sb, "<--- %s", __func__); return i; conv_err: befs_error(sb, "Name using charecter set %s contains a charecter that " "cannot be converted to unicode.", nls->charset); - befs_debug(sb, "<--- nls2utf()"); + befs_debug(sb, "<--- %s", __func__); kfree(result); return -EILSEQ; } @@ -715,8 +717,8 @@ parse_options(char *options, befs_mount_options * opts) if (option >= 0) uid = make_kuid(current_user_ns(), option); if (!uid_valid(uid)) { - printk(KERN_ERR "BeFS: Invalid uid %d, " - "using default\n", option); + pr_err("Invalid uid %d, " + "using default\n", option); break; } opts->uid = uid; @@ -729,8 +731,8 @@ parse_options(char *options, befs_mount_options * opts) if (option >= 0) gid = make_kgid(current_user_ns(), option); if (!gid_valid(gid)) { - printk(KERN_ERR "BeFS: Invalid gid %d, " - "using default\n", option); + pr_err("Invalid gid %d, " + "using default\n", option); break; } opts->gid = gid; @@ -740,8 +742,8 @@ parse_options(char *options, befs_mount_options * opts) kfree(opts->iocharset); opts->iocharset = match_strdup(&args[0]); if (!opts->iocharset) { - printk(KERN_ERR "BeFS: allocation failure for " - "iocharset string\n"); + pr_err("allocation failure for " + "iocharset string\n"); return 0; } break; @@ -749,8 +751,8 @@ parse_options(char *options, befs_mount_options * opts) opts->debug = 1; break; default: - printk(KERN_ERR "BeFS: Unrecognized mount option \"%s\" " - "or missing value\n", p); + pr_err("Unrecognized mount option \"%s\" " + "or missing value\n", p); return 0; } } @@ -791,22 +793,20 @@ befs_fill_super(struct super_block *sb, void *data, int silent) save_mount_options(sb, data); - sb->s_fs_info = kmalloc(sizeof (*befs_sb), GFP_KERNEL); + sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL); if (sb->s_fs_info == NULL) { - printk(KERN_ERR - "BeFS(%s): Unable to allocate memory for private " + pr_err("(%s): Unable to allocate memory for private " "portion of superblock. Bailing.\n", sb->s_id); goto unacquire_none; } befs_sb = BEFS_SB(sb); - memset(befs_sb, 0, sizeof(befs_sb_info)); if (!parse_options((char *) data, &befs_sb->mount_opts)) { befs_error(sb, "cannot parse mount options"); goto unacquire_priv_sbp; } - befs_debug(sb, "---> befs_fill_super()"); + befs_debug(sb, "---> %s", __func__); #ifndef CONFIG_BEFS_RW if (!(sb->s_flags & MS_RDONLY)) { @@ -854,7 +854,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent) goto unacquire_priv_sbp; if( befs_sb->num_blocks > ~((sector_t)0) ) { - befs_error(sb, "blocks count: %Lu " + befs_error(sb, "blocks count: %llu " "is larger than the host can use", befs_sb->num_blocks); goto unacquire_priv_sbp; @@ -924,7 +924,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf) struct super_block *sb = dentry->d_sb; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); - befs_debug(sb, "---> befs_statfs()"); + befs_debug(sb, "---> %s", __func__); buf->f_type = BEFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; @@ -937,7 +937,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_fsid.val[1] = (u32)(id >> 32); buf->f_namelen = BEFS_NAME_LEN; - befs_debug(sb, "<--- befs_statfs()"); + befs_debug(sb, "<--- %s", __func__); return 0; } @@ -963,7 +963,7 @@ init_befs_fs(void) { int err; - printk(KERN_INFO "BeFS version: %s\n", BEFS_VERSION); + pr_info("version: %s\n", BEFS_VERSION); err = befs_init_inodecache(); if (err) diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 8defc6b3f9a2..29aa5cf6639b 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -172,7 +172,7 @@ static void bfs_evict_inode(struct inode *inode) dprintf("ino=%08lx\n", ino); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 67be2951b98a..0f59799fa105 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -46,10 +46,15 @@ #endif static int load_elf_binary(struct linux_binprm *bprm); -static int load_elf_library(struct file *); static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *, int, int, unsigned long); +#ifdef CONFIG_USELIB +static int load_elf_library(struct file *); +#else +#define load_elf_library NULL +#endif + /* * If we don't support core dumping, then supply a NULL so we * don't even try. @@ -1005,6 +1010,7 @@ out_free_ph: goto out; } +#ifdef CONFIG_USELIB /* This is really simpleminded and specialized - we are loading an a.out library that is given an ELF header. */ static int load_elf_library(struct file *file) @@ -1083,6 +1089,7 @@ out_free_ph: out: return error; } +#endif /* #ifdef CONFIG_USELIB */ #ifdef CONFIG_ELF_CORE /* diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 1c740e152f38..b60500300dd7 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -656,6 +656,7 @@ static ssize_t bm_status_write(struct file * file, const char __user * buffer, mutex_unlock(&root->d_inode->i_mutex); dput(root); + break; default: return res; } return count; diff --git a/fs/block_dev.c b/fs/block_dev.c index 1e86823a9cbd..ba0d2b05bb78 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -83,7 +83,7 @@ void kill_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; - if (mapping->nrpages == 0) + if (mapping->nrpages == 0 && mapping->nrshadows == 0) return; invalidate_bh_lrus(); @@ -419,7 +419,7 @@ static void bdev_evict_inode(struct inode *inode) { struct block_device *bdev = &BDEV_I(inode)->bdev; struct list_head *p; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); spin_lock(&bdev_lock); @@ -1523,7 +1523,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, ssize_t err; err = generic_write_sync(file, pos, ret); - if (err < 0 && ret > 0) + if (err < 0) ret = err; } blk_finish_plug(&plug); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b01fb6c527e3..d43c544d3b68 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, pg_index); rcu_read_unlock(); - if (page) { + if (page && !radix_tree_exceptional_entry(page)) { misses++; if (misses > 4) break; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0165b8672f09..7331a230e30b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1797,7 +1797,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, BTRFS_I(inode)->last_sub_trans = root->log_transid; if (num_written > 0) { err = generic_write_sync(file, pos, num_written); - if (err < 0 && num_written > 0) + if (err < 0) num_written = err; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3d44486290b..49ec1398879f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4593,7 +4593,7 @@ static void evict_inode_truncate_pages(struct inode *inode) struct rb_node *node; ASSERT(inode->i_state & I_FREEING); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); write_lock(&map_tree->lock); while (!RB_EMPTY_ROOT(&map_tree->map)) { diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index ebaff368120d..4b1fb5ca65b8 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -265,24 +265,22 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object, goto nomem_monitor; } - ret = add_to_page_cache(newpage, bmapping, - netpage->index, cachefiles_gfp); + ret = add_to_page_cache_lru(newpage, bmapping, + netpage->index, cachefiles_gfp); if (ret == 0) goto installed_new_backing_page; if (ret != -EEXIST) goto nomem_page; } - /* we've installed a new backing page, so now we need to add it - * to the LRU list and start it reading */ + /* we've installed a new backing page, so now we need to start + * it reading */ installed_new_backing_page: _debug("- new %p", newpage); backpage = newpage; newpage = NULL; - lru_cache_add_file(backpage); - read_backing_page: ret = bmapping->a_ops->readpage(NULL, backpage); if (ret < 0) @@ -510,24 +508,23 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, goto nomem; } - ret = add_to_page_cache(newpage, bmapping, - netpage->index, cachefiles_gfp); + ret = add_to_page_cache_lru(newpage, bmapping, + netpage->index, + cachefiles_gfp); if (ret == 0) goto installed_new_backing_page; if (ret != -EEXIST) goto nomem; } - /* we've installed a new backing page, so now we need to add it - * to the LRU list and start it reading */ + /* we've installed a new backing page, so now we need + * to start it reading */ installed_new_backing_page: _debug("- new %p", newpage); backpage = newpage; newpage = NULL; - lru_cache_add_file(backpage); - reread_backing_page: ret = bmapping->a_ops->readpage(NULL, backpage); if (ret < 0) @@ -538,8 +535,8 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, monitor_backing_page: _debug("- monitor add"); - ret = add_to_page_cache(netpage, op->mapping, netpage->index, - cachefiles_gfp); + ret = add_to_page_cache_lru(netpage, op->mapping, + netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { page_cache_release(netpage); @@ -549,8 +546,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, goto nomem; } - lru_cache_add_file(netpage); - /* install a monitor */ page_cache_get(netpage); monitor->netfs_page = netpage; @@ -613,8 +608,8 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, backing_page_already_uptodate: _debug("- uptodate"); - ret = add_to_page_cache(netpage, op->mapping, netpage->index, - cachefiles_gfp); + ret = add_to_page_cache_lru(netpage, op->mapping, + netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { page_cache_release(netpage); @@ -631,8 +626,6 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, fscache_mark_page_cached(op, netpage); - lru_cache_add_file(netpage); - /* the netpage is unlocked and marked up to date here */ fscache_end_io(op, netpage, 0); page_cache_release(netpage); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 849f6132b327..ab8ad2546c3e 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -286,7 +286,7 @@ cifs_destroy_inode(struct inode *inode) static void cifs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); cifs_fscache_release_inode_cookie(inode); } @@ -1005,7 +1005,7 @@ cifs_init_once(void *inode) init_rwsem(&cifsi->lock_sem); } -static int +static int __init cifs_init_inodecache(void) { cifs_inode_cachep = kmem_cache_create("cifs_inode_cache", diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h index b7143cf783ac..381c993b1427 100644 --- a/fs/coda/coda_int.h +++ b/fs/coda/coda_int.h @@ -10,7 +10,7 @@ extern int coda_hard; extern int coda_fake_statfs; void coda_destroy_inodecache(void); -int coda_init_inodecache(void); +int __init coda_init_inodecache(void); int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync); void coda_sysctl_init(void); void coda_sysctl_clean(void); diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 506de34a4ef3..626abc02b694 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -73,7 +73,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -int coda_init_inodecache(void) +int __init coda_init_inodecache(void) { coda_inode_cachep = kmem_cache_create("coda_inode_cache", sizeof(struct coda_inode_info), @@ -250,7 +250,7 @@ static void coda_put_super(struct super_block *sb) static void coda_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); coda_cache_clear_inode(inode); } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 06610cf94d57..a1f801c14fbc 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = NULL; if (blocknr + i < devsize) { - page = read_mapping_page_async(mapping, blocknr + i, - NULL); + page = read_mapping_page(mapping, blocknr + i, NULL); /* synchronous error? */ if (IS_ERR(page)) page = NULL; diff --git a/fs/direct-io.c b/fs/direct-io.c index 160a5489a939..6e6bff375244 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -664,7 +664,6 @@ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio, goto out; sector = start_sector << (sdio->blkbits - 9); nr_pages = min(sdio->pages_in_io, bio_get_nr_vecs(map_bh->b_bdev)); - nr_pages = min(nr_pages, BIO_MAX_PAGES); BUG_ON(nr_pages <= 0); dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages); sdio->boundary = 0; diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 9fd702f5bfb2..9280202e488c 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write, if (ret) return ret; if (write) { - if (sysctl_drop_caches & 1) + static int stfu; + + if (sysctl_drop_caches & 1) { iterate_supers(drop_pagecache_sb, NULL); - if (sysctl_drop_caches & 2) + count_vm_event(DROP_PAGECACHE); + } + if (sysctl_drop_caches & 2) { drop_slab(); + count_vm_event(DROP_SLAB); + } + if (!stfu) { + pr_info("%s (%d): drop_caches: %d\n", + current->comm, task_pid_nr(current), + sysctl_drop_caches); + } + stfu |= sysctl_drop_caches & 4; } return 0; } diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index e879cf8ff0b1..afa1b81c3418 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -132,7 +132,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf) */ static void ecryptfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); iput(ecryptfs_inode_to_lower(inode)); } diff --git a/fs/efs/super.c b/fs/efs/super.c index 50215bbd6463..f8def1acf08c 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -91,7 +91,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -static int init_inodecache(void) +static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", sizeof(struct efs_inode_info), diff --git a/fs/exec.c b/fs/exec.c index 4f59402fdda5..25dfeba6d55f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -97,6 +97,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt) module_put(fmt->module); } +#ifdef CONFIG_USELIB /* * Note that a shared library must be both readable and executable due to * security reasons. @@ -156,6 +157,7 @@ exit: out: return error; } +#endif /* #ifdef CONFIG_USELIB */ #ifdef CONFIG_MMU /* diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index ee4317faccb1..d1c244d67667 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1486,7 +1486,7 @@ void exofs_evict_inode(struct inode *inode) struct ore_io_state *ios; int ret; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); /* TODO: should do better here */ if (inode->i_nlink || is_bad_inode(inode)) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 94ed36849b71..b1d2a4675d42 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -78,7 +78,7 @@ void ext2_evict_inode(struct inode * inode) dquot_drop(inode); } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (want_delete) { sb_start_intwrite(inode->i_sb); diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 384b6ebb655f..efce2bbfb5e5 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -228,7 +228,7 @@ void ext3_evict_inode (struct inode *inode) log_wait_commit(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); ext3_discard_reservation(inode); rsv = ei->i_block_alloc_info; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 1a5073959f32..6db7f7db7777 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -153,7 +153,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, ssize_t err; err = generic_write_sync(file, iocb->ki_pos - ret, ret); - if (err < 0 && ret > 0) + if (err < 0) ret = err; } blk_finish_plug(&plug); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 24bfd7ff3049..175c3f933816 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -215,7 +215,7 @@ void ext4_evict_inode(struct inode *inode) jbd2_complete_transaction(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count)); goto no_delete; @@ -226,7 +226,7 @@ void ext4_evict_inode(struct inode *inode) if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count)); if (is_bad_inode(inode)) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 4d67ed736dca..28cea76d78c6 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -260,7 +260,7 @@ void f2fs_evict_inode(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); trace_f2fs_evict_inode(inode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (inode->i_ino == F2FS_NODE_INO(sbi) || inode->i_ino == F2FS_META_INO(sbi)) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 854b578f6695..c68d9f27135e 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(fat_build_inode); static void fat_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; fat_truncate_blocks(inode, 0); diff --git a/fs/filesystems.c b/fs/filesystems.c index 92567d95ba6a..5797d45a78cb 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -121,6 +121,7 @@ int unregister_filesystem(struct file_system_type * fs) EXPORT_SYMBOL(unregister_filesystem); +#ifdef CONFIG_SYSFS_SYSCALL static int fs_index(const char __user * __name) { struct file_system_type * tmp; @@ -199,6 +200,7 @@ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) } return retval; } +#endif int __init get_filesystem_list(char *buf) { diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index f47df72cef17..363e3ae25f6b 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -354,7 +354,7 @@ static void vxfs_i_callback(struct rcu_head *head) void vxfs_evict_inode(struct inode *ip) { - truncate_inode_pages(&ip->i_data, 0); + truncate_inode_pages_final(&ip->i_data); clear_inode(ip); call_rcu(&ip->i_rcu, vxfs_i_callback); } diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index 25d4099a4aea..99c7f0a37af4 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -192,7 +192,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp) * vxfs_lookup - lookup pathname component * @dip: dir in which we lookup * @dp: dentry we lookup - * @nd: lookup nameidata + * @flags: lookup flags * * Description: * vxfs_lookup tries to lookup the pathname component described diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index d754e3cf99a8..a16315957ef3 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -89,16 +89,29 @@ static inline struct inode *wb_inode(struct list_head *head) #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> +static void bdi_wakeup_thread(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi->wb_lock); + if (test_bit(BDI_registered, &bdi->state)) + mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + spin_unlock_bh(&bdi->wb_lock); +} + static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { trace_writeback_queue(bdi, work); spin_lock_bh(&bdi->wb_lock); + if (!test_bit(BDI_registered, &bdi->state)) { + if (work->done) + complete(work->done); + goto out_unlock; + } list_add_tail(&work->list, &bdi->work_list); - spin_unlock_bh(&bdi->wb_lock); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); +out_unlock: + spin_unlock_bh(&bdi->wb_lock); } static void @@ -114,7 +127,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) { trace_writeback_nowork(bdi); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + bdi_wakeup_thread(bdi); return; } @@ -161,7 +174,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi) * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(bdi); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + bdi_wakeup_thread(bdi); } /* @@ -1017,7 +1030,7 @@ void bdi_writeback_workfn(struct work_struct *work) current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || - list_empty(&bdi->bdi_list))) { + !test_bit(BDI_registered, &bdi->state))) { /* * The normal path. Keep writing back @bdi until its * work_list is empty. Note that this path is also taken @@ -1039,10 +1052,10 @@ void bdi_writeback_workfn(struct work_struct *work) trace_writeback_pages_written(pages_written); } - if (!list_empty(&bdi->work_list) || - (wb_has_dirty_io(wb) && dirty_writeback_interval)) - queue_delayed_work(bdi_wq, &wb->dwork, - msecs_to_jiffies(dirty_writeback_interval * 10)); + if (!list_empty(&bdi->work_list)) + mod_delayed_work(bdi_wq, &wb->dwork, 0); + else if (wb_has_dirty_io(wb) && dirty_writeback_interval) + bdi_wakeup_thread_delayed(bdi); current->flags &= ~PF_SWAPWRITE; } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d468643a68b2..9c761b611c54 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -123,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode) static void fuse_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & MS_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 60f60f6181f3..24410cd9a82a 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1558,7 +1558,7 @@ out_unlock: fs_warn(sdp, "gfs2_evict_inode: %d\n", error); out: /* Case 3 starts here */ - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); gfs2_rs_delete(ip, NULL); gfs2_ordered_del_inode(ip); clear_inode(inode); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 380ab31b5e0f..9e2fecd62f62 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -547,7 +547,7 @@ out: void hfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) { HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL; diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c index 0f47890299c4..caf89a7be0a1 100644 --- a/fs/hfsplus/attributes.c +++ b/fs/hfsplus/attributes.c @@ -11,7 +11,7 @@ static struct kmem_cache *hfsplus_attr_tree_cachep; -int hfsplus_create_attr_tree_cache(void) +int __init hfsplus_create_attr_tree_cache(void) { if (hfsplus_attr_tree_cachep) return -EEXIST; diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index fbb212fbb1ef..a7aafb35b624 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -227,10 +227,8 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, u32 ablock, dblock, mask; sector_t sector; int was_dirty = 0; - int shift; /* Convert inode block to disk allocation block */ - shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits; ablock = iblock >> sbi->fs_shift; if (iblock >= hip->fs_blocks) { @@ -498,11 +496,13 @@ int hfsplus_file_extend(struct inode *inode) goto insert_extent; } out: - mutex_unlock(&hip->extents_lock); if (!res) { hip->alloc_blocks += len; + mutex_unlock(&hip->extents_lock); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY); + return 0; } + mutex_unlock(&hip->extents_lock); return res; insert_extent: @@ -556,11 +556,13 @@ void hfsplus_file_truncate(struct inode *inode) blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >> HFSPLUS_SB(sb)->alloc_blksz_shift; + + mutex_lock(&hip->extents_lock); + alloc_cnt = hip->alloc_blocks; if (blk_cnt == alloc_cnt) - goto out; + goto out_unlock; - mutex_lock(&hip->extents_lock); res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); if (res) { mutex_unlock(&hip->extents_lock); @@ -592,10 +594,10 @@ void hfsplus_file_truncate(struct inode *inode) hfs_brec_remove(&fd); } hfs_find_exit(&fd); - mutex_unlock(&hip->extents_lock); hip->alloc_blocks = blk_cnt; -out: +out_unlock: + mutex_unlock(&hip->extents_lock); hip->phys_size = inode->i_size; hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 62d571eb69ba..83dc29286b10 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -367,7 +367,7 @@ typedef int (*search_strategy_t)(struct hfs_bnode *, */ /* attributes.c */ -int hfsplus_create_attr_tree_cache(void); +int __init hfsplus_create_attr_tree_cache(void); void hfsplus_destroy_attr_tree_cache(void); hfsplus_attr_entry *hfsplus_alloc_attr_entry(void); void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 80875aa640ef..a6abf87d79d0 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -161,7 +161,7 @@ static int hfsplus_write_inode(struct inode *inode, static void hfsplus_evict_inode(struct inode *inode) { hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HFSPLUS_IS_RSRC(inode)) { HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index fe649d325b1f..9c470fde9878 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -230,7 +230,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) static void hostfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HOSTFS_I(inode)->fd != -1) { close_file(&HOSTFS_I(inode)->fd); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 9edeeb0ea97e..50a427313835 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -304,7 +304,7 @@ void hpfs_write_if_changed(struct inode *inode) void hpfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (!inode->i_nlink) { hpfs_lock(inode->i_sb); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d19b30ababf1..204027520937 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -366,7 +366,13 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart) static void hugetlbfs_evict_inode(struct inode *inode) { + struct resv_map *resv_map; + truncate_hugepages(inode, 0); + resv_map = (struct resv_map *)inode->i_mapping->private_data; + /* root inode doesn't have the resv_map, so we should check it */ + if (resv_map) + resv_map_release(&resv_map->refs); clear_inode(inode); } @@ -476,6 +482,11 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; + struct resv_map *resv_map; + + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; inode = new_inode(sb); if (inode) { @@ -487,7 +498,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - INIT_LIST_HEAD(&inode->i_mapping->private_list); + inode->i_mapping->private_data = resv_map; info = HUGETLBFS_I(inode); /* * The policy is initialized here even if we are creating a @@ -517,7 +528,9 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; } lockdep_annotate_inode_mutex_key(inode); - } + } else + kref_put(&resv_map->refs, resv_map_release); + return inode; } diff --git a/fs/inode.c b/fs/inode.c index 4bcdad3c9361..e6905152c39f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -503,6 +503,7 @@ void clear_inode(struct inode *inode) */ spin_lock_irq(&inode->i_data.tree_lock); BUG_ON(inode->i_data.nrpages); + BUG_ON(inode->i_data.nrshadows); spin_unlock_irq(&inode->i_data.tree_lock); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); @@ -548,8 +549,7 @@ static void evict(struct inode *inode) if (op->evict_inode) { op->evict_inode(inode); } else { - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a69e426435dd..f73991522672 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -242,7 +242,7 @@ void jffs2_evict_inode (struct inode *inode) jffs2_dbg(1, "%s(): ino #%lu mode %o\n", __func__, inode->i_ino, inode->i_mode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); jffs2_do_clear_inode(c, f); } @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index f4aab719add5..6f8fe72c2a7a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -154,7 +154,7 @@ void jfs_evict_inode(struct inode *inode) dquot_initialize(inode); if (JFS_IP(inode)->fileset == FILESYSTEM_I) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (test_cflag(COMMIT_Freewmap, inode)) jfs_free_zero_link(inode); @@ -168,7 +168,7 @@ void jfs_evict_inode(struct inode *inode) dquot_free_inode(inode); } } else { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); } clear_inode(inode); dquot_drop(inode); diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index e55126f85bd2..abb0f1f53d93 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -355,7 +355,7 @@ void kernfs_evict_inode(struct inode *inode) { struct kernfs_node *kn = inode->i_private; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); kernfs_put(kn); } diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index 9a59cbade2fb..48140315f627 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -2180,7 +2180,7 @@ void logfs_evict_inode(struct inode *inode) do_delete_inode(inode); } } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Cheaper version of write_inode. All changes are concealed in diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 0332109162a5..0ad2ec9601de 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -26,7 +26,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data); static void minix_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; minix_truncate(inode); @@ -86,7 +86,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -static int init_inodecache(void) +static int __init init_inodecache(void) { minix_inode_cachep = kmem_cache_create("minix_inode_cache", sizeof(struct minix_inode_info), diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 2cf2ebecb55f..ee59d35ff069 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -296,7 +296,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info) static void ncp_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (S_ISDIR(inode->i_mode)) { diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 56ff823ca82e..65d849bdf77a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); if (end != NFS_I(inode)->npages) { rcu_read_lock(); - end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 360114ae8b82..c4702baa22b8 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nfs_clear_inode(inode); } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 808f29574412..6f340f02f2ba 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -90,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc) */ static void nfs4_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); pnfs_return_layout(inode); pnfs_destroy_layout(NFS_I(inode)); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 06cddd572264..2645be435e75 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -71,10 +71,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) if (gid_eq(new->fsgid, INVALID_GID)) new->fsgid = exp->ex_anon_gid; - ret = set_groups(new, gi); + set_groups(new, gi); put_group_info(gi); - if (ret < 0) - goto error; if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID)) new->cap_effective = cap_drop_nfsd_set(new->cap_effective); @@ -89,7 +87,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) oom: ret = -ENOMEM; -error: abort_creds(new); return ret; } diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index deaa3d33a0aa..0d58075f34e2 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -942,6 +942,18 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize, struct inode *cpfile; int err; + if (cpsize > sb->s_blocksize) { + printk(KERN_ERR + "NILFS: too large checkpoint size: %zu bytes.\n", + cpsize); + return -EINVAL; + } else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) { + printk(KERN_ERR + "NILFS: too small checkpoint size: %zu bytes.\n", + cpsize); + return -EINVAL; + } + cpfile = nilfs_iget_locked(sb, NULL, NILFS_CPFILE_INO); if (unlikely(!cpfile)) return -ENOMEM; diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index fa0f80308c2d..0d5fada91191 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -484,6 +484,18 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size, struct nilfs_dat_info *di; int err; + if (entry_size > sb->s_blocksize) { + printk(KERN_ERR + "NILFS: too large DAT entry size: %zu bytes.\n", + entry_size); + return -EINVAL; + } else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) { + printk(KERN_ERR + "NILFS: too small DAT entry size: %zu bytes.\n", + entry_size); + return -EINVAL; + } + dat = nilfs_iget_locked(sb, NULL, NILFS_DAT_INO); if (unlikely(!dat)) return -ENOMEM; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7e350c562e0e..b9c5726120e3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -783,16 +783,14 @@ void nilfs_evict_inode(struct inode *inode) int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nilfs_clear_inode(inode); return; } nilfs_transaction_begin(sb, &ti, 0); /* never fails */ - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 2b34021948e4..422fb54b7377 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1072,6 +1072,48 @@ out: } /** + * nilfs_ioctl_trim_fs() - trim ioctl handle function + * @inode: inode object + * @argp: pointer on argument from userspace + * + * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It + * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which + * performs the actual trim operation. + * + * Return Value: On success, 0 is returned or negative error code, otherwise. + */ +static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp) +{ + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; + struct request_queue *q = bdev_get_queue(nilfs->ns_bdev); + struct fstrim_range range; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + + if (copy_from_user(&range, argp, sizeof(range))) + return -EFAULT; + + range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity); + + down_read(&nilfs->ns_segctor_sem); + ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range); + up_read(&nilfs->ns_segctor_sem); + + if (ret < 0) + return ret; + + if (copy_to_user(argp, &range, sizeof(range))) + return -EFAULT; + + return 0; +} + +/** * nilfs_ioctl_set_alloc_range - limit range of segments to be allocated * @inode: inode object * @argp: pointer on argument from userspace @@ -1163,6 +1205,95 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp, return ret; } +/** + * nilfs_ioctl_set_suinfo - set segment usage info + * @inode: inode object + * @filp: file object + * @cmd: ioctl's request code + * @argp: pointer on argument from userspace + * + * Description: Expects an array of nilfs_suinfo_update structures + * encapsulated in nilfs_argv and updates the segment usage info + * according to the flags in nilfs_suinfo_update. + * + * Return Value: On success, 0 is returned. On error, one of the + * following negative error codes is returned. + * + * %-EPERM - Not enough permissions + * + * %-EFAULT - Error copying input data + * + * %-EIO - I/O error. + * + * %-ENOMEM - Insufficient amount of memory available. + * + * %-EINVAL - Invalid values in input (segment number, flags or nblocks) + */ +static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp, + unsigned int cmd, void __user *argp) +{ + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; + struct nilfs_transaction_info ti; + struct nilfs_argv argv; + size_t len; + void __user *base; + void *kbuf; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + ret = -EFAULT; + if (copy_from_user(&argv, argp, sizeof(argv))) + goto out; + + ret = -EINVAL; + if (argv.v_size < sizeof(struct nilfs_suinfo_update)) + goto out; + + if (argv.v_nmembs > nilfs->ns_nsegments) + goto out; + + if (argv.v_nmembs >= UINT_MAX / argv.v_size) + goto out; + + len = argv.v_size * argv.v_nmembs; + if (!len) { + ret = 0; + goto out; + } + + base = (void __user *)(unsigned long)argv.v_base; + kbuf = vmalloc(len); + if (!kbuf) { + ret = -ENOMEM; + goto out; + } + + if (copy_from_user(kbuf, base, len)) { + ret = -EFAULT; + goto out_free; + } + + nilfs_transaction_begin(inode->i_sb, &ti, 0); + ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size, + argv.v_nmembs); + if (unlikely(ret < 0)) + nilfs_transaction_abort(inode->i_sb); + else + nilfs_transaction_commit(inode->i_sb); /* never fails */ + +out_free: + vfree(kbuf); +out: + mnt_drop_write_file(filp); + return ret; +} + long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1189,6 +1320,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return nilfs_ioctl_get_info(inode, filp, cmd, argp, sizeof(struct nilfs_suinfo), nilfs_ioctl_do_get_suinfo); + case NILFS_IOCTL_SET_SUINFO: + return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp); case NILFS_IOCTL_GET_SUSTAT: return nilfs_ioctl_get_sustat(inode, filp, cmd, argp); case NILFS_IOCTL_GET_VINFO: @@ -1205,6 +1338,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return nilfs_ioctl_resize(inode, filp, argp); case NILFS_IOCTL_SET_ALLOC_RANGE: return nilfs_ioctl_set_alloc_range(inode, argp); + case FITRIM: + return nilfs_ioctl_trim_fs(inode, argp); default: return -ENOTTY; } @@ -1228,6 +1363,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case NILFS_IOCTL_GET_CPINFO: case NILFS_IOCTL_GET_CPSTAT: case NILFS_IOCTL_GET_SUINFO: + case NILFS_IOCTL_SET_SUINFO: case NILFS_IOCTL_GET_SUSTAT: case NILFS_IOCTL_GET_VINFO: case NILFS_IOCTL_GET_BDESCS: @@ -1235,6 +1371,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case NILFS_IOCTL_SYNC: case NILFS_IOCTL_RESIZE: case NILFS_IOCTL_SET_ALLOC_RANGE: + case FITRIM: break; default: return -ENOIOCTLCMD; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 3127e9f438a7..2a869c35c362 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -870,6 +870,289 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf, } /** + * nilfs_sufile_set_suinfo - sets segment usage info + * @sufile: inode of segment usage file + * @buf: array of suinfo_update + * @supsz: byte size of suinfo_update + * @nsup: size of suinfo_update array + * + * Description: Takes an array of nilfs_suinfo_update structs and updates + * segment usage accordingly. Only the fields indicated by the sup_flags + * are updated. + * + * Return Value: On success, 0 is returned. On error, one of the + * following negative error codes is returned. + * + * %-EIO - I/O error. + * + * %-ENOMEM - Insufficient amount of memory available. + * + * %-EINVAL - Invalid values in input (segment number, flags or nblocks) + */ +ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf, + unsigned supsz, size_t nsup) +{ + struct the_nilfs *nilfs = sufile->i_sb->s_fs_info; + struct buffer_head *header_bh, *bh; + struct nilfs_suinfo_update *sup, *supend = buf + supsz * nsup; + struct nilfs_segment_usage *su; + void *kaddr; + unsigned long blkoff, prev_blkoff; + int cleansi, cleansu, dirtysi, dirtysu; + long ncleaned = 0, ndirtied = 0; + int ret = 0; + + if (unlikely(nsup == 0)) + return ret; + + for (sup = buf; sup < supend; sup = (void *)sup + supsz) { + if (sup->sup_segnum >= nilfs->ns_nsegments + || (sup->sup_flags & + (~0UL << __NR_NILFS_SUINFO_UPDATE_FIELDS)) + || (nilfs_suinfo_update_nblocks(sup) && + sup->sup_sui.sui_nblocks > + nilfs->ns_blocks_per_segment)) + return -EINVAL; + } + + down_write(&NILFS_MDT(sufile)->mi_sem); + + ret = nilfs_sufile_get_header_block(sufile, &header_bh); + if (ret < 0) + goto out_sem; + + sup = buf; + blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum); + ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh); + if (ret < 0) + goto out_header; + + for (;;) { + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage( + sufile, sup->sup_segnum, bh, kaddr); + + if (nilfs_suinfo_update_lastmod(sup)) + su->su_lastmod = cpu_to_le64(sup->sup_sui.sui_lastmod); + + if (nilfs_suinfo_update_nblocks(sup)) + su->su_nblocks = cpu_to_le32(sup->sup_sui.sui_nblocks); + + if (nilfs_suinfo_update_flags(sup)) { + /* + * Active flag is a virtual flag projected by running + * nilfs kernel code - drop it not to write it to + * disk. + */ + sup->sup_sui.sui_flags &= + ~(1UL << NILFS_SEGMENT_USAGE_ACTIVE); + + cleansi = nilfs_suinfo_clean(&sup->sup_sui); + cleansu = nilfs_segment_usage_clean(su); + dirtysi = nilfs_suinfo_dirty(&sup->sup_sui); + dirtysu = nilfs_segment_usage_dirty(su); + + if (cleansi && !cleansu) + ++ncleaned; + else if (!cleansi && cleansu) + --ncleaned; + + if (dirtysi && !dirtysu) + ++ndirtied; + else if (!dirtysi && dirtysu) + --ndirtied; + + su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags); + } + + kunmap_atomic(kaddr); + + sup = (void *)sup + supsz; + if (sup >= supend) + break; + + prev_blkoff = blkoff; + blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum); + if (blkoff == prev_blkoff) + continue; + + /* get different block */ + mark_buffer_dirty(bh); + put_bh(bh); + ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh); + if (unlikely(ret < 0)) + goto out_mark; + } + mark_buffer_dirty(bh); + put_bh(bh); + + out_mark: + if (ncleaned || ndirtied) { + nilfs_sufile_mod_counter(header_bh, (u64)ncleaned, + (u64)ndirtied); + NILFS_SUI(sufile)->ncleansegs += ncleaned; + } + nilfs_mdt_mark_dirty(sufile); + out_header: + put_bh(header_bh); + out_sem: + up_write(&NILFS_MDT(sufile)->mi_sem); + return ret; +} + +/** + * nilfs_sufile_trim_fs() - trim ioctl handle function + * @sufile: inode of segment usage file + * @range: fstrim_range structure + * + * start: First Byte to trim + * len: number of Bytes to trim from start + * minlen: minimum extent length in Bytes + * + * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes + * from start to start+len. start is rounded up to the next block boundary + * and start+len is rounded down. For each clean segment blkdev_issue_discard + * function is invoked. + * + * Return Value: On success, 0 is returned or negative error code, otherwise. + */ +int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range) +{ + struct the_nilfs *nilfs = sufile->i_sb->s_fs_info; + struct buffer_head *su_bh; + struct nilfs_segment_usage *su; + void *kaddr; + size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size; + sector_t seg_start, seg_end, start_block, end_block; + sector_t start = 0, nblocks = 0; + u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0; + int ret = 0; + unsigned int sects_per_block; + + sects_per_block = (1 << nilfs->ns_blocksize_bits) / + bdev_logical_block_size(nilfs->ns_bdev); + len = range->len >> nilfs->ns_blocksize_bits; + minlen = range->minlen >> nilfs->ns_blocksize_bits; + max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment); + + if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits) + return -EINVAL; + + start_block = (range->start + nilfs->ns_blocksize - 1) >> + nilfs->ns_blocksize_bits; + + /* + * range->len can be very large (actually, it is set to + * ULLONG_MAX by default) - truncate upper end of the range + * carefully so as not to overflow. + */ + if (max_blocks - start_block < len) + end_block = max_blocks - 1; + else + end_block = start_block + len - 1; + + segnum = nilfs_get_segnum_of_block(nilfs, start_block); + segnum_end = nilfs_get_segnum_of_block(nilfs, end_block); + + down_read(&NILFS_MDT(sufile)->mi_sem); + + while (segnum <= segnum_end) { + n = nilfs_sufile_segment_usages_in_block(sufile, segnum, + segnum_end); + + ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, + &su_bh); + if (ret < 0) { + if (ret != -ENOENT) + goto out_sem; + /* hole */ + segnum += n; + continue; + } + + kaddr = kmap_atomic(su_bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, + su_bh, kaddr); + for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) { + if (!nilfs_segment_usage_clean(su)) + continue; + + nilfs_get_segment_range(nilfs, segnum, &seg_start, + &seg_end); + + if (!nblocks) { + /* start new extent */ + start = seg_start; + nblocks = seg_end - seg_start + 1; + continue; + } + + if (start + nblocks == seg_start) { + /* add to previous extent */ + nblocks += seg_end - seg_start + 1; + continue; + } + + /* discard previous extent */ + if (start < start_block) { + nblocks -= start_block - start; + start = start_block; + } + + if (nblocks >= minlen) { + kunmap_atomic(kaddr); + + ret = blkdev_issue_discard(nilfs->ns_bdev, + start * sects_per_block, + nblocks * sects_per_block, + GFP_NOFS, 0); + if (ret < 0) { + put_bh(su_bh); + goto out_sem; + } + + ndiscarded += nblocks; + kaddr = kmap_atomic(su_bh->b_page); + su = nilfs_sufile_block_get_segment_usage( + sufile, segnum, su_bh, kaddr); + } + + /* start new extent */ + start = seg_start; + nblocks = seg_end - seg_start + 1; + } + kunmap_atomic(kaddr); + put_bh(su_bh); + } + + + if (nblocks) { + /* discard last extent */ + if (start < start_block) { + nblocks -= start_block - start; + start = start_block; + } + if (start + nblocks > end_block + 1) + nblocks = end_block - start + 1; + + if (nblocks >= minlen) { + ret = blkdev_issue_discard(nilfs->ns_bdev, + start * sects_per_block, + nblocks * sects_per_block, + GFP_NOFS, 0); + if (!ret) + ndiscarded += nblocks; + } + } + +out_sem: + up_read(&NILFS_MDT(sufile)->mi_sem); + + range->len = ndiscarded << nilfs->ns_blocksize_bits; + return ret; +} + +/** * nilfs_sufile_read - read or get sufile inode * @sb: super block instance * @susize: size of a segment usage entry @@ -886,6 +1169,18 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize, void *kaddr; int err; + if (susize > sb->s_blocksize) { + printk(KERN_ERR + "NILFS: too large segment usage size: %zu bytes.\n", + susize); + return -EINVAL; + } else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) { + printk(KERN_ERR + "NILFS: too small segment usage size: %zu bytes.\n", + susize); + return -EINVAL; + } + sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO); if (unlikely(!sufile)) return -ENOMEM; diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index e84bc5b51fc1..b8afd72f2379 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -44,6 +44,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *); ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned, size_t); +ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned , size_t); int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *, void (*dofunc)(struct inode *, __u64, @@ -65,6 +66,7 @@ void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *, int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs); int nilfs_sufile_read(struct super_block *sb, size_t susize, struct nilfs_inode *raw_inode, struct inode **inodep); +int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range); /** * nilfs_sufile_scrap - make a segment garbage diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 94c451ce6d24..8ba8229ba076 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -399,6 +399,16 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, return -EINVAL; nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size); + if (nilfs->ns_inode_size > nilfs->ns_blocksize) { + printk(KERN_ERR "NILFS: too large inode size: %d bytes.\n", + nilfs->ns_inode_size); + return -EINVAL; + } else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) { + printk(KERN_ERR "NILFS: too small inode size: %d bytes.\n", + nilfs->ns_inode_size); + return -EINVAL; + } + nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino); nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index dc638f786d5c..ee9cb3795c2b 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -60,8 +60,8 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS -static int fanotify_get_response_from_access(struct fsnotify_group *group, - struct fanotify_event_info *event) +static int fanotify_get_response(struct fsnotify_group *group, + struct fanotify_perm_event_info *event) { int ret; @@ -142,6 +142,40 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark, return false; } +struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask, + struct path *path) +{ + struct fanotify_event_info *event; + +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + if (mask & FAN_ALL_PERM_EVENTS) { + struct fanotify_perm_event_info *pevent; + + pevent = kmem_cache_alloc(fanotify_perm_event_cachep, + GFP_KERNEL); + if (!pevent) + return NULL; + event = &pevent->fae; + pevent->response = 0; + goto init; + } +#endif + event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL); + if (!event) + return NULL; +init: __maybe_unused + fsnotify_init_event(&event->fse, inode, mask); + event->tgid = get_pid(task_tgid(current)); + if (path) { + event->path = *path; + path_get(&event->path); + } else { + event->path.mnt = NULL; + event->path.dentry = NULL; + } + return event; +} + static int fanotify_handle_event(struct fsnotify_group *group, struct inode *inode, struct fsnotify_mark *inode_mark, @@ -171,25 +205,11 @@ static int fanotify_handle_event(struct fsnotify_group *group, pr_debug("%s: group=%p inode=%p mask=%x\n", __func__, group, inode, mask); - event = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL); + event = fanotify_alloc_event(inode, mask, data); if (unlikely(!event)) return -ENOMEM; fsn_event = &event->fse; - fsnotify_init_event(fsn_event, inode, mask); - event->tgid = get_pid(task_tgid(current)); - if (data_type == FSNOTIFY_EVENT_PATH) { - struct path *path = data; - event->path = *path; - path_get(&event->path); - } else { - event->path.mnt = NULL; - event->path.dentry = NULL; - } -#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS - event->response = 0; -#endif - ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge); if (ret) { /* Permission events shouldn't be merged */ @@ -202,7 +222,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS if (mask & FAN_ALL_PERM_EVENTS) { - ret = fanotify_get_response_from_access(group, event); + ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event)); fsnotify_destroy_event(group, fsn_event); } #endif @@ -225,6 +245,13 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event) event = FANOTIFY_E(fsn_event); path_put(&event->path); put_pid(event->tgid); +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + if (fsn_event->mask & FAN_ALL_PERM_EVENTS) { + kmem_cache_free(fanotify_perm_event_cachep, + FANOTIFY_PE(fsn_event)); + return; + } +#endif kmem_cache_free(fanotify_event_cachep, event); } diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 32a2f034fb94..2a5fb14115df 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -3,13 +3,12 @@ #include <linux/slab.h> extern struct kmem_cache *fanotify_event_cachep; +extern struct kmem_cache *fanotify_perm_event_cachep; /* - * Lifetime of the structure differs for normal and permission events. In both - * cases the structure is allocated in fanotify_handle_event(). For normal - * events the structure is freed immediately after reporting it to userspace. - * For permission events we free it only after we receive response from - * userspace. + * Structure for normal fanotify events. It gets allocated in + * fanotify_handle_event() and freed when the information is retrieved by + * userspace */ struct fanotify_event_info { struct fsnotify_event fse; @@ -19,12 +18,33 @@ struct fanotify_event_info { */ struct path path; struct pid *tgid; +}; + #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS - u32 response; /* userspace answer to question */ -#endif +/* + * Structure for permission fanotify events. It gets allocated and freed in + * fanotify_handle_event() since we wait there for user response. When the + * information is retrieved by userspace the structure is moved from + * group->notification_list to group->fanotify_data.access_list to wait for + * user response. + */ +struct fanotify_perm_event_info { + struct fanotify_event_info fae; + int response; /* userspace answer to question */ + int fd; /* fd we passed to userspace for this event */ }; +static inline struct fanotify_perm_event_info * +FANOTIFY_PE(struct fsnotify_event *fse) +{ + return container_of(fse, struct fanotify_perm_event_info, fae.fse); +} +#endif + static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse) { return container_of(fse, struct fanotify_event_info, fse); } + +struct fanotify_event_info *fanotify_alloc_event(struct inode *inode, u32 mask, + struct path *path); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 287a22c04149..4e565c814309 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -28,14 +28,8 @@ extern const struct fsnotify_ops fanotify_fsnotify_ops; static struct kmem_cache *fanotify_mark_cache __read_mostly; -static struct kmem_cache *fanotify_response_event_cache __read_mostly; struct kmem_cache *fanotify_event_cachep __read_mostly; - -struct fanotify_response_event { - struct list_head list; - __s32 fd; - struct fanotify_event_info *event; -}; +struct kmem_cache *fanotify_perm_event_cachep __read_mostly; /* * Get an fsnotify notification event if one exists and is small @@ -135,33 +129,34 @@ static int fill_event_metadata(struct fsnotify_group *group, } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS -static struct fanotify_response_event *dequeue_re(struct fsnotify_group *group, - __s32 fd) +static struct fanotify_perm_event_info *dequeue_event( + struct fsnotify_group *group, int fd) { - struct fanotify_response_event *re, *return_re = NULL; + struct fanotify_perm_event_info *event, *return_e = NULL; - mutex_lock(&group->fanotify_data.access_mutex); - list_for_each_entry(re, &group->fanotify_data.access_list, list) { - if (re->fd != fd) + spin_lock(&group->fanotify_data.access_lock); + list_for_each_entry(event, &group->fanotify_data.access_list, + fae.fse.list) { + if (event->fd != fd) continue; - list_del_init(&re->list); - return_re = re; + list_del_init(&event->fae.fse.list); + return_e = event; break; } - mutex_unlock(&group->fanotify_data.access_mutex); + spin_unlock(&group->fanotify_data.access_lock); - pr_debug("%s: found return_re=%p\n", __func__, return_re); + pr_debug("%s: found return_re=%p\n", __func__, return_e); - return return_re; + return return_e; } static int process_access_response(struct fsnotify_group *group, struct fanotify_response *response_struct) { - struct fanotify_response_event *re; - __s32 fd = response_struct->fd; - __u32 response = response_struct->response; + struct fanotify_perm_event_info *event; + int fd = response_struct->fd; + int response = response_struct->response; pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group, fd, response); @@ -181,58 +176,15 @@ static int process_access_response(struct fsnotify_group *group, if (fd < 0) return -EINVAL; - re = dequeue_re(group, fd); - if (!re) + event = dequeue_event(group, fd); + if (!event) return -ENOENT; - re->event->response = response; - + event->response = response; wake_up(&group->fanotify_data.access_waitq); - kmem_cache_free(fanotify_response_event_cache, re); - - return 0; -} - -static int prepare_for_access_response(struct fsnotify_group *group, - struct fsnotify_event *event, - __s32 fd) -{ - struct fanotify_response_event *re; - - if (!(event->mask & FAN_ALL_PERM_EVENTS)) - return 0; - - re = kmem_cache_alloc(fanotify_response_event_cache, GFP_KERNEL); - if (!re) - return -ENOMEM; - - re->event = FANOTIFY_E(event); - re->fd = fd; - - mutex_lock(&group->fanotify_data.access_mutex); - - if (atomic_read(&group->fanotify_data.bypass_perm)) { - mutex_unlock(&group->fanotify_data.access_mutex); - kmem_cache_free(fanotify_response_event_cache, re); - FANOTIFY_E(event)->response = FAN_ALLOW; - return 0; - } - - list_add_tail(&re->list, &group->fanotify_data.access_list); - mutex_unlock(&group->fanotify_data.access_mutex); - - return 0; -} - -#else -static int prepare_for_access_response(struct fsnotify_group *group, - struct fsnotify_event *event, - __s32 fd) -{ return 0; } - #endif static ssize_t copy_event_to_user(struct fsnotify_group *group, @@ -247,7 +199,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f); if (ret < 0) - goto out; + return ret; fd = fanotify_event_metadata.fd; ret = -EFAULT; @@ -255,9 +207,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, fanotify_event_metadata.event_len)) goto out_close_fd; - ret = prepare_for_access_response(group, event, fd); - if (ret) - goto out_close_fd; +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + if (event->mask & FAN_ALL_PERM_EVENTS) + FANOTIFY_PE(event)->fd = fd; +#endif if (fd != FAN_NOFD) fd_install(fd, f); @@ -268,13 +221,6 @@ out_close_fd: put_unused_fd(fd); fput(f); } -out: -#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS - if (event->mask & FAN_ALL_PERM_EVENTS) { - FANOTIFY_E(event)->response = FAN_DENY; - wake_up(&group->fanotify_data.access_waitq); - } -#endif return ret; } @@ -314,35 +260,50 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, kevent = get_one_event(group, count); mutex_unlock(&group->notification_mutex); - if (kevent) { + if (IS_ERR(kevent)) { ret = PTR_ERR(kevent); - if (IS_ERR(kevent)) + break; + } + + if (!kevent) { + ret = -EAGAIN; + if (file->f_flags & O_NONBLOCK) break; - ret = copy_event_to_user(group, kevent, buf); - /* - * Permission events get destroyed after we - * receive response - */ - if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) - fsnotify_destroy_event(group, kevent); - if (ret < 0) + + ret = -ERESTARTSYS; + if (signal_pending(current)) + break; + + if (start != buf) break; - buf += ret; - count -= ret; + schedule(); continue; } - ret = -EAGAIN; - if (file->f_flags & O_NONBLOCK) - break; - ret = -ERESTARTSYS; - if (signal_pending(current)) - break; - - if (start != buf) - break; - - schedule(); + ret = copy_event_to_user(group, kevent, buf); + /* + * Permission events get queued to wait for response. Other + * events can be destroyed now. + */ + if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) { + fsnotify_destroy_event(group, kevent); + if (ret < 0) + break; + } else { +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + if (ret < 0) { + FANOTIFY_PE(kevent)->response = FAN_DENY; + wake_up(&group->fanotify_data.access_waitq); + break; + } + spin_lock(&group->fanotify_data.access_lock); + list_add_tail(&kevent->list, + &group->fanotify_data.access_list); + spin_unlock(&group->fanotify_data.access_lock); +#endif + } + buf += ret; + count -= ret; } finish_wait(&group->notification_waitq, &wait); @@ -383,22 +344,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) struct fsnotify_group *group = file->private_data; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS - struct fanotify_response_event *re, *lre; + struct fanotify_perm_event_info *event, *next; - mutex_lock(&group->fanotify_data.access_mutex); + spin_lock(&group->fanotify_data.access_lock); atomic_inc(&group->fanotify_data.bypass_perm); - list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) { - pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group, - re, re->event); + list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, + fae.fse.list) { + pr_debug("%s: found group=%p event=%p\n", __func__, group, + event); - list_del_init(&re->list); - re->event->response = FAN_ALLOW; - - kmem_cache_free(fanotify_response_event_cache, re); + list_del_init(&event->fae.fse.list); + event->response = FAN_ALLOW; } - mutex_unlock(&group->fanotify_data.access_mutex); + spin_unlock(&group->fanotify_data.access_lock); wake_up(&group->fanotify_data.access_waitq); #endif @@ -731,21 +691,16 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user; atomic_inc(&user->fanotify_listeners); - oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL); + oevent = fanotify_alloc_event(NULL, FS_Q_OVERFLOW, NULL); if (unlikely(!oevent)) { fd = -ENOMEM; goto out_destroy_group; } group->overflow_event = &oevent->fse; - fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); - oevent->tgid = get_pid(task_tgid(current)); - oevent->path.mnt = NULL; - oevent->path.dentry = NULL; group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS - oevent->response = 0; - mutex_init(&group->fanotify_data.access_mutex); + spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); atomic_set(&group->fanotify_data.bypass_perm, 0); @@ -920,9 +875,11 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark, static int __init fanotify_user_setup(void) { fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC); - fanotify_response_event_cache = KMEM_CACHE(fanotify_response_event, - SLAB_PANIC); fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC); +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event_info, + SLAB_PANIC); +#endif return 0; } diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index ffb9b3675736..9d8153ebacfb 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2259,7 +2259,7 @@ void ntfs_evict_big_inode(struct inode *vi) { ntfs_inode *ni = NTFS_I(vi); - truncate_inode_pages(&vi->i_data, 0); + truncate_inode_pages_final(&vi->i_data); clear_inode(vi); #ifdef NTFS_RW diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 555f4cddefe3..7e8282dcea2a 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -205,6 +205,7 @@ static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh, di->i_mode = cpu_to_le16(inode->i_mode); di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index e2edff38be52..b4deb5f750d9 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5728,6 +5728,7 @@ int ocfs2_remove_btree_range(struct inode *inode, } ocfs2_et_update_clusters(et, -len); + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, et->et_root_bh); @@ -6932,6 +6933,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); spin_unlock(&oi->ip_lock); + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_dinode_new_extent_list(inode, di); ocfs2_journal_dirty(handle, di_bh); @@ -7208,6 +7210,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec); di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, di_bh); out_commit: diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index aeb44e879c51..d310d12a9adc 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -571,7 +571,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, { struct inode *inode = file_inode(iocb->ki_filp); int level; - wait_queue_head_t *wq = ocfs2_ioend_wq(inode); /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); @@ -582,10 +581,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, if (ocfs2_iocb_is_unaligned_aio(iocb)) { ocfs2_iocb_clear_unaligned_aio(iocb); - if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) && - waitqueue_active(wq)) { - wake_up_all(wq); - } + mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio); } ocfs2_iocb_clear_rw_locked(iocb); @@ -2043,6 +2039,7 @@ out_write_size: inode->i_mtime = inode->i_ctime = CURRENT_TIME; di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, wc->w_di_bh); ocfs2_commit_trans(osb, handle); diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index f671e49beb34..6cae155d54df 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -102,9 +102,4 @@ enum ocfs2_iocb_lock_bits { #define ocfs2_iocb_is_unaligned_aio(iocb) \ test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private) -#define OCFS2_IOEND_WQ_HASH_SZ 37 -#define ocfs2_ioend_wq(v) (&ocfs2__ioend_wq[((unsigned long)(v)) %\ - OCFS2_IOEND_WQ_HASH_SZ]) -extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ]; - #endif /* OCFS2_FILE_H */ diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 5b704c63a103..1edcb141f639 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -90,7 +90,6 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, * information for this bh as it's not marked locally * uptodate. */ ret = -EIO; - put_bh(bh); mlog_errno(ret); } @@ -420,7 +419,6 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb, if (!buffer_uptodate(bh)) { ret = -EIO; - put_bh(bh); mlog_errno(ret); } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 2cd2406b4140..eb649d23a4de 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -262,17 +262,17 @@ static void o2net_update_recv_stats(struct o2net_sock_container *sc) #endif /* CONFIG_OCFS2_FS_STATS */ -static inline int o2net_reconnect_delay(void) +static inline unsigned int o2net_reconnect_delay(void) { return o2nm_single_cluster->cl_reconnect_delay_ms; } -static inline int o2net_keepalive_delay(void) +static inline unsigned int o2net_keepalive_delay(void) { return o2nm_single_cluster->cl_keepalive_delay_ms; } -static inline int o2net_idle_timeout(void) +static inline unsigned int o2net_idle_timeout(void) { return o2nm_single_cluster->cl_idle_timeout_ms; } @@ -1964,18 +1964,30 @@ static void o2net_listen_data_ready(struct sock *sk, int bytes) goto out; } - /* ->sk_data_ready is also called for a newly established child socket - * before it has been accepted and the acceptor has set up their - * data_ready.. we only want to queue listen work for our listening - * socket */ + /* This callback may called twice when a new connection + * is being established as a child socket inherits everything + * from a parent LISTEN socket, including the data_ready cb of + * the parent. This leads to a hazard. In o2net_accept_one() + * we are still initializing the child socket but have not + * changed the inherited data_ready callback yet when + * data starts arriving. + * We avoid this hazard by checking the state. + * For the listening socket, the state will be TCP_LISTEN; for the new + * socket, will be TCP_ESTABLISHED. Also, in this case, + * sk->sk_user_data is not a valid function pointer. + */ + if (sk->sk_state == TCP_LISTEN) { mlog(ML_TCP, "bytes: %d\n", bytes); queue_work(o2net_wq, &o2net_listen_work); + } else { + ready = NULL; } out: read_unlock(&sk->sk_callback_lock); - ready(sk, bytes); + if (ready != NULL) + ready(sk, bytes); } static int o2net_open_listening_sock(__be32 addr, __be16 port) diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 0d3a97d2d5f6..e2e05a106beb 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -37,7 +37,6 @@ #include "dlmglue.h" #include "file.h" #include "inode.h" -#include "super.h" #include "ocfs2_trace.h" void ocfs2_dentry_attach_gen(struct dentry *dentry) @@ -346,52 +345,6 @@ out_attach: return ret; } -DEFINE_SPINLOCK(dentry_list_lock); - -/* We limit the number of dentry locks to drop in one go. We have - * this limit so that we don't starve other users of ocfs2_wq. */ -#define DL_INODE_DROP_COUNT 64 - -/* Drop inode references from dentry locks */ -static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count) -{ - struct ocfs2_dentry_lock *dl; - - spin_lock(&dentry_list_lock); - while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) { - dl = osb->dentry_lock_list; - osb->dentry_lock_list = dl->dl_next; - spin_unlock(&dentry_list_lock); - iput(dl->dl_inode); - kfree(dl); - spin_lock(&dentry_list_lock); - } - spin_unlock(&dentry_list_lock); -} - -void ocfs2_drop_dl_inodes(struct work_struct *work) -{ - struct ocfs2_super *osb = container_of(work, struct ocfs2_super, - dentry_lock_work); - - __ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT); - /* - * Don't queue dropping if umount is in progress. We flush the - * list in ocfs2_dismount_volume - */ - spin_lock(&dentry_list_lock); - if (osb->dentry_lock_list && - !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED)) - queue_work(ocfs2_wq, &osb->dentry_lock_work); - spin_unlock(&dentry_list_lock); -} - -/* Flush the whole work queue */ -void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb) -{ - __ocfs2_drop_dl_inodes(osb, -1); -} - /* * ocfs2_dentry_iput() and friends. * @@ -416,24 +369,16 @@ void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb) static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl) { + iput(dl->dl_inode); ocfs2_simple_drop_lockres(osb, &dl->dl_lockres); ocfs2_lock_res_free(&dl->dl_lockres); - - /* We leave dropping of inode reference to ocfs2_wq as that can - * possibly lead to inode deletion which gets tricky */ - spin_lock(&dentry_list_lock); - if (!osb->dentry_lock_list && - !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED)) - queue_work(ocfs2_wq, &osb->dentry_lock_work); - dl->dl_next = osb->dentry_lock_list; - osb->dentry_lock_list = dl; - spin_unlock(&dentry_list_lock); + kfree(dl); } void ocfs2_dentry_lock_put(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl) { - int unlock; + int unlock = 0; BUG_ON(dl->dl_count == 0); diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h index b79eff709958..55f58892b153 100644 --- a/fs/ocfs2/dcache.h +++ b/fs/ocfs2/dcache.h @@ -29,13 +29,8 @@ extern const struct dentry_operations ocfs2_dentry_ops; struct ocfs2_dentry_lock { - /* Use count of dentry lock */ unsigned int dl_count; - union { - /* Linked list of dentry locks to release */ - struct ocfs2_dentry_lock *dl_next; - u64 dl_parent_blkno; - }; + u64 dl_parent_blkno; /* * The ocfs2_dentry_lock keeps an inode reference until @@ -49,14 +44,9 @@ struct ocfs2_dentry_lock { int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode, u64 parent_blkno); -extern spinlock_t dentry_list_lock; - void ocfs2_dentry_lock_put(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl); -void ocfs2_drop_dl_inodes(struct work_struct *work); -void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb); - struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 91a7e85ac8fd..0717662b4aef 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2957,6 +2957,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, ocfs2_init_dir_trailer(dir, dirdata_bh, i); } + ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, dirdata_bh); if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) { @@ -3005,6 +3006,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, di->i_size = cpu_to_le64(sb->s_blocksize); di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec); di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, dir, 1); /* * This should never fail as our extent list is empty and all @@ -3338,6 +3340,7 @@ do_extend: } else { de->rec_len = cpu_to_le16(sb->s_blocksize); } + ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, new_bh); dir_i_size += dir->i_sb->s_blocksize; @@ -3896,6 +3899,7 @@ out_commit: dquot_free_space_nodirty(dir, ocfs2_clusters_to_bytes(dir->i_sb, 1)); + ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_commit_trans(osb, handle); out: @@ -4134,6 +4138,7 @@ static int ocfs2_expand_inline_dx_root(struct inode *dir, mlog_errno(ret); did_quota = 0; + ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, dx_root_bh); out_commit: @@ -4401,6 +4406,7 @@ static int ocfs2_dx_dir_remove_index(struct inode *dir, di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features); spin_unlock(&OCFS2_I(dir)->ip_lock); di->i_dx_root = cpu_to_le64(0ULL); + ocfs2_update_inode_fsync_trans(handle, dir, 1); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 33660a4a52fa..c973690dc0bc 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1123,7 +1123,6 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len, struct dlm_ctxt *dlm = NULL; char *local = NULL; int status = 0; - int locked = 0; qr = (struct dlm_query_region *) msg->buf; @@ -1132,10 +1131,8 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len, /* buffer used in dlm_mast_regions() */ local = kmalloc(sizeof(qr->qr_regions), GFP_KERNEL); - if (!local) { - status = -ENOMEM; - goto bail; - } + if (!local) + return -ENOMEM; status = -EINVAL; @@ -1144,16 +1141,15 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len, if (!dlm) { mlog(ML_ERROR, "Node %d queried hb regions on domain %s " "before join domain\n", qr->qr_node, qr->qr_domain); - goto bail; + goto out_domain_lock; } spin_lock(&dlm->spinlock); - locked = 1; if (dlm->joining_node != qr->qr_node) { mlog(ML_ERROR, "Node %d queried hb regions on domain %s " "but joining node is %d\n", qr->qr_node, qr->qr_domain, dlm->joining_node); - goto bail; + goto out_dlm_lock; } /* Support for global heartbeat was added in 1.1 */ @@ -1163,14 +1159,15 @@ static int dlm_query_region_handler(struct o2net_msg *msg, u32 len, "but active dlm protocol is %d.%d\n", qr->qr_node, qr->qr_domain, dlm->dlm_locking_proto.pv_major, dlm->dlm_locking_proto.pv_minor); - goto bail; + goto out_dlm_lock; } status = dlm_match_regions(dlm, qr, local, sizeof(qr->qr_regions)); -bail: - if (locked) - spin_unlock(&dlm->spinlock); +out_dlm_lock: + spin_unlock(&dlm->spinlock); + +out_domain_lock: spin_unlock(&dlm_domain_lock); kfree(local); @@ -1877,19 +1874,19 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) goto bail; } - status = dlm_debug_init(dlm); + status = dlm_launch_thread(dlm); if (status < 0) { mlog_errno(status); goto bail; } - status = dlm_launch_thread(dlm); + status = dlm_launch_recovery_thread(dlm); if (status < 0) { mlog_errno(status); goto bail; } - status = dlm_launch_recovery_thread(dlm); + status = dlm_debug_init(dlm); if (status < 0) { mlog_errno(status); goto bail; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 7035af09cc03..fe29f7978f81 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -537,7 +537,10 @@ master_here: /* success! see if any other nodes need recovery */ mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n", dlm->name, dlm->reco.dead_node, dlm->node_num); - dlm_reset_recovery(dlm); + spin_lock(&dlm->spinlock); + __dlm_reset_recovery(dlm); + dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE; + spin_unlock(&dlm->spinlock); } dlm_end_recovery(dlm); @@ -695,6 +698,14 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) if (all_nodes_done) { int ret; + /* Set this flag on recovery master to avoid + * a new recovery for another dead node start + * before the recovery is not done. That may + * cause recovery hung.*/ + spin_lock(&dlm->spinlock); + dlm->reco.state |= DLM_RECO_STATE_FINALIZE; + spin_unlock(&dlm->spinlock); + /* all nodes are now in DLM_RECO_NODE_DATA_DONE state * just send a finalize message to everyone and * clean up */ @@ -1750,13 +1761,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, struct dlm_migratable_lockres *mres) { struct dlm_migratable_lock *ml; - struct list_head *queue; + struct list_head *queue, *iter; struct list_head *tmpq = NULL; struct dlm_lock *newlock = NULL; struct dlm_lockstatus *lksb = NULL; int ret = 0; int i, j, bad; - struct dlm_lock *lock = NULL; + struct dlm_lock *lock; u8 from = O2NM_MAX_NODES; unsigned int added = 0; __be64 c; @@ -1791,14 +1802,16 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, /* MIGRATION ONLY! */ BUG_ON(!(mres->flags & DLM_MRES_MIGRATION)); + lock = NULL; spin_lock(&res->spinlock); for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) { tmpq = dlm_list_idx_to_ptr(res, j); - list_for_each_entry(lock, tmpq, list) { - if (lock->ml.cookie != ml->cookie) - lock = NULL; - else + list_for_each(iter, tmpq) { + lock = list_entry(iter, + struct dlm_lock, list); + if (lock->ml.cookie == ml->cookie) break; + lock = NULL; } if (lock) break; @@ -2882,8 +2895,8 @@ int dlm_finalize_reco_handler(struct o2net_msg *msg, u32 len, void *data, BUG(); } dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE; + __dlm_reset_recovery(dlm); spin_unlock(&dlm->spinlock); - dlm_reset_recovery(dlm); dlm_kick_recovery_thread(dlm); break; default: diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 19986959d149..6bd690b5a061 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3144,22 +3144,60 @@ out: return 0; } +static void ocfs2_process_blocked_lock(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres); + /* Mark the lockres as being dropped. It will no longer be * queued if blocking, but we still may have to wait on it * being dequeued from the downconvert thread before we can consider * it safe to drop. * * You can *not* attempt to call cluster_lock on this lockres anymore. */ -void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres) +void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres) { int status; struct ocfs2_mask_waiter mw; - unsigned long flags; + unsigned long flags, flags2; ocfs2_init_mask_waiter(&mw); spin_lock_irqsave(&lockres->l_lock, flags); lockres->l_flags |= OCFS2_LOCK_FREEING; + if (lockres->l_flags & OCFS2_LOCK_QUEUED && current == osb->dc_task) { + /* + * We know the downconvert is queued but not in progress + * because we are the downconvert thread and processing + * different lock. So we can just remove the lock from the + * queue. This is not only an optimization but also a way + * to avoid the following deadlock: + * ocfs2_dentry_post_unlock() + * ocfs2_dentry_lock_put() + * ocfs2_drop_dentry_lock() + * iput() + * ocfs2_evict_inode() + * ocfs2_clear_inode() + * ocfs2_mark_lockres_freeing() + * ... blocks waiting for OCFS2_LOCK_QUEUED + * since we are the downconvert thread which + * should clear the flag. + */ + spin_unlock_irqrestore(&lockres->l_lock, flags); + spin_lock_irqsave(&osb->dc_task_lock, flags2); + list_del_init(&lockres->l_blocked_list); + osb->blocked_lock_count--; + spin_unlock_irqrestore(&osb->dc_task_lock, flags2); + /* + * Warn if we recurse into another post_unlock call. Strictly + * speaking it isn't a problem but we need to be careful if + * that happens (stack overflow, deadlocks, ...) so warn if + * ocfs2 grows a path for which this can happen. + */ + WARN_ON_ONCE(lockres->l_ops->post_unlock); + /* Since the lock is freeing we don't do much in the fn below */ + ocfs2_process_blocked_lock(osb, lockres); + return; + } while (lockres->l_flags & OCFS2_LOCK_QUEUED) { lockres_add_mask_waiter(lockres, &mw, OCFS2_LOCK_QUEUED, 0); spin_unlock_irqrestore(&lockres->l_lock, flags); @@ -3180,7 +3218,7 @@ void ocfs2_simple_drop_lockres(struct ocfs2_super *osb, { int ret; - ocfs2_mark_lockres_freeing(lockres); + ocfs2_mark_lockres_freeing(osb, lockres); ret = ocfs2_drop_lock(osb, lockres); if (ret) mlog_errno(ret); diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 1d596d8c4a4a..d293a22c32c5 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -157,7 +157,8 @@ int ocfs2_refcount_lock(struct ocfs2_refcount_tree *ref_tree, int ex); void ocfs2_refcount_unlock(struct ocfs2_refcount_tree *ref_tree, int ex); -void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres); +void ocfs2_mark_lockres_freeing(struct ocfs2_super *osb, + struct ocfs2_lock_res *lockres); void ocfs2_simple_drop_lockres(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 51632c40e896..ff33c5ef87f2 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -175,9 +175,13 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { int err = 0; - journal_t *journal; struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct ocfs2_inode_info *oi = OCFS2_I(inode); + journal_t *journal = osb->journal->j_journal; + int ret; + tid_t commit_tid; + bool needs_barrier = false; trace_ocfs2_sync_file(inode, file, file->f_path.dentry, OCFS2_I(inode)->ip_blkno, @@ -192,29 +196,19 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, if (err) return err; - /* - * Probably don't need the i_mutex at all in here, just putting it here - * to be consistent with how fsync used to be called, someone more - * familiar with the fs could possibly remove it. - */ - mutex_lock(&inode->i_mutex); - if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) { - /* - * We still have to flush drive's caches to get data to the - * platter - */ - if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); - goto bail; + commit_tid = datasync ? oi->i_datasync_tid : oi->i_sync_tid; + if (journal->j_flags & JBD2_BARRIER && + !jbd2_trans_will_send_data_barrier(journal, commit_tid)) + needs_barrier = true; + err = jbd2_complete_transaction(journal, commit_tid); + if (needs_barrier) { + ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (!err) + err = ret; } - journal = osb->journal->j_journal; - err = jbd2_journal_force_commit(journal); - -bail: if (err) mlog_errno(err); - mutex_unlock(&inode->i_mutex); return (err < 0) ? -EIO : 0; } @@ -292,6 +286,7 @@ int ocfs2_update_inode_atime(struct inode *inode, inode->i_atime = CURRENT_TIME; di->i_atime = cpu_to_le64(inode->i_atime.tv_sec); di->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, bh); out_commit: @@ -341,6 +336,7 @@ int ocfs2_simple_size_update(struct inode *inode, if (ret < 0) mlog_errno(ret); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_commit_trans(osb, handle); out: return ret; @@ -435,6 +431,7 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb, di->i_size = cpu_to_le64(new_i_size); di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec); di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); @@ -650,7 +647,7 @@ restarted_transaction: mlog_errno(status); goto leave; } - + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, bh); spin_lock(&OCFS2_I(inode)->ip_lock); @@ -743,6 +740,7 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) mlog_errno(ret); + ocfs2_update_inode_fsync_trans(handle, inode, 1); out: if (ret) { @@ -840,6 +838,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); di->i_mtime_nsec = di->i_ctime_nsec; ocfs2_journal_dirty(handle, di_bh); + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); } @@ -1344,6 +1343,7 @@ static int __ocfs2_write_remove_suid(struct inode *inode, di = (struct ocfs2_dinode *) bh->b_data; di->i_mode = cpu_to_le16(inode->i_mode); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, bh); @@ -1576,6 +1576,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, if (ret) mlog_errno(ret); } + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_commit_trans(osb, handle); out: @@ -2061,13 +2062,6 @@ out: return ret; } -static void ocfs2_aiodio_wait(struct inode *inode) -{ - wait_queue_head_t *wq = ocfs2_ioend_wq(inode); - - wait_event(*wq, (atomic_read(&OCFS2_I(inode)->ip_unaligned_aio) == 0)); -} - static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) { int blockmask = inode->i_sb->s_blocksize - 1; @@ -2345,10 +2339,8 @@ relock: * Wait on previous unaligned aio to complete before * proceeding. */ - ocfs2_aiodio_wait(inode); - - /* Mark the iocb as needing a decrement in ocfs2_dio_end_io */ - atomic_inc(&OCFS2_I(inode)->ip_unaligned_aio); + mutex_lock(&OCFS2_I(inode)->ip_unaligned_aio); + /* Mark the iocb as needing an unlock in ocfs2_dio_end_io */ ocfs2_iocb_set_unaligned_aio(iocb); } @@ -2428,7 +2420,7 @@ out_dio: if (unaligned_dio) { ocfs2_iocb_clear_unaligned_aio(iocb); - atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio); + mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio); } out: @@ -2645,7 +2637,16 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence) case SEEK_SET: break; case SEEK_END: - offset += inode->i_size; + /* SEEK_END requires the OCFS2 inode lock for the file + * because it references the file's size. + */ + ret = ocfs2_inode_lock(inode, NULL, 0); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + offset += i_size_read(inode); + ocfs2_inode_unlock(inode, 0); break; case SEEK_CUR: if (offset == 0) { diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index f29a90fde619..437de7f768c6 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -130,6 +130,7 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, struct inode *inode = NULL; struct super_block *sb = osb->sb; struct ocfs2_find_inode_args args; + journal_t *journal = OCFS2_SB(sb)->journal->j_journal; trace_ocfs2_iget_begin((unsigned long long)blkno, flags, sysfile_type); @@ -169,6 +170,32 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, goto bail; } + /* + * Set transaction id's of transactions that have to be committed + * to finish f[data]sync. We set them to currently running transaction + * as we cannot be sure that the inode or some of its metadata isn't + * part of the transaction - the inode could have been reclaimed and + * now it is reread from disk. + */ + if (journal) { + transaction_t *transaction; + tid_t tid; + struct ocfs2_inode_info *oi = OCFS2_I(inode); + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction) + transaction = journal->j_running_transaction; + else + transaction = journal->j_committing_transaction; + if (transaction) + tid = transaction->t_tid; + else + tid = journal->j_commit_sequence; + read_unlock(&journal->j_state_lock); + oi->i_sync_tid = tid; + oi->i_datasync_tid = tid; + } + bail: if (!IS_ERR(inode)) { trace_ocfs2_iget_end(inode, @@ -804,11 +831,13 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode) goto bail; } - /* If we're coming from downconvert_thread we can't go into our own - * voting [hello, deadlock city!], so unforuntately we just - * have to skip deleting this guy. That's OK though because - * the node who's doing the actual deleting should handle it - * anyway. */ + /* + * If we're coming from downconvert_thread we can't go into our own + * voting [hello, deadlock city!] so we cannot delete the inode. But + * since we dropped last inode ref when downconverting dentry lock, + * we cannot have the file open and thus the node doing unlink will + * take care of deleting the inode. + */ if (current == osb->dc_task) goto bail; @@ -822,12 +851,6 @@ static int ocfs2_inode_is_valid_to_delete(struct inode *inode) goto bail_unlock; } - /* If we have allowd wipe of this inode for another node, it - * will be marked here so we can safely skip it. Recovery will - * cleanup any inodes we might inadvertently skip here. */ - if (oi->ip_flags & OCFS2_INODE_SKIP_DELETE) - goto bail_unlock; - ret = 1; bail_unlock: spin_unlock(&oi->ip_lock); @@ -941,7 +964,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode, (unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data); if (sync_data) filemap_write_and_wait(inode->i_mapping); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); } static void ocfs2_delete_inode(struct inode *inode) @@ -960,8 +983,6 @@ static void ocfs2_delete_inode(struct inode *inode) if (is_bad_inode(inode) || !OCFS2_I(inode)->ip_blkno) goto bail; - dquot_initialize(inode); - if (!ocfs2_inode_is_valid_to_delete(inode)) { /* It's probably not necessary to truncate_inode_pages * here but we do it for safety anyway (it will most @@ -970,6 +991,8 @@ static void ocfs2_delete_inode(struct inode *inode) goto bail; } + dquot_initialize(inode); + /* We want to block signals in delete_inode as the lock and * messaging paths may return us -ERESTARTSYS. Which would * cause us to exit early, resulting in inodes being orphaned @@ -1057,6 +1080,7 @@ static void ocfs2_clear_inode(struct inode *inode) { int status; struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); clear_inode(inode); trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno, @@ -1073,9 +1097,9 @@ static void ocfs2_clear_inode(struct inode *inode) /* Do these before all the other work so that we don't bounce * the downconvert thread while waiting to destroy the locks. */ - ocfs2_mark_lockres_freeing(&oi->ip_rw_lockres); - ocfs2_mark_lockres_freeing(&oi->ip_inode_lockres); - ocfs2_mark_lockres_freeing(&oi->ip_open_lockres); + ocfs2_mark_lockres_freeing(osb, &oi->ip_rw_lockres); + ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres); + ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres); ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap, &oi->ip_la_data_resv); @@ -1157,7 +1181,7 @@ void ocfs2_evict_inode(struct inode *inode) (OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) { ocfs2_delete_inode(inode); } else { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); } ocfs2_clear_inode(inode); } @@ -1260,6 +1284,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle, fe->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); ocfs2_journal_dirty(handle, bh); + ocfs2_update_inode_fsync_trans(handle, inode, 1); leave: return status; } diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 621fc73bf23d..a6c991c0fc98 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -44,7 +44,7 @@ struct ocfs2_inode_info struct rw_semaphore ip_xattr_sem; /* Number of outstanding AIO's which are not page aligned */ - atomic_t ip_unaligned_aio; + struct mutex ip_unaligned_aio; /* These fields are protected by ip_lock */ spinlock_t ip_lock; @@ -73,6 +73,13 @@ struct ocfs2_inode_info u32 ip_dir_lock_gen; struct ocfs2_alloc_reservation ip_la_data_resv; + + /* + * Transactions that contain inode's metadata needed to complete + * fsync and fdatasync, respectively. + */ + tid_t i_sync_tid; + tid_t i_datasync_tid; }; /* @@ -84,8 +91,6 @@ struct ocfs2_inode_info #define OCFS2_INODE_BITMAP 0x00000004 /* This inode has been wiped from disk */ #define OCFS2_INODE_DELETED 0x00000008 -/* Another node is deleting, so our delete is a nop */ -#define OCFS2_INODE_SKIP_DELETE 0x00000010 /* Has the inode been orphaned on another node? * * This hints to ocfs2_drop_inode that it should clear i_nlink before @@ -100,11 +105,11 @@ struct ocfs2_inode_info * rely on ocfs2_delete_inode to sort things out under the proper * cluster locks. */ -#define OCFS2_INODE_MAYBE_ORPHANED 0x00000020 +#define OCFS2_INODE_MAYBE_ORPHANED 0x00000010 /* Does someone have the file open O_DIRECT */ -#define OCFS2_INODE_OPEN_DIRECT 0x00000040 +#define OCFS2_INODE_OPEN_DIRECT 0x00000020 /* Tell the inode wipe code it's not in orphan dir */ -#define OCFS2_INODE_SKIP_ORPHAN_DIR 0x00000080 +#define OCFS2_INODE_SKIP_ORPHAN_DIR 0x00000040 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode) { diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 8ca3c29accbf..490229f43731 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -413,11 +413,12 @@ int ocfs2_info_handle_freeinode(struct inode *inode, } status = ocfs2_info_scan_inode_alloc(osb, inode_alloc, blkno, oifi, i); - if (status < 0) - goto bail; iput(inode_alloc); inode_alloc = NULL; + + if (status < 0) + goto bail; } o2info_set_request_filled(&oifi->ifi_req); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 44fc3e530c3d..03ea9314fecd 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -2132,12 +2132,6 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb, iter = oi->ip_next_orphan; spin_lock(&oi->ip_lock); - /* The remote delete code may have set these on the - * assumption that the other node would wipe them - * successfully. If they are still in the node's - * orphan dir, we need to reset that state. */ - oi->ip_flags &= ~(OCFS2_INODE_DELETED|OCFS2_INODE_SKIP_DELETE); - /* Set the proper information to get us going into * ocfs2_delete_inode. */ oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED; diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 9ff4e8cf9d97..7f8cde94abfe 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -626,4 +626,15 @@ static inline int ocfs2_begin_ordered_truncate(struct inode *inode, new_size); } +static inline void ocfs2_update_inode_fsync_trans(handle_t *handle, + struct inode *inode, + int datasync) +{ + struct ocfs2_inode_info *oi = OCFS2_I(inode); + + oi->i_sync_tid = handle->h_transaction->t_tid; + if (datasync) + oi->i_datasync_tid = handle->h_transaction->t_tid; +} + #endif /* OCFS2_JOURNAL_H */ diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index e57c804069ea..6b6d092b0998 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -82,6 +82,8 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, } ret = flock_lock_file_wait(file, fl); + if (ret) + ocfs2_file_unlock(file); out: mutex_unlock(&fp->fp_mutex); diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 64c304d668f0..599eb4c4c8be 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -151,6 +151,7 @@ static int __ocfs2_move_extent(handle_t *handle, old_blkno, len); } + ocfs2_update_inode_fsync_trans(handle, inode, 0); out: ocfs2_free_path(path); return ret; @@ -690,8 +691,11 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh, goal_bit, len); - if (ret) + if (ret) { + ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len, + le16_to_cpu(gd->bg_chain)); mlog_errno(ret); + } /* * Here we should write the new page out first if we are @@ -957,6 +961,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context) inode->i_ctime = CURRENT_TIME; di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3683643f3f0e..2060fc398445 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -450,7 +450,6 @@ leave: brelse(new_fe_bh); brelse(parent_fe_bh); - kfree(si.name); kfree(si.value); ocfs2_free_dir_lookup_result(&lookup); @@ -495,6 +494,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, struct ocfs2_dinode *fe = NULL; struct ocfs2_extent_list *fel; u16 feat; + struct ocfs2_inode_info *oi = OCFS2_I(inode); *new_fe_bh = NULL; @@ -576,8 +576,8 @@ static int __ocfs2_mknod_locked(struct inode *dir, mlog_errno(status); } - status = 0; /* error in ocfs2_create_new_inode_locks is not - * critical */ + oi->i_sync_tid = handle->h_transaction->t_tid; + oi->i_datasync_tid = handle->h_transaction->t_tid; leave: if (status < 0) { @@ -1855,7 +1855,6 @@ bail: brelse(new_fe_bh); brelse(parent_fe_bh); - kfree(si.name); kfree(si.value); ocfs2_free_dir_lookup_result(&lookup); if (inode_ac) @@ -2481,6 +2480,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir, di->i_orphaned_slot = 0; set_nlink(inode, 1); ocfs2_set_links_count(di, inode->i_nlink); + ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, di_bh); status = ocfs2_add_entry(handle, dentry, inode, diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 553f53cc73ae..8d64a97a9d5e 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -30,6 +30,7 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/list.h> +#include <linux/llist.h> #include <linux/rbtree.h> #include <linux/workqueue.h> #include <linux/kref.h> @@ -274,19 +275,16 @@ enum ocfs2_mount_options OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */ }; -#define OCFS2_OSB_SOFT_RO 0x0001 -#define OCFS2_OSB_HARD_RO 0x0002 -#define OCFS2_OSB_ERROR_FS 0x0004 -#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED 0x0008 - -#define OCFS2_DEFAULT_ATIME_QUANTUM 60 +#define OCFS2_OSB_SOFT_RO 0x0001 +#define OCFS2_OSB_HARD_RO 0x0002 +#define OCFS2_OSB_ERROR_FS 0x0004 +#define OCFS2_DEFAULT_ATIME_QUANTUM 60 struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; struct ocfs2_replay_map; struct ocfs2_quota_recovery; -struct ocfs2_dentry_lock; struct ocfs2_super { struct task_struct *commit_task; @@ -414,10 +412,9 @@ struct ocfs2_super struct list_head blocked_lock_list; unsigned long blocked_lock_count; - /* List of dentry locks to release. Anyone can add locks to - * the list, ocfs2_wq processes the list */ - struct ocfs2_dentry_lock *dentry_lock_list; - struct work_struct dentry_lock_work; + /* List of dquot structures to drop last reference to */ + struct llist_head dquot_drop_list; + struct work_struct dquot_drop_work; wait_queue_head_t osb_mount_event; @@ -449,6 +446,8 @@ struct ocfs2_super /* rb tree root for refcount lock. */ struct rb_root osb_rf_lock_tree; struct ocfs2_refcount_tree *osb_ref_tree_lru; + + struct mutex system_file_mutex; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) @@ -579,18 +578,6 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb, spin_unlock(&osb->osb_lock); } - -static inline unsigned long ocfs2_test_osb_flag(struct ocfs2_super *osb, - unsigned long flag) -{ - unsigned long ret; - - spin_lock(&osb->osb_lock); - ret = osb->osb_flags & flag; - spin_unlock(&osb->osb_lock); - return ret; -} - static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb, int hard) { diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index d5ab56cbe5c5..f266d67df3c6 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -28,6 +28,7 @@ struct ocfs2_dquot { unsigned int dq_use_count; /* Number of nodes having reference to this entry in global quota file */ s64 dq_origspace; /* Last globally synced space usage */ s64 dq_originodes; /* Last globally synced inode usage */ + struct llist_node list; /* Member of list of dquots to drop */ }; /* Description of one chunk to recover in memory */ @@ -110,6 +111,7 @@ int ocfs2_read_quota_phys_block(struct inode *inode, u64 p_block, int ocfs2_create_local_dquot(struct dquot *dquot); int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot); int ocfs2_local_write_dquot(struct dquot *dquot); +void ocfs2_drop_dquot_refs(struct work_struct *work); extern const struct dquot_operations ocfs2_quota_operations; extern struct quota_format_type ocfs2_quota_format; diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index d7b5108789e2..b990a62cff50 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -10,6 +10,7 @@ #include <linux/jiffies.h> #include <linux/writeback.h> #include <linux/workqueue.h> +#include <linux/llist.h> #include <cluster/masklog.h> @@ -679,6 +680,27 @@ static int ocfs2_calc_qdel_credits(struct super_block *sb, int type) OCFS2_INODE_UPDATE_CREDITS; } +void ocfs2_drop_dquot_refs(struct work_struct *work) +{ + struct ocfs2_super *osb = container_of(work, struct ocfs2_super, + dquot_drop_work); + struct llist_node *list; + struct ocfs2_dquot *odquot, *next_odquot; + + list = llist_del_all(&osb->dquot_drop_list); + llist_for_each_entry_safe(odquot, next_odquot, list, list) { + /* Drop the reference we acquired in ocfs2_dquot_release() */ + dqput(&odquot->dq_dquot); + } +} + +/* + * Called when the last reference to dquot is dropped. If we are called from + * downconvert thread, we cannot do all the handling here because grabbing + * quota lock could deadlock (the node holding the quota lock could need some + * other cluster lock to proceed but with blocked downconvert thread we cannot + * release any lock). + */ static int ocfs2_release_dquot(struct dquot *dquot) { handle_t *handle; @@ -694,6 +716,19 @@ static int ocfs2_release_dquot(struct dquot *dquot) /* Check whether we are not racing with some other dqget() */ if (atomic_read(&dquot->dq_count) > 1) goto out; + /* Running from downconvert thread? Postpone quota processing to wq */ + if (current == osb->dc_task) { + /* + * Grab our own reference to dquot and queue it for delayed + * dropping. Quota code rechecks after calling + * ->release_dquot() and won't free dquot structure. + */ + dqgrab(dquot); + /* First entry on list -> queue work */ + if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list)) + queue_work(ocfs2_wq, &osb->dquot_drop_work); + goto out; + } status = ocfs2_lock_global_qf(oinfo, 1); if (status < 0) goto out; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index ca5ce14cbddc..5c8343fe7438 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -603,11 +603,25 @@ static struct kobj_attribute ocfs2_attr_cluster_stack = ocfs2_cluster_stack_show, ocfs2_cluster_stack_store); + + +static ssize_t ocfs2_dlm_recover_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "1\n"); +} + +static struct kobj_attribute ocfs2_attr_dlm_recover_support = + __ATTR(dlm_recover_callback_support, S_IRUGO, + ocfs2_dlm_recover_show, NULL); + static struct attribute *ocfs2_attrs[] = { &ocfs2_attr_max_locking_protocol.attr, &ocfs2_attr_loaded_cluster_plugins.attr, &ocfs2_attr_active_cluster_plugin.attr, &ocfs2_attr_cluster_stack.attr, + &ocfs2_attr_dlm_recover_support.attr, NULL, }; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 47ae2663a6f5..0cb889a17ae1 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -771,6 +771,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, spin_unlock(&OCFS2_I(alloc_inode)->ip_lock); i_size_write(alloc_inode, le64_to_cpu(fe->i_size)); alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode); + ocfs2_update_inode_fsync_trans(handle, alloc_inode, 0); status = 0; @@ -1607,6 +1608,21 @@ out: return ret; } +void ocfs2_rollback_alloc_dinode_counts(struct inode *inode, + struct buffer_head *di_bh, + u32 num_bits, + u16 chain) +{ + u32 tmp_used; + struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data; + struct ocfs2_chain_list *cl; + + cl = (struct ocfs2_chain_list *)&di->id2.i_chain; + tmp_used = le32_to_cpu(di->id1.bitmap1.i_used); + di->id1.bitmap1.i_used = cpu_to_le32(tmp_used - num_bits); + le32_add_cpu(&cl->cl_recs[chain].c_free, num_bits); +} + static int ocfs2_bg_discontig_fix_by_rec(struct ocfs2_suballoc_result *res, struct ocfs2_extent_rec *rec, struct ocfs2_chain_list *cl) @@ -1707,8 +1723,12 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac, ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh, res->sr_bit_offset, res->sr_bits); - if (ret < 0) + if (ret < 0) { + ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh, + res->sr_bits, + le16_to_cpu(gd->bg_chain)); mlog_errno(ret); + } out_loc_only: *bits_left = le16_to_cpu(gd->bg_free_bits_count); @@ -1838,6 +1858,8 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, res->sr_bit_offset, res->sr_bits); if (status < 0) { + ocfs2_rollback_alloc_dinode_counts(alloc_inode, + ac->ac_bh, res->sr_bits, chain); mlog_errno(status); goto bail; } @@ -2091,7 +2113,7 @@ int ocfs2_find_new_inode_loc(struct inode *dir, ac->ac_find_loc_priv = res; *fe_blkno = res->sr_blkno; - + ocfs2_update_inode_fsync_trans(handle, dir, 0); out: if (handle) ocfs2_commit_trans(OCFS2_SB(dir->i_sb), handle); @@ -2149,6 +2171,8 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle, res->sr_bit_offset, res->sr_bits); if (ret < 0) { + ocfs2_rollback_alloc_dinode_counts(ac->ac_inode, + ac->ac_bh, res->sr_bits, chain); mlog_errno(ret); goto out; } @@ -2870,6 +2894,7 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res) status = ocfs2_inode_lock(inode_alloc_inode, &alloc_bh, 0); if (status < 0) { mutex_unlock(&inode_alloc_inode->i_mutex); + iput(inode_alloc_inode); mlog(ML_ERROR, "lock on alloc inode on slot %u failed %d\n", (u32)suballoc_slot, status); goto bail; diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index 218d8036b3e7..2d2501767c0c 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -91,6 +91,10 @@ int ocfs2_alloc_dinode_update_counts(struct inode *inode, struct buffer_head *di_bh, u32 num_bits, u16 chain); +void ocfs2_rollback_alloc_dinode_counts(struct inode *inode, + struct buffer_head *di_bh, + u32 num_bits, + u16 chain); int ocfs2_block_group_set_bits(handle_t *handle, struct inode *alloc_inode, struct ocfs2_group_desc *bg, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 49d84f80f36c..1aecd626e645 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -561,6 +561,9 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb) if (!oi) return NULL; + oi->i_sync_tid = 0; + oi->i_datasync_tid = 0; + jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode); return &oi->vfs_inode; } @@ -1238,30 +1241,11 @@ static struct dentry *ocfs2_mount(struct file_system_type *fs_type, return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super); } -static void ocfs2_kill_sb(struct super_block *sb) -{ - struct ocfs2_super *osb = OCFS2_SB(sb); - - /* Failed mount? */ - if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED) - goto out; - - /* Prevent further queueing of inode drop events */ - spin_lock(&dentry_list_lock); - ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED); - spin_unlock(&dentry_list_lock); - /* Wait for work to finish and/or remove it */ - cancel_work_sync(&osb->dentry_lock_work); -out: - kill_block_super(sb); -} - static struct file_system_type ocfs2_fs_type = { .owner = THIS_MODULE, .name = "ocfs2", .mount = ocfs2_mount, - .kill_sb = ocfs2_kill_sb, - + .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE, .next = NULL }; @@ -1612,14 +1596,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root) return 0; } -wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ]; - static int __init ocfs2_init(void) { - int status, i; - - for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++) - init_waitqueue_head(&ocfs2__ioend_wq[i]); + int status; status = init_ocfs2_uptodate_cache(); if (status < 0) @@ -1761,7 +1740,7 @@ static void ocfs2_inode_init_once(void *data) ocfs2_extent_map_init(&oi->vfs_inode); INIT_LIST_HEAD(&oi->ip_io_markers); oi->ip_dir_start_lookup = 0; - atomic_set(&oi->ip_unaligned_aio, 0); + mutex_init(&oi->ip_unaligned_aio); init_rwsem(&oi->ip_alloc_sem); init_rwsem(&oi->ip_xattr_sem); mutex_init(&oi->ip_io_mutex); @@ -1932,17 +1911,16 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) debugfs_remove(osb->osb_ctxt); - /* - * Flush inode dropping work queue so that deletes are - * performed while the filesystem is still working - */ - ocfs2_drop_all_dl_inodes(osb); - /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); ocfs2_disable_quotas(osb); + /* All dquots should be freed by now */ + WARN_ON(!llist_empty(&osb->dquot_drop_list)); + /* Wait for worker to be done with the work structure in osb */ + cancel_work_sync(&osb->dquot_drop_work); + ocfs2_shutdown_local_alloc(osb); /* This will disable recovery and flush any recovery work. */ @@ -2077,7 +2055,6 @@ static int ocfs2_initialize_super(struct super_block *sb, struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data; struct inode *inode = NULL; struct ocfs2_journal *journal; - __le32 uuid_net_key; struct ocfs2_super *osb; u64 total_blocks; @@ -2123,6 +2100,8 @@ static int ocfs2_initialize_super(struct super_block *sb, spin_lock_init(&osb->osb_xattr_lock); ocfs2_init_steal_slots(osb); + mutex_init(&osb->system_file_mutex); + atomic_set(&osb->alloc_stats.moves, 0); atomic_set(&osb->alloc_stats.local_data, 0); atomic_set(&osb->alloc_stats.bitmap_data, 0); @@ -2276,8 +2255,8 @@ static int ocfs2_initialize_super(struct super_block *sb, INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery); journal->j_state = OCFS2_JOURNAL_FREE; - INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes); - osb->dentry_lock_list = NULL; + INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs); + init_llist_head(&osb->dquot_drop_list); /* get some pseudo constants for clustersize bits */ osb->s_clustersize_bits = @@ -2311,8 +2290,6 @@ static int ocfs2_initialize_super(struct super_block *sb, goto bail; } - memcpy(&uuid_net_key, di->id2.i_super.s_uuid, sizeof(uuid_net_key)); - strncpy(osb->vol_label, di->id2.i_super.s_label, 63); osb->vol_label[63] = '\0'; osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno); diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c index f053688d22a3..af155c183123 100644 --- a/fs/ocfs2/sysfile.c +++ b/fs/ocfs2/sysfile.c @@ -113,9 +113,11 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb, } else arr = get_local_system_inode(osb, type, slot); + mutex_lock(&osb->system_file_mutex); if (arr && ((inode = *arr) != NULL)) { /* get a ref in addition to the array ref */ inode = igrab(inode); + mutex_unlock(&osb->system_file_mutex); BUG_ON(!inode); return inode; @@ -129,6 +131,7 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb, *arr = igrab(inode); BUG_ON(!*arr); } + mutex_unlock(&osb->system_file_mutex); return inode; } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 185fa3b7f962..016f01df3825 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -369,7 +369,7 @@ static void ocfs2_xattr_bucket_free(struct ocfs2_xattr_bucket *bucket) * them fully. */ static int ocfs2_init_xattr_bucket(struct ocfs2_xattr_bucket *bucket, - u64 xb_blkno) + u64 xb_blkno, int new) { int i, rc = 0; @@ -383,9 +383,16 @@ static int ocfs2_init_xattr_bucket(struct ocfs2_xattr_bucket *bucket, } if (!ocfs2_buffer_uptodate(INODE_CACHE(bucket->bu_inode), - bucket->bu_bhs[i])) - ocfs2_set_new_buffer_uptodate(INODE_CACHE(bucket->bu_inode), - bucket->bu_bhs[i]); + bucket->bu_bhs[i])) { + if (new) + ocfs2_set_new_buffer_uptodate(INODE_CACHE(bucket->bu_inode), + bucket->bu_bhs[i]); + else { + set_buffer_uptodate(bucket->bu_bhs[i]); + ocfs2_set_buffer_uptodate(INODE_CACHE(bucket->bu_inode), + bucket->bu_bhs[i]); + } + } } if (rc) @@ -2602,6 +2609,7 @@ int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh) oi->ip_dyn_features &= ~(OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL); di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); spin_unlock(&oi->ip_lock); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, di_bh); out_commit: @@ -3200,8 +3208,15 @@ meta_guess: clusters_add += 1; } } else { - meta_add += 1; credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS; + if (xi->xi_value_len > OCFS2_XATTR_INLINE_SIZE) { + struct ocfs2_extent_list *el = &def_xv.xv.xr_list; + meta_add += ocfs2_extend_meta_needed(el); + credits += ocfs2_calc_extend_credits(inode->i_sb, + el); + } else { + meta_add += 1; + } } out: if (clusters_need) @@ -3614,6 +3629,7 @@ int ocfs2_xattr_set(struct inode *inode, } ret = __ocfs2_xattr_set_handle(inode, di, &xi, &xis, &xbs, &ctxt); + ocfs2_update_inode_fsync_trans(ctxt.handle, inode, 0); ocfs2_commit_trans(osb, ctxt.handle); @@ -4294,7 +4310,7 @@ static int ocfs2_xattr_create_index_block(struct inode *inode, trace_ocfs2_xattr_create_index_block((unsigned long long)blkno); - ret = ocfs2_init_xattr_bucket(xs->bucket, blkno); + ret = ocfs2_init_xattr_bucket(xs->bucket, blkno, 1); if (ret) { mlog_errno(ret); goto out; @@ -4638,7 +4654,7 @@ static int ocfs2_divide_xattr_bucket(struct inode *inode, * Even if !new_bucket_head, we're overwriting t_bucket. Thus, * there's no need to read it. */ - ret = ocfs2_init_xattr_bucket(t_bucket, new_blk); + ret = ocfs2_init_xattr_bucket(t_bucket, new_blk, new_bucket_head); if (ret) { mlog_errno(ret); goto out; @@ -4804,7 +4820,7 @@ static int ocfs2_cp_xattr_bucket(struct inode *inode, * Even if !t_is_new, we're overwriting t_bucket. Thus, * there's no need to read it. */ - ret = ocfs2_init_xattr_bucket(t_bucket, t_blkno); + ret = ocfs2_init_xattr_bucket(t_bucket, t_blkno, t_is_new); if (ret) goto out; @@ -5476,6 +5492,7 @@ static int ocfs2_rm_xattr_cluster(struct inode *inode, ret = ocfs2_truncate_log_append(osb, handle, blkno, len); if (ret) mlog_errno(ret); + ocfs2_update_inode_fsync_trans(handle, inode, 0); out_commit: ocfs2_commit_trans(osb, handle); @@ -6830,7 +6847,7 @@ static int ocfs2_reflink_xattr_bucket(handle_t *handle, break; } - ret = ocfs2_init_xattr_bucket(args->new_bucket, new_blkno); + ret = ocfs2_init_xattr_bucket(args->new_bucket, new_blkno, 1); if (ret) { mlog_errno(ret); break; diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index d8b0afde2179..ec58c7659183 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -183,7 +183,7 @@ int omfs_sync_inode(struct inode *inode) */ static void omfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_nlink) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 124fc43c7090..8f20e3404fd2 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -35,7 +35,7 @@ static void proc_evict_inode(struct inode *inode) const struct proc_ns_operations *ns_ops; void *ns; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Stop tracking associated processes */ diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index cfc8dcc16043..9cd5f63715c0 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -528,7 +528,7 @@ restart: if (atomic_read(&dquot->dq_count)) { DEFINE_WAIT(wait); - atomic_inc(&dquot->dq_count); + dqgrab(dquot); prepare_to_wait(&dquot->dq_wait_unused, &wait, TASK_UNINTERRUPTIBLE); spin_unlock(&dq_list_lock); @@ -632,7 +632,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type) /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ - atomic_inc(&dquot->dq_count); + dqgrab(dquot); spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); err = sb->dq_op->write_dquot(dquot); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index ad62bdbb451e..bc8b8009897d 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -35,7 +35,7 @@ void reiserfs_evict_inode(struct inode *inode) if (!inode->i_nlink && !is_bad_inode(inode)) dquot_initialize(inode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (inode->i_nlink) goto no_delete; diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 8d06adf89948..83d4eac8059a 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -2831,6 +2831,7 @@ void reiserfs_init_alloc_options(struct super_block *s); */ __le32 reiserfs_choose_packing(struct inode *dir); +void show_alloc_options(struct seq_file *seq, struct super_block *s); int reiserfs_init_bitmap_cache(struct super_block *sb); void reiserfs_free_bitmap_cache(struct super_block *sb); void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 2c803353f8ac..ed54a04c33bd 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -62,7 +62,6 @@ static int is_any_reiserfs_magic_string(struct reiserfs_super_block *rs) static int reiserfs_remount(struct super_block *s, int *flags, char *data); static int reiserfs_statfs(struct dentry *dentry, struct kstatfs *buf); -void show_alloc_options(struct seq_file *seq, struct super_block *s); static int reiserfs_sync_fs(struct super_block *s, int wait) { @@ -597,7 +596,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -static int init_inodecache(void) +static int __init init_inodecache(void) { reiserfs_inode_cachep = kmem_cache_create("reiser_inode_cache", sizeof(struct diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index c327d4ee1235..5625ca920f5e 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -295,7 +295,7 @@ int sysv_sync_inode(struct inode *inode) static void sysv_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; sysv_truncate(inode); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5ded8490c0c6..48f943f7f5d5 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -351,7 +351,7 @@ static void ubifs_evict_inode(struct inode *inode) dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode); ubifs_assert(!atomic_read(&inode->i_count)); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (inode->i_nlink) goto done; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 982ce05c87ed..5d643706212f 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -146,8 +146,8 @@ void udf_evict_inode(struct inode *inode) want_delete = 1; udf_setsize(inode, 0); udf_update_inode(inode, IS_SYNC(inode)); - } else - truncate_inode_pages(&inode->i_data, 0); + } + truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index c8ca96086784..61e8a9b021dd 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -885,7 +885,7 @@ void ufs_evict_inode(struct inode * inode) if (!inode->i_nlink && !is_bad_inode(inode)) want_delete = 1; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (want_delete) { loff_t old_i_size; /*UFS_I(inode)->i_dtime = CURRENT_TIME;*/ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d971f4932b5d..0ef599218991 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -996,7 +996,7 @@ xfs_fs_evict_inode( trace_xfs_evict_inode(ip); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); XFS_STATS_INC(vn_rele); XFS_STATS_INC(vn_remove); |