diff options
Diffstat (limited to 'fs')
98 files changed, 1117 insertions, 826 deletions
diff --git a/fs/Makefile b/fs/Makefile index 293733f61594..23fcd8c164a3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -12,7 +12,8 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o d_path.o \ - stack.o fs_struct.o statfs.o fs_pin.o nsfs.o + stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ + fs_types.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o diff --git a/fs/afs/cell.c b/fs/afs/cell.c index cf445dbd5f2e..9de46116c749 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -173,6 +173,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = TIME64_MAX; + __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags); } else { cell->dns_expiry = ktime_get_real_seconds(); } @@ -167,9 +167,13 @@ struct kioctx { unsigned id; }; +/* + * First field must be the file pointer in all the + * iocb unions! See also 'struct kiocb' in <linux/fs.h> + */ struct fsync_iocb { - struct work_struct work; struct file *file; + struct work_struct work; bool datasync; }; @@ -183,8 +187,15 @@ struct poll_iocb { struct work_struct work; }; +/* + * NOTE! Each of the iocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'ki_filp' in this struct. + */ struct aio_kiocb { union { + struct file *ki_filp; struct kiocb rw; struct fsync_iocb fsync; struct poll_iocb poll; @@ -1060,6 +1071,8 @@ static inline void iocb_put(struct aio_kiocb *iocb) { if (refcount_read(&iocb->ki_refcnt) == 0 || refcount_dec_and_test(&iocb->ki_refcnt)) { + if (iocb->ki_filp) + fput(iocb->ki_filp); percpu_ref_put(&iocb->ki_ctx->reqs); kmem_cache_free(kiocb_cachep, iocb); } @@ -1424,7 +1437,6 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - fput(kiocb->ki_filp); aio_complete(iocb, res, res2); } @@ -1432,10 +1444,8 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) { int ret; - req->ki_filp = fget(iocb->aio_fildes); - if (unlikely(!req->ki_filp)) - return -EBADF; req->ki_complete = aio_complete_rw; + req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) @@ -1450,7 +1460,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); - goto out_fput; + return ret; } req->ki_ioprio = iocb->aio_reqprio; @@ -1459,14 +1469,10 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); if (unlikely(ret)) - goto out_fput; + return ret; req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */ return 0; - -out_fput: - fput(req->ki_filp); - return ret; } static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec, @@ -1520,24 +1526,19 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, if (ret) return ret; file = req->ki_filp; - - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) - goto out_fput; + return -EBADF; ret = -EINVAL; if (unlikely(!file->f_op->read_iter)) - goto out_fput; + return -EINVAL; ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter); if (ret) - goto out_fput; + return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) aio_rw_done(req, call_read_iter(file, req, &iter)); kfree(iovec); -out_fput: - if (unlikely(ret)) - fput(file); return ret; } @@ -1554,16 +1555,14 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, return ret; file = req->ki_filp; - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_WRITE))) - goto out_fput; - ret = -EINVAL; + return -EBADF; if (unlikely(!file->f_op->write_iter)) - goto out_fput; + return -EINVAL; ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter); if (ret) - goto out_fput; + return ret; ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) { /* @@ -1581,9 +1580,6 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, aio_rw_done(req, call_write_iter(file, req, &iter)); } kfree(iovec); -out_fput: - if (unlikely(ret)) - fput(file); return ret; } @@ -1593,7 +1589,6 @@ static void aio_fsync_work(struct work_struct *work) int ret; ret = vfs_fsync(req->file, req->datasync); - fput(req->file); aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); } @@ -1604,13 +1599,8 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, iocb->aio_rw_flags)) return -EINVAL; - req->file = fget(iocb->aio_fildes); - if (unlikely(!req->file)) - return -EBADF; - if (unlikely(!req->file->f_op->fsync)) { - fput(req->file); + if (unlikely(!req->file->f_op->fsync)) return -EINVAL; - } req->datasync = datasync; INIT_WORK(&req->work, aio_fsync_work); @@ -1620,10 +1610,7 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) { - struct file *file = iocb->poll.file; - aio_complete(iocb, mangle_poll(mask), 0); - fput(file); } static void aio_poll_complete_work(struct work_struct *work) @@ -1679,6 +1666,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); __poll_t mask = key_to_poll(key); + unsigned long flags; req->woken = true; @@ -1687,10 +1675,15 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (!(mask & req->events)) return 0; - /* try to complete the iocb inline if we can: */ - if (spin_trylock(&iocb->ki_ctx->ctx_lock)) { + /* + * Try to complete the iocb inline if we can. Use + * irqsave/irqrestore because not all filesystems (e.g. fuse) + * call this function with IRQs disabled and because IRQs + * have to be disabled before ctx_lock is obtained. + */ + if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { list_del(&iocb->ki_list); - spin_unlock(&iocb->ki_ctx->ctx_lock); + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); list_del_init(&req->wait.entry); aio_poll_complete(iocb, mask); @@ -1742,9 +1735,6 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_WORK(&req->work, aio_poll_complete_work); req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; - req->file = fget(iocb->aio_fildes); - if (unlikely(!req->file)) - return -EBADF; req->head = NULL; req->woken = false; @@ -1787,10 +1777,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) spin_unlock_irq(&ctx->ctx_lock); out: - if (unlikely(apt.error)) { - fput(req->file); + if (unlikely(apt.error)) return apt.error; - } if (mask) aio_poll_complete(aiocb, mask); @@ -1828,6 +1816,11 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, if (unlikely(!req)) goto out_put_reqs_available; + req->ki_filp = fget(iocb->aio_fildes); + ret = -EBADF; + if (unlikely(!req->ki_filp)) + goto out_put_req; + if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an @@ -2198,11 +2191,11 @@ SYSCALL_DEFINE6(io_pgetevents_time32, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, - compat_long_t, min_nr, - compat_long_t, nr, - struct io_event __user *, events, - struct old_timespec32 __user *, timeout) +SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, + __s32, min_nr, + __s32, nr, + struct io_event __user *, events, + struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index d441244b79df..28d9c2b1b3bb 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -596,7 +596,6 @@ int autofs_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; @@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 0e8ea2d9a2bb..078992eee299 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs_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/binfmt_aout.c b/fs/binfmt_aout.c index ca9725f18e00..1fefd87eb4b4 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -29,97 +29,14 @@ #include <linux/uaccess.h> #include <asm/cacheflush.h> -#include <asm/a.out-core.h> static int load_aout_binary(struct linux_binprm *); static int load_aout_library(struct file*); -#ifdef CONFIG_COREDUMP -/* - * Routine writes a core dump image in the current directory. - * Currently only a stub-function. - * - * Note that setuid/setgid files won't make a core-dump if the uid/gid - * changed due to the set[u|g]id. It's enforced by the "current->mm->dumpable" - * field, which also makes sure the core-dumps won't be recursive if the - * dumping of the process results in another error.. - */ -static int aout_core_dump(struct coredump_params *cprm) -{ - mm_segment_t fs; - int has_dumped = 0; - void __user *dump_start; - int dump_size; - struct user dump; -#ifdef __alpha__ -# define START_DATA(u) ((void __user *)u.start_data) -#else -# define START_DATA(u) ((void __user *)((u.u_tsize << PAGE_SHIFT) + \ - u.start_code)) -#endif -# define START_STACK(u) ((void __user *)u.start_stack) - - fs = get_fs(); - set_fs(KERNEL_DS); - has_dumped = 1; - strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm)); - dump.u_ar0 = offsetof(struct user, regs); - dump.signal = cprm->siginfo->si_signo; - aout_dump_thread(cprm->regs, &dump); - -/* If the size of the dump file exceeds the rlimit, then see what would happen - if we wrote the stack, but not the data area. */ - if ((dump.u_dsize + dump.u_ssize+1) * PAGE_SIZE > cprm->limit) - dump.u_dsize = 0; - -/* Make sure we have enough room to write the stack and data areas. */ - if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) - dump.u_ssize = 0; - -/* make sure we actually have a data and stack area to dump */ - set_fs(USER_DS); - if (!access_ok(START_DATA(dump), dump.u_dsize << PAGE_SHIFT)) - dump.u_dsize = 0; - if (!access_ok(START_STACK(dump), dump.u_ssize << PAGE_SHIFT)) - dump.u_ssize = 0; - - set_fs(KERNEL_DS); -/* struct user */ - if (!dump_emit(cprm, &dump, sizeof(dump))) - goto end_coredump; -/* Now dump all of the user data. Include malloced stuff as well */ - if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump))) - goto end_coredump; -/* now we start writing out the user space info */ - set_fs(USER_DS); -/* Dump the data area */ - if (dump.u_dsize != 0) { - dump_start = START_DATA(dump); - dump_size = dump.u_dsize << PAGE_SHIFT; - if (!dump_emit(cprm, dump_start, dump_size)) - goto end_coredump; - } -/* Now prepare to dump the stack area */ - if (dump.u_ssize != 0) { - dump_start = START_STACK(dump); - dump_size = dump.u_ssize << PAGE_SHIFT; - if (!dump_emit(cprm, dump_start, dump_size)) - goto end_coredump; - } -end_coredump: - set_fs(fs); - return has_dumped; -} -#else -#define aout_core_dump NULL -#endif - static struct linux_binfmt aout_format = { .module = THIS_MODULE, .load_binary = load_aout_binary, .load_shlib = load_aout_library, - .core_dump = aout_core_dump, - .min_coredump = PAGE_SIZE }; #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index d0078cbb718b..e996174cbfc0 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -14,13 +14,30 @@ #include <linux/err.h> #include <linux/fs.h> +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline char *next_non_spacetab(char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline char *next_terminator(char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + static int load_script(struct linux_binprm *bprm) { const char *i_arg, *i_name; - char *cp; + char *cp, *buf_end; struct file *file; int retval; + /* Not ours to exec if we don't start with "#!". */ if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) return -ENOEXEC; @@ -33,23 +50,41 @@ static int load_script(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; - /* - * This section does the #! interpretation. - * Sorta complicated, but hopefully it will work. -TYT - */ - + /* Release since we are not mapping a binary into memory. */ allow_write_access(bprm->file); fput(bprm->file); bprm->file = NULL; - for (cp = bprm->buf+2;; cp++) { - if (cp >= bprm->buf + BINPRM_BUF_SIZE) + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!cp) { + cp = next_non_spacetab(bprm->buf + 2, buf_end); + if (!cp) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(cp, buf_end)) return -ENOEXEC; - if (!*cp || (*cp == '\n')) - break; + cp = buf_end; } + /* NUL-terminate the buffer and any trailing spaces/tabs. */ *cp = '\0'; - while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index f64aad613727..5a6c39b44c84 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -968,6 +968,48 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return 0; } +static struct extent_buffer *alloc_tree_block_no_bg_flush( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, + u64 parent_start, + const struct btrfs_disk_key *disk_key, + int level, + u64 hint, + u64 empty_size) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct extent_buffer *ret; + + /* + * If we are COWing a node/leaf from the extent, chunk, device or free + * space trees, make sure that we do not finish block group creation of + * pending block groups. We do this to avoid a deadlock. + * COWing can result in allocation of a new chunk, and flushing pending + * block groups (btrfs_create_pending_block_groups()) can be triggered + * when finishing allocation of a new chunk. Creation of a pending block + * group modifies the extent, chunk, device and free space trees, + * therefore we could deadlock with ourselves since we are holding a + * lock on an extent buffer that btrfs_create_pending_block_groups() may + * try to COW later. + * For similar reasons, we also need to delay flushing pending block + * groups when splitting a leaf or node, from one of those trees, since + * we are holding a write lock on it and its parent or when inserting a + * new root node for one of those trees. + */ + if (root == fs_info->extent_root || + root == fs_info->chunk_root || + root == fs_info->dev_root || + root == fs_info->free_space_root) + trans->can_flush_pending_bgs = false; + + ret = btrfs_alloc_tree_block(trans, root, parent_start, + root->root_key.objectid, disk_key, level, + hint, empty_size); + trans->can_flush_pending_bgs = true; + + return ret; +} + /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked @@ -1015,28 +1057,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent) parent_start = parent->start; - /* - * If we are COWing a node/leaf from the extent, chunk, device or free - * space trees, make sure that we do not finish block group creation of - * pending block groups. We do this to avoid a deadlock. - * COWing can result in allocation of a new chunk, and flushing pending - * block groups (btrfs_create_pending_block_groups()) can be triggered - * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk, device and free space trees, - * therefore we could deadlock with ourselves since we are holding a - * lock on an extent buffer that btrfs_create_pending_block_groups() may - * try to COW later. - */ - if (root == fs_info->extent_root || - root == fs_info->chunk_root || - root == fs_info->dev_root || - root == fs_info->free_space_root) - trans->can_flush_pending_bgs = false; - - cow = btrfs_alloc_tree_block(trans, root, parent_start, - root->root_key.objectid, &disk_key, level, - search_start, empty_size); - trans->can_flush_pending_bgs = true; + cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key, + level, search_start, empty_size); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -3345,8 +3367,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, else btrfs_node_key(lower, &lower_key, 0); - c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &lower_key, level, root->node->start, 0); + c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level, + root->node->start, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -3475,8 +3497,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); - split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, level, c->start, 0); + split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level, + c->start, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -4260,8 +4282,8 @@ again: else btrfs_item_key(l, &disk_key, mid); - right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0); + right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0, + l->start, 0); if (IS_ERR(right)) return PTR_ERR(right); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c5586ffd1426..0a3f122dd61f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1621,6 +1621,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, flags | SB_RDONLY, device_name, data); if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } @@ -1630,12 +1631,14 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error < 0) { root = ERR_PTR(error); mntput(mnt_root); + kfree(subvol_name); goto out; } } } if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 127fa1535f58..4ec2b660d014 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -850,14 +850,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_chunk_metadata(trans); - if (lock && should_end_transaction(trans) && - READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) { - spin_lock(&info->trans_lock); - if (cur_trans->state == TRANS_STATE_RUNNING) - cur_trans->state = TRANS_STATE_BLOCKED; - spin_unlock(&info->trans_lock); - } - if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { if (throttle) return btrfs_commit_transaction(trans); @@ -1879,6 +1871,21 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) kmem_cache_free(btrfs_trans_handle_cachep, trans); } +/* + * Release reserved delayed ref space of all pending block groups of the + * transaction and remove them from the list + */ +static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_block_group_cache *block_group, *tmp; + + list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { + btrfs_delayed_refs_rsv_release(fs_info, 1); + list_del_init(&block_group->bg_list); + } +} + static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) { /* @@ -2270,6 +2277,7 @@ scrub_continue: btrfs_scrub_continue(fs_info); cleanup_transaction: btrfs_trans_release_metadata(trans); + btrfs_cleanup_pending_block_groups(trans); btrfs_trans_release_chunk_metadata(trans); trans->block_rsv = NULL; btrfs_warn(fs_info, "Skipping commit of aborted transaction."); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3e4f8f88353e..15561926ab32 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -957,11 +957,11 @@ static noinline struct btrfs_device *device_list_add(const char *path, else fs_devices = alloc_fs_devices(disk_super->fsid, NULL); - fs_devices->fsid_change = fsid_change_in_progress; - if (IS_ERR(fs_devices)) return ERR_CAST(fs_devices); + fs_devices->fsid_change = fsid_change_in_progress; + mutex_lock(&fs_devices->device_list_mutex); list_add(&fs_devices->fs_list, &fs_uuids); diff --git a/fs/buffer.c b/fs/buffer.c index 52d024bfdbc1..48318fb74938 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -200,6 +200,7 @@ __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); @@ -227,15 +228,15 @@ __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); diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 041c27ea8de1..f74193da0e09 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -616,7 +616,8 @@ 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/cifsfs.h b/fs/cifs/cifsfs.h index d1f9c2f3f575..7652551a1fc4 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.16" +#define CIFS_VERSION "2.17" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2c7689f3998d..659ce1b92c44 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2696,6 +2696,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, rc = cifs_write_allocate_pages(wdata->pages, nr_pages); if (rc) { + kvfree(wdata->pages); kfree(wdata); add_credits_and_wake_if(server, credits, 0); break; @@ -2707,6 +2708,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, if (rc) { for (i = 0; i < nr_pages; i++) put_page(wdata->pages[i]); + kvfree(wdata->pages); kfree(wdata); add_credits_and_wake_if(server, credits, 0); break; @@ -3386,8 +3388,12 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, } rc = cifs_read_allocate_pages(rdata, npages); - if (rc) - goto error; + if (rc) { + kvfree(rdata->pages); + kfree(rdata); + add_credits_and_wake_if(server, credits, 0); + break; + } rdata->tailsz = PAGE_SIZE; } @@ -3407,7 +3413,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, if (!rdata->cfile->invalidHandle || !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); -error: if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); kref_put(&rdata->refcount, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 153238fc4fa9..6f96e2292856 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -866,7 +866,9 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, FILE_READ_EA, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, - SMB2_MAX_EA_BUF, + CIFSMaxBufSize - + MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE, &rsp_iov, &buftype, cifs_sb); if (rc) { /* diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2ff209ec4fab..77b3aaa39b35 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3241,8 +3241,17 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->mr = NULL; } #endif - if (rdata->result) + if (rdata->result && rdata->result != -ENODATA) { cifs_stats_fail_inc(tcon, SMB2_READ_HE); + trace_smb3_read_err(0 /* xid */, + rdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, rdata->offset, + rdata->bytes, rdata->result); + } else + trace_smb3_read_done(0 /* xid */, + rdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->offset, rdata->got_bytes); queue_work(cifsiod_wq, &rdata->work); DeleteMidQEntry(mid); @@ -3317,13 +3326,11 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rc) { kref_put(&rdata->refcount, cifs_readdata_release); cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE); - trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid, - io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, io_parms.length); - } else - trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid, - io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, io_parms.length); + trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid, + io_parms.tcon->tid, + io_parms.tcon->ses->Suid, + io_parms.offset, io_parms.length, rc); + } cifs_small_buf_release(buf); return rc; @@ -3367,10 +3374,11 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, if (rc != -ENODATA) { cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); cifs_dbg(VFS, "Send error in read = %d\n", rc); + trace_smb3_read_err(xid, req->PersistentFileId, + io_parms->tcon->tid, ses->Suid, + io_parms->offset, io_parms->length, + rc); } - trace_smb3_read_err(rc, xid, req->PersistentFileId, - io_parms->tcon->tid, ses->Suid, - io_parms->offset, io_parms->length); free_rsp_buf(resp_buftype, rsp_iov.iov_base); return rc == -ENODATA ? 0 : rc; } else @@ -3459,8 +3467,17 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->mr = NULL; } #endif - if (wdata->result) + if (wdata->result) { cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); + trace_smb3_write_err(0 /* no xid */, + wdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, wdata->offset, + wdata->bytes, wdata->result); + } else + trace_smb3_write_done(0 /* no xid */, + wdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + wdata->offset, wdata->bytes); queue_work(cifsiod_wq, &wdata->work); DeleteMidQEntry(mid); @@ -3602,10 +3619,7 @@ smb2_async_writev(struct cifs_writedata *wdata, wdata->bytes, rc); kref_put(&wdata->refcount, release); cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); - } else - trace_smb3_write_done(0 /* no xid */, req->PersistentFileId, - tcon->tid, tcon->ses->Suid, wdata->offset, - wdata->bytes); + } async_writev_out: cifs_small_buf_release(req); @@ -3831,8 +3845,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) { srch_inf->endOfSearch = true; rc = 0; - } - cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); + } else + cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } @@ -4427,8 +4441,8 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); - please_key_low = (__u64 *)req->LeaseKey; - please_key_high = (__u64 *)(req->LeaseKey+8); + please_key_low = (__u64 *)lease_key; + please_key_high = (__u64 *)(lease_key+8); if (rc) { cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE); trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 7a2d0a2255e6..538e2299805f 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,9 @@ #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 SMB2_TRANSFORM_HEADER_SIZE 52 +#define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) @@ -648,6 +649,13 @@ struct smb2_create_req { __u8 Buffer[0]; } __packed; +/* + * Maximum size of a SMB2_CREATE response is 64 (smb2 header) + + * 88 (fixed part of create response) + 520 (path) + 150 (contexts) + + * 2 bytes of padding. + */ +#define MAX_SMB2_CREATE_RESPONSE_SIZE 824 + struct smb2_create_rsp { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 89 */ @@ -996,6 +1004,11 @@ struct smb2_close_req { __u64 VolatileFileId; /* opaque endianness */ } __packed; +/* + * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data) + */ +#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124 + struct smb2_close_rsp { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* 60 */ @@ -1398,8 +1411,6 @@ struct smb2_file_link_info { /* encoding of request for level 11 */ char FileName[0]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ -#define SMB2_MAX_EA_BUF 65536 - struct smb2_file_full_ea_info { /* encoding of response for level 15 */ __le32 next_entry_offset; __u8 flags; diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 1e11a683f63d..322ce9686bdb 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -47,7 +47,7 @@ static int derive_key_aes(const u8 *master_key, tfm = NULL; goto out; } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) { res = -ENOMEM; @@ -257,7 +257,7 @@ allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, mode->friendly_name, crypto_skcipher_alg(tfm)->base.cra_driver_name); } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); if (err) goto err_free_tfm; diff --git a/fs/dcache.c b/fs/dcache.c index 2593153471cf..aac41adf4743 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -119,6 +119,7 @@ struct dentry_stat_t dentry_stat = { static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); +static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) @@ -152,11 +153,22 @@ static long get_nr_dentry_unused(void) return sum < 0 ? 0 : sum; } +static long get_nr_dentry_negative(void) +{ + int i; + long sum = 0; + + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry_negative, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); + dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -317,6 +329,8 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) @@ -371,6 +385,11 @@ static void dentry_unlink_inode(struct dentry * dentry) * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * + * The per-cpu "nr_dentry_negative" counters are only updated + * when deleted from or added to the per-superblock LRU list, not + * from/to the shrink list. That is to avoid an unneeded dec/inc + * pair when moving from LRU to shrink list in select_collect(). + * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ @@ -380,6 +399,8 @@ static void d_lru_add(struct dentry *dentry) D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -388,6 +409,8 @@ static void d_lru_del(struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -418,6 +441,8 @@ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } @@ -426,6 +451,8 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } @@ -1188,15 +1215,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, */ void shrink_dcache_sb(struct super_block *sb) { - long freed; - do { LIST_HEAD(dispose); - freed = list_lru_walk(&sb->s_dentry_lru, + list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); - - this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } @@ -1820,6 +1843,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); + /* + * Decrement negative dentry count if it was in the LRU list. + */ + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 13b01351dd1c..95b5e78c22b1 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -324,7 +324,7 @@ static struct dentry *failed_creating(struct dentry *dentry) inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); - return NULL; + return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) @@ -347,7 +347,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, dentry = start_creating(name, parent); if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -386,7 +386,8 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -422,8 +423,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); * debugfs core. * * It is your responsibility to protect your struct file_operation - * methods against file removals by means of debugfs_use_file_start() - * and debugfs_use_file_finish(). ->open() is still protected by + * methods against file removals by means of debugfs_file_get() + * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of @@ -464,7 +465,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -495,7 +497,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -506,7 +509,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -545,7 +548,7 @@ struct dentry *debugfs_create_automount(const char *name, struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -581,8 +584,8 @@ EXPORT_SYMBOL(debugfs_create_automount); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is - * unloaded, you are responsible here.) If an error occurs, %NULL will be - * returned. + * unloaded, you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) + * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -594,12 +597,12 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) - return NULL; + return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); - return NULL; + return dentry; } inode = debugfs_get_inode(dentry->d_sb); @@ -787,6 +790,13 @@ 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)) @@ -820,7 +830,9 @@ exit: if (dentry && !IS_ERR(dentry)) dput(dentry); unlock_rename(new_dir, old_dir); - return NULL; + if (IS_ERR(dentry)) + return dentry; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(debugfs_rename); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 76976d6e50f9..c98ad9777ad9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1089,12 +1089,12 @@ static void sctp_connect_to_sock(struct connection *con) * since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len, 0); memset(&tv, 0, sizeof(tv)); - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); if (result == -EINPROGRESS) 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/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 4dd842f72846..f664da55234e 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -610,7 +610,8 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) full_alg_name); goto out_free; } - crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(crypt_stat->tfm, + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); rc = 0; out_free: kfree(full_alg_name); @@ -1590,7 +1591,7 @@ ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm, "[%s]; rc = [%d]\n", full_alg_name, rc); goto out; } - crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (*key_size == 0) *key_size = crypto_skcipher_default_keysize(*key_tfm); get_random_bytes(dummy_key, *key_size); diff --git a/fs/exec.c b/fs/exec.c index fb72d36f7823..74f3672146a7 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -932,7 +932,7 @@ 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) @@ -1189,7 +1189,7 @@ no_thread_group: flush_itimer_signals(); #endif - if (atomic_read(&oldsighand->count) != 1) { + if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND @@ -1199,7 +1199,7 @@ no_thread_group: if (!newsighand) return -ENOMEM; - atomic_set(&newsighand->count, 1); + refcount_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 3b8114def693..13318e255ebf 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -252,33 +252,10 @@ ext2_validate_entry(char *base, unsigned offset, unsigned mask) return (char *)p - base; } -static unsigned char ext2_filetype_table[EXT2_FT_MAX] = { - [EXT2_FT_UNKNOWN] = DT_UNKNOWN, - [EXT2_FT_REG_FILE] = DT_REG, - [EXT2_FT_DIR] = DT_DIR, - [EXT2_FT_CHRDEV] = DT_CHR, - [EXT2_FT_BLKDEV] = DT_BLK, - [EXT2_FT_FIFO] = DT_FIFO, - [EXT2_FT_SOCK] = DT_SOCK, - [EXT2_FT_SYMLINK] = DT_LNK, -}; - -#define S_SHIFT 12 -static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = { - [S_IFREG >> S_SHIFT] = EXT2_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = EXT2_FT_DIR, - [S_IFCHR >> S_SHIFT] = EXT2_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = EXT2_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = EXT2_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = EXT2_FT_SOCK, - [S_IFLNK >> S_SHIFT] = EXT2_FT_SYMLINK, -}; - static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode) { - umode_t mode = inode->i_mode; if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE)) - de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; + de->file_type = fs_umode_to_ftype(inode->i_mode); else de->file_type = 0; } @@ -293,14 +270,14 @@ ext2_readdir(struct file *file, struct dir_context *ctx) unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(ext2_chunk_size(inode)-1); - unsigned char *types = NULL; bool need_revalidate = !inode_eq_iversion(inode, file->f_version); + bool has_filetype; if (pos > inode->i_size - EXT2_DIR_REC_LEN(1)) return 0; - if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE)) - types = ext2_filetype_table; + has_filetype = + EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE); for ( ; n < npages; n++, offset = 0) { char *kaddr, *limit; @@ -335,8 +312,8 @@ ext2_readdir(struct file *file, struct dir_context *ctx) if (de->inode) { unsigned char d_type = DT_UNKNOWN; - if (types && de->file_type < EXT2_FT_MAX) - d_type = types[de->file_type]; + if (has_filetype) + d_type = fs_ftype_to_dtype(de->file_type); if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index e770cd100a6a..10ab238de9a6 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -604,22 +604,6 @@ struct ext2_dir_entry_2 { }; /* - * Ext2 directory file types. Only the low 3 bits are used. The - * other bits are reserved for now. - */ -enum { - EXT2_FT_UNKNOWN = 0, - EXT2_FT_REG_FILE = 1, - EXT2_FT_DIR = 2, - EXT2_FT_CHRDEV = 3, - EXT2_FT_BLKDEV = 4, - EXT2_FT_FIFO = 5, - EXT2_FT_SOCK = 6, - EXT2_FT_SYMLINK = 7, - EXT2_FT_MAX -}; - -/* * EXT2_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 @@ -774,6 +758,7 @@ extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_evict_inode(struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int ext2_setattr (struct dentry *, struct iattr *); +extern int ext2_getattr (const struct path *, struct kstat *, u32, unsigned int); extern void ext2_set_inode_flags(struct inode *inode); extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 28b2609f25c1..39c4772e96c9 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -199,6 +199,7 @@ const struct inode_operations ext2_file_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, #endif + .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, .set_acl = ext2_set_acl, diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 5c3d7b7e4975..a0c5ea91fcd4 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -222,8 +222,6 @@ static int find_group_dir(struct super_block *sb, struct inode *parent) best_desc = desc; } } - if (!best_desc) - return -1; return best_group; } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index e4bb9386c045..c27c27300d95 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -717,7 +717,7 @@ static int ext2_get_blocks(struct inode *inode, /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; /* - * Next look up the indirect map to count the totoal number of + * Next look up the indirect map to count the total number of * direct blocks to allocate for this branch. */ count = ext2_blks_to_allocate(partial, indirect_blks, @@ -1239,6 +1239,7 @@ do_indirects: mark_inode_dirty(inode); ext2_free_branches(inode, &nr, &nr+1, 1); } + /* fall through */ case EXT2_IND_BLOCK: nr = i_data[EXT2_DIND_BLOCK]; if (nr) { @@ -1246,6 +1247,7 @@ do_indirects: mark_inode_dirty(inode); ext2_free_branches(inode, &nr, &nr+1, 2); } + /* fall through */ case EXT2_DIND_BLOCK: nr = i_data[EXT2_TIND_BLOCK]; if (nr) { @@ -1635,6 +1637,32 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } +int ext2_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_falgs) +{ + struct inode *inode = d_inode(path->dentry); + struct ext2_inode_info *ei = EXT2_I(inode); + unsigned int flags; + + flags = ei->i_flags & EXT2_FL_USER_VISIBLE; + if (flags & EXT2_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (flags & EXT2_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (flags & EXT2_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (flags & EXT2_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); + + generic_fillattr(inode, stat); + return 0; +} + int ext2_setattr(struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 0c26dcc5d850..ccfbbf59e2fc 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -416,6 +416,7 @@ const struct inode_operations ext2_dir_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, #endif + .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, .set_acl = ext2_set_acl, @@ -426,6 +427,7 @@ const struct inode_operations ext2_special_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, #endif + .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, .set_acl = ext2_set_acl, diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 73b2d528237f..0128010a0874 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -757,7 +757,8 @@ 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 @@ -771,24 +772,34 @@ 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; @@ -1024,8 +1035,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - if (EXT2_INODE_SIZE(sb) == 0) - goto cantfind_ext2; sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0) goto cantfind_ext2; @@ -1087,12 +1096,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sizeof(struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { + ret = -ENOMEM; ext2_msg(sb, KERN_ERR, "error: not enough memory"); goto failed_mount; } bgl_lock_init(sbi->s_blockgroup_lock); sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL); if (!sbi->s_debts) { + ret = -ENOMEM; ext2_msg(sb, KERN_ERR, "error: not enough memory"); goto failed_mount_group_desc; } @@ -1148,6 +1159,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_EXT2_FS_XATTR sbi->s_ea_block_cache = ext2_xattr_create_cache(); if (!sbi->s_ea_block_cache) { + ret = -ENOMEM; ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); goto failed_mount3; } diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c index d5589ddcc281..00cdb8679486 100644 --- a/fs/ext2/symlink.c +++ b/fs/ext2/symlink.c @@ -23,6 +23,7 @@ const struct inode_operations ext2_symlink_inode_operations = { .get_link = page_get_link, + .getattr = ext2_getattr, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, @@ -31,6 +32,7 @@ const struct inode_operations ext2_symlink_inode_operations = { const struct inode_operations ext2_fast_symlink_inode_operations = { .get_link = simple_get_link, + .getattr = ext2_getattr, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 4f30876ee325..1e33e0ac8cf1 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -342,6 +342,7 @@ static void ext2_xattr_update_super_block(struct super_block *sb) return; spin_lock(&EXT2_SB(sb)->s_lock); + ext2_update_dynamic_rev(sb); EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR); spin_unlock(&EXT2_SB(sb)->s_lock); mark_buffer_dirty(EXT2_SB(sb)->s_sbh); 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/f2fs/debug.c b/fs/f2fs/debug.c index ebcc121920ba..fd7f170e2f2d 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -506,30 +506,16 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) kvfree(si); } -int __init f2fs_create_root_stats(void) +void __init f2fs_create_root_stats(void) { - struct dentry *file; - f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); - if (!f2fs_debugfs_root) - return -ENOMEM; - file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, - NULL, &stat_fops); - if (!file) { - debugfs_remove(f2fs_debugfs_root); - f2fs_debugfs_root = NULL; - return -ENOMEM; - } - - return 0; + debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, + &stat_fops); } void f2fs_destroy_root_stats(void) { - if (!f2fs_debugfs_root) - return; - debugfs_remove_recursive(f2fs_debugfs_root); f2fs_debugfs_root = NULL; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 12fabd6735dd..8f23ee6e8eb9 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3328,7 +3328,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *sbi); void f2fs_destroy_stats(struct f2fs_sb_info *sbi); -int __init f2fs_create_root_stats(void); +void __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) do { } while (0) @@ -3366,7 +3366,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline int __init f2fs_create_root_stats(void) { return 0; } +static inline void __init f2fs_create_root_stats(void) { } static inline void f2fs_destroy_root_stats(void) { } #endif diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c46a1d4318d4..3d3ce9eb6d13 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3545,9 +3545,7 @@ static int __init init_f2fs_fs(void) err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - err = f2fs_create_root_stats(); - if (err) - goto free_filesystem; + f2fs_create_root_stats(); err = f2fs_init_post_read_processing(); if (err) goto free_root_stats; @@ -3555,7 +3553,6 @@ static int __init init_f2fs_fs(void) free_root_stats: f2fs_destroy_root_stats(); -free_filesystem: unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); diff --git a/fs/file.c b/fs/file.c index 3209ee271c41..a10487aa0a84 100644 --- a/fs/file.c +++ b/fs/file.c @@ -457,6 +457,7 @@ 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_types.c b/fs/fs_types.c new file mode 100644 index 000000000000..78365e5dc08c --- /dev/null +++ b/fs/fs_types.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/fs.h> +#include <linux/export.h> + +/* + * fs on-disk file type to dirent file type conversion + */ +static const unsigned char fs_dtype_by_ftype[FT_MAX] = { + [FT_UNKNOWN] = DT_UNKNOWN, + [FT_REG_FILE] = DT_REG, + [FT_DIR] = DT_DIR, + [FT_CHRDEV] = DT_CHR, + [FT_BLKDEV] = DT_BLK, + [FT_FIFO] = DT_FIFO, + [FT_SOCK] = DT_SOCK, + [FT_SYMLINK] = DT_LNK +}; + +/** + * fs_ftype_to_dtype() - fs on-disk file type to dirent type. + * @filetype: The on-disk file type to convert. + * + * This function converts the on-disk file type value (FT_*) to the directory + * entry type (DT_*). + * + * Context: Any context. + * Return: + * * DT_UNKNOWN - Unknown type + * * DT_FIFO - FIFO + * * DT_CHR - Character device + * * DT_DIR - Directory + * * DT_BLK - Block device + * * DT_REG - Regular file + * * DT_LNK - Symbolic link + * * DT_SOCK - Local-domain socket + */ +unsigned char fs_ftype_to_dtype(unsigned int filetype) +{ + if (filetype >= FT_MAX) + return DT_UNKNOWN; + + return fs_dtype_by_ftype[filetype]; +} +EXPORT_SYMBOL_GPL(fs_ftype_to_dtype); + +/* + * dirent file type to fs on-disk file type conversion + * Values not initialized explicitly are FT_UNKNOWN (0). + */ +static const unsigned char fs_ftype_by_dtype[DT_MAX] = { + [DT_REG] = FT_REG_FILE, + [DT_DIR] = FT_DIR, + [DT_LNK] = FT_SYMLINK, + [DT_CHR] = FT_CHRDEV, + [DT_BLK] = FT_BLKDEV, + [DT_FIFO] = FT_FIFO, + [DT_SOCK] = FT_SOCK, +}; + +/** + * fs_umode_to_ftype() - file mode to on-disk file type. + * @mode: The file mode to convert. + * + * This function converts the file mode value to the on-disk file type (FT_*). + * + * Context: Any context. + * Return: + * * FT_UNKNOWN - Unknown type + * * FT_REG_FILE - Regular file + * * FT_DIR - Directory + * * FT_CHRDEV - Character device + * * FT_BLKDEV - Block device + * * FT_FIFO - FIFO + * * FT_SOCK - Local-domain socket + * * FT_SYMLINK - Symbolic link + */ +unsigned char fs_umode_to_ftype(umode_t mode) +{ + return fs_ftype_by_dtype[S_DT(mode)]; +} +EXPORT_SYMBOL_GPL(fs_umode_to_ftype); + +/** + * fs_umode_to_dtype() - file mode to dirent file type. + * @mode: The file mode to convert. + * + * This function converts the file mode value to the directory + * entry type (DT_*). + * + * Context: Any context. + * Return: + * * DT_UNKNOWN - Unknown type + * * DT_FIFO - FIFO + * * DT_CHR - Character device + * * DT_DIR - Directory + * * DT_BLK - Block device + * * DT_REG - Regular file + * * DT_LNK - Symbolic link + * * DT_SOCK - Local-domain socket + */ +unsigned char fs_umode_to_dtype(umode_t mode) +{ + return fs_ftype_to_dtype(fs_umode_to_ftype(mode)); +} +EXPORT_SYMBOL_GPL(fs_umode_to_dtype); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index a5e516a40e7a..809c0f2f9942 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1742,7 +1742,6 @@ 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; @@ -1757,6 +1756,7 @@ 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++; @@ -2077,8 +2077,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); + pipe_lock(pipe); for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); + pipe_unlock(pipe); out: kvfree(bufs); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index ffaffe18352a..a59c16bd90ac 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1782,7 +1782,7 @@ 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/fuse/inode.c b/fs/fuse/inode.c index 76baaa6be393..c2d4099429be 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -628,6 +628,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns) get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); + fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; } EXPORT_SYMBOL_GPL(fuse_conn_init); @@ -1162,7 +1163,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->user_id = d.user_id; fc->group_id = d.group_id; fc->max_read = max_t(unsigned, 4096, d.max_read); - fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; /* Used by get_root_inode() */ sb->s_fs_info = fc; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f15b4c57c4bd..78510ab91835 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,7 +28,6 @@ #include "util.h" #include "trans.h" #include "dir.h" -#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 5bfaf381921a..b8830fda51e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_crc = cpu_to_be32(crc); gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); log_flush_wait(sdp); } @@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 94dcab655bc0..2295042bc625 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,9 +17,7 @@ #include <linux/bio.h> #include <linux/fs.h> #include <linux/list_sort.h> -#include <linux/blkdev.h> -#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio + * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @opf: REQ_OP | op_flags + * @op: REQ_OP + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int opf) +void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio->bi_opf = opf; + bio_set_op_attrs(bio, op, op_flags); submit_bio(bio); *biop = NULL; } @@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op); + gfs2_log_submit_bio(biop, op, 0); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } -/** - * gfs2_end_log_read - end I/O callback for reads from the log - * @bio: The bio - * - * Simply unlock the pages in the bio. The main thread will wait on them and - * process them in order as necessary. - */ - -static void gfs2_end_log_read(struct bio *bio) -{ - struct page *page; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - page = bvec->bv_page; - if (bio->bi_status) { - int err = blk_status_to_errno(bio->bi_status); - - SetPageError(page); - mapping_set_error(page->mapping, err); - } - unlock_page(page); - } - - bio_put(bio); -} - -/** - * gfs2_jhead_pg_srch - Look for the journal head in a given page. - * @jd: The journal descriptor - * @page: The page to look in - * - * Returns: 1 if found, 0 otherwise. - */ - -static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head, - struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct gfs2_log_header_host uninitialized_var(lh); - void *kaddr = kmap_atomic(page); - unsigned int offset; - bool ret = false; - - for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { - if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) - *head = lh; - else { - ret = true; - break; - } - } - } - kunmap_atomic(kaddr); - return ret; -} - -/** - * gfs2_jhead_process_page - Search/cleanup a page - * @jd: The journal descriptor - * @index: Index of the page to look into - * @done: If set, perform only cleanup, else search and set if found. - * - * Find the page with 'index' in the journal's mapping. Search the page for - * the journal head if requested (cleanup == false). Release refs on the - * page so the page cache can reclaim it (put_page() twice). We grabbed a - * reference on this page two times, first when we did a find_or_create_page() - * to obtain the page to add it to the bio and second when we do a - * find_get_page() here to get the page to wait on while I/O on it is being - * completed. - * This function is also used to free up a page we might've grabbed but not - * used. Maybe we added it to a bio, but not submitted it for I/O. Or we - * submitted the I/O, but we already found the jhead so we only need to drop - * our references to the page. - */ - -static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, - struct gfs2_log_header_host *head, - bool *done) -{ - struct page *page; - - page = find_get_page(jd->jd_inode->i_mapping, index); - wait_on_page_locked(page); - - if (PageError(page)) - *done = true; - - if (!*done) - *done = gfs2_jhead_pg_srch(jd, head, page); - - put_page(page); /* Once for find_get_page */ - put_page(page); /* Once more for find_or_create_page */ -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: The journal descriptor - * @head: The log descriptor for the head of the log is returned here - * - * Do a search of a journal by reading it in large chunks using bios and find - * the valid log entry with the highest sequence number. (i.e. the log head) - * - * Returns: 0 on success, errno otherwise - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct address_space *mapping = jd->jd_inode->i_mapping; - struct gfs2_journal_extent *je; - u32 block, read_idx = 0, submit_idx = 0, index = 0; - int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; - int blocks_per_page = 1 << shift, sz, ret = 0; - struct bio *bio = NULL; - struct page *page; - bool done = false; - errseq_t since; - - memset(head, 0, sizeof(*head)); - if (list_empty(&jd->extent_list)) - gfs2_map_journal_extents(sdp, jd); - - since = filemap_sample_wb_err(mapping); - list_for_each_entry(je, &jd->extent_list, list) { - for (block = 0; block < je->blocks; block += blocks_per_page) { - index = (je->lblock + block) >> shift; - - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; - done = true; - goto out; - } - - if (bio) { - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - if (sz == PAGE_SIZE) - goto page_added; - submit_idx = index; - submit_bio(bio); - bio = NULL; - } - - bio = gfs2_log_alloc_bio(sdp, - je->dblock + (index << shift), - gfs2_end_log_read); - bio->bi_opf = REQ_OP_READ; - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - gfs2_assert_warn(sdp, sz == PAGE_SIZE); - -page_added: - if (submit_idx <= read_idx + BIO_MAX_PAGES) { - /* Keep at least one bio in flight */ - continue; - } - - gfs2_jhead_process_page(jd, read_idx++, head, &done); - if (done) - goto out; /* found */ - } - } - -out: - if (bio) - submit_bio(bio); - while (read_idx <= index) - gfs2_jhead_process_page(jd, read_idx++, head, &done); - - if (!ret) - ret = filemap_check_wb_err(mapping, since); - - return ret; -} - static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 331160fc568b..711c4d89c063 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int opf); +extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1179763f6370..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,7 +41,6 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" -#include "lops.h" #define DO 0 #define UNDO 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 7389e445a7a7..2dac43065382 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -182,6 +182,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, } /** + * find_good_lh - find a good log header + * @jd: the journal + * @blk: the segment to start searching from + * @lh: the log header to fill in + * @forward: if true search forward in the log, else search backward + * + * Call get_log_header() to get a log header for a segment, but if the + * segment is bad, either scan forward or backward until we find a good one. + * + * Returns: errno + */ + +static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, + struct gfs2_log_header_host *head) +{ + unsigned int orig_blk = *blk; + int error; + + for (;;) { + error = get_log_header(jd, *blk, head); + if (error <= 0) + return error; + + if (++*blk == jd->jd_blocks) + *blk = 0; + + if (*blk == orig_blk) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + } +} + +/** + * jhead_scan - make sure we've found the head of the log + * @jd: the journal + * @head: this is filled in with the log descriptor of the head + * + * At this point, seg and lh should be either the head of the log or just + * before. Scan forward until we find the head. + * + * Returns: errno + */ + +static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + unsigned int blk = head->lh_blkno; + struct gfs2_log_header_host lh; + int error; + + for (;;) { + if (++blk == jd->jd_blocks) + blk = 0; + + error = get_log_header(jd, blk, &lh); + if (error < 0) + return error; + if (error == 1) + continue; + + if (lh.lh_sequence == head->lh_sequence) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + if (lh.lh_sequence < head->lh_sequence) + break; + + *head = lh; + } + + return 0; +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: the journal + * @head: the log descriptor for the head of the log is returned here + * + * Do a binary search of a journal and find the valid log entry with the + * highest sequence number. (i.e. the log head) + * + * Returns: errno + */ + +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + struct gfs2_log_header_host lh_1, lh_m; + u32 blk_1, blk_2, blk_m; + int error; + + blk_1 = 0; + blk_2 = jd->jd_blocks - 1; + + for (;;) { + blk_m = (blk_1 + blk_2) / 2; + + error = find_good_lh(jd, &blk_1, &lh_1); + if (error) + return error; + + error = find_good_lh(jd, &blk_m, &lh_m); + if (error) + return error; + + if (blk_1 == blk_m || blk_m == blk_2) + break; + + if (lh_1.lh_sequence <= lh_m.lh_sequence) + blk_1 = blk_m; + else + blk_2 = blk_m; + } + + error = jhead_scan(jd, &lh_1); + if (error) + return error; + + *head = lh_1; + + return error; +} + +/** * foreach_descriptor - go through the active part of the log * @jd: the journal * @start: the first log header in the active region diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 99575ab81202..11d81248be85 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 831d7cb5a49c..17a8d3b43990 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1780,9 +1780,9 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, goto next_iter; } if (ret == -E2BIG) { - n += rbm->bii - initial_bii; rbm->bii = 0; rbm->offset = 0; + n += (rbm->bii - initial_bii); goto res_covered_end_of_rgrp; } return ret; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d4b11c903971..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,7 +45,6 @@ #include "util.h" #include "sys.h" #include "xattr.h" -#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 32920a10100e..b0eef008de67 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -530,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); /* protected by i_mutex */ - if (info->seals & F_SEAL_WRITE) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } @@ -859,6 +859,18 @@ 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/inode.c b/fs/inode.c index 0cd47fe0dbe5..e9d97add2b36 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* - * Recently referenced inodes and inodes with many attached pages - * get one more pass. - */ - if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; @@ -2096,14 +2093,8 @@ EXPORT_SYMBOL(inode_dio_wait); void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { - unsigned int old_flags, new_flags; - WARN_ON_ONCE(flags & ~mask); - do { - old_flags = READ_ONCE(inode->i_flags); - new_flags = (old_flags & ~mask) | flags; - } while (unlikely(cmpxchg(&inode->i_flags, old_flags, - new_flags) != old_flags)); + set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); diff --git a/fs/iomap.c b/fs/iomap.c index a3088fae567b..897c60215dd1 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + + /* + * migrate_page_move_mapping() assumes that pages with private data have + * their count elevated by 1. + */ + get_page(page); set_page_private(page, (unsigned long)iop); SetPagePrivate(page); return iop; @@ -132,6 +138,7 @@ iomap_page_release(struct page *page) WARN_ON_ONCE(atomic_read(&iop->write_count)); ClearPagePrivate(page); set_page_private(page, 0); + put_page(page); kfree(iop); } @@ -569,8 +576,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage, if (page_has_private(page)) { ClearPagePrivate(page); + get_page(newpage); set_page_private(newpage, page_private(page)); set_page_private(page, 0); + put_page(page); SetPagePrivate(newpage); } @@ -1804,6 +1813,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t pos = iocb->ki_pos, start = pos; loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; + bool wait_for_completion = is_sync_kiocb(iocb); struct blk_plug plug; struct iomap_dio *dio; @@ -1823,7 +1833,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->end_io = end_io; dio->error = 0; dio->flags = 0; - dio->wait_for_completion = is_sync_kiocb(iocb); dio->submit.iter = iter; dio->submit.waiter = current; @@ -1878,7 +1887,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio_warn_stale_pagecache(iocb->ki_filp); ret = 0; - if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion && + if (iov_iter_rw(iter) == WRITE && !wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) @@ -1894,7 +1903,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret <= 0) { /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { - dio->wait_for_completion = true; + wait_for_completion = true; ret = 0; } break; @@ -1916,8 +1925,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (dio->flags & IOMAP_DIO_WRITE_FUA) dio->flags &= ~IOMAP_DIO_NEED_SYNC; + /* + * We are about to drop our additional submission reference, which + * might be the last reference to the dio. There are three three + * different ways we can progress here: + * + * (a) If this is the last reference we will always complete and free + * the dio ourselves. + * (b) If this is not the last reference, and we serve an asynchronous + * iocb, we must never touch the dio after the decrement, the + * I/O completion handler will complete and free it. + * (c) If this is not the last reference, but we serve a synchronous + * iocb, the I/O completion handler will wake us up on the drop + * of the final reference, and we will complete and free it here + * after we got woken by the I/O completion handler. + */ + dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { - if (!dio->wait_for_completion) + if (!wait_for_completion) return -EIOCBQUEUED; for (;;) { @@ -1934,9 +1959,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, __set_current_state(TASK_RUNNING); } - ret = iomap_dio_complete(dio); - - return ret; + return iomap_dio_complete(dio); out_free_dio: kfree(dio); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 4ca0b5c18192..b84d635567d3 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -536,8 +536,8 @@ void kernfs_put(struct kernfs_node *kn) security_release_secctx(kn->iattr->ia_secdata, kn->iattr->ia_secdata_len); simple_xattrs_free(&kn->iattr->xattrs); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } - kfree(kn->iattr); spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, kn->id.ino); spin_unlock(&kernfs_idr_lock); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f8d5021a652e..ae948aaa4c53 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + + return DEFAULT_POLLMASK; +} + static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + __poll_t ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 80cebcd94c90..0c1fd945ce42 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -42,7 +42,7 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) if (kn->iattr) goto out_unlock; - kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL); + kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL); if (!kn->iattr) goto out_unlock; iattrs = &kn->iattr->ia_iattr; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 3d83b114bb08..dba810cd83b1 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -78,7 +78,7 @@ static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) } extern const struct super_operations kernfs_sops; -extern struct kmem_cache *kernfs_node_cache; +extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index fdf527b6d79c..f3ac352699cf 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -20,7 +20,7 @@ #include "kernfs-internal.h" -struct kmem_cache *kernfs_node_cache; +struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data) { @@ -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); @@ -417,4 +421,9 @@ void __init kernfs_init(void) 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); + + /* Creates slab cache for kernfs inode attributes */ + kernfs_iattrs_cache = kmem_cache_create("kernfs_iattrs_cache", + sizeof(struct kernfs_iattrs), + 0, SLAB_PANIC, NULL); } diff --git a/fs/locks.c b/fs/locks.c index ff6af2c32601..eaa1cfaf73b0 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1058,7 +1058,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) return -ENOMEM; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -1100,7 +1100,7 @@ find_conflict: out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -1138,7 +1138,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, new_fl2 = locks_alloc_lock(); } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If @@ -1312,7 +1312,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); /* * Free any unused locks. */ @@ -1584,7 +1584,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1636,13 +1636,13 @@ restart: locks_insert_block(fl, new_fl, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_blocker, break_time); - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); @@ -1659,7 +1659,7 @@ restart: } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1729,7 +1729,7 @@ int fcntl_getlease(struct file *filp) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { @@ -1739,7 +1739,7 @@ int fcntl_getlease(struct file *filp) break; } spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } @@ -1813,7 +1813,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg, lease->fl_flags); @@ -1884,7 +1884,7 @@ out_setup: lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); @@ -1907,7 +1907,7 @@ static int generic_delete_lease(struct file *filp, void *owner) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && @@ -1920,7 +1920,7 @@ static int generic_delete_lease(struct file *filp, void *owner) if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } @@ -2643,13 +2643,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) if (list_empty(&ctx->flc_lease)) return; - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } diff --git a/fs/namespace.c b/fs/namespace.c index a677b59efd74..c4e83d94840c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2698,7 +2698,6 @@ static long exact_copy_from_user(void *to, const void __user * from, if (!access_ok(from, n)) return n; - current->kernel_uaccess_faults_ok++; while (n) { if (__get_user(c, f)) { memset(t, 0, n); @@ -2708,7 +2707,6 @@ static long exact_copy_from_user(void *to, const void __user * from, f++; n--; } - current->kernel_uaccess_faults_ok--; return n; } @@ -2746,7 +2744,7 @@ void *copy_mount_options(const void __user * data) char *copy_mount_string(const void __user *data) { - return data ? strndup_user(data, PAGE_SIZE) : NULL; + return data ? strndup_user(data, PATH_MAX) : NULL; } /* 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/super.c b/fs/nfs/super.c index 22ce3c8a2f46..0570391eaa16 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1895,6 +1895,11 @@ 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, ']'); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5a0bbf917a32..d09c9f878141 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); } /* @@ -621,11 +621,12 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_set_page_writeback(page); WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); - ret = 0; + ret = req->wb_context->error; /* If there is a fatal error that covers this write, just exit */ - if (nfs_error_is_fatal_on_server(req->wb_context->error)) + if (nfs_error_is_fatal_on_server(ret)) goto out_launder; + ret = 0; if (!nfs_pageio_add_request(pgio, req)) { ret = pgio->pg_error; /* @@ -635,9 +636,9 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_context_set_write_error(req->wb_context, ret); if (nfs_error_is_fatal_on_server(ret)) goto out_launder; - } + } else + ret = -EAGAIN; nfs_redirty_request(req); - ret = -EAGAIN; } else nfs_add_stats(page_file_mapping(page)->host, NFSIOS_WRITEPAGES, 1); @@ -993,7 +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; } @@ -1347,7 +1348,8 @@ 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); @@ -1365,7 +1367,7 @@ 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/nfsctl.c b/fs/nfsd/nfsctl.c index b33f9785b756..72a7681f4046 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1239,8 +1239,8 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; - nn->nfsd4_lease = 45; /* default lease time */ - nn->nfsd4_grace = 45; + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->clverifier_counter = prandom_u32(); nn->clientid_counter = prandom_u32(); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9824e32b2f23..7dc98e14655d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -557,9 +557,11 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, loff_t cloned; cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); + if (cloned < 0) + return nfserrno(cloned); if (count && cloned != count) - cloned = -EINVAL; - return nfserrno(cloned < 0 ? cloned : 0); + return nfserrno(-EINVAL); + return 0; } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index d1cbb27808e2..6f0999015a44 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7532,10 +7532,11 @@ static int ocfs2_trim_group(struct super_block *sb, return count; } -int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) +static +int ocfs2_trim_mainbm(struct super_block *sb, struct fstrim_range *range) { struct ocfs2_super *osb = OCFS2_SB(sb); - u64 start, len, trimmed, first_group, last_group, group; + u64 start, len, trimmed = 0, first_group, last_group = 0, group = 0; int ret, cnt; u32 first_bit, last_bit, minlen; struct buffer_head *main_bm_bh = NULL; @@ -7543,7 +7544,6 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) struct buffer_head *gd_bh = NULL; struct ocfs2_dinode *main_bm; struct ocfs2_group_desc *gd = NULL; - struct ocfs2_trim_fs_info info, *pinfo = NULL; start = range->start >> osb->s_clustersize_bits; len = range->len >> osb->s_clustersize_bits; @@ -7552,6 +7552,9 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen >= osb->bitmap_cpg || range->len < sb->s_blocksize) return -EINVAL; + trace_ocfs2_trim_mainbm(start, len, minlen); + +next_group: main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); @@ -7570,64 +7573,34 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) } main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data; - if (start >= le32_to_cpu(main_bm->i_clusters)) { - ret = -EINVAL; - goto out_unlock; - } - - len = range->len >> osb->s_clustersize_bits; - if (start + len > le32_to_cpu(main_bm->i_clusters)) - len = le32_to_cpu(main_bm->i_clusters) - start; - - trace_ocfs2_trim_fs(start, len, minlen); - - ocfs2_trim_fs_lock_res_init(osb); - ret = ocfs2_trim_fs_lock(osb, NULL, 1); - if (ret < 0) { - if (ret != -EAGAIN) { - mlog_errno(ret); - ocfs2_trim_fs_lock_res_uninit(osb); + /* + * Do some check before trim the first group. + */ + if (!group) { + if (start >= le32_to_cpu(main_bm->i_clusters)) { + ret = -EINVAL; goto out_unlock; } - mlog(ML_NOTICE, "Wait for trim on device (%s) to " - "finish, which is running from another node.\n", - osb->dev_str); - ret = ocfs2_trim_fs_lock(osb, &info, 0); - if (ret < 0) { - mlog_errno(ret); - ocfs2_trim_fs_lock_res_uninit(osb); - goto out_unlock; - } + if (start + len > le32_to_cpu(main_bm->i_clusters)) + len = le32_to_cpu(main_bm->i_clusters) - start; - if (info.tf_valid && info.tf_success && - info.tf_start == start && info.tf_len == len && - info.tf_minlen == minlen) { - /* Avoid sending duplicated trim to a shared device */ - mlog(ML_NOTICE, "The same trim on device (%s) was " - "just done from node (%u), return.\n", - osb->dev_str, info.tf_nodenum); - range->len = info.tf_trimlen; - goto out_trimunlock; - } + /* + * Determine first and last group to examine based on + * start and len + */ + first_group = ocfs2_which_cluster_group(main_bm_inode, start); + if (first_group == osb->first_cluster_group_blkno) + first_bit = start; + else + first_bit = start - ocfs2_blocks_to_clusters(sb, + first_group); + last_group = ocfs2_which_cluster_group(main_bm_inode, + start + len - 1); + group = first_group; } - info.tf_nodenum = osb->node_num; - info.tf_start = start; - info.tf_len = len; - info.tf_minlen = minlen; - - /* Determine first and last group to examine based on start and len */ - first_group = ocfs2_which_cluster_group(main_bm_inode, start); - if (first_group == osb->first_cluster_group_blkno) - first_bit = start; - else - first_bit = start - ocfs2_blocks_to_clusters(sb, first_group); - last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1); - last_bit = osb->bitmap_cpg; - - trimmed = 0; - for (group = first_group; group <= last_group;) { + do { if (first_bit + len >= osb->bitmap_cpg) last_bit = osb->bitmap_cpg; else @@ -7659,21 +7632,81 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg); else group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg); - } - range->len = trimmed * sb->s_blocksize; + } while (0); - info.tf_trimlen = range->len; - info.tf_success = (ret ? 0 : 1); - pinfo = &info; -out_trimunlock: - ocfs2_trim_fs_unlock(osb, pinfo); - ocfs2_trim_fs_lock_res_uninit(osb); out_unlock: ocfs2_inode_unlock(main_bm_inode, 0); brelse(main_bm_bh); + main_bm_bh = NULL; out_mutex: inode_unlock(main_bm_inode); iput(main_bm_inode); + + /* + * If all the groups trim are not done or failed, but we should release + * main_bm related locks for avoiding the current IO starve, then go to + * trim the next group + */ + if (ret >= 0 && group <= last_group) + goto next_group; out: + range->len = trimmed * sb->s_blocksize; + return ret; +} + +int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) +{ + int ret; + struct ocfs2_super *osb = OCFS2_SB(sb); + struct ocfs2_trim_fs_info info, *pinfo = NULL; + + ocfs2_trim_fs_lock_res_init(osb); + + trace_ocfs2_trim_fs(range->start, range->len, range->minlen); + + ret = ocfs2_trim_fs_lock(osb, NULL, 1); + if (ret < 0) { + if (ret != -EAGAIN) { + mlog_errno(ret); + ocfs2_trim_fs_lock_res_uninit(osb); + return ret; + } + + mlog(ML_NOTICE, "Wait for trim on device (%s) to " + "finish, which is running from another node.\n", + osb->dev_str); + ret = ocfs2_trim_fs_lock(osb, &info, 0); + if (ret < 0) { + mlog_errno(ret); + ocfs2_trim_fs_lock_res_uninit(osb); + return ret; + } + + if (info.tf_valid && info.tf_success && + info.tf_start == range->start && + info.tf_len == range->len && + info.tf_minlen == range->minlen) { + /* Avoid sending duplicated trim to a shared device */ + mlog(ML_NOTICE, "The same trim on device (%s) was " + "just done from node (%u), return.\n", + osb->dev_str, info.tf_nodenum); + range->len = info.tf_trimlen; + goto out; + } + } + + info.tf_nodenum = osb->node_num; + info.tf_start = range->start; + info.tf_len = range->len; + info.tf_minlen = range->minlen; + + ret = ocfs2_trim_mainbm(sb, range); + + info.tf_trimlen = range->len; + info.tf_success = (ret < 0 ? 0 : 1); + pinfo = &info; +out: + ocfs2_trim_fs_unlock(osb, pinfo); + ocfs2_trim_fs_lock_res_uninit(osb); return ret; } diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 0e4166cc23a0..4ac775e32240 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/dlmglue.c b/fs/ocfs2/dlmglue.c index 7c835824247e..af405586c5b1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -686,6 +686,9 @@ void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; + /* Only one trimfs thread are allowed to work at the same time. */ + mutex_lock(&osb->obs_trim_fs_mutex); + ocfs2_lock_res_init_once(lockres); ocfs2_build_lock_name(OCFS2_LOCK_TYPE_TRIM_FS, 0, 0, lockres->l_name); ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_TRIM_FS, @@ -698,6 +701,8 @@ void ocfs2_trim_fs_lock_res_uninit(struct ocfs2_super *osb) ocfs2_simple_drop_lockres(osb, lockres); ocfs2_lock_res_free(lockres); + + mutex_unlock(&osb->obs_trim_fs_mutex); } static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res, diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 4f86ac0027b5..1f029fbe8b8d 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -407,6 +407,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; struct ocfs2_lock_res osb_trim_fs_lockres; + struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; struct dentry *osb_debug_root; diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 2ee76a90ba8f..dc4bce1649c1 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -712,6 +712,8 @@ TRACE_EVENT(ocfs2_trim_extent, DEFINE_OCFS2_ULL_UINT_UINT_UINT_EVENT(ocfs2_trim_group); +DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_mainbm); + DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_fs); /* End of trace events for fs/ocfs2/alloc.c. */ diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index d7407994f308..ea0756d83250 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -55,7 +55,7 @@ struct ocfs2_slot_info { unsigned int si_blocks; struct buffer_head **si_bh; unsigned int si_num_slots; - struct ocfs2_slot *si_slots; + struct ocfs2_slot si_slots[]; }; @@ -420,9 +420,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) struct inode *inode = NULL; struct ocfs2_slot_info *si; - si = kzalloc(sizeof(struct ocfs2_slot_info) + - (sizeof(struct ocfs2_slot) * osb->max_slots), - GFP_KERNEL); + si = kzalloc(struct_size(si, si_slots, osb->max_slots), GFP_KERNEL); if (!si) { status = -ENOMEM; mlog_errno(status); @@ -431,8 +429,6 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) si->si_extended = ocfs2_uses_extended_slot_map(osb); si->si_num_slots = osb->max_slots; - si->si_slots = (struct ocfs2_slot *)((char *)si + - sizeof(struct ocfs2_slot_info)); inode = ocfs2_get_system_file_inode(osb, SLOT_MAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 3415e0b09398..96ae7cedd487 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1847,6 +1847,8 @@ static int ocfs2_mount_volume(struct super_block *sb) if (ocfs2_is_hard_readonly(osb)) goto leave; + mutex_init(&osb->obs_trim_fs_mutex); + status = ocfs2_dlm_init(osb); if (status < 0) { mlog_errno(status); diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index a5a2fe76568f..b094d3d79354 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -398,8 +398,6 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter loff_t pos = iocb->ki_pos; ssize_t rc = 0; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n"); orangefs_stats.reads++; @@ -416,8 +414,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite loff_t pos; ssize_t rc; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n"); inode_lock(file->f_mapping->host); diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..51d5fd8840ab 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -140,8 +140,7 @@ static int anon_pipe_buf_steal(struct pipe_inode_info *pipe, struct page *page = buf->page; if (page_count(page) == 1) { - if (memcg_kmem_enabled()) - memcg_kmem_uncharge(page, 0); + memcg_kmem_uncharge(page, 0); __SetPageLocked(page); return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 9d428d5a0ac8..2edbb657f859 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -343,28 +343,28 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif - seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + seq_puts(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: - seq_printf(m, "unknown"); + seq_puts(m, "unknown"); break; case PR_SPEC_NOT_AFFECTED: - seq_printf(m, "not vulnerable"); + seq_puts(m, "not vulnerable"); break; case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: - seq_printf(m, "thread force mitigated"); + seq_puts(m, "thread force mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: - seq_printf(m, "thread mitigated"); + seq_puts(m, "thread mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_ENABLE: - seq_printf(m, "thread vulnerable"); + seq_puts(m, "thread vulnerable"); break; case PR_SPEC_DISABLE: - seq_printf(m, "globally mitigated"); + seq_puts(m, "globally mitigated"); break; default: - seq_printf(m, "vulnerable"); + seq_puts(m, "vulnerable"); break; } seq_putc(m, '\n'); diff --git a/fs/proc/base.c b/fs/proc/base.c index 633a63462573..511b279ec69c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -456,7 +456,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) - seq_printf(m, "0 0 0\n"); + seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, @@ -1086,10 +1086,6 @@ 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; @@ -3165,7 +3161,7 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, return d_splice_alias(inode, dentry); } -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) +struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8ae109429a88..e39bac94dead 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &proc_misc_dentry_ops); + d_set_d_op(dentry, de->proc_dops); return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); @@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); + ent->proc_dops = &proc_misc_dentry_ops; + out: return ent; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5185d7f6a51e..4fc5a9b68f76 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -44,6 +44,7 @@ struct proc_dir_entry { struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; + const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); @@ -161,7 +162,7 @@ extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struc extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); -extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int); +struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ diff --git a/fs/proc/page.c b/fs/proc/page.c index 40b05e0d4274..544d1ee15aee 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page) else if (page_count(page) == 0 && is_free_buddy_page(page)) u |= 1 << KPF_BUDDY; - if (PageBalloon(page)) - u |= 1 << KPF_BALLOON; + if (PageOffline(page)) + u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index d5e0fcb3439e..a7b12435519e 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +static const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + +static void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} + static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; return proc_register(parent, p); @@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; p->write = write; diff --git a/fs/proc/root.c b/fs/proc/root.c index f4b1a9d2eca6..621e6ec322ca 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -154,7 +154,7 @@ static int proc_root_getattr(const struct path *path, struct kstat *stat, static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_pid_lookup(dir, dentry, flags)) + if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); diff --git a/fs/proc/self.c b/fs/proc/self.c index 127265e5c55f..57c0a1047250 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -38,6 +38,7 @@ int proc_setup_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; + int ret = -ENOMEM; inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); @@ -51,20 +52,19 @@ int proc_setup_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_self_inode_operations; d_add(self, inode); + ret = 0; } else { dput(self); - self = ERR_PTR(-ENOMEM); } - } else { - self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); - return PTR_ERR(self); - } - ns->proc_self = self; - return 0; + else + ns->proc_self = self; + + return ret; } void __init proc_self_init(void) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 535eda7857cf..80c305f206bb 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -23,21 +23,21 @@ #ifdef arch_idle_time -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) idle += arch_idle_time(cpu); return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait; - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; if (cpu_online(cpu) && nr_iowait_cpu(cpu)) iowait += arch_idle_time(cpu); return iowait; @@ -45,7 +45,7 @@ static u64 get_iowait_time(int cpu) #else -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; @@ -54,14 +54,14 @@ static u64 get_idle_time(int cpu) if (idle_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; else idle = idle_usecs * NSEC_PER_USEC; return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait, iowait_usecs = -1ULL; @@ -70,7 +70,7 @@ static u64 get_iowait_time(int cpu) if (iowait_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; else iowait = iowait_usecs * NSEC_PER_USEC; @@ -79,6 +79,31 @@ static u64 get_iowait_time(int cpu) #endif +static void show_irq_gap(struct seq_file *p, unsigned int gap) +{ + static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"; + + while (gap > 0) { + unsigned int inc; + + inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2); + seq_write(p, zeros, 2 * inc); + gap -= inc; + } +} + +static void show_all_irqs(struct seq_file *p) +{ + unsigned int i, next = 0; + + for_each_active_irq(i) { + show_irq_gap(p, i - next); + seq_put_decimal_ull(p, " ", kstat_irqs_usr(i)); + next = i + 1; + } + show_irq_gap(p, nr_irqs - next); +} + static int show_stat(struct seq_file *p, void *v) { int i, j; @@ -95,16 +120,18 @@ static int show_stat(struct seq_file *p, void *v) getboottime64(&boottime); for_each_possible_cpu(i) { - user += kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle += get_idle_time(i); - iowait += get_iowait_time(i); - irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + + user += kcs->cpustat[CPUTIME_USER]; + nice += kcs->cpustat[CPUTIME_NICE]; + system += kcs->cpustat[CPUTIME_SYSTEM]; + idle += get_idle_time(kcs, i); + iowait += get_iowait_time(kcs, i); + irq += kcs->cpustat[CPUTIME_IRQ]; + softirq += kcs->cpustat[CPUTIME_SOFTIRQ]; + steal += kcs->cpustat[CPUTIME_STEAL]; + guest += kcs->cpustat[CPUTIME_GUEST]; + guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE]; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); @@ -130,17 +157,19 @@ static int show_stat(struct seq_file *p, void *v) seq_putc(p, '\n'); for_each_online_cpu(i) { + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle = get_idle_time(i); - iowait = get_iowait_time(i); - irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + user = kcs->cpustat[CPUTIME_USER]; + nice = kcs->cpustat[CPUTIME_NICE]; + system = kcs->cpustat[CPUTIME_SYSTEM]; + idle = get_idle_time(kcs, i); + iowait = get_iowait_time(kcs, i); + irq = kcs->cpustat[CPUTIME_IRQ]; + softirq = kcs->cpustat[CPUTIME_SOFTIRQ]; + steal = kcs->cpustat[CPUTIME_STEAL]; + guest = kcs->cpustat[CPUTIME_GUEST]; + guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); @@ -156,9 +185,7 @@ static int show_stat(struct seq_file *p, void *v) } seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); - /* sum again ? it could be updated? */ - for_each_irq_nr(j) - seq_put_decimal_ull(p, " ", kstat_irqs_usr(j)); + show_all_irqs(p); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0ec9edab2f3..beccb0b1d57c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -423,7 +423,7 @@ 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; @@ -450,24 +450,31 @@ 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; } } } @@ -490,6 +497,7 @@ 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)) { @@ -532,7 +540,7 @@ 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 @@ -541,6 +549,7 @@ 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 */ @@ -555,7 +564,7 @@ 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, @@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma, } } #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; } #define SEQ_PUT_DEC(str, val) \ @@ -942,10 +948,12 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, pte_t ptent = *pte; if (pte_present(ptent)) { - ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte); - ptent = pte_wrprotect(ptent); + pte_t old_pte; + + old_pte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); - ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); set_pte_at(vma->vm_mm, addr, pte, ptent); diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 0b63d68dedb2..36bf0f2e102e 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -64,7 +64,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) else bytes += kobjsize(current->files); - if (current->sighand && atomic_read(¤t->sighand->count) > 1) + if (current->sighand && refcount_read(¤t->sighand->count) > 1) sbytes += kobjsize(current->sighand); else bytes += kobjsize(current->sighand); @@ -178,7 +178,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) seq_file_path(m, file, ""); } else if (mm && is_stack(vma)) { seq_pad(m, ' '); - seq_printf(m, "[stack]"); + seq_puts(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index b905010ca9eb..f61ae53533f5 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -38,6 +38,7 @@ int proc_setup_thread_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *thread_self; + int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); @@ -51,20 +52,19 @@ int proc_setup_thread_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); + ret = 0; } else { dput(thread_self); - thread_self = ERR_PTR(-ENOMEM); } - } else { - thread_self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(thread_self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); - return PTR_ERR(thread_self); - } - ns->proc_thread_self = thread_self; - return 0; + else + ns->proc_thread_self = thread_self; + + return ret; } void __init proc_thread_self_init(void) diff --git a/fs/read_write.c b/fs/read_write.c index ff3c5e6f87cf..30df848b7451 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -426,7 +426,7 @@ ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) ssize_t result; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ result = vfs_read(file, (void __user *)buf, count, pos); set_fs(old_fs); @@ -499,7 +499,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t return -EINVAL; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; @@ -521,7 +521,7 @@ ssize_t kernel_write(struct file *file, const void *buf, size_t count, ssize_t res; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_write(file, (__force const char __user *)buf, count, pos); set_fs(old_fs); diff --git a/fs/select.c b/fs/select.c index d0f35dbc0e8f..6cbc9ff56ba0 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1379,7 +1379,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, +COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { @@ -1402,7 +1402,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, #endif #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, +COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { diff --git a/fs/splice.c b/fs/splice.c index de2ede048473..6489fb9436e4 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -357,7 +357,7 @@ static ssize_t kernel_readv(struct file *file, const struct kvec *vec, ssize_t res; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0); set_fs(old_fs); @@ -1123,6 +1123,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (ipipe == opipe) return -EINVAL; + if ((in->f_flags | out->f_flags) & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + return splice_pipe_to_pipe(ipipe, opipe, len, flags); } @@ -1148,6 +1151,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (unlikely(ret < 0)) return ret; + if (in->f_flags & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + file_start_write(out); ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); @@ -1172,6 +1178,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, offset = in->f_pos; } + if (out->f_flags & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) @@ -1717,6 +1726,9 @@ static long do_tee(struct file *in, struct file *out, size_t len, * copying the data. */ if (ipipe && opipe && ipipe != opipe) { + if ((in->f_flags | out->f_flags) & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + /* * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 51398457fe00..130fc6fbcc03 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -17,7 +17,6 @@ #include <linux/seq_file.h> #include "sysfs.h" -#include "../kernfs/kernfs-internal.h" /* * Determine ktype->sysfs_ops for the given kernfs_node. This function @@ -497,6 +496,7 @@ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; + for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } diff --git a/fs/timerfd.c b/fs/timerfd.c index 803ca070d42e..6a6fc8aa1de7 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -560,7 +560,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, +SYSCALL_DEFINE4(timerfd_settime32, int, ufd, int, flags, const struct old_itimerspec32 __user *, utmr, struct old_itimerspec32 __user *, otmr) { @@ -577,7 +577,7 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, +SYSCALL_DEFINE2(timerfd_gettime32, int, ufd, struct old_itimerspec32 __user *, otmr) { struct itimerspec64 kotmr; diff --git a/fs/udf/super.c b/fs/udf/super.c index e3d684ea3203..ffd8038ff728 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1474,6 +1474,17 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, if (lvd->integritySeqExt.extLength) udf_load_logicalvolint(sb, leea_to_cpu(lvd->integritySeqExt)); ret = 0; + + if (!sbi->s_lvid_bh) { + /* We can't generate unique IDs without a valid LVID */ + if (sb_rdonly(sb)) { + UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); + } else { + udf_warn(sb, "Damaged or missing LVID, forcing " + "readonly mount\n"); + ret = -EACCES; + } + } out_bh: brelse(bh); return ret; @@ -1943,13 +1954,24 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, return 0; } +static void udf_finalize_lvid(struct logicalVolIntegrityDesc *lvid) +{ + struct timespec64 ts; + + ktime_get_real_ts64(&ts); + udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); + lvid->descTag.descCRC = cpu_to_le16( + crc_itu_t(0, (char *)lvid + sizeof(struct tag), + le16_to_cpu(lvid->descTag.descCRCLength))); + lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); +} + static void udf_open_lvid(struct super_block *sb) { struct udf_sb_info *sbi = UDF_SB(sb); struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; - struct timespec64 ts; if (!bh) return; @@ -1961,18 +1983,12 @@ static void udf_open_lvid(struct super_block *sb) mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; - ktime_get_real_ts64(&ts); - udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); if (le32_to_cpu(lvid->integrityType) == LVID_INTEGRITY_TYPE_CLOSE) lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN); else UDF_SET_FLAG(sb, UDF_FLAG_INCONSISTENT); - lvid->descTag.descCRC = cpu_to_le16( - crc_itu_t(0, (char *)lvid + sizeof(struct tag), - le16_to_cpu(lvid->descTag.descCRCLength))); - - lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); + udf_finalize_lvid(lvid); mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; mutex_unlock(&sbi->s_alloc_mutex); @@ -1986,7 +2002,6 @@ static void udf_close_lvid(struct super_block *sb) struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; - struct timespec64 ts; if (!bh) return; @@ -1998,8 +2013,6 @@ static void udf_close_lvid(struct super_block *sb) mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; - ktime_get_real_ts64(&ts); - udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); if (UDF_MAX_WRITE_VERSION > le16_to_cpu(lvidiu->maxUDFWriteRev)) lvidiu->maxUDFWriteRev = cpu_to_le16(UDF_MAX_WRITE_VERSION); if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFReadRev)) @@ -2009,17 +2022,13 @@ static void udf_close_lvid(struct super_block *sb) if (!UDF_QUERY_FLAG(sb, UDF_FLAG_INCONSISTENT)) lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_CLOSE); - lvid->descTag.descCRC = cpu_to_le16( - crc_itu_t(0, (char *)lvid + sizeof(struct tag), - le16_to_cpu(lvid->descTag.descCRCLength))); - - lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); /* * We set buffer uptodate unconditionally here to avoid spurious * warnings from mark_buffer_dirty() when previous EIO has marked * the buffer as !uptodate */ set_buffer_uptodate(bh); + udf_finalize_lvid(lvid); mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; mutex_unlock(&sbi->s_alloc_mutex); @@ -2048,8 +2057,8 @@ u64 lvid_get_unique_id(struct super_block *sb) if (!(++uniqueID & 0xFFFFFFFF)) uniqueID += 16; lvhd->uniqueID = cpu_to_le64(uniqueID); + udf_updated_lvid(sb); mutex_unlock(&sbi->s_alloc_mutex); - mark_buffer_dirty(bh); return ret; } @@ -2320,11 +2329,17 @@ static int udf_sync_fs(struct super_block *sb, int wait) mutex_lock(&sbi->s_alloc_mutex); if (sbi->s_lvid_dirty) { + struct buffer_head *bh = sbi->s_lvid_bh; + struct logicalVolIntegrityDesc *lvid; + + lvid = (struct logicalVolIntegrityDesc *)bh->b_data; + udf_finalize_lvid(lvid); + /* * Blockdevice will be synced later so we don't have to submit * the buffer for IO */ - mark_buffer_dirty(sbi->s_lvid_bh); + mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; } mutex_unlock(&sbi->s_alloc_mutex); diff --git a/fs/utimes.c b/fs/utimes.c index bdcf2daf39c1..350c9c16ace1 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -224,8 +224,8 @@ SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) * of sys_utimes. */ #ifdef __ARCH_WANT_SYS_UTIME32 -COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, - struct old_utimbuf32 __user *, t) +SYSCALL_DEFINE2(utime32, const char __user *, filename, + struct old_utimbuf32 __user *, t) { struct timespec64 tv[2]; @@ -240,7 +240,7 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, } #endif -COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) +SYSCALL_DEFINE4(utimensat_time32, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { struct timespec64 tv[2]; @@ -276,14 +276,14 @@ static long do_compat_futimesat(unsigned int dfd, const char __user *filename, return do_utimes(dfd, filename, t ? tv : NULL, 0); } -COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, +SYSCALL_DEFINE3(futimesat_time32, unsigned int, dfd, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(dfd, filename, t); } -COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct old_timeval32 __user *, t) +SYSCALL_DEFINE2(utimes_time32, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(AT_FDCWD, filename, t); } diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 1c8eecfe52b8..6acf1bfa0bfe 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -768,18 +768,23 @@ xrep_findroot_block( if (!uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) goto out; + /* + * Read verifiers can reference b_ops, so we set the pointer + * here. If the verifier fails we'll reset the buffer state + * to what it was before we touched the buffer. + */ + bp->b_ops = fab->buf_ops; fab->buf_ops->verify_read(bp); if (bp->b_error) { + bp->b_ops = NULL; bp->b_error = 0; goto out; } /* * Some read verifiers will (re)set b_ops, so we must be - * careful not to blow away any such assignment. + * careful not to change b_ops after running the verifier. */ - if (!bp->b_ops) - bp->b_ops = fab->buf_ops; } /* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 338b9d9984e0..d9048bcea49c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -449,6 +449,7 @@ xfs_map_blocks( } wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap); return 0; allocate_blocks: @@ -459,6 +460,7 @@ allocate_blocks: ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF || imap.br_startoff + imap.br_blockcount <= cow_fsb); wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap); return 0; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index eedc5e0156ff..4f5f2ff3f70f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -776,10 +776,26 @@ _xfs_buf_read( } /* + * Set buffer ops on an unchecked buffer and validate it, if possible. + * * If the caller passed in an ops structure and the buffer doesn't have ops * assigned, set the ops and use them to verify the contents. If the contents * cannot be verified, we'll clear XBF_DONE. We assume the buffer has no * recorded errors and is already in XBF_DONE state. + * + * Under normal operations, every in-core buffer must have buffer ops assigned + * to them when the buffer is read in from disk so that we can validate the + * metadata. + * + * However, there are two scenarios where one can encounter in-core buffers + * that don't have buffer ops. The first is during log recovery of buffers on + * a V4 filesystem, though these buffers are purged at the end of recovery. + * + * The other is online repair, which tries to match arbitrary metadata blocks + * with btree types in order to find the root. If online repair doesn't match + * the buffer with /any/ btree type, the buffer remains in memory in DONE state + * with no ops, and a subsequent read_buf call from elsewhere will not set the + * ops. This function helps us fix this situation. */ int xfs_buf_ensure_ops( @@ -1536,8 +1552,7 @@ __xfs_buf_submit( xfs_buf_ioerror(bp, -EIO); bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); - if (bp->b_flags & XBF_ASYNC) - xfs_buf_ioend(bp); + xfs_buf_ioend(bp); return -EIO; } |