diff options
author | Philippe Schenker <philippe.schenker@toradex.com> | 2019-05-08 16:08:30 +0200 |
---|---|---|
committer | Philippe Schenker <philippe.schenker@toradex.com> | 2019-05-08 16:08:30 +0200 |
commit | 774f42075a4800fe4106dffca804e3207bc3c2e7 (patch) | |
tree | 4bb3e8ca84f7f23ac41966017e81ffe09e98412e /fs | |
parent | 95a0514c2e68a035e2adbdb5a297da310dccb09c (diff) | |
parent | 33e2f28596a7059dbe31d837caae924a74aa36d8 (diff) |
Merge branch 'linux-4.14.y_for_4.14-2.0.x-imx' into 4.14-2.0.x-imx
Diffstat (limited to 'fs')
107 files changed, 1130 insertions, 385 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 8fb89ddc6cc7..c52f10efdc9c 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -61,6 +61,8 @@ enum { Opt_cache_loose, Opt_fscache, Opt_mmap, /* Access options */ Opt_access, Opt_posixacl, + /* Lock timeout option */ + Opt_locktimeout, /* Error token */ Opt_err }; @@ -80,6 +82,7 @@ static const match_table_t tokens = { {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, + {Opt_locktimeout, "locktimeout=%u"}, {Opt_err, NULL} }; @@ -187,6 +190,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #ifdef CONFIG_9P_FSCACHE v9ses->cachetag = NULL; #endif + v9ses->session_lock_timeout = P9_LOCK_TIMEOUT; if (!opts) return 0; @@ -360,6 +364,23 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) #endif break; + case Opt_locktimeout: + r = match_int(&args[0], &option); + if (r < 0) { + p9_debug(P9_DEBUG_ERROR, + "integer field, but no integer?\n"); + ret = r; + continue; + } + if (option < 1) { + p9_debug(P9_DEBUG_ERROR, + "locktimeout must be a greater than zero integer.\n"); + ret = -EINVAL; + continue; + } + v9ses->session_lock_timeout = (long)option * HZ; + break; + default: continue; } diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 982e017acadb..129e5243a6bf 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -116,6 +116,7 @@ struct v9fs_session_info { struct p9_client *clnt; /* 9p client */ struct list_head slist; /* list of sessions registered with v9fs */ struct rw_semaphore rename_sem; + long session_lock_timeout; /* retry interval for blocking locks */ }; /* cache_validity flags */ diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 5a0db6dec8d1..aaee1e6584e6 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -40,6 +40,9 @@ */ #define P9_LOCK_TIMEOUT (30*HZ) +/* flags for v9fs_stat2inode() & v9fs_stat2inode_dotl() */ +#define V9FS_STAT2INODE_KEEP_ISIZE 1 + extern struct file_system_type v9fs_fs_type; extern const struct address_space_operations v9fs_addr_operations; extern const struct file_operations v9fs_file_operations; @@ -61,8 +64,10 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t); void v9fs_evict_inode(struct inode *inode); ino_t v9fs_qid2ino(struct p9_qid *qid); -void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *); -void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *); +void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, + struct super_block *sb, unsigned int flags); +void v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, + unsigned int flags); int v9fs_dir_release(struct inode *inode, struct file *filp); int v9fs_file_open(struct inode *inode, struct file *file); void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat); @@ -83,4 +88,18 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode) } int v9fs_open_to_dotl_flags(int flags); + +static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size) +{ + /* + * 32-bit need the lock, concurrent updates could break the + * sequences and make i_size_read() loop forever. + * 64-bit updates are atomic and can skip the locking. + */ + if (sizeof(i_size) > sizeof(long)) + spin_lock(&inode->i_lock); + i_size_write(inode, i_size); + if (sizeof(i_size) > sizeof(long)) + spin_unlock(&inode->i_lock); +} #endif diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 48db9a9f13f9..cb6c4031af55 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -105,7 +105,6 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) int err = 0; struct p9_fid *fid; int buflen; - int reclen = 0; struct p9_rdir *rdir; struct kvec kvec; @@ -138,11 +137,10 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) while (rdir->head < rdir->tail) { err = p9stat_read(fid->clnt, rdir->buf + rdir->head, rdir->tail - rdir->head, &st); - if (err) { + if (err <= 0) { p9_debug(P9_DEBUG_VFS, "returned %d\n", err); return -EIO; } - reclen = st.size+2; over = !dir_emit(ctx, st.name, strlen(st.name), v9fs_qid2ino(&st.qid), dt_type(&st)); @@ -150,8 +148,8 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) if (over) return 0; - rdir->head += reclen; - ctx->pos += reclen; + rdir->head += err; + ctx->pos += err; } } } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 3a2f37ad1f89..89e69904976a 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -154,6 +154,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) uint8_t status = P9_LOCK_ERROR; int res = 0; unsigned char fl_type; + struct v9fs_session_info *v9ses; fid = filp->private_data; BUG_ON(fid == NULL); @@ -189,6 +190,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) if (IS_SETLKW(cmd)) flock.flags = P9_LOCK_FLAGS_BLOCK; + v9ses = v9fs_inode2v9ses(file_inode(filp)); + /* * if its a blocked request and we get P9_LOCK_BLOCKED as the status * for lock request, keep on trying @@ -202,7 +205,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd)) break; - if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0) + if (schedule_timeout_interruptible(v9ses->session_lock_timeout) + != 0) break; /* * p9_client_lock_dotl overwrites flock.client_id with the @@ -442,7 +446,11 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) i_size = i_size_read(inode); if (iocb->ki_pos > i_size) { inode_add_bytes(inode, iocb->ki_pos - i_size); - i_size_write(inode, iocb->ki_pos); + /* + * Need to serialize against i_size_write() in + * v9fs_stat2inode() + */ + v9fs_i_size_write(inode, iocb->ki_pos); } return retval; } diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index bdabb2765d1b..e88cb25176dc 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -538,7 +538,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, if (retval) goto error; - v9fs_stat2inode(st, inode, sb); + v9fs_stat2inode(st, inode, sb, 0); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; @@ -1080,7 +1080,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb); + v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0); generic_fillattr(d_inode(dentry), stat); p9stat_free(st); @@ -1158,12 +1158,13 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) * @stat: Plan 9 metadata (mistat) structure * @inode: inode to populate * @sb: superblock of filesystem + * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, - struct super_block *sb) + struct super_block *sb, unsigned int flags) { umode_t mode; char ext[32]; @@ -1204,10 +1205,11 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, mode = p9mode2perm(v9ses, stat); mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - i_size_write(inode, stat->length); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) + v9fs_i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ - inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9; + inode->i_blocks = (stat->length + 512 - 1) >> 9; v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR; } @@ -1404,9 +1406,9 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) { int umode; dev_t rdev; - loff_t i_size; struct p9_wstat *st; struct v9fs_session_info *v9ses; + unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_stat(fid); @@ -1419,16 +1421,13 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) if ((inode->i_mode & S_IFMT) != (umode & S_IFMT)) goto out; - spin_lock(&inode->i_lock); /* * We don't want to refresh inode->i_size, * because we may have cached data */ - i_size = inode->i_size; - v9fs_stat2inode(st, inode, inode->i_sb); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - inode->i_size = i_size; - spin_unlock(&inode->i_lock); + flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + V9FS_STAT2INODE_KEEP_ISIZE : 0; + v9fs_stat2inode(st, inode, inode->i_sb, flags); out: p9stat_free(st); kfree(st); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 7f6ae21a27b3..3446ab1f44e7 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -143,7 +143,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, if (retval) goto error; - v9fs_stat2inode_dotl(st, inode); + v9fs_stat2inode_dotl(st, inode, 0); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); if (retval) @@ -497,7 +497,7 @@ v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode_dotl(st, d_inode(dentry)); + v9fs_stat2inode_dotl(st, d_inode(dentry), 0); generic_fillattr(d_inode(dentry), stat); /* Change block size to what the server returned */ stat->blksize = st->st_blksize; @@ -608,11 +608,13 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) * v9fs_stat2inode_dotl - populate an inode structure with stat info * @stat: stat structure * @inode: inode to populate + * @flags: ctrl flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void -v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) +v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, + unsigned int flags) { umode_t mode; struct v9fs_inode *v9inode = V9FS_I(inode); @@ -632,7 +634,8 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - i_size_write(inode, stat->st_size); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) + v9fs_i_size_write(inode, stat->st_size); inode->i_blocks = stat->st_blocks; } else { if (stat->st_result_mask & P9_STATS_ATIME) { @@ -662,8 +665,9 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) } if (stat->st_result_mask & P9_STATS_RDEV) inode->i_rdev = new_decode_dev(stat->st_rdev); - if (stat->st_result_mask & P9_STATS_SIZE) - i_size_write(inode, stat->st_size); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && + stat->st_result_mask & P9_STATS_SIZE) + v9fs_i_size_write(inode, stat->st_size); if (stat->st_result_mask & P9_STATS_BLOCKS) inode->i_blocks = stat->st_blocks; } @@ -929,9 +933,9 @@ v9fs_vfs_get_link_dotl(struct dentry *dentry, int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) { - loff_t i_size; struct p9_stat_dotl *st; struct v9fs_session_info *v9ses; + unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_getattr_dotl(fid, P9_STATS_ALL); @@ -943,16 +947,13 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT)) goto out; - spin_lock(&inode->i_lock); /* * We don't want to refresh inode->i_size, * because we may have cached data */ - i_size = inode->i_size; - v9fs_stat2inode_dotl(st, inode); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - inode->i_size = i_size; - spin_unlock(&inode->i_lock); + flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + V9FS_STAT2INODE_KEEP_ISIZE : 0; + v9fs_stat2inode_dotl(st, inode, flags); out: kfree(st); return 0; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 8b75463cb211..d4400779f6d9 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -172,7 +172,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, goto release_sb; } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); - v9fs_stat2inode_dotl(st, d_inode(root)); + v9fs_stat2inode_dotl(st, d_inode(root), 0); kfree(st); } else { struct p9_wstat *st = NULL; @@ -183,7 +183,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); - v9fs_stat2inode(st, d_inode(root), sb); + v9fs_stat2inode(st, d_inode(root), sb, 0); p9stat_free(st); kfree(st); diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 57725d4a8c59..141f9bc213a3 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -567,7 +567,6 @@ int autofs4_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -580,6 +579,8 @@ int autofs4_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 3c7e727612fa..e455388a939c 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -259,8 +259,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs4_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino; diff --git a/fs/block_dev.c b/fs/block_dev.c index 23e62bad0b75..b4b462d289f3 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -306,10 +306,10 @@ static void blkdev_bio_end_io(struct bio *bio) struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->should_dirty; - if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_status && !dio->bio.bi_status) - dio->bio.bi_status = bio->bi_status; - } else { + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; + + if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret; diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 1ba49ebe67da..1c42d9f1d6c8 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -22,6 +22,7 @@ #include <linux/posix_acl_xattr.h> #include <linux/posix_acl.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <linux/slab.h> #include "ctree.h" @@ -89,8 +90,16 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, } if (acl) { + unsigned int nofs_flag; + size = posix_acl_xattr_size(acl->a_count); + /* + * We're holding a transaction handle, so use a NOFS memory + * allocation context to avoid deadlock if reclaim happens. + */ + nofs_flag = memalloc_nofs_save(); value = kmalloc(size, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!value) { ret = -ENOMEM; goto out; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 5b62e06567a3..4cc534584665 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3014,11 +3014,11 @@ static int __do_readpage(struct extent_io_tree *tree, */ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) && prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->orig_start) + *prev_em_start != em->start) force_bio_submit = true; if (prev_em_start) - *prev_em_start = em->orig_start; + *prev_em_start = em->start; free_extent_map(em); em = NULL; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index cddd63b9103f..dd3b4820ac30 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -357,6 +357,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* + * If the fs is mounted with nologreplay, which requires it to be + * mounted in RO mode as well, we can not allow discard on free space + * inside block groups, because log trees refer to extents that are not + * pinned in a block group's free space cache (pinning the extents is + * precisely the first phase of replaying a log tree). + */ + if (btrfs_test_opt(fs_info, NOLOGREPLAY)) + return -EROFS; + rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index cbabc6f2b322..266f9069307b 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -386,11 +386,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, static int prop_compression_validate(const char *value, size_t len) { - if (!strncmp("lzo", value, len)) + if (!strncmp("lzo", value, 3)) return 0; - else if (!strncmp("zlib", value, len)) + else if (!strncmp("zlib", value, 4)) return 0; - else if (!strncmp("zstd", value, len)) + else if (!strncmp("zstd", value, 4)) return 0; return -EINVAL; @@ -416,7 +416,7 @@ static int prop_compression_apply(struct inode *inode, btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { + } else if (!strncmp("zstd", value, 4)) { type = BTRFS_COMPRESS_ZSTD; btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } else { diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 2e995e565633..1e35a2327478 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2414,8 +2414,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bitmap_clear(rbio->dbitmap, pagenr, 1); kunmap(p); - for (stripe = 0; stripe < rbio->real_stripes; stripe++) + for (stripe = 0; stripe < nr_data; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); + kunmap(p_page); } __free_page(p_page); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 179a383a4aaa..9d72882b0f72 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3422,9 +3422,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - /* find the first key from this transaction again */ + /* + * Find the first key from this transaction again. See the note for + * log_new_dir_dentries, if we're logging a directory recursively we + * won't be holding its i_mutex, which means we can modify the directory + * while we're logging it. If we remove an entry between our first + * search and this search we'll not find the key again and can just + * bail. + */ ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); - if (WARN_ON(ret != 0)) + if (ret != 0) goto done; /* @@ -4501,6 +4508,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); *size_ret = btrfs_inode_size(path->nodes[0], item); + /* + * If the in-memory inode's i_size is smaller then the inode + * size stored in the btree, return the inode's i_size, so + * that we get a correct inode size after replaying the log + * when before a power failure we had a shrinking truncate + * followed by addition of a new name (rename / new hard link). + * Otherwise return the inode size from the btree, to avoid + * data loss when replaying a log due to previously doing a + * write that expands the inode's size and logging a new name + * immediately after. + */ + if (*size_ret > inode->vfs_inode.i_size) + *size_ret = inode->vfs_inode.i_size; } btrfs_release_path(path); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9663b6aa2a56..38ed8e259e00 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6420,10 +6420,10 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info, } if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) || + (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || - (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) || + (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != 1)) { btrfs_err(fs_info, diff --git a/fs/buffer.c b/fs/buffer.c index b96f3b98a6ef..bdca7b10e239 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -208,6 +208,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -235,15 +236,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); @@ -3083,6 +3084,13 @@ void guard_bio_eod(int op, struct bio *bio) /* Uhhuh. We've got a bio that straddles the device size! */ truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9); + /* + * The bio contains more than one segment which spans EOD, just return + * and let IO layer turn it into an EIO + */ + if (truncated_bytes > bvec->bv_len) + return; + /* Truncate the bio.. */ bio->bi_iter.bi_size -= truncated_bytes; bvec->bv_len -= truncated_bytes; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 8a5266699b67..56e8fc896f6b 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1454,6 +1454,7 @@ void ceph_dentry_lru_del(struct dentry *dn) unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash; switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1461,8 +1462,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) return dn->d_name.hash; default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index a1492bdc6d03..f2b722f0df5d 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -520,6 +520,7 @@ static void ceph_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); + kfree(ci->i_symlink); kmem_cache_free(ceph_inode_cachep, ci); } @@ -551,7 +552,6 @@ void ceph_destroy_inode(struct inode *inode) ceph_put_snap_realm(mdsc, realm); } - kfree(ci->i_symlink); while ((n = rb_first(&ci->i_fragtree)) != NULL) { frag = rb_entry(n, struct ceph_inode_frag, node); rb_erase(n, &ci->i_fragtree); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a48984dd6426..e1ded4bd6115 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1219,6 +1219,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); ci->i_prealloc_cap_flush = NULL; } + + if (drop && + ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } } spin_unlock(&ci->i_ceph_lock); while (!list_empty(&to_remove)) { @@ -1863,10 +1872,39 @@ retry: return path; } +/* Duplicate the dentry->d_name.name safely */ +static int clone_dentry_name(struct dentry *dentry, const char **ppath, + int *ppathlen) +{ + u32 len; + char *name; + +retry: + len = READ_ONCE(dentry->d_name.len); + name = kmalloc(len + 1, GFP_NOFS); + if (!name) + return -ENOMEM; + + spin_lock(&dentry->d_lock); + if (dentry->d_name.len != len) { + spin_unlock(&dentry->d_lock); + kfree(name); + goto retry; + } + memcpy(name, dentry->d_name.name, len); + spin_unlock(&dentry->d_lock); + + name[len] = '\0'; + *ppath = name; + *ppathlen = len; + return 0; +} + static int build_dentry_path(struct dentry *dentry, struct inode *dir, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath, bool parent_locked) { + int ret; char *path; rcu_read_lock(); @@ -1875,8 +1913,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (dir && ceph_snap(dir) == CEPH_NOSNAP) { *pino = ceph_ino(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + if (parent_locked) { + *ppath = dentry->d_name.name; + *ppathlen = dentry->d_name.len; + } else { + ret = clone_dentry_name(dentry, ppath, ppathlen); + if (ret) + return ret; + *pfreepath = true; + } return 0; } rcu_read_unlock(); @@ -1884,13 +1929,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } static int build_inode_path(struct inode *inode, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath) { struct dentry *dentry; char *path; @@ -1906,7 +1951,7 @@ static int build_inode_path(struct inode *inode, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } @@ -1917,7 +1962,7 @@ static int build_inode_path(struct inode *inode, static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, const char *rpath, u64 rino, const char **ppath, int *pathlen, - u64 *ino, int *freepath) + u64 *ino, bool *freepath, bool parent_locked) { int r = 0; @@ -1927,7 +1972,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, ceph_snap(rinode)); } else if (rdentry) { r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino, - freepath); + freepath, parent_locked); dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); } else if (rpath || rino) { @@ -1953,7 +1998,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, const char *path2 = NULL; u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; - int freepath1 = 0, freepath2 = 0; + bool freepath1 = false, freepath2 = false; int len; u16 releases; void *p, *end; @@ -1961,16 +2006,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ret = set_request_path_attr(req->r_inode, req->r_dentry, req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1); + &path1, &pathlen1, &ino1, &freepath1, + test_bit(CEPH_MDS_R_PARENT_LOCKED, + &req->r_req_flags)); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* If r_old_dentry is set, then assume that its parent is locked */ ret = set_request_path_attr(NULL, req->r_old_dentry, req->r_old_dentry_dir, req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2); + &path2, &pathlen2, &ino2, &freepath2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 8a2ca41e4b97..a7e763dac038 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -568,7 +568,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) old_snapc = NULL; update_snapc: - if (ci->i_head_snapc) { + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ci->i_head_snapc = NULL; + } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); dout(" new snapc is %p\n", new_snapc); } @@ -616,7 +621,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + if (list_empty(&ci->i_snap_flush_item)) + list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 6b61df117fd4..563e2f6268c3 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -271,9 +271,9 @@ static void dump_referral(const struct dfs_info3_param *ref) { cifs_dbg(FYI, "DFS: ref path: %s\n", ref->path_name); cifs_dbg(FYI, "DFS: node path: %s\n", ref->node_name); - cifs_dbg(FYI, "DFS: fl: %hd, srv_type: %hd\n", + cifs_dbg(FYI, "DFS: fl: %d, srv_type: %d\n", ref->flags, ref->server_type); - cifs_dbg(FYI, "DFS: ref_flags: %hd, path_consumed: %hd\n", + cifs_dbg(FYI, "DFS: ref_flags: %d, path_consumed: %d\n", ref->ref_flag, ref->path_consumed); } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index f29cdb1cdeb7..7b7ab10a9db1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1189,6 +1189,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1693,6 +1694,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 48aa854c564a..33cd844579ae 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1265,6 +1265,11 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol) const char *delims = "/\\"; size_t len; + if (unlikely(!devname || !*devname)) { + cifs_dbg(VFS, "Device name not specified.\n"); + return -EINVAL; + } + /* make sure we have a valid UNC double delimiter prefix */ len = strspn(devname, delims); if (len != 2) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 1e176e11dbfa..48ea9dfd5f02 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -358,13 +358,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +{ struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); struct TCP_Server_Info *server = tcon->ses->server; @@ -411,7 +429,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -1128,6 +1147,10 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -1466,6 +1489,10 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -1623,8 +1650,20 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, rc = server->ops->mand_unlock_range(cfile, flock, xid); out: - if (flock->fl_flags & FL_POSIX && !rc) + if (flock->fl_flags & FL_POSIX) { + /* + * If this is a request to remove all locks because we + * are closing the file, it doesn't matter if the + * unlocking failed as both cifs.ko and the SMB server + * remove the lock on file close + */ + if (rc) { + cifs_dbg(VFS, "%s failed rc=%d\n", __func__, rc); + if (!(flock->fl_flags & FL_CLOSE)) + return rc; + } rc = locks_lock_file_wait(file, flock); + } return rc; } @@ -2881,14 +2920,16 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) * these pages but not on the region from pos to ppos+len-1. */ written = cifs_user_writev(iocb, from); - if (written > 0 && CIFS_CACHE_READ(cinode)) { + if (CIFS_CACHE_READ(cinode)) { /* - * Windows 7 server can delay breaking level2 oplock if a write - * request comes - break it on the client to prevent reading - * an old data. + * We have read level caching and we have just sent a write + * request to the server thus making data in the cache stale. + * Zap the cache and set oplock/lease level to NONE to avoid + * reading stale data from the cache. All subsequent read + * operations will read new data from the server. */ cifs_zap_mapping(inode); - cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n", + cifs_dbg(FYI, "Set Oplock/Lease to NONE for inode=%p after write\n", inode); cinode->oplock = 0; } @@ -4114,6 +4155,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a90a637ae79a..e7192ee7a89c 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -779,43 +779,50 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, } else if ((rc == -EACCES) && backup_cred(cifs_sb) && (strcmp(server->vals->version_string, SMB1_VERSION_STRING) == 0)) { - /* - * For SMB2 and later the backup intent flag is already - * sent if needed on open and there is no path based - * FindFirst operation to use to retry with - */ + /* + * For SMB2 and later the backup intent flag is already + * sent if needed on open and there is no path based + * FindFirst operation to use to retry with + */ - srchinf = kzalloc(sizeof(struct cifs_search_info), - GFP_KERNEL); - if (srchinf == NULL) { - rc = -ENOMEM; - goto cgii_exit; - } + srchinf = kzalloc(sizeof(struct cifs_search_info), + GFP_KERNEL); + if (srchinf == NULL) { + rc = -ENOMEM; + goto cgii_exit; + } - srchinf->endOfSearch = false; + srchinf->endOfSearch = false; + if (tcon->unix_ext) + srchinf->info_level = SMB_FIND_FILE_UNIX; + else if ((tcon->ses->capabilities & + tcon->ses->server->vals->cap_nt_find) == 0) + srchinf->info_level = SMB_FIND_FILE_INFO_STANDARD; + else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) srchinf->info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; + else /* no srvino useful for fallback to some netapp */ + srchinf->info_level = SMB_FIND_FILE_DIRECTORY_INFO; - srchflgs = CIFS_SEARCH_CLOSE_ALWAYS | - CIFS_SEARCH_CLOSE_AT_END | - CIFS_SEARCH_BACKUP_SEARCH; + srchflgs = CIFS_SEARCH_CLOSE_ALWAYS | + CIFS_SEARCH_CLOSE_AT_END | + CIFS_SEARCH_BACKUP_SEARCH; - rc = CIFSFindFirst(xid, tcon, full_path, - cifs_sb, NULL, srchflgs, srchinf, false); - if (!rc) { - data = - (FILE_ALL_INFO *)srchinf->srch_entries_start; + rc = CIFSFindFirst(xid, tcon, full_path, + cifs_sb, NULL, srchflgs, srchinf, false); + if (!rc) { + data = (FILE_ALL_INFO *)srchinf->srch_entries_start; - cifs_dir_info_to_fattr(&fattr, - (FILE_DIRECTORY_INFO *)data, cifs_sb); - fattr.cf_uniqueid = le64_to_cpu( - ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); - validinum = true; + cifs_dir_info_to_fattr(&fattr, + (FILE_DIRECTORY_INFO *)data, cifs_sb); + fattr.cf_uniqueid = le64_to_cpu( + ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); + validinum = true; - cifs_buf_release(srchinf->ntwrk_buf_start); - } - kfree(srchinf); - if (rc) - goto cgii_exit; + cifs_buf_release(srchinf->ntwrk_buf_start); + } + kfree(srchinf); + if (rc) + goto cgii_exit; } else goto cgii_exit; @@ -1723,6 +1730,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (rc == 0 || rc != -EBUSY) goto do_rename_exit; + /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index bcab30d4a6c7..76f1649ab444 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -486,8 +486,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -584,6 +583,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index ef24b4527459..68183872bf8b 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -655,7 +655,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* scan and find it */ int i; char *cur_ent; - char *end_of_smb = cfile->srch_inf.ntwrk_buf_start + + char *end_of_smb; + + if (cfile->srch_inf.ntwrk_buf_start == NULL) { + cifs_dbg(VFS, "ntwrk_buf_start is NULL during readdir\n"); + return -EIO; + } + + end_of_smb = cfile->srch_inf.ntwrk_buf_start + server->ops->calc_smb_size( cfile->srch_inf.ntwrk_buf_start); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index d8cd82001c1c..f50d3d0b9b87 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -306,7 +306,7 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr) remaining = tgt_total_cnt - total_in_tgt; if (remaining < 0) { - cifs_dbg(FYI, "Server sent too much data. tgt_total_cnt=%hu total_in_tgt=%hu\n", + cifs_dbg(FYI, "Server sent too much data. tgt_total_cnt=%hu total_in_tgt=%u\n", tgt_total_cnt, total_in_tgt); return -EPROTO; } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 79078533f807..1add404618f0 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -130,6 +130,8 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, if (max_buf < sizeof(struct smb2_lock_element)) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) @@ -266,6 +268,8 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile) return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) { diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index d7e839cb773f..92c9cdf4704d 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -1035,7 +1035,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_UNFINISHED_CONTEXT_DELETED, -EIO, "STATUS_UNFINISHED_CONTEXT_DELETED"}, {STATUS_NO_TGT_REPLY, -EIO, "STATUS_NO_TGT_REPLY"}, - {STATUS_OBJECTID_NOT_FOUND, -EIO, "STATUS_OBJECTID_NOT_FOUND"}, + /* Note that ENOATTTR and ENODATA are the same errno */ + {STATUS_OBJECTID_NOT_FOUND, -ENODATA, "STATUS_OBJECTID_NOT_FOUND"}, {STATUS_NO_IP_ADDRESSES, -EIO, "STATUS_NO_IP_ADDRESSES"}, {STATUS_WRONG_CREDENTIAL_HANDLE, -EIO, "STATUS_WRONG_CREDENTIAL_HANDLE"}, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index efdfdb47a7dd..31f01f09d25a 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -479,7 +479,6 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, __u8 lease_state; struct list_head *tmp; struct cifsFileInfo *cfile; - struct TCP_Server_Info *server = tcon->ses->server; struct cifs_pending_open *open; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & @@ -499,14 +498,26 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, cifs_dbg(FYI, "lease key match, lease break 0x%x\n", le32_to_cpu(rsp->NewLeaseState)); - server->ops->set_oplock_level(cinode, lease_state, 0, NULL); - if (ack_req) cfile->oplock_break_cancelled = false; else cfile->oplock_break_cancelled = true; - queue_work(cifsoplockd_wq, &cfile->oplock_break); + set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); + + /* + * Set or clear flags depending on the lease state being READ. + * HANDLE caching flag should be added when the client starts + * to defer closing remote file handles with HANDLE leases. + */ + if (lease_state & SMB2_LEASE_READ_CACHING_HE) + set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &cinode->flags); + else + clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &cinode->flags); + + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -650,8 +661,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index fb1c65f93114..418062c7f040 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1933,6 +1933,15 @@ smb2_downgrade_oplock(struct TCP_Server_Info *server, } static void +smb21_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, bool set_level2) +{ + server->ops->set_oplock_level(cinode, + set_level2 ? SMB2_LEASE_READ_CACHING_HE : + 0, 0, NULL); +} + +static void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { @@ -2917,7 +2926,7 @@ struct smb_version_operations smb21_operations = { .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb2_downgrade_oplock, + .downgrade_oplock = smb21_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -3012,7 +3021,7 @@ struct smb_version_operations smb30_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb2_downgrade_oplock, + .downgrade_oplock = smb21_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -3117,7 +3126,7 @@ struct smb_version_operations smb311_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb2_downgrade_oplock, + .downgrade_oplock = smb21_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index e52454059725..bad458a2b579 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ -#define MAX_SMB2_HDR_SIZE 0x00b0 +/* 52 transform hdr + 64 hdr + 88 create rsp */ +#define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index c59f015f386e..f4df6feec271 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -170,19 +170,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void debugfs_evict_inode(struct inode *inode) +static void debugfs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void debugfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, debugfs_i_callback); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, - .evict_inode = debugfs_evict_inode, + .destroy_inode = debugfs_destroy_inode, }; static struct vfsmount *debugfs_automount(struct path *path) @@ -766,6 +771,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; + if (IS_ERR(old_dir)) + return old_dir; + if (IS_ERR(new_dir)) + return new_dir; + if (IS_ERR_OR_NULL(old_dentry)) + return old_dentry; + trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 542364bf923e..32f6f1c683d9 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -439,6 +439,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent) s->s_blocksize_bits = 10; s->s_magic = DEVPTS_SUPER_MAGIC; s->s_op = &devpts_sops; + s->s_d_op = &simple_dentry_operations; s->s_time_gran = 1; error = -ENOMEM; diff --git a/fs/direct-io.c b/fs/direct-io.c index 0a1cba33adaa..2cd493494c3b 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -219,6 +219,27 @@ static inline struct page *dio_get_page(struct dio *dio, return dio->pages[sdio->head]; } +/* + * Warn about a page cache invalidation failure during a direct io write. + */ +void dio_warn_stale_pagecache(struct file *filp) +{ + static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); + char pathname[128]; + struct inode *inode = file_inode(filp); + char *path; + + errseq_set(&inode->i_mapping->wb_err, -EIO); + if (__ratelimit(&_rs)) { + path = file_path(filp, pathname, sizeof(pathname)); + if (IS_ERR(path)) + path = "(unknown)"; + pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); + pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, + current->comm); + } +} + /** * dio_complete() - called when all DIO BIO I/O has been completed * @offset: the byte offset in the file of the completed operation @@ -290,7 +311,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) err = invalidate_inode_pages2_range(dio->inode->i_mapping, offset >> PAGE_SHIFT, (offset + ret - 1) >> PAGE_SHIFT); - WARN_ON_ONCE(err); + if (err) + dio_warn_stale_pagecache(dio->iocb->ki_filp); } if (!(dio->flags & DIO_SKIP_DIO_COUNT)) @@ -658,6 +680,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, unsigned long fs_count; /* Number of filesystem-sized blocks */ int create; unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor; + loff_t i_size; /* * If there was a memory error and we've overwritten all the @@ -687,8 +710,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, */ create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { - if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> - i_blkbits)) + i_size = i_size_read(dio->inode); + if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits) create = 0; } diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 07fed838d8fd..15fa4239ae9f 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -290,6 +290,8 @@ void dlm_callback_suspend(struct dlm_ls *ls) flush_workqueue(ls->ls_callback_wq); } +#define MAX_CB_QUEUE 25 + void dlm_callback_resume(struct dlm_ls *ls) { struct dlm_lkb *lkb, *safe; @@ -300,15 +302,23 @@ void dlm_callback_resume(struct dlm_ls *ls) if (!ls->ls_callback_wq) return; +more: mutex_lock(&ls->ls_cb_mutex); list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) { list_del_init(&lkb->lkb_cb_list); queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); count++; + if (count == MAX_CB_QUEUE) + break; } mutex_unlock(&ls->ls_cb_mutex); if (count) log_rinfo(ls, "dlm_callback_resume %d", count); + if (count == MAX_CB_QUEUE) { + count = 0; + cond_resched(); + goto more; + } } diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 82377017130f..d31b6c72b476 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 2fabd19cdeea..c291bf61afb9 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1167,7 +1167,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ - if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) { + if (ep->ovflist != EP_UNACTIVE_PTR) { if (epi->next == EP_UNACTIVE_PTR) { epi->next = ep->ovflist; ep->ovflist = epi; diff --git a/fs/exec.c b/fs/exec.c index 0da4d748b4e6..0936b5a8199a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -925,7 +925,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, bytes = kernel_read(file, *buf + pos, i_size - pos, &pos); if (bytes < 0) { ret = bytes; - goto out; + goto out_free; } if (bytes == 0) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 726e680a3368..13f470636672 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -754,7 +754,8 @@ static loff_t ext2_max_size(int bits) { loff_t res = EXT2_NDIR_BLOCKS; int meta_blocks; - loff_t upper_limit; + unsigned int upper_limit; + unsigned int ppb = 1 << (bits-2); /* This is calculated to be the largest file size for a * dense, file such that the total number of @@ -768,24 +769,34 @@ static loff_t ext2_max_size(int bits) /* total blocks in file system block size */ upper_limit >>= (bits - 9); + /* Compute how many blocks we can address by block tree */ + res += 1LL << (bits-2); + res += 1LL << (2*(bits-2)); + res += 1LL << (3*(bits-2)); + /* Does block tree limit file size? */ + if (res < upper_limit) + goto check_lfs; + res = upper_limit; + /* How many metadata blocks are needed for addressing upper_limit? */ + upper_limit -= EXT2_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; + upper_limit -= ppb; /* double indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)); - /* tripple indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); - - upper_limit -= meta_blocks; - upper_limit <<= bits; - - res += 1LL << (bits-2); - res += 1LL << (2*(bits-2)); - res += 1LL << (3*(bits-2)); + if (upper_limit < ppb * ppb) { + meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb); + res -= meta_blocks; + goto check_lfs; + } + meta_blocks += 1 + ppb; + upper_limit -= ppb * ppb; + /* tripple indirect blocks for the rest */ + meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) + + DIV_ROUND_UP(upper_limit, ppb*ppb); + res -= meta_blocks; +check_lfs: res <<= bits; - if (res > upper_limit) - res = upper_limit; - if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 02970a2e86a3..95ef26b39e69 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -426,6 +426,9 @@ struct flex_groups { /* Flags that are appropriate for non-directories/regular files. */ #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) +/* The only flags that should be swapped */ +#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL) + /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags) { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 48143e32411c..1437f62d068c 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -387,7 +387,7 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle, { struct ext4_inode_info *ei = EXT4_I(inode); - if (ext4_handle_valid(handle)) { + if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 5cb9aa3ad249..1913c69498c1 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -123,7 +123,7 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos) struct super_block *sb = inode->i_sb; int blockmask = sb->s_blocksize - 1; - if (pos >= i_size_read(inode)) + if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize)) return 0; if ((pos | iov_iter_alignment(from)) & blockmask) diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 712f00995390..5508baa11bb6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; - if (!journal) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL - }; - - ret = ext4_write_inode(inode, &wbc); + ret = __generic_file_fsync(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index bf7fa1507e81..e1801b288847 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1219,6 +1219,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t offsets[4], offsets2[4]; Indirect chain[4], chain2[4]; Indirect *partial, *partial2; + Indirect *p = NULL, *p2 = NULL; ext4_lblk_t max_block; __le32 nr = 0, nr2 = 0; int n = 0, n2 = 0; @@ -1260,7 +1261,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, } - partial = ext4_find_shared(inode, n, offsets, chain, &nr); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); if (nr) { if (partial == chain) { /* Shared branch grows from the inode */ @@ -1285,13 +1286,11 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); partial--; } end_range: - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); if (nr2) { if (partial2 == chain2) { /* @@ -1321,16 +1320,14 @@ end_range: (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); partial2--; } goto do_indirects; } /* Punch happened within the same level (n == n2) */ - partial = ext4_find_shared(inode, n, offsets, chain, &nr); - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); /* Free top, but only if partial2 isn't its subtree. */ if (nr) { @@ -1387,11 +1384,7 @@ end_range: partial->p + 1, partial2->p, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); - return 0; + goto cleanup; } /* @@ -1406,8 +1399,6 @@ end_range: partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); partial--; } if (partial2 > chain2 && depth2 <= depth) { @@ -1415,11 +1406,21 @@ end_range: (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); partial2--; } } + +cleanup: + while (p && p > chain) { + BUFFER_TRACE(p->bh, "call brelse"); + brelse(p->bh); + p--; + } + while (p2 && p2 > chain2) { + BUFFER_TRACE(p2->bh, "call brelse"); + brelse(p2->bh); + p2--; + } return 0; do_indirects: @@ -1427,7 +1428,7 @@ do_indirects: switch (offsets[0]) { default: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_IND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); @@ -1435,7 +1436,7 @@ do_indirects: } case EXT4_IND_BLOCK: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); @@ -1443,7 +1444,7 @@ do_indirects: } case EXT4_DIND_BLOCK: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); @@ -1452,5 +1453,5 @@ do_indirects: case EXT4_TIND_BLOCK: ; } - return 0; + goto cleanup; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index b2a47058e04c..3dbf4e414706 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -61,6 +61,7 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) loff_t isize; struct ext4_inode_info *ei1; struct ext4_inode_info *ei2; + unsigned long tmp; ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); @@ -73,7 +74,10 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) swap(inode1->i_mtime, inode2->i_mtime); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); - swap(ei1->i_flags, ei2->i_flags); + tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP; + ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) | + (ei1->i_flags & ~EXT4_FL_SHOULD_SWAP); + ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP); swap(ei1->i_disksize, ei2->i_disksize); ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS); ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS); @@ -936,6 +940,13 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* + * We haven't replayed the journal, so we cannot use our + * block-bitmap-guided storage zapping commands. + */ + if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) + return -EROFS; + if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 703b516366fd..333fba05e1a5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -907,11 +907,18 @@ static int add_new_gdb_meta_bg(struct super_block *sb, memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); n_group_desc[gdb_num] = gdb_bh; + + BUFFER_TRACE(gdb_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, gdb_bh); + if (err) { + kvfree(n_group_desc); + brelse(gdb_bh); + return err; + } + EXT4_SB(sb)->s_group_desc = n_group_desc; EXT4_SB(sb)->s_gdb_count++; kvfree(o_group_desc); - BUFFER_TRACE(gdb_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, gdb_bh); return err; } @@ -1930,7 +1937,8 @@ retry: le16_to_cpu(es->s_reserved_gdt_blocks); n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); n_blocks_count = (ext4_fsblk_t)n_group * - EXT4_BLOCKS_PER_GROUP(sb); + EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(es->s_first_data_block); n_group--; /* set to last group number */ } @@ -2041,6 +2049,10 @@ out: free_flex_gd(flex_gd); if (resize_inode != NULL) iput(resize_inode); - ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); + if (err) + ext4_warning(sb, "error (%d) occurred during " + "file system resize", err); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", + ext4_blocks_count(es)); return err; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 311761a6ef6d..6761e905cab0 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -828,6 +828,7 @@ int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { ret = PTR_ERR(bh); + bh = NULL; goto out; } @@ -2905,6 +2906,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, if (error == -EIO) EXT4_ERROR_INODE(inode, "block %llu read error", EXT4_I(inode)->i_file_acl); + bh = NULL; goto cleanup; } error = ext4_xattr_check_block(inode, bh); @@ -3061,6 +3063,7 @@ ext4_xattr_block_cache_find(struct inode *inode, if (IS_ERR(bh)) { if (PTR_ERR(bh) == -ENOMEM) return NULL; + bh = NULL; EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 436b3a1464d9..5e4860b8bbfc 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -349,12 +349,14 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, return PTR_ERR(p); clone = f2fs_acl_clone(p, GFP_NOFS); - if (!clone) - goto no_mem; + if (!clone) { + ret = -ENOMEM; + goto release_acl; + } ret = f2fs_acl_create_masq(clone, mode); if (ret < 0) - goto no_mem_clone; + goto release_clone; if (ret == 0) posix_acl_release(clone); @@ -368,11 +370,11 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, return 0; -no_mem_clone: +release_clone: posix_acl_release(clone); -no_mem: +release_acl: posix_acl_release(p); - return -ENOMEM; + return ret; } int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c68b319b07aa..3d37124eb63e 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1880,6 +1880,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, bool locked = false; struct extent_info ei = {0,0,0}; int err = 0; + int flag; /* * we already allocated all the blocks, so we don't need to get @@ -1889,9 +1890,15 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, !is_inode_flag_set(inode, FI_NO_PREALLOC)) return 0; + /* f2fs_lock_op avoids race between write CP and convert_inline_page */ + if (f2fs_has_inline_data(inode) && pos + len > MAX_INLINE_DATA(inode)) + flag = F2FS_GET_BLOCK_DEFAULT; + else + flag = F2FS_GET_BLOCK_PRE_AIO; + if (f2fs_has_inline_data(inode) || (pos & PAGE_MASK) >= i_size_read(inode)) { - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + __do_map_lock(sbi, flag, true); locked = true; } restart: @@ -1929,6 +1936,7 @@ restart: f2fs_put_dnode(&dn); __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO); locked = true; goto restart; } @@ -1942,7 +1950,7 @@ out: f2fs_put_dnode(&dn); unlock_out: if (locked) - __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + __do_map_lock(sbi, flag, false); return err; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 3f1a44696036..634165fb64f1 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2294,10 +2294,19 @@ static inline bool is_dot_dotdot(const struct qstr *str) static inline bool f2fs_may_extent_tree(struct inode *inode) { - if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) || + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (!test_opt(sbi, EXTENT_CACHE) || is_inode_flag_set(inode, FI_NO_EXTENT)) return false; + /* + * for recovered files during mount do not create extents + * if shrinker is not registered. + */ + if (list_empty(&sbi->s_list)) + return false; + return S_ISREG(inode->i_mode); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 7d3189f1941c..5f549bc4e097 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -205,6 +205,9 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, trace_f2fs_sync_file_enter(inode); + if (S_ISDIR(inode->i_mode)) + goto go_write; + /* if fdatasync is triggered, let's do in-place-update */ if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) set_inode_flag(inode, FI_NEED_IPU); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 888a9dc13677..506e365cf903 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -656,6 +656,12 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (IS_ERR(ipage)) return PTR_ERR(ipage); + /* + * f2fs_readdir was protected by inode.i_rwsem, it is safe to access + * ipage without page's lock held. + */ + unlock_page(ipage); + inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); @@ -664,7 +670,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (!err) ctx->pos = d.max; - f2fs_put_page(ipage, 1); + f2fs_put_page(ipage, 0); return err < 0 ? err : 0; } diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index 5c60fc28ec75..ec71d2e29a15 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -138,6 +138,6 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi) f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi)); spin_lock(&f2fs_list_lock); - list_del(&sbi->s_list); + list_del_init(&sbi->s_list); spin_unlock(&f2fs_list_lock); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index fc5c41257e68..4c169ba50c0f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1959,7 +1959,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count; - int i; + int i, j; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -2000,11 +2000,43 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_node_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Node segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_data_segno[i])); + return 1; + } + } + } + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + for (j = i; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u) and Data segment (%u)" + " has the same segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index bccbbf2616d2..8ac1851a21c0 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -61,6 +61,7 @@ void f2fs_trace_pid(struct page *page) set_page_private(page, (unsigned long)pid); +retry: if (radix_tree_preload(GFP_NOFS)) return; @@ -71,7 +72,12 @@ void f2fs_trace_pid(struct page *page) if (p) radix_tree_delete(&pids, pid); - f2fs_radix_tree_insert(&pids, pid, current); + if (radix_tree_insert(&pids, pid, current)) { + spin_unlock(&pids_lock); + radix_tree_preload_end(); + cond_resched(); + goto retry; + } trace_printk("%3x:%3x %4x %-16s\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), diff --git a/fs/file.c b/fs/file.c index 4eecbf4244a5..0c25b980affe 100644 --- a/fs/file.c +++ b/fs/file.c @@ -462,6 +462,7 @@ struct files_struct init_files = { .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), + .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 3244932f4d5c..6a76616c9401 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -331,11 +331,22 @@ struct inode_switch_wbs_context { struct work_struct work; }; +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + down_write(&bdi->wb_switch_rwsem); +} + +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + up_write(&bdi->wb_switch_rwsem); +} + static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; + struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -344,6 +355,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) void **slot; /* + * If @inode switches cgwb membership while sync_inodes_sb() is + * being issued, sync_inodes_sb() might miss it. Synchronize. + */ + down_read(&bdi->wb_switch_rwsem); + + /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be @@ -435,6 +452,8 @@ skip_switch: spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); + up_read(&bdi->wb_switch_rwsem); + if (switched) { wb_wakeup(new_wb); wb_put(old_wb); @@ -475,9 +494,18 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (inode->i_state & I_WB_SWITCH) return; + /* + * Avoid starting new switches while sync_inodes_sb() is in + * progress. Otherwise, if the down_write protected issue path + * blocks heavily, we might end up starting a large number of + * switches which will block on the rwsem. + */ + if (!down_read_trylock(&bdi->wb_switch_rwsem)) + return; + isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) - return; + goto out_unlock; /* find and pin the new wb */ rcu_read_lock(); @@ -511,12 +539,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); - return; + goto out_unlock; out_free: if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); +out_unlock: + up_read(&bdi->wb_switch_rwsem); } /** @@ -894,6 +924,9 @@ fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } + static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) @@ -2408,8 +2441,11 @@ void sync_inodes_sb(struct super_block *sb) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); + /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ + bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(bdi, &done); + bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f7280c44cd4b..770733106d6d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1691,7 +1691,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.h.nodeid = outarg->nodeid; req->in.numargs = 2; req->in.argpages = 1; - req->page_descs[0].offset = offset; req->end = fuse_retrieve_end; index = outarg->offset >> PAGE_SHIFT; @@ -1706,6 +1705,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, this_num = min_t(unsigned, num, PAGE_SIZE - offset); req->pages[req->num_pages] = page; + req->page_descs[req->num_pages].offset = offset; req->page_descs[req->num_pages].length = this_num; req->num_pages++; @@ -1981,10 +1981,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2002,7 +2000,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2024,10 +2024,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); + pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); + pipe_unlock(pipe); -out: kfree(bufs); return ret; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 52514a64dcd6..19ea122a7d03 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1777,7 +1777,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, spin_unlock(&fc->lock); dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(page, NR_WRITEBACK_TEMP); + dec_node_page_state(new_req->pages[0], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); fuse_writepage_free(fc, new_req); fuse_request_free(new_req); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 11066d8647d2..d5284d0dbdb5 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -107,7 +107,7 @@ static int glock_wake_function(wait_queue_entry_t *wait, unsigned int mode, static wait_queue_head_t *glock_waitqueue(struct lm_lockname *name) { - u32 hash = jhash2((u32 *)name, sizeof(*name) / 4, 0); + u32 hash = jhash2((u32 *)name, ht_parms.key_len / 4, 0); return glock_wait_table + hash_32(hash, GLOCK_WAIT_TABLE_BITS); } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 2a6ed036d207..dd28a9b287da 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -730,11 +730,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; - struct resv_map *resv_map; + struct resv_map *resv_map = NULL; - resv_map = resv_map_alloc(); - if (!resv_map) - return NULL; + /* + * Reserve maps are only needed for inodes that can have associated + * page allocations. + */ + if (S_ISREG(mode) || S_ISLNK(mode)) { + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; + } inode = new_inode(sb); if (inode) { @@ -766,8 +772,10 @@ 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); + } else { + if (resv_map) + kref_put(&resv_map->refs, resv_map_release); + } return inode; } @@ -845,6 +853,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; + + /* + * page_private is subpool pointer in hugetlb pages. Transfer to + * new page. PagePrivate is not associated with page_private for + * hugetlb pages and can not be set here as only page_huge_active + * pages can be migrated. + */ + if (page_private(page)) { + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + } + if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); else diff --git a/fs/iomap.c b/fs/iomap.c index 6a5f3d0ce87c..4966abd956d4 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -753,7 +753,8 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio) err = invalidate_inode_pages2_range(inode->i_mapping, offset >> PAGE_SHIFT, (offset + dio->size - 1) >> PAGE_SHIFT); - WARN_ON_ONCE(err); + if (err) + dio_warn_stale_pagecache(iocb->ki_filp); } inode_dio_end(file_inode(iocb->ki_filp)); @@ -1010,9 +1011,16 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret) goto out_free_dio; + /* + * Try to invalidate cache pages for the range we're direct + * writing. If this invalidation fails, tough, the write will + * still work, but racing two incompatible write paths is a + * pretty crazy thing to do, so we don't support it 100%. + */ ret = invalidate_inode_pages2_range(mapping, start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(ret); + if (ret) + dio_warn_stale_pagecache(iocb->ki_filp); ret = 0; if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion && diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 3c1c31321d9b..d11401afd52f 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -693,9 +693,11 @@ void jbd2_journal_commit_transaction(journal_t *journal) the last tag we set up. */ tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG); - - jbd2_descriptor_block_csum_set(journal, descriptor); start_journal_io: + if (descriptor) + jbd2_descriptor_block_csum_set(journal, + descriptor); + for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; /* diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 61d48f0c41a1..0c8f77db60e2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1343,6 +1343,10 @@ static int journal_reset(journal_t *journal) return jbd2_journal_start_thread(journal); } +/* + * This function expects that the caller will have locked the journal + * buffer head, and will return with it unlocked + */ static int jbd2_write_superblock(journal_t *journal, int write_flags) { struct buffer_head *bh = journal->j_sb_buffer; @@ -1352,7 +1356,6 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); - lock_buffer(bh); if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal @@ -1411,6 +1414,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", tail_block, tail_tid); + lock_buffer(journal->j_sb_buffer); sb->s_sequence = cpu_to_be32(tail_tid); sb->s_start = cpu_to_be32(tail_block); @@ -1441,18 +1445,17 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op) journal_superblock_t *sb = journal->j_superblock; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); - read_lock(&journal->j_state_lock); - /* Is it already empty? */ - if (sb->s_start == 0) { - read_unlock(&journal->j_state_lock); + lock_buffer(journal->j_sb_buffer); + if (sb->s_start == 0) { /* Is it already empty? */ + unlock_buffer(journal->j_sb_buffer); return; } + jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); sb->s_start = cpu_to_be32(0); - read_unlock(&journal->j_state_lock); jbd2_write_superblock(journal, write_op); @@ -1475,9 +1478,8 @@ void jbd2_journal_update_sb_errno(journal_t *journal) journal_superblock_t *sb = journal->j_superblock; int errcode; - read_lock(&journal->j_state_lock); + lock_buffer(journal->j_sb_buffer); errcode = journal->j_errno; - read_unlock(&journal->j_state_lock); if (errcode == -ESHUTDOWN) errcode = 0; jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); @@ -1881,28 +1883,27 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, sb = journal->j_superblock; + /* Load the checksum driver if necessary */ + if ((journal->j_chksum_driver == NULL) && + INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); + journal->j_chksum_driver = NULL; + return 0; + } + /* Precompute checksum seed for all metadata */ + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); + } + + lock_buffer(journal->j_sb_buffer); + /* If enabling v3 checksums, update superblock */ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); - - /* Load the checksum driver */ - if (journal->j_chksum_driver == NULL) { - journal->j_chksum_driver = crypto_alloc_shash("crc32c", - 0, 0); - if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD2: Cannot load crc32c " - "driver.\n"); - journal->j_chksum_driver = NULL; - return 0; - } - - /* Precompute checksum seed for all metadata */ - journal->j_csum_seed = jbd2_chksum(journal, ~0, - sb->s_uuid, - sizeof(sb->s_uuid)); - } } /* If enabling v1 checksums, downgrade superblock */ @@ -1914,6 +1915,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); + unlock_buffer(journal->j_sb_buffer); return 1; #undef COMPAT_FEATURE_ON diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e42736c1fdc8..650927f0a2dc 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1224,11 +1224,12 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; char *committed_data = NULL; - JBUFFER_TRACE(jh, "entry"); if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); + JBUFFER_TRACE(jh, "entry"); + /* * Do this first --- it can drop the journal lock, so we want to * make sure that obtaining the committed_data is done @@ -1339,15 +1340,17 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) if (is_handle_aborted(handle)) return -EROFS; - if (!buffer_jbd(bh)) { - ret = -EUCLEAN; - goto out; - } + if (!buffer_jbd(bh)) + return -EUCLEAN; + /* * We don't grab jh reference here since the buffer must be part * of the running transaction. */ jh = bh2jh(bh); + jbd_debug(5, "journal_head %p\n", jh); + JBUFFER_TRACE(jh, "entry"); + /* * This and the following assertions are unreliable since we may see jh * in inconsistent state unless we grab bh_state lock. But this is @@ -1381,9 +1384,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) } journal = transaction->t_journal; - jbd_debug(5, "journal_head %p\n", jh); - JBUFFER_TRACE(jh, "entry"); - jbd_lock_bh_state(bh); if (jh->b_modified == 0) { @@ -1581,14 +1581,21 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) /* However, if the buffer is still owned by a prior * (committing) transaction, we can't drop it yet... */ JBUFFER_TRACE(jh, "belongs to older transaction"); - /* ... but we CAN drop it from the new transaction if we - * have also modified it since the original commit. */ + /* ... but we CAN drop it from the new transaction through + * marking the buffer as freed and set j_next_transaction to + * the new transaction, so that not only the commit code + * knows it should clear dirty bits when it is done with the + * buffer, but also the buffer can be checkpointed only + * after the new transaction commits. */ - if (jh->b_next_transaction) { - J_ASSERT(jh->b_next_transaction == transaction); + set_buffer_freed(bh); + + if (!jh->b_next_transaction) { spin_lock(&journal->j_list_lock); - jh->b_next_transaction = NULL; + jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); + } else { + J_ASSERT(jh->b_next_transaction == transaction); /* * only drop a reference if this transaction modified diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 389ea53ea487..bccfc40b3a74 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - if (f->target) { - kfree(f->target); - f->target = NULL; - } - fds = f->dents; while(fds) { fd = fds; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 83340496645b..9a9f30eddbbb 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) static void jffs2_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); + struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + + kfree(f->target); + kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_destroy_inode(struct inode *inode) diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 95a7c88baed9..5019058e0f6a 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -196,8 +196,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, return dentry; knparent = find_next_ancestor(kn, NULL); - if (WARN_ON(!knparent)) + if (WARN_ON(!knparent)) { + dput(dentry); return ERR_PTR(-EINVAL); + } do { struct dentry *dtmp; @@ -206,8 +208,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, if (kn == knparent) return dentry; kntmp = find_next_ancestor(kn, knparent); - if (WARN_ON(!kntmp)) + if (WARN_ON(!kntmp)) { + dput(dentry); return ERR_PTR(-EINVAL); + } dtmp = lookup_one_len_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 7d6ddfd60271..a98d64a6eda5 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -459,7 +459,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, case XPRT_TRANSPORT_RDMA: if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_TCP_RETRANS; - if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) + if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_TCP_TIMEOUT) to->to_initval = NFS_MAX_TCP_TIMEOUT; diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index b6f9d84ba19b..ae2d6f220627 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -44,6 +44,7 @@ #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> +#include <keys/request_key_auth-type.h> #include <linux/module.h> #include "internal.h" @@ -59,7 +60,7 @@ static struct key_type key_type_id_resolver_legacy; struct idmap_legacy_upcalldata { struct rpc_pipe_msg pipe_msg; struct idmap_msg idmap_msg; - struct key_construction *key_cons; + struct key *authkey; struct idmap *idmap; }; @@ -384,7 +385,7 @@ static const match_table_t nfs_idmap_tokens = { { Opt_find_err, NULL } }; -static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); +static int nfs_idmap_legacy_upcall(struct key *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); static void idmap_release_pipe(struct inode *); @@ -545,11 +546,12 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, static void nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) { - struct key_construction *cons = idmap->idmap_upcall_data->key_cons; + struct key *authkey = idmap->idmap_upcall_data->authkey; kfree(idmap->idmap_upcall_data); idmap->idmap_upcall_data = NULL; - complete_request_key(cons, ret); + complete_request_key(authkey, ret); + key_put(authkey); } static void @@ -559,15 +561,14 @@ nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) nfs_idmap_complete_pipe_upcall_locked(idmap, ret); } -static int nfs_idmap_legacy_upcall(struct key_construction *cons, - const char *op, - void *aux) +static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) { struct idmap_legacy_upcalldata *data; + struct request_key_auth *rka = get_request_key_auth(authkey); struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; - struct key *key = cons->key; + struct key *key = rka->target_key; int ret = -ENOKEY; if (!aux) @@ -582,7 +583,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, msg = &data->pipe_msg; im = &data->idmap_msg; data->idmap = idmap; - data->key_cons = cons; + data->authkey = key_get(authkey); ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) @@ -600,7 +601,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, out2: kfree(data); out1: - complete_request_key(cons, ret); + complete_request_key(authkey, ret); return ret; } @@ -647,9 +648,10 @@ out: static ssize_t idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { + struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; - struct key_construction *cons; + struct key *authkey; struct idmap_msg im; size_t namelen_in; int ret = -ENOKEY; @@ -661,7 +663,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (idmap->idmap_upcall_data == NULL) goto out_noupcall; - cons = idmap->idmap_upcall_data->key_cons; + authkey = idmap->idmap_upcall_data->authkey; + rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { ret = -ENOSPC; @@ -686,9 +689,9 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) ret = nfs_idmap_read_and_verify_message(&im, &idmap->idmap_upcall_data->idmap_msg, - cons->key, cons->authkey); + rka->target_key, authkey); if (ret >= 0) { - key_set_timeout(cons->key, nfs_idmap_cache_timeout); + key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a3b67d3b1dfb..a225f98c9903 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -914,6 +914,13 @@ nfs4_sequence_process_interrupted(struct nfs_client *client, #endif /* !CONFIG_NFS_V4_1 */ +static void nfs41_sequence_res_init(struct nfs4_sequence_res *res) +{ + res->sr_timestamp = jiffies; + res->sr_status_flags = 0; + res->sr_status = 1; +} + static void nfs4_sequence_attach_slot(struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, @@ -925,10 +932,6 @@ void nfs4_sequence_attach_slot(struct nfs4_sequence_args *args, args->sa_slot = slot; res->sr_slot = slot; - res->sr_timestamp = jiffies; - res->sr_status_flags = 0; - res->sr_status = 1; - } int nfs4_setup_sequence(struct nfs_client *client, @@ -974,6 +977,7 @@ int nfs4_setup_sequence(struct nfs_client *client, trace_nfs4_setup_sequence(session, args); out_start: + nfs41_sequence_res_init(res); rpc_call_start(task); return 0; @@ -2742,7 +2746,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, nfs4_schedule_stateid_recovery(server, state); } out: - nfs4_sequence_free_slot(&opendata->o_res.seq_res); + if (!opendata->cancelled) + nfs4_sequence_free_slot(&opendata->o_res.seq_res); return ret; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 37f20d7a26ed..28b013d1d44a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -988,6 +988,17 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) } } +static void +nfs_pageio_cleanup_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + LIST_HEAD(head); + + nfs_list_remove_request(req); + nfs_list_add_request(req, &head); + desc->pg_completion_ops->error_cleanup(&head); +} + /** * nfs_pageio_add_request - Attempt to coalesce a request into a page list. * @desc: destination io descriptor @@ -1025,10 +1036,8 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_page_group_unlock(req); desc->pg_moreio = 1; nfs_pageio_doio(desc); - if (desc->pg_error < 0) - return 0; - if (mirror->pg_recoalesce) - return 0; + if (desc->pg_error < 0 || mirror->pg_recoalesce) + goto out_cleanup_subreq; /* retry add_request for this subreq */ nfs_page_group_lock(req); continue; @@ -1061,6 +1070,10 @@ err_ptr: desc->pg_error = PTR_ERR(subreq); nfs_page_group_unlock(req); return 0; +out_cleanup_subreq: + if (req != subreq) + nfs_pageio_cleanup_request(desc, subreq); + return 0; } static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) @@ -1079,7 +1092,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) struct nfs_page *req; req = list_first_entry(&head, struct nfs_page, wb_list); - nfs_list_remove_request(req); if (__nfs_pageio_add_request(desc, req)) continue; if (desc->pg_error < 0) { @@ -1168,11 +1180,14 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (nfs_pgio_has_mirroring(desc)) desc->pg_mirror_idx = midx; if (!nfs_pageio_add_request_mirror(desc, dupreq)) - goto out_failed; + goto out_cleanup_subreq; } return 1; +out_cleanup_subreq: + if (req != dupreq) + nfs_pageio_cleanup_request(desc, dupreq); out_failed: /* remember fatal errors */ if (nfs_error_is_fatal(desc->pg_error)) @@ -1198,7 +1213,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); - if (!mirror->pg_recoalesce) + if (desc->pg_error < 0 || !mirror->pg_recoalesce) break; if (!nfs_do_recoalesce(desc)) break; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 38de09b08e96..f464f8d9060c 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1901,6 +1901,11 @@ static int nfs_parse_devname(const char *dev_name, size_t len; char *end; + if (unlikely(!dev_name || !*dev_name)) { + dfprintk(MOUNT, "NFS: device name not specified\n"); + return -EINVAL; + } + /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); @@ -2039,7 +2044,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) @@ -2401,8 +2407,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->acdirmax != b->acdirmax) goto Ebusy; - if (b->auth_info.flavor_len > 0 && - clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) + if (clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) goto Ebusy; return 1; Ebusy: diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2d956a7d5378..50ed3944d183 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -236,9 +236,9 @@ out: } /* A writeback failed: mark the page as bad, and invalidate the page cache */ -static void nfs_set_pageerror(struct page *page) +static void nfs_set_pageerror(struct address_space *mapping) { - nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); + nfs_zap_mapping(mapping->host, mapping); } /* @@ -994,7 +994,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - nfs_set_pageerror(req->wb_page); + nfs_set_pageerror(page_file_mapping(req->wb_page)); nfs_context_set_write_error(req->wb_context, hdr->error); goto remove_req; } @@ -1330,7 +1330,8 @@ int nfs_updatepage(struct file *file, struct page *page, unsigned int offset, unsigned int count) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct inode *inode = page_file_mapping(page)->host; + struct address_space *mapping = page_file_mapping(page); + struct inode *inode = mapping->host; int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -1348,7 +1349,7 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) - nfs_set_pageerror(page); + nfs_set_pageerror(mapping); else __set_page_dirty_nobuffers(page); out: diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 1d0ce3c57d93..c0de4d6cd857 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -446,8 +446,19 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); resp->count = resp->buffer - argp->buffer; - if (resp->offset) - xdr_encode_hyper(resp->offset, argp->cookie); + if (resp->offset) { + loff_t offset = argp->cookie; + + if (unlikely(resp->offset1)) { + /* we ended up with offset on a page boundary */ + *resp->offset = htonl(offset >> 32); + *resp->offset1 = htonl(offset & 0xffffffff); + resp->offset1 = NULL; + } else { + xdr_encode_hyper(resp->offset, offset); + } + resp->offset = NULL; + } RETURN_STATUS(nfserr); } @@ -516,6 +527,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp) } else { xdr_encode_hyper(resp->offset, offset); } + resp->offset = NULL; } RETURN_STATUS(nfserr); diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index f38acd905441..ef3e7878456c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -922,6 +922,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, } else { xdr_encode_hyper(cd->offset, offset64); } + cd->offset = NULL; } /* diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 49b0a9e7ff18..80aeb19b176b 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -939,8 +939,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -967,6 +968,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -1004,6 +1008,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1211,6 +1216,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 3cef6bfa09d4..94128643ec1a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1472,8 +1472,10 @@ free_session_slots(struct nfsd4_session *ses) { int i; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) + for (i = 0; i < ses->se_fchannel.maxreqs; i++) { + free_svc_cred(&ses->se_slots[i]->sl_cred); kfree(ses->se_slots[i]); + } } /* @@ -2331,14 +2333,18 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) dprintk("--> %s slot %p\n", __func__, slot); + slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; slot->sl_status = resp->cstate.status; + free_svc_cred(&slot->sl_cred); + copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); - slot->sl_flags |= NFSD4_SLOT_INITIALIZED; - if (nfsd4_not_cached(resp)) { - slot->sl_datalen = 0; + if (!nfsd4_cache_this(resp)) { + slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } + slot->sl_flags |= NFSD4_SLOT_CACHED; + base = resp->cstate.data_offset; slot->sl_datalen = buf->len - base; if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) @@ -2365,8 +2371,16 @@ nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args, op = &args->ops[resp->opcnt - 1]; nfsd4_encode_operation(resp, op); - /* Return nfserr_retry_uncached_rep in next operation. */ - if (args->opcnt > 1 && !(slot->sl_flags & NFSD4_SLOT_CACHETHIS)) { + if (slot->sl_flags & NFSD4_SLOT_CACHED) + return op->status; + if (args->opcnt == 1) { + /* + * The original operation wasn't a solo sequence--we + * always cache those--so this retry must not match the + * original: + */ + op->status = nfserr_seq_false_retry; + } else { op = &args->ops[resp->opcnt++]; op->status = nfserr_retry_uncached_rep; nfsd4_encode_operation(resp, op); @@ -3030,6 +3044,34 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp, return xb->len > session->se_fchannel.maxreq_sz; } +static bool replay_matches_cache(struct svc_rqst *rqstp, + struct nfsd4_sequence *seq, struct nfsd4_slot *slot) +{ + struct nfsd4_compoundargs *argp = rqstp->rq_argp; + + if ((bool)(slot->sl_flags & NFSD4_SLOT_CACHETHIS) != + (bool)seq->cachethis) + return false; + /* + * If there's an error than the reply can have fewer ops than + * the call. But if we cached a reply with *more* ops than the + * call you're sending us now, then this new call is clearly not + * really a replay of the old one: + */ + if (slot->sl_opcnt < argp->opcnt) + return false; + /* This is the only check explicitly called by spec: */ + if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) + return false; + /* + * There may be more comparisons we could actually do, but the + * spec doesn't require us to catch every case where the calls + * don't match (that would require caching the call as well as + * the reply), so we don't bother. + */ + return true; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -3089,6 +3131,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) goto out_put_session; + status = nfserr_seq_false_retry; + if (!replay_matches_cache(rqstp, seq, slot)) + goto out_put_session; cstate->slot = slot; cstate->session = session; cstate->clp = clp; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 6493df6b1bd5..d44402241d9e 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1126,6 +1126,8 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': + if (!nn->nfsd_serv) + return -EBUSY; nfsd4_end_grace(nn); break; default: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 005c911b34ac..133d8bf62a5c 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -69,6 +69,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { @@ -169,11 +170,13 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) struct nfsd4_slot { u32 sl_seqid; __be32 sl_status; + struct svc_cred sl_cred; u32 sl_datalen; u16 sl_opcnt; #define NFSD4_SLOT_INUSE (1 << 0) #define NFSD4_SLOT_CACHETHIS (1 << 1) #define NFSD4_SLOT_INITIALIZED (1 << 2) +#define NFSD4_SLOT_CACHED (1 << 3) u8 sl_flags; char sl_data[]; }; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index aa4375eac475..f47c392cbd57 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -651,9 +651,18 @@ static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE; } -static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) +/* + * The session reply cache only needs to cache replies that the client + * actually asked us to. But it's almost free for us to cache compounds + * consisting of only a SEQUENCE op, so we may as well cache those too. + * Also, the protocol doesn't give us a convenient response in the case + * of a replay of a solo SEQUENCE op that wasn't cached + * (RETRY_UNCACHED_REP can only be returned in the second op of a + * compound). + */ +static inline bool nfsd4_cache_this(struct nfsd4_compoundres *resp) { - return !(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS) + return (resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS) || nfsd4_is_solo_sequence(resp); } diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile index 99ee093182cb..cc9b32b9db7c 100644 --- a/fs/ocfs2/Makefile +++ b/fs/ocfs2/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y := -Ifs/ocfs2 +ccflags-y := -I$(src) obj-$(CONFIG_OCFS2_FS) += \ ocfs2.o \ diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 1d098c3c00e0..9f8250df99f1 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -152,7 +152,6 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, #endif } - clear_buffer_uptodate(bh); get_bh(bh); /* for end_buffer_read_sync() */ bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); @@ -306,7 +305,6 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, continue; } - clear_buffer_uptodate(bh); get_bh(bh); /* for end_buffer_read_sync() */ if (validate) set_buffer_needs_validate(bh); diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index c204ac9b49e5..81a0d5d82757 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -621,13 +621,15 @@ static void o2nm_node_group_drop_item(struct config_group *group, struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent); - o2net_disconnect_node(node); + if (cluster->cl_nodes[node->nd_num] == node) { + o2net_disconnect_node(node); - if (cluster->cl_has_local && - (cluster->cl_local_node == node->nd_num)) { - cluster->cl_has_local = 0; - cluster->cl_local_node = O2NM_INVALID_NODE_NUM; - o2net_stop_listening(node); + if (cluster->cl_has_local && + (cluster->cl_local_node == node->nd_num)) { + cluster->cl_has_local = 0; + cluster->cl_local_node = O2NM_INVALID_NODE_NUM; + o2net_stop_listening(node); + } } /* XXX call into net to stop this node from trading messages */ diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile index bd1aab1f49a4..ef2854422a6e 100644 --- a/fs/ocfs2/dlm/Makefile +++ b/fs/ocfs2/dlm/Makefile @@ -1,4 +1,4 @@ -ccflags-y := -Ifs/ocfs2 +ccflags-y := -I$(src)/.. obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile index eed3db8c5b49..33431a0296a3 100644 --- a/fs/ocfs2/dlmfs/Makefile +++ b/fs/ocfs2/dlmfs/Makefile @@ -1,4 +1,4 @@ -ccflags-y := -Ifs/ocfs2 +ccflags-y := -I$(src)/.. obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 824f407df1db..3a4e1bca5e31 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4716,22 +4716,23 @@ out: /* Lock an inode and grab a bh pointing to the inode. */ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, - struct buffer_head **bh1, + struct buffer_head **bh_s, struct inode *t_inode, - struct buffer_head **bh2) + struct buffer_head **bh_t) { - struct inode *inode1; - struct inode *inode2; + struct inode *inode1 = s_inode; + struct inode *inode2 = t_inode; struct ocfs2_inode_info *oi1; struct ocfs2_inode_info *oi2; + struct buffer_head *bh1 = NULL; + struct buffer_head *bh2 = NULL; bool same_inode = (s_inode == t_inode); + bool need_swap = (inode1->i_ino > inode2->i_ino); int status; /* First grab the VFS and rw locks. */ lock_two_nondirectories(s_inode, t_inode); - inode1 = s_inode; - inode2 = t_inode; - if (inode1->i_ino > inode2->i_ino) + if (need_swap) swap(inode1, inode2); status = ocfs2_rw_lock(inode1, 1); @@ -4754,17 +4755,13 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno); - if (*bh1) - *bh1 = NULL; - if (*bh2) - *bh2 = NULL; - /* We always want to lock the one with the lower lockid first. */ if (oi1->ip_blkno > oi2->ip_blkno) mlog_errno(-ENOLCK); /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); + status = ocfs2_inode_lock_nested(inode1, &bh1, 1, + OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -4773,15 +4770,25 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, /* lock id2 */ if (!same_inode) { - status = ocfs2_inode_lock_nested(inode2, bh2, 1, + status = ocfs2_inode_lock_nested(inode2, &bh2, 1, OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto out_cl1; } - } else - *bh2 = *bh1; + } else { + bh2 = bh1; + } + + /* + * If we swapped inode order above, we have to swap the buffer heads + * before passing them back to the caller. + */ + if (need_swap) + swap(bh1, bh2); + *bh_s = bh1; + *bh_t = bh2; trace_ocfs2_double_lock_end( (unsigned long long)OCFS2_I(inode1)->ip_blkno, @@ -4791,8 +4798,7 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode, out_cl1: ocfs2_inode_unlock(inode1, 1); - brelse(*bh1); - *bh1 = NULL; + brelse(bh1); out_rw2: ocfs2_rw_unlock(inode2, 1); out_i2: diff --git a/fs/open.c b/fs/open.c index 7ea118471dce..28a3956c4479 100644 --- a/fs/open.c +++ b/fs/open.c @@ -716,6 +716,12 @@ static int do_dentry_open(struct file *f, return 0; } + /* Any file opened for execve()/uselib() has to be a regular file. */ + if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) { + error = -EACCES; + goto cleanup_file; + } + if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) diff --git a/fs/pipe.c b/fs/pipe.c index 8ef7d7bef775..fa3c2c25cec5 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -194,9 +194,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); @@ -239,6 +239,14 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = anon_pipe_buf_release, + .steal = anon_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + static const struct pipe_buf_operations packet_pipe_buf_ops = { .can_merge = 0, .confirm = generic_pipe_buf_confirm, @@ -247,6 +255,12 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +void pipe_buf_mark_unmergeable(struct pipe_buffer *buf) +{ + if (buf->ops == &anon_pipe_buf_ops) + buf->ops = &anon_pipe_buf_nomerge_ops; +} + static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { diff --git a/fs/proc/base.c b/fs/proc/base.c index 9063738ff1f0..64695dcf89f3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1108,10 +1108,6 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { - pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n", - task_pid_nr(p), p->comm, - p->signal->oom_score_adj, oom_adj, - task_pid_nr(task), task->comm); p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index f69c545f5868..555698ddb943 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1620,8 +1620,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - put_links(header); - start_unregistering(header); + if (parent) { + put_links(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2b47757c9c68..309d24118f9a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -459,7 +459,7 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty) + bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -486,24 +486,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + if (locked) + mss->pss_locked += (u64)size << PSS_SHIFT; return; } for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); + unsigned long pss = (PAGE_SIZE << PSS_SHIFT); if (mapcount >= 2) { if (dirty || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; - mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + mss->pss += pss / mapcount; + if (locked) + mss->pss_locked += pss / mapcount; } else { if (dirty || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; - mss->pss += PAGE_SIZE << PSS_SHIFT; + mss->pss += pss; + if (locked) + mss->pss_locked += pss; } } } @@ -526,6 +533,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; if (pte_present(*pte)) { @@ -568,7 +576,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -577,6 +585,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -591,7 +600,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -792,11 +801,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) } } #endif - /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); - if (vma->vm_flags & VM_LOCKED) - mss->pss_locked += mss->pss; if (!rollup_mode) { show_map_vma(m, vma, is_pid); @@ -1154,6 +1160,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/read_write.c b/fs/read_write.c index 57a00ef895b2..1c3eada2fe25 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1235,6 +1235,9 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { + if (pos == -1) + return do_compat_readv(fd, vec, vlen, flags); + return do_compat_preadv64(fd, vec, vlen, pos, flags); } #endif @@ -1341,6 +1344,9 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { + if (pos == -1) + return do_compat_writev(fd, vec, vlen, flags); + return do_compat_pwritev64(fd, vec, vlen, pos, flags); } #endif diff --git a/fs/splice.c b/fs/splice.c index f3084cce0ea6..c84ac7e97e21 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -332,8 +332,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = { .get = generic_pipe_buf_get, }; -static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { return 1; } @@ -1571,7 +1571,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1580,6 +1584,8 @@ retry: */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + obuf->len = len; opipe->nrbufs++; ibuf->offset += obuf->len; @@ -1643,7 +1649,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; @@ -1654,6 +1664,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + if (obuf->len > len) obuf->len = len; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8dacf4f57414..28b9d7cca29b 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1357,6 +1357,12 @@ reread: iinfo->i_alloc_type = le16_to_cpu(fe->icbTag.flags) & ICBTAG_FLAG_AD_MASK; + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_SHORT && + iinfo->i_alloc_type != ICBTAG_FLAG_AD_LONG && + iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { + ret = -EIO; + goto out; + } iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 42b8c57795cb..c6ce7503a329 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -260,6 +260,9 @@ void udf_truncate_extents(struct inode *inode) epos.block = eloc; epos.bh = udf_tread(sb, udf_get_lb_pblock(sb, &eloc, 0)); + /* Error reading indirect block? */ + if (!epos.bh) + return; if (elen) indirect_ext_len = (elen + sb->s_blocksize - 1) >> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 5f10052d2671..7a908d683258 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -627,6 +627,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -867,6 +869,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -889,6 +893,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1327,6 +1332,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1514,6 +1521,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index ea66f04f46f7..e4265db08e4b 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -212,6 +212,7 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; + struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_defer_ops dfops; struct xfs_trans_res tres; @@ -327,9 +328,16 @@ xfs_attr_set( * GROT: another possible req'mt for a double-split btree op. */ xfs_defer_init(args.dfops, args.firstblock); - error = xfs_attr_shortform_to_leaf(&args); + error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); if (error) goto out_defer_cancel; + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + */ + xfs_trans_bhold(args.trans, leaf_bp); + xfs_defer_bjoin(args.dfops, leaf_bp); xfs_defer_ijoin(args.dfops, dp); error = xfs_defer_finish(&args.trans, args.dfops); if (error) @@ -337,13 +345,14 @@ xfs_attr_set( /* * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf. + * transaction to add the new attribute to the leaf, which + * means that we have to hold & join the leaf buffer here too. */ - error = xfs_trans_roll_inode(&args.trans, dp); if (error) goto out; - + xfs_trans_bjoin(args.trans, leaf_bp); + leaf_bp = NULL; } if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) @@ -374,8 +383,9 @@ xfs_attr_set( out_defer_cancel: xfs_defer_cancel(&dfops); - args.trans = NULL; out: + if (leaf_bp) + xfs_trans_brelse(args.trans, leaf_bp); if (args.trans) xfs_trans_cancel(args.trans); xfs_iunlock(dp, XFS_ILOCK_EXCL); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 40e53a4fc0a6..73a541755d5b 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -739,10 +739,13 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args) } /* - * Convert from using the shortform to the leaf. + * Convert from using the shortform to the leaf. On success, return the + * buffer so that we can keep it locked until we're totally done with it. */ int -xfs_attr_shortform_to_leaf(xfs_da_args_t *args) +xfs_attr_shortform_to_leaf( + struct xfs_da_args *args, + struct xfs_buf **leaf_bp) { xfs_inode_t *dp; xfs_attr_shortform_t *sf; @@ -821,7 +824,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) sfe = XFS_ATTR_SF_NEXTENTRY(sfe); } error = 0; - + *leaf_bp = bp; out: kmem_free(tmpbuffer); return error; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index f7dda0c237b0..894124efb421 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -48,7 +48,8 @@ void xfs_attr_shortform_create(struct xfs_da_args *args); void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff); int xfs_attr_shortform_lookup(struct xfs_da_args *args); int xfs_attr_shortform_getvalue(struct xfs_da_args *args); -int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); +int xfs_attr_shortform_to_leaf(struct xfs_da_args *args, + struct xfs_buf **leaf_bp); int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 072ebfe1d6ae..087fea02c389 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -249,6 +249,10 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE); + /* Hold the (previously bjoin'd) buffer locked across the roll. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) + xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]); + trace_xfs_defer_trans_roll((*tp)->t_mountp, dop); /* Roll the transaction. */ @@ -264,6 +268,12 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0); + /* Rejoin the buffers and dirty them so the log moves forward. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) { + xfs_trans_bjoin(*tp, dop->dop_bufs[i]); + xfs_trans_bhold(*tp, dop->dop_bufs[i]); + } + return error; } @@ -295,6 +305,31 @@ xfs_defer_ijoin( } } + ASSERT(0); + return -EFSCORRUPTED; +} + +/* + * Add this buffer to the deferred op. Each joined buffer is relogged + * each time we roll the transaction. + */ +int +xfs_defer_bjoin( + struct xfs_defer_ops *dop, + struct xfs_buf *bp) +{ + int i; + + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) { + if (dop->dop_bufs[i] == bp) + return 0; + else if (dop->dop_bufs[i] == NULL) { + dop->dop_bufs[i] = bp; + return 0; + } + } + + ASSERT(0); return -EFSCORRUPTED; } @@ -493,9 +528,7 @@ xfs_defer_init( struct xfs_defer_ops *dop, xfs_fsblock_t *fbp) { - dop->dop_committed = false; - dop->dop_low = false; - memset(&dop->dop_inodes, 0, sizeof(dop->dop_inodes)); + memset(dop, 0, sizeof(struct xfs_defer_ops)); *fbp = NULLFSBLOCK; INIT_LIST_HEAD(&dop->dop_intake); INIT_LIST_HEAD(&dop->dop_pending); diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index d4f046dd44bd..045beacdd37d 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -59,6 +59,7 @@ enum xfs_defer_ops_type { }; #define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */ +#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */ struct xfs_defer_ops { bool dop_committed; /* did any trans commit? */ @@ -66,8 +67,9 @@ struct xfs_defer_ops { struct list_head dop_intake; /* unlogged pending work */ struct list_head dop_pending; /* logged pending work */ - /* relog these inodes with each roll */ + /* relog these with each roll */ struct xfs_inode *dop_inodes[XFS_DEFER_OPS_NR_INODES]; + struct xfs_buf *dop_bufs[XFS_DEFER_OPS_NR_BUFS]; }; void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type, @@ -77,6 +79,7 @@ void xfs_defer_cancel(struct xfs_defer_ops *dop); void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp); bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop); int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip); +int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp); /* Description of a deferred type. */ struct xfs_defer_op_type { |