diff options
Diffstat (limited to 'fs')
37 files changed, 300 insertions, 208 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 3c3abff731a7..e4e57d59edb7 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1036,11 +1036,13 @@ out: * on error we return an unlocked page and the error value * on success we return a locked page and 0 */ -static int prepare_uptodate_page(struct page *page, u64 pos) +static int prepare_uptodate_page(struct page *page, u64 pos, + bool force_uptodate) { int ret = 0; - if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) { + if (((pos & (PAGE_CACHE_SIZE - 1)) || force_uptodate) && + !PageUptodate(page)) { ret = btrfs_readpage(NULL, page); if (ret) return ret; @@ -1061,7 +1063,7 @@ static int prepare_uptodate_page(struct page *page, u64 pos) static noinline int prepare_pages(struct btrfs_root *root, struct file *file, struct page **pages, size_t num_pages, loff_t pos, unsigned long first_index, - size_t write_bytes) + size_t write_bytes, bool force_uptodate) { struct extent_state *cached_state = NULL; int i; @@ -1086,10 +1088,11 @@ again: } if (i == 0) - err = prepare_uptodate_page(pages[i], pos); + err = prepare_uptodate_page(pages[i], pos, + force_uptodate); if (i == num_pages - 1) err = prepare_uptodate_page(pages[i], - pos + write_bytes); + pos + write_bytes, false); if (err) { page_cache_release(pages[i]); faili = i - 1; @@ -1158,6 +1161,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, size_t num_written = 0; int nrptrs; int ret = 0; + bool force_page_uptodate = false; nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) / PAGE_CACHE_SIZE, PAGE_CACHE_SIZE / @@ -1200,7 +1204,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, * contents of pages from loop to loop */ ret = prepare_pages(root, file, pages, num_pages, - pos, first_index, write_bytes); + pos, first_index, write_bytes, + force_page_uptodate); if (ret) { btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT); @@ -1217,12 +1222,15 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, if (copied < write_bytes) nrptrs = 1; - if (copied == 0) + if (copied == 0) { + force_page_uptodate = true; dirty_pages = 0; - else + } else { + force_page_uptodate = false; dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + } /* * If we had a short copy we need to release the excess delaloc @@ -1817,6 +1825,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) goto out; case SEEK_DATA: case SEEK_HOLE: + if (offset >= i_size_read(inode)) { + mutex_unlock(&inode->i_mutex); + return -ENXIO; + } + ret = find_desired_extent(inode, &offset, origin); if (ret) { mutex_unlock(&inode->i_mutex); @@ -1825,11 +1838,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) } if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) { - ret = -EINVAL; + offset = -EINVAL; goto out; } if (offset > inode->i_sb->s_maxbytes) { - ret = -EINVAL; + offset = -EINVAL; goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4d14de6d121b..b2d004ad66a0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4018,7 +4018,8 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) memcpy(&location, dentry->d_fsdata, sizeof(struct btrfs_key)); kfree(dentry->d_fsdata); dentry->d_fsdata = NULL; - d_clear_need_lookup(dentry); + /* This thing is hashed, drop it for now */ + d_drop(dentry); } else { ret = btrfs_inode_by_name(dir, dentry, &location); } @@ -4085,7 +4086,15 @@ static void btrfs_dentry_release(struct dentry *dentry) static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { - return d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry); + struct dentry *ret; + + ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry); + if (unlikely(d_need_lookup(dentry))) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_NEED_LOOKUP; + spin_unlock(&dentry->d_lock); + } + return ret; } unsigned char btrfs_filetype_table[] = { @@ -4125,7 +4134,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, /* special case for "." */ if (filp->f_pos == 0) { - over = filldir(dirent, ".", 1, 1, btrfs_ino(inode), DT_DIR); + over = filldir(dirent, ".", 1, + filp->f_pos, btrfs_ino(inode), DT_DIR); if (over) return 0; filp->f_pos = 1; @@ -4134,7 +4144,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, if (filp->f_pos == 1) { u64 pino = parent_ino(filp->f_path.dentry); over = filldir(dirent, "..", 2, - 2, pino, DT_DIR); + filp->f_pos, pino, DT_DIR); if (over) return 0; filp->f_pos = 2; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3351b1b24574..dae5dfe41ba5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1047,7 +1047,16 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (!max_to_defrag) max_to_defrag = last_index - 1; - while (i <= last_index && defrag_count < max_to_defrag) { + /* + * make writeback starts from i, so the defrag range can be + * written sequentially. + */ + if (i < inode->i_mapping->writeback_index) + inode->i_mapping->writeback_index = i; + + while (i <= last_index && defrag_count < max_to_defrag && + (i < (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT)) { /* * make sure we stop running if someone unmounts * the FS @@ -2177,6 +2186,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (!(src_file->f_mode & FMODE_READ)) goto out_fput; + /* don't make the dst file partly checksummed */ + if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != + (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) + goto out_fput; + ret = -EISDIR; if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode)) goto out_fput; @@ -2226,6 +2240,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, goto out_unlock; } + /* truncate page cache pages from target inode range */ + truncate_inode_pages_range(&inode->i_data, destoff, + PAGE_CACHE_ALIGN(destoff + len) - 1); + /* do any pending delalloc/csum calc on src, one way or another, and lock file content */ while (1) { @@ -2242,10 +2260,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, btrfs_wait_ordered_range(src, off, len); } - /* truncate page cache pages from target inode range */ - truncate_inode_pages_range(&inode->i_data, off, - ALIGN(off + len, PAGE_CACHE_SIZE) - 1); - /* clone data */ key.objectid = btrfs_ino(src); key.type = BTRFS_EXTENT_DATA_KEY; @@ -2323,7 +2337,12 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, else new_key.offset = destoff; - trans = btrfs_start_transaction(root, 1); + /* + * 1 - adjusting old extent (we may have to split it) + * 1 - add new extent + * 1 - inode update + */ + trans = btrfs_start_transaction(root, 3); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out; @@ -2442,7 +2461,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (endoff > inode->i_size) btrfs_i_size_write(inode, endoff); - BTRFS_I(inode)->flags = BTRFS_I(src)->flags; ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); btrfs_end_transaction(trans, root); diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index e76bfeb68267..30acd22147e1 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -351,9 +351,7 @@ static int build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp) { unsigned int dlen; - unsigned int wlen; - unsigned int size = 6 * sizeof(struct ntlmssp2_name); - __le64 curtime; + unsigned int size = 2 * sizeof(struct ntlmssp2_name); char *defdmname = "WORKGROUP"; unsigned char *blobptr; struct ntlmssp2_name *attrptr; @@ -365,15 +363,14 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp) } dlen = strlen(ses->domainName); - wlen = strlen(ses->server->hostname); - /* The length of this blob is a size which is - * six times the size of a structure which holds name/size + - * two times the unicode length of a domain name + - * two times the unicode length of a server name + - * size of a timestamp (which is 8 bytes). + /* + * The length of this blob is two times the size of a + * structure (av pair) which holds name/size + * ( for NTLMSSP_AV_NB_DOMAIN_NAME followed by NTLMSSP_AV_EOL ) + + * unicode length of a netbios domain name */ - ses->auth_key.len = size + 2 * (2 * dlen) + 2 * (2 * wlen) + 8; + ses->auth_key.len = size + 2 * dlen; ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL); if (!ses->auth_key.response) { ses->auth_key.len = 0; @@ -384,44 +381,15 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp) blobptr = ses->auth_key.response; attrptr = (struct ntlmssp2_name *) blobptr; + /* + * As defined in MS-NTLM 3.3.2, just this av pair field + * is sufficient as part of the temp + */ attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_DOMAIN_NAME); attrptr->length = cpu_to_le16(2 * dlen); blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp); - blobptr += 2 * dlen; - attrptr = (struct ntlmssp2_name *) blobptr; - - attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_COMPUTER_NAME); - attrptr->length = cpu_to_le16(2 * wlen); - blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); - cifs_strtoUCS((__le16 *)blobptr, ses->server->hostname, wlen, nls_cp); - - blobptr += 2 * wlen; - attrptr = (struct ntlmssp2_name *) blobptr; - - attrptr->type = cpu_to_le16(NTLMSSP_AV_DNS_DOMAIN_NAME); - attrptr->length = cpu_to_le16(2 * dlen); - blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); - cifs_strtoUCS((__le16 *)blobptr, ses->domainName, dlen, nls_cp); - - blobptr += 2 * dlen; - attrptr = (struct ntlmssp2_name *) blobptr; - - attrptr->type = cpu_to_le16(NTLMSSP_AV_DNS_COMPUTER_NAME); - attrptr->length = cpu_to_le16(2 * wlen); - blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); - cifs_strtoUCS((__le16 *)blobptr, ses->server->hostname, wlen, nls_cp); - - blobptr += 2 * wlen; - attrptr = (struct ntlmssp2_name *) blobptr; - - attrptr->type = cpu_to_le16(NTLMSSP_AV_TIMESTAMP); - attrptr->length = cpu_to_le16(sizeof(__le64)); - blobptr = (unsigned char *)attrptr + sizeof(struct ntlmssp2_name); - curtime = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); - memcpy(blobptr, &curtime, sizeof(__le64)); - return 0; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f93eb948d071..54b8f1e7da94 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -548,6 +548,12 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) struct inode *dir = dentry->d_inode; struct dentry *child; + if (!dir) { + dput(dentry); + dentry = ERR_PTR(-ENOENT); + break; + } + /* skip separators */ while (*s == sep) s++; @@ -563,10 +569,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) mutex_unlock(&dir->i_mutex); dput(dentry); dentry = child; - if (!dentry->d_inode) { - dput(dentry); - dentry = ERR_PTR(-ENOENT); - } } while (!IS_ERR(dentry)); _FreeXid(xid); kfree(full_path); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index aac37d99a487..a80f7bd97b90 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4079,7 +4079,8 @@ int CIFSFindNext(const int xid, struct cifs_tcon *tcon, T2_FNEXT_RSP_PARMS *parms; char *response_data; int rc = 0; - int bytes_returned, name_len; + int bytes_returned; + unsigned int name_len; __u16 params, byte_count; cFYI(1, "In FindNext"); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 633c246b6775..71beb0201970 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1298,7 +1298,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, /* ignore */ } else if (strnicmp(data, "guest", 5) == 0) { /* ignore */ - } else if (strnicmp(data, "rw", 2) == 0) { + } else if (strnicmp(data, "rw", 2) == 0 && strlen(data) == 2) { /* ignore */ } else if (strnicmp(data, "ro", 2) == 0) { /* ignore */ @@ -1401,7 +1401,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->server_ino = 1; } else if (strnicmp(data, "noserverino", 9) == 0) { vol->server_ino = 0; - } else if (strnicmp(data, "rwpidforward", 4) == 0) { + } else if (strnicmp(data, "rwpidforward", 12) == 0) { vol->rwpidforward = 1; } else if (strnicmp(data, "cifsacl", 7) == 0) { vol->cifs_acl = 1; @@ -2018,7 +2018,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) warned_on_ntlm = true; cERROR(1, "default security mechanism requested. The default " "security mechanism will be upgraded from ntlm to " - "ntlmv2 in kernel release 3.1"); + "ntlmv2 in kernel release 3.2"); } ses->overrideSecFlg = volume_info->secFlg; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 04da6acde85d..12661e1deedd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1134,7 +1134,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -2807,7 +2807,7 @@ make_io: trace_ext3_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext3_error(inode->i_sb, "ext3_get_inode_loc", diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 5571708b6a58..0629e09f6511 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -922,7 +922,8 @@ restart: bh = ext3_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, + 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 18d2558b7624..986e2388f031 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -647,7 +647,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -3298,7 +3298,7 @@ make_io: trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f8068c7bae9f..1c924faeb6c8 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -922,7 +922,8 @@ restart: bh = ext4_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, + 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 85c62923ee29..598646434362 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -624,9 +624,9 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) bh->b_end_io = end_buffer_write_sync; get_bh(bh); if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) - submit_bh(WRITE_SYNC | REQ_META, bh); + submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); else - submit_bh(WRITE_FLUSH_FUA | REQ_META, bh); + submit_bh(WRITE_FLUSH_FUA | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 747238cd9f96..be29858900f6 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -37,7 +37,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb { struct buffer_head *bh, *head; int nr_underway = 0; - int write_op = REQ_META | + int write_op = REQ_META | REQ_PRIO | (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); BUG_ON(!PageLocked(page)); @@ -225,7 +225,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, } bh->b_end_io = end_buffer_read_sync; get_bh(bh); - submit_bh(READ_SYNC | REQ_META, bh); + submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh); if (!(flags & DIO_WAIT)) return 0; @@ -435,7 +435,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh); + ll_rw_block(READ_SYNC | REQ_META | REQ_PRIO, 1, &first_bh); dblock++; extlen--; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 3bc073a4cf82..079587e53849 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -224,7 +224,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) bio->bi_end_io = end_bio_io_page; bio->bi_private = page; - submit_bio(READ_SYNC | REQ_META, bio); + submit_bio(READ_SYNC | REQ_META | REQ_PRIO, bio); wait_on_page_locked(page); bio_put(bio); if (!PageUptodate(page)) { diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 42e8d23bc047..0e8bb13381e4 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -709,7 +709,7 @@ get_a_page: set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) goto unlock_out; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index c106ca22e812..d24a9b666a23 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -344,6 +344,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) struct inode *root, *inode; struct qstr str; struct nls_table *nls = NULL; + u64 last_fs_block, last_fs_page; int err; err = -EINVAL; @@ -399,9 +400,13 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (!sbi->rsrc_clump_blocks) sbi->rsrc_clump_blocks = 1; - err = generic_check_addressable(sbi->alloc_blksz_shift, - sbi->total_blocks); - if (err) { + err = -EFBIG; + last_fs_block = sbi->total_blocks - 1; + last_fs_page = (last_fs_block << sbi->alloc_blksz_shift) >> + PAGE_CACHE_SHIFT; + + if ((last_fs_block > (sector_t)(~0ULL) >> (sbi->alloc_blksz_shift - 9)) || + (last_fs_page > (pgoff_t)(~0ULL))) { printk(KERN_ERR "hfs: filesystem size too large.\n"); goto out_free_vhdr; } @@ -525,8 +530,8 @@ out_close_cat_tree: out_close_ext_tree: hfs_btree_close(sbi->ext_tree); out_free_vhdr: - kfree(sbi->s_vhdr); - kfree(sbi->s_backup_vhdr); + kfree(sbi->s_vhdr_buf); + kfree(sbi->s_backup_vhdr_buf); out_unload_nls: unload_nls(sbi->nls); unload_nls(nls); diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 10e515a0d452..7daf4b852d1c 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -272,9 +272,9 @@ reread: return 0; out_free_backup_vhdr: - kfree(sbi->s_backup_vhdr); + kfree(sbi->s_backup_vhdr_buf); out_free_vhdr: - kfree(sbi->s_vhdr); + kfree(sbi->s_vhdr_buf); out: return error; } diff --git a/fs/namei.c b/fs/namei.c index b52bc685465f..0b3138de2a3b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -721,12 +721,6 @@ static int follow_automount(struct path *path, unsigned flags, if (!path->dentry->d_op || !path->dentry->d_op->d_automount) return -EREMOTE; - /* We don't want to mount if someone supplied AT_NO_AUTOMOUNT - * and this is the terminal part of the path. - */ - if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_PARENT)) - return -EISDIR; /* we actually want to stop here */ - /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. @@ -739,7 +733,7 @@ static int follow_automount(struct path *path, unsigned flags, * of the daemon to instantiate them before they can be used. */ if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | - LOOKUP_OPEN | LOOKUP_CREATE)) && + LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && path->dentry->d_inode) return -EISDIR; @@ -2616,6 +2610,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) if (!dir->i_op->rmdir) return -EPERM; + dget(dentry); mutex_lock(&dentry->d_inode->i_mutex); error = -EBUSY; @@ -2636,6 +2631,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) out: mutex_unlock(&dentry->d_inode->i_mutex); + dput(dentry); if (!error) d_delete(dentry); return error; @@ -3025,6 +3021,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, if (error) return error; + dget(new_dentry); if (target) mutex_lock(&target->i_mutex); @@ -3045,6 +3042,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, out: if (target) mutex_unlock(&target->i_mutex); + dput(new_dentry); if (!error) if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) d_move(old_dentry,new_dentry); diff --git a/fs/namespace.c b/fs/namespace.c index 22bfe8273c68..b4febb29d3bb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1757,7 +1757,7 @@ static int do_loopback(struct path *path, char *old_name, return err; if (!old_name || !*old_name) return -EINVAL; - err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); + err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 1ec1a85fa71c..3e93e9a1bee1 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -56,6 +56,9 @@ enum nfs4_session_state { NFS4_SESSION_DRAINING, }; +#define NFS4_RENEW_TIMEOUT 0x01 +#define NFS4_RENEW_DELEGATION_CB 0x02 + struct nfs4_minor_version_ops { u32 minor_version; @@ -225,7 +228,7 @@ struct nfs4_state_recovery_ops { }; struct nfs4_state_maintenance_ops { - int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *); + int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *, unsigned); struct rpc_cred * (*get_state_renewal_cred_locked)(struct nfs_client *); int (*renew_lease)(struct nfs_client *, struct rpc_cred *); }; @@ -237,8 +240,6 @@ extern const struct inode_operations nfs4_dir_inode_operations; extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); -extern int nfs4_proc_async_renew(struct nfs_client *, struct rpc_cred *); -extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc); @@ -349,6 +350,7 @@ extern void nfs4_close_sync(struct nfs4_state *, fmode_t); extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t); extern void nfs4_schedule_lease_recovery(struct nfs_client *); extern void nfs4_schedule_state_manager(struct nfs_client *); +extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp); extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_recall_slot(struct nfs_client *clp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8c77039e7a81..4700fae1ada0 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3374,9 +3374,13 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata) if (task->tk_status < 0) { /* Unless we're shutting down, schedule state recovery! */ - if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) != 0) + if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0) + return; + if (task->tk_status != NFS4ERR_CB_PATH_DOWN) { nfs4_schedule_lease_recovery(clp); - return; + return; + } + nfs4_schedule_path_down_recovery(clp); } do_renew_lease(clp, timestamp); } @@ -3386,7 +3390,7 @@ static const struct rpc_call_ops nfs4_renew_ops = { .rpc_release = nfs4_renew_release, }; -int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred) +static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW], @@ -3395,9 +3399,11 @@ int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred) }; struct nfs4_renewdata *data; + if (renew_flags == 0) + return 0; if (!atomic_inc_not_zero(&clp->cl_count)) return -EIO; - data = kmalloc(sizeof(*data), GFP_KERNEL); + data = kmalloc(sizeof(*data), GFP_NOFS); if (data == NULL) return -ENOMEM; data->client = clp; @@ -3406,7 +3412,7 @@ int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred) &nfs4_renew_ops, data); } -int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred) +static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW], @@ -5504,11 +5510,13 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_ return rpc_run_task(&task_setup_data); } -static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred) +static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags) { struct rpc_task *task; int ret = 0; + if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0) + return 0; task = _nfs41_proc_sequence(clp, cred); if (IS_ERR(task)) ret = PTR_ERR(task); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index df8e7f3ca56d..dc484c0eae7f 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -60,6 +60,7 @@ nfs4_renew_state(struct work_struct *work) struct rpc_cred *cred; long lease; unsigned long last, now; + unsigned renew_flags = 0; ops = clp->cl_mvops->state_renewal_ops; dprintk("%s: start\n", __func__); @@ -72,18 +73,23 @@ nfs4_renew_state(struct work_struct *work) last = clp->cl_last_renewal; now = jiffies; /* Are we close to a lease timeout? */ - if (time_after(now, last + lease/3)) { + if (time_after(now, last + lease/3)) + renew_flags |= NFS4_RENEW_TIMEOUT; + if (nfs_delegations_present(clp)) + renew_flags |= NFS4_RENEW_DELEGATION_CB; + + if (renew_flags != 0) { cred = ops->get_state_renewal_cred_locked(clp); spin_unlock(&clp->cl_lock); if (cred == NULL) { - if (!nfs_delegations_present(clp)) { + if (!(renew_flags & NFS4_RENEW_DELEGATION_CB)) { set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); goto out; } nfs_expire_all_delegations(clp); } else { /* Queue an asynchronous RENEW. */ - ops->sched_state_renewal(clp, cred); + ops->sched_state_renewal(clp, cred, renew_flags); put_rpccred(cred); goto out_exp; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 72ab97ef3d61..39914be40b03 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1038,6 +1038,12 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp) nfs4_schedule_state_manager(clp); } +void nfs4_schedule_path_down_recovery(struct nfs_client *clp) +{ + nfs_handle_cb_pathdown(clp); + nfs4_schedule_state_manager(clp); +} + static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state) { diff --git a/fs/nfs/super.c b/fs/nfs/super.c index b961ceac66b4..5b19b6aabe18 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2035,9 +2035,6 @@ static inline void nfs_initialise_sb(struct super_block *sb) sb->s_blocksize = nfs_block_bits(server->wsize, &sb->s_blocksize_bits); - if (server->flags & NFS_MOUNT_NOAC) - sb->s_flags |= MS_SYNCHRONOUS; - sb->s_bdi = &server->backing_dev_info; nfs_super_set_maxbytes(sb, server->maxfilesize); @@ -2249,6 +2246,10 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, if (server->flags & NFS_MOUNT_UNSHARED) compare_super = NULL; + /* -o noac implies -o sync */ + if (server->flags & NFS_MOUNT_NOAC) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(fs_type, compare_super, nfs_set_super, &sb_mntdata); if (IS_ERR(s)) { @@ -2361,6 +2362,10 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags, if (server->flags & NFS_MOUNT_UNSHARED) compare_super = NULL; + /* -o noac implies -o sync */ + if (server->flags & NFS_MOUNT_NOAC) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(&nfs_fs_type, compare_super, nfs_set_super, &sb_mntdata); if (IS_ERR(s)) { @@ -2628,6 +2633,10 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags, if (server->flags & NFS4_MOUNT_UNSHARED) compare_super = NULL; + /* -o noac implies -o sync */ + if (server->flags & NFS_MOUNT_NOAC) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata); if (IS_ERR(s)) { @@ -2789,7 +2798,7 @@ static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, goto out_put_mnt_ns; ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt, - export_path, LOOKUP_FOLLOW, &path); + export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); nfs_referral_loop_unprotect(); put_mnt_ns(ns_private); @@ -2916,6 +2925,10 @@ nfs4_xdev_mount(struct file_system_type *fs_type, int flags, if (server->flags & NFS4_MOUNT_UNSHARED) compare_super = NULL; + /* -o noac implies -o sync */ + if (server->flags & NFS_MOUNT_NOAC) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata); if (IS_ERR(s)) { @@ -3003,6 +3016,10 @@ nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, if (server->flags & NFS4_MOUNT_UNSHARED) compare_super = NULL; + /* -o noac implies -o sync */ + if (server->flags & NFS_MOUNT_NOAC) + sb_mntdata.mntflags |= MS_SYNCHRONOUS; + /* Get a superblock - note that we may end up sharing one that already exists */ s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata); if (IS_ERR(s)) { diff --git a/fs/nfs/write.c b/fs/nfs/write.c index b39b37f80913..c9bd2a6b7d4b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -958,7 +958,7 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head if (!data) goto out_bad; data->pagevec[0] = page; - nfs_write_rpcsetup(req, data, wsize, offset, desc->pg_ioflags); + nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); list_add(&data->list, res); requests++; nbytes -= len; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 25b6a887adb9..5afaa58a8630 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -877,30 +877,54 @@ struct numa_maps_private { struct numa_maps md; }; -static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty) +static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty, + unsigned long nr_pages) { int count = page_mapcount(page); - md->pages++; + md->pages += nr_pages; if (pte_dirty || PageDirty(page)) - md->dirty++; + md->dirty += nr_pages; if (PageSwapCache(page)) - md->swapcache++; + md->swapcache += nr_pages; if (PageActive(page) || PageUnevictable(page)) - md->active++; + md->active += nr_pages; if (PageWriteback(page)) - md->writeback++; + md->writeback += nr_pages; if (PageAnon(page)) - md->anon++; + md->anon += nr_pages; if (count > md->mapcount_max) md->mapcount_max = count; - md->node[page_to_nid(page)]++; + md->node[page_to_nid(page)] += nr_pages; +} + +static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pte_present(pte)) + return NULL; + + page = vm_normal_page(vma, addr, pte); + if (!page) + return NULL; + + if (PageReserved(page)) + return NULL; + + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_HIGH_MEMORY])) + return NULL; + + return page; } static int gather_pte_stats(pmd_t *pmd, unsigned long addr, @@ -912,26 +936,32 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *pte; md = walk->private; - orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - do { - struct page *page; - int nid; + spin_lock(&walk->mm->page_table_lock); + if (pmd_trans_huge(*pmd)) { + if (pmd_trans_splitting(*pmd)) { + spin_unlock(&walk->mm->page_table_lock); + wait_split_huge_page(md->vma->anon_vma, pmd); + } else { + pte_t huge_pte = *(pte_t *)pmd; + struct page *page; - if (!pte_present(*pte)) - continue; + page = can_gather_numa_stats(huge_pte, md->vma, addr); + if (page) + gather_stats(page, md, pte_dirty(huge_pte), + HPAGE_PMD_SIZE/PAGE_SIZE); + spin_unlock(&walk->mm->page_table_lock); + return 0; + } + } else { + spin_unlock(&walk->mm->page_table_lock); + } - page = vm_normal_page(md->vma, addr, *pte); + orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + do { + struct page *page = can_gather_numa_stats(*pte, md->vma, addr); if (!page) continue; - - if (PageReserved(page)) - continue; - - nid = page_to_nid(page); - if (!node_isset(nid, node_states[N_HIGH_MEMORY])) - continue; - - gather_stats(page, md, pte_dirty(*pte)); + gather_stats(page, md, pte_dirty(*pte), 1); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap_unlock(orig_pte, ptl); @@ -952,7 +982,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte)); + gather_stats(page, md, pte_dirty(*pte), 1); return 0; } diff --git a/fs/quota/quota.c b/fs/quota/quota.c index b34bdb25490c..10b6be3ca280 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -355,7 +355,7 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special, * resolution (think about autofs) and thus deadlocks could arise. */ if (cmds == Q_QUOTAON) { - ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW, &path); + ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); if (ret) pathp = ERR_PTR(ret); else diff --git a/fs/stat.c b/fs/stat.c index ba5316ffac61..78a3aa83c7ea 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -81,8 +81,6 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, if (!(flag & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; - if (flag & AT_NO_AUTOMOUNT) - lookup_flags |= LOOKUP_NO_AUTOMOUNT; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 63e971e2b837..8c37dde4c521 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1300,6 +1300,7 @@ xfs_end_io_direct_write( bool is_async) { struct xfs_ioend *ioend = iocb->private; + struct inode *inode = ioend->io_inode; /* * blockdev_direct_IO can return an error even after the I/O @@ -1331,7 +1332,7 @@ xfs_end_io_direct_write( } /* XXX: probably should move into the real I/O completion handler */ - inode_dio_done(ioend->io_inode); + inode_dio_done(inode); } STATIC ssize_t diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index cac2ecfa6746..ef43fce519a1 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -629,7 +629,7 @@ xfs_buf_item_push( * the xfsbufd to get this buffer written. We have to unlock the buffer * to allow the xfsbufd to write it, too. */ -STATIC void +STATIC bool xfs_buf_item_pushbuf( struct xfs_log_item *lip) { @@ -643,6 +643,7 @@ xfs_buf_item_pushbuf( xfs_buf_delwri_promote(bp); xfs_buf_relse(bp); + return true; } STATIC void diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 9e0e2fa3f2c8..bb3f71d236d2 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -183,13 +183,14 @@ xfs_qm_dqunpin_wait( * search the buffer cache can be a time consuming thing, and AIL lock is a * spinlock. */ -STATIC void +STATIC bool xfs_qm_dquot_logitem_pushbuf( struct xfs_log_item *lip) { struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_buf *bp; + bool ret = true; ASSERT(XFS_DQ_IS_LOCKED(dqp)); @@ -201,17 +202,20 @@ xfs_qm_dquot_logitem_pushbuf( if (completion_done(&dqp->q_flush) || !(lip->li_flags & XFS_LI_IN_AIL)) { xfs_dqunlock(dqp); - return; + return true; } bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno, dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK); xfs_dqunlock(dqp); if (!bp) - return; + return true; if (XFS_BUF_ISDELAYWRITE(bp)) xfs_buf_delwri_promote(bp); + if (xfs_buf_ispinned(bp)) + ret = false; xfs_buf_relse(bp); + return ret; } /* diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 588406dc6a35..836ad80d4f2b 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -708,13 +708,14 @@ xfs_inode_item_committed( * marked delayed write. If that's the case, we'll promote it and that will * allow the caller to write the buffer by triggering the xfsbufd to run. */ -STATIC void +STATIC bool xfs_inode_item_pushbuf( struct xfs_log_item *lip) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; struct xfs_buf *bp; + bool ret = true; ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); @@ -725,7 +726,7 @@ xfs_inode_item_pushbuf( if (completion_done(&ip->i_flush) || !(lip->li_flags & XFS_LI_IN_AIL)) { xfs_iunlock(ip, XFS_ILOCK_SHARED); - return; + return true; } bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno, @@ -733,10 +734,13 @@ xfs_inode_item_pushbuf( xfs_iunlock(ip, XFS_ILOCK_SHARED); if (!bp) - return; + return true; if (XFS_BUF_ISDELAYWRITE(bp)) xfs_buf_delwri_promote(bp); + if (xfs_buf_ispinned(bp)) + ret = false; xfs_buf_relse(bp); + return ret; } /* diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 1e8a45e74c3e..828662f70d64 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -68,6 +68,8 @@ #include <linux/ctype.h> #include <linux/writeback.h> #include <linux/capability.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include <linux/list_sort.h> #include <asm/page.h> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 2366c54cc4fa..5cf06b85fd9d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1652,24 +1652,13 @@ xfs_init_workqueues(void) */ xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8); if (!xfs_syncd_wq) - goto out; - - xfs_ail_wq = alloc_workqueue("xfsail", WQ_CPU_INTENSIVE, 8); - if (!xfs_ail_wq) - goto out_destroy_syncd; - + return -ENOMEM; return 0; - -out_destroy_syncd: - destroy_workqueue(xfs_syncd_wq); -out: - return -ENOMEM; } STATIC void xfs_destroy_workqueues(void) { - destroy_workqueue(xfs_ail_wq); destroy_workqueue(xfs_syncd_wq); } diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 06a9759b6352..53597f4db9b5 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -350,7 +350,7 @@ typedef struct xfs_item_ops { void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); void (*iop_push)(xfs_log_item_t *); - void (*iop_pushbuf)(xfs_log_item_t *); + bool (*iop_pushbuf)(xfs_log_item_t *); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); } xfs_item_ops_t; diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index c15aa29fa169..3a1e7ca54c2d 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -28,8 +28,6 @@ #include "xfs_trans_priv.h" #include "xfs_error.h" -struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ - #ifdef DEBUG /* * Check that the list is sorted as it should be. @@ -356,16 +354,10 @@ xfs_ail_delete( xfs_trans_ail_cursor_clear(ailp, lip); } -/* - * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself - * to run at a later time if there is more work to do to complete the push. - */ -STATIC void -xfs_ail_worker( - struct work_struct *work) +static long +xfsaild_push( + struct xfs_ail *ailp) { - struct xfs_ail *ailp = container_of(to_delayed_work(work), - struct xfs_ail, xa_work); xfs_mount_t *mp = ailp->xa_mount; struct xfs_ail_cursor cur; xfs_log_item_t *lip; @@ -427,8 +419,13 @@ xfs_ail_worker( case XFS_ITEM_PUSHBUF: XFS_STATS_INC(xs_push_ail_pushbuf); - IOP_PUSHBUF(lip); - ailp->xa_last_pushed_lsn = lsn; + + if (!IOP_PUSHBUF(lip)) { + stuck++; + flush_log = 1; + } else { + ailp->xa_last_pushed_lsn = lsn; + } push_xfsbufd = 1; break; @@ -440,7 +437,6 @@ xfs_ail_worker( case XFS_ITEM_LOCKED: XFS_STATS_INC(xs_push_ail_locked); - ailp->xa_last_pushed_lsn = lsn; stuck++; break; @@ -501,20 +497,6 @@ out_done: /* We're past our target or empty, so idle */ ailp->xa_last_pushed_lsn = 0; - /* - * We clear the XFS_AIL_PUSHING_BIT first before checking - * whether the target has changed. If the target has changed, - * this pushes the requeue race directly onto the result of the - * atomic test/set bit, so we are guaranteed that either the - * the pusher that changed the target or ourselves will requeue - * the work (but not both). - */ - clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags); - smp_rmb(); - if (XFS_LSN_CMP(ailp->xa_target, target) == 0 || - test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags)) - return; - tout = 50; } else if (XFS_LSN_CMP(lsn, target) >= 0) { /* @@ -537,9 +519,30 @@ out_done: tout = 20; } - /* There is more to do, requeue us. */ - queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, - msecs_to_jiffies(tout)); + return tout; +} + +static int +xfsaild( + void *data) +{ + struct xfs_ail *ailp = data; + long tout = 0; /* milliseconds */ + + while (!kthread_should_stop()) { + if (tout && tout <= 20) + __set_current_state(TASK_KILLABLE); + else + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(tout ? + msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT); + + try_to_freeze(); + + tout = xfsaild_push(ailp); + } + + return 0; } /* @@ -574,8 +577,9 @@ xfs_ail_push( */ smp_wmb(); xfs_trans_ail_copy_lsn(ailp, &ailp->xa_target, &threshold_lsn); - if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags)) - queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0); + smp_wmb(); + + wake_up_process(ailp->xa_task); } /* @@ -813,9 +817,18 @@ xfs_trans_ail_init( INIT_LIST_HEAD(&ailp->xa_ail); INIT_LIST_HEAD(&ailp->xa_cursors); spin_lock_init(&ailp->xa_lock); - INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker); + + ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s", + ailp->xa_mount->m_fsname); + if (IS_ERR(ailp->xa_task)) + goto out_free_ailp; + mp->m_ail = ailp; return 0; + +out_free_ailp: + kmem_free(ailp); + return ENOMEM; } void @@ -824,6 +837,6 @@ xfs_trans_ail_destroy( { struct xfs_ail *ailp = mp->m_ail; - cancel_delayed_work_sync(&ailp->xa_work); + kthread_stop(ailp->xa_task); kmem_free(ailp); } diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 212946b97239..22750b5e4a8f 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -64,23 +64,17 @@ struct xfs_ail_cursor { */ struct xfs_ail { struct xfs_mount *xa_mount; + struct task_struct *xa_task; struct list_head xa_ail; xfs_lsn_t xa_target; struct list_head xa_cursors; spinlock_t xa_lock; - struct delayed_work xa_work; xfs_lsn_t xa_last_pushed_lsn; - unsigned long xa_flags; }; -#define XFS_AIL_PUSHING_BIT 0 - /* * From xfs_trans_ail.c */ - -extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ - void xfs_trans_ail_update_bulk(struct xfs_ail *ailp, struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, |