diff options
Diffstat (limited to 'fs')
36 files changed, 465 insertions, 182 deletions
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_file.c b/fs/9p/vfs_file.c index ab3d5f5dbb00..c87e6d6ec069 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -442,7 +442,11 @@ 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 85ff859d3af5..72b779bc0942 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; @@ -1092,7 +1092,7 @@ 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); @@ -1170,12 +1170,13 @@ 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]; @@ -1216,10 +1217,11 @@ 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; } @@ -1416,9 +1418,9 @@ 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); @@ -1431,16 +1433,13 @@ 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 4823e1c46999..a950a927a626 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) @@ -496,7 +496,7 @@ 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; @@ -607,11 +607,13 @@ 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); @@ -631,7 +633,8 @@ 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) { @@ -661,8 +664,9 @@ 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; } @@ -928,9 +932,9 @@ 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); @@ -942,16 +946,13 @@ 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 48ce50484e80..eeab9953af89 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/btrfs/acl.c b/fs/btrfs/acl.c index 3b66c957ea6f..5810463dc6d2 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -9,6 +9,7 @@ #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" @@ -72,8 +73,16 @@ 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/disk-io.c b/fs/btrfs/disk-io.c index d96d1390068a..b4f61a3d560a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -17,6 +17,7 @@ #include <linux/semaphore.h> #include <linux/error-injection.h> #include <linux/crc32c.h> +#include <linux/sched/mm.h> #include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" @@ -1236,10 +1237,17 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *root; struct btrfs_key key; + unsigned int nofs_flag; int ret = 0; uuid_le uuid = NULL_UUID_LE; + /* + * We're holding a transaction handle, so use a NOFS memory allocation + * context to avoid deadlock if reclaim happens. + */ + nofs_flag = memalloc_nofs_save(); root = btrfs_alloc_root(fs_info, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!root) return ERR_PTR(-ENOMEM); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 79f82f2ec4d5..90b0a6eff535 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3002,11 +3002,11 @@ 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/volumes.c b/fs/btrfs/volumes.c index 285f64f2de5f..c13f62182513 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6425,10 +6425,10 @@ 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/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 9dcaed031843..80f33582059e 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -235,6 +235,8 @@ struct smb_version_operations { int * (*get_credits_field)(struct TCP_Server_Info *, const int); unsigned int (*get_credits)(struct mid_q_entry *); __u64 (*get_next_mid)(struct TCP_Server_Info *); + void (*revert_current_mid)(struct TCP_Server_Info *server, + const unsigned int val); /* data offset from read response message */ unsigned int (*read_data_offset)(char *); /* @@ -756,6 +758,22 @@ get_next_mid(struct TCP_Server_Info *server) return cpu_to_le16(mid); } +static inline void +revert_current_mid(struct TCP_Server_Info *server, const unsigned int val) +{ + if (server->ops->revert_current_mid) + server->ops->revert_current_mid(server, val); +} + +static inline void +revert_current_mid_from_hdr(struct TCP_Server_Info *server, + const struct smb2_sync_hdr *shdr) +{ + unsigned int num = le16_to_cpu(shdr->CreditCharge); + + return revert_current_mid(server, num > 0 ? num : 1); +} + static inline __u16 get_mid(const struct smb_hdr *smb) { @@ -1391,6 +1409,7 @@ struct mid_q_entry { struct kref refcount; struct TCP_Server_Info *server; /* server corresponding to this mid */ __u64 mid; /* multiplex id */ + __u16 credits; /* number of credits consumed by this mid */ __u32 pid; /* process id */ __u32 sequence_number; /* for CIFS signing */ unsigned long when_alloc; /* when mid was created */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 23db881daab5..08761a6a039d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2871,14 +2871,16 @@ 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; } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 7b8b58fb4d3f..58700d2ba8cd 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -517,7 +517,6 @@ 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 & @@ -537,13 +536,25 @@ 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; + 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); + queue_work(cifsoplockd_wq, &cfile->oplock_break); kfree(lw); return true; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 237d7281ada3..d4d7d61a6fe2 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -204,6 +204,15 @@ smb2_get_next_mid(struct TCP_Server_Info *server) return mid; } +static void +smb2_revert_current_mid(struct TCP_Server_Info *server, const unsigned int val) +{ + spin_lock(&GlobalMid_Lock); + if (server->CurrentMid >= val) + server->CurrentMid -= val; + spin_unlock(&GlobalMid_Lock); +} + static struct mid_q_entry * smb2_find_mid(struct TCP_Server_Info *server, char *buf) { @@ -2301,6 +2310,15 @@ 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) { @@ -3247,6 +3265,7 @@ struct smb_version_operations smb20_operations = { .get_credits = smb2_get_credits, .wait_mtu_credits = cifs_wait_mtu_credits, .get_next_mid = smb2_get_next_mid, + .revert_current_mid = smb2_revert_current_mid, .read_data_offset = smb2_read_data_offset, .read_data_length = smb2_read_data_length, .map_error = map_smb2_to_linux_error, @@ -3341,6 +3360,7 @@ struct smb_version_operations smb21_operations = { .get_credits = smb2_get_credits, .wait_mtu_credits = smb2_wait_mtu_credits, .get_next_mid = smb2_get_next_mid, + .revert_current_mid = smb2_revert_current_mid, .read_data_offset = smb2_read_data_offset, .read_data_length = smb2_read_data_length, .map_error = map_smb2_to_linux_error, @@ -3351,7 +3371,7 @@ 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, @@ -3436,6 +3456,7 @@ struct smb_version_operations smb30_operations = { .get_credits = smb2_get_credits, .wait_mtu_credits = smb2_wait_mtu_credits, .get_next_mid = smb2_get_next_mid, + .revert_current_mid = smb2_revert_current_mid, .read_data_offset = smb2_read_data_offset, .read_data_length = smb2_read_data_length, .map_error = map_smb2_to_linux_error, @@ -3447,7 +3468,7 @@ 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, @@ -3540,6 +3561,7 @@ struct smb_version_operations smb311_operations = { .get_credits = smb2_get_credits, .wait_mtu_credits = smb2_wait_mtu_credits, .get_next_mid = smb2_get_next_mid, + .revert_current_mid = smb2_revert_current_mid, .read_data_offset = smb2_read_data_offset, .read_data_length = smb2_read_data_length, .map_error = map_smb2_to_linux_error, @@ -3551,7 +3573,7 @@ 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/smb2transport.c b/fs/cifs/smb2transport.c index 7b351c65ee46..63264db78b89 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -576,6 +576,7 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr, struct TCP_Server_Info *server) { struct mid_q_entry *temp; + unsigned int credits = le16_to_cpu(shdr->CreditCharge); if (server == NULL) { cifs_dbg(VFS, "Null TCP session in smb2_mid_entry_alloc\n"); @@ -586,6 +587,7 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr, memset(temp, 0, sizeof(struct mid_q_entry)); kref_init(&temp->refcount); temp->mid = le64_to_cpu(shdr->MessageId); + temp->credits = credits > 0 ? credits : 1; temp->pid = current->pid; temp->command = shdr->Command; /* Always LE */ temp->when_alloc = jiffies; @@ -674,13 +676,18 @@ smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst) smb2_seq_num_into_buf(ses->server, shdr); rc = smb2_get_mid_entry(ses, shdr, &mid); - if (rc) + if (rc) { + revert_current_mid_from_hdr(ses->server, shdr); return ERR_PTR(rc); + } + rc = smb2_sign_rqst(rqst, ses->server); if (rc) { + revert_current_mid_from_hdr(ses->server, shdr); cifs_delete_mid(mid); return ERR_PTR(rc); } + return mid; } @@ -695,11 +702,14 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst) smb2_seq_num_into_buf(server, shdr); mid = smb2_mid_entry_alloc(shdr, server); - if (mid == NULL) + if (mid == NULL) { + revert_current_mid_from_hdr(server, shdr); return ERR_PTR(-ENOMEM); + } rc = smb2_sign_rqst(rqst, server); if (rc) { + revert_current_mid_from_hdr(server, shdr); DeleteMidQEntry(mid); return ERR_PTR(rc); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 66348b3d28e6..f2938bd95c40 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -638,6 +638,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, cifs_in_send_dec(server); if (rc < 0) { + revert_current_mid(server, mid->credits); server->sequence_number -= 2; cifs_delete_mid(mid); } @@ -842,6 +843,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, for (i = 0; i < num_rqst; i++) { midQ[i] = ses->server->ops->setup_request(ses, &rqst[i]); if (IS_ERR(midQ[i])) { + revert_current_mid(ses->server, i); for (j = 0; j < i; j++) cifs_delete_mid(midQ[j]); mutex_unlock(&ses->server->srv_mutex); @@ -867,8 +869,10 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, for (i = 0; i < num_rqst; i++) cifs_save_when_sent(midQ[i]); - if (rc < 0) + if (rc < 0) { + revert_current_mid(ses->server, num_rqst); ses->server->sequence_number -= 2; + } mutex_unlock(&ses->server->srv_mutex); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index c53814539070..553a3f3300ae 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -455,6 +455,7 @@ 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/ext2/super.c b/fs/ext2/super.c index 0c38e31ec938..364e647d87c0 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -761,7 +761,8 @@ 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 @@ -775,24 +776,34 @@ 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 032cf9b92665..2ddf7833350d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -435,6 +435,9 @@ 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/ioctl.c b/fs/ext4/ioctl.c index d37dafa1d133..2e76fb55d94a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -63,18 +63,20 @@ 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); swap(inode1->i_version, inode2->i_version); - swap(inode1->i_blocks, inode2->i_blocks); - swap(inode1->i_bytes, inode2->i_bytes); swap(inode1->i_atime, inode2->i_atime); 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); @@ -115,28 +117,41 @@ static long swap_inode_boot_loader(struct super_block *sb, int err; struct inode *inode_bl; struct ext4_inode_info *ei_bl; - - if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || - IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || - ext4_has_inline_data(inode)) - return -EINVAL; - - if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || - !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) - return -EPERM; + qsize_t size, size_bl, diff; + blkcnt_t blocks; + unsigned short bytes; inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); - filemap_flush(inode->i_mapping); - filemap_flush(inode_bl->i_mapping); - /* Protect orig inodes against a truncate and make sure, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); + if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || + IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || + ext4_has_inline_data(inode)) { + err = -EINVAL; + goto journal_err_out; + } + + if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || + !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto journal_err_out; + } + + down_write(&EXT4_I(inode)->i_mmap_sem); + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto err_out; + + err = filemap_write_and_wait(inode_bl->i_mapping); + if (err) + goto err_out; + /* Wait for all existing dio workers */ inode_dio_wait(inode); inode_dio_wait(inode_bl); @@ -147,7 +162,7 @@ static long swap_inode_boot_loader(struct super_block *sb, handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; - goto journal_err_out; + goto err_out; } /* Protect extent tree against block allocations via delalloc */ @@ -170,6 +185,13 @@ static long swap_inode_boot_loader(struct super_block *sb, memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); } + err = dquot_initialize(inode); + if (err) + goto err_out1; + + size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes; + size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes; + diff = size - size_bl; swap_inode_data(inode, inode_bl); inode->i_ctime = inode_bl->i_ctime = current_time(inode); @@ -183,27 +205,51 @@ static long swap_inode_boot_loader(struct super_block *sb, err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { + /* No need to update quota information. */ ext4_warning(inode->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); - } else { - err = ext4_mark_inode_dirty(handle, inode_bl); - if (err < 0) { - ext4_warning(inode_bl->i_sb, - "couldn't mark inode #%lu dirty (err %d)", - inode_bl->i_ino, err); - /* Revert all changes: */ - swap_inode_data(inode, inode_bl); - ext4_mark_inode_dirty(handle, inode); - ext4_mark_inode_dirty(handle, inode_bl); - } + goto err_out1; + } + + blocks = inode_bl->i_blocks; + bytes = inode_bl->i_bytes; + inode_bl->i_blocks = inode->i_blocks; + inode_bl->i_bytes = inode->i_bytes; + err = ext4_mark_inode_dirty(handle, inode_bl); + if (err < 0) { + /* No need to update quota information. */ + ext4_warning(inode_bl->i_sb, + "couldn't mark inode #%lu dirty (err %d)", + inode_bl->i_ino, err); + goto revert; + } + + /* Bootloader inode should not be counted into quota information. */ + if (diff > 0) + dquot_free_space(inode, diff); + else + err = dquot_alloc_space(inode, -1 * diff); + + if (err < 0) { +revert: + /* Revert all changes: */ + inode_bl->i_blocks = blocks; + inode_bl->i_bytes = bytes; + swap_inode_data(inode, inode_bl); + ext4_mark_inode_dirty(handle, inode); + ext4_mark_inode_dirty(handle, inode_bl); } + +err_out1: ext4_journal_stop(handle); ext4_double_up_write_data_sem(inode, inode_bl); +err_out: + up_write(&EXT4_I(inode)->i_mmap_sem); journal_err_out: unlock_two_nondirectories(inode, inode_bl); iput(inode_bl); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 48421de803b7..3d9b18505c0c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1960,7 +1960,8 @@ 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 */ } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index fd36aa6569dc..81c1dd635a8d 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1736,10 +1736,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (!get_dirty_pages(inode)) - goto skip_flush; - - f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, + /* + * Should wait end_io to count F2FS_WB_CP_DATA correctly by + * f2fs_is_atomic_file. + */ + if (get_dirty_pages(inode)) + f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, "Unexpected flush for atomic writes: ino=%lu, npages=%u", inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); @@ -1747,7 +1749,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); goto out; } -skip_flush: + set_inode_flag(inode, FI_ATOMIC_FILE); clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index c0b66a7a795b..914e725c82c4 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1219,11 +1219,12 @@ 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 @@ -1334,15 +1335,17 @@ 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 @@ -1376,9 +1379,6 @@ 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) { @@ -1576,14 +1576,21 @@ 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/kernfs/mount.c b/fs/kernfs/mount.c index ff2716f9322e..0b22c39dad47 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/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 3f23b6840547..bf34ddaa2ad7 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 *); @@ -549,11 +550,12 @@ 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 @@ -563,15 +565,14 @@ 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) @@ -586,7 +587,7 @@ 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) @@ -604,7 +605,7 @@ 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; } @@ -651,9 +652,10 @@ 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; @@ -665,7 +667,8 @@ 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; @@ -690,9 +693,9 @@ 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 77f0a23dc3e4..d95afb31b918 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -947,6 +947,13 @@ 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, @@ -958,10 +965,6 @@ 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, @@ -1007,6 +1010,7 @@ 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; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 3dbd15b47c27..0ec6bce3dd69 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -989,6 +989,17 @@ 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 @@ -1026,10 +1037,8 @@ 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; @@ -1062,6 +1071,10 @@ 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) @@ -1080,7 +1093,6 @@ 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) { @@ -1169,11 +1181,14 @@ 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)) @@ -1199,7 +1214,7 @@ 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/write.c b/fs/nfs/write.c index d790faff8e47..51d0b7913c04 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -238,9 +238,9 @@ 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 9eb8086ea841..c9cf46e0c040 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -463,8 +463,19 @@ 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); } @@ -533,6 +544,7 @@ 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 9b973f4f7d01..83919116d5cb 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -921,6 +921,7 @@ 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/nfs4state.c b/fs/nfsd/nfs4state.c index 9c6d1d57b598..bec75600e692 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1514,16 +1514,16 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) { u32 slotsize = slot_bytes(ca); u32 num = ca->maxreqs; - int avail; + unsigned long avail, total_avail; spin_lock(&nfsd_drc_lock); - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, - nfsd_drc_max_mem - nfsd_drc_mem_used); + total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; + avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); /* * Never use more than a third of the remaining memory, * unless it's the only way to give this client a slot: */ - avail = clamp_t(int, avail, slotsize, avail/3); + avail = clamp_t(int, avail, slotsize, total_avail/3); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 39b835d7c445..cb69660d0779 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1126,7 +1126,7 @@ 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) + if (!nn->nfsd_serv) return -EBUSY; nfsd4_end_grace(nn); break; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 1cc797a08a5b..75eeee08d848 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -501,6 +501,24 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp) { int err; + /* + * Copy up data first and then xattrs. Writing data after + * xattrs will remove security.capability xattr automatically. + */ + if (S_ISREG(c->stat.mode) && !c->metacopy) { + struct path upperpath, datapath; + + ovl_path_upper(c->dentry, &upperpath); + if (WARN_ON(upperpath.dentry != NULL)) + return -EIO; + upperpath.dentry = temp; + + ovl_path_lowerdata(c->dentry, &datapath); + err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size); + if (err) + return err; + } + err = ovl_copy_xattr(c->lowerpath.dentry, temp); if (err) return err; @@ -518,19 +536,6 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp) return err; } - if (S_ISREG(c->stat.mode) && !c->metacopy) { - struct path upperpath, datapath; - - ovl_path_upper(c->dentry, &upperpath); - BUG_ON(upperpath.dentry != NULL); - upperpath.dentry = temp; - - ovl_path_lowerdata(c->dentry, &datapath); - err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size); - if (err) - return err; - } - if (c->metacopy) { err = ovl_check_setxattr(c->dentry, temp, OVL_XATTR_METACOPY, NULL, 0, -EOPNOTSUPP); @@ -706,6 +711,8 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) { struct path upperpath, datapath; int err; + char *capability = NULL; + ssize_t uninitialized_var(cap_size); ovl_path_upper(c->dentry, &upperpath); if (WARN_ON(upperpath.dentry == NULL)) @@ -715,15 +722,37 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) if (WARN_ON(datapath.dentry == NULL)) return -EIO; + if (c->stat.size) { + err = cap_size = ovl_getxattr(upperpath.dentry, XATTR_NAME_CAPS, + &capability, 0); + if (err < 0 && err != -ENODATA) + goto out; + } + err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size); if (err) - return err; + goto out_free; + + /* + * Writing to upper file will clear security.capability xattr. We + * don't want that to happen for normal copy-up operation. + */ + if (capability) { + err = ovl_do_setxattr(upperpath.dentry, XATTR_NAME_CAPS, + capability, cap_size, 0); + if (err) + goto out_free; + } + err = vfs_removexattr(upperpath.dentry, OVL_XATTR_METACOPY); if (err) - return err; + goto out_free; ovl_set_upperdata(d_inode(c->dentry)); +out_free: + kfree(capability); +out: return err; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index a3c0d9584312..d9c16ceebfe7 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -277,6 +277,8 @@ int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir); int ovl_check_metacopy_xattr(struct dentry *dentry); bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct dentry *dentry, int padding); +ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value, + size_t padding); static inline bool ovl_is_impuredir(struct dentry *dentry) { diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index ace4fe4c39a9..c9a2e3c6d537 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -867,28 +867,49 @@ bool ovl_is_metacopy_dentry(struct dentry *dentry) return (oe->numlower > 1); } -char *ovl_get_redirect_xattr(struct dentry *dentry, int padding) +ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value, + size_t padding) { - int res; - char *s, *next, *buf = NULL; + ssize_t res; + char *buf = NULL; - res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0); + res = vfs_getxattr(dentry, name, NULL, 0); if (res < 0) { if (res == -ENODATA || res == -EOPNOTSUPP) - return NULL; + return -ENODATA; goto fail; } - buf = kzalloc(res + padding + 1, GFP_KERNEL); - if (!buf) - return ERR_PTR(-ENOMEM); + if (res != 0) { + buf = kzalloc(res + padding, GFP_KERNEL); + if (!buf) + return -ENOMEM; - if (res == 0) - goto invalid; + res = vfs_getxattr(dentry, name, buf, res); + if (res < 0) + goto fail; + } + *value = buf; + + return res; + +fail: + pr_warn_ratelimited("overlayfs: failed to get xattr %s: err=%zi)\n", + name, res); + kfree(buf); + return res; +} - res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res); +char *ovl_get_redirect_xattr(struct dentry *dentry, int padding) +{ + int res; + char *s, *next, *buf = NULL; + + res = ovl_getxattr(dentry, OVL_XATTR_REDIRECT, &buf, padding + 1); + if (res == -ENODATA) + return NULL; if (res < 0) - goto fail; + return ERR_PTR(res); if (res == 0) goto invalid; @@ -904,15 +925,9 @@ char *ovl_get_redirect_xattr(struct dentry *dentry, int padding) } return buf; - -err_free: - kfree(buf); - return ERR_PTR(res); -fail: - pr_warn_ratelimited("overlayfs: failed to get redirect (%i)\n", res); - goto err_free; invalid: pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf); res = -EINVAL; - goto err_free; + kfree(buf); + return ERR_PTR(res); } diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..c51750ed4011 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -234,6 +234,14 @@ 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, @@ -242,6 +250,12 @@ 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/splice.c b/fs/splice.c index b3daa971f597..29e92b506394 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1593,6 +1593,8 @@ retry: */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + obuf->len = len; opipe->nrbufs++; ibuf->offset += obuf->len; @@ -1667,6 +1669,8 @@ 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; |