diff options
Diffstat (limited to 'fs')
379 files changed, 5805 insertions, 3670 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 0d28ecf668d0..b845ee18a80b 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -260,7 +260,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_blocks = 0; inode->i_rdev = rdev; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mapping->a_ops = &v9fs_addr_operations; inode->i_private = NULL; @@ -1150,8 +1150,8 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, set_nlink(inode, 1); - inode->i_atime.tv_sec = stat->atime; - inode->i_mtime.tv_sec = stat->mtime; + inode_set_atime(inode, stat->atime, 0); + inode_set_mtime(inode, stat->mtime, 0); inode_set_ctime(inode, stat->mtime, 0); inode->i_uid = v9ses->dfltuid; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 1312f68965ac..c7319af2f471 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -641,10 +641,10 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, struct v9fs_inode *v9inode = V9FS_I(inode); if ((stat->st_result_mask & P9_STATS_BASIC) == P9_STATS_BASIC) { - inode->i_atime.tv_sec = stat->st_atime_sec; - inode->i_atime.tv_nsec = stat->st_atime_nsec; - inode->i_mtime.tv_sec = stat->st_mtime_sec; - inode->i_mtime.tv_nsec = stat->st_mtime_nsec; + inode_set_atime(inode, stat->st_atime_sec, + stat->st_atime_nsec); + inode_set_mtime(inode, stat->st_mtime_sec, + stat->st_mtime_nsec); inode_set_ctime(inode, stat->st_ctime_sec, stat->st_ctime_nsec); inode->i_uid = stat->st_uid; @@ -660,12 +660,12 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, inode->i_blocks = stat->st_blocks; } else { if (stat->st_result_mask & P9_STATS_ATIME) { - inode->i_atime.tv_sec = stat->st_atime_sec; - inode->i_atime.tv_nsec = stat->st_atime_nsec; + inode_set_atime(inode, stat->st_atime_sec, + stat->st_atime_nsec); } if (stat->st_result_mask & P9_STATS_MTIME) { - inode->i_mtime.tv_sec = stat->st_mtime_sec; - inode->i_mtime.tv_nsec = stat->st_mtime_nsec; + inode_set_mtime(inode, stat->st_mtime_sec, + stat->st_mtime_nsec); } if (stat->st_result_mask & P9_STATS_CTIME) { inode_set_ctime(inode, stat->st_ctime_sec, diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index e00cf8109b3f..053d1cef6e13 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -162,27 +162,27 @@ static int v9fs_xattr_handler_set(const struct xattr_handler *handler, return v9fs_xattr_set(dentry, full_name, value, size, flags); } -static struct xattr_handler v9fs_xattr_user_handler = { +static const struct xattr_handler v9fs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .get = v9fs_xattr_handler_get, .set = v9fs_xattr_handler_set, }; -static struct xattr_handler v9fs_xattr_trusted_handler = { +static const struct xattr_handler v9fs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .get = v9fs_xattr_handler_get, .set = v9fs_xattr_handler_set, }; #ifdef CONFIG_9P_FS_SECURITY -static struct xattr_handler v9fs_xattr_security_handler = { +static const struct xattr_handler v9fs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = v9fs_xattr_handler_get, .set = v9fs_xattr_handler_set, }; #endif -const struct xattr_handler *v9fs_xattr_handlers[] = { +const struct xattr_handler * const v9fs_xattr_handlers[] = { &v9fs_xattr_user_handler, &v9fs_xattr_trusted_handler, #ifdef CONFIG_9P_FS_SECURITY diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h index b5636e544c8a..3ad5a802352a 100644 --- a/fs/9p/xattr.h +++ b/fs/9p/xattr.h @@ -10,7 +10,7 @@ #include <net/9p/9p.h> #include <net/9p/client.h> -extern const struct xattr_handler *v9fs_xattr_handlers[]; +extern const struct xattr_handler * const v9fs_xattr_handlers[]; ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, void *buffer, size_t buffer_size); diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 20963002578a..3081edb09e46 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -242,6 +242,7 @@ struct inode * adfs_iget(struct super_block *sb, struct object_info *obj) { struct inode *inode; + struct timespec64 ts; inode = new_inode(sb); if (!inode) @@ -268,9 +269,10 @@ adfs_iget(struct super_block *sb, struct object_info *obj) ADFS_I(inode)->attr = obj->attr; inode->i_mode = adfs_atts2mode(sb, inode); - adfs_adfs2unix_time(&inode->i_mtime, inode); - inode->i_atime = inode->i_mtime; - inode_set_ctime_to_ts(inode, inode->i_mtime); + adfs_adfs2unix_time(&ts, inode); + inode_set_atime_to_ts(inode, ts); + inode_set_mtime_to_ts(inode, ts); + inode_set_ctime_to_ts(inode, ts); if (S_ISDIR(inode->i_mode)) { inode->i_op = &adfs_dir_inode_operations; @@ -321,7 +323,8 @@ adfs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, if (ia_valid & ATTR_MTIME && adfs_inode_is_stamped(inode)) { adfs_unix2adfs_time(inode, &attr->ia_mtime); - adfs_adfs2unix_time(&inode->i_mtime, inode); + adfs_adfs2unix_time(&attr->ia_mtime, inode); + inode_set_mtime_to_ts(inode, attr->ia_mtime); } /* @@ -329,7 +332,7 @@ adfs_notify_change(struct mnt_idmap *idmap, struct dentry *dentry, * have the ability to represent them in our filesystem? */ if (ia_valid & ATTR_ATIME) - inode->i_atime = attr->ia_atime; + inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(inode, attr->ia_ctime); if (ia_valid & ATTR_MODE) { diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 7ba93efc1143..fd669daa4e7b 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -60,7 +60,7 @@ affs_insert_hash(struct inode *dir, struct buffer_head *bh) mark_buffer_dirty_inode(dir_bh, dir); affs_brelse(dir_bh); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_inc_iversion(dir); mark_inode_dirty(dir); @@ -114,7 +114,7 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh) affs_brelse(bh); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_inc_iversion(dir); mark_inode_dirty(dir); diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 060746c63151..0210df8d3500 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -149,13 +149,9 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) break; } - inode->i_mtime.tv_sec = inode->i_atime.tv_sec = - inode_set_ctime(inode, - (be32_to_cpu(tail->change.days) * 86400LL + - be32_to_cpu(tail->change.mins) * 60 + - be32_to_cpu(tail->change.ticks) / 50 + AFFS_EPOCH_DELTA) - + sys_tz.tz_minuteswest * 60, 0).tv_sec; - inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = 0; + inode_set_mtime(inode, + inode_set_atime(inode, inode_set_ctime(inode, (be32_to_cpu(tail->change.days) * 86400LL + be32_to_cpu(tail->change.mins) * 60 + be32_to_cpu(tail->change.ticks) / 50 + AFFS_EPOCH_DELTA) + sys_tz.tz_minuteswest * 60, 0).tv_sec, 0).tv_sec, + 0); affs_brelse(bh); unlock_new_inode(inode); return inode; @@ -187,12 +183,13 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc) } tail = AFFS_TAIL(sb, bh); if (tail->stype == cpu_to_be32(ST_ROOT)) { - affs_secs_to_datestamp(inode->i_mtime.tv_sec, + affs_secs_to_datestamp(inode_get_mtime_sec(inode), &AFFS_ROOT_TAIL(sb, bh)->root_change); } else { tail->protect = cpu_to_be32(AFFS_I(inode)->i_protect); tail->size = cpu_to_be32(inode->i_size); - affs_secs_to_datestamp(inode->i_mtime.tv_sec, &tail->change); + affs_secs_to_datestamp(inode_get_mtime_sec(inode), + &tail->change); if (!(inode->i_ino == AFFS_SB(sb)->s_root_block)) { uid = i_uid_read(inode); gid = i_gid_read(inode); @@ -314,7 +311,7 @@ affs_new_inode(struct inode *dir) inode->i_gid = current_fsgid(); inode->i_ino = block; set_nlink(inode, 1); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); atomic_set(&AFFS_I(inode)->i_opencnt, 0); AFFS_I(inode)->i_blkcnt = 0; AFFS_I(inode)->i_lc = NULL; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 95bcbd7654d1..4d04ef2d3ae7 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -88,7 +88,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_blocks = 0; inode->i_generation = 0; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1c794a1896aa..78efc9719349 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -91,8 +91,8 @@ static int afs_inode_init_from_status(struct afs_operation *op, t = status->mtime_client; inode_set_ctime_to_ts(inode, t); - inode->i_mtime = t; - inode->i_atime = t; + inode_set_mtime_to_ts(inode, t); + inode_set_atime_to_ts(inode, t); inode->i_flags |= S_NOATIME; inode->i_uid = make_kuid(&init_user_ns, status->owner); inode->i_gid = make_kgid(&init_user_ns, status->group); @@ -204,7 +204,7 @@ static void afs_apply_status(struct afs_operation *op, } t = status->mtime_client; - inode->i_mtime = t; + inode_set_mtime_to_ts(inode, t); if (vp->update_ctime) inode_set_ctime_to_ts(inode, op->ctime); @@ -253,7 +253,7 @@ static void afs_apply_status(struct afs_operation *op, if (change_size) { afs_set_i_size(vnode, status->size); inode_set_ctime_to_ts(inode, t); - inode->i_atime = t; + inode_set_atime_to_ts(inode, t); } } } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index da73b97e19a9..23e2cc4efe41 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1541,7 +1541,7 @@ int afs_launder_folio(struct folio *); /* * xattr.c */ -extern const struct xattr_handler *afs_xattr_handlers[]; +extern const struct xattr_handler * const afs_xattr_handlers[]; /* * yfsclient.c diff --git a/fs/afs/write.c b/fs/afs/write.c index e1c45341719b..4a168781936b 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -424,7 +424,7 @@ try_next_key: op->store.write_iter = iter; op->store.i_size = max(pos + size, vnode->netfs.remote_i_size); - op->mtime = vnode->netfs.inode.i_mtime; + op->mtime = inode_get_mtime(&vnode->netfs.inode); afs_wait_for_operation(op); diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index 9048d8ccc715..64b2c0224f62 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -353,7 +353,7 @@ static const struct xattr_handler afs_xattr_afs_volume_handler = { .get = afs_xattr_get_volume, }; -const struct xattr_handler *afs_xattr_handlers[] = { +const struct xattr_handler * const afs_xattr_handlers[] = { &afs_xattr_afs_acl_handler, &afs_xattr_afs_cell_handler, &afs_xattr_afs_fid_handler, @@ -80,7 +80,7 @@ struct aio_ring { struct kioctx_table { struct rcu_head rcu; unsigned nr; - struct kioctx __rcu *table[]; + struct kioctx __rcu *table[] __counted_by(nr); }; struct kioctx_cpu { diff --git a/fs/attr.c b/fs/attr.c index a8ae5f6d9b16..bdf5deb06ea9 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -308,9 +308,9 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_ATIME) - inode->i_atime = attr->ia_atime; + inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) - inode->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(inode, attr->ia_ctime); if (ia_valid & ATTR_MODE) { diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index d5a44fa88acf..8c1d587b3eef 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -25,6 +25,8 @@ #include <linux/completion.h> #include <linux/file.h> #include <linux/magic.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY @@ -205,20 +207,34 @@ static inline void managed_dentry_clear_managed(struct dentry *dentry) /* Initializing function */ -int autofs_fill_super(struct super_block *, void *, int); +extern const struct fs_parameter_spec autofs_param_specs[]; +int autofs_init_fs_context(struct fs_context *fc); struct autofs_info *autofs_new_ino(struct autofs_sb_info *); void autofs_clean_ino(struct autofs_info *); -static inline int autofs_prepare_pipe(struct file *pipe) +static inline int autofs_check_pipe(struct file *pipe) { if (!(pipe->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!S_ISFIFO(file_inode(pipe)->i_mode)) return -EINVAL; + return 0; +} + +static inline void autofs_set_packet_pipe_flags(struct file *pipe) +{ /* We want a packet pipe */ pipe->f_flags |= O_DIRECT; /* We don't expect -EAGAIN */ pipe->f_flags &= ~O_NONBLOCK; +} + +static inline int autofs_prepare_pipe(struct file *pipe) +{ + int ret = autofs_check_pipe(pipe); + if (ret < 0) + return ret; + autofs_set_packet_pipe_flags(pipe); return 0; } diff --git a/fs/autofs/init.c b/fs/autofs/init.c index d3f55e874338..b5e4dfa04ed0 100644 --- a/fs/autofs/init.c +++ b/fs/autofs/init.c @@ -7,16 +7,11 @@ #include <linux/init.h> #include "autofs_i.h" -static struct dentry *autofs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_nodev(fs_type, flags, data, autofs_fill_super); -} - struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", - .mount = autofs_mount, + .init_fs_context = autofs_init_fs_context, + .parameters = autofs_param_specs, .kill_sb = autofs_kill_sb, }; MODULE_ALIAS_FS("autofs"); diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 2b49662ed237..a5083d447a62 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -6,7 +6,6 @@ #include <linux/seq_file.h> #include <linux/pagemap.h> -#include <linux/parser.h> #include "autofs_i.h" @@ -110,189 +109,179 @@ static const struct super_operations autofs_sops = { .evict_inode = autofs_evict_inode, }; -enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto, - Opt_indirect, Opt_direct, Opt_offset, Opt_strictexpire, - Opt_ignore}; - -static const match_table_t tokens = { - {Opt_fd, "fd=%u"}, - {Opt_uid, "uid=%u"}, - {Opt_gid, "gid=%u"}, - {Opt_pgrp, "pgrp=%u"}, - {Opt_minproto, "minproto=%u"}, - {Opt_maxproto, "maxproto=%u"}, - {Opt_indirect, "indirect"}, - {Opt_direct, "direct"}, - {Opt_offset, "offset"}, - {Opt_strictexpire, "strictexpire"}, - {Opt_ignore, "ignore"}, - {Opt_err, NULL} +enum { + Opt_direct, + Opt_fd, + Opt_gid, + Opt_ignore, + Opt_indirect, + Opt_maxproto, + Opt_minproto, + Opt_offset, + Opt_pgrp, + Opt_strictexpire, + Opt_uid, }; -static int parse_options(char *options, - struct inode *root, int *pgrp, bool *pgrp_set, - struct autofs_sb_info *sbi) +const struct fs_parameter_spec autofs_param_specs[] = { + fsparam_flag ("direct", Opt_direct), + fsparam_fd ("fd", Opt_fd), + fsparam_u32 ("gid", Opt_gid), + fsparam_flag ("ignore", Opt_ignore), + fsparam_flag ("indirect", Opt_indirect), + fsparam_u32 ("maxproto", Opt_maxproto), + fsparam_u32 ("minproto", Opt_minproto), + fsparam_flag ("offset", Opt_offset), + fsparam_u32 ("pgrp", Opt_pgrp), + fsparam_flag ("strictexpire", Opt_strictexpire), + fsparam_u32 ("uid", Opt_uid), + {} +}; + +struct autofs_fs_context { + kuid_t uid; + kgid_t gid; + int pgrp; + bool pgrp_set; +}; + +/* + * Open the fd. We do it here rather than in get_tree so that it's done in the + * context of the system call that passed the data and not the one that + * triggered the superblock creation, lest the fd gets reassigned. + */ +static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi, + struct fs_parameter *param, + struct fs_parse_result *result) { - char *p; - substring_t args[MAX_OPT_ARGS]; - int option; - int pipefd = -1; - kuid_t uid; - kgid_t gid; + struct file *pipe; + int ret; - root->i_uid = current_uid(); - root->i_gid = current_gid(); + if (param->type == fs_value_is_file) { + /* came through the new api */ + pipe = param->file; + param->file = NULL; + } else { + pipe = fget(result->uint_32); + } + if (!pipe) { + errorf(fc, "could not open pipe file descriptor"); + return -EBADF; + } - sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; - sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; + ret = autofs_check_pipe(pipe); + if (ret < 0) { + errorf(fc, "Invalid/unusable pipe"); + if (param->type != fs_value_is_file) + fput(pipe); + return -EBADF; + } - sbi->pipefd = -1; + autofs_set_packet_pipe_flags(pipe); - if (!options) - return 1; - - while ((p = strsep(&options, ",")) != NULL) { - int token; - - if (!*p) - continue; - - token = match_token(p, tokens, args); - switch (token) { - case Opt_fd: - if (match_int(args, &pipefd)) - return 1; - sbi->pipefd = pipefd; - break; - case Opt_uid: - if (match_int(args, &option)) - return 1; - uid = make_kuid(current_user_ns(), option); - if (!uid_valid(uid)) - return 1; - root->i_uid = uid; - break; - case Opt_gid: - if (match_int(args, &option)) - return 1; - gid = make_kgid(current_user_ns(), option); - if (!gid_valid(gid)) - return 1; - root->i_gid = gid; - break; - case Opt_pgrp: - if (match_int(args, &option)) - return 1; - *pgrp = option; - *pgrp_set = true; - break; - case Opt_minproto: - if (match_int(args, &option)) - return 1; - sbi->min_proto = option; - break; - case Opt_maxproto: - if (match_int(args, &option)) - return 1; - sbi->max_proto = option; - break; - case Opt_indirect: - set_autofs_type_indirect(&sbi->type); - break; - case Opt_direct: - set_autofs_type_direct(&sbi->type); - break; - case Opt_offset: - set_autofs_type_offset(&sbi->type); - break; - case Opt_strictexpire: - sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; - break; - case Opt_ignore: - sbi->flags |= AUTOFS_SBI_IGNORE; - break; - default: - return 1; - } + if (sbi->pipe) + fput(sbi->pipe); + + sbi->pipefd = result->uint_32; + sbi->pipe = pipe; + + return 0; +} + +static int autofs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct autofs_fs_context *ctx = fc->fs_private; + struct autofs_sb_info *sbi = fc->s_fs_info; + struct fs_parse_result result; + kuid_t uid; + kgid_t gid; + int opt; + + opt = fs_parse(fc, autofs_param_specs, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_fd: + return autofs_parse_fd(fc, sbi, param, &result); + case Opt_uid: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + return invalfc(fc, "Invalid uid"); + ctx->uid = uid; + break; + case Opt_gid: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + return invalfc(fc, "Invalid gid"); + ctx->gid = gid; + break; + case Opt_pgrp: + ctx->pgrp = result.uint_32; + ctx->pgrp_set = true; + break; + case Opt_minproto: + sbi->min_proto = result.uint_32; + break; + case Opt_maxproto: + sbi->max_proto = result.uint_32; + break; + case Opt_indirect: + set_autofs_type_indirect(&sbi->type); + break; + case Opt_direct: + set_autofs_type_direct(&sbi->type); + break; + case Opt_offset: + set_autofs_type_offset(&sbi->type); + break; + case Opt_strictexpire: + sbi->flags |= AUTOFS_SBI_STRICTEXPIRE; + break; + case Opt_ignore: + sbi->flags |= AUTOFS_SBI_IGNORE; } - return (sbi->pipefd < 0); + + return 0; } -int autofs_fill_super(struct super_block *s, void *data, int silent) +static struct autofs_sb_info *autofs_alloc_sbi(void) { - struct inode *root_inode; - struct dentry *root; - struct file *pipe; struct autofs_sb_info *sbi; - struct autofs_info *ino; - int pgrp = 0; - bool pgrp_set = false; - int ret = -EINVAL; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) - return -ENOMEM; - pr_debug("starting up, sbi = %p\n", sbi); + return NULL; - s->s_fs_info = sbi; sbi->magic = AUTOFS_SBI_MAGIC; - sbi->pipefd = -1; - sbi->pipe = NULL; - sbi->exp_timeout = 0; - sbi->oz_pgrp = NULL; - sbi->sb = s; - sbi->version = 0; - sbi->sub_version = 0; sbi->flags = AUTOFS_SBI_CATATONIC; + sbi->min_proto = AUTOFS_MIN_PROTO_VERSION; + sbi->max_proto = AUTOFS_MAX_PROTO_VERSION; + sbi->pipefd = -1; + set_autofs_type_indirect(&sbi->type); - sbi->min_proto = 0; - sbi->max_proto = 0; mutex_init(&sbi->wq_mutex); mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); - sbi->queues = NULL; spin_lock_init(&sbi->lookup_lock); INIT_LIST_HEAD(&sbi->active_list); INIT_LIST_HEAD(&sbi->expiring_list); - s->s_blocksize = 1024; - s->s_blocksize_bits = 10; - s->s_magic = AUTOFS_SUPER_MAGIC; - s->s_op = &autofs_sops; - s->s_d_op = &autofs_dentry_operations; - s->s_time_gran = 1; - /* - * Get the root inode and dentry, but defer checking for errors. - */ - ino = autofs_new_ino(sbi); - if (!ino) { - ret = -ENOMEM; - goto fail_free; - } - root_inode = autofs_get_inode(s, S_IFDIR | 0755); - root = d_make_root(root_inode); - if (!root) { - ret = -ENOMEM; - goto fail_ino; - } - pipe = NULL; - - root->d_fsdata = ino; + return sbi; +} - /* Can this call block? */ - if (parse_options(data, root_inode, &pgrp, &pgrp_set, sbi)) { - pr_err("called with bogus options\n"); - goto fail_dput; - } +static int autofs_validate_protocol(struct fs_context *fc) +{ + struct autofs_sb_info *sbi = fc->s_fs_info; /* Test versions first */ if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) { - pr_err("kernel does not match daemon version " + errorf(fc, "kernel does not match daemon version " "daemon (%d, %d) kernel (%d, %d)\n", sbi->min_proto, sbi->max_proto, AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION); - goto fail_dput; + return -EINVAL; } /* Establish highest kernel protocol version */ @@ -300,13 +289,62 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) sbi->version = AUTOFS_MAX_PROTO_VERSION; else sbi->version = sbi->max_proto; - sbi->sub_version = AUTOFS_PROTO_SUBVERSION; - if (pgrp_set) { - sbi->oz_pgrp = find_get_pid(pgrp); + switch (sbi->version) { + case 4: + sbi->sub_version = 7; + break; + case 5: + sbi->sub_version = AUTOFS_PROTO_SUBVERSION; + break; + default: + sbi->sub_version = 0; + } + + return 0; +} + +static int autofs_fill_super(struct super_block *s, struct fs_context *fc) +{ + struct autofs_fs_context *ctx = fc->fs_private; + struct autofs_sb_info *sbi = s->s_fs_info; + struct inode *root_inode; + struct dentry *root; + struct autofs_info *ino; + int ret = -ENOMEM; + + pr_debug("starting up, sbi = %p\n", sbi); + + sbi->sb = s; + s->s_blocksize = 1024; + s->s_blocksize_bits = 10; + s->s_magic = AUTOFS_SUPER_MAGIC; + s->s_op = &autofs_sops; + s->s_d_op = &autofs_dentry_operations; + s->s_time_gran = 1; + + /* + * Get the root inode and dentry, but defer checking for errors. + */ + ino = autofs_new_ino(sbi); + if (!ino) + goto fail; + + root_inode = autofs_get_inode(s, S_IFDIR | 0755); + root_inode->i_uid = ctx->uid; + root_inode->i_gid = ctx->gid; + + root = d_make_root(root_inode); + if (!root) + goto fail_ino; + + root->d_fsdata = ino; + + if (ctx->pgrp_set) { + sbi->oz_pgrp = find_get_pid(ctx->pgrp); if (!sbi->oz_pgrp) { - pr_err("could not find process group %d\n", - pgrp); + ret = invalf(fc, "Could not find process group %d", + ctx->pgrp); goto fail_dput; } } else { @@ -321,16 +359,7 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) pr_debug("pipe fd = %d, pgrp = %u\n", sbi->pipefd, pid_nr(sbi->oz_pgrp)); - pipe = fget(sbi->pipefd); - if (!pipe) { - pr_err("could not open pipe file descriptor\n"); - goto fail_put_pid; - } - ret = autofs_prepare_pipe(pipe); - if (ret < 0) - goto fail_fput; - sbi->pipe = pipe; sbi->flags &= ~AUTOFS_SBI_CATATONIC; /* @@ -342,22 +371,82 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) /* * Failure ... clean up. */ -fail_fput: - pr_err("pipe file descriptor does not contain proper ops\n"); - fput(pipe); -fail_put_pid: - put_pid(sbi->oz_pgrp); fail_dput: dput(root); - goto fail_free; + goto fail; fail_ino: autofs_free_ino(ino); -fail_free: - kfree(sbi); - s->s_fs_info = NULL; +fail: return ret; } +/* + * Validate the parameters and then request a superblock. + */ +static int autofs_get_tree(struct fs_context *fc) +{ + struct autofs_sb_info *sbi = fc->s_fs_info; + int ret; + + ret = autofs_validate_protocol(fc); + if (ret) + return ret; + + if (sbi->pipefd < 0) + return invalf(fc, "No control pipe specified"); + + return get_tree_nodev(fc, autofs_fill_super); +} + +static void autofs_free_fc(struct fs_context *fc) +{ + struct autofs_fs_context *ctx = fc->fs_private; + struct autofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) { + if (sbi->pipe) + fput(sbi->pipe); + kfree(sbi); + } + kfree(ctx); +} + +static const struct fs_context_operations autofs_context_ops = { + .free = autofs_free_fc, + .parse_param = autofs_parse_param, + .get_tree = autofs_get_tree, +}; + +/* + * Set up the filesystem mount context. + */ +int autofs_init_fs_context(struct fs_context *fc) +{ + struct autofs_fs_context *ctx; + struct autofs_sb_info *sbi; + + ctx = kzalloc(sizeof(struct autofs_fs_context), GFP_KERNEL); + if (!ctx) + goto nomem; + + ctx->uid = current_uid(); + ctx->gid = current_gid(); + + sbi = autofs_alloc_sbi(); + if (!sbi) + goto nomem_ctx; + + fc->fs_private = ctx; + fc->s_fs_info = sbi; + fc->ops = &autofs_context_ops; + return 0; + +nomem_ctx: + kfree(ctx); +nomem: + return -ENOMEM; +} + struct inode *autofs_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); @@ -370,7 +459,7 @@ struct inode *autofs_get_inode(struct super_block *sb, umode_t mode) inode->i_uid = d_inode(sb->s_root)->i_uid; inode->i_gid = d_inode(sb->s_root)->i_gid; } - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_ino = get_next_ino(); if (S_ISDIR(mode)) { diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 512b9a26c63d..530d18827e35 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -600,7 +600,7 @@ static int autofs_dir_symlink(struct mnt_idmap *idmap, p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return 0; } @@ -633,7 +633,7 @@ static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry) d_inode(dentry)->i_size = 0; clear_nlink(d_inode(dentry)); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); spin_lock(&sbi->lookup_lock); __autofs_add_expiring(dentry); @@ -749,7 +749,7 @@ static int autofs_dir_mkdir(struct mnt_idmap *idmap, p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; inc_nlink(dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return 0; } diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 83f9566c973b..316d88da2ce1 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -208,7 +208,7 @@ void make_bad_inode(struct inode *inode) remove_inode_hash(inode); inode->i_mode = S_IFREG; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &bad_inode_ops; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &bad_file_ops; diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 9a16a51fbb88..9acdec56f626 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -360,11 +360,11 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) * for indexing purposes. (PFD, page 54) */ - inode->i_mtime.tv_sec = - fs64_to_cpu(sb, raw_inode->last_modified_time) >> 16; - inode->i_mtime.tv_nsec = 0; /* lower 16 bits are not a time */ - inode_set_ctime_to_ts(inode, inode->i_mtime); - inode->i_atime = inode->i_mtime; + inode_set_mtime(inode, + fs64_to_cpu(sb, raw_inode->last_modified_time) >> 16, + 0);/* lower 16 bits are not a time */ + inode_set_ctime_to_ts(inode, inode_get_mtime(inode)); + inode_set_atime_to_ts(inode, inode_get_mtime(inode)); befs_ino->i_inode_num = fsrun_to_cpu(sb, raw_inode->inode_num); befs_ino->i_parent = fsrun_to_cpu(sb, raw_inode->parent); diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 12b8af04dcb3..fbc4ae80a4b2 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -97,7 +97,7 @@ static int bfs_create(struct mnt_idmap *idmap, struct inode *dir, set_bit(ino, info->si_imap); info->si_freei--; inode_init_owner(&nop_mnt_idmap, inode, dir, mode); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_blocks = 0; inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; @@ -187,7 +187,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry) } de->ino = 0; mark_buffer_dirty_inode(bh, dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); inode_dec_link_count(inode); @@ -240,7 +240,7 @@ static int bfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, goto end_rename; } old_de->ino = 0; - old_dir->i_mtime = inode_set_ctime_current(old_dir); + inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); mark_inode_dirty(old_dir); if (new_inode) { inode_set_ctime_current(new_inode); @@ -294,7 +294,8 @@ static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino) dir->i_size += BFS_DIRENT_SIZE; inode_set_ctime_current(dir); } - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, + inode_set_ctime_current(dir)); mark_inode_dirty(dir); de->ino = cpu_to_le16((u16)ino); for (i = 0; i < BFS_NAMELEN; i++) diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index e6a76ae9eb44..355957dbce39 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -80,11 +80,9 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) set_nlink(inode, le32_to_cpu(di->i_nlink)); inode->i_size = BFS_FILESIZE(di); inode->i_blocks = BFS_FILEBLOCKS(di); - inode->i_atime.tv_sec = le32_to_cpu(di->i_atime); - inode->i_mtime.tv_sec = le32_to_cpu(di->i_mtime); + inode_set_atime(inode, le32_to_cpu(di->i_atime), 0); + inode_set_mtime(inode, le32_to_cpu(di->i_mtime), 0); inode_set_ctime(inode, le32_to_cpu(di->i_ctime), 0); - inode->i_atime.tv_nsec = 0; - inode->i_mtime.tv_nsec = 0; brelse(bh); unlock_new_inode(inode); @@ -140,9 +138,9 @@ static int bfs_write_inode(struct inode *inode, struct writeback_control *wbc) di->i_uid = cpu_to_le32(i_uid_read(inode)); di->i_gid = cpu_to_le32(i_gid_read(inode)); di->i_nlink = cpu_to_le32(inode->i_nlink); - di->i_atime = cpu_to_le32(inode->i_atime.tv_sec); - di->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec); - di->i_ctime = cpu_to_le32(inode_get_ctime(inode).tv_sec); + di->i_atime = cpu_to_le32(inode_get_atime_sec(inode)); + di->i_mtime = cpu_to_le32(inode_get_mtime_sec(inode)); + di->i_ctime = cpu_to_le32(inode_get_ctime_sec(inode)); i_sblock = BFS_I(inode)->i_sblock; di->i_sblock = cpu_to_le32(i_sblock); di->i_eblock = cpu_to_le32(BFS_I(inode)->i_eblock); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 43b2a2851ba3..206812ce544a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -345,10 +345,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ + SET_PERSONALITY(exec_params.hdr); if (elf_check_fdpic(&exec_params.hdr)) - set_personality(PER_LINUX_FDPIC); - else - set_personality(PER_LINUX); + current->personality |= PER_LINUX_FDPIC; if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index e0108d17b085..5d2be9b0a0a5 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -547,7 +547,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } return inode; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b7d54efb4728..a4a809efc92f 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3196,12 +3196,14 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, * We still need to do a tree search to find out the parents. This is for * TREE_BLOCK_REF backref (keyed or inlined). * + * @trans: Transaction handle. * @ref_key: The same as @ref_key in handle_direct_tree_backref() * @tree_key: The first key of this tree block. * @path: A clean (released) path, to avoid allocating path every time * the function get called. */ -static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, +static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_key *ref_key, struct btrfs_key *tree_key, @@ -3315,7 +3317,7 @@ static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, * If we know the block isn't shared we can avoid * checking its backrefs. */ - if (btrfs_block_can_be_shared(root, eb)) + if (btrfs_block_can_be_shared(trans, root, eb)) upper->checked = 0; else upper->checked = 1; @@ -3363,11 +3365,13 @@ out: * links aren't yet bi-directional. Needs to finish such links. * Use btrfs_backref_finish_upper_links() to finish such linkage. * + * @trans: Transaction handle. * @path: Released path for indirect tree backref lookup * @iter: Released backref iter for extent tree search * @node_key: The first key of the tree block */ -int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, +int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, @@ -3467,8 +3471,8 @@ int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, * offset means the root objectid. We need to search * the tree to get its parent bytenr. */ - ret = handle_indirect_tree_backref(cache, path, &key, node_key, - cur); + ret = handle_indirect_tree_backref(trans, cache, path, + &key, node_key, cur); if (ret < 0) goto out; } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 1616e3e3f1e4..71d535e03dca 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -540,7 +540,8 @@ static inline void btrfs_backref_panic(struct btrfs_fs_info *fs_info, bytenr); } -int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, +int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a4cb4b642987..617d4827eec2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -367,7 +367,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, /* * check if the tree block can be shared by multiple trees */ -int btrfs_block_can_be_shared(struct btrfs_root *root, +int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf) { /* @@ -376,11 +377,21 @@ int btrfs_block_can_be_shared(struct btrfs_root *root, * not allocated by tree relocation, we know the block is not shared. */ if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && - buf != root->node && buf != root->commit_root && + buf != root->node && (btrfs_header_generation(buf) <= btrfs_root_last_snapshot(&root->root_item) || - btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) - return 1; + btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) { + if (buf != root->commit_root) + return 1; + /* + * An extent buffer that used to be the commit root may still be + * shared because the tree height may have increased and it + * became a child of a higher level root. This can happen when + * snapshotting a subvolume created in the current transaction. + */ + if (btrfs_header_generation(buf) == trans->transid) + return 1; + } return 0; } @@ -415,7 +426,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, * are only allowed for blocks use full backrefs. */ - if (btrfs_block_can_be_shared(root, buf)) { + if (btrfs_block_can_be_shared(trans, root, buf)) { ret = btrfs_lookup_extent_info(trans, fs_info, buf->start, btrfs_header_level(buf), 1, &refs, &flags); @@ -682,18 +693,30 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans, u64 search_start; int ret; - if (test_bit(BTRFS_ROOT_DELETING, &root->state)) - btrfs_err(fs_info, - "COW'ing blocks on a fs root that's being dropped"); - - if (trans->transaction != fs_info->running_transaction) - WARN(1, KERN_CRIT "trans %llu running %llu\n", - trans->transid, - fs_info->running_transaction->transid); + if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { + btrfs_abort_transaction(trans, -EUCLEAN); + btrfs_crit(fs_info, + "attempt to COW block %llu on root %llu that is being deleted", + buf->start, btrfs_root_id(root)); + return -EUCLEAN; + } - if (trans->transid != fs_info->generation) - WARN(1, KERN_CRIT "trans %llu running %llu\n", - trans->transid, fs_info->generation); + /* + * COWing must happen through a running transaction, which always + * matches the current fs generation (it's a transaction with a state + * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs + * into error state to prevent the commit of any transaction. + */ + if (unlikely(trans->transaction != fs_info->running_transaction || + trans->transid != fs_info->generation)) { + btrfs_abort_transaction(trans, -EUCLEAN); + btrfs_crit(fs_info, +"unexpected transaction when attempting to COW block %llu on root %llu, transaction %llu running transaction %llu fs generation %llu", + buf->start, btrfs_root_id(root), trans->transid, + fs_info->running_transaction->transid, + fs_info->generation); + return -EUCLEAN; + } if (!should_cow_block(trans, root, buf)) { *cow_ret = buf; @@ -805,8 +828,22 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, int progress_passed = 0; struct btrfs_disk_key disk_key; - WARN_ON(trans->transaction != fs_info->running_transaction); - WARN_ON(trans->transid != fs_info->generation); + /* + * COWing must happen through a running transaction, which always + * matches the current fs generation (it's a transaction with a state + * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs + * into error state to prevent the commit of any transaction. + */ + if (unlikely(trans->transaction != fs_info->running_transaction || + trans->transid != fs_info->generation)) { + btrfs_abort_transaction(trans, -EUCLEAN); + btrfs_crit(fs_info, +"unexpected transaction when attempting to reallocate parent %llu for root %llu, transaction %llu running transaction %llu fs generation %llu", + parent->start, btrfs_root_id(root), trans->transid, + fs_info->running_transaction->transid, + fs_info->generation); + return -EUCLEAN; + } parent_nritems = btrfs_header_nritems(parent); blocksize = fs_info->nodesize; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9419f4e37a58..ff40acd63a37 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -540,7 +540,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer **cow_ret, u64 new_root_objectid); -int btrfs_block_can_be_shared(struct btrfs_root *root, +int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf); int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index caf0bbd028d1..c401908eb468 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -313,7 +313,7 @@ static struct btrfs_delayed_item *btrfs_alloc_delayed_item(u16 data_len, { struct btrfs_delayed_item *item; - item = kmalloc(sizeof(*item) + data_len, GFP_NOFS); + item = kmalloc(struct_size(item, data, data_len), GFP_NOFS); if (item) { item->data_len = data_len; item->type = type; @@ -1834,19 +1834,19 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, btrfs_set_stack_inode_block_group(inode_item, 0); btrfs_set_stack_timespec_sec(&inode_item->atime, - inode->i_atime.tv_sec); + inode_get_atime_sec(inode)); btrfs_set_stack_timespec_nsec(&inode_item->atime, - inode->i_atime.tv_nsec); + inode_get_atime_nsec(inode)); btrfs_set_stack_timespec_sec(&inode_item->mtime, - inode->i_mtime.tv_sec); + inode_get_mtime_sec(inode)); btrfs_set_stack_timespec_nsec(&inode_item->mtime, - inode->i_mtime.tv_nsec); + inode_get_mtime_nsec(inode)); btrfs_set_stack_timespec_sec(&inode_item->ctime, - inode_get_ctime(inode).tv_sec); + inode_get_ctime_sec(inode)); btrfs_set_stack_timespec_nsec(&inode_item->ctime, - inode_get_ctime(inode).tv_nsec); + inode_get_ctime_nsec(inode)); btrfs_set_stack_timespec_sec(&inode_item->otime, BTRFS_I(inode)->i_otime.tv_sec); @@ -1891,11 +1891,11 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) btrfs_inode_split_flags(btrfs_stack_inode_flags(inode_item), &BTRFS_I(inode)->flags, &BTRFS_I(inode)->ro_flags); - inode->i_atime.tv_sec = btrfs_stack_timespec_sec(&inode_item->atime); - inode->i_atime.tv_nsec = btrfs_stack_timespec_nsec(&inode_item->atime); + inode_set_atime(inode, btrfs_stack_timespec_sec(&inode_item->atime), + btrfs_stack_timespec_nsec(&inode_item->atime)); - inode->i_mtime.tv_sec = btrfs_stack_timespec_sec(&inode_item->mtime); - inode->i_mtime.tv_nsec = btrfs_stack_timespec_nsec(&inode_item->mtime); + inode_set_mtime(inode, btrfs_stack_timespec_sec(&inode_item->mtime), + btrfs_stack_timespec_nsec(&inode_item->mtime)); inode_set_ctime(inode, btrfs_stack_timespec_sec(&inode_item->ctime), btrfs_stack_timespec_nsec(&inode_item->ctime)); diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index dc1085b2a397..1da213197f55 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -95,7 +95,7 @@ struct btrfs_delayed_item { bool logged; /* The maximum leaf size is 64K, so u16 is more than enough. */ u16 data_len; - char data[]; + char data[] __counted_by(data_len); }; static inline void btrfs_init_delayed_root( diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 6a13cf00218b..9fe4ccca50a0 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -103,24 +103,17 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans) * Transfer bytes to our delayed refs rsv. * * @fs_info: the filesystem - * @src: source block rsv to transfer from * @num_bytes: number of bytes to transfer * - * This transfers up to the num_bytes amount from the src rsv to the + * This transfers up to the num_bytes amount, previously reserved, to the * delayed_refs_rsv. Any extra bytes are returned to the space info. */ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *src, u64 num_bytes) { struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv; u64 to_free = 0; - spin_lock(&src->lock); - src->reserved -= num_bytes; - src->size -= num_bytes; - spin_unlock(&src->lock); - spin_lock(&delayed_refs_rsv->lock); if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) { u64 delta = delayed_refs_rsv->size - @@ -163,6 +156,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv; u64 limit = btrfs_calc_delayed_ref_bytes(fs_info, 1); u64 num_bytes = 0; + u64 refilled_bytes; + u64 to_free; int ret = -ENOSPC; spin_lock(&block_rsv->lock); @@ -178,9 +173,38 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, num_bytes, flush); if (ret) return ret; - btrfs_block_rsv_add_bytes(block_rsv, num_bytes, false); - trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", - 0, num_bytes, 1); + + /* + * We may have raced with someone else, so check again if we the block + * reserve is still not full and release any excess space. + */ + spin_lock(&block_rsv->lock); + if (block_rsv->reserved < block_rsv->size) { + u64 needed = block_rsv->size - block_rsv->reserved; + + if (num_bytes >= needed) { + block_rsv->reserved += needed; + block_rsv->full = true; + to_free = num_bytes - needed; + refilled_bytes = needed; + } else { + block_rsv->reserved += num_bytes; + to_free = 0; + refilled_bytes = num_bytes; + } + } else { + to_free = num_bytes; + refilled_bytes = 0; + } + spin_unlock(&block_rsv->lock); + + if (to_free > 0) + btrfs_space_info_free_bytes_may_use(fs_info, block_rsv->space_info, + to_free); + + if (refilled_bytes > 0) + trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv", 0, + refilled_bytes, 1); return 0; } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index b8e14b0ba5f1..fd9bf2b709c0 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -407,7 +407,6 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans); int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info, - struct btrfs_block_rsv *src, u64 num_bytes); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index fff22ed55c42..6b5b6cec13c4 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -247,6 +247,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; + struct bdev_handle *bdev_handle; struct block_device *bdev; u64 devid = BTRFS_DEV_REPLACE_DEVID; int ret = 0; @@ -257,12 +258,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return -EINVAL; } - bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, - fs_info->bdev_holder, NULL); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); + if (IS_ERR(bdev_handle)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); - return PTR_ERR(bdev); + return PTR_ERR(bdev_handle); } + bdev = bdev_handle->bdev; if (!btrfs_check_device_zone_type(fs_info, bdev)) { btrfs_err(fs_info, @@ -313,9 +315,9 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, device->commit_bytes_used = device->bytes_used; device->fs_info = fs_info; device->bdev = bdev; + device->bdev_handle = bdev_handle; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; @@ -334,7 +336,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return 0; error: - blkdev_put(bdev, fs_info->bdev_holder); + bdev_release(bdev_handle); return ret; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f356f08b55cb..fc313fce5bbd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1514,15 +1514,14 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_release_path(path); /* now insert the actual backref */ - if (owner < BTRFS_FIRST_FREE_OBJECTID) { - BUG_ON(refs_to_add != 1); + if (owner < BTRFS_FIRST_FREE_OBJECTID) ret = insert_tree_block_ref(trans, path, bytenr, parent, root_objectid); - } else { + else ret = insert_extent_data_ref(trans, path, bytenr, parent, root_objectid, owner, offset, refs_to_add); - } + if (ret) btrfs_abort_transaction(trans, ret); out: @@ -1656,7 +1655,10 @@ again: goto again; } } else { - err = -EIO; + err = -EUCLEAN; + btrfs_err(fs_info, + "missing extent item for extent %llu num_bytes %llu level %d", + head->bytenr, head->num_bytes, extent_op->level); goto out; } } @@ -1699,12 +1701,12 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent = ref->parent; ref_root = ref->root; - if (node->ref_mod != 1) { + if (unlikely(node->ref_mod != 1)) { btrfs_err(trans->fs_info, - "btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu", + "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu", node->bytenr, node->ref_mod, node->action, ref_root, parent); - return -EIO; + return -EUCLEAN; } if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { BUG_ON(!extent_op || !extent_op->update_flags); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6954ae763b86..caccd0376342 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3995,8 +3995,14 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, char *dst = (char *)dstv; unsigned long i = get_eb_page_index(start); - if (check_eb_range(eb, start, len)) + if (check_eb_range(eb, start, len)) { + /* + * Invalid range hit, reset the memory, so callers won't get + * some random garbage for their uninitialzed memory. + */ + memset(dstv, 0, len); return; + } offset = get_eb_offset_in_page(eb, start); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 361535c71c0f..278a4ea651e1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1108,17 +1108,18 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode) static void update_time_for_write(struct inode *inode) { - struct timespec64 now, ctime; + struct timespec64 now, ts; if (IS_NOCMTIME(inode)) return; now = current_time(inode); - if (!timespec64_equal(&inode->i_mtime, &now)) - inode->i_mtime = now; + ts = inode_get_mtime(inode); + if (!timespec64_equal(&ts, &now)) + inode_set_mtime_to_ts(inode, now); - ctime = inode_get_ctime(inode); - if (!timespec64_equal(&ctime, &now)) + ts = inode_get_ctime(inode); + if (!timespec64_equal(&ts, &now)) inode_set_ctime_to_ts(inode, now); if (IS_I_VERSION(inode)) @@ -2473,7 +2474,8 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode, inode_inc_iversion(&inode->vfs_inode); if (!extent_info || extent_info->update_times) - inode->vfs_inode.i_mtime = inode_set_ctime_current(&inode->vfs_inode); + inode_set_mtime_to_ts(&inode->vfs_inode, + inode_set_ctime_current(&inode->vfs_inode)); ret = btrfs_update_inode(trans, root, inode); if (ret) @@ -2714,7 +2716,7 @@ static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) ASSERT(trans != NULL); inode_inc_iversion(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); updated_inode = true; btrfs_end_transaction(trans); @@ -2734,7 +2736,7 @@ out_only_mutex: struct timespec64 now = inode_set_ctime_current(inode); inode_inc_iversion(inode); - inode->i_mtime = now; + inode_set_mtime_to_ts(inode, now); trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7814b9d654ce..6e3ce1aecb6e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3754,11 +3754,11 @@ static int btrfs_read_locked_inode(struct inode *inode, btrfs_inode_set_file_extent_range(BTRFS_I(inode), 0, round_up(i_size_read(inode), fs_info->sectorsize)); - inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime); - inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime); + inode_set_atime(inode, btrfs_timespec_sec(leaf, &inode_item->atime), + btrfs_timespec_nsec(leaf, &inode_item->atime)); - inode->i_mtime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->mtime); - inode->i_mtime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->mtime); + inode_set_mtime(inode, btrfs_timespec_sec(leaf, &inode_item->mtime), + btrfs_timespec_nsec(leaf, &inode_item->mtime)); inode_set_ctime(inode, btrfs_timespec_sec(leaf, &inode_item->ctime), btrfs_timespec_nsec(leaf, &inode_item->ctime)); @@ -3922,19 +3922,19 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_token_inode_nlink(&token, item, inode->i_nlink); btrfs_set_token_timespec_sec(&token, &item->atime, - inode->i_atime.tv_sec); + inode_get_atime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->atime, - inode->i_atime.tv_nsec); + inode_get_atime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->mtime, - inode->i_mtime.tv_sec); + inode_get_mtime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->mtime, - inode->i_mtime.tv_nsec); + inode_get_mtime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->ctime, - inode_get_ctime(inode).tv_sec); + inode_get_ctime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->ctime, - inode_get_ctime(inode).tv_nsec); + inode_get_ctime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->otime, BTRFS_I(inode)->i_otime.tv_sec); @@ -4132,8 +4132,7 @@ err: btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2); inode_inc_iversion(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); - inode_set_ctime_current(&inode->vfs_inode); - dir->vfs_inode.i_mtime = inode_set_ctime_current(&dir->vfs_inode); + inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); ret = btrfs_update_inode(trans, root, dir); out: return ret; @@ -4306,7 +4305,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, btrfs_i_size_write(dir, dir->vfs_inode.i_size - fname.disk_name.len * 2); inode_inc_iversion(&dir->vfs_inode); - dir->vfs_inode.i_mtime = inode_set_ctime_current(&dir->vfs_inode); + inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); ret = btrfs_update_inode_fallback(trans, root, dir); if (ret) btrfs_abort_transaction(trans, ret); @@ -4956,7 +4955,8 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) if (newsize != oldsize) { inode_inc_iversion(inode); if (!(mask & (ATTR_CTIME | ATTR_MTIME))) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); } } @@ -5600,9 +5600,9 @@ static struct inode *new_simple_dir(struct inode *dir, inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &simple_dir_operations; inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO; - inode->i_mtime = inode_set_ctime_current(inode); - inode->i_atime = dir->i_atime; - BTRFS_I(inode)->i_otime = inode->i_mtime; + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + inode_set_atime_to_ts(inode, inode_get_atime(dir)); + BTRFS_I(inode)->i_otime = inode_get_mtime(inode); inode->i_uid = dir->i_uid; inode->i_gid = dir->i_gid; @@ -6277,9 +6277,8 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, goto discard; } - inode->i_mtime = inode_set_ctime_current(inode); - inode->i_atime = inode->i_mtime; - BTRFS_I(inode)->i_otime = inode->i_mtime; + simple_inode_init_ts(inode); + BTRFS_I(inode)->i_otime = inode_get_mtime(inode); /* * We're going to fill the inode item now, so at this point the inode @@ -6444,8 +6443,8 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, * values (the ones it had when the fsync was done). */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags)) - parent_inode->vfs_inode.i_mtime = - inode_set_ctime_current(&parent_inode->vfs_inode); + inode_set_mtime_to_ts(&parent_inode->vfs_inode, + inode_set_ctime_current(&parent_inode->vfs_inode)); ret = btrfs_update_inode(trans, root, parent_inode); if (ret) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 75ab766fe156..108edf8ffedf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2676,8 +2676,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args_v2 *vol_args; - struct block_device *bdev = NULL; - void *holder; + struct bdev_handle *bdev_handle = NULL; int ret; bool cancel = false; @@ -2714,7 +2713,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) goto err_drop; /* Exclusive operation is now claimed */ - ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); + ret = btrfs_rm_device(fs_info, &args, &bdev_handle); btrfs_exclop_finish(fs_info); @@ -2728,8 +2727,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) } err_drop: mnt_drop_write_file(file); - if (bdev) - blkdev_put(bdev, holder); + if (bdev_handle) + bdev_release(bdev_handle); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -2742,8 +2741,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args *vol_args; - struct block_device *bdev = NULL; - void *holder; + struct bdev_handle *bdev_handle = NULL; int ret; bool cancel = false; @@ -2770,15 +2768,15 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE, cancel); if (ret == 0) { - ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); + ret = btrfs_rm_device(fs_info, &args, &bdev_handle); if (!ret) btrfs_info(fs_info, "disk deleted %s", vol_args->name); btrfs_exclop_finish(fs_info); } mnt_drop_write_file(file); - if (bdev) - blkdev_put(bdev, holder); + if (bdev_handle) + bdev_release(bdev_handle); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -2978,7 +2976,7 @@ static void get_block_group_info(struct list_head *groups_list, static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, void __user *arg) { - struct btrfs_ioctl_space_args space_args; + struct btrfs_ioctl_space_args space_args = { 0 }; struct btrfs_ioctl_space_info space; struct btrfs_ioctl_space_info *dest; struct btrfs_ioctl_space_info *dest_orig; @@ -4338,7 +4336,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat if (compat) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_send_args_32 args32; + struct btrfs_ioctl_send_args_32 args32 = { 0 }; ret = copy_from_user(&args32, argp, sizeof(args32)); if (ret) diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 65d2bd6910f2..13ecb4f85941 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -30,7 +30,7 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans, inode_inc_iversion(inode); if (!no_time_update) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); } /* * We round up to the block size at eof when determining which diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 9951a0caf5bb..c6d4bb8cbe29 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -466,6 +466,7 @@ static bool handle_useless_nodes(struct reloc_control *rc, * cached. */ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( + struct btrfs_trans_handle *trans, struct reloc_control *rc, struct btrfs_key *node_key, int level, u64 bytenr) { @@ -499,8 +500,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( /* Breadth-first search to build backref cache */ do { - ret = btrfs_backref_add_tree_node(cache, path, iter, node_key, - cur); + ret = btrfs_backref_add_tree_node(trans, cache, path, iter, + node_key, cur); if (ret < 0) { err = ret; goto out; @@ -2803,7 +2804,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Do tree relocation */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { - node = build_backref_tree(rc, &block->key, + node = build_backref_tree(trans, rc, &block->key, block->level, block->bytenr); if (IS_ERR(node)) { err = PTR_ERR(node); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cffdd6f7f8e8..1a093ec0f7e3 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2117,7 +2117,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * calculated f_bavail. */ if (!mixed && block_rsv->space_info->full && - total_free_meta - thresh < block_rsv->size) + (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size)) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 0bf42dccb041..38a2775c5c7b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -631,14 +631,14 @@ start_transaction(struct btrfs_root *root, unsigned int num_items, reloc_reserved = true; } - ret = btrfs_block_rsv_add(fs_info, rsv, num_bytes, flush); + ret = btrfs_reserve_metadata_bytes(fs_info, rsv, num_bytes, flush); if (ret) goto reserve_fail; if (delayed_refs_bytes) { - btrfs_migrate_to_delayed_refs_rsv(fs_info, rsv, - delayed_refs_bytes); + btrfs_migrate_to_delayed_refs_rsv(fs_info, delayed_refs_bytes); num_bytes -= delayed_refs_bytes; } + btrfs_block_rsv_add_bytes(rsv, num_bytes, true); if (rsv->space_info->force_alloc) do_chunk_alloc = true; @@ -1860,7 +1860,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size + fname.disk_name.len * 2); - parent_inode->i_mtime = inode_set_ctime_current(parent_inode); + inode_set_mtime_to_ts(parent_inode, + inode_set_ctime_current(parent_inode)); ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode)); if (ret) { btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6b309f8a99a8..93869cda6af9 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -219,8 +219,8 @@ do { \ (errno))) { \ /* Stack trace printed. */ \ } else { \ - btrfs_debug((trans)->fs_info, \ - "Transaction aborted (error %d)", \ + btrfs_err((trans)->fs_info, \ + "Transaction aborted (error %d)", \ (errno)); \ } \ } \ diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d1e46b839519..bfee3ebb422f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4138,19 +4138,19 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_token_inode_nlink(&token, item, inode->i_nlink); btrfs_set_token_timespec_sec(&token, &item->atime, - inode->i_atime.tv_sec); + inode_get_atime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->atime, - inode->i_atime.tv_nsec); + inode_get_atime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->mtime, - inode->i_mtime.tv_sec); + inode_get_mtime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->mtime, - inode->i_mtime.tv_nsec); + inode_get_mtime_nsec(inode)); btrfs_set_token_timespec_sec(&token, &item->ctime, - inode_get_ctime(inode).tv_sec); + inode_get_ctime_sec(inode)); btrfs_set_token_timespec_nsec(&token, &item->ctime, - inode_get_ctime(inode).tv_nsec); + inode_get_ctime_nsec(inode)); /* * We do not need to set the nbytes field, in fact during a fast fsync @@ -4722,7 +4722,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int slot; int ins_nr = 0; - int start_slot; + int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9621455edebc..1f38affa4d9c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -511,37 +511,39 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( static int btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, - int flush, struct block_device **bdev, + int flush, struct bdev_handle **bdev_handle, struct btrfs_super_block **disk_super) { + struct block_device *bdev; int ret; - *bdev = blkdev_get_by_path(device_path, flags, holder, NULL); + *bdev_handle = bdev_open_by_path(device_path, flags, holder, NULL); - if (IS_ERR(*bdev)) { - ret = PTR_ERR(*bdev); + if (IS_ERR(*bdev_handle)) { + ret = PTR_ERR(*bdev_handle); goto error; } + bdev = (*bdev_handle)->bdev; if (flush) - sync_blockdev(*bdev); - ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE); + sync_blockdev(bdev); + ret = set_blocksize(bdev, BTRFS_BDEV_BLOCKSIZE); if (ret) { - blkdev_put(*bdev, holder); + bdev_release(*bdev_handle); goto error; } - invalidate_bdev(*bdev); - *disk_super = btrfs_read_dev_super(*bdev); + invalidate_bdev(bdev); + *disk_super = btrfs_read_dev_super(bdev); if (IS_ERR(*disk_super)) { ret = PTR_ERR(*disk_super); - blkdev_put(*bdev, holder); + bdev_release(*bdev_handle); goto error; } return 0; error: - *bdev = NULL; + *bdev_handle = NULL; return ret; } @@ -613,7 +615,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, struct btrfs_device *device, blk_mode_t flags, void *holder) { - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct btrfs_super_block *disk_super; u64 devid; int ret; @@ -624,7 +626,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, return -EINVAL; ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1, - &bdev, &disk_super); + &bdev_handle, &disk_super); if (ret) return ret; @@ -648,21 +650,21 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); fs_devices->seeding = true; } else { - if (bdev_read_only(bdev)) + if (bdev_read_only(bdev_handle->bdev)) clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); else set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); } - if (!bdev_nonrot(bdev)) + if (!bdev_nonrot(bdev_handle->bdev)) fs_devices->rotating = true; - if (bdev_max_discard_sectors(bdev)) + if (bdev_max_discard_sectors(bdev_handle->bdev)) fs_devices->discardable = true; - device->bdev = bdev; + device->bdev_handle = bdev_handle; + device->bdev = bdev_handle->bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); - device->holder = holder; fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && @@ -676,7 +678,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, error_free_page: btrfs_release_disk_super(disk_super); - blkdev_put(bdev, holder); + bdev_release(bdev_handle); return -EINVAL; } @@ -1068,9 +1070,10 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (device->devid == BTRFS_DEV_REPLACE_DEVID) continue; - if (device->bdev) { - blkdev_put(device->bdev, device->holder); + if (device->bdev_handle) { + bdev_release(device->bdev_handle); device->bdev = NULL; + device->bdev_handle = NULL; fs_devices->open_devices--; } if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { @@ -1115,7 +1118,7 @@ static void btrfs_close_bdev(struct btrfs_device *device) invalidate_bdev(device->bdev); } - blkdev_put(device->bdev, device->holder); + bdev_release(device->bdev_handle); } static void btrfs_close_one_device(struct btrfs_device *device) @@ -1363,7 +1366,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) struct btrfs_super_block *disk_super; bool new_device_added = false; struct btrfs_device *device = NULL; - struct block_device *bdev; + struct bdev_handle *bdev_handle; u64 bytenr, bytenr_orig; int ret; @@ -1386,18 +1389,19 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) * values temporarily, as the device paths of the fsid are the only * required information for assembling the volume. */ - bdev = blkdev_get_by_path(path, flags, NULL, NULL); - if (IS_ERR(bdev)) - return ERR_CAST(bdev); + bdev_handle = bdev_open_by_path(path, flags, NULL, NULL); + if (IS_ERR(bdev_handle)) + return ERR_CAST(bdev_handle); bytenr_orig = btrfs_sb_offset(0); - ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr); + ret = btrfs_sb_log_location_bdev(bdev_handle->bdev, 0, READ, &bytenr); if (ret) { device = ERR_PTR(ret); goto error_bdev_put; } - disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig); + disk_super = btrfs_read_disk_super(bdev_handle->bdev, bytenr, + bytenr_orig); if (IS_ERR(disk_super)) { device = ERR_CAST(disk_super); goto error_bdev_put; @@ -1410,7 +1414,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) btrfs_release_disk_super(disk_super); error_bdev_put: - blkdev_put(bdev, NULL); + bdev_release(bdev_handle); return device; } @@ -1594,7 +1598,7 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 search_start; u64 hole_size; u64 max_hole_start; - u64 max_hole_size; + u64 max_hole_size = 0; u64 extent_end; u64 search_end = device->total_bytes; int ret; @@ -1602,17 +1606,16 @@ static int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, struct extent_buffer *l; search_start = dev_extent_search_start(device); + max_hole_start = search_start; WARN_ON(device->zone_info && !IS_ALIGNED(num_bytes, device->zone_info->zone_size)); path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - max_hole_start = search_start; - max_hole_size = 0; - + if (!path) { + ret = -ENOMEM; + goto out; + } again: if (search_start >= search_end || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { @@ -2088,7 +2091,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, void **holder) + struct bdev_handle **bdev_handle) { struct btrfs_trans_handle *trans; struct btrfs_device *device; @@ -2197,7 +2200,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, btrfs_assign_next_active_device(device, NULL); - if (device->bdev) { + if (device->bdev_handle) { cur_devices->open_devices--; /* remove sysfs entry */ btrfs_sysfs_remove_device(device); @@ -2213,9 +2216,9 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, * free the device. * * We cannot call btrfs_close_bdev() here because we're holding the sb - * write lock, and blkdev_put() will pull in the ->open_mutex on the - * block device and it's dependencies. Instead just flush the device - * and let the caller do the final blkdev_put. + * write lock, and bdev_release() will pull in the ->open_mutex on + * the block device and it's dependencies. Instead just flush the + * device and let the caller do the final bdev_release. */ if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { btrfs_scratch_superblocks(fs_info, device->bdev, @@ -2226,8 +2229,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, } } - *bdev = device->bdev; - *holder = device->holder; + *bdev_handle = device->bdev_handle; synchronize_rcu(); btrfs_free_device(device); @@ -2364,7 +2366,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, const char *path) { struct btrfs_super_block *disk_super; - struct block_device *bdev; + struct bdev_handle *bdev_handle; int ret; if (!path || !path[0]) @@ -2382,7 +2384,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, } ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0, - &bdev, &disk_super); + &bdev_handle, &disk_super); if (ret) { btrfs_put_dev_args_from_path(args); return ret; @@ -2395,7 +2397,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, else memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE); btrfs_release_disk_super(disk_super); - blkdev_put(bdev, NULL); + bdev_release(bdev_handle); return 0; } @@ -2615,7 +2617,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path struct btrfs_root *root = fs_info->dev_root; struct btrfs_trans_handle *trans; struct btrfs_device *device; - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct super_block *sb = fs_info->sb; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_fs_devices *seed_devices = NULL; @@ -2628,12 +2630,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (sb_rdonly(sb) && !fs_devices->seeding) return -EROFS; - bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, - fs_info->bdev_holder, NULL); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); + bdev_handle = bdev_open_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); + if (IS_ERR(bdev_handle)) + return PTR_ERR(bdev_handle); - if (!btrfs_check_device_zone_type(fs_info, bdev)) { + if (!btrfs_check_device_zone_type(fs_info, bdev_handle->bdev)) { ret = -EINVAL; goto error; } @@ -2645,11 +2647,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path locked = true; } - sync_blockdev(bdev); + sync_blockdev(bdev_handle->bdev); rcu_read_lock(); list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) { - if (device->bdev == bdev) { + if (device->bdev == bdev_handle->bdev) { ret = -EEXIST; rcu_read_unlock(); goto error; @@ -2665,7 +2667,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path } device->fs_info = fs_info; - device->bdev = bdev; + device->bdev_handle = bdev_handle; + device->bdev = bdev_handle->bdev; ret = lookup_bdev(device_path, &device->devt); if (ret) goto error_free_device; @@ -2686,12 +2689,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; device->total_bytes = - round_down(bdev_nr_bytes(bdev), fs_info->sectorsize); + round_down(bdev_nr_bytes(device->bdev), fs_info->sectorsize); device->disk_total_bytes = device->total_bytes; device->commit_total_bytes = device->total_bytes; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); @@ -2727,7 +2729,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path atomic64_add(device->total_bytes, &fs_info->free_chunk_space); - if (!bdev_nonrot(bdev)) + if (!bdev_nonrot(device->bdev)) fs_devices->rotating = true; orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy); @@ -2849,7 +2851,7 @@ error_free_zone: error_free_device: btrfs_free_device(device); error: - blkdev_put(bdev, fs_info->bdev_holder); + bdev_release(bdev_handle); if (locked) { mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); @@ -5110,7 +5112,7 @@ static void init_alloc_chunk_ctl_policy_regular( ASSERT(space_info); ctl->max_chunk_size = READ_ONCE(space_info->chunk_size); - ctl->max_stripe_size = ctl->max_chunk_size; + ctl->max_stripe_size = min_t(u64, ctl->max_chunk_size, SZ_1G); if (ctl->type & BTRFS_BLOCK_GROUP_SYSTEM) ctl->devs_max = min_t(int, ctl->devs_max, BTRFS_MAX_DEVS_SYS_CHUNK); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 2128a032c3b7..1702cb7cac00 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -90,13 +90,11 @@ struct btrfs_device { u64 generation; + struct bdev_handle *bdev_handle; struct block_device *bdev; struct btrfs_zoned_device_info *zone_info; - /* block device holder for blkdev_get/put */ - void *holder; - /* * Device's major-minor number. Must be set even if the device is not * opened (bdev == NULL), unless the device is missing. @@ -629,7 +627,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args); int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, void **holder); + struct bdev_handle **bdev_handle); void __exit btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 96828a13dd43..a9f8b173a99f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -442,7 +442,7 @@ static const struct xattr_handler btrfs_btrfs_xattr_handler = { .set = btrfs_xattr_handler_set_prop, }; -const struct xattr_handler *btrfs_xattr_handlers[] = { +const struct xattr_handler * const btrfs_xattr_handlers[] = { &btrfs_security_xattr_handler, &btrfs_trusted_xattr_handler, &btrfs_user_xattr_handler, diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 1cd3fc0a8f17..118118ca3e1d 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -8,7 +8,7 @@ #include <linux/xattr.h> -extern const struct xattr_handler *btrfs_xattr_handlers[]; +extern const struct xattr_handler * const btrfs_xattr_handlers[]; int btrfs_getxattr(struct inode *inode, const char *name, void *buffer, size_t size); diff --git a/fs/buffer.c b/fs/buffer.c index a6785cd07081..12e9a71c693d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2058,8 +2058,17 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || - offset >= i_size_read(inode)) + offset >= i_size_read(inode)) { + /* + * This can happen if truncating the block device races + * with the check in the caller as i_size updates on + * block devices aren't synchronized by i_rwsem for + * block devices. + */ + if (S_ISBLK(inode->i_mode)) + return -EIO; set_buffer_new(bh); + } bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index f4863078f7fe..936b9e0b351d 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -750,7 +750,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %llu~%llu (%llu bytes, %sencrypted)\n", page_off, len, wlen, IS_ENCRYPTED(inode) ? "" : "not "); - req->r_mtime = inode->i_mtime; + req->r_mtime = inode_get_mtime(inode); ceph_osdc_start_request(osdc, req); err = ceph_osdc_wait_request(osdc, req); @@ -1327,7 +1327,7 @@ new_request: pages = NULL; } - req->r_mtime = inode->i_mtime; + req->r_mtime = inode_get_mtime(inode); ceph_osdc_start_request(&fsc->client->osdc, req); req = NULL; @@ -1875,7 +1875,7 @@ int ceph_uninline_data(struct file *file) goto out_unlock; } - req->r_mtime = inode->i_mtime; + req->r_mtime = inode_get_mtime(inode); ceph_osdc_start_request(&fsc->client->osdc, req); err = ceph_osdc_wait_request(&fsc->client->osdc, req); ceph_osdc_put_request(req); @@ -1917,7 +1917,7 @@ int ceph_uninline_data(struct file *file) goto out_put_req; } - req->r_mtime = inode->i_mtime; + req->r_mtime = inode_get_mtime(inode); ceph_osdc_start_request(&fsc->client->osdc, req); err = ceph_osdc_wait_request(&fsc->client->osdc, req); @@ -2092,7 +2092,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, 0, false, true); ceph_osdc_start_request(&fsc->client->osdc, rd_req); - wr_req->r_mtime = ci->netfs.inode.i_mtime; + wr_req->r_mtime = inode_get_mtime(&ci->netfs.inode); ceph_osdc_start_request(&fsc->client->osdc, wr_req); err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 14215ec646f7..a104669fcf4c 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1421,8 +1421,8 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, arg->old_xattr_buf = NULL; } - arg->mtime = inode->i_mtime; - arg->atime = inode->i_atime; + arg->mtime = inode_get_mtime(inode); + arg->atime = inode_get_atime(inode); arg->ctime = inode_get_ctime(inode); arg->btime = ci->i_btime; arg->change_attr = inode_peek_iversion_raw(inode); diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index cc63f1e6fdef..e3b1c3fab412 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -250,11 +250,9 @@ static struct inode *parse_longname(const struct inode *parent, if (!dir) { /* This can happen if we're not mounting cephfs on the root */ dir = ceph_get_inode(parent->i_sb, vino, NULL); - if (!dir) - dir = ERR_PTR(-ENOENT); + if (IS_ERR(dir)) + dout("Can't find inode %s (%s)\n", inode_number, name); } - if (IS_ERR(dir)) - dout("Can't find inode %s (%s)\n", inode_number, name); out: kfree(inode_number); @@ -463,7 +461,7 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, out: fscrypt_fname_free_buffer(&_tname); out_inode: - if ((dir != fname->dir) && !IS_ERR(dir)) { + if (dir != fname->dir) { if ((dir->i_state & I_NEW)) discard_new_inode(dir); else diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b1da02f5dbe3..649600d0a7b6 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2489,7 +2489,7 @@ static int ceph_zero_partial_object(struct inode *inode, goto out; } - req->r_mtime = inode->i_mtime; + req->r_mtime = inode_get_mtime(inode); ceph_osdc_start_request(&fsc->client->osdc, req); ret = ceph_osdc_wait_request(&fsc->client->osdc, req); if (ret == -ENOENT) @@ -2969,7 +2969,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, ret = do_splice_direct(src_file, &src_off, dst_file, &dst_off, src_objlen, flags); /* Abort on short copies or on error */ - if (ret < src_objlen) { + if (ret < (long)src_objlen) { dout("Failed partial copy (%zd)\n", ret); goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 800ab7920513..2e2a303b9e64 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -185,9 +185,9 @@ struct inode *ceph_get_snapdir(struct inode *parent) inode->i_mode = parent->i_mode; inode->i_uid = parent->i_uid; inode->i_gid = parent->i_gid; - inode->i_mtime = parent->i_mtime; + inode_set_mtime_to_ts(inode, inode_get_mtime(parent)); inode_set_ctime_to_ts(inode, inode_get_ctime(parent)); - inode->i_atime = parent->i_atime; + inode_set_atime_to_ts(inode, inode_get_atime(parent)); ci->i_rbytes = 0; ci->i_btime = ceph_inode(parent)->i_btime; @@ -769,9 +769,7 @@ int ceph_fill_file_size(struct inode *inode, int issued, ci->i_truncate_seq = truncate_seq; /* the MDS should have revoked these caps */ - WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL | - CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR | + WARN_ON_ONCE(issued & (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_LAZYIO)); /* * If we hold relevant caps, or in the case where we're @@ -837,28 +835,31 @@ void ceph_fill_file_time(struct inode *inode, int issued, /* the MDS did a utimes() */ dout("mtime %lld.%09ld -> %lld.%09ld " "tw %d -> %d\n", - inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, + inode_get_mtime_sec(inode), + inode_get_mtime_nsec(inode), mtime->tv_sec, mtime->tv_nsec, ci->i_time_warp_seq, (int)time_warp_seq); - inode->i_mtime = *mtime; - inode->i_atime = *atime; + inode_set_mtime_to_ts(inode, *mtime); + inode_set_atime_to_ts(inode, *atime); ci->i_time_warp_seq = time_warp_seq; } else if (time_warp_seq == ci->i_time_warp_seq) { + struct timespec64 ts; + /* nobody did utimes(); take the max */ - if (timespec64_compare(mtime, &inode->i_mtime) > 0) { + ts = inode_get_mtime(inode); + if (timespec64_compare(mtime, &ts) > 0) { dout("mtime %lld.%09ld -> %lld.%09ld inc\n", - inode->i_mtime.tv_sec, - inode->i_mtime.tv_nsec, + ts.tv_sec, ts.tv_nsec, mtime->tv_sec, mtime->tv_nsec); - inode->i_mtime = *mtime; + inode_set_mtime_to_ts(inode, *mtime); } - if (timespec64_compare(atime, &inode->i_atime) > 0) { + ts = inode_get_atime(inode); + if (timespec64_compare(atime, &ts) > 0) { dout("atime %lld.%09ld -> %lld.%09ld inc\n", - inode->i_atime.tv_sec, - inode->i_atime.tv_nsec, + ts.tv_sec, ts.tv_nsec, atime->tv_sec, atime->tv_nsec); - inode->i_atime = *atime; + inode_set_atime_to_ts(inode, *atime); } } else if (issued & CEPH_CAP_FILE_EXCL) { /* we did a utimes(); ignore mds values */ @@ -869,8 +870,8 @@ void ceph_fill_file_time(struct inode *inode, int issued, /* we have no write|excl caps; whatever the MDS says is true */ if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) { inode_set_ctime_to_ts(inode, *ctime); - inode->i_mtime = *mtime; - inode->i_atime = *atime; + inode_set_mtime_to_ts(inode, *mtime); + inode_set_atime_to_ts(inode, *atime); ci->i_time_warp_seq = time_warp_seq; } else { warn = 1; @@ -2553,20 +2554,22 @@ retry: } if (ia_valid & ATTR_ATIME) { + struct timespec64 atime = inode_get_atime(inode); + dout("setattr %p atime %lld.%ld -> %lld.%ld\n", inode, - inode->i_atime.tv_sec, inode->i_atime.tv_nsec, + atime.tv_sec, atime.tv_nsec, attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec); if (issued & CEPH_CAP_FILE_EXCL) { ci->i_time_warp_seq++; - inode->i_atime = attr->ia_atime; + inode_set_atime_to_ts(inode, attr->ia_atime); dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_WR) && - timespec64_compare(&inode->i_atime, - &attr->ia_atime) < 0) { - inode->i_atime = attr->ia_atime; + timespec64_compare(&atime, + &attr->ia_atime) < 0) { + inode_set_atime_to_ts(inode, attr->ia_atime); dirtied |= CEPH_CAP_FILE_WR; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || - !timespec64_equal(&inode->i_atime, &attr->ia_atime)) { + !timespec64_equal(&atime, &attr->ia_atime)) { ceph_encode_timespec64(&req->r_args.setattr.atime, &attr->ia_atime); mask |= CEPH_SETATTR_ATIME; @@ -2626,20 +2629,21 @@ retry: } } if (ia_valid & ATTR_MTIME) { + struct timespec64 mtime = inode_get_mtime(inode); + dout("setattr %p mtime %lld.%ld -> %lld.%ld\n", inode, - inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, + mtime.tv_sec, mtime.tv_nsec, attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec); if (issued & CEPH_CAP_FILE_EXCL) { ci->i_time_warp_seq++; - inode->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(inode, attr->ia_mtime); dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_WR) && - timespec64_compare(&inode->i_mtime, - &attr->ia_mtime) < 0) { - inode->i_mtime = attr->ia_mtime; + timespec64_compare(&mtime, &attr->ia_mtime) < 0) { + inode_set_mtime_to_ts(inode, attr->ia_mtime); dirtied |= CEPH_CAP_FILE_WR; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || - !timespec64_equal(&inode->i_mtime, &attr->ia_mtime)) { + !timespec64_equal(&mtime, &attr->ia_mtime)) { ceph_encode_timespec64(&req->r_args.setattr.mtime, &attr->ia_mtime); mask |= CEPH_SETATTR_MTIME; @@ -2653,8 +2657,8 @@ retry: bool only = (ia_valid & (ATTR_SIZE|ATTR_MTIME|ATTR_ATIME| ATTR_MODE|ATTR_UID|ATTR_GID)) == 0; dout("setattr %p ctime %lld.%ld -> %lld.%ld (%s)\n", inode, - inode_get_ctime(inode).tv_sec, - inode_get_ctime(inode).tv_nsec, + inode_get_ctime_sec(inode), + inode_get_ctime_nsec(inode), attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec, only ? "ctime only" : "ignored"); if (only) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 615db141b6c4..de798444bb97 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -861,8 +861,8 @@ int ceph_wait_on_conflict_unlink(struct dentry *dentry) if (!d_same_name(udentry, pdentry, &dname)) goto next; + found = dget_dlock(udentry); spin_unlock(&udentry->d_lock); - found = dget(udentry); break; next: spin_unlock(&udentry->d_lock); @@ -4353,12 +4353,16 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) rec.v2.flock_len = (__force __le32) ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); } else { + struct timespec64 ts; + rec.v1.cap_id = cpu_to_le64(cap->cap_id); rec.v1.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); rec.v1.issued = cpu_to_le32(cap->issued); rec.v1.size = cpu_to_le64(i_size_read(inode)); - ceph_encode_timespec64(&rec.v1.mtime, &inode->i_mtime); - ceph_encode_timespec64(&rec.v1.atime, &inode->i_atime); + ts = inode_get_mtime(inode); + ceph_encode_timespec64(&rec.v1.mtime, &ts); + ts = inode_get_atime(inode); + ceph_encode_timespec64(&rec.v1.atime, &ts); rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); rec.v1.pathbase = cpu_to_le64(pathbase); } diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 813f21add992..6732e1ea97d9 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -658,8 +658,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, BUG_ON(capsnap->writing); capsnap->size = i_size_read(inode); - capsnap->mtime = inode->i_mtime; - capsnap->atime = inode->i_atime; + capsnap->mtime = inode_get_mtime(inode); + capsnap->atime = inode_get_atime(inode); capsnap->ctime = inode_get_ctime(inode); capsnap->btime = ci->i_btime; capsnap->change_attr = inode_peek_iversion_raw(inode); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 51c7f2b14f6f..98844fc8a2f7 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1119,7 +1119,7 @@ ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t); extern ssize_t ceph_listxattr(struct dentry *, char *, size_t); extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci); extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci); -extern const struct xattr_handler *ceph_xattr_handlers[]; +extern const struct xattr_handler * const ceph_xattr_handlers[]; struct ceph_acl_sec_ctx { #ifdef CONFIG_CEPH_FS_POSIX_ACL diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 0deae4a0f5f1..097ce7f74073 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1446,7 +1446,7 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. */ -const struct xattr_handler *ceph_xattr_handlers[] = { +const struct xattr_handler * const ceph_xattr_handlers[] = { &ceph_other_xattr_handler, NULL, }; diff --git a/fs/char_dev.c b/fs/char_dev.c index 950b6919fb87..6ba032442b39 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -350,7 +350,7 @@ static struct kobject *cdev_get(struct cdev *p) struct module *owner = p->owner; struct kobject *kobj; - if (owner && !try_module_get(owner)) + if (!try_module_get(owner)) return NULL; kobj = kobject_get_unless_zero(&p->kobj); if (!kobj) diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index ae023853a98f..1d2dac95f86a 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -123,9 +123,11 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) if (attr->va_size != -1) inode->i_blocks = (attr->va_size + 511) >> 9; if (attr->va_atime.tv_sec != -1) - inode->i_atime = coda_to_timespec64(attr->va_atime); + inode_set_atime_to_ts(inode, + coda_to_timespec64(attr->va_atime)); if (attr->va_mtime.tv_sec != -1) - inode->i_mtime = coda_to_timespec64(attr->va_mtime); + inode_set_mtime_to_ts(inode, + coda_to_timespec64(attr->va_mtime)); if (attr->va_ctime.tv_sec != -1) inode_set_ctime_to_ts(inode, coda_to_timespec64(attr->va_ctime)); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index cb512b10473b..4e552ba7bd43 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -111,7 +111,7 @@ static inline void coda_dir_update_mtime(struct inode *dir) /* optimistically we can also act as if our nose bleeds. The * granularity of the mtime is coarse anyways so we might actually be * right most of the time. Note: we only do this for directories. */ - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); #endif } diff --git a/fs/coda/file.c b/fs/coda/file.c index 42346618b4ed..16acc58311ea 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -84,7 +84,7 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0); coda_inode->i_size = file_inode(host_file)->i_size; coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9; - coda_inode->i_mtime = inode_set_ctime_current(coda_inode); + inode_set_mtime_to_ts(coda_inode, inode_set_ctime_current(coda_inode)); inode_unlock(coda_inode); file_end_write(host_file); diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index fbdcb3582926..dcc22f593e43 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -88,7 +88,7 @@ int configfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, static inline void set_default_inode_attr(struct inode * inode, umode_t mode) { inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) @@ -96,8 +96,8 @@ static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) inode->i_mode = iattr->ia_mode; inode->i_uid = iattr->ia_uid; inode->i_gid = iattr->ia_gid; - inode->i_atime = iattr->ia_atime; - inode->i_mtime = iattr->ia_mtime; + inode_set_atime_to_ts(inode, iattr->ia_atime); + inode_set_mtime_to_ts(inode, iattr->ia_mtime); inode_set_ctime_to_ts(inode, iattr->ia_ctime); } @@ -171,7 +171,7 @@ struct inode *configfs_create(struct dentry *dentry, umode_t mode) return ERR_PTR(-ENOMEM); p_inode = d_inode(dentry->d_parent); - p_inode->i_mtime = inode_set_ctime_current(p_inode); + inode_set_mtime_to_ts(p_inode, inode_set_ctime_current(p_inode)); configfs_set_inode_lock_class(sd, inode); return inode; } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 5ee7d7bbb361..60dbfa0f8805 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -133,8 +133,8 @@ static struct inode *get_cramfs_inode(struct super_block *sb, } /* Struct copy intentional */ - inode->i_mtime = inode->i_atime = inode_set_ctime_to_ts(inode, - zerotime); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, zerotime))); /* inode->i_nlink is left 1 - arguably wrong for directories, but it's the best we can do without reading the directory contents. 1 yields the right result in GNU find, even @@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb) sb->s_mtd = NULL; } else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) { sync_blockdev(sb->s_bdev); - blkdev_put(sb->s_bdev, sb); + bdev_release(sb->s_bdev_handle); } kfree(sbi); } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 83e57e9f9fa0..5d41765e0c77 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -72,7 +72,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb) struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } return inode; } diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 299c295a27a0..c830261aa883 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -338,7 +338,7 @@ static int mknod_ptmx(struct super_block *sb) } inode->i_ino = 2; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); mode = S_IFCHR|opts->ptmxmode; init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2)); @@ -451,7 +451,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent) if (!inode) goto fail; inode->i_ino = 1; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; @@ -560,7 +560,7 @@ struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv) inode->i_ino = index + 3; inode->i_uid = opts->setuid ? opts->uid : current_fsuid(); inode->i_gid = opts->setgid ? opts->gid : current_fsgid(); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); init_special_inode(inode, S_IFCHR|opts->mode, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index)); sprintf(s, "%d", index); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index f2ed0c0266cb..c586c5db18b5 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -702,6 +702,6 @@ int ecryptfs_set_f_namelen(long *namelen, long lower_namelen, int ecryptfs_derive_iv(char *iv, struct ecryptfs_crypt_stat *crypt_stat, loff_t offset); -extern const struct xattr_handler *ecryptfs_xattr_handlers[]; +extern const struct xattr_handler * const ecryptfs_xattr_handlers[]; #endif /* #ifndef ECRYPTFS_KERNEL_H */ diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 992d9c7e64ae..a25dd3d20008 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1210,7 +1210,7 @@ static const struct xattr_handler ecryptfs_xattr_handler = { .set = ecryptfs_xattr_set, }; -const struct xattr_handler *ecryptfs_xattr_handlers[] = { +const struct xattr_handler * const ecryptfs_xattr_handlers[] = { &ecryptfs_xattr_handler, NULL }; diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 59b52718a3a2..7e9961639802 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -51,7 +51,7 @@ static ssize_t efivarfs_file_write(struct file *file, } else { inode_lock(inode); i_size_write(inode, datasize + sizeof(attributes)); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); inode_unlock(inode); } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index db9231f0e77b..76dd3c7295d9 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -25,7 +25,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 3789d22ba501..7844ab24b813 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -103,10 +103,9 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) i_uid_write(inode, (uid_t)be16_to_cpu(efs_inode->di_uid)); i_gid_write(inode, (gid_t)be16_to_cpu(efs_inode->di_gid)); inode->i_size = be32_to_cpu(efs_inode->di_size); - inode->i_atime.tv_sec = be32_to_cpu(efs_inode->di_atime); - inode->i_mtime.tv_sec = be32_to_cpu(efs_inode->di_mtime); + inode_set_atime(inode, be32_to_cpu(efs_inode->di_atime), 0); + inode_set_mtime(inode, be32_to_cpu(efs_inode->di_mtime), 0); inode_set_ctime(inode, be32_to_cpu(efs_inode->di_ctime), 0); - inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = 0; /* this is the number of blocks in the file */ if (inode->i_size == 0) { diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 0c2c99c58b5e..f6a0a1748521 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -222,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - map->m_bdev = dif->bdev; + map->m_bdev = dif->bdev_handle->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; @@ -240,7 +240,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - map->m_bdev = dif->bdev; + map->m_bdev = dif->bdev_handle->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 73091fbe3ea4..dee10d22ada9 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -217,9 +217,12 @@ again: strm->buf.out_size = min_t(u32, outlen, PAGE_SIZE - pageofs); outlen -= strm->buf.out_size; - if (!rq->out[no] && rq->fillgaps) /* deduped */ + if (!rq->out[no] && rq->fillgaps) { /* deduped */ rq->out[no] = erofs_allocpage(pagepool, GFP_KERNEL | __GFP_NOFAIL); + set_page_private(rq->out[no], + Z_EROFS_SHORTLIVED_PAGE); + } if (rq->out[no]) strm->buf.out = kmap(rq->out[no]) + pageofs; pageofs = 0; diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index edc8ec7581b8..b8ad05b4509d 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -175,7 +175,8 @@ static void *erofs_read_inode(struct erofs_buf *buf, vi->chunkbits = sb->s_blocksize_bits + (vi->chunkformat & EROFS_CHUNK_FORMAT_BLKBITS_MASK); } - inode->i_mtime = inode->i_atime = inode_get_ctime(inode); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_get_ctime(inode))); inode->i_flags &= ~S_DAX; if (test_opt(&sbi->opt, DAX_ALWAYS) && S_ISREG(inode->i_mode) && diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 4ff88d0dd980..cf04e21bfda2 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -47,7 +47,7 @@ typedef u32 erofs_blk_t; struct erofs_device_info { char *path; struct erofs_fscache *fscache; - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct dax_device *dax_dev; u64 dax_part_off; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 44a24d573f1f..6fd04781fec5 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -227,7 +227,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_fscache *fscache; struct erofs_deviceslot *dis; - struct block_device *bdev; + struct bdev_handle *bdev_handle; void *ptr; ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP); @@ -235,7 +235,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, return PTR_ERR(ptr); dis = ptr + erofs_blkoff(sb, *pos); - if (!dif->path) { + if (!sbi->devs->flatdev && !dif->path) { if (!dis->tag[0]) { erofs_err(sb, "empty device tag @ pos %llu", *pos); return -EINVAL; @@ -251,13 +251,13 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, return PTR_ERR(fscache); dif->fscache = fscache; } else if (!sbi->devs->flatdev) { - bdev = blkdev_get_by_path(dif->path, BLK_OPEN_READ, sb->s_type, - NULL); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off, - NULL, NULL); + bdev_handle = bdev_open_by_path(dif->path, BLK_OPEN_READ, + sb->s_type, NULL); + if (IS_ERR(bdev_handle)) + return PTR_ERR(bdev_handle); + dif->bdev_handle = bdev_handle; + dif->dax_dev = fs_dax_get_by_bdev(bdev_handle->bdev, + &dif->dax_part_off, NULL, NULL); } dif->blocks = le32_to_cpu(dis->blocks); @@ -806,8 +806,8 @@ static int erofs_release_device_info(int id, void *ptr, void *data) struct erofs_device_info *dif = ptr; fs_put_dax(dif->dax_dev, NULL); - if (dif->bdev) - blkdev_put(dif->bdev, &erofs_fs_type); + if (dif->bdev_handle) + bdev_release(dif->bdev_handle); erofs_fscache_unregister_cookie(dif->fscache); dif->fscache = NULL; kfree(dif->path); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 09d341675e89..b58316b49a43 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -168,7 +168,7 @@ const struct xattr_handler __maybe_unused erofs_xattr_security_handler = { }; #endif -const struct xattr_handler *erofs_xattr_handlers[] = { +const struct xattr_handler * const erofs_xattr_handlers[] = { &erofs_xattr_user_handler, &erofs_xattr_trusted_handler, #ifdef CONFIG_EROFS_FS_SECURITY diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h index f16283cb8c93..b246cd0e135e 100644 --- a/fs/erofs/xattr.h +++ b/fs/erofs/xattr.h @@ -23,7 +23,7 @@ static inline const char *erofs_xattr_prefix(unsigned int idx, { const struct xattr_handler *handler = NULL; - static const struct xattr_handler *xattr_handler_map[] = { + static const struct xattr_handler * const xattr_handler_map[] = { [EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler, #ifdef CONFIG_EROFS_FS_POSIX_ACL [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, @@ -44,7 +44,7 @@ static inline const char *erofs_xattr_prefix(unsigned int idx, return xattr_prefix(handler); } -extern const struct xattr_handler *erofs_xattr_handlers[]; +extern const struct xattr_handler * const erofs_xattr_handlers[]; int erofs_xattr_prefixes_init(struct super_block *sb); void erofs_xattr_prefixes_cleanup(struct super_block *sb); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index f55498e5c23d..f78b614f44dc 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -549,6 +549,7 @@ void __exfat_fs_error(struct super_block *sb, int report, const char *fmt, ...) void exfat_get_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 tz, __le16 time, __le16 date, u8 time_cs); void exfat_truncate_atime(struct timespec64 *ts); +void exfat_truncate_inode_atime(struct inode *inode); void exfat_set_entry_time(struct exfat_sb_info *sbi, struct timespec64 *ts, u8 *tz, __le16 *time, __le16 *date, u8 *time_cs); u16 exfat_calc_chksum16(void *data, int len, u16 chksum, int type); diff --git a/fs/exfat/file.c b/fs/exfat/file.c index 32395ef686a2..30ee2c8d36a5 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -22,7 +22,7 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) if (err) return err; - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); if (!IS_SYNC(inode)) @@ -290,10 +290,9 @@ int exfat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, } if (attr->ia_valid & ATTR_SIZE) - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - setattr_copy(&nop_mnt_idmap, inode, attr); - exfat_truncate_atime(&inode->i_atime); + exfat_truncate_inode_atime(inode); if (attr->ia_valid & ATTR_SIZE) { error = exfat_block_truncate_page(inode, attr->ia_size); diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 13329baeafbc..a2185e6f0548 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -26,6 +26,7 @@ int __exfat_write_inode(struct inode *inode, int sync) struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); bool is_dir = (ei->type == TYPE_DIR) ? true : false; + struct timespec64 ts; if (inode->i_ino == EXFAT_ROOT_INO) return 0; @@ -55,16 +56,18 @@ int __exfat_write_inode(struct inode *inode, int sync) &ep->dentry.file.create_time, &ep->dentry.file.create_date, &ep->dentry.file.create_time_cs); - exfat_set_entry_time(sbi, &inode->i_mtime, - &ep->dentry.file.modify_tz, - &ep->dentry.file.modify_time, - &ep->dentry.file.modify_date, - &ep->dentry.file.modify_time_cs); - exfat_set_entry_time(sbi, &inode->i_atime, - &ep->dentry.file.access_tz, - &ep->dentry.file.access_time, - &ep->dentry.file.access_date, - NULL); + exfat_set_entry_time(sbi, &ts, + &ep->dentry.file.modify_tz, + &ep->dentry.file.modify_time, + &ep->dentry.file.modify_date, + &ep->dentry.file.modify_time_cs); + inode_set_mtime_to_ts(inode, ts); + exfat_set_entry_time(sbi, &ts, + &ep->dentry.file.access_tz, + &ep->dentry.file.access_time, + &ep->dentry.file.access_date, + NULL); + inode_set_atime_to_ts(inode, ts); /* File size should be zero if there is no cluster allocated */ on_disk_size = i_size_read(inode); @@ -355,7 +358,7 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) if (to > i_size_read(inode)) { truncate_pagecache(inode, i_size_read(inode)); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); exfat_truncate(inode); } } @@ -398,7 +401,7 @@ static int exfat_write_end(struct file *file, struct address_space *mapping, exfat_write_failed(mapping, pos+len); if (!(err < 0) && !(ei->attr & ATTR_ARCHIVE)) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ei->attr |= ATTR_ARCHIVE; mark_inode_dirty(inode); } @@ -576,10 +579,10 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) exfat_save_attr(inode, info->attr); inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; - inode->i_mtime = info->mtime; + inode_set_mtime_to_ts(inode, info->mtime); inode_set_ctime_to_ts(inode, info->mtime); ei->i_crtime = info->crtime; - inode->i_atime = info->atime; + inode_set_atime_to_ts(inode, info->atime); return 0; } diff --git a/fs/exfat/misc.c b/fs/exfat/misc.c index 2e1a1a6b1021..fa8459828046 100644 --- a/fs/exfat/misc.c +++ b/fs/exfat/misc.c @@ -126,6 +126,14 @@ void exfat_truncate_atime(struct timespec64 *ts) ts->tv_nsec = 0; } +void exfat_truncate_inode_atime(struct inode *inode) +{ + struct timespec64 atime = inode_get_atime(inode); + + exfat_truncate_atime(&atime); + inode_set_atime_to_ts(inode, atime); +} + u16 exfat_calc_chksum16(void *data, int len, u16 chksum, int type) { int i; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 1b9f587f6cca..b92e46916dea 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -569,7 +569,7 @@ static int exfat_create(struct mnt_idmap *idmap, struct inode *dir, goto unlock; inode_inc_iversion(dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else @@ -582,8 +582,9 @@ static int exfat_create(struct mnt_idmap *idmap, struct inode *dir, goto unlock; inode_inc_iversion(inode); - inode->i_mtime = inode->i_atime = EXFAT_I(inode)->i_crtime = inode_set_ctime_current(inode); - exfat_truncate_atime(&inode->i_atime); + EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); + /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); @@ -816,16 +817,16 @@ static int exfat_unlink(struct inode *dir, struct dentry *dentry) ei->dir.dir = DIR_DELETED; inode_inc_iversion(dir); - dir->i_mtime = dir->i_atime = inode_set_ctime_current(dir); - exfat_truncate_atime(&dir->i_atime); + simple_inode_init_ts(dir); + exfat_truncate_inode_atime(dir); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else mark_inode_dirty(dir); clear_nlink(inode); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - exfat_truncate_atime(&inode->i_atime); + simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); exfat_unhash_inode(inode); exfat_d_version_set(dentry, inode_query_iversion(dir)); unlock: @@ -851,7 +852,7 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, goto unlock; inode_inc_iversion(dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else @@ -865,8 +866,8 @@ static int exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, goto unlock; inode_inc_iversion(inode); - inode->i_mtime = inode->i_atime = EXFAT_I(inode)->i_crtime = inode_set_ctime_current(inode); - exfat_truncate_atime(&inode->i_atime); + EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); @@ -977,8 +978,8 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) ei->dir.dir = DIR_DELETED; inode_inc_iversion(dir); - dir->i_mtime = dir->i_atime = inode_set_ctime_current(dir); - exfat_truncate_atime(&dir->i_atime); + simple_inode_init_ts(dir); + exfat_truncate_inode_atime(dir); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else @@ -986,8 +987,8 @@ static int exfat_rmdir(struct inode *dir, struct dentry *dentry) drop_nlink(dir); clear_nlink(inode); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - exfat_truncate_atime(&inode->i_atime); + simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); exfat_unhash_inode(inode); exfat_d_version_set(dentry, inode_query_iversion(dir)); unlock: @@ -1312,7 +1313,7 @@ static int exfat_rename(struct mnt_idmap *idmap, inode_inc_iversion(new_dir); simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); EXFAT_I(new_dir)->i_crtime = current_time(new_dir); - exfat_truncate_atime(&new_dir->i_atime); + exfat_truncate_inode_atime(new_dir); if (IS_DIRSYNC(new_dir)) exfat_sync_inode(new_dir); else diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 2778bd9b631e..e919a68bf4a1 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -370,8 +370,8 @@ static int exfat_read_root(struct inode *inode) ei->i_size_ondisk = i_size_read(inode); exfat_save_attr(inode, ATTR_SUBDIR); - inode->i_mtime = inode->i_atime = ei->i_crtime = inode_set_ctime_current(inode); - exfat_truncate_atime(&inode->i_atime); + ei->i_crtime = simple_inode_init_ts(inode); + exfat_truncate_inode_atime(inode); return 0; } diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index b335f17f682f..c7900868171b 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -468,7 +468,7 @@ int ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, ext2_set_de_type(de, inode); ext2_commit_chunk(page, pos, len); if (update_times) - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; mark_inode_dirty(dir); return ext2_handle_dirsync(dir); @@ -555,7 +555,7 @@ got_it: de->inode = cpu_to_le32(inode->i_ino); ext2_set_de_type (de, inode); ext2_commit_chunk(page, pos, rec_len); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; mark_inode_dirty(dir); err = ext2_handle_dirsync(dir); @@ -606,7 +606,7 @@ int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page) pde->rec_len = ext2_rec_len_to_disk(to - from); dir->inode = 0; ext2_commit_chunk(page, pos, to - from); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL; mark_inode_dirty(inode); return ext2_handle_dirsync(inode); diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index c24d0de95a83..fdf63e9c6e7c 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -546,7 +546,7 @@ got: inode->i_ino = ino; inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_flags = ext2_mask_flags(mode, EXT2_I(dir)->i_flags & EXT2_FL_INHERITED); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 314b415ee518..464faf6c217e 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1291,7 +1291,7 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) __ext2_truncate_blocks(inode, newsize); filemap_invalidate_unlock(inode->i_mapping); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (inode_needs_sync(inode)) { sync_mapping_buffers(inode->i_mapping); sync_inode_metadata(inode, 1); @@ -1412,10 +1412,9 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); - inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); + inode_set_atime(inode, (signed)le32_to_cpu(raw_inode->i_atime), 0); inode_set_ctime(inode, (signed)le32_to_cpu(raw_inode->i_ctime), 0); - inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime); - inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = 0; + inode_set_mtime(inode, (signed)le32_to_cpu(raw_inode->i_mtime), 0); ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); /* We now have enough fields to check if the inode was active or not. * This is needed because nfsd might try to access dead inodes @@ -1544,9 +1543,9 @@ static int __ext2_write_inode(struct inode *inode, int do_sync) } raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); raw_inode->i_size = cpu_to_le32(inode->i_size); - raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec); - raw_inode->i_ctime = cpu_to_le32(inode_get_ctime(inode).tv_sec); - raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec); + raw_inode->i_atime = cpu_to_le32(inode_get_atime_sec(inode)); + raw_inode->i_ctime = cpu_to_le32(inode_get_ctime_sec(inode)); + raw_inode->i_mtime = cpu_to_le32(inode_get_mtime_sec(inode)); raw_inode->i_blocks = cpu_to_le32(inode->i_blocks); raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); diff --git a/fs/ext2/super.c b/fs/ext2/super.c index aaf3e3e88cb2..645ee6142f69 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1572,7 +1572,7 @@ out: if (inode->i_size < off+len-towrite) i_size_write(inode, off+len-towrite); inode_inc_iversion(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); return len - towrite; } diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 20f741184673..e849241ebb8f 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -98,7 +98,7 @@ static struct buffer_head *ext2_xattr_cache_find(struct inode *, static void ext2_xattr_rehash(struct ext2_xattr_header *, struct ext2_xattr_entry *); -static const struct xattr_handler *ext2_xattr_handler_map[] = { +static const struct xattr_handler * const ext2_xattr_handler_map[] = { [EXT2_XATTR_INDEX_USER] = &ext2_xattr_user_handler, #ifdef CONFIG_EXT2_FS_POSIX_ACL [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, @@ -110,7 +110,7 @@ static const struct xattr_handler *ext2_xattr_handler_map[] = { #endif }; -const struct xattr_handler *ext2_xattr_handlers[] = { +const struct xattr_handler * const ext2_xattr_handlers[] = { &ext2_xattr_user_handler, &ext2_xattr_trusted_handler, #ifdef CONFIG_EXT2_FS_SECURITY diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h index 7925f596e8e2..6a4966949047 100644 --- a/fs/ext2/xattr.h +++ b/fs/ext2/xattr.h @@ -72,7 +72,7 @@ extern void ext2_xattr_delete_inode(struct inode *); extern struct mb_cache *ext2_xattr_create_cache(void); extern void ext2_xattr_destroy_cache(struct mb_cache *cache); -extern const struct xattr_handler *ext2_xattr_handlers[]; +extern const struct xattr_handler * const ext2_xattr_handlers[]; # else /* CONFIG_EXT2_FS_XATTR */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9418359b1d9d..8da5fb680210 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -891,10 +891,13 @@ do { \ (raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \ } while (0) -#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ - EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, (inode)->xtime) +#define EXT4_INODE_SET_ATIME(inode, raw_inode) \ + EXT4_INODE_SET_XTIME_VAL(i_atime, inode, raw_inode, inode_get_atime(inode)) -#define EXT4_INODE_SET_CTIME(inode, raw_inode) \ +#define EXT4_INODE_SET_MTIME(inode, raw_inode) \ + EXT4_INODE_SET_XTIME_VAL(i_mtime, inode, raw_inode, inode_get_mtime(inode)) + +#define EXT4_INODE_SET_CTIME(inode, raw_inode) \ EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode)) #define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ @@ -910,9 +913,16 @@ do { \ .tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \ }) -#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \ +#define EXT4_INODE_GET_ATIME(inode, raw_inode) \ +do { \ + inode_set_atime_to_ts(inode, \ + EXT4_INODE_GET_XTIME_VAL(i_atime, inode, raw_inode)); \ +} while (0) + +#define EXT4_INODE_GET_MTIME(inode, raw_inode) \ do { \ - (inode)->xtime = EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode); \ + inode_set_mtime_to_ts(inode, \ + EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode)); \ } while (0) #define EXT4_INODE_GET_CTIME(inode, raw_inode) \ @@ -1537,7 +1547,7 @@ struct ext4_sb_info { unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; - struct block_device *s_journal_bdev; + struct bdev_handle *s_journal_bdev_handle; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 202c76996b62..4c4176ee1749 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4481,7 +4481,8 @@ retry: if (epos > new_size) epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) - inode->i_mtime = inode_get_ctime(inode); + inode_set_mtime_to_ts(inode, + inode_get_ctime(inode)); } ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); @@ -4617,7 +4618,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); @@ -4642,7 +4643,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, goto out_mutex; } - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (new_size) ext4_update_inode_size(inode, new_size); ret = ext4_mark_inode_dirty(handle, inode); @@ -5378,7 +5379,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); @@ -5488,7 +5489,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_stop; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index cdf9bfe10137..11e6f33677a2 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -576,8 +576,9 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb, if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev)) return true; - if (EXT4_SB(sb)->s_journal_bdev && - fm->fmr_device == new_encode_dev(EXT4_SB(sb)->s_journal_bdev->bd_dev)) + if (EXT4_SB(sb)->s_journal_bdev_handle && + fm->fmr_device == + new_encode_dev(EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev)) return true; return false; } @@ -647,9 +648,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, memset(handlers, 0, sizeof(handlers)); handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev); handlers[0].gfd_fn = ext4_getfsmap_datadev; - if (EXT4_SB(sb)->s_journal_bdev) { + if (EXT4_SB(sb)->s_journal_bdev_handle) { handlers[1].gfd_dev = new_encode_dev( - EXT4_SB(sb)->s_journal_bdev->bd_dev); + EXT4_SB(sb)->s_journal_bdev_handle->bdev->bd_dev); handlers[1].gfd_fn = ext4_getfsmap_logdev; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b65058d972f9..e9bbb1da2d0a 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1250,8 +1250,8 @@ got: inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - ei->i_crtime = inode->i_mtime; + simple_inode_init_ts(inode); + ei->i_crtime = inode_get_mtime(inode); memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_dir_start_lookup = 0; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 012d9259ff53..9a84a5f9fef4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1037,7 +1037,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, * happen is that the times are slightly out of date * and/or different from the directory change time. */ - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); inode_inc_iversion(dir); return 1; @@ -1991,7 +1991,7 @@ out: ext4_orphan_del(handle, inode); if (err == 0) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); if (IS_SYNC(inode)) ext4_handle_sync(handle); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4ce35f1c8b0a..08cb5c0e0d51 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4020,7 +4020,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) if (IS_SYNC(inode)) ext4_handle_sync(handle); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret2)) ret = ret2; @@ -4180,7 +4180,7 @@ out_stop: if (inode->i_nlink) ext4_orphan_del(handle, inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; @@ -4284,8 +4284,8 @@ static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); EXT4_INODE_SET_CTIME(inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_SET_MTIME(inode, raw_inode); + EXT4_INODE_SET_ATIME(inode, raw_inode); EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); @@ -4893,8 +4893,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, } EXT4_INODE_GET_CTIME(inode, raw_inode); - EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_GET_ATIME(inode, raw_inode); + EXT4_INODE_GET_MTIME(inode, raw_inode); EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { @@ -5019,8 +5019,8 @@ static void __ext4_update_other_inode_time(struct super_block *sb, spin_lock(&ei->i_raw_lock); EXT4_INODE_SET_CTIME(inode, raw_inode); - EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode); - EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode); + EXT4_INODE_SET_MTIME(inode, raw_inode); + EXT4_INODE_SET_ATIME(inode, raw_inode); ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); trace_ext4_other_inode_update_time(inode, orig_ino); @@ -5413,7 +5413,8 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, * update c/mtime in shrink case below */ if (!shrink) - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); if (shrink) ext4_fc_track_range(handle, inode, diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0bfe2ce589e2..4f931f80cb34 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -312,13 +312,22 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) struct ext4_inode_info *ei1; struct ext4_inode_info *ei2; unsigned long tmp; + struct timespec64 ts1, ts2; ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); swap(inode1->i_version, inode2->i_version); - swap(inode1->i_atime, inode2->i_atime); - swap(inode1->i_mtime, inode2->i_mtime); + + ts1 = inode_get_atime(inode1); + ts2 = inode_get_atime(inode2); + inode_set_atime_to_ts(inode1, ts2); + inode_set_atime_to_ts(inode2, ts1); + + ts1 = inode_get_mtime(inode1); + ts2 = inode_get_mtime(inode2); + inode_set_mtime_to_ts(inode1, ts2); + inode_set_mtime_to_ts(inode2, ts1); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index bbda587f76b8..057d74467293 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2207,7 +2207,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, * happen is that the times are slightly out of date * and/or different from the directory change time. */ - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); inode_inc_iversion(dir); err2 = ext4_mark_inode_dirty(handle, dir); @@ -3202,7 +3202,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) * recovery. */ inode->i_size = 0; ext4_orphan_add(handle, inode); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_set_ctime_current(inode); retval = ext4_mark_inode_dirty(handle, inode); if (retval) @@ -3277,7 +3277,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto out_handle; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) @@ -3648,7 +3648,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, if (ext4_has_feature_filetype(ent->dir->i_sb)) ent->de->file_type = file_type; inode_inc_iversion(ent->dir); - ent->dir->i_mtime = inode_set_ctime_current(ent->dir); + inode_set_mtime_to_ts(ent->dir, inode_set_ctime_current(ent->dir)); retval = ext4_mark_inode_dirty(handle, ent->dir); BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata"); if (!ent->inlined) { @@ -3963,7 +3963,7 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir, ext4_dec_count(new.inode); inode_set_ctime_current(new.inode); } - old.dir->i_mtime = inode_set_ctime_current(old.dir); + inode_set_mtime_to_ts(old.dir, inode_set_ctime_current(old.dir)); ext4_update_dx_flag(old.dir); if (old.dir_bh) { retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dbebd8b3127e..42a44990d99c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1351,14 +1351,14 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); - if (sbi->s_journal_bdev) { + if (sbi->s_journal_bdev_handle) { /* * Invalidate the journal device's buffers. We don't want them * floating about in memory - the physical journal device may * hotswapped, and it breaks the `ro-after' testing code. */ - sync_blockdev(sbi->s_journal_bdev); - invalidate_bdev(sbi->s_journal_bdev); + sync_blockdev(sbi->s_journal_bdev_handle->bdev); + invalidate_bdev(sbi->s_journal_bdev_handle->bdev); } ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); @@ -4233,7 +4233,7 @@ int ext4_calculate_overhead(struct super_block *sb) * Add the internal journal blocks whether the journal has been * loaded or not */ - if (sbi->s_journal && !sbi->s_journal_bdev) + if (sbi->s_journal && !sbi->s_journal_bdev_handle) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ @@ -5670,9 +5670,9 @@ failed_mount: #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); brelse(sbi->s_sbh); - if (sbi->s_journal_bdev) { - invalidate_bdev(sbi->s_journal_bdev); - blkdev_put(sbi->s_journal_bdev, sb); + if (sbi->s_journal_bdev_handle) { + invalidate_bdev(sbi->s_journal_bdev_handle->bdev); + bdev_release(sbi->s_journal_bdev_handle); } out_fail: invalidate_bdev(sb->s_bdev); @@ -5842,12 +5842,13 @@ static journal_t *ext4_open_inode_journal(struct super_block *sb, return journal; } -static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, +static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb, dev_t j_dev, ext4_fsblk_t *j_start, ext4_fsblk_t *j_len) { struct buffer_head *bh; struct block_device *bdev; + struct bdev_handle *bdev_handle; int hblock, blocksize; ext4_fsblk_t sb_block; unsigned long offset; @@ -5856,16 +5857,17 @@ static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, /* see get_tree_bdev why this is needed and safe */ up_write(&sb->s_umount); - bdev = blkdev_get_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, - &fs_holder_ops); + bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, + sb, &fs_holder_ops); down_write(&sb->s_umount); - if (IS_ERR(bdev)) { + if (IS_ERR(bdev_handle)) { ext4_msg(sb, KERN_ERR, "failed to open journal device unknown-block(%u,%u) %ld", - MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev)); - return ERR_CAST(bdev); + MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle)); + return bdev_handle; } + bdev = bdev_handle->bdev; blocksize = sb->s_blocksize; hblock = bdev_logical_block_size(bdev); if (blocksize < hblock) { @@ -5912,12 +5914,12 @@ static struct block_device *ext4_get_journal_blkdev(struct super_block *sb, *j_start = sb_block + 1; *j_len = ext4_blocks_count(es); brelse(bh); - return bdev; + return bdev_handle; out_bh: brelse(bh); out_bdev: - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return ERR_PTR(errno); } @@ -5927,14 +5929,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, journal_t *journal; ext4_fsblk_t j_start; ext4_fsblk_t j_len; - struct block_device *journal_bdev; + struct bdev_handle *bdev_handle; int errno = 0; - journal_bdev = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); - if (IS_ERR(journal_bdev)) - return ERR_CAST(journal_bdev); + bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len); + if (IS_ERR(bdev_handle)) + return ERR_CAST(bdev_handle); - journal = jbd2_journal_init_dev(journal_bdev, sb->s_bdev, j_start, + journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start, j_len, sb->s_blocksize); if (IS_ERR(journal)) { ext4_msg(sb, KERN_ERR, "failed to create device journal"); @@ -5949,14 +5951,14 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, goto out_journal; } journal->j_private = sb; - EXT4_SB(sb)->s_journal_bdev = journal_bdev; + EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle; ext4_init_journal_params(sb, journal); return journal; out_journal: jbd2_journal_destroy(journal); out_bdev: - blkdev_put(journal_bdev, sb); + bdev_release(bdev_handle); return ERR_PTR(errno); } @@ -7127,7 +7129,7 @@ static int ext4_quota_off(struct super_block *sb, int type) } EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); out_unlock: @@ -7300,12 +7302,12 @@ static inline int ext3_feature_set_ok(struct super_block *sb) static void ext4_kill_sb(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL; + struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL; kill_block_super(sb); - if (journal_bdev) - blkdev_put(journal_bdev, sb); + if (handle) + bdev_release(handle); } static struct file_system_type ext4_fs_type = { diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 92ba28cebac6..82dc5e673d5c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -98,7 +98,7 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; -const struct xattr_handler *ext4_xattr_handlers[] = { +const struct xattr_handler * const ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY @@ -356,7 +356,7 @@ ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) { - return ((u64) inode_get_ctime(ea_inode).tv_sec << 32) | + return ((u64) inode_get_ctime_sec(ea_inode) << 32) | (u32) inode_peek_iversion_raw(ea_inode); } @@ -368,12 +368,12 @@ static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) { - return (u32)ea_inode->i_atime.tv_sec; + return (u32) inode_get_atime_sec(ea_inode); } static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) { - ea_inode->i_atime.tv_sec = hash; + inode_set_atime(ea_inode, hash, 0); } /* @@ -418,7 +418,7 @@ free_bhs: return ret; } -#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec) +#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode_get_mtime_sec(inode))) static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, u32 ea_inode_hash, struct inode **ea_inode) diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 824faf0b15a8..bd97c4aa8177 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -193,7 +193,7 @@ extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); extern void ext4_evict_ea_inode(struct inode *inode); -extern const struct xattr_handler *ext4_xattr_handlers[]; +extern const struct xattr_handler * const ext4_xattr_handlers[]; extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 8aa29fe2e87b..042593aed1ec 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -455,7 +455,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, de->file_type = fs_umode_to_ftype(inode->i_mode); set_page_dirty(page); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); f2fs_mark_inode_dirty_sync(dir, false); f2fs_put_page(page, 1); } @@ -609,7 +609,7 @@ void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, f2fs_i_links_write(dir, true); clear_inode_flag(inode, FI_NEW_INODE); } - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); f2fs_mark_inode_dirty_sync(dir, false); if (F2FS_I(dir)->i_current_depth != current_depth) @@ -919,7 +919,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, } f2fs_put_page(page, 1); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); f2fs_mark_inode_dirty_sync(dir, false); if (inode) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6d688e42d89c..9043cedfa12b 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1234,6 +1234,7 @@ struct f2fs_bio_info { #define FDEV(i) (sbi->devs[i]) #define RDEV(i) (raw_super->devs[i]) struct f2fs_dev_info { + struct bdev_handle *bdev_handle; struct block_device *bdev; char path[MAX_PATH_LEN]; unsigned int total_segments; @@ -3317,13 +3318,15 @@ static inline void clear_file(struct inode *inode, int type) static inline bool f2fs_is_time_consistent(struct inode *inode) { - struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 ts = inode_get_atime(inode); - if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) + if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &ts)) return false; - if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &ctime)) + ts = inode_get_ctime(inode); + if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &ts)) return false; - if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) + ts = inode_get_mtime(inode); + if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &ts)) return false; return true; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ca5904129b16..dd99abbb7186 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -798,7 +798,7 @@ int f2fs_truncate(struct inode *inode) if (err) return err; - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); f2fs_mark_inode_dirty_sync(inode, false); return 0; } @@ -905,9 +905,9 @@ static void __setattr_copy(struct mnt_idmap *idmap, i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_ATIME) - inode->i_atime = attr->ia_atime; + inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) - inode->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(inode, attr->ia_ctime); if (ia_valid & ATTR_MODE) { @@ -1012,7 +1012,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return err; spin_lock(&F2FS_I(inode)->i_size_lock); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); F2FS_I(inode)->last_disk_size = i_size_read(inode); spin_unlock(&F2FS_I(inode)->i_size_lock); } @@ -1840,7 +1840,7 @@ static long f2fs_fallocate(struct file *file, int mode, } if (!ret) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); f2fs_mark_inode_dirty_sync(inode, false); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); } @@ -2888,10 +2888,10 @@ out_src: if (ret) goto out_unlock; - src->i_mtime = inode_set_ctime_current(src); + inode_set_mtime_to_ts(src, inode_set_ctime_current(src)); f2fs_mark_inode_dirty_sync(src, false); if (src != dst) { - dst->i_mtime = inode_set_ctime_current(dst); + inode_set_mtime_to_ts(dst, inode_set_ctime_current(dst)); f2fs_mark_inode_dirty_sync(dst, false); } f2fs_update_time(sbi, REQ_TIME); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 2fe25619ccb5..ac00423f117b 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -699,7 +699,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, set_page_dirty(page); f2fs_put_page(page, 1); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); f2fs_mark_inode_dirty_sync(dir, false); if (inode) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index cde243840abd..5779c7edd49b 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -386,9 +386,9 @@ static void init_idisk_time(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); - fi->i_disk_time[0] = inode->i_atime; + fi->i_disk_time[0] = inode_get_atime(inode); fi->i_disk_time[1] = inode_get_ctime(inode); - fi->i_disk_time[2] = inode->i_mtime; + fi->i_disk_time[2] = inode_get_mtime(inode); } static int do_read_inode(struct inode *inode) @@ -417,12 +417,12 @@ static int do_read_inode(struct inode *inode) inode->i_size = le64_to_cpu(ri->i_size); inode->i_blocks = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1); - inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime); + inode_set_atime(inode, le64_to_cpu(ri->i_atime), + le32_to_cpu(ri->i_atime_nsec)); inode_set_ctime(inode, le64_to_cpu(ri->i_ctime), le32_to_cpu(ri->i_ctime_nsec)); - inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime); - inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec); - inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); + inode_set_mtime(inode, le64_to_cpu(ri->i_mtime), + le32_to_cpu(ri->i_mtime_nsec)); inode->i_generation = le32_to_cpu(ri->i_generation); if (S_ISDIR(inode->i_mode)) fi->i_current_depth = le32_to_cpu(ri->i_current_depth); @@ -698,12 +698,12 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) } set_raw_inline(inode, ri); - ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec); - ri->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec); - ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); - ri->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); - ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + ri->i_atime = cpu_to_le64(inode_get_atime_sec(inode)); + ri->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + ri->i_mtime = cpu_to_le64(inode_get_mtime_sec(inode)); + ri->i_atime_nsec = cpu_to_le32(inode_get_atime_nsec(inode)); + ri->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); + ri->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); if (S_ISDIR(inode->i_mode)) ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 193b22a2d6bf..d0053b0284d8 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -243,8 +243,8 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap, inode->i_ino = ino; inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - F2FS_I(inode)->i_crtime = inode->i_mtime; + simple_inode_init_ts(inode); + F2FS_I(inode)->i_crtime = inode_get_mtime(inode); inode->i_generation = get_random_u32(); if (S_ISDIR(inode->i_mode)) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 7be60df277a5..b56d0f1078a7 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -320,12 +320,12 @@ static int recover_inode(struct inode *inode, struct page *page) } f2fs_i_size_write(inode, le64_to_cpu(raw->i_size)); - inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime); + inode_set_atime(inode, le64_to_cpu(raw->i_atime), + le32_to_cpu(raw->i_atime_nsec)); inode_set_ctime(inode, le64_to_cpu(raw->i_ctime), le32_to_cpu(raw->i_ctime_nsec)); - inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime); - inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec); - inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + inode_set_mtime(inode, le64_to_cpu(raw->i_mtime), + le32_to_cpu(raw->i_mtime_nsec)); F2FS_I(inode)->i_advise = raw->i_advise; F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 66a5bf4216b7..be17d77513d5 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1562,7 +1562,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { if (i > 0) - blkdev_put(FDEV(i).bdev, sbi->sb); + bdev_release(FDEV(i).bdev_handle); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif @@ -2710,7 +2710,7 @@ retry: if (len == towrite) return err; - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); f2fs_mark_inode_dirty_sync(inode, false); return len - towrite; } @@ -4193,7 +4193,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) for (i = 0; i < max_devices; i++) { if (i == 0) - FDEV(0).bdev = sbi->sb->s_bdev; + FDEV(0).bdev_handle = sbi->sb->s_bdev_handle; else if (!RDEV(i).path[0]) break; @@ -4213,13 +4213,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) FDEV(i).end_blk = FDEV(i).start_blk + (FDEV(i).total_segments << sbi->log_blocks_per_seg) - 1; - FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, - mode, sbi->sb, NULL); + FDEV(i).bdev_handle = bdev_open_by_path( + FDEV(i).path, mode, sbi->sb, NULL); } } - if (IS_ERR(FDEV(i).bdev)) - return PTR_ERR(FDEV(i).bdev); + if (IS_ERR(FDEV(i).bdev_handle)) + return PTR_ERR(FDEV(i).bdev_handle); + FDEV(i).bdev = FDEV(i).bdev_handle->bdev; /* to release errored devices */ sbi->s_ndevs = i + 1; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index a657284faee3..4314456854f6 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -189,7 +189,7 @@ const struct xattr_handler f2fs_xattr_security_handler = { .set = f2fs_xattr_generic_set, }; -static const struct xattr_handler *f2fs_xattr_handler_map[] = { +static const struct xattr_handler * const f2fs_xattr_handler_map[] = { [F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler, #ifdef CONFIG_F2FS_FS_POSIX_ACL [F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, @@ -202,7 +202,7 @@ static const struct xattr_handler *f2fs_xattr_handler_map[] = { [F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler, }; -const struct xattr_handler *f2fs_xattr_handlers[] = { +const struct xattr_handler * const f2fs_xattr_handlers[] = { &f2fs_xattr_user_handler, &f2fs_xattr_trusted_handler, #ifdef CONFIG_F2FS_FS_SECURITY diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index b1811c392e6f..a005ffdcf717 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -125,7 +125,7 @@ extern const struct xattr_handler f2fs_xattr_trusted_handler; extern const struct xattr_handler f2fs_xattr_advise_handler; extern const struct xattr_handler f2fs_xattr_security_handler; -extern const struct xattr_handler *f2fs_xattr_handlers[]; +extern const struct xattr_handler * const f2fs_xattr_handlers[]; extern int f2fs_setxattr(struct inode *, int, const char *, const void *, size_t, struct page *, int); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index cdd39b6020f3..1fac3dabf130 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -512,6 +512,7 @@ static int fat_validate_dir(struct inode *dir) int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + struct timespec64 mtime; int error; MSDOS_I(inode)->i_pos = 0; @@ -561,14 +562,18 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; - fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0); - inode_set_ctime_to_ts(inode, inode->i_mtime); + fat_time_fat2unix(sbi, &mtime, de->time, de->date, 0); + inode_set_mtime_to_ts(inode, mtime); + inode_set_ctime_to_ts(inode, mtime); if (sbi->options.isvfat) { - fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0); + struct timespec64 atime; + + fat_time_fat2unix(sbi, &atime, 0, de->adate, 0); + inode_set_atime_to_ts(inode, atime); fat_time_fat2unix(sbi, &MSDOS_I(inode)->i_crtime, de->ctime, de->cdate, de->ctime_cs); } else - inode->i_atime = fat_truncate_atime(sbi, &inode->i_mtime); + inode_set_atime_to_ts(inode, fat_truncate_atime(sbi, &mtime)); return 0; } @@ -849,6 +854,7 @@ static int __fat_write_inode(struct inode *inode, int wait) struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *raw_entry; + struct timespec64 mtime; loff_t i_pos; sector_t blocknr; int err, offset; @@ -882,12 +888,14 @@ retry: raw_entry->size = cpu_to_le32(inode->i_size); raw_entry->attr = fat_make_attrs(inode); fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); - fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time, + mtime = inode_get_mtime(inode); + fat_time_unix2fat(sbi, &mtime, &raw_entry->time, &raw_entry->date, NULL); if (sbi->options.isvfat) { + struct timespec64 ts = inode_get_atime(inode); __le16 atime; - fat_time_unix2fat(sbi, &inode->i_atime, &atime, - &raw_entry->adate, NULL); + + fat_time_unix2fat(sbi, &ts, &atime, &raw_entry->adate, NULL); fat_time_unix2fat(sbi, &MSDOS_I(inode)->i_crtime, &raw_entry->ctime, &raw_entry->cdate, &raw_entry->ctime_cs); } @@ -1407,7 +1415,8 @@ static int fat_read_root(struct inode *inode) MSDOS_I(inode)->mmu_private = inode->i_size; fat_save_attrs(inode, ATTR_DIR); - inode->i_mtime = inode->i_atime = inode_set_ctime(inode, 0, 0); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime(inode, 0, 0))); set_nlink(inode, fat_subdirs(inode)+2); return 0; diff --git a/fs/fat/misc.c b/fs/fat/misc.c index f2304a1054aa..c7a2d27120ba 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -325,15 +325,15 @@ int fat_truncate_time(struct inode *inode, struct timespec64 *now, int flags) } if (flags & S_ATIME) - inode->i_atime = fat_truncate_atime(sbi, now); + inode_set_atime_to_ts(inode, fat_truncate_atime(sbi, now)); /* * ctime and mtime share the same on-disk field, and should be * identical in memory. all mtime updates will be applied to ctime, * but ctime updates are ignored. */ if (flags & S_MTIME) - inode->i_mtime = inode_set_ctime_to_ts(inode, - fat_truncate_mtime(sbi, now)); + inode_set_mtime_to_ts(inode, + inode_set_ctime_to_ts(inode, fat_truncate_mtime(sbi, now))); return 0; } diff --git a/fs/file.c b/fs/file.c index 3e4a4dfa38fc..5fb0b146e79e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -604,6 +604,9 @@ void fd_install(unsigned int fd, struct file *file) struct files_struct *files = current->files; struct fdtable *fdt; + if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) + return; + rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { @@ -853,8 +856,104 @@ void do_close_on_exec(struct files_struct *files) spin_unlock(&files->file_lock); } +static struct file *__get_file_rcu(struct file __rcu **f) +{ + struct file __rcu *file; + struct file __rcu *file_reloaded; + struct file __rcu *file_reloaded_cmp; + + file = rcu_dereference_raw(*f); + if (!file) + return NULL; + + if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) + return ERR_PTR(-EAGAIN); + + file_reloaded = rcu_dereference_raw(*f); + + /* + * Ensure that all accesses have a dependency on the load from + * rcu_dereference_raw() above so we get correct ordering + * between reuse/allocation and the pointer check below. + */ + file_reloaded_cmp = file_reloaded; + OPTIMIZER_HIDE_VAR(file_reloaded_cmp); + + /* + * atomic_long_inc_not_zero() above provided a full memory + * barrier when we acquired a reference. + * + * This is paired with the write barrier from assigning to the + * __rcu protected file pointer so that if that pointer still + * matches the current file, we know we have successfully + * acquired a reference to the right file. + * + * If the pointers don't match the file has been reallocated by + * SLAB_TYPESAFE_BY_RCU. + */ + if (file == file_reloaded_cmp) + return file_reloaded; + + fput(file); + return ERR_PTR(-EAGAIN); +} + +/** + * get_file_rcu - try go get a reference to a file under rcu + * @f: the file to get a reference on + * + * This function tries to get a reference on @f carefully verifying that + * @f hasn't been reused. + * + * This function should rarely have to be used and only by users who + * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. + * + * Return: Returns @f with the reference count increased or NULL. + */ +struct file *get_file_rcu(struct file __rcu **f) +{ + for (;;) { + struct file __rcu *file; + + file = __get_file_rcu(f); + if (unlikely(!file)) + return NULL; + + if (unlikely(IS_ERR(file))) + continue; + + return file; + } +} +EXPORT_SYMBOL_GPL(get_file_rcu); + +/** + * get_file_active - try go get a reference to a file + * @f: the file to get a reference on + * + * In contast to get_file_rcu() the pointer itself isn't part of the + * reference counting. + * + * This function should rarely have to be used and only by users who + * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. + * + * Return: Returns @f with the reference count increased or NULL. + */ +struct file *get_file_active(struct file **f) +{ + struct file __rcu *file; + + rcu_read_lock(); + file = __get_file_rcu(f); + rcu_read_unlock(); + if (IS_ERR(file)) + file = NULL; + return file; +} +EXPORT_SYMBOL_GPL(get_file_active); + static inline struct file *__fget_files_rcu(struct files_struct *files, - unsigned int fd, fmode_t mask) + unsigned int fd, fmode_t mask) { for (;;) { struct file *file; @@ -865,12 +964,6 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, return NULL; fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); - file = rcu_dereference_raw(*fdentry); - if (unlikely(!file)) - return NULL; - - if (unlikely(file->f_mode & mask)) - return NULL; /* * Ok, we have a file pointer. However, because we do @@ -879,10 +972,15 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, * * Such a race can take two forms: * - * (a) the file ref already went down to zero, - * and get_file_rcu() fails. Just try again: + * (a) the file ref already went down to zero and the + * file hasn't been reused yet or the file count + * isn't zero but the file has already been reused. */ - if (unlikely(!get_file_rcu(file))) + file = __get_file_rcu(fdentry); + if (unlikely(!file)) + return NULL; + + if (unlikely(IS_ERR(file))) continue; /* @@ -893,13 +991,21 @@ static inline struct file *__fget_files_rcu(struct files_struct *files, * * If so, we need to put our ref and try again. */ - if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || - unlikely(rcu_dereference_raw(*fdentry) != file)) { + if (unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* + * This isn't the file we're looking for or we're not + * allowed to get a reference to it. + */ + if (unlikely(file->f_mode & mask)) { + fput(file); + return NULL; + } + + /* * Ok, we have a ref to the file, and checked that it * still exists. */ @@ -948,7 +1054,14 @@ struct file *fget_task(struct task_struct *task, unsigned int fd) return file; } -struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) +struct file *lookup_fdget_rcu(unsigned int fd) +{ + return __fget_files_rcu(current->files, fd, 0); + +} +EXPORT_SYMBOL_GPL(lookup_fdget_rcu); + +struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; @@ -957,13 +1070,13 @@ struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) task_lock(task); files = task->files; if (files) - file = files_lookup_fd_rcu(files, fd); + file = __fget_files_rcu(files, fd, 0); task_unlock(task); return file; } -struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret_fd) +struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; @@ -974,7 +1087,7 @@ struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret files = task->files; if (files) { for (; fd < files_fdtable(files)->max_fds; fd++) { - file = files_lookup_fd_rcu(files, fd); + file = __fget_files_rcu(files, fd, 0); if (file) break; } @@ -983,7 +1096,7 @@ struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret *ret_fd = fd; return file; } -EXPORT_SYMBOL(task_lookup_next_fd_rcu); +EXPORT_SYMBOL(task_lookup_next_fdget_rcu); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. @@ -1272,12 +1385,16 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; + struct file *f; int retval = oldfd; rcu_read_lock(); - if (!files_lookup_fd_rcu(files, oldfd)) + f = __fget_files_rcu(files, oldfd, 0); + if (!f) retval = -EBADF; rcu_read_unlock(); + if (f) + fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); diff --git a/fs/file_table.c b/fs/file_table.c index ee21b3da9d08..fa92743ba6a9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -44,10 +44,10 @@ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; -/* Container for backing file with optional real path */ +/* Container for backing file with optional user path */ struct backing_file { struct file file; - struct path real_path; + struct path user_path; }; static inline struct backing_file *backing_file(struct file *f) @@ -55,31 +55,36 @@ static inline struct backing_file *backing_file(struct file *f) return container_of(f, struct backing_file, file); } -struct path *backing_file_real_path(struct file *f) +struct path *backing_file_user_path(struct file *f) { - return &backing_file(f)->real_path; + return &backing_file(f)->user_path; } -EXPORT_SYMBOL_GPL(backing_file_real_path); +EXPORT_SYMBOL_GPL(backing_file_user_path); -static void file_free_rcu(struct rcu_head *head) +static inline void file_free(struct file *f) { - struct file *f = container_of(head, struct file, f_rcuhead); - + security_file_free(f); + if (likely(!(f->f_mode & FMODE_NOACCOUNT))) + percpu_counter_dec(&nr_files); put_cred(f->f_cred); - if (unlikely(f->f_mode & FMODE_BACKING)) + if (unlikely(f->f_mode & FMODE_BACKING)) { + path_put(backing_file_user_path(f)); kfree(backing_file(f)); - else + } else { kmem_cache_free(filp_cachep, f); + } } -static inline void file_free(struct file *f) +void release_empty_file(struct file *f) { - security_file_free(f); - if (unlikely(f->f_mode & FMODE_BACKING)) - path_put(backing_file_real_path(f)); - if (likely(!(f->f_mode & FMODE_NOACCOUNT))) - percpu_counter_dec(&nr_files); - call_rcu(&f->f_rcuhead, file_free_rcu); + WARN_ON_ONCE(f->f_mode & (FMODE_BACKING | FMODE_OPENED)); + if (atomic_long_dec_and_test(&f->f_count)) { + security_file_free(f); + put_cred(f->f_cred); + if (likely(!(f->f_mode & FMODE_NOACCOUNT))) + percpu_counter_dec(&nr_files); + kmem_cache_free(filp_cachep, f); + } } /* @@ -164,7 +169,6 @@ static int init_file(struct file *f, int flags, const struct cred *cred) return error; } - atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); @@ -172,6 +176,12 @@ static int init_file(struct file *f, int flags, const struct cred *cred) f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ + /* + * We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While + * fget-rcu pattern users need to be able to handle spurious + * refcount bumps we should reinitialize the reused file first. + */ + atomic_long_set(&f->f_count, 1); return 0; } @@ -471,7 +481,8 @@ EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, - SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); + SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN | + SLAB_PANIC | SLAB_ACCOUNT, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index ac5d43b164b5..20600e9ea202 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -109,11 +109,9 @@ static inline void dip2vip_cpy(struct vxfs_sb_info *sbi, set_nlink(inode, vip->vii_nlink); inode->i_size = vip->vii_size; - inode->i_atime.tv_sec = vip->vii_atime; + inode_set_atime(inode, vip->vii_atime, 0); inode_set_ctime(inode, vip->vii_ctime, 0); - inode->i_mtime.tv_sec = vip->vii_mtime; - inode->i_atime.tv_nsec = 0; - inode->i_mtime.tv_nsec = 0; + inode_set_mtime(inode, vip->vii_mtime, 0); inode->i_blocks = vip->vii_blocks; inode->i_generation = vip->vii_gen; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 969ce991b0b0..1767493dffda 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -613,6 +613,24 @@ out_free: kfree(isw); } +static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, + struct list_head *list, int *nr) +{ + struct inode *inode; + + list_for_each_entry(inode, list, i_io_list) { + if (!inode_prepare_wbs_switch(inode, isw->new_wb)) + continue; + + isw->inodes[*nr] = inode; + (*nr)++; + + if (*nr >= WB_MAX_INODES_PER_ISW - 1) + return true; + } + return false; +} + /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb @@ -625,7 +643,6 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; - struct inode *inode; int nr; bool restart = false; @@ -647,17 +664,17 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb) nr = 0; spin_lock(&wb->list_lock); - list_for_each_entry(inode, &wb->b_attached, i_io_list) { - if (!inode_prepare_wbs_switch(inode, isw->new_wb)) - continue; - - isw->inodes[nr++] = inode; - - if (nr >= WB_MAX_INODES_PER_ISW - 1) { - restart = true; - break; - } - } + /* + * In addition to the inodes that have completed writeback, also switch + * cgwbs for those inodes only with dirty timestamps. Otherwise, those + * inodes won't be written back for a long time when lazytime is + * enabled, and thus pinning the dying cgwbs. It won't break the + * bandwidth restrictions, as writeback of inode metadata is not + * accounted for. + */ + restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); + if (!restart) + restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ @@ -1535,10 +1552,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, if (wbc->pages_skipped) { /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. + * Writeback is not making progress due to locked buffers. + * Skip this inode for now. Although having skipped pages + * is odd for clean inodes, it can happen for some + * filesystems so handle that gracefully. */ - redirty_tail_locked(inode, wb); + if (inode->i_state & I_DIRTY_ALL) + redirty_tail_locked(inode, wb); + else + inode_cgwb_move_to_attached(inode, wb); return; } diff --git a/fs/fs_context.c b/fs/fs_context.c index a0ad7a0c4680..98589aae5208 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -192,17 +192,19 @@ int vfs_parse_fs_string(struct fs_context *fc, const char *key, EXPORT_SYMBOL(vfs_parse_fs_string); /** - * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data + * vfs_parse_monolithic_sep - Parse key[=val][,key[=val]]* mount data * @fc: The superblock configuration to fill in. * @data: The data to parse + * @sep: callback for separating next option * - * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be - * called from the ->monolithic_mount_data() fs_context operation. + * Parse a blob of data that's in key[=val][,key[=val]]* form with a custom + * option separator callback. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ -int generic_parse_monolithic(struct fs_context *fc, void *data) +int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, + char *(*sep)(char **)) { char *options = data, *key; int ret = 0; @@ -214,7 +216,7 @@ int generic_parse_monolithic(struct fs_context *fc, void *data) if (ret) return ret; - while ((key = strsep(&options, ",")) != NULL) { + while ((key = sep(&options)) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); @@ -233,6 +235,28 @@ int generic_parse_monolithic(struct fs_context *fc, void *data) return ret; } +EXPORT_SYMBOL(vfs_parse_monolithic_sep); + +static char *vfs_parse_comma_sep(char **s) +{ + return strsep(s, ","); +} + +/** + * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data + * @fc: The superblock configuration to fill in. + * @data: The data to parse + * + * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be + * called from the ->monolithic_mount_data() fs_context operation. + * + * Returns 0 on success or the error returned by the ->parse_option() fs_context + * operation on failure. + */ +int generic_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, vfs_parse_comma_sep); +} EXPORT_SYMBOL(generic_parse_monolithic); /** diff --git a/fs/fsopen.c b/fs/fsopen.c index ce03f6521c88..6593ae518115 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -465,6 +465,7 @@ SYSCALL_DEFINE5(fsconfig, param.file = fget(aux); if (!param.file) goto out_key; + param.dirfd = aux; break; default: break; diff --git a/fs/fuse/control.c b/fs/fuse/control.c index ab62e4624256..284a35006462 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -235,7 +235,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, inode->i_mode = mode; inode->i_uid = fc->user_id; inode->i_gid = fc->group_id; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); /* setting ->i_op to NULL is not allowed */ if (iop) inode->i_op = iop; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d707e6987da9..d19cbf34c634 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1812,12 +1812,12 @@ int fuse_flush_times(struct inode *inode, struct fuse_file *ff) memset(&outarg, 0, sizeof(outarg)); inarg.valid = FATTR_MTIME; - inarg.mtime = inode->i_mtime.tv_sec; - inarg.mtimensec = inode->i_mtime.tv_nsec; + inarg.mtime = inode_get_mtime_sec(inode); + inarg.mtimensec = inode_get_mtime_nsec(inode); if (fm->fc->minor >= 23) { inarg.valid |= FATTR_CTIME; - inarg.ctime = inode_get_ctime(inode).tv_sec; - inarg.ctimensec = inode_get_ctime(inode).tv_nsec; + inarg.ctime = inode_get_ctime_sec(inode); + inarg.ctimensec = inode_get_ctime_nsec(inode); } if (ff) { inarg.valid |= FATTR_FH; @@ -1956,7 +1956,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, /* the kernel maintains i_mtime locally */ if (trust_local_cmtime) { if (attr->ia_valid & ATTR_MTIME) - inode->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(inode, attr->ia_mtime); if (attr->ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(inode, attr->ia_ctime); /* FIXME: clear I_DIRTY_SYNC? */ diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index bf0b85d0b95c..6e6e721f421b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1284,7 +1284,7 @@ ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, size_t size); ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size); int fuse_removexattr(struct inode *inode, const char *name); -extern const struct xattr_handler *fuse_xattr_handlers[]; +extern const struct xattr_handler * const fuse_xattr_handlers[]; struct posix_acl; struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2e4eb7cf26fb..caa8121ad99c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -188,12 +188,10 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1); attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1); - inode->i_atime.tv_sec = attr->atime; - inode->i_atime.tv_nsec = attr->atimensec; + inode_set_atime(inode, attr->atime, attr->atimensec); /* mtime from server may be stale due to local buffered write */ if (!(cache_mask & STATX_MTIME)) { - inode->i_mtime.tv_sec = attr->mtime; - inode->i_mtime.tv_nsec = attr->mtimensec; + inode_set_mtime(inode, attr->mtime, attr->mtimensec); } if (!(cache_mask & STATX_CTIME)) { inode_set_ctime(inode, attr->ctime, attr->ctimensec); @@ -276,12 +274,12 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, attr->size = i_size_read(inode); if (cache_mask & STATX_MTIME) { - attr->mtime = inode->i_mtime.tv_sec; - attr->mtimensec = inode->i_mtime.tv_nsec; + attr->mtime = inode_get_mtime_sec(inode); + attr->mtimensec = inode_get_mtime_nsec(inode); } if (cache_mask & STATX_CTIME) { - attr->ctime = inode_get_ctime(inode).tv_sec; - attr->ctimensec = inode_get_ctime(inode).tv_nsec; + attr->ctime = inode_get_ctime_sec(inode); + attr->ctimensec = inode_get_ctime_nsec(inode); } if ((attr_version != 0 && fi->attr_version > attr_version) || @@ -290,7 +288,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, return; } - old_mtime = inode->i_mtime; + old_mtime = inode_get_mtime(inode); fuse_change_attributes_common(inode, attr, sx, attr_valid, cache_mask); oldsize = inode->i_size; @@ -337,8 +335,7 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, { inode->i_mode = attr->mode & S_IFMT; inode->i_size = attr->size; - inode->i_mtime.tv_sec = attr->mtime; - inode->i_mtime.tv_nsec = attr->mtimensec; + inode_set_mtime(inode, attr->mtime, attr->mtimensec); inode_set_ctime(inode, attr->ctime, attr->ctimensec); if (S_ISREG(inode->i_mode)) { fuse_init_common(inode); @@ -1423,17 +1420,19 @@ EXPORT_SYMBOL_GPL(fuse_dev_free); static void fuse_fill_attr_from_inode(struct fuse_attr *attr, const struct fuse_inode *fi) { + struct timespec64 atime = inode_get_atime(&fi->inode); + struct timespec64 mtime = inode_get_mtime(&fi->inode); struct timespec64 ctime = inode_get_ctime(&fi->inode); *attr = (struct fuse_attr){ .ino = fi->inode.i_ino, .size = fi->inode.i_size, .blocks = fi->inode.i_blocks, - .atime = fi->inode.i_atime.tv_sec, - .mtime = fi->inode.i_mtime.tv_sec, + .atime = atime.tv_sec, + .mtime = mtime.tv_sec, .ctime = ctime.tv_sec, - .atimensec = fi->inode.i_atime.tv_nsec, - .mtimensec = fi->inode.i_mtime.tv_nsec, + .atimensec = atime.tv_nsec, + .mtimensec = mtime.tv_nsec, .ctimensec = ctime.tv_nsec, .mode = fi->inode.i_mode, .nlink = fi->inode.i_nlink, diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 9e6d587b3e67..c66a54d6c7d3 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -476,7 +476,7 @@ retry_locked: if (!fi->rdc.cached) { /* Starting cache? Set cache mtime. */ if (!ctx->pos && !fi->rdc.size) { - fi->rdc.mtime = inode->i_mtime; + fi->rdc.mtime = inode_get_mtime(inode); fi->rdc.iversion = inode_query_iversion(inode); } spin_unlock(&fi->rdc.lock); @@ -488,8 +488,10 @@ retry_locked: * changed, and reset the cache if so. */ if (!ctx->pos) { + struct timespec64 mtime = inode_get_mtime(inode); + if (inode_peek_iversion(inode) != fi->rdc.iversion || - !timespec64_equal(&fi->rdc.mtime, &inode->i_mtime)) { + !timespec64_equal(&fi->rdc.mtime, &mtime)) { fuse_rdc_reset(inode); goto retry_locked; } diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 49c01559580f..5b423fdbb13f 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -209,7 +209,7 @@ static const struct xattr_handler fuse_xattr_handler = { .set = fuse_xattr_set, }; -const struct xattr_handler *fuse_xattr_handlers[] = { +const struct xattr_handler * const fuse_xattr_handlers[] = { &fuse_xattr_handler, NULL }; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index ef7017fb6951..011cd992e0e6 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1386,7 +1386,7 @@ static int trunc_start(struct inode *inode, u64 newsize) ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG; i_size_write(inode, newsize); - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_dinode_out(ip, dibh->b_data); if (journaled) @@ -1583,7 +1583,7 @@ out_unlock: /* Every transaction boundary, we rewrite the dinode to keep its di_blocks current in case of failure. */ - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -1949,7 +1949,7 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) gfs2_statfs_change(sdp, 0, +btotal, 0); gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid, ip->i_inode.i_gid); - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); up_write(&ip->i_rw_mutex); @@ -1992,7 +1992,7 @@ static int trunc_end(struct gfs2_inode *ip) gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); gfs2_ordered_del_inode(ip); } - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG; gfs2_trans_add_meta(ip->i_gl, dibh); @@ -2093,7 +2093,7 @@ static int do_grow(struct inode *inode, u64 size) goto do_end_trans; truncate_setsize(inode, size); - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 1a2afa88f8be..61ddd03ea111 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -130,7 +130,7 @@ static int gfs2_dir_write_stuffed(struct gfs2_inode *ip, const char *buf, memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size); if (ip->i_inode.i_size < offset + size) i_size_write(&ip->i_inode, offset + size); - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -227,7 +227,7 @@ out: if (ip->i_inode.i_size < offset + copied) i_size_write(&ip->i_inode, offset + copied); - ip->i_inode.i_mtime = inode_set_ctime_current(&ip->i_inode); + inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); @@ -1825,7 +1825,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name, da->bh = NULL; brelse(bh); ip->i_entries++; - ip->i_inode.i_mtime = tv; + inode_set_mtime_to_ts(&ip->i_inode, tv); if (S_ISDIR(nip->i_inode.i_mode)) inc_nlink(&ip->i_inode); mark_inode_dirty(inode); @@ -1911,7 +1911,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry) if (!dip->i_entries) gfs2_consist_inode(dip); dip->i_entries--; - dip->i_inode.i_mtime = tv; + inode_set_mtime_to_ts(&dip->i_inode, tv); if (d_is_dir(dentry)) drop_nlink(&dip->i_inode); mark_inode_dirty(&dip->i_inode); @@ -1952,7 +1952,7 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename, dent->de_type = cpu_to_be16(new_type); brelse(bh); - dip->i_inode.i_mtime = inode_set_ctime_current(&dip->i_inode); + inode_set_mtime_to_ts(&dip->i_inode, inode_set_ctime_current(&dip->i_inode)); mark_inode_dirty_sync(&dip->i_inode); return 0; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 4a280be229a6..3772a5d9e85c 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2719,16 +2719,19 @@ static struct file *gfs2_glockfd_next_file(struct gfs2_glockfd_iter *i) for(;; i->fd++) { struct inode *inode; - i->file = task_lookup_next_fd_rcu(i->task, &i->fd); + i->file = task_lookup_next_fdget_rcu(i->task, &i->fd); if (!i->file) { i->fd = 0; break; } + inode = file_inode(i->file); - if (inode->i_sb != i->sb) - continue; - if (get_file_rcu(i->file)) + if (inode->i_sb == i->sb) break; + + rcu_read_unlock(); + fput(i->file); + rcu_read_lock(); } rcu_read_unlock(); return i->file; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f41ca89d216b..e7d334c277a1 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -403,7 +403,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); const struct gfs2_dinode *str = buf; - struct timespec64 atime; + struct timespec64 atime, iatime; u16 height, depth; umode_t mode = be32_to_cpu(str->di_mode); struct inode *inode = &ip->i_inode; @@ -433,10 +433,11 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) gfs2_set_inode_blocks(inode, be64_to_cpu(str->di_blocks)); atime.tv_sec = be64_to_cpu(str->di_atime); atime.tv_nsec = be32_to_cpu(str->di_atime_nsec); - if (timespec64_compare(&inode->i_atime, &atime) < 0) - inode->i_atime = atime; - inode->i_mtime.tv_sec = be64_to_cpu(str->di_mtime); - inode->i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec); + iatime = inode_get_atime(inode); + if (timespec64_compare(&iatime, &atime) < 0) + inode_set_atime_to_ts(inode, atime); + inode_set_mtime(inode, be64_to_cpu(str->di_mtime), + be32_to_cpu(str->di_mtime_nsec)); inode_set_ctime(inode, be64_to_cpu(str->di_ctime), be32_to_cpu(str->di_ctime_nsec)); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 0eac04507904..7fe77bc771e5 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -185,8 +185,9 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags); /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */ - inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1); - inode->i_atime.tv_nsec = 0; + inode_set_atime(inode, + 1LL << (8 * sizeof(inode_get_atime_sec(inode)) - 1), + 0); glock_set_object(ip->i_gl, ip); @@ -696,7 +697,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, set_nlink(inode, S_ISDIR(mode) ? 2 : 1); inode->i_rdev = dev; inode->i_size = size; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); munge_mode_uid_gid(dip, inode); check_and_update_goal(dip); ip->i_goal = dip->i_goal; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 171b2713d2e5..d9854aece15b 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -886,7 +886,7 @@ static int gfs2_adjust_quota(struct gfs2_sbd *sdp, loff_t loc, size = loc + sizeof(struct gfs2_quota); if (size > inode->i_size) i_size_write(inode, size); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); set_bit(QDF_REFRESH, &qd->qd_flags); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 02d93da21b2b..52a878fa7139 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -410,9 +410,9 @@ void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf) str->di_nlink = cpu_to_be32(inode->i_nlink); str->di_size = cpu_to_be64(i_size_read(inode)); str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(inode)); - str->di_atime = cpu_to_be64(inode->i_atime.tv_sec); - str->di_mtime = cpu_to_be64(inode->i_mtime.tv_sec); - str->di_ctime = cpu_to_be64(inode_get_ctime(inode).tv_sec); + str->di_atime = cpu_to_be64(inode_get_atime_sec(inode)); + str->di_mtime = cpu_to_be64(inode_get_mtime_sec(inode)); + str->di_ctime = cpu_to_be64(inode_get_ctime_sec(inode)); str->di_goal_meta = cpu_to_be64(ip->i_goal); str->di_goal_data = cpu_to_be64(ip->i_goal); @@ -427,9 +427,9 @@ void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf) str->di_entries = cpu_to_be32(ip->i_entries); str->di_eattr = cpu_to_be64(ip->i_eattr); - str->di_atime_nsec = cpu_to_be32(inode->i_atime.tv_nsec); - str->di_mtime_nsec = cpu_to_be32(inode->i_mtime.tv_nsec); - str->di_ctime_nsec = cpu_to_be32(inode_get_ctime(inode).tv_nsec); + str->di_atime_nsec = cpu_to_be32(inode_get_atime_nsec(inode)); + str->di_mtime_nsec = cpu_to_be32(inode_get_mtime_nsec(inode)); + str->di_ctime_nsec = cpu_to_be32(inode_get_ctime_nsec(inode)); } /** diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index ab9c83106932..b4ddf6244586 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -60,8 +60,8 @@ extern const struct export_operations gfs2_export_ops; extern const struct super_operations gfs2_super_ops; extern const struct dentry_operations gfs2_dops; -extern const struct xattr_handler *gfs2_xattr_handlers_max[]; -extern const struct xattr_handler **gfs2_xattr_handlers_min; +extern const struct xattr_handler * const gfs2_xattr_handlers_max[]; +extern const struct xattr_handler * const *gfs2_xattr_handlers_min; #endif /* __SUPER_DOT_H__ */ diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 4fea70c0fe3d..79d5c5559512 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1494,7 +1494,7 @@ static const struct xattr_handler gfs2_xattr_trusted_handler = { .set = gfs2_xattr_set, }; -const struct xattr_handler *gfs2_xattr_handlers_max[] = { +const struct xattr_handler * const gfs2_xattr_handlers_max[] = { /* GFS2_FS_FORMAT_MAX */ &gfs2_xattr_trusted_handler, @@ -1504,4 +1504,4 @@ const struct xattr_handler *gfs2_xattr_handlers_max[] = { NULL, }; -const struct xattr_handler **gfs2_xattr_handlers_min = gfs2_xattr_handlers_max + 1; +const struct xattr_handler * const *gfs2_xattr_handlers_min = gfs2_xattr_handlers_max + 1; diff --git a/fs/hfs/attr.c b/fs/hfs/attr.c index 6341bb248247..f8395cdd1adf 100644 --- a/fs/hfs/attr.c +++ b/fs/hfs/attr.c @@ -146,7 +146,7 @@ static const struct xattr_handler hfs_type_handler = { .set = hfs_xattr_set, }; -const struct xattr_handler *hfs_xattr_handlers[] = { +const struct xattr_handler * const hfs_xattr_handlers[] = { &hfs_creator_handler, &hfs_type_handler, NULL diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 632c226a3972..d63880e7d9d6 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -133,7 +133,7 @@ int hfs_cat_create(u32 cnid, struct inode *dir, const struct qstr *str, struct i goto err1; dir->i_size++; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); hfs_find_exit(&fd); return 0; @@ -269,7 +269,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, const struct qstr *str) } dir->i_size--; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); res = 0; out: @@ -337,7 +337,7 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, const struct qstr *src_name, if (err) goto out; dst_dir->i_size++; - dst_dir->i_mtime = inode_set_ctime_current(dst_dir); + inode_set_mtime_to_ts(dst_dir, inode_set_ctime_current(dst_dir)); mark_inode_dirty(dst_dir); /* finally remove the old entry */ @@ -349,7 +349,7 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, const struct qstr *src_name, if (err) goto out; src_dir->i_size--; - src_dir->i_mtime = inode_set_ctime_current(src_dir); + inode_set_mtime_to_ts(src_dir, inode_set_ctime_current(src_dir)); mark_inode_dirty(src_dir); type = entry.type; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 49d02524e667..b5a6ad5df357 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -215,7 +215,7 @@ extern void hfs_evict_inode(struct inode *); extern void hfs_delete_inode(struct inode *); /* attr.c */ -extern const struct xattr_handler *hfs_xattr_handlers[]; +extern const struct xattr_handler * const hfs_xattr_handlers[]; /* mdb.c */ extern int hfs_mdb_get(struct super_block *); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index ee349b72cfb3..a7bc4690a780 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -200,7 +200,7 @@ struct inode *hfs_new_inode(struct inode *dir, const struct qstr *name, umode_t inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); set_nlink(inode, 1); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); HFS_I(inode)->flags = 0; HFS_I(inode)->rsrc_inode = NULL; HFS_I(inode)->fs_blocks = 0; @@ -355,8 +355,8 @@ static int hfs_read_inode(struct inode *inode, void *data) inode->i_mode |= S_IWUGO; inode->i_mode &= ~hsb->s_file_umask; inode->i_mode |= S_IFREG; - inode->i_atime = inode->i_mtime = inode_set_ctime_to_ts(inode, - hfs_m_to_utime(rec->file.MdDat)); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, hfs_m_to_utime(rec->file.MdDat)))); inode->i_op = &hfs_file_inode_operations; inode->i_fop = &hfs_file_operations; inode->i_mapping->a_ops = &hfs_aops; @@ -366,8 +366,8 @@ static int hfs_read_inode(struct inode *inode, void *data) inode->i_size = be16_to_cpu(rec->dir.Val) + 2; HFS_I(inode)->fs_blocks = 0; inode->i_mode = S_IFDIR | (S_IRWXUGO & ~hsb->s_dir_umask); - inode->i_atime = inode->i_mtime = inode_set_ctime_to_ts(inode, - hfs_m_to_utime(rec->dir.MdDat)); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, hfs_m_to_utime(rec->dir.MdDat)))); inode->i_op = &hfs_dir_inode_operations; inode->i_fop = &hfs_dir_operations; break; @@ -474,7 +474,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) be32_to_cpu(rec.dir.DirID) != inode->i_ino) { } - rec.dir.MdDat = hfs_u_to_mtime(inode->i_mtime); + rec.dir.MdDat = hfs_u_to_mtime(inode_get_mtime(inode)); rec.dir.Val = cpu_to_be16(inode->i_size - 2); hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, @@ -502,7 +502,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) else rec.file.Flags |= HFS_FIL_LOCK; hfs_inode_write_fork(inode, rec.file.ExtRec, &rec.file.LgLen, &rec.file.PyLen); - rec.file.MdDat = hfs_u_to_mtime(inode->i_mtime); + rec.file.MdDat = hfs_u_to_mtime(inode_get_mtime(inode)); hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); @@ -654,7 +654,7 @@ int hfs_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, truncate_setsize(inode, attr->ia_size); hfs_file_truncate(inode); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } setattr_copy(&nop_mnt_idmap, inode, attr); diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c index dc27d418fbcd..76fa02e3835b 100644 --- a/fs/hfs/sysdep.c +++ b/fs/hfs/sysdep.c @@ -28,11 +28,13 @@ static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags) /* fix up inode on a timezone change */ diff = sys_tz.tz_minuteswest * 60 - HFS_I(inode)->tz_secondswest; if (diff) { - struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 ts = inode_get_ctime(inode); - inode_set_ctime(inode, ctime.tv_sec + diff, ctime.tv_nsec); - inode->i_atime.tv_sec += diff; - inode->i_mtime.tv_sec += diff; + inode_set_ctime(inode, ts.tv_sec + diff, ts.tv_nsec); + ts = inode_get_atime(inode); + inode_set_atime(inode, ts.tv_sec + diff, ts.tv_nsec); + ts = inode_get_mtime(inode); + inode_set_mtime(inode, ts.tv_sec + diff, ts.tv_nsec); HFS_I(inode)->tz_secondswest += diff; } return 1; diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index e71ae2537eaa..1995bafee839 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -312,7 +312,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, dir->i_size++; if (S_ISDIR(inode->i_mode)) hfsplus_subfolders_inc(dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); hfs_find_exit(&fd); @@ -417,7 +417,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, const struct qstr *str) dir->i_size--; if (type == HFSPLUS_FOLDER) hfsplus_subfolders_dec(dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY); if (type == HFSPLUS_FILE || type == HFSPLUS_FOLDER) { @@ -494,7 +494,7 @@ int hfsplus_rename_cat(u32 cnid, dst_dir->i_size++; if (type == HFSPLUS_FOLDER) hfsplus_subfolders_inc(dst_dir); - dst_dir->i_mtime = inode_set_ctime_current(dst_dir); + inode_set_mtime_to_ts(dst_dir, inode_set_ctime_current(dst_dir)); /* finally remove the old entry */ err = hfsplus_cat_build_key(sb, src_fd.search_key, @@ -511,7 +511,7 @@ int hfsplus_rename_cat(u32 cnid, src_dir->i_size--; if (type == HFSPLUS_FOLDER) hfsplus_subfolders_dec(src_dir); - src_dir->i_mtime = inode_set_ctime_current(src_dir); + inode_set_mtime_to_ts(src_dir, inode_set_ctime_current(src_dir)); /* remove old thread entry */ hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index c65c8c4b03dd..702a0663b1d8 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -267,7 +267,7 @@ static int hfsplus_setattr(struct mnt_idmap *idmap, } truncate_setsize(inode, attr->ia_size); hfsplus_file_truncate(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); } setattr_copy(&nop_mnt_idmap, inode, attr); @@ -392,7 +392,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, inode->i_ino = sbi->next_cnid++; inode_init_owner(&nop_mnt_idmap, inode, dir, mode); set_nlink(inode, 1); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); hip = HFSPLUS_I(inode); INIT_LIST_HEAD(&hip->open_dir_list); @@ -521,8 +521,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) hfsplus_get_perms(inode, &folder->permissions, 1); set_nlink(inode, 1); inode->i_size = 2 + be32_to_cpu(folder->valence); - inode->i_atime = hfsp_mt2ut(folder->access_date); - inode->i_mtime = hfsp_mt2ut(folder->content_mod_date); + inode_set_atime_to_ts(inode, hfsp_mt2ut(folder->access_date)); + inode_set_mtime_to_ts(inode, + hfsp_mt2ut(folder->content_mod_date)); inode_set_ctime_to_ts(inode, hfsp_mt2ut(folder->attribute_mod_date)); HFSPLUS_I(inode)->create_date = folder->create_date; @@ -563,8 +564,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) init_special_inode(inode, inode->i_mode, be32_to_cpu(file->permissions.dev)); } - inode->i_atime = hfsp_mt2ut(file->access_date); - inode->i_mtime = hfsp_mt2ut(file->content_mod_date); + inode_set_atime_to_ts(inode, hfsp_mt2ut(file->access_date)); + inode_set_mtime_to_ts(inode, + hfsp_mt2ut(file->content_mod_date)); inode_set_ctime_to_ts(inode, hfsp_mt2ut(file->attribute_mod_date)); HFSPLUS_I(inode)->create_date = file->create_date; @@ -609,8 +611,8 @@ int hfsplus_cat_write_inode(struct inode *inode) sizeof(struct hfsplus_cat_folder)); /* simple node checks? */ hfsplus_cat_set_perms(inode, &folder->permissions); - folder->access_date = hfsp_ut2mt(inode->i_atime); - folder->content_mod_date = hfsp_ut2mt(inode->i_mtime); + folder->access_date = hfsp_ut2mt(inode_get_atime(inode)); + folder->content_mod_date = hfsp_ut2mt(inode_get_mtime(inode)); folder->attribute_mod_date = hfsp_ut2mt(inode_get_ctime(inode)); folder->valence = cpu_to_be32(inode->i_size - 2); if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) { @@ -644,8 +646,8 @@ int hfsplus_cat_write_inode(struct inode *inode) file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED); else file->flags &= cpu_to_be16(~HFSPLUS_FILE_LOCKED); - file->access_date = hfsp_ut2mt(inode->i_atime); - file->content_mod_date = hfsp_ut2mt(inode->i_mtime); + file->access_date = hfsp_ut2mt(inode_get_atime(inode)); + file->content_mod_date = hfsp_ut2mt(inode_get_mtime(inode)); file->attribute_mod_date = hfsp_ut2mt(inode_get_ctime(inode)); hfs_bnode_write(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_file)); diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 58021e73c00b..9c9ff6b8c6f7 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -13,7 +13,7 @@ static int hfsplus_removexattr(struct inode *inode, const char *name); -const struct xattr_handler *hfsplus_xattr_handlers[] = { +const struct xattr_handler * const hfsplus_xattr_handlers[] = { &hfsplus_xattr_osx_handler, &hfsplus_xattr_user_handler, &hfsplus_xattr_trusted_handler, diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h index d14e362b3eba..15cc55e41410 100644 --- a/fs/hfsplus/xattr.h +++ b/fs/hfsplus/xattr.h @@ -17,7 +17,7 @@ extern const struct xattr_handler hfsplus_xattr_user_handler; extern const struct xattr_handler hfsplus_xattr_trusted_handler; extern const struct xattr_handler hfsplus_xattr_security_handler; -extern const struct xattr_handler *hfsplus_xattr_handlers[]; +extern const struct xattr_handler * const hfsplus_xattr_handlers[]; int __hfsplus_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index dc5a5cea5fae..ea87f24c6c3f 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -513,10 +513,14 @@ static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st) set_nlink(ino, st->nlink); i_uid_write(ino, st->uid); i_gid_write(ino, st->gid); - ino->i_atime = - (struct timespec64){ st->atime.tv_sec, st->atime.tv_nsec }; - ino->i_mtime = - (struct timespec64){ st->mtime.tv_sec, st->mtime.tv_nsec }; + inode_set_atime_to_ts(ino, (struct timespec64){ + st->atime.tv_sec, + st->atime.tv_nsec, + }); + inode_set_mtime_to_ts(ino, (struct timespec64){ + st->mtime.tv_sec, + st->mtime.tv_nsec, + }); inode_set_ctime(ino, st->ctime.tv_sec, st->ctime.tv_nsec); ino->i_size = st->size; ino->i_blocks = st->blocks; diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index f36566d61215..49dd585c2b17 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -277,14 +277,16 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in * inode. */ - if (!inode_get_ctime(result).tv_sec) { + if (!inode_get_ctime_sec(result)) { time64_t csec = local_to_gmt(dir->i_sb, le32_to_cpu(de->creation_date)); inode_set_ctime(result, csec ? csec : 1, 0); - result->i_mtime.tv_sec = local_to_gmt(dir->i_sb, le32_to_cpu(de->write_date)); - result->i_mtime.tv_nsec = 0; - result->i_atime.tv_sec = local_to_gmt(dir->i_sb, le32_to_cpu(de->read_date)); - result->i_atime.tv_nsec = 0; + inode_set_mtime(result, + local_to_gmt(dir->i_sb, le32_to_cpu(de->write_date)), + 0); + inode_set_atime(result, + local_to_gmt(dir->i_sb, le32_to_cpu(de->read_date)), + 0); hpfs_result->i_ea_size = le32_to_cpu(de->ea_size); if (!hpfs_result->i_ea_mode && de->read_only) result->i_mode &= ~0222; diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 479166378bae..a59e8fa630db 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -37,8 +37,8 @@ void hpfs_init_inode(struct inode *i) hpfs_inode->i_dirty = 0; inode_set_ctime(i, 0, 0); - i->i_mtime.tv_sec = i->i_mtime.tv_nsec = 0; - i->i_atime.tv_sec = i->i_atime.tv_nsec = 0; + inode_set_mtime(i, 0, 0); + inode_set_atime(i, 0, 0); } void hpfs_read_inode(struct inode *i) @@ -230,9 +230,9 @@ void hpfs_write_inode_nolock(struct inode *i) } hpfs_write_inode_ea(i, fnode); if (de) { - de->write_date = cpu_to_le32(gmt_to_local(i->i_sb, i->i_mtime.tv_sec)); - de->read_date = cpu_to_le32(gmt_to_local(i->i_sb, i->i_atime.tv_sec)); - de->creation_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_ctime(i).tv_sec)); + de->write_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_mtime_sec(i))); + de->read_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_atime_sec(i))); + de->creation_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_ctime_sec(i))); de->read_only = !(i->i_mode & 0222); de->ea_size = cpu_to_le32(hpfs_inode->i_ea_size); hpfs_mark_4buffers_dirty(&qbh); @@ -240,9 +240,9 @@ void hpfs_write_inode_nolock(struct inode *i) } if (S_ISDIR(i->i_mode)) { if ((de = map_dirent(i, hpfs_inode->i_dno, "\001\001", 2, NULL, &qbh))) { - de->write_date = cpu_to_le32(gmt_to_local(i->i_sb, i->i_mtime.tv_sec)); - de->read_date = cpu_to_le32(gmt_to_local(i->i_sb, i->i_atime.tv_sec)); - de->creation_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_ctime(i).tv_sec)); + de->write_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_mtime_sec(i))); + de->read_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_atime_sec(i))); + de->creation_date = cpu_to_le32(gmt_to_local(i->i_sb, inode_get_ctime_sec(i))); de->read_only = !(i->i_mode & 0222); de->ea_size = cpu_to_le32(/*hpfs_inode->i_ea_size*/0); de->file_size = cpu_to_le32(0); diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index f4eb8d6f5989..9184b4584b01 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -12,10 +12,10 @@ static void hpfs_update_directory_times(struct inode *dir) { time64_t t = local_to_gmt(dir->i_sb, local_get_seconds(dir->i_sb)); - if (t == dir->i_mtime.tv_sec && - t == inode_get_ctime(dir).tv_sec) + if (t == inode_get_mtime_sec(dir) && + t == inode_get_ctime_sec(dir)) return; - dir->i_mtime = inode_set_ctime(dir, t, 0); + inode_set_mtime_to_ts(dir, inode_set_ctime(dir, t, 0)); hpfs_write_inode_nolock(dir); } @@ -58,8 +58,8 @@ static int hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; hpfs_i(result)->i_dno = dno; - result->i_mtime = result->i_atime = - inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0); + inode_set_mtime_to_ts(result, + inode_set_atime_to_ts(result, inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0))); hpfs_i(result)->i_ea_size = 0; result->i_mode |= S_IFDIR; result->i_op = &hpfs_dir_iops; @@ -164,8 +164,8 @@ static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, result->i_fop = &hpfs_file_ops; set_nlink(result, 1); hpfs_i(result)->i_parent_dir = dir->i_ino; - result->i_mtime = result->i_atime = - inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0); + inode_set_mtime_to_ts(result, + inode_set_atime_to_ts(result, inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0))); hpfs_i(result)->i_ea_size = 0; if (dee.read_only) result->i_mode &= ~0222; @@ -245,8 +245,8 @@ static int hpfs_mknod(struct mnt_idmap *idmap, struct inode *dir, hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; - result->i_mtime = result->i_atime = - inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0); + inode_set_mtime_to_ts(result, + inode_set_atime_to_ts(result, inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0))); hpfs_i(result)->i_ea_size = 0; result->i_uid = current_fsuid(); result->i_gid = current_fsgid(); @@ -319,8 +319,8 @@ static int hpfs_symlink(struct mnt_idmap *idmap, struct inode *dir, result->i_ino = fno; hpfs_init_inode(result); hpfs_i(result)->i_parent_dir = dir->i_ino; - result->i_mtime = result->i_atime = - inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0); + inode_set_mtime_to_ts(result, + inode_set_atime_to_ts(result, inode_set_ctime(result, local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)), 0))); hpfs_i(result)->i_ea_size = 0; result->i_mode = S_IFLNK | 0777; result->i_uid = current_fsuid(); diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 758a51564124..6b0ba3c1efba 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -725,10 +725,12 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) if (!de) hpfs_error(s, "unable to find root dir"); else { - root->i_atime.tv_sec = local_to_gmt(s, le32_to_cpu(de->read_date)); - root->i_atime.tv_nsec = 0; - root->i_mtime.tv_sec = local_to_gmt(s, le32_to_cpu(de->write_date)); - root->i_mtime.tv_nsec = 0; + inode_set_atime(root, + local_to_gmt(s, le32_to_cpu(de->read_date)), + 0); + inode_set_mtime(root, + local_to_gmt(s, le32_to_cpu(de->write_date)), + 0); inode_set_ctime(root, local_to_gmt(s, le32_to_cpu(de->creation_date)), 0); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316c4cebd3f3..da217eaba102 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -980,7 +980,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, inode->i_mode = S_IFDIR | ctx->mode; inode->i_uid = ctx->uid; inode->i_gid = ctx->gid; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ @@ -1024,7 +1024,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mapping->private_data = resv_map; info->seals = F_SEAL_SEAL; switch (mode & S_IFMT) { @@ -1067,7 +1067,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev); if (!inode) return -ENOSPC; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_instantiate(dentry, inode); dget(dentry);/* Extra count - pin the dentry in core */ return 0; @@ -1099,7 +1099,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0); if (!inode) return -ENOSPC; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_tmpfile(file, inode); return finish_open_simple(file, 0); } @@ -1121,7 +1121,7 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap, } else iput(inode); } - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return error; } diff --git a/fs/init.c b/fs/init.c index 9684406a8416..e9387b6c4f30 100644 --- a/fs/init.c +++ b/fs/init.c @@ -153,8 +153,7 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev) if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); + mode = mode_strip_umask(d_inode(path.dentry), mode); error = security_path_mknod(&path, dentry, mode, dev); if (!error) error = vfs_mknod(mnt_idmap(path.mnt), path.dentry->d_inode, @@ -229,8 +228,7 @@ int __init init_mkdir(const char *pathname, umode_t mode) dentry = kern_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); + mode = mode_strip_umask(d_inode(path.dentry), mode); error = security_path_mkdir(&path, dentry, mode); if (!error) error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode, diff --git a/fs/inode.c b/fs/inode.c index 84bc3c76e5cc..4f8984b97df0 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1837,27 +1837,29 @@ EXPORT_SYMBOL(bmap); static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { - struct timespec64 ctime; + struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) return 1; /* * Is mtime younger than or equal to atime? If yes, update atime: */ - if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) + atime = inode_get_atime(inode); + mtime = inode_get_mtime(inode); + if (timespec64_compare(&mtime, &atime) >= 0) return 1; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); - if (timespec64_compare(&ctime, &inode->i_atime) >= 0) + if (timespec64_compare(&ctime, &atime) >= 0) return 1; /* * Is the previous atime value older than a day? If yes, * update atime: */ - if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60) + if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) return 1; /* * Good, we can skip the atime update: @@ -1888,12 +1890,13 @@ int inode_update_timestamps(struct inode *inode, int flags) if (flags & (S_MTIME|S_CTIME|S_VERSION)) { struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 mtime = inode_get_mtime(inode); now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; - if (!timespec64_equal(&now, &inode->i_mtime)) { - inode->i_mtime = now; + if (!timespec64_equal(&now, &mtime)) { + inode_set_mtime_to_ts(inode, now); updated |= S_MTIME; } if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated)) @@ -1903,8 +1906,10 @@ int inode_update_timestamps(struct inode *inode, int flags) } if (flags & S_ATIME) { - if (!timespec64_equal(&now, &inode->i_atime)) { - inode->i_atime = now; + struct timespec64 atime = inode_get_atime(inode); + + if (!timespec64_equal(&now, &atime)) { + inode_set_atime_to_ts(inode, now); updated |= S_ATIME; } } @@ -1963,7 +1968,7 @@ EXPORT_SYMBOL(inode_update_time); bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; - struct timespec64 now; + struct timespec64 now, atime; if (inode->i_flags & S_NOATIME) return false; @@ -1989,7 +1994,8 @@ bool atime_needs_update(const struct path *path, struct inode *inode) if (!relatime_need_update(mnt, inode, now)) return false; - if (timespec64_equal(&inode->i_atime, &now)) + atime = inode_get_atime(inode); + if (timespec64_equal(&atime, &now)) return false; return true; @@ -2006,7 +2012,7 @@ void touch_atime(const struct path *path) if (!sb_start_write_trylock(inode->i_sb)) return; - if (__mnt_want_write(mnt) != 0) + if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to @@ -2018,7 +2024,7 @@ void touch_atime(const struct path *path) * of the fs read only, e.g. subvolumes in Btrfs. */ inode_update_time(inode, S_ATIME); - __mnt_drop_write(mnt); + mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } @@ -2106,17 +2112,18 @@ static int inode_needs_update_time(struct inode *inode) { int sync_it = 0; struct timespec64 now = current_time(inode); - struct timespec64 ctime; + struct timespec64 ts; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; - if (!timespec64_equal(&inode->i_mtime, &now)) + ts = inode_get_mtime(inode); + if (!timespec64_equal(&ts, &now)) sync_it = S_MTIME; - ctime = inode_get_ctime(inode); - if (!timespec64_equal(&ctime, &now)) + ts = inode_get_ctime(inode); + if (!timespec64_equal(&ts, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) @@ -2131,9 +2138,9 @@ static int __file_update_time(struct file *file, int sync_mode) struct inode *inode = file_inode(file); /* try to update time settings */ - if (!__mnt_want_write_file(file)) { + if (!mnt_get_write_access_file(file)) { ret = inode_update_time(inode, sync_mode); - __mnt_drop_write_file(file); + mnt_put_write_access_file(file); } return ret; diff --git a/fs/internal.h b/fs/internal.h index d64ae03998cc..58e43341aebf 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -73,8 +73,8 @@ extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); -extern int __mnt_want_write_file(struct file *); -extern void __mnt_drop_write_file(struct file *); +int mnt_get_write_access_file(struct file *file); +void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); @@ -94,14 +94,22 @@ extern void chroot_fs_refs(const struct path *, const struct path *); struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred); +void release_empty_file(struct file *f); + +static inline void file_put_write_access(struct file *file) +{ + put_write_access(file->f_inode); + mnt_put_write_access(file->f_path.mnt); + if (unlikely(file->f_mode & FMODE_BACKING)) + mnt_put_write_access(backing_file_user_path(file)->mnt); +} static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { - put_write_access(file->f_inode); - __mnt_drop_write(file->f_path.mnt); + file_put_write_access(file); } } @@ -130,9 +138,9 @@ static inline void sb_start_ro_state_change(struct super_block *sb) * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in - * __mnt_want_write() before the mnt_is_readonly() check. The barrier - * makes sure if __mnt_want_write() sees MNT_WRITE_HOLD already - * cleared, it will see s_readonly_remount set. + * mnt_get_write_access() before the mnt_is_readonly() check. + * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD + * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 644479ccefbd..2bc0aa23fde3 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -881,8 +881,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + bytes = iov_iter_count(i); +retry: offset = pos & (chunk - 1); - bytes = min(chunk - offset, iov_iter_count(i)); + bytes = min(chunk - offset, bytes); status = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); if (unlikely(status)) @@ -933,10 +935,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) * halfway through, might be a race with munmap, * might be severe memory pressure. */ - if (copied) - bytes = copied; if (chunk > PAGE_SIZE) chunk /= 2; + if (copied) { + bytes = copied; + goto retry; + } } else { pos += status; written += status; @@ -1049,7 +1053,7 @@ static int iomap_write_delalloc_punch(struct inode *inode, struct folio *folio, /* * Scan the data range passed to us for dirty page cache folios. If we find a - * dirty folio, punch out the preceeding range and update the offset from which + * dirty folio, punch out the preceding range and update the offset from which * the next punch will start from. * * We can punch out storage reservations under clean pages because they either diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 2ee21286ac8f..3e4d53e26f94 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1422,8 +1422,8 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_ino, de->flags[-high_sierra]); } #endif - inode->i_mtime = inode->i_atime = - inode_set_ctime(inode, iso_date(de->date, high_sierra), 0); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime(inode, iso_date(de->date, high_sierra), 0))); ei->i_first_extent = (isonum_733(de->extent) + isonum_711(de->ext_attr_length)); diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 348783a70f57..d6c17ad69dee 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -426,16 +426,14 @@ repeat: 0); } if (rr->u.TF.flags & TF_MODIFY) { - inode->i_mtime.tv_sec = - iso_date(rr->u.TF.times[cnt++].time, - 0); - inode->i_mtime.tv_nsec = 0; + inode_set_mtime(inode, + iso_date(rr->u.TF.times[cnt++].time, 0), + 0); } if (rr->u.TF.flags & TF_ACCESS) { - inode->i_atime.tv_sec = - iso_date(rr->u.TF.times[cnt++].time, - 0); - inode->i_atime.tv_nsec = 0; + inode_set_atime(inode, + iso_date(rr->u.TF.times[cnt++].time, 0), + 0); } if (rr->u.TF.flags & TF_ATTRIBUTES) { inode_set_ctime(inode, @@ -531,9 +529,9 @@ repeat: inode->i_rdev = reloc->i_rdev; inode->i_size = reloc->i_size; inode->i_blocks = reloc->i_blocks; - inode->i_atime = reloc->i_atime; + inode_set_atime_to_ts(inode, inode_get_atime(reloc)); inode_set_ctime_to_ts(inode, inode_get_ctime(reloc)); - inode->i_mtime = reloc->i_mtime; + inode_set_mtime_to_ts(inode, inode_get_mtime(reloc)); iput(reloc); break; #ifdef CONFIG_ZISOFS diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 091ab0eaabbe..2b2938970da3 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -204,8 +204,8 @@ static int jffs2_create(struct mnt_idmap *idmap, struct inode *dir_i, if (ret) goto fail; - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, - ITIME(je32_to_cpu(ri->ctime))); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(je32_to_cpu(ri->ctime)))); jffs2_free_raw_inode(ri); @@ -238,7 +238,8 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry) if (dead_f->inocache) set_nlink(d_inode(dentry), dead_f->inocache->pino_nlink); if (!ret) - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, ITIME(now)); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(now))); return ret; } /***********************************************************************/ @@ -272,7 +273,8 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de set_nlink(d_inode(old_dentry), ++f->inocache->pino_nlink); mutex_unlock(&f->sem); d_instantiate(dentry, d_inode(old_dentry)); - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, ITIME(now)); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(now))); ihold(d_inode(old_dentry)); } return ret; @@ -423,8 +425,8 @@ static int jffs2_symlink (struct mnt_idmap *idmap, struct inode *dir_i, goto fail; } - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, - ITIME(je32_to_cpu(rd->mctime))); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(je32_to_cpu(rd->mctime)))); jffs2_free_raw_dirent(rd); @@ -568,8 +570,8 @@ static int jffs2_mkdir (struct mnt_idmap *idmap, struct inode *dir_i, goto fail; } - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, - ITIME(je32_to_cpu(rd->mctime))); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(je32_to_cpu(rd->mctime)))); inc_nlink(dir_i); jffs2_free_raw_dirent(rd); @@ -610,7 +612,8 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name, dentry->d_name.len, f, now); if (!ret) { - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, ITIME(now)); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(now))); clear_nlink(d_inode(dentry)); drop_nlink(dir_i); } @@ -746,8 +749,8 @@ static int jffs2_mknod (struct mnt_idmap *idmap, struct inode *dir_i, goto fail; } - dir_i->i_mtime = inode_set_ctime_to_ts(dir_i, - ITIME(je32_to_cpu(rd->mctime))); + inode_set_mtime_to_ts(dir_i, + inode_set_ctime_to_ts(dir_i, ITIME(je32_to_cpu(rd->mctime)))); jffs2_free_raw_dirent(rd); @@ -868,16 +871,18 @@ static int jffs2_rename (struct mnt_idmap *idmap, * caller won't do it on its own since we are returning an error. */ d_invalidate(new_dentry); - new_dir_i->i_mtime = inode_set_ctime_to_ts(new_dir_i, - ITIME(now)); + inode_set_mtime_to_ts(new_dir_i, + inode_set_ctime_to_ts(new_dir_i, ITIME(now))); return ret; } if (d_is_dir(old_dentry)) drop_nlink(old_dir_i); - old_dir_i->i_mtime = inode_set_ctime_to_ts(old_dir_i, ITIME(now)); - new_dir_i->i_mtime = inode_set_ctime_to_ts(new_dir_i, ITIME(now)); + inode_set_mtime_to_ts(old_dir_i, + inode_set_ctime_to_ts(old_dir_i, ITIME(now))); + inode_set_mtime_to_ts(new_dir_i, + inode_set_ctime_to_ts(new_dir_i, ITIME(now))); return 0; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 11c66793960e..62ea76da7fdf 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -317,8 +317,8 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, inode->i_size = pos + writtenlen; inode->i_blocks = (inode->i_size + 511) >> 9; - inode->i_mtime = inode_set_ctime_to_ts(inode, - ITIME(je32_to_cpu(ri->ctime))); + inode_set_mtime_to_ts(inode, + inode_set_ctime_to_ts(inode, ITIME(je32_to_cpu(ri->ctime)))); } } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 0403efab4089..d175cccb7c55 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -113,8 +113,8 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) ri->isize = cpu_to_je32((ivalid & ATTR_SIZE)?iattr->ia_size:inode->i_size); - ri->atime = cpu_to_je32(I_SEC((ivalid & ATTR_ATIME)?iattr->ia_atime:inode->i_atime)); - ri->mtime = cpu_to_je32(I_SEC((ivalid & ATTR_MTIME)?iattr->ia_mtime:inode->i_mtime)); + ri->atime = cpu_to_je32(I_SEC((ivalid & ATTR_ATIME)?iattr->ia_atime:inode_get_atime(inode))); + ri->mtime = cpu_to_je32(I_SEC((ivalid & ATTR_MTIME)?iattr->ia_mtime:inode_get_mtime(inode))); ri->ctime = cpu_to_je32(I_SEC((ivalid & ATTR_CTIME)?iattr->ia_ctime:inode_get_ctime(inode))); ri->offset = cpu_to_je32(0); @@ -147,9 +147,9 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) return PTR_ERR(new_metadata); } /* It worked. Update the inode */ - inode->i_atime = ITIME(je32_to_cpu(ri->atime)); + inode_set_atime_to_ts(inode, ITIME(je32_to_cpu(ri->atime))); inode_set_ctime_to_ts(inode, ITIME(je32_to_cpu(ri->ctime))); - inode->i_mtime = ITIME(je32_to_cpu(ri->mtime)); + inode_set_mtime_to_ts(inode, ITIME(je32_to_cpu(ri->mtime))); inode->i_mode = jemode_to_cpu(ri->mode); i_uid_write(inode, je16_to_cpu(ri->uid)); i_gid_write(inode, je16_to_cpu(ri->gid)); @@ -282,8 +282,8 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) i_uid_write(inode, je16_to_cpu(latest_node.uid)); i_gid_write(inode, je16_to_cpu(latest_node.gid)); inode->i_size = je32_to_cpu(latest_node.isize); - inode->i_atime = ITIME(je32_to_cpu(latest_node.atime)); - inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime)); + inode_set_atime_to_ts(inode, ITIME(je32_to_cpu(latest_node.atime))); + inode_set_mtime_to_ts(inode, ITIME(je32_to_cpu(latest_node.mtime))); inode_set_ctime_to_ts(inode, ITIME(je32_to_cpu(latest_node.ctime))); set_nlink(inode, f->inocache->pino_nlink); @@ -386,8 +386,8 @@ void jffs2_dirty_inode(struct inode *inode, int flags) iattr.ia_mode = inode->i_mode; iattr.ia_uid = inode->i_uid; iattr.ia_gid = inode->i_gid; - iattr.ia_atime = inode->i_atime; - iattr.ia_mtime = inode->i_mtime; + iattr.ia_atime = inode_get_atime(inode); + iattr.ia_mtime = inode_get_mtime(inode); iattr.ia_ctime = inode_get_ctime(inode); jffs2_do_setattr(inode, &iattr); @@ -475,8 +475,8 @@ struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_r inode->i_mode = jemode_to_cpu(ri->mode); i_gid_write(inode, je16_to_cpu(ri->gid)); i_uid_write(inode, je16_to_cpu(ri->uid)); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); - ri->atime = ri->mtime = ri->ctime = cpu_to_je32(I_SEC(inode->i_mtime)); + simple_inode_init_ts(inode); + ri->atime = ri->mtime = ri->ctime = cpu_to_je32(I_SEC(inode_get_mtime(inode))); inode->i_blocks = 0; inode->i_size = 0; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 50727a1ff931..86ab014a349c 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -36,8 +36,8 @@ struct kvec; #define JFFS2_NOW() JFFS2_CLAMP_TIME(ktime_get_real_seconds()) #define I_SEC(tv) JFFS2_CLAMP_TIME((tv).tv_sec) #define JFFS2_F_I_CTIME(f) I_SEC(inode_get_ctime(OFNI_EDONI_2SFFJ(f))) -#define JFFS2_F_I_MTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_mtime) -#define JFFS2_F_I_ATIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_atime) +#define JFFS2_F_I_MTIME(f) I_SEC(inode_get_mtime(OFNI_EDONI_2SFFJ(f))) +#define JFFS2_F_I_ATIME(f) I_SEC(inode_get_atime(OFNI_EDONI_2SFFJ(f))) #define sleep_on_spinunlock(wq, s) \ do { \ DECLARE_WAITQUEUE(__wait, current); \ diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 3b6bdc9a49e1..00224f3a8d6e 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -920,7 +920,7 @@ struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, * do_jffs2_setxattr(inode, xprefix, xname, buffer, size, flags) * is an implementation of setxattr handler on jffs2. * -------------------------------------------------- */ -const struct xattr_handler *jffs2_xattr_handlers[] = { +const struct xattr_handler * const jffs2_xattr_handlers[] = { &jffs2_user_xattr_handler, #ifdef CONFIG_JFFS2_FS_SECURITY &jffs2_security_xattr_handler, diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 1b5030a3349d..7e7de093ec0a 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -94,7 +94,7 @@ extern int do_jffs2_getxattr(struct inode *inode, int xprefix, const char *xname extern int do_jffs2_setxattr(struct inode *inode, int xprefix, const char *xname, const char *buffer, size_t size, int flags); -extern const struct xattr_handler *jffs2_xattr_handlers[]; +extern const struct xattr_handler * const jffs2_xattr_handlers[]; extern const struct xattr_handler jffs2_user_xattr_handler; extern const struct xattr_handler jffs2_trusted_xattr_handler; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 920d58a1566b..1a6b5921d17a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -393,7 +393,7 @@ void jfs_truncate_nolock(struct inode *ip, loff_t length) break; } - ip->i_mtime = inode_set_ctime_current(ip); + inode_set_mtime_to_ts(ip, inode_set_ctime_current(ip)); mark_inode_dirty(ip); txCommit(tid, 1, &ip, 0); diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 923a58422c46..8e87264e56ce 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -3061,10 +3061,10 @@ static int copy_from_dinode(struct dinode * dip, struct inode *ip) } ip->i_size = le64_to_cpu(dip->di_size); - ip->i_atime.tv_sec = le32_to_cpu(dip->di_atime.tv_sec); - ip->i_atime.tv_nsec = le32_to_cpu(dip->di_atime.tv_nsec); - ip->i_mtime.tv_sec = le32_to_cpu(dip->di_mtime.tv_sec); - ip->i_mtime.tv_nsec = le32_to_cpu(dip->di_mtime.tv_nsec); + inode_set_atime(ip, le32_to_cpu(dip->di_atime.tv_sec), + le32_to_cpu(dip->di_atime.tv_nsec)); + inode_set_mtime(ip, le32_to_cpu(dip->di_mtime.tv_sec), + le32_to_cpu(dip->di_mtime.tv_nsec)); inode_set_ctime(ip, le32_to_cpu(dip->di_ctime.tv_sec), le32_to_cpu(dip->di_ctime.tv_nsec)); ip->i_blocks = LBLK2PBLK(ip->i_sb, le64_to_cpu(dip->di_nblocks)); @@ -3138,12 +3138,12 @@ static void copy_to_dinode(struct dinode * dip, struct inode *ip) else /* Leave the original permissions alone */ dip->di_mode = cpu_to_le32(jfs_ip->mode2); - dip->di_atime.tv_sec = cpu_to_le32(ip->i_atime.tv_sec); - dip->di_atime.tv_nsec = cpu_to_le32(ip->i_atime.tv_nsec); - dip->di_ctime.tv_sec = cpu_to_le32(inode_get_ctime(ip).tv_sec); - dip->di_ctime.tv_nsec = cpu_to_le32(inode_get_ctime(ip).tv_nsec); - dip->di_mtime.tv_sec = cpu_to_le32(ip->i_mtime.tv_sec); - dip->di_mtime.tv_nsec = cpu_to_le32(ip->i_mtime.tv_nsec); + dip->di_atime.tv_sec = cpu_to_le32(inode_get_atime_sec(ip)); + dip->di_atime.tv_nsec = cpu_to_le32(inode_get_atime_nsec(ip)); + dip->di_ctime.tv_sec = cpu_to_le32(inode_get_ctime_sec(ip)); + dip->di_ctime.tv_nsec = cpu_to_le32(inode_get_ctime_nsec(ip)); + dip->di_mtime.tv_sec = cpu_to_le32(inode_get_mtime_sec(ip)); + dip->di_mtime.tv_nsec = cpu_to_le32(inode_get_mtime_nsec(ip)); dip->di_ixpxd = jfs_ip->ixpxd; /* in-memory pxd's are little-endian */ dip->di_acl = jfs_ip->acl; /* as are dxd's */ dip->di_ea = jfs_ip->ea; diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index 87594efa7f7c..f10f295d1502 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -97,8 +97,8 @@ struct inode *ialloc(struct inode *parent, umode_t mode) jfs_inode->mode2 |= inode->i_mode; inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - jfs_inode->otime = inode_get_ctime(inode).tv_sec; + simple_inode_init_ts(inode); + jfs_inode->otime = inode_get_ctime_sec(inode); inode->i_generation = JFS_SBI(sb)->gengen++; jfs_inode->cflag = 0; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index e855b8fde76c..cb6d1fda66a7 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1058,7 +1058,7 @@ void jfs_syncpt(struct jfs_log *log, int hard_sync) int lmLogOpen(struct super_block *sb) { int rc; - struct block_device *bdev; + struct bdev_handle *bdev_handle; struct jfs_log *log; struct jfs_sb_info *sbi = JFS_SBI(sb); @@ -1070,7 +1070,7 @@ int lmLogOpen(struct super_block *sb) mutex_lock(&jfs_log_mutex); list_for_each_entry(log, &jfs_external_logs, journal_list) { - if (log->bdev->bd_dev == sbi->logdev) { + if (log->bdev_handle->bdev->bd_dev == sbi->logdev) { if (!uuid_equal(&log->uuid, &sbi->loguuid)) { jfs_warn("wrong uuid on JFS journal"); mutex_unlock(&jfs_log_mutex); @@ -1100,14 +1100,14 @@ int lmLogOpen(struct super_block *sb) * file systems to log may have n-to-1 relationship; */ - bdev = blkdev_get_by_dev(sbi->logdev, BLK_OPEN_READ | BLK_OPEN_WRITE, - log, NULL); - if (IS_ERR(bdev)) { - rc = PTR_ERR(bdev); + bdev_handle = bdev_open_by_dev(sbi->logdev, + BLK_OPEN_READ | BLK_OPEN_WRITE, log, NULL); + if (IS_ERR(bdev_handle)) { + rc = PTR_ERR(bdev_handle); goto free; } - log->bdev = bdev; + log->bdev_handle = bdev_handle; uuid_copy(&log->uuid, &sbi->loguuid); /* @@ -1141,7 +1141,7 @@ journal_found: lbmLogShutdown(log); close: /* close external log device */ - blkdev_put(bdev, log); + bdev_release(bdev_handle); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1162,7 +1162,7 @@ static int open_inline_log(struct super_block *sb) init_waitqueue_head(&log->syncwait); set_bit(log_INLINELOG, &log->flag); - log->bdev = sb->s_bdev; + log->bdev_handle = sb->s_bdev_handle; log->base = addressPXD(&JFS_SBI(sb)->logpxd); log->size = lengthPXD(&JFS_SBI(sb)->logpxd) >> (L2LOGPSIZE - sb->s_blocksize_bits); @@ -1436,7 +1436,7 @@ int lmLogClose(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); struct jfs_log *log = sbi->log; - struct block_device *bdev; + struct bdev_handle *bdev_handle; int rc = 0; jfs_info("lmLogClose: log:0x%p", log); @@ -1482,10 +1482,10 @@ int lmLogClose(struct super_block *sb) * external log as separate logical volume */ list_del(&log->journal_list); - bdev = log->bdev; + bdev_handle = log->bdev_handle; rc = lmLogShutdown(log); - blkdev_put(bdev, log); + bdev_release(bdev_handle); kfree(log); @@ -1972,7 +1972,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bp->l_flag |= lbmREAD; - bio = bio_alloc(log->bdev, 1, REQ_OP_READ, GFP_NOFS); + bio = bio_alloc(log->bdev_handle->bdev, 1, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); @@ -2110,10 +2110,15 @@ static void lbmStartIO(struct lbuf * bp) { struct bio *bio; struct jfs_log *log = bp->l_log; + struct block_device *bdev = NULL; jfs_info("lbmStartIO"); - bio = bio_alloc(log->bdev, 1, REQ_OP_WRITE | REQ_SYNC, GFP_NOFS); + if (!log->no_integrity) + bdev = log->bdev_handle->bdev; + + bio = bio_alloc(bdev, 1, REQ_OP_WRITE | REQ_SYNC, + GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h index 805877ce5020..84aa2d253907 100644 --- a/fs/jfs/jfs_logmgr.h +++ b/fs/jfs/jfs_logmgr.h @@ -356,7 +356,7 @@ struct jfs_log { * before writing syncpt. */ struct list_head journal_list; /* Global list */ - struct block_device *bdev; /* 4: log lv pointer */ + struct bdev_handle *bdev_handle; /* 4: log lv pointer */ int serial; /* 4: log mount serial number */ s64 base; /* @8: log extent address (inline log ) */ diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index b83aae56a1f2..415eb65a36ff 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -430,7 +430,8 @@ int updateSuper(struct super_block *sb, uint state) if (state == FM_MOUNT) { /* record log's dev_t and mount serial number */ - j_sb->s_logdev = cpu_to_le32(new_encode_dev(sbi->log->bdev->bd_dev)); + j_sb->s_logdev = cpu_to_le32( + new_encode_dev(sbi->log->bdev_handle->bdev->bd_dev)); j_sb->s_logserial = cpu_to_le32(sbi->log->serial); } else if (state == FM_CLEAN) { /* diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h index 0d33816d251d..ec67d8554d2c 100644 --- a/fs/jfs/jfs_xattr.h +++ b/fs/jfs/jfs_xattr.h @@ -46,7 +46,7 @@ extern int __jfs_setxattr(tid_t, struct inode *, const char *, const void *, extern ssize_t __jfs_getxattr(struct inode *, const char *, void *, size_t); extern ssize_t jfs_listxattr(struct dentry *, char *, size_t); -extern const struct xattr_handler *jfs_xattr_handlers[]; +extern const struct xattr_handler * const jfs_xattr_handlers[]; #ifdef CONFIG_JFS_SECURITY extern int jfs_init_security(tid_t, struct inode *, struct inode *, diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 57d7a4300210..d68a4e6ac345 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -149,7 +149,7 @@ static int jfs_create(struct mnt_idmap *idmap, struct inode *dip, mark_inode_dirty(ip); - dip->i_mtime = inode_set_ctime_current(dip); + inode_set_mtime_to_ts(dip, inode_set_ctime_current(dip)); mark_inode_dirty(dip); @@ -284,7 +284,7 @@ static int jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, /* update parent directory inode */ inc_nlink(dip); /* for '..' from child directory */ - dip->i_mtime = inode_set_ctime_current(dip); + inode_set_mtime_to_ts(dip, inode_set_ctime_current(dip)); mark_inode_dirty(dip); rc = txCommit(tid, 2, &iplist[0], 0); @@ -390,7 +390,7 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry) /* update parent directory's link count corresponding * to ".." entry of the target directory deleted */ - dip->i_mtime = inode_set_ctime_current(dip); + inode_set_mtime_to_ts(dip, inode_set_ctime_current(dip)); inode_dec_link_count(dip); /* @@ -512,7 +512,8 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) ASSERT(ip->i_nlink); - dip->i_mtime = inode_set_ctime_to_ts(dip, inode_set_ctime_current(ip)); + inode_set_mtime_to_ts(dip, + inode_set_ctime_to_ts(dip, inode_set_ctime_current(ip))); mark_inode_dirty(dip); /* update target's inode */ @@ -828,7 +829,7 @@ static int jfs_link(struct dentry *old_dentry, /* update object inode */ inc_nlink(ip); /* for new link */ inode_set_ctime_current(ip); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); ihold(ip); @@ -1028,7 +1029,7 @@ static int jfs_symlink(struct mnt_idmap *idmap, struct inode *dip, mark_inode_dirty(ip); - dip->i_mtime = inode_set_ctime_current(dip); + inode_set_mtime_to_ts(dip, inode_set_ctime_current(dip)); mark_inode_dirty(dip); /* * commit update of parent directory and link object @@ -1271,7 +1272,7 @@ static int jfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, inode_set_ctime_current(old_ip); mark_inode_dirty(old_ip); - new_dir->i_mtime = inode_set_ctime_current(new_dir); + inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); mark_inode_dirty(new_dir); /* Build list of inodes modified by this transaction */ @@ -1283,7 +1284,8 @@ static int jfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (old_dir != new_dir) { iplist[ipcount++] = new_dir; - old_dir->i_mtime = inode_set_ctime_current(old_dir); + inode_set_mtime_to_ts(old_dir, + inode_set_ctime_current(old_dir)); mark_inode_dirty(old_dir); } @@ -1416,7 +1418,7 @@ static int jfs_mknod(struct mnt_idmap *idmap, struct inode *dir, mark_inode_dirty(ip); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 2e2f7f6d36a0..966826c394ee 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -818,7 +818,7 @@ out: } if (inode->i_size < off+len-towrite) i_size_write(inode, off+len-towrite); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); inode_unlock(inode); return len - towrite; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 8577ad494e05..0fb7afac298e 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -985,7 +985,7 @@ static const struct xattr_handler jfs_trusted_xattr_handler = { .set = jfs_xattr_set, }; -const struct xattr_handler *jfs_xattr_handlers[] = { +const struct xattr_handler * const jfs_xattr_handlers[] = { &jfs_os2_xattr_handler, &jfs_user_xattr_handler, &jfs_security_xattr_handler, diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 922719a343a7..b83054da68b3 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -151,7 +151,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) static inline void set_default_inode_attr(struct inode *inode, umode_t mode) { inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } static inline void set_inode_attr(struct inode *inode, @@ -159,8 +159,8 @@ static inline void set_inode_attr(struct inode *inode, { inode->i_uid = attrs->ia_uid; inode->i_gid = attrs->ia_gid; - inode->i_atime = attrs->ia_atime; - inode->i_mtime = attrs->ia_mtime; + inode_set_atime_to_ts(inode, attrs->ia_atime); + inode_set_mtime_to_ts(inode, attrs->ia_mtime); inode_set_ctime_to_ts(inode, attrs->ia_ctime); } @@ -445,7 +445,7 @@ static const struct xattr_handler kernfs_user_xattr_handler = { .set = kernfs_vfs_user_xattr_set, }; -const struct xattr_handler *kernfs_xattr_handlers[] = { +const struct xattr_handler * const kernfs_xattr_handlers[] = { &kernfs_trusted_xattr_handler, &kernfs_security_xattr_handler, &kernfs_user_xattr_handler, diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index a9b854cdfdb5..237f2764b941 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -127,7 +127,7 @@ extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c */ -extern const struct xattr_handler *kernfs_xattr_handlers[]; +extern const struct xattr_handler * const kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); int kernfs_iop_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); diff --git a/fs/libfs.c b/fs/libfs.c index a4eb12757886..abe2b5a40ba1 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -541,7 +541,8 @@ void simple_recursive_removal(struct dentry *dentry, dput(victim); // unpin it } if (victim == dentry) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); if (d_is_dir(dentry)) drop_nlink(inode); inode_unlock(inode); @@ -582,7 +583,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; - root->i_atime = root->i_mtime = inode_set_ctime_current(root); + simple_inode_init_ts(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; @@ -638,8 +639,8 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den { struct inode *inode = d_inode(old_dentry); - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inc_nlink(inode); ihold(inode); dget(dentry); @@ -673,8 +674,8 @@ int simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); drop_nlink(inode); dput(dentry); return 0; @@ -709,9 +710,10 @@ void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, { struct inode *newino = d_inode(new_dentry); - old_dir->i_mtime = inode_set_ctime_current(old_dir); + inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (new_dir != old_dir) - new_dir->i_mtime = inode_set_ctime_current(new_dir); + inode_set_mtime_to_ts(new_dir, + inode_set_ctime_current(new_dir)); inode_set_ctime_current(d_inode(old_dentry)); if (newino) inode_set_ctime_current(newino); @@ -926,7 +928,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic, */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); @@ -952,7 +954,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic, goto out; } inode->i_mode = S_IFREG | files->mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_fop = files->ops; inode->i_ino = i; d_add(dentry, inode); @@ -1520,7 +1522,7 @@ struct inode *alloc_anon_inode(struct super_block *s) inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); @@ -1903,6 +1905,7 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ + iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; @@ -1911,3 +1914,20 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, return direct_written + buffered_written; } EXPORT_SYMBOL_GPL(direct_write_fallback); + +/** + * simple_inode_init_ts - initialize the timestamps for a new inode + * @inode: inode to be initialized + * + * When a new inode is created, most filesystems set the timestamps to the + * current time. Add a helper to do this. + */ +struct timespec64 simple_inode_init_ts(struct inode *inode) +{ + struct timespec64 ts = inode_set_ctime_current(inode); + + inode_set_atime_to_ts(inode, ts); + inode_set_mtime_to_ts(inode, ts); + return ts; +} +EXPORT_SYMBOL(simple_inode_init_ts); diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 6579948070a4..81be07c1d3d1 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -24,7 +24,6 @@ #include <linux/uio.h> #include <linux/smp.h> #include <linux/mutex.h> -#include <linux/kthread.h> #include <linux/freezer.h> #include <linux/inetdevice.h> @@ -135,11 +134,11 @@ lockd(void *vrqstp) * The main request loop. We don't terminate until the last * NFS mount or NFS daemon has gone away. */ - while (!kthread_should_stop()) { + while (!svc_thread_should_stop(rqstp)) { /* update sv_maxconn if it has changed */ rqstp->rq_server->sv_maxconn = nlm_max_connections; - nlmsvc_retry_blocked(); + nlmsvc_retry_blocked(rqstp); svc_recv(rqstp); } if (nlmsvc_ops) @@ -373,7 +372,9 @@ static void lockd_put(void) unregister_inet6addr_notifier(&lockd_inet6addr_notifier); #endif + svc_get(nlmsvc_serv); svc_set_num_threads(nlmsvc_serv, NULL, 0); + svc_put(nlmsvc_serv); timer_delete_sync(&nlmsvc_retry); nlmsvc_serv = NULL; dprintk("lockd_down: service destroyed\n"); diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 43aeba9de55c..2dc10900ad1c 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -30,7 +30,6 @@ #include <linux/sunrpc/svc_xprt.h> #include <linux/lockd/nlm.h> #include <linux/lockd/lockd.h> -#include <linux/kthread.h> #include <linux/exportfs.h> #define NLMDBG_FACILITY NLMDBG_SVCLOCK @@ -481,9 +480,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, struct nlm_host *host, struct nlm_lock *lock, int wait, struct nlm_cookie *cookie, int reclaim) { -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct inode *inode = nlmsvc_file_inode(file); -#endif struct nlm_block *block = NULL; int error; int mode; @@ -497,7 +494,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, (long long)lock->fl.fl_end, wait); - if (nlmsvc_file_file(file)->f_op->lock) { + if (!exportfs_lock_op_is_async(inode->i_sb->s_export_op)) { async_block = wait; wait = 0; } @@ -543,6 +540,25 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } + spin_lock(&nlm_blocked_lock); + /* + * If this is a lock request for an already pending + * lock request we return nlm_lck_blocked without calling + * vfs_lock_file() again. Otherwise we have two pending + * requests on the underlaying ->lock() implementation but + * only one nlm_block to being granted by lm_grant(). + */ + if (exportfs_lock_op_is_async(inode->i_sb->s_export_op) && + !list_empty(&block->b_list)) { + spin_unlock(&nlm_blocked_lock); + ret = nlm_lck_blocked; + goto out; + } + + /* Append to list of blocked */ + nlmsvc_insert_block_locked(block, NLM_NEVER); + spin_unlock(&nlm_blocked_lock); + if (!wait) lock->fl.fl_flags &= ~FL_SLEEP; mode = lock_to_openmode(&lock->fl); @@ -552,16 +568,12 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, dprintk("lockd: vfs_lock_file returned %d\n", error); switch (error) { case 0: + nlmsvc_remove_block(block); ret = nlm_granted; goto out; case -EAGAIN: - /* - * If this is a blocking request for an - * already pending lock request then we need - * to put it back on lockd's block list - */ - if (wait) - break; + if (!wait) + nlmsvc_remove_block(block); ret = async_block ? nlm_lck_blocked : nlm_lck_denied; goto out; case FILE_LOCK_DEFERRED: @@ -572,17 +584,16 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, ret = nlmsvc_defer_lock_rqst(rqstp, block); goto out; case -EDEADLK: + nlmsvc_remove_block(block); ret = nlm_deadlock; goto out; default: /* includes ENOLCK */ + nlmsvc_remove_block(block); ret = nlm_lck_denied_nolocks; goto out; } ret = nlm_lck_blocked; - - /* Append to list of blocked */ - nlmsvc_insert_block(block, NLM_NEVER); out: mutex_unlock(&file->f_mutex); nlmsvc_release_block(block); @@ -1020,13 +1031,13 @@ retry_deferred_block(struct nlm_block *block) * be retransmitted. */ void -nlmsvc_retry_blocked(void) +nlmsvc_retry_blocked(struct svc_rqst *rqstp) { unsigned long timeout = MAX_SCHEDULE_TIMEOUT; struct nlm_block *block; spin_lock(&nlm_blocked_lock); - while (!list_empty(&nlm_blocked) && !kthread_should_stop()) { + while (!list_empty(&nlm_blocked) && !svc_thread_should_stop(rqstp)) { block = list_entry(nlm_blocked.next, struct nlm_block, b_list); if (block->b_when == NLM_NEVER) diff --git a/fs/locks.c b/fs/locks.c index 76ad05f8070a..d4e49a990a8d 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2264,11 +2264,13 @@ out: * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) - * lm_grant is set. Callers expecting ->lock() to return asynchronously - * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if) - * the request is for a blocking lock. When ->lock() does return asynchronously, - * it must return FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock - * request completes. + * lm_grant is set. Additionally EXPORT_OP_ASYNC_LOCK in export_operations + * flags need to be set. + * + * Callers expecting ->lock() to return asynchronously will only use F_SETLK, + * not F_SETLKW; they will set FL_SLEEP if (and only if) the request is for a + * blocking lock. When ->lock() does return asynchronously, it must return + * FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine * with the result. If the request timed out the callback routine will return a diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index 25c08fbfcb9d..7da66ca184f4 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -251,7 +251,7 @@ struct inode *minix_new_inode(const struct inode *dir, umode_t mode) } inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = j; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_blocks = 0; memset(&minix_i(inode)->u, 0, sizeof(minix_i(inode)->u)); insert_inode_hash(inode); diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 20f23e6e58ad..62c313fc9a49 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -281,7 +281,7 @@ got_it: de->inode = inode->i_ino; } dir_commit_chunk(page, pos, sbi->s_dirsize); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); err = minix_handle_dirsync(dir); out_put: @@ -313,7 +313,7 @@ int minix_delete_entry(struct minix_dir_entry *de, struct page *page) else de->inode = 0; dir_commit_chunk(page, pos, len); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); return minix_handle_dirsync(inode); } @@ -436,7 +436,7 @@ int minix_set_link(struct minix_dir_entry *de, struct page *page, else de->inode = inode->i_ino; dir_commit_chunk(page, pos, sbi->s_dirsize); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); return minix_handle_dirsync(dir); } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index df575473c1cc..f8af6c3ae336 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -501,7 +501,8 @@ static struct inode *V1_minix_iget(struct inode *inode) i_gid_write(inode, raw_inode->i_gid); set_nlink(inode, raw_inode->i_nlinks); inode->i_size = raw_inode->i_size; - inode->i_mtime = inode->i_atime = inode_set_ctime(inode, raw_inode->i_time, 0); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime(inode, raw_inode->i_time, 0))); inode->i_blocks = 0; for (i = 0; i < 9; i++) minix_inode->u.i1_data[i] = raw_inode->i_zone[i]; @@ -538,11 +539,9 @@ static struct inode *V2_minix_iget(struct inode *inode) i_gid_write(inode, raw_inode->i_gid); set_nlink(inode, raw_inode->i_nlinks); inode->i_size = raw_inode->i_size; - inode->i_mtime.tv_sec = raw_inode->i_mtime; - inode->i_atime.tv_sec = raw_inode->i_atime; + inode_set_mtime(inode, raw_inode->i_mtime, 0); + inode_set_atime(inode, raw_inode->i_atime, 0); inode_set_ctime(inode, raw_inode->i_ctime, 0); - inode->i_mtime.tv_nsec = 0; - inode->i_atime.tv_nsec = 0; inode->i_blocks = 0; for (i = 0; i < 10; i++) minix_inode->u.i2_data[i] = raw_inode->i_zone[i]; @@ -589,7 +588,7 @@ static struct buffer_head * V1_minix_update_inode(struct inode * inode) raw_inode->i_gid = fs_high2lowgid(i_gid_read(inode)); raw_inode->i_nlinks = inode->i_nlink; raw_inode->i_size = inode->i_size; - raw_inode->i_time = inode->i_mtime.tv_sec; + raw_inode->i_time = inode_get_mtime_sec(inode); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) raw_inode->i_zone[0] = old_encode_dev(inode->i_rdev); else for (i = 0; i < 9; i++) @@ -616,9 +615,9 @@ static struct buffer_head * V2_minix_update_inode(struct inode * inode) raw_inode->i_gid = fs_high2lowgid(i_gid_read(inode)); raw_inode->i_nlinks = inode->i_nlink; raw_inode->i_size = inode->i_size; - raw_inode->i_mtime = inode->i_mtime.tv_sec; - raw_inode->i_atime = inode->i_atime.tv_sec; - raw_inode->i_ctime = inode_get_ctime(inode).tv_sec; + raw_inode->i_mtime = inode_get_mtime_sec(inode); + raw_inode->i_atime = inode_get_atime_sec(inode); + raw_inode->i_ctime = inode_get_ctime_sec(inode); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) raw_inode->i_zone[0] = old_encode_dev(inode->i_rdev); else for (i = 0; i < 10; i++) diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c index ce18ae37c29d..dad131e30c05 100644 --- a/fs/minix/itree_common.c +++ b/fs/minix/itree_common.c @@ -350,7 +350,7 @@ do_indirects: } first_whole++; } - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); } diff --git a/fs/namei.c b/fs/namei.c index 567ee547492b..71c13b2990b4 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -188,7 +188,7 @@ getname_flags(const char __user *filename, int flags, int *empty) } } - result->refcnt = 1; + atomic_set(&result->refcnt, 1); /* The empty path is special. */ if (unlikely(!len)) { if (empty) @@ -249,7 +249,7 @@ getname_kernel(const char * filename) memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; - result->refcnt = 1; + atomic_set(&result->refcnt, 1); audit_getname(result); return result; @@ -261,9 +261,10 @@ void putname(struct filename *name) if (IS_ERR(name)) return; - BUG_ON(name->refcnt <= 0); + if (WARN_ON_ONCE(!atomic_read(&name->refcnt))) + return; - if (--name->refcnt > 0) + if (!atomic_dec_and_test(&name->refcnt)) return; if (name->name != name->iname) { @@ -3104,25 +3105,6 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) EXPORT_SYMBOL(unlock_rename); /** - * mode_strip_umask - handle vfs umask stripping - * @dir: parent directory of the new inode - * @mode: mode of the new inode to be created in @dir - * - * Umask stripping depends on whether or not the filesystem supports POSIX - * ACLs. If the filesystem doesn't support it umask stripping is done directly - * in here. If the filesystem does support POSIX ACLs umask stripping is - * deferred until the filesystem calls posix_acl_create(). - * - * Returns: mode - */ -static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) -{ - if (!IS_POSIXACL(dir)) - mode &= ~current_umask(); - return mode; -} - -/** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode @@ -3535,7 +3517,8 @@ static const char *open_last_lookups(struct nameidata *nd, if (likely(dentry)) goto finish_lookup; - BUG_ON(nd->flags & LOOKUP_RCU); + if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU)) + return ERR_PTR(-ECHILD); } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { @@ -3802,7 +3785,10 @@ static struct file *path_openat(struct nameidata *nd, WARN_ON(1); error = -EINVAL; } - fput(file); + if (unlikely(file->f_mode & FMODE_OPENED)) + fput(file); + else + release_empty_file(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; @@ -4386,11 +4372,9 @@ retry_deleg: if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ - if (last.name[last.len]) + if (last.name[last.len] || d_is_negative(dentry)) goto slashes; inode = dentry->d_inode; - if (d_is_negative(dentry)) - goto slashes; ihold(inode); error = security_path_unlink(&path, dentry); if (error) diff --git a/fs/namespace.c b/fs/namespace.c index e157efc54023..6bde71735efa 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -330,16 +330,16 @@ static int mnt_is_readonly(struct vfsmount *mnt) * can determine when writes are able to occur to a filesystem. */ /** - * __mnt_want_write - get write access to a mount without freeze protection + * mnt_get_write_access - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being - * frozen. When the write operation is finished, __mnt_drop_write() must be + * frozen. When the write operation is finished, mnt_put_write_access() must be * called. This is effectively a refcount. */ -int __mnt_want_write(struct vfsmount *m) +int mnt_get_write_access(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; @@ -386,6 +386,7 @@ int __mnt_want_write(struct vfsmount *m) return ret; } +EXPORT_SYMBOL_GPL(mnt_get_write_access); /** * mnt_want_write - get write access to a mount @@ -401,7 +402,7 @@ int mnt_want_write(struct vfsmount *m) int ret; sb_start_write(m->mnt_sb); - ret = __mnt_want_write(m); + ret = mnt_get_write_access(m); if (ret) sb_end_write(m->mnt_sb); return ret; @@ -409,15 +410,15 @@ int mnt_want_write(struct vfsmount *m) EXPORT_SYMBOL_GPL(mnt_want_write); /** - * __mnt_want_write_file - get write access to a file's mount + * mnt_get_write_access_file - get write access to a file's mount * @file: the file who's mount on which to take a write * - * This is like __mnt_want_write, but if the file is already open for writing it + * This is like mnt_get_write_access, but if @file is already open for write it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be - * paired with __mnt_drop_write_file. + * paired with mnt_put_write_access_file. */ -int __mnt_want_write_file(struct file *file) +int mnt_get_write_access_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* @@ -428,7 +429,7 @@ int __mnt_want_write_file(struct file *file) return -EROFS; return 0; } - return __mnt_want_write(file->f_path.mnt); + return mnt_get_write_access(file->f_path.mnt); } /** @@ -445,7 +446,7 @@ int mnt_want_write_file(struct file *file) int ret; sb_start_write(file_inode(file)->i_sb); - ret = __mnt_want_write_file(file); + ret = mnt_get_write_access_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; @@ -453,19 +454,20 @@ int mnt_want_write_file(struct file *file) EXPORT_SYMBOL_GPL(mnt_want_write_file); /** - * __mnt_drop_write - give up write access to a mount + * mnt_put_write_access - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with - * __mnt_want_write() call above. + * mnt_get_write_access() call above. */ -void __mnt_drop_write(struct vfsmount *mnt) +void mnt_put_write_access(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } +EXPORT_SYMBOL_GPL(mnt_put_write_access); /** * mnt_drop_write - give up write access to a mount @@ -477,20 +479,20 @@ void __mnt_drop_write(struct vfsmount *mnt) */ void mnt_drop_write(struct vfsmount *mnt) { - __mnt_drop_write(mnt); + mnt_put_write_access(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); -void __mnt_drop_write_file(struct file *file) +void mnt_put_write_access_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) - __mnt_drop_write(file->f_path.mnt); + mnt_put_write_access(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { - __mnt_drop_write_file(file); + mnt_put_write_access_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); @@ -1344,9 +1346,9 @@ void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); - /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ + /* avoid cacheline pingpong */ if (unlikely(m->mnt_expiry_mark)) - m->mnt_expiry_mark = 0; + WRITE_ONCE(m->mnt_expiry_mark, 0); mntput_no_expire(m); } } diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index 716bc75e9ed2..b4294a8aa2d4 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -108,7 +108,7 @@ struct pnfs_block_dev { struct pnfs_block_dev *children; u64 chunk_size; - struct block_device *bdev; + struct bdev_handle *bdev_handle; u64 disk_offset; u64 pr_key; diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index 65cbb5607a5f..f318a05a80e1 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -25,17 +25,17 @@ bl_free_device(struct pnfs_block_dev *dev) } else { if (dev->pr_registered) { const struct pr_ops *ops = - dev->bdev->bd_disk->fops->pr_ops; + dev->bdev_handle->bdev->bd_disk->fops->pr_ops; int error; - error = ops->pr_register(dev->bdev, dev->pr_key, 0, - false); + error = ops->pr_register(dev->bdev_handle->bdev, + dev->pr_key, 0, false); if (error) pr_err("failed to unregister PR key.\n"); } - if (dev->bdev) - blkdev_put(dev->bdev, NULL); + if (dev->bdev_handle) + bdev_release(dev->bdev_handle); } } @@ -169,7 +169,7 @@ static bool bl_map_simple(struct pnfs_block_dev *dev, u64 offset, map->start = dev->start; map->len = dev->len; map->disk_offset = dev->disk_offset; - map->bdev = dev->bdev; + map->bdev = dev->bdev_handle->bdev; return true; } @@ -236,28 +236,26 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) { struct pnfs_block_volume *v = &volumes[idx]; - struct block_device *bdev; + struct bdev_handle *bdev_handle; dev_t dev; dev = bl_resolve_deviceid(server, v, gfp_mask); if (!dev) return -EIO; - bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, - NULL); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, + NULL, NULL); + if (IS_ERR(bdev_handle)) { printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n", - MAJOR(dev), MINOR(dev), PTR_ERR(bdev)); - return PTR_ERR(bdev); + MAJOR(dev), MINOR(dev), PTR_ERR(bdev_handle)); + return PTR_ERR(bdev_handle); } - d->bdev = bdev; - - - d->len = bdev_nr_bytes(d->bdev); + d->bdev_handle = bdev_handle; + d->len = bdev_nr_bytes(bdev_handle->bdev); d->map = bl_map_simple; printk(KERN_INFO "pNFS: using block device %s\n", - d->bdev->bd_disk->disk_name); + bdev_handle->bdev->bd_disk->disk_name); return 0; } @@ -302,10 +300,10 @@ bl_validate_designator(struct pnfs_block_volume *v) } } -static struct block_device * +static struct bdev_handle * bl_open_path(struct pnfs_block_volume *v, const char *prefix) { - struct block_device *bdev; + struct bdev_handle *bdev_handle; const char *devname; devname = kasprintf(GFP_KERNEL, "/dev/disk/by-id/%s%*phN", @@ -313,15 +311,15 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix) if (!devname) return ERR_PTR(-ENOMEM); - bdev = blkdev_get_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, - NULL); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, + NULL, NULL); + if (IS_ERR(bdev_handle)) { pr_warn("pNFS: failed to open device %s (%ld)\n", - devname, PTR_ERR(bdev)); + devname, PTR_ERR(bdev_handle)); } kfree(devname); - return bdev; + return bdev_handle; } static int @@ -329,7 +327,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, struct pnfs_block_volume *volumes, int idx, gfp_t gfp_mask) { struct pnfs_block_volume *v = &volumes[idx]; - struct block_device *bdev; + struct bdev_handle *bdev_handle; const struct pr_ops *ops; int error; @@ -342,32 +340,32 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, * On other distributions like Debian, the default SCSI by-id path will * point to the dm-multipath device if one exists. */ - bdev = bl_open_path(v, "dm-uuid-mpath-0x"); - if (IS_ERR(bdev)) - bdev = bl_open_path(v, "wwn-0x"); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - d->bdev = bdev; - - d->len = bdev_nr_bytes(d->bdev); + bdev_handle = bl_open_path(v, "dm-uuid-mpath-0x"); + if (IS_ERR(bdev_handle)) + bdev_handle = bl_open_path(v, "wwn-0x"); + if (IS_ERR(bdev_handle)) + return PTR_ERR(bdev_handle); + d->bdev_handle = bdev_handle; + + d->len = bdev_nr_bytes(d->bdev_handle->bdev); d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; pr_info("pNFS: using block device %s (reservation key 0x%llx)\n", - d->bdev->bd_disk->disk_name, d->pr_key); + d->bdev_handle->bdev->bd_disk->disk_name, d->pr_key); - ops = d->bdev->bd_disk->fops->pr_ops; + ops = d->bdev_handle->bdev->bd_disk->fops->pr_ops; if (!ops) { pr_err("pNFS: block device %s does not support reservations.", - d->bdev->bd_disk->disk_name); + d->bdev_handle->bdev->bd_disk->disk_name); error = -EINVAL; goto out_blkdev_put; } - error = ops->pr_register(d->bdev, 0, d->pr_key, true); + error = ops->pr_register(d->bdev_handle->bdev, 0, d->pr_key, true); if (error) { pr_err("pNFS: failed to register key for block device %s.", - d->bdev->bd_disk->disk_name); + d->bdev_handle->bdev->bd_disk->disk_name); goto out_blkdev_put; } @@ -375,7 +373,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, return 0; out_blkdev_put: - blkdev_put(d->bdev, NULL); + bdev_release(d->bdev_handle); return error; } diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 466ebf1d41b2..4ffa1f469e90 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -78,7 +78,7 @@ nfs4_callback_svc(void *vrqstp) set_freezable(); - while (!kthread_freezable_should_stop(NULL)) + while (!svc_thread_should_stop(rqstp)) svc_recv(rqstp); svc_exit_thread(rqstp); @@ -86,45 +86,6 @@ nfs4_callback_svc(void *vrqstp) } #if defined(CONFIG_NFS_V4_1) -/* - * The callback service for NFSv4.1 callbacks - */ -static int -nfs41_callback_svc(void *vrqstp) -{ - struct svc_rqst *rqstp = vrqstp; - struct svc_serv *serv = rqstp->rq_server; - struct rpc_rqst *req; - int error; - DEFINE_WAIT(wq); - - set_freezable(); - - while (!kthread_freezable_should_stop(NULL)) { - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_IDLE); - spin_lock_bh(&serv->sv_cb_lock); - if (!list_empty(&serv->sv_cb_list)) { - req = list_first_entry(&serv->sv_cb_list, - struct rpc_rqst, rq_bc_list); - list_del(&req->rq_bc_list); - spin_unlock_bh(&serv->sv_cb_lock); - finish_wait(&serv->sv_cb_waitq, &wq); - dprintk("Invoking bc_svc_process()\n"); - error = bc_svc_process(serv, req, rqstp); - dprintk("bc_svc_process() returned w/ error code= %d\n", - error); - } else { - spin_unlock_bh(&serv->sv_cb_lock); - if (!kthread_should_stop()) - schedule(); - finish_wait(&serv->sv_cb_waitq, &wq); - } - } - - svc_exit_thread(rqstp); - return 0; -} - static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt, struct svc_serv *serv) { @@ -237,10 +198,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) cb_info->users); threadfn = nfs4_callback_svc; -#if defined(CONFIG_NFS_V4_1) - if (minorversion) - threadfn = nfs41_callback_svc; -#else +#if !defined(CONFIG_NFS_V4_1) if (minorversion) return ERR_PTR(-ENOTSUPP); #endif diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 6bed1394d748..96a4923080ae 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -60,7 +60,7 @@ __be32 nfs4_callback_getattr(void *argp, void *resp, if (nfs_have_writebacks(inode)) res->change_attr++; res->ctime = inode_get_ctime(inode); - res->mtime = inode->i_mtime; + res->mtime = inode_get_mtime(inode); res->bitmap[0] = (FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE) & args->bitmap[0]; res->bitmap[1] = (FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY) & diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a1dc33864906..ef817a0475ff 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2520,9 +2520,9 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, return i; } -static int -ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) +static int ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) { + struct pnfs_layout_hdr *lo; struct nfs4_flexfile_layout *ff_layout; const int dev_count = PNFS_LAYOUTSTATS_MAXDEV; @@ -2533,11 +2533,14 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) return -ENOMEM; spin_lock(&args->inode->i_lock); - ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout); - args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr, - &args->devinfo[0], - dev_count, - NFS4_FF_OP_LAYOUTSTATS); + lo = NFS_I(args->inode)->layout; + if (lo && pnfs_layout_is_valid(lo)) { + ff_layout = FF_LAYOUT_FROM_HDR(lo); + args->num_dev = ff_layout_mirror_prepare_stats( + &ff_layout->generic_hdr, &args->devinfo[0], dev_count, + NFS4_FF_OP_LAYOUTSTATS); + } else + args->num_dev = 0; spin_unlock(&args->inode->i_lock); if (!args->num_dev) { kfree(args->devinfo); diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 2dc64454492b..5407ab8c8783 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -114,8 +114,8 @@ static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata * struct inode *inode) { memset(auxdata, 0, sizeof(*auxdata)); - auxdata->mtime_sec = inode->i_mtime.tv_sec; - auxdata->mtime_nsec = inode->i_mtime.tv_nsec; + auxdata->mtime_sec = inode_get_mtime(inode).tv_sec; + auxdata->mtime_nsec = inode_get_mtime(inode).tv_nsec; auxdata->ctime_sec = inode_get_ctime(inode).tv_sec; auxdata->ctime_nsec = inode_get_ctime(inode).tv_nsec; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e21c073158e5..ebb8d60e1152 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -512,8 +512,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) } else init_special_inode(inode, inode->i_mode, fattr->rdev); - memset(&inode->i_atime, 0, sizeof(inode->i_atime)); - memset(&inode->i_mtime, 0, sizeof(inode->i_mtime)); + inode_set_atime(inode, 0, 0); + inode_set_mtime(inode, 0, 0); inode_set_ctime(inode, 0, 0); inode_set_iversion_raw(inode, 0); inode->i_size = 0; @@ -527,11 +527,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = fattr->atime; + inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = fattr->mtime; + inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) @@ -742,9 +742,9 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = fattr->atime; + inode_set_atime_to_ts(inode, fattr->atime); else if (attr->ia_valid & ATTR_ATIME_SET) - inode->i_atime = attr->ia_atime; + inode_set_atime_to_ts(inode, attr->ia_atime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); @@ -758,9 +758,9 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = fattr->mtime; + inode_set_mtime_to_ts(inode, fattr->mtime); else if (attr->ia_valid & ATTR_MTIME_SET) - inode->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(inode, attr->ia_mtime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); @@ -1451,11 +1451,11 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode_set_ctime_to_ts(inode, fattr->ctime); } - ts = inode->i_mtime; + ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec64_equal(&ts, &fattr->pre_mtime)) { - inode->i_mtime = fattr->mtime; + inode_set_mtime_to_ts(inode, fattr->mtime); } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) @@ -1506,7 +1506,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr)) invalid |= NFS_INO_INVALID_CHANGE; - ts = inode->i_mtime; + ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; @@ -1534,7 +1534,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_NLINK; - ts = inode->i_atime; + ts = inode_get_atime(inode); if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; @@ -2002,7 +2002,7 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { - fattr->pre_mtime = inode->i_mtime; + fattr->pre_mtime = inode_get_mtime(inode); fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && @@ -2184,7 +2184,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = fattr->mtime; + inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MTIME; @@ -2220,7 +2220,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) save_cache_validity & NFS_INO_INVALID_SIZE; if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = fattr->atime; + inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATIME; diff --git a/fs/nfs/nfs.h b/fs/nfs/nfs.h index 5ba00610aede..0d3ce0460e35 100644 --- a/fs/nfs/nfs.h +++ b/fs/nfs/nfs.h @@ -18,7 +18,7 @@ struct nfs_subversion { const struct rpc_version *rpc_vers; /* NFS version information */ const struct nfs_rpc_ops *rpc_ops; /* NFS operations */ const struct super_operations *sops; /* NFS Super operations */ - const struct xattr_handler **xattr; /* NFS xattr handlers */ + const struct xattr_handler * const *xattr; /* NFS xattr handlers */ struct list_head list; /* List of NFS versions */ }; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 063e00aff87e..28704f924612 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -81,7 +81,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, if (status == 0) { if (nfs_should_remove_suid(inode)) { spin_lock(&inode->i_lock); - nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + nfs_set_cache_invalid(inode, + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_MODE); spin_unlock(&inode->i_lock); } status = nfs_post_op_update_inode_force_wcc(inode, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 47c5c1f86d66..827d00e2f094 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -315,7 +315,7 @@ extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct nfs_fh *, struct nfs_fattr *); extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); -extern const struct xattr_handler *nfs4_xattr_handlers[]; +extern const struct xattr_handler * const nfs4_xattr_handlers[]; extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3508d8238826..a654d7234f51 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8870,8 +8870,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre /* Save the EXCHANGE_ID verifier session trunk tests */ memcpy(clp->cl_confirm.data, argp->verifier.data, sizeof(clp->cl_confirm.data)); - if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS) - set_bit(NFS_CS_DS, &clp->cl_flags); out: trace_nfs4_exchange_id(clp, status); rpc_put_task(task); @@ -10622,7 +10620,9 @@ static void nfs4_disable_swap(struct inode *inode) */ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + wake_up_var(&clp->cl_state); } static const struct inode_operations nfs4_dir_inode_operations = { @@ -10737,7 +10737,7 @@ static const struct xattr_handler nfs4_xattr_nfs4_user_handler = { }; #endif -const struct xattr_handler *nfs4_xattr_handlers[] = { +const struct xattr_handler * const nfs4_xattr_handlers[] = { &nfs4_xattr_nfs4_acl_handler, #if defined(CONFIG_NFS_V4_1) &nfs4_xattr_nfs4_dacl_handler, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e079987af4a3..9a5d911a7edc 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *clnt = clp->cl_rpcclient; + bool swapon = false; - if (clp->cl_rpcclient->cl_shutdown) + if (clnt->cl_shutdown) return; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { - wake_up_var(&clp->cl_state); - return; + + if (atomic_read(&clnt->cl_swapper)) { + swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, + &clp->cl_state); + if (!swapon) { + wake_up_var(&clp->cl_state); + return; + } } - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) __func__, PTR_ERR(task)); if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); + if (swapon) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs4_clear_state_manager_bit(clp); - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2703,6 +2714,13 @@ static void nfs4_state_manager(struct nfs_client *clp) nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); + if (test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, + &clp->cl_state)) { + memflags = memalloc_nofs_save(); + continue; + } + if (!test_and_set_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state)) { if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) { nfs_client_return_marked_delegations(clp); @@ -2741,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); again: - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); - if (atomic_read(&cl->cl_swapper)) { + + if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) && + !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) { wait_var_event_interruptible(&clp->cl_state, test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)); - if (atomic_read(&cl->cl_swapper) && - test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + if (!atomic_read(&cl->cl_swapper)) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; /* Either no longer a swapper, or were signalled */ + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); } - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); if (refcount_read(&clp->cl_count) > 1 && !signalled() && test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && - !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; nfs_put_client(clp); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 306cba0b9e69..84343aefbbd6 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2634,31 +2634,44 @@ pnfs_should_return_unused_layout(struct pnfs_layout_hdr *lo, return mode == 0; } -static int -pnfs_layout_return_unused_byserver(struct nfs_server *server, void *data) +static int pnfs_layout_return_unused_byserver(struct nfs_server *server, + void *data) { const struct pnfs_layout_range *range = data; + const struct cred *cred; struct pnfs_layout_hdr *lo; struct inode *inode; + nfs4_stateid stateid; + enum pnfs_iomode iomode; + restart: rcu_read_lock(); list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) { - if (!pnfs_layout_can_be_returned(lo) || + inode = lo->plh_inode; + if (!inode || !pnfs_layout_can_be_returned(lo) || test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) continue; - inode = lo->plh_inode; spin_lock(&inode->i_lock); - if (!pnfs_should_return_unused_layout(lo, range)) { + if (!lo->plh_inode || + !pnfs_should_return_unused_layout(lo, range)) { spin_unlock(&inode->i_lock); continue; } + pnfs_get_layout_hdr(lo); + pnfs_set_plh_return_info(lo, range->iomode, 0); + if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + range, 0) != 0 || + !pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + pnfs_put_layout_hdr(lo); + cond_resched(); + goto restart; + } spin_unlock(&inode->i_lock); - inode = pnfs_grab_inode_layout_hdr(lo); - if (!inode) - continue; rcu_read_unlock(); - pnfs_mark_layout_for_return(inode, range); - iput(inode); + pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false); + pnfs_put_layout_hdr(lo); cond_resched(); goto restart; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0d6473cb00cb..9b1cfca8112a 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1071,7 +1071,7 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx) sb->s_export_op = &nfs_export_ops; break; case 4: - sb->s_flags |= SB_POSIXACL; + sb->s_iflags |= SB_I_NOUMASK; sb->s_time_gran = 1; sb->s_time_min = S64_MIN; sb->s_time_max = S64_MAX; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 8c1ee1a1a28f..9d82d50ce0b1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -788,6 +788,8 @@ static void nfs_inode_add_request(struct nfs_page *req) */ static void nfs_inode_remove_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); + if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio_file_mapping(folio); @@ -802,8 +804,8 @@ static void nfs_inode_remove_request(struct nfs_page *req) } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { + atomic_long_dec(&nfsi->nrequests); nfs_release_request(req); - atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests); } } diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 6fffc8f03f74..b8736a82e57c 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -12,7 +12,8 @@ nfsd-y += trace.o nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ export.o auth.o lockd.o nfscache.o \ - stats.o filecache.o nfs3proc.o nfs3xdr.o + stats.o filecache.o nfs3proc.o nfs3xdr.o \ + netlink.o nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 01d7fd108cf3..46fd74d91ea9 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -117,12 +117,13 @@ static __be32 nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp, struct iomap *iomaps, int nr_iomaps) { + struct timespec64 mtime = inode_get_mtime(inode); loff_t new_size = lcp->lc_last_wr + 1; struct iattr iattr = { .ia_valid = 0 }; int error; if (lcp->lc_mtime.tv_nsec == UTIME_NOW || - timespec64_compare(&lcp->lc_mtime, &inode->i_mtime) < 0) + timespec64_compare(&lcp->lc_mtime, &mtime) < 0) lcp->lc_mtime = current_time(inode); iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME; iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime; diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 1ed2f691ebb9..ce78f74715ee 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -16,9 +16,9 @@ __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp) + const struct nfsd4_layoutget *lgp) { - struct pnfs_block_extent *b = lgp->lg_content; + const struct pnfs_block_extent *b = lgp->lg_content; int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32); __be32 *p; @@ -77,7 +77,7 @@ nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b) __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp) + const struct nfsd4_getdeviceinfo *gdp) { struct pnfs_block_deviceaddr *dev = gdp->gd_device; int len = sizeof(__be32), ret, i; diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h index bc5166bfe46b..b0361e8aa9a7 100644 --- a/fs/nfsd/blocklayoutxdr.h +++ b/fs/nfsd/blocklayoutxdr.h @@ -51,9 +51,9 @@ struct pnfs_block_deviceaddr { }; __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp); + const struct nfsd4_getdeviceinfo *gdp); __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp); + const struct nfsd4_layoutget *lgp); int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, u32 block_size); int nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 11a0eaa2f914..b7da17e53007 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -339,12 +339,16 @@ static int export_stats_init(struct export_stats *stats) static void export_stats_reset(struct export_stats *stats) { - nfsd_percpu_counters_reset(stats->counter, EXP_STATS_COUNTERS_NUM); + if (stats) + nfsd_percpu_counters_reset(stats->counter, + EXP_STATS_COUNTERS_NUM); } static void export_stats_destroy(struct export_stats *stats) { - nfsd_percpu_counters_destroy(stats->counter, EXP_STATS_COUNTERS_NUM); + if (stats) + nfsd_percpu_counters_destroy(stats->counter, + EXP_STATS_COUNTERS_NUM); } static void svc_export_put(struct kref *ref) @@ -353,7 +357,8 @@ static void svc_export_put(struct kref *ref) path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); - export_stats_destroy(&exp->ex_stats); + export_stats_destroy(exp->ex_stats); + kfree(exp->ex_stats); kfree(exp->ex_uuid); kfree_rcu(exp, ex_rcu); } @@ -767,13 +772,15 @@ static int svc_export_show(struct seq_file *m, seq_putc(m, '\t'); seq_escape(m, exp->ex_client->name, " \t\n\\"); if (export_stats) { - seq_printf(m, "\t%lld\n", exp->ex_stats.start_time); + struct percpu_counter *counter = exp->ex_stats->counter; + + seq_printf(m, "\t%lld\n", exp->ex_stats->start_time); seq_printf(m, "\tfh_stale: %lld\n", - percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_FH_STALE])); + percpu_counter_sum_positive(&counter[EXP_STATS_FH_STALE])); seq_printf(m, "\tio_read: %lld\n", - percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_READ])); + percpu_counter_sum_positive(&counter[EXP_STATS_IO_READ])); seq_printf(m, "\tio_write: %lld\n", - percpu_counter_sum_positive(&exp->ex_stats.counter[EXP_STATS_IO_WRITE])); + percpu_counter_sum_positive(&counter[EXP_STATS_IO_WRITE])); seq_putc(m, '\n'); return 0; } @@ -819,7 +826,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) new->ex_layout_types = 0; new->ex_uuid = NULL; new->cd = item->cd; - export_stats_reset(&new->ex_stats); + export_stats_reset(new->ex_stats); } static void export_update(struct cache_head *cnew, struct cache_head *citem) @@ -856,7 +863,14 @@ static struct cache_head *svc_export_alloc(void) if (!i) return NULL; - if (export_stats_init(&i->ex_stats)) { + i->ex_stats = kmalloc(sizeof(*(i->ex_stats)), GFP_KERNEL); + if (!i->ex_stats) { + kfree(i); + return NULL; + } + + if (export_stats_init(i->ex_stats)) { + kfree(i->ex_stats); kfree(i); return NULL; } diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 2df8ae25aad3..ca9dc230ae3d 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -64,10 +64,10 @@ struct svc_export { struct cache_head h; struct auth_domain * ex_client; int ex_flags; + int ex_fsid; struct path ex_path; kuid_t ex_anon_uid; kgid_t ex_anon_gid; - int ex_fsid; unsigned char * ex_uuid; /* 16 byte fsid */ struct nfsd4_fs_locations ex_fslocs; uint32_t ex_nflavors; @@ -76,8 +76,8 @@ struct svc_export { struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; struct rcu_head ex_rcu; - struct export_stats ex_stats; unsigned long ex_xprtsec_modes; + struct export_stats *ex_stats; }; /* an "export key" (expkey) maps a filehandlefragement to an diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index ee9c923192e0..07bf219f9ae4 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -989,22 +989,21 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned char need = may_flags & NFSD_FILE_MAY_MASK; struct net *net = SVC_NET(rqstp); struct nfsd_file *new, *nf; - const struct cred *cred; + bool stale_retry = true; bool open_retry = true; struct inode *inode; __be32 status; int ret; +retry: status = fh_verify(rqstp, fhp, S_IFREG, may_flags|NFSD_MAY_OWNER_OVERRIDE); if (status != nfs_ok) return status; inode = d_inode(fhp->fh_dentry); - cred = get_current_cred(); -retry: rcu_read_lock(); - nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); + nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc); rcu_read_unlock(); if (nf) { @@ -1026,7 +1025,7 @@ retry: rcu_read_lock(); spin_lock(&inode->i_lock); - nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); + nf = nfsd_file_lookup_locked(net, current_cred(), inode, need, want_gc); if (unlikely(nf)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); @@ -1058,6 +1057,7 @@ wait_for_construction: goto construction_err; } open_retry = false; + fh_put(fhp); goto retry; } this_cpu_inc(nfsd_file_cache_hits); @@ -1074,7 +1074,6 @@ out: nfsd_file_check_write_error(nf); *pnf = nf; } - put_cred(cred); trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; @@ -1088,8 +1087,20 @@ open_file: status = nfs_ok; trace_nfsd_file_opened(nf, status); } else { - status = nfsd_open_verified(rqstp, fhp, may_flags, - &nf->nf_file); + ret = nfsd_open_verified(rqstp, fhp, may_flags, + &nf->nf_file); + if (ret == -EOPENSTALE && stale_retry) { + stale_retry = false; + nfsd_file_unhash(nf); + clear_and_wake_up_bit(NFSD_FILE_PENDING, + &nf->nf_flags); + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; + fh_put(fhp); + goto retry; + } + status = nfserrno(ret); trace_nfsd_file_open(nf, status); } } else diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index bb205328e043..aeb71c10ff1b 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -17,9 +17,9 @@ struct ff_idmap { __be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp) + const struct nfsd4_layoutget *lgp) { - struct pnfs_ff_layout *fl = lgp->lg_content; + const struct pnfs_ff_layout *fl = lgp->lg_content; int len, mirror_len, ds_len, fh_len; __be32 *p; @@ -77,7 +77,7 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, __be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp) + const struct nfsd4_getdeviceinfo *gdp) { struct pnfs_ff_device_addr *da = gdp->gd_device; int len; diff --git a/fs/nfsd/flexfilelayoutxdr.h b/fs/nfsd/flexfilelayoutxdr.h index 8e195aeca023..6d5a1066a903 100644 --- a/fs/nfsd/flexfilelayoutxdr.h +++ b/fs/nfsd/flexfilelayoutxdr.h @@ -43,8 +43,8 @@ struct pnfs_ff_layout { }; __be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdp); + const struct nfsd4_getdeviceinfo *gdp); __be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, - struct nfsd4_layoutget *lgp); + const struct nfsd4_layoutget *lgp); #endif /* _NFSD_FLEXFILELAYOUTXDR_H */ diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c new file mode 100644 index 000000000000..0e1d635ec5f9 --- /dev/null +++ b/fs/nfsd/netlink.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "netlink.h" + +#include <uapi/linux/nfsd_netlink.h> + +/* Ops table for nfsd */ +static const struct genl_split_ops nfsd_nl_ops[] = { + { + .cmd = NFSD_CMD_RPC_STATUS_GET, + .start = nfsd_nl_rpc_status_get_start, + .dumpit = nfsd_nl_rpc_status_get_dumpit, + .done = nfsd_nl_rpc_status_get_done, + .flags = GENL_CMD_CAP_DUMP, + }, +}; + +struct genl_family nfsd_nl_family __ro_after_init = { + .name = NFSD_FAMILY_NAME, + .version = NFSD_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = nfsd_nl_ops, + .n_split_ops = ARRAY_SIZE(nfsd_nl_ops), +}; diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h new file mode 100644 index 000000000000..d83dd6bdee92 --- /dev/null +++ b/fs/nfsd/netlink.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/nfsd.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_NFSD_GEN_H +#define _LINUX_NFSD_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/nfsd_netlink.h> + +int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb); +int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb); + +int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); + +extern struct genl_family nfsd_nl_family; + +#endif /* _LINUX_NFSD_GEN_H */ diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 268ef57751c4..b78eceebd945 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -171,7 +171,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp) * + 1 (xdr opaque byte count) = 26 */ resp->count = argp->count; - svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3)<<2) + resp->count +4); + svc_reserve_auth(rqstp, ((1 + NFS3_POST_OP_ATTR_WORDS + 3) << 2) + + resp->count + 4); fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_read(rqstp, &resp->fh, argp->offset, @@ -194,7 +195,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh), argp->len, (unsigned long long) argp->offset, - argp->stable? " stable" : ""); + argp->stable ? " stable" : ""); resp->status = nfserr_fbig; if (argp->offset > (u64)OFFSET_MAX || @@ -294,8 +295,8 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_exist; break; case NFS3_CREATE_EXCLUSIVE: - if (d_inode(child)->i_mtime.tv_sec == v_mtime && - d_inode(child)->i_atime.tv_sec == v_atime && + if (inode_get_mtime_sec(d_inode(child)) == v_mtime && + inode_get_atime_sec(d_inode(child)) == v_atime && d_inode(child)->i_size == 0) { break; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 4039ffcf90ba..92bc109dabe6 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -84,7 +84,21 @@ static void encode_uint32(struct xdr_stream *xdr, u32 n) static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, size_t len) { - WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); + xdr_stream_encode_uint32_array(xdr, bitmap, len); +} + +static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs4_cb_fattr *fattr) +{ + fattr->ncf_cb_change = 0; + fattr->ncf_cb_fsize = 0; + if (bitmap[0] & FATTR4_WORD0_CHANGE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0) + return -NFSERR_BAD_XDR; + if (bitmap[0] & FATTR4_WORD0_SIZE) + if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0) + return -NFSERR_BAD_XDR; + return 0; } /* @@ -358,6 +372,30 @@ encode_cb_recallany4args(struct xdr_stream *xdr, } /* + * CB_GETATTR4args + * struct CB_GETATTR4args { + * nfs_fh4 fh; + * bitmap4 attr_request; + * }; + * + * The size and change attributes are the only one + * guaranteed to be serviced by the client. + */ +static void +encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr, + struct nfs4_cb_fattr *fattr) +{ + struct nfs4_delegation *dp = + container_of(fattr, struct nfs4_delegation, dl_cb_fattr); + struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle; + + encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR); + encode_nfs_fh4(xdr, fh); + encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap)); + hdr->nops++; +} + +/* * CB_SEQUENCE4args * * struct CB_SEQUENCE4args { @@ -493,6 +531,26 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static void nfs4_xdr_enc_cb_getattr(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_getattr4args(xdr, &hdr, ncf); + encode_cb_nops(&hdr); +} + +/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, @@ -548,6 +606,42 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, } /* + * 20.1. Operation 3: CB_GETATTR - Get Attributes + */ +static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + u32 bitmap[3] = {0}; + u32 attrlen; + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + + status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); + if (status) + return status; + if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) + return -NFSERR_BAD_XDR; + if (xdr_stream_decode_u32(xdr, &attrlen) < 0) + return -NFSERR_BAD_XDR; + if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize))) + return -NFSERR_BAD_XDR; + status = decode_cb_fattr4(xdr, bitmap, ncf); + return status; +} + +/* * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, @@ -855,6 +949,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), + PROC(CB_GETATTR, COMPOUND, cb_getattr, cb_getattr), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index e8a80052cb1b..5e8096bc5eaa 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -515,11 +515,11 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, if (!list_empty(&ls->ls_layouts)) { if (found) nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid); - lrp->lrs_present = 1; + lrp->lrs_present = true; } else { trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid); nfs4_unhash_stid(&ls->ls_stid); - lrp->lrs_present = 0; + lrp->lrs_present = false; } spin_unlock(&ls->ls_lock); @@ -539,7 +539,7 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp, struct nfs4_layout *lp, *t; LIST_HEAD(reaplist); - lrp->lrs_present = 0; + lrp->lrs_present = false; spin_lock(&clp->cl_lock); list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4199ede0583c..6f2d4aa4970d 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -322,8 +322,8 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_exist; break; case NFS4_CREATE_EXCLUSIVE: - if (d_inode(child)->i_mtime.tv_sec == v_mtime && - d_inode(child)->i_atime.tv_sec == v_atime && + if (inode_get_mtime_sec(d_inode(child)) == v_mtime && + inode_get_atime_sec(d_inode(child)) == v_atime && d_inode(child)->i_size == 0) { open->op_created = true; break; /* subtle */ @@ -331,8 +331,8 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_exist; break; case NFS4_CREATE_EXCLUSIVE4_1: - if (d_inode(child)->i_mtime.tv_sec == v_mtime && - d_inode(child)->i_atime.tv_sec == v_atime && + if (inode_get_mtime_sec(d_inode(child)) == v_mtime && + inode_get_atime_sec(d_inode(child)) == v_atime && d_inode(child)->i_size == 0) { open->op_created = true; goto set_attr; /* subtle */ @@ -1329,7 +1329,8 @@ extern void nfs_sb_deactive(struct super_block *sb); * setup a work entry in the ssc delayed unmount list. */ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, - struct nfsd4_ssc_umount_item **nsui) + struct nfsd4_ssc_umount_item **nsui, + struct svc_rqst *rqstp) { struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *work = NULL; @@ -1351,7 +1352,7 @@ try_again: spin_unlock(&nn->nfsd_ssc_lock); /* allow 20secs for mount/unmount for now - revisit */ - if (kthread_should_stop() || + if (svc_thread_should_stop(rqstp) || (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); @@ -1467,7 +1468,7 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, goto out_free_rawdata; snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep); - status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui); + status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui, rqstp); if (status) goto out_free_devname; if ((*nsui)->nsui_vfsmount) @@ -1642,6 +1643,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, if (bytes_total == 0) bytes_total = ULLONG_MAX; do { + /* Only async copies can be stopped here */ if (kthread_should_stop()) break; bytes_copied = nfsd_copy_file_range(src, src_pos, dst, dst_pos, @@ -1760,6 +1762,7 @@ static int nfsd4_do_async_copy(void *data) struct nfsd4_copy *copy = (struct nfsd4_copy *)data; __be32 nfserr; + trace_nfsd_copy_do_async(copy); if (nfsd4_ssc_is_inter(copy)) { struct file *filp; @@ -1798,21 +1801,27 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd4_copy *async_copy = NULL; + copy->cp_clp = cstate->clp; if (nfsd4_ssc_is_inter(copy)) { + trace_nfsd_copy_inter(copy); if (!inter_copy_offload_enable || nfsd4_copy_is_sync(copy)) { status = nfserr_notsupp; goto out; } status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); - if (status) + if (status) { + trace_nfsd_copy_done(copy, status); return nfserr_offload_denied; + } } else { + trace_nfsd_copy_intra(copy); status = nfsd4_setup_intra_ssc(rqstp, cstate, copy); - if (status) + if (status) { + trace_nfsd_copy_done(copy, status); return status; + } } - copy->cp_clp = cstate->clp; memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) { @@ -1847,6 +1856,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy->nf_dst->nf_file, true); } out: + trace_nfsd_copy_done(copy, status); release_copy_files(copy); return status; out_err: @@ -1929,8 +1939,8 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) return status; - cn->cpn_sec = nn->nfsd4_lease; - cn->cpn_nsec = 0; + cn->cpn_lease_time.tv_sec = nn->nfsd4_lease; + cn->cpn_lease_time.tv_nsec = 0; status = nfserrno(-ENOMEM); cps = nfs4_alloc_init_cpntf_state(nn, stid); @@ -2347,10 +2357,10 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, mutex_unlock(&ls->ls_mutex); if (new_size > i_size_read(inode)) { - lcp->lc_size_chg = 1; + lcp->lc_size_chg = true; lcp->lc_newsize = new_size; } else { - lcp->lc_size_chg = 0; + lcp->lc_size_chg = false; } nfserr = ops->proc_layoutcommit(inode, lcp); @@ -3200,6 +3210,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_LOCK] = { .op_func = nfsd4_lock, + .op_release = nfsd4_lock_release, .op_flags = OP_MODIFIES_SOMETHING | OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_LOCK", @@ -3208,6 +3219,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_LOCKT] = { .op_func = nfsd4_lockt, + .op_release = nfsd4_lockt_release, .op_flags = OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_LOCKT", .op_rsize_bop = nfsd4_lock_rsize, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8534693eb6a4..65fd5510323a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -59,7 +59,7 @@ #define NFSDDBG_FACILITY NFSDDBG_PROC -#define all_ones {{~0,~0},~0} +#define all_ones {{ ~0, ~0}, ~0} static const stateid_t one_stateid = { .si_generation = ~0, .si_opaque = all_ones, @@ -127,6 +127,7 @@ static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; static struct workqueue_struct *laundry_wq; @@ -297,7 +298,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, nbl = find_blocked_lock(lo, fh, nn); if (!nbl) { - nbl= kmalloc(sizeof(*nbl), GFP_KERNEL); + nbl = kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { INIT_LIST_HEAD(&nbl->nbl_list); INIT_LIST_HEAD(&nbl->nbl_lru); @@ -1159,6 +1160,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate, u32 dl_type) { struct nfs4_delegation *dp; + struct nfs4_stid *stid; long n; dprintk("NFSD alloc_init_deleg\n"); @@ -1167,9 +1169,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, goto out_dec; if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); - if (dp == NULL) + stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg); + if (stid == NULL) goto out_dec; + dp = delegstateid(stid); /* * delegation seqid's are never incremented. The 4.1 special @@ -1187,6 +1190,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); + nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, + &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); + dp->dl_cb_fattr.ncf_file_modified = false; + dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; @@ -2894,11 +2901,56 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) spin_unlock(&nn->client_lock); } +static int +nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + + ncf->ncf_cb_status = task->tk_status; + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_getattr_release(struct nfsd4_callback *cb) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + nfs4_put_stid(&dp->dl_stid); + clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags); + wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY); +} + static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { .done = nfsd4_cb_recall_any_done, .release = nfsd4_cb_recall_any_release, }; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { + .done = nfsd4_cb_getattr_done, + .release = nfsd4_cb_getattr_release, +}; + +void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) +{ + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags)) + return; + refcount_inc(&dp->dl_stid.sc_count); + nfsd4_run_cb(&ncf->ncf_getattr); +} + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -5634,13 +5686,15 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent = NULL; int cb_up; int status = 0; + struct kstat stat; + struct path path; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); - open->op_recall = 0; + open->op_recall = false; switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_PREVIOUS: if (!cb_up) - open->op_recall = 1; + open->op_recall = true; break; case NFS4_OPEN_CLAIM_NULL: parent = currentfh; @@ -5671,6 +5725,18 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE; trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); + path.mnt = currentfh->fh_export->ex_path.mnt; + path.dentry = currentfh->fh_dentry; + if (vfs_getattr(&path, &stat, + (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE), + AT_STATX_SYNC_AS_STAT)) { + nfs4_put_stid(&dp->dl_stid); + destroy_delegation(dp); + goto out_no_deleg; + } + dp->dl_cb_fattr.ncf_cur_fsize = stat.size; + dp->dl_cb_fattr.ncf_initial_cinfo = + nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry)); } else { open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); @@ -5682,7 +5748,7 @@ out_no_deleg: if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) { dprintk("NFSD: WARNING: refusing delegation reclaim\n"); - open->op_recall = 1; + open->op_recall = true; } /* 4.1 client asking for a delegation? */ @@ -7487,6 +7553,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; + struct super_block *sb; __be32 status = 0; int lkflg; int err; @@ -7508,6 +7575,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } + sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) @@ -7559,7 +7627,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate)) + if (nfsd4_has_session(cstate) || + exportfs_lock_op_is_async(sb->s_export_op)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: @@ -7571,7 +7640,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fl_type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate)) + if (nfsd4_has_session(cstate) || + exportfs_lock_op_is_async(sb->s_export_op)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: @@ -7599,7 +7669,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * for file locks), so don't attempt blocking lock notifications * on those filesystems: */ - if (nf->nf_file->f_op->lock) + if (!exportfs_lock_op_is_async(sb->s_export_op)) fl_flags &= ~FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); @@ -7705,6 +7775,14 @@ out: return status; } +void nfsd4_lock_release(union nfsd4_op_u *u) +{ + struct nfsd4_lock *lock = &u->lock; + struct nfsd4_lock_denied *deny = &lock->lk_denied; + + kfree(deny->ld_owner.data); +} + /* * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN, * so we do a temporary open here just to get an open file to pass to @@ -7810,6 +7888,14 @@ out: return status; } +void nfsd4_lockt_release(union nfsd4_op_u *u) +{ + struct nfsd4_lockt *lockt = &u->lockt; + struct nfsd4_lock_denied *deny = &lockt->lt_denied; + + kfree(deny->ld_owner.data); +} + __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -8403,6 +8489,8 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context * @inode: file to be checked for a conflict + * @modified: return true if file was modified + * @size: new size of file if modified is true * * This function is called when there is a conflict between a write * delegation and a change/size GETATTR from another client. The server @@ -8411,21 +8499,23 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * delegation before replying to the GETATTR. See RFC 8881 section * 18.7.4. * - * The current implementation does not support CB_GETATTR yet. However - * this can avoid recalling the delegation could be added in follow up - * work. - * * Returns 0 if there is no conflict; otherwise an nfs_stat * code is returned. */ __be32 -nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode) +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, + bool *modified, u64 *size) { - __be32 status; struct file_lock_context *ctx; - struct file_lock *fl; struct nfs4_delegation *dp; + struct nfs4_cb_fattr *ncf; + struct file_lock *fl; + struct iattr attrs; + __be32 status; + might_sleep(); + + *modified = false; ctx = locks_inode_context(inode); if (!ctx) return 0; @@ -8452,10 +8542,34 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode) break_lease: spin_unlock(&ctx->flc_lock); nfsd_stats_wdeleg_getattr_inc(); - status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); - if (status != nfserr_jukebox || - !nfsd_wait_for_delegreturn(rqstp, inode)) - return status; + + dp = fl->fl_owner; + ncf = &dp->dl_cb_fattr; + nfs4_cb_getattr(&dp->dl_cb_fattr); + wait_on_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE); + if (ncf->ncf_cb_status) { + status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + return status; + } + if (!ncf->ncf_file_modified && + (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || + ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) + ncf->ncf_file_modified = true; + if (ncf->ncf_file_modified) { + /* + * The server would not update the file's metadata + * with the client's modified size. + */ + attrs.ia_mtime = attrs.ia_ctime = current_time(inode); + attrs.ia_valid = ATTR_MTIME | ATTR_CTIME; + setattr_copy(&nop_mnt_idmap, inode, &attrs); + mark_inode_dirty(inode); + ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; + *size = ncf->ncf_cur_fsize; + *modified = true; + } return 0; } break; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2e40c74d2f72..ec4ed6206df1 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2530,66 +2530,62 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) return true; } -static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, - struct svc_export *exp) +static __be32 nfsd4_encode_nfs_fh4(struct xdr_stream *xdr, + struct knfsd_fh *fh_handle) { - if (exp->ex_flags & NFSEXP_V4ROOT) { - *p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time)); - *p++ = 0; - } else - p = xdr_encode_hyper(p, nfsd4_change_attribute(stat, inode)); - return p; + return nfsd4_encode_opaque(xdr, fh_handle->fh_raw, fh_handle->fh_size); } +/* This is a frequently-encoded type; open-coded for speed */ static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr, - struct timespec64 *tv) + const struct timespec64 *tv) { __be32 *p; p = xdr_reserve_space(xdr, XDR_UNIT * 3); if (!p) return nfserr_resource; - - p = xdr_encode_hyper(p, (s64)tv->tv_sec); + p = xdr_encode_hyper(p, tv->tv_sec); *p = cpu_to_be32(tv->tv_nsec); return nfs_ok; } -/* - * ctime (in NFSv4, time_metadata) is not writeable, and the client - * doesn't really care what resolution could theoretically be stored by - * the filesystem. - * - * The client cares how close together changes can be while still - * guaranteeing ctime changes. For most filesystems (which have - * timestamps with nanosecond fields) that is limited by the resolution - * of the time returned from current_time() (which I'm assuming to be - * 1/HZ). - */ -static __be32 *encode_time_delta(__be32 *p, struct inode *inode) +static __be32 nfsd4_encode_specdata4(struct xdr_stream *xdr, + unsigned int major, unsigned int minor) { - struct timespec64 ts; - u32 ns; + __be32 status; - ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran); - ts = ns_to_timespec64(ns); + status = nfsd4_encode_uint32_t(xdr, major); + if (status != nfs_ok) + return status; + return nfsd4_encode_uint32_t(xdr, minor); +} - p = xdr_encode_hyper(p, ts.tv_sec); - *p++ = cpu_to_be32(ts.tv_nsec); +static __be32 +nfsd4_encode_change_info4(struct xdr_stream *xdr, const struct nfsd4_change_info *c) +{ + __be32 status; - return p; + status = nfsd4_encode_bool(xdr, c->atomic); + if (status != nfs_ok) + return status; + status = nfsd4_encode_changeid4(xdr, c->before_change); + if (status != nfs_ok) + return status; + return nfsd4_encode_changeid4(xdr, c->after_change); } -static __be32 -nfsd4_encode_change_info4(struct xdr_stream *xdr, struct nfsd4_change_info *c) +static __be32 nfsd4_encode_netaddr4(struct xdr_stream *xdr, + const struct nfs42_netaddr *addr) { - if (xdr_stream_encode_bool(xdr, c->atomic) < 0) - return nfserr_resource; - if (xdr_stream_encode_u64(xdr, c->before_change) < 0) - return nfserr_resource; - if (xdr_stream_encode_u64(xdr, c->after_change) < 0) - return nfserr_resource; - return nfs_ok; + __be32 status; + + /* na_r_netid */ + status = nfsd4_encode_opaque(xdr, addr->netid, addr->netid_len); + if (status != nfs_ok) + return status; + /* na_r_addr */ + return nfsd4_encode_opaque(xdr, addr->addr, addr->addr_len); } /* Encode as an array of strings the string given with components @@ -2661,9 +2657,6 @@ static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep, return nfsd4_encode_components_esc(xdr, sep, components, 0, 0); } -/* - * encode a location element of a fs_locations structure - */ static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr, struct nfsd4_fs_location *location) { @@ -2676,15 +2669,12 @@ static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr, status = nfsd4_encode_components(xdr, '/', location->path); if (status) return status; - return 0; + return nfs_ok; } -/* - * Encode a path in RFC3530 'pathname4' format - */ -static __be32 nfsd4_encode_path(struct xdr_stream *xdr, - const struct path *root, - const struct path *path) +static __be32 nfsd4_encode_pathname4(struct xdr_stream *xdr, + const struct path *root, + const struct path *path) { struct path cur = *path; __be32 *p; @@ -2752,89 +2742,59 @@ out_free: return err; } -static __be32 nfsd4_encode_fsloc_fsroot(struct xdr_stream *xdr, - struct svc_rqst *rqstp, const struct path *path) +static __be32 nfsd4_encode_fs_locations4(struct xdr_stream *xdr, + struct svc_rqst *rqstp, + struct svc_export *exp) { + struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs; struct svc_export *exp_ps; - __be32 res; + unsigned int i; + __be32 status; + /* fs_root */ exp_ps = rqst_find_fsidzero_export(rqstp); if (IS_ERR(exp_ps)) return nfserrno(PTR_ERR(exp_ps)); - res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path); + status = nfsd4_encode_pathname4(xdr, &exp_ps->ex_path, &exp->ex_path); exp_put(exp_ps); - return res; -} - -/* - * encode a fs_locations structure - */ -static __be32 nfsd4_encode_fs_locations(struct xdr_stream *xdr, - struct svc_rqst *rqstp, struct svc_export *exp) -{ - __be32 status; - int i; - __be32 *p; - struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs; - - status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path); - if (status) + if (status != nfs_ok) return status; - p = xdr_reserve_space(xdr, 4); - if (!p) + + /* locations<> */ + if (xdr_stream_encode_u32(xdr, fslocs->locations_count) != XDR_UNIT) return nfserr_resource; - *p++ = cpu_to_be32(fslocs->locations_count); - for (i=0; i<fslocs->locations_count; i++) { + for (i = 0; i < fslocs->locations_count; i++) { status = nfsd4_encode_fs_location4(xdr, &fslocs->locations[i]); - if (status) + if (status != nfs_ok) return status; } - return 0; -} -static u32 nfs4_file_type(umode_t mode) -{ - switch (mode & S_IFMT) { - case S_IFIFO: return NF4FIFO; - case S_IFCHR: return NF4CHR; - case S_IFDIR: return NF4DIR; - case S_IFBLK: return NF4BLK; - case S_IFLNK: return NF4LNK; - case S_IFREG: return NF4REG; - case S_IFSOCK: return NF4SOCK; - default: return NF4BAD; - } + return nfs_ok; } -static inline __be32 -nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, - struct nfs4_ace *ace) +static __be32 nfsd4_encode_nfsace4(struct xdr_stream *xdr, struct svc_rqst *rqstp, + struct nfs4_ace *ace) { + __be32 status; + + /* type */ + status = nfsd4_encode_acetype4(xdr, ace->type); + if (status != nfs_ok) + return nfserr_resource; + /* flag */ + status = nfsd4_encode_aceflag4(xdr, ace->flag); + if (status != nfs_ok) + return nfserr_resource; + /* access mask */ + status = nfsd4_encode_acemask4(xdr, ace->access_mask & NFS4_ACE_MASK_ALL); + if (status != nfs_ok) + return nfserr_resource; + /* who */ if (ace->whotype != NFS4_ACL_WHO_NAMED) return nfs4_acl_write_who(xdr, ace->whotype); - else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) + if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP) return nfsd4_encode_group(xdr, rqstp, ace->who_gid); - else - return nfsd4_encode_user(xdr, rqstp, ace->who_uid); -} - -static inline __be32 -nfsd4_encode_layout_types(struct xdr_stream *xdr, u32 layout_types) -{ - __be32 *p; - unsigned long i = hweight_long(layout_types); - - p = xdr_reserve_space(xdr, 4 + 4 * i); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(i); - - for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i) - if (layout_types & (1 << i)) - *p++ = cpu_to_be32(i); - - return 0; + return nfsd4_encode_user(xdr, rqstp, ace->who_uid); } #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ @@ -2906,12 +2866,12 @@ static int nfsd4_get_mounted_on_ino(struct svc_export *exp, u64 *pino) } static __be32 -nfsd4_encode_bitmap(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) +nfsd4_encode_bitmap4(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) { __be32 *p; if (bmval2) { - p = xdr_reserve_space(xdr, 16); + p = xdr_reserve_space(xdr, XDR_UNIT * 4); if (!p) goto out_resource; *p++ = cpu_to_be32(3); @@ -2919,94 +2879,687 @@ nfsd4_encode_bitmap(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2) *p++ = cpu_to_be32(bmval1); *p++ = cpu_to_be32(bmval2); } else if (bmval1) { - p = xdr_reserve_space(xdr, 12); + p = xdr_reserve_space(xdr, XDR_UNIT * 3); if (!p) goto out_resource; *p++ = cpu_to_be32(2); *p++ = cpu_to_be32(bmval0); *p++ = cpu_to_be32(bmval1); } else { - p = xdr_reserve_space(xdr, 8); + p = xdr_reserve_space(xdr, XDR_UNIT * 2); if (!p) goto out_resource; *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(bmval0); } - return 0; + return nfs_ok; out_resource: return nfserr_resource; } +struct nfsd4_fattr_args { + struct svc_rqst *rqstp; + struct svc_fh *fhp; + struct svc_export *exp; + struct dentry *dentry; + struct kstat stat; + struct kstatfs statfs; + struct nfs4_acl *acl; + u64 size; +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + void *context; + int contextlen; +#endif + u32 rdattr_err; + bool contextsupport; + bool ignore_crossmnt; +}; + +typedef __be32(*nfsd4_enc_attr)(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args); + +static __be32 nfsd4_encode_fattr4__noop(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4__true(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_bool(xdr, true); +} + +static __be32 nfsd4_encode_fattr4__false(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_bool(xdr, false); +} + +static __be32 nfsd4_encode_fattr4_supported_attrs(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfsd4_compoundres *resp = args->rqstp->rq_resp; + u32 minorversion = resp->cstate.minorversion; + u32 supp[3]; + + memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp)); + if (!IS_POSIXACL(d_inode(args->dentry))) + supp[0] &= ~FATTR4_WORD0_ACL; + if (!args->contextsupport) + supp[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + + return nfsd4_encode_bitmap4(xdr, supp[0], supp[1], supp[2]); +} + +static __be32 nfsd4_encode_fattr4_type(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT); + if (!p) + return nfserr_resource; + + switch (args->stat.mode & S_IFMT) { + case S_IFIFO: + *p = cpu_to_be32(NF4FIFO); + break; + case S_IFCHR: + *p = cpu_to_be32(NF4CHR); + break; + case S_IFDIR: + *p = cpu_to_be32(NF4DIR); + break; + case S_IFBLK: + *p = cpu_to_be32(NF4BLK); + break; + case S_IFLNK: + *p = cpu_to_be32(NF4LNK); + break; + case S_IFREG: + *p = cpu_to_be32(NF4REG); + break; + case S_IFSOCK: + *p = cpu_to_be32(NF4SOCK); + break; + default: + return nfserr_serverfault; + } + + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_fh_expire_type(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u32 mask; + + mask = NFS4_FH_PERSISTENT; + if (!(args->exp->ex_flags & NFSEXP_NOSUBTREECHECK)) + mask |= NFS4_FH_VOL_RENAME; + return nfsd4_encode_uint32_t(xdr, mask); +} + +static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + const struct svc_export *exp = args->exp; + u64 c; + + if (unlikely(exp->ex_flags & NFSEXP_V4ROOT)) { + u32 flush_time = convert_to_wallclock(exp->cd->flush_time); + + if (xdr_stream_encode_u32(xdr, flush_time) != XDR_UNIT) + return nfserr_resource; + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + + c = nfsd4_change_attribute(&args->stat, d_inode(args->dentry)); + return nfsd4_encode_changeid4(xdr, c); +} + +static __be32 nfsd4_encode_fattr4_size(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->size); +} + +static __be32 nfsd4_encode_fattr4_fsid(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT * 2 + XDR_UNIT * 2); + if (!p) + return nfserr_resource; + + if (unlikely(args->exp->ex_fslocs.migrated)) { + p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR); + xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR); + return nfs_ok; + } + switch (fsid_source(args->fhp)) { + case FSIDSOURCE_FSID: + p = xdr_encode_hyper(p, (u64)args->exp->ex_fsid); + xdr_encode_hyper(p, (u64)0); + break; + case FSIDSOURCE_DEV: + *p++ = xdr_zero; + *p++ = cpu_to_be32(MAJOR(args->stat.dev)); + *p++ = xdr_zero; + *p = cpu_to_be32(MINOR(args->stat.dev)); + break; + case FSIDSOURCE_UUID: + xdr_encode_opaque_fixed(p, args->exp->ex_uuid, EX_UUID_LEN); + break; + } + + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_lease_time(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfsd_net *nn = net_generic(SVC_NET(args->rqstp), nfsd_net_id); + + return nfsd4_encode_nfs_lease4(xdr, nn->nfsd4_lease); +} + +static __be32 nfsd4_encode_fattr4_rdattr_error(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->rdattr_err); +} + +static __be32 nfsd4_encode_fattr4_aclsupport(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u32 mask; + + mask = 0; + if (IS_POSIXACL(d_inode(args->dentry))) + mask = ACL4_SUPPORT_ALLOW_ACL | ACL4_SUPPORT_DENY_ACL; + return nfsd4_encode_uint32_t(xdr, mask); +} + +static __be32 nfsd4_encode_fattr4_acl(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfs4_acl *acl = args->acl; + struct nfs4_ace *ace; + __be32 status; + + /* nfsace4<> */ + if (!acl) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + } else { + if (xdr_stream_encode_u32(xdr, acl->naces) != XDR_UNIT) + return nfserr_resource; + for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) { + status = nfsd4_encode_nfsace4(xdr, args->rqstp, ace); + if (status != nfs_ok) + return status; + } + } + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_filehandle(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfs_fh4(xdr, &args->fhp->fh_handle); +} + +static __be32 nfsd4_encode_fattr4_fileid(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->stat.ino); +} + +static __be32 nfsd4_encode_fattr4_files_avail(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->statfs.f_ffree); +} + +static __be32 nfsd4_encode_fattr4_files_free(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->statfs.f_ffree); +} + +static __be32 nfsd4_encode_fattr4_files_total(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, args->statfs.f_files); +} + +static __be32 nfsd4_encode_fattr4_fs_locations(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_fs_locations4(xdr, args->rqstp, args->exp); +} + +static __be32 nfsd4_encode_fattr4_maxfilesize(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct super_block *sb = args->exp->ex_path.mnt->mnt_sb; + + return nfsd4_encode_uint64_t(xdr, sb->s_maxbytes); +} + +static __be32 nfsd4_encode_fattr4_maxlink(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, 255); +} + +static __be32 nfsd4_encode_fattr4_maxname(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->statfs.f_namelen); +} + +static __be32 nfsd4_encode_fattr4_maxread(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, svc_max_payload(args->rqstp)); +} + +static __be32 nfsd4_encode_fattr4_maxwrite(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, svc_max_payload(args->rqstp)); +} + +static __be32 nfsd4_encode_fattr4_mode(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_mode4(xdr, args->stat.mode & S_IALLUGO); +} + +static __be32 nfsd4_encode_fattr4_numlinks(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->stat.nlink); +} + +static __be32 nfsd4_encode_fattr4_owner(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_user(xdr, args->rqstp, args->stat.uid); +} + +static __be32 nfsd4_encode_fattr4_owner_group(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_group(xdr, args->rqstp, args->stat.gid); +} + +static __be32 nfsd4_encode_fattr4_rawdev(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_specdata4(xdr, MAJOR(args->stat.rdev), + MINOR(args->stat.rdev)); +} + +static __be32 nfsd4_encode_fattr4_space_avail(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 avail = (u64)args->statfs.f_bavail * (u64)args->statfs.f_bsize; + + return nfsd4_encode_uint64_t(xdr, avail); +} + +static __be32 nfsd4_encode_fattr4_space_free(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 free = (u64)args->statfs.f_bfree * (u64)args->statfs.f_bsize; + + return nfsd4_encode_uint64_t(xdr, free); +} + +static __be32 nfsd4_encode_fattr4_space_total(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 total = (u64)args->statfs.f_blocks * (u64)args->statfs.f_bsize; + + return nfsd4_encode_uint64_t(xdr, total); +} + +static __be32 nfsd4_encode_fattr4_space_used(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint64_t(xdr, (u64)args->stat.blocks << 9); +} + +static __be32 nfsd4_encode_fattr4_time_access(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.atime); +} + +static __be32 nfsd4_encode_fattr4_time_create(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.btime); +} + +/* + * ctime (in NFSv4, time_metadata) is not writeable, and the client + * doesn't really care what resolution could theoretically be stored by + * the filesystem. + * + * The client cares how close together changes can be while still + * guaranteeing ctime changes. For most filesystems (which have + * timestamps with nanosecond fields) that is limited by the resolution + * of the time returned from current_time() (which I'm assuming to be + * 1/HZ). + */ +static __be32 nfsd4_encode_fattr4_time_delta(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + const struct inode *inode = d_inode(args->dentry); + u32 ns = max_t(u32, NSEC_PER_SEC/HZ, inode->i_sb->s_time_gran); + struct timespec64 ts = ns_to_timespec64(ns); + + return nfsd4_encode_nfstime4(xdr, &ts); +} + +static __be32 nfsd4_encode_fattr4_time_metadata(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.ctime); +} + +static __be32 nfsd4_encode_fattr4_time_modify(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_nfstime4(xdr, &args->stat.mtime); +} + +static __be32 nfsd4_encode_fattr4_mounted_on_fileid(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + u64 ino; + int err; + + if (!args->ignore_crossmnt && + args->dentry == args->exp->ex_path.mnt->mnt_root) { + err = nfsd4_get_mounted_on_ino(args->exp, &ino); + if (err) + return nfserrno(err); + } else + ino = args->stat.ino; + + return nfsd4_encode_uint64_t(xdr, ino); +} + +#ifdef CONFIG_NFSD_PNFS + +static __be32 nfsd4_encode_fattr4_fs_layout_types(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + unsigned long mask = args->exp->ex_layout_types; + int i; + + /* Hamming weight of @mask is the number of layout types to return */ + if (xdr_stream_encode_u32(xdr, hweight_long(mask)) != XDR_UNIT) + return nfserr_resource; + for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i) + if (mask & BIT(i)) { + /* layouttype4 */ + if (xdr_stream_encode_u32(xdr, i) != XDR_UNIT) + return nfserr_resource; + } + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_layout_types(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + unsigned long mask = args->exp->ex_layout_types; + int i; + + /* Hamming weight of @mask is the number of layout types to return */ + if (xdr_stream_encode_u32(xdr, hweight_long(mask)) != XDR_UNIT) + return nfserr_resource; + for (i = LAYOUT_NFSV4_1_FILES; i < LAYOUT_TYPE_MAX; ++i) + if (mask & BIT(i)) { + /* layouttype4 */ + if (xdr_stream_encode_u32(xdr, i) != XDR_UNIT) + return nfserr_resource; + } + return nfs_ok; +} + +static __be32 nfsd4_encode_fattr4_layout_blksize(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_uint32_t(xdr, args->stat.blksize); +} + +#endif + +static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + struct nfsd4_compoundres *resp = args->rqstp->rq_resp; + u32 supp[3]; + + memcpy(supp, nfsd_suppattrs[resp->cstate.minorversion], sizeof(supp)); + supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; + supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; + supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; + + return nfsd4_encode_bitmap4(xdr, supp[0], supp[1], supp[2]); +} + +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL +static __be32 nfsd4_encode_fattr4_sec_label(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfsd4_encode_security_label(xdr, args->rqstp, + args->context, args->contextlen); +} +#endif + +static __be32 nfsd4_encode_fattr4_xattr_support(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + int err = xattr_supports_user_prefix(d_inode(args->dentry)); + + return nfsd4_encode_bool(xdr, err == 0); +} + +static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = { + [FATTR4_SUPPORTED_ATTRS] = nfsd4_encode_fattr4_supported_attrs, + [FATTR4_TYPE] = nfsd4_encode_fattr4_type, + [FATTR4_FH_EXPIRE_TYPE] = nfsd4_encode_fattr4_fh_expire_type, + [FATTR4_CHANGE] = nfsd4_encode_fattr4_change, + [FATTR4_SIZE] = nfsd4_encode_fattr4_size, + [FATTR4_LINK_SUPPORT] = nfsd4_encode_fattr4__true, + [FATTR4_SYMLINK_SUPPORT] = nfsd4_encode_fattr4__true, + [FATTR4_NAMED_ATTR] = nfsd4_encode_fattr4__false, + [FATTR4_FSID] = nfsd4_encode_fattr4_fsid, + [FATTR4_UNIQUE_HANDLES] = nfsd4_encode_fattr4__true, + [FATTR4_LEASE_TIME] = nfsd4_encode_fattr4_lease_time, + [FATTR4_RDATTR_ERROR] = nfsd4_encode_fattr4_rdattr_error, + [FATTR4_ACL] = nfsd4_encode_fattr4_acl, + [FATTR4_ACLSUPPORT] = nfsd4_encode_fattr4_aclsupport, + [FATTR4_ARCHIVE] = nfsd4_encode_fattr4__noop, + [FATTR4_CANSETTIME] = nfsd4_encode_fattr4__true, + [FATTR4_CASE_INSENSITIVE] = nfsd4_encode_fattr4__false, + [FATTR4_CASE_PRESERVING] = nfsd4_encode_fattr4__true, + [FATTR4_CHOWN_RESTRICTED] = nfsd4_encode_fattr4__true, + [FATTR4_FILEHANDLE] = nfsd4_encode_fattr4_filehandle, + [FATTR4_FILEID] = nfsd4_encode_fattr4_fileid, + [FATTR4_FILES_AVAIL] = nfsd4_encode_fattr4_files_avail, + [FATTR4_FILES_FREE] = nfsd4_encode_fattr4_files_free, + [FATTR4_FILES_TOTAL] = nfsd4_encode_fattr4_files_total, + [FATTR4_FS_LOCATIONS] = nfsd4_encode_fattr4_fs_locations, + [FATTR4_HIDDEN] = nfsd4_encode_fattr4__noop, + [FATTR4_HOMOGENEOUS] = nfsd4_encode_fattr4__true, + [FATTR4_MAXFILESIZE] = nfsd4_encode_fattr4_maxfilesize, + [FATTR4_MAXLINK] = nfsd4_encode_fattr4_maxlink, + [FATTR4_MAXNAME] = nfsd4_encode_fattr4_maxname, + [FATTR4_MAXREAD] = nfsd4_encode_fattr4_maxread, + [FATTR4_MAXWRITE] = nfsd4_encode_fattr4_maxwrite, + [FATTR4_MIMETYPE] = nfsd4_encode_fattr4__noop, + [FATTR4_MODE] = nfsd4_encode_fattr4_mode, + [FATTR4_NO_TRUNC] = nfsd4_encode_fattr4__true, + [FATTR4_NUMLINKS] = nfsd4_encode_fattr4_numlinks, + [FATTR4_OWNER] = nfsd4_encode_fattr4_owner, + [FATTR4_OWNER_GROUP] = nfsd4_encode_fattr4_owner_group, + [FATTR4_QUOTA_AVAIL_HARD] = nfsd4_encode_fattr4__noop, + [FATTR4_QUOTA_AVAIL_SOFT] = nfsd4_encode_fattr4__noop, + [FATTR4_QUOTA_USED] = nfsd4_encode_fattr4__noop, + [FATTR4_RAWDEV] = nfsd4_encode_fattr4_rawdev, + [FATTR4_SPACE_AVAIL] = nfsd4_encode_fattr4_space_avail, + [FATTR4_SPACE_FREE] = nfsd4_encode_fattr4_space_free, + [FATTR4_SPACE_TOTAL] = nfsd4_encode_fattr4_space_total, + [FATTR4_SPACE_USED] = nfsd4_encode_fattr4_space_used, + [FATTR4_SYSTEM] = nfsd4_encode_fattr4__noop, + [FATTR4_TIME_ACCESS] = nfsd4_encode_fattr4_time_access, + [FATTR4_TIME_ACCESS_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_TIME_BACKUP] = nfsd4_encode_fattr4__noop, + [FATTR4_TIME_CREATE] = nfsd4_encode_fattr4_time_create, + [FATTR4_TIME_DELTA] = nfsd4_encode_fattr4_time_delta, + [FATTR4_TIME_METADATA] = nfsd4_encode_fattr4_time_metadata, + [FATTR4_TIME_MODIFY] = nfsd4_encode_fattr4_time_modify, + [FATTR4_TIME_MODIFY_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_MOUNTED_ON_FILEID] = nfsd4_encode_fattr4_mounted_on_fileid, + [FATTR4_DIR_NOTIF_DELAY] = nfsd4_encode_fattr4__noop, + [FATTR4_DIRENT_NOTIF_DELAY] = nfsd4_encode_fattr4__noop, + [FATTR4_DACL] = nfsd4_encode_fattr4__noop, + [FATTR4_SACL] = nfsd4_encode_fattr4__noop, + [FATTR4_CHANGE_POLICY] = nfsd4_encode_fattr4__noop, + [FATTR4_FS_STATUS] = nfsd4_encode_fattr4__noop, + +#ifdef CONFIG_NFSD_PNFS + [FATTR4_FS_LAYOUT_TYPES] = nfsd4_encode_fattr4_fs_layout_types, + [FATTR4_LAYOUT_HINT] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_TYPES] = nfsd4_encode_fattr4_layout_types, + [FATTR4_LAYOUT_BLKSIZE] = nfsd4_encode_fattr4_layout_blksize, + [FATTR4_LAYOUT_ALIGNMENT] = nfsd4_encode_fattr4__noop, +#else + [FATTR4_FS_LAYOUT_TYPES] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_HINT] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_TYPES] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_BLKSIZE] = nfsd4_encode_fattr4__noop, + [FATTR4_LAYOUT_ALIGNMENT] = nfsd4_encode_fattr4__noop, +#endif + + [FATTR4_FS_LOCATIONS_INFO] = nfsd4_encode_fattr4__noop, + [FATTR4_MDSTHRESHOLD] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTION_GET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTION_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTEVT_GET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTEVT_SET] = nfsd4_encode_fattr4__noop, + [FATTR4_RETENTION_HOLD] = nfsd4_encode_fattr4__noop, + [FATTR4_MODE_SET_MASKED] = nfsd4_encode_fattr4__noop, + [FATTR4_SUPPATTR_EXCLCREAT] = nfsd4_encode_fattr4_suppattr_exclcreat, + [FATTR4_FS_CHARSET_CAP] = nfsd4_encode_fattr4__noop, + [FATTR4_CLONE_BLKSIZE] = nfsd4_encode_fattr4__noop, + [FATTR4_SPACE_FREED] = nfsd4_encode_fattr4__noop, + [FATTR4_CHANGE_ATTR_TYPE] = nfsd4_encode_fattr4__noop, + +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL + [FATTR4_SEC_LABEL] = nfsd4_encode_fattr4_sec_label, +#else + [FATTR4_SEC_LABEL] = nfsd4_encode_fattr4__noop, +#endif + + [FATTR4_MODE_UMASK] = nfsd4_encode_fattr4__noop, + [FATTR4_XATTR_SUPPORT] = nfsd4_encode_fattr4_xattr_support, +}; + /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. */ static __be32 -nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, - struct svc_export *exp, - struct dentry *dentry, u32 *bmval, - struct svc_rqst *rqstp, int ignore_crossmnt) +nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, + struct svc_fh *fhp, struct svc_export *exp, + struct dentry *dentry, const u32 *bmval, + int ignore_crossmnt) { - u32 bmval0 = bmval[0]; - u32 bmval1 = bmval[1]; - u32 bmval2 = bmval[2]; - struct kstat stat; + struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; - struct kstatfs statfs; - __be32 *p, *attrlen_p; int starting_len = xdr->buf->len; + __be32 *attrlen_p, status; int attrlen_offset; - u32 dummy; - u64 dummy64; - u32 rdattr_err = 0; - __be32 status; int err; - struct nfs4_acl *acl = NULL; -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL - void *context = NULL; - int contextlen; -#endif - bool contextsupport = false; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; struct path path = { .mnt = exp->ex_path.mnt, .dentry = dentry, }; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + union { + u32 attrmask[3]; + unsigned long mask[2]; + } u; + bool file_modified; + unsigned long bit; + u64 size = 0; + + WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1); + WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval)); + + args.rqstp = rqstp; + args.exp = exp; + args.dentry = dentry; + args.ignore_crossmnt = (ignore_crossmnt != 0); - BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1); - BUG_ON(!nfsd_attrs_supported(minorversion, bmval)); + /* + * Make a local copy of the attribute bitmap that can be modified. + */ + memset(&u, 0, sizeof(u)); + u.attrmask[0] = bmval[0]; + u.attrmask[1] = bmval[1]; + u.attrmask[2] = bmval[2]; + args.rdattr_err = 0; if (exp->ex_fslocs.migrated) { - status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err); + status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1], + &u.attrmask[2], &args.rdattr_err); if (status) goto out; } - if (bmval0 & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { - status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry)); + args.size = 0; + if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), + &file_modified, &size); if (status) goto out; } - err = vfs_getattr(&path, &stat, + err = vfs_getattr(&path, &args.stat, STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; - if (!(stat.result_mask & STATX_BTIME)) + args.size = file_modified ? size : args.stat.size; + + if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ - bmval1 &= ~FATTR4_WORD1_TIME_CREATE; - if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; + if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || - (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | + (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { - err = vfs_statfs(&path, &statfs); + err = vfs_statfs(&path, &args.statfs); if (err) goto out_nfserr; } - if ((bmval0 & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { + if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && + !fhp) { tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); status = nfserr_jukebox; if (!tempfh) @@ -3015,12 +3568,15 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, status = fh_compose(tempfh, exp, dentry, NULL); if (status) goto out; - fhp = tempfh; - } - if (bmval0 & FATTR4_WORD0_ACL) { - err = nfsd4_get_nfs4_acl(rqstp, dentry, &acl); + args.fhp = tempfh; + } else + args.fhp = fhp; + + args.acl = NULL; + if (u.attrmask[0] & FATTR4_WORD0_ACL) { + err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) - bmval0 &= ~FATTR4_WORD0_ACL; + u.attrmask[0] &= ~FATTR4_WORD0_ACL; else if (err == -EINVAL) { status = nfserr_attrnotsupp; goto out; @@ -3028,452 +3584,53 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out_nfserr; } + args.contextsupport = false; + #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) || - bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { + args.context = NULL; + if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || + u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), - &context, &contextlen); + &args.context, &args.contextlen); else err = -EOPNOTSUPP; - contextsupport = (err == 0); - if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { + args.contextsupport = (err == 0); + if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { if (err == -EOPNOTSUPP) - bmval2 &= ~FATTR4_WORD2_SECURITY_LABEL; + u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; else if (err) goto out_nfserr; } } #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ - status = nfsd4_encode_bitmap(xdr, bmval0, bmval1, bmval2); + /* attrmask */ + status = nfsd4_encode_bitmap4(xdr, u.attrmask[0], + u.attrmask[1], u.attrmask[2]); if (status) goto out; + /* attr_vals */ attrlen_offset = xdr->buf->len; attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); if (!attrlen_p) goto out_resource; - - if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { - u32 supp[3]; - - memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp)); - - if (!IS_POSIXACL(dentry->d_inode)) - supp[0] &= ~FATTR4_WORD0_ACL; - if (!contextsupport) - supp[2] &= ~FATTR4_WORD2_SECURITY_LABEL; - if (!supp[2]) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(2); - *p++ = cpu_to_be32(supp[0]); - *p++ = cpu_to_be32(supp[1]); - } else { - p = xdr_reserve_space(xdr, 16); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(supp[0]); - *p++ = cpu_to_be32(supp[1]); - *p++ = cpu_to_be32(supp[2]); - } - } - if (bmval0 & FATTR4_WORD0_TYPE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - dummy = nfs4_file_type(stat.mode); - if (dummy == NF4BAD) { - status = nfserr_serverfault; + for_each_set_bit(bit, (const unsigned long *)&u.mask, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) { + status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args); + if (status != nfs_ok) goto out; - } - *p++ = cpu_to_be32(dummy); - } - if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) - *p++ = cpu_to_be32(NFS4_FH_PERSISTENT); - else - *p++ = cpu_to_be32(NFS4_FH_PERSISTENT| - NFS4_FH_VOL_RENAME); } - if (bmval0 & FATTR4_WORD0_CHANGE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = encode_change(p, &stat, d_inode(dentry), exp); - } - if (bmval0 & FATTR4_WORD0_SIZE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, stat.size); - } - if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_NAMED_ATTR) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(0); - } - if (bmval0 & FATTR4_WORD0_FSID) { - p = xdr_reserve_space(xdr, 16); - if (!p) - goto out_resource; - if (exp->ex_fslocs.migrated) { - p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR); - p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR); - } else switch(fsid_source(fhp)) { - case FSIDSOURCE_FSID: - p = xdr_encode_hyper(p, (u64)exp->ex_fsid); - p = xdr_encode_hyper(p, (u64)0); - break; - case FSIDSOURCE_DEV: - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(MAJOR(stat.dev)); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(MINOR(stat.dev)); - break; - case FSIDSOURCE_UUID: - p = xdr_encode_opaque_fixed(p, exp->ex_uuid, - EX_UUID_LEN); - break; - } - } - if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(0); - } - if (bmval0 & FATTR4_WORD0_LEASE_TIME) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(nn->nfsd4_lease); - } - if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(rdattr_err); - } - if (bmval0 & FATTR4_WORD0_ACL) { - struct nfs4_ace *ace; - - if (acl == NULL) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - - *p++ = cpu_to_be32(0); - goto out_acl; - } - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(acl->naces); - - for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) { - p = xdr_reserve_space(xdr, 4*3); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(ace->type); - *p++ = cpu_to_be32(ace->flag); - *p++ = cpu_to_be32(ace->access_mask & - NFS4_ACE_MASK_ALL); - status = nfsd4_encode_aclname(xdr, rqstp, ace); - if (status) - goto out; - } - } -out_acl: - if (bmval0 & FATTR4_WORD0_ACLSUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(IS_POSIXACL(dentry->d_inode) ? - ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0); - } - if (bmval0 & FATTR4_WORD0_CANSETTIME) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(0); - } - if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_FILEHANDLE) { - p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4); - if (!p) - goto out_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, - fhp->fh_handle.fh_size); - } - if (bmval0 & FATTR4_WORD0_FILEID) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, stat.ino); - } - if (bmval0 & FATTR4_WORD0_FILES_AVAIL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) statfs.f_ffree); - } - if (bmval0 & FATTR4_WORD0_FILES_FREE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) statfs.f_ffree); - } - if (bmval0 & FATTR4_WORD0_FILES_TOTAL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) statfs.f_files); - } - if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) { - status = nfsd4_encode_fs_locations(xdr, rqstp, exp); - if (status) - goto out; - } - if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval0 & FATTR4_WORD0_MAXFILESIZE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, exp->ex_path.mnt->mnt_sb->s_maxbytes); - } - if (bmval0 & FATTR4_WORD0_MAXLINK) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(255); - } - if (bmval0 & FATTR4_WORD0_MAXNAME) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(statfs.f_namelen); - } - if (bmval0 & FATTR4_WORD0_MAXREAD) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); - } - if (bmval0 & FATTR4_WORD0_MAXWRITE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp)); - } - if (bmval1 & FATTR4_WORD1_MODE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(stat.mode & S_IALLUGO); - } - if (bmval1 & FATTR4_WORD1_NO_TRUNC) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(1); - } - if (bmval1 & FATTR4_WORD1_NUMLINKS) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(stat.nlink); - } - if (bmval1 & FATTR4_WORD1_OWNER) { - status = nfsd4_encode_user(xdr, rqstp, stat.uid); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_OWNER_GROUP) { - status = nfsd4_encode_group(xdr, rqstp, stat.gid); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_RAWDEV) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - *p++ = cpu_to_be32((u32) MAJOR(stat.rdev)); - *p++ = cpu_to_be32((u32) MINOR(stat.rdev)); - } - if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_SPACE_FREE) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_SPACE_USED) { - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - dummy64 = (u64)stat.blocks << 9; - p = xdr_encode_hyper(p, dummy64); - } - if (bmval1 & FATTR4_WORD1_TIME_ACCESS) { - status = nfsd4_encode_nfstime4(xdr, &stat.atime); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_TIME_CREATE) { - status = nfsd4_encode_nfstime4(xdr, &stat.btime); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_TIME_DELTA) { - p = xdr_reserve_space(xdr, 12); - if (!p) - goto out_resource; - p = encode_time_delta(p, d_inode(dentry)); - } - if (bmval1 & FATTR4_WORD1_TIME_METADATA) { - status = nfsd4_encode_nfstime4(xdr, &stat.ctime); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_TIME_MODIFY) { - status = nfsd4_encode_nfstime4(xdr, &stat.mtime); - if (status) - goto out; - } - if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) { - u64 ino = stat.ino; - - p = xdr_reserve_space(xdr, 8); - if (!p) - goto out_resource; - /* - * Get ino of mountpoint in parent filesystem, if not ignoring - * crossmount and this is the root of a cross-mounted - * filesystem. - */ - if (ignore_crossmnt == 0 && - dentry == exp->ex_path.mnt->mnt_root) { - err = nfsd4_get_mounted_on_ino(exp, &ino); - if (err) - goto out_nfserr; - } - p = xdr_encode_hyper(p, ino); - } -#ifdef CONFIG_NFSD_PNFS - if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) { - status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types); - if (status) - goto out; - } - - if (bmval2 & FATTR4_WORD2_LAYOUT_TYPES) { - status = nfsd4_encode_layout_types(xdr, exp->ex_layout_types); - if (status) - goto out; - } - - if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - *p++ = cpu_to_be32(stat.blksize); - } -#endif /* CONFIG_NFSD_PNFS */ - if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { - u32 supp[3]; - - memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp)); - supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; - supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; - supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; - - status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]); - if (status) - goto out; - } - -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { - status = nfsd4_encode_security_label(xdr, rqstp, context, - contextlen); - if (status) - goto out; - } -#endif - - if (bmval2 & FATTR4_WORD2_XATTR_SUPPORT) { - p = xdr_reserve_space(xdr, 4); - if (!p) - goto out_resource; - err = xattr_supports_user_prefix(d_inode(dentry)); - *p++ = cpu_to_be32(err == 0); - } - *attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT); status = nfs_ok; out: #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (context) - security_release_secctx(context, contextlen); + if (args.context) + security_release_secctx(args.context, args.contextlen); #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ - kfree(acl); + kfree(args.acl); if (tempfh) { fh_put(tempfh); kfree(tempfh); @@ -3514,12 +3671,28 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, __be32 ret; svcxdr_init_encode_from_buffer(&xdr, &dummy, *p, words << 2); - ret = nfsd4_encode_fattr(&xdr, fhp, exp, dentry, bmval, rqstp, - ignore_crossmnt); + ret = nfsd4_encode_fattr4(rqstp, &xdr, fhp, exp, dentry, bmval, + ignore_crossmnt); *p = xdr.p; return ret; } +/* + * The buffer space for this field was reserved during a previous + * call to nfsd4_encode_entry4(). + */ +static void nfsd4_encode_entry4_nfs_cookie4(const struct nfsd4_readdir *readdir, + u64 offset) +{ + __be64 cookie = cpu_to_be64(offset); + struct xdr_stream *xdr = readdir->xdr; + + if (!readdir->cookie_offset) + return; + write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset, &cookie, + sizeof(cookie)); +} + static inline int attributes_need_mount(u32 *bmval) { if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME)) @@ -3530,8 +3703,8 @@ static inline int attributes_need_mount(u32 *bmval) } static __be32 -nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, - const char *name, int namlen) +nfsd4_encode_entry4_fattr(struct nfsd4_readdir *cd, const char *name, + int namlen) { struct svc_export *exp = cd->rd_fhp->fh_export; struct dentry *dentry; @@ -3574,33 +3747,34 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, } out_encode: - nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval, - cd->rd_rqstp, ignore_crossmnt); + nfserr = nfsd4_encode_fattr4(cd->rd_rqstp, cd->xdr, NULL, exp, dentry, + cd->rd_bmval, ignore_crossmnt); out_put: dput(dentry); exp_put(exp); return nfserr; } -static __be32 * -nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) +static __be32 +nfsd4_encode_entry4_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) { - __be32 *p; - - p = xdr_reserve_space(xdr, 20); - if (!p) - return NULL; - *p++ = htonl(2); - *p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */ - *p++ = htonl(0); /* bmval1 */ + __be32 status; - *p++ = htonl(4); /* attribute length */ - *p++ = nfserr; /* no htonl */ - return p; + /* attrmask */ + status = nfsd4_encode_bitmap4(xdr, FATTR4_WORD0_RDATTR_ERROR, 0, 0); + if (status != nfs_ok) + return status; + /* attr_vals */ + if (xdr_stream_encode_u32(xdr, XDR_UNIT) != XDR_UNIT) + return nfserr_resource; + /* rdattr_error */ + if (xdr_stream_encode_be32(xdr, nfserr) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; } static int -nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, +nfsd4_encode_entry4(void *ccdv, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { struct readdir_cd *ccd = ccdv; @@ -3611,8 +3785,6 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, u32 name_and_cookie; int entry_bytes; __be32 nfserr = nfserr_toosmall; - __be64 wire_offset; - __be32 *p; /* In nfsv4, "." and ".." never make it onto the wire.. */ if (name && isdotent(name, namlen)) { @@ -3620,24 +3792,19 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, return 0; } - if (cd->cookie_offset) { - wire_offset = cpu_to_be64(offset); - write_bytes_to_xdr_buf(xdr->buf, cd->cookie_offset, - &wire_offset, 8); - } + /* Encode the previous entry's cookie value */ + nfsd4_encode_entry4_nfs_cookie4(cd, offset); - p = xdr_reserve_space(xdr, 4); - if (!p) + if (xdr_stream_encode_item_present(xdr) != XDR_UNIT) goto fail; - *p++ = xdr_one; /* mark entry present */ + + /* Reserve send buffer space for this entry's cookie value. */ cookie_offset = xdr->buf->len; - p = xdr_reserve_space(xdr, 3*4 + namlen); - if (!p) + if (nfsd4_encode_nfs_cookie4(xdr, OFFSET_MAX) != nfs_ok) goto fail; - p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */ - p = xdr_encode_array(p, name, namlen); /* name length & name */ - - nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); + if (nfsd4_encode_component4(xdr, name, namlen) != nfs_ok) + goto fail; + nfserr = nfsd4_encode_entry4_fattr(cd, name, namlen); switch (nfserr) { case nfs_ok: break; @@ -3668,8 +3835,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, */ if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR)) goto fail; - p = nfsd4_encode_rdattr_error(xdr, nfserr); - if (p == NULL) { + if (nfsd4_encode_entry4_rdattr_error(xdr, nfserr)) { nfserr = nfserr_toosmall; goto fail; } @@ -3727,18 +3893,26 @@ nfsd4_encode_clientid4(struct xdr_stream *xdr, const clientid_t *clientid) return nfs_ok; } +/* This is a frequently-encoded item; open-coded for speed */ static __be32 -nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) +nfsd4_encode_stateid4(struct xdr_stream *xdr, const stateid_t *sid) { __be32 *p; - p = xdr_reserve_space(xdr, sizeof(stateid_t)); + p = xdr_reserve_space(xdr, NFS4_STATEID_SIZE); if (!p) return nfserr_resource; *p++ = cpu_to_be32(sid->si_generation); - p = xdr_encode_opaque_fixed(p, &sid->si_opaque, - sizeof(stateid_opaque_t)); - return 0; + memcpy(p, &sid->si_opaque, sizeof(sid->si_opaque)); + return nfs_ok; +} + +static __be32 +nfsd4_encode_sessionid4(struct xdr_stream *xdr, + const struct nfs4_sessionid *sessionid) +{ + return nfsd4_encode_opaque_fixed(xdr, sessionid->data, + NFS4_MAX_SESSIONID_LEN); } static __be32 @@ -3747,14 +3921,14 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_access *access = &u->access; struct xdr_stream *xdr = resp->xdr; - __be32 *p; + __be32 status; - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(access->ac_supported); - *p++ = cpu_to_be32(access->ac_resp_access); - return 0; + /* supported */ + status = nfsd4_encode_uint32_t(xdr, access->ac_supported); + if (status != nfs_ok) + return status; + /* access */ + return nfsd4_encode_uint32_t(xdr, access->ac_resp_access); } static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, @@ -3762,17 +3936,16 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, { struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8); - if (!p) + /* bctsr_sessid */ + nfserr = nfsd4_encode_sessionid4(xdr, &bcts->sessionid); + if (nfserr != nfs_ok) + return nfserr; + /* bctsr_dir */ + if (xdr_stream_encode_u32(xdr, bcts->dir) != XDR_UNIT) return nfserr_resource; - p = xdr_encode_opaque_fixed(p, bcts->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(bcts->dir); - /* Upshifting from TCP to RDMA is not supported */ - *p++ = cpu_to_be32(0); - return 0; + /* bctsr_use_conn_in_rdma_mode */ + return nfsd4_encode_bool(xdr, false); } static __be32 @@ -3782,7 +3955,8 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close = &u->close; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &close->cl_stateid); + /* open_stateid */ + return nfsd4_encode_stateid4(xdr, &close->cl_stateid); } @@ -3802,11 +3976,13 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; + /* cinfo */ nfserr = nfsd4_encode_change_info4(xdr, &create->cr_cinfo); if (nfserr) return nfserr; - return nfsd4_encode_bitmap(xdr, create->cr_bmval[0], - create->cr_bmval[1], create->cr_bmval[2]); + /* attrset */ + return nfsd4_encode_bitmap4(xdr, create->cr_bmval[0], + create->cr_bmval[1], create->cr_bmval[2]); } static __be32 @@ -3817,65 +3993,56 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry, - getattr->ga_bmval, resp->rqstp, 0); + /* obj_attributes */ + return nfsd4_encode_fattr4(resp->rqstp, xdr, fhp, fhp->fh_export, + fhp->fh_dentry, getattr->ga_bmval, 0); } static __be32 nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { - struct svc_fh **fhpp = &u->getfh; struct xdr_stream *xdr = resp->xdr; - struct svc_fh *fhp = *fhpp; - unsigned int len; - __be32 *p; + struct svc_fh *fhp = u->getfh; - len = fhp->fh_handle.fh_size; - p = xdr_reserve_space(xdr, len + 4); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_raw, len); - return 0; + /* object */ + return nfsd4_encode_nfs_fh4(xdr, &fhp->fh_handle); } -/* -* Including all fields other than the name, a LOCK4denied structure requires -* 8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes. -*/ static __be32 -nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld) +nfsd4_encode_lock_owner4(struct xdr_stream *xdr, const clientid_t *clientid, + const struct xdr_netobj *owner) { - struct xdr_netobj *conf = &ld->ld_owner; - __be32 *p; + __be32 status; -again: - p = xdr_reserve_space(xdr, 32 + XDR_LEN(conf->len)); - if (!p) { - /* - * Don't fail to return the result just because we can't - * return the conflicting open: - */ - if (conf->len) { - kfree(conf->data); - conf->len = 0; - conf->data = NULL; - goto again; - } + /* clientid */ + status = nfsd4_encode_clientid4(xdr, clientid); + if (status != nfs_ok) + return status; + /* owner */ + return nfsd4_encode_opaque(xdr, owner->data, owner->len); +} + +static __be32 +nfsd4_encode_lock4denied(struct xdr_stream *xdr, + const struct nfsd4_lock_denied *ld) +{ + __be32 status; + + /* offset */ + status = nfsd4_encode_offset4(xdr, ld->ld_start); + if (status != nfs_ok) + return status; + /* length */ + status = nfsd4_encode_length4(xdr, ld->ld_length); + if (status != nfs_ok) + return status; + /* locktype */ + if (xdr_stream_encode_u32(xdr, ld->ld_type) != XDR_UNIT) return nfserr_resource; - } - p = xdr_encode_hyper(p, ld->ld_start); - p = xdr_encode_hyper(p, ld->ld_length); - *p++ = cpu_to_be32(ld->ld_type); - if (conf->len) { - p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8); - p = xdr_encode_opaque(p, conf->data, conf->len); - kfree(conf->data); - } else { /* non - nfsv4 lock in conflict, no clientid nor owner */ - p = xdr_encode_hyper(p, (u64)0); /* clientid */ - *p++ = cpu_to_be32(0); /* length of owner name */ - } - return nfserr_denied; + /* owner */ + return nfsd4_encode_lock_owner4(xdr, &ld->ld_clientid, + &ld->ld_owner); } static __be32 @@ -3884,13 +4051,21 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_lock *lock = &u->lock; struct xdr_stream *xdr = resp->xdr; + __be32 status; - if (!nfserr) - nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid); - else if (nfserr == nfserr_denied) - nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied); - - return nfserr; + switch (nfserr) { + case nfs_ok: + /* resok4 */ + status = nfsd4_encode_stateid4(xdr, &lock->lk_resp_stateid); + break; + case nfserr_denied: + /* denied */ + status = nfsd4_encode_lock4denied(xdr, &lock->lk_denied); + break; + default: + return nfserr; + } + return status != nfs_ok ? status : nfserr; } static __be32 @@ -3899,9 +4074,14 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_lockt *lockt = &u->lockt; struct xdr_stream *xdr = resp->xdr; + __be32 status; - if (nfserr == nfserr_denied) - nfsd4_encode_lock_denied(xdr, &lockt->lt_denied); + if (nfserr == nfserr_denied) { + /* denied */ + status = nfsd4_encode_lock4denied(xdr, &lockt->lt_denied); + if (status != nfs_ok) + return status; + } return nfserr; } @@ -3912,7 +4092,8 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku = &u->locku; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &locku->lu_stateid); + /* lock_stateid */ + return nfsd4_encode_stateid4(xdr, &locku->lu_stateid); } @@ -3926,104 +4107,159 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, return nfsd4_encode_change_info4(xdr, &link->li_cinfo); } +/* + * This implementation does not yet support returning an ACE in an + * OPEN that offers a delegation. + */ +static __be32 +nfsd4_encode_open_nfsace4(struct xdr_stream *xdr) +{ + __be32 status; + + /* type */ + status = nfsd4_encode_acetype4(xdr, NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); + if (status != nfs_ok) + return nfserr_resource; + /* flag */ + status = nfsd4_encode_aceflag4(xdr, 0); + if (status != nfs_ok) + return nfserr_resource; + /* access mask */ + status = nfsd4_encode_acemask4(xdr, 0); + if (status != nfs_ok) + return nfserr_resource; + /* who - empty for now */ + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; +} static __be32 -nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_open_read_delegation4(struct xdr_stream *xdr, struct nfsd4_open *open) { - struct nfsd4_open *open = &u->open; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; + __be32 status; - nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); - if (nfserr) - return nfserr; - nfserr = nfsd4_encode_change_info4(xdr, &open->op_cinfo); - if (nfserr) - return nfserr; - if (xdr_stream_encode_u32(xdr, open->op_rflags) < 0) + /* stateid */ + status = nfsd4_encode_stateid4(xdr, &open->op_delegate_stateid); + if (status != nfs_ok) + return status; + /* recall */ + status = nfsd4_encode_bool(xdr, open->op_recall); + if (status != nfs_ok) + return status; + /* permissions */ + return nfsd4_encode_open_nfsace4(xdr); +} + +static __be32 +nfsd4_encode_nfs_space_limit4(struct xdr_stream *xdr, u64 filesize) +{ + /* limitby */ + if (xdr_stream_encode_u32(xdr, NFS4_LIMIT_SIZE) != XDR_UNIT) return nfserr_resource; + /* filesize */ + return nfsd4_encode_uint64_t(xdr, filesize); +} - nfserr = nfsd4_encode_bitmap(xdr, open->op_bmval[0], open->op_bmval[1], - open->op_bmval[2]); - if (nfserr) - return nfserr; +static __be32 +nfsd4_encode_open_write_delegation4(struct xdr_stream *xdr, + struct nfsd4_open *open) +{ + __be32 status; - p = xdr_reserve_space(xdr, 4); - if (!p) + /* stateid */ + status = nfsd4_encode_stateid4(xdr, &open->op_delegate_stateid); + if (status != nfs_ok) + return status; + /* recall */ + status = nfsd4_encode_bool(xdr, open->op_recall); + if (status != nfs_ok) + return status; + /* space_limit */ + status = nfsd4_encode_nfs_space_limit4(xdr, 0); + if (status != nfs_ok) + return status; + return nfsd4_encode_open_nfsace4(xdr); +} + +static __be32 +nfsd4_encode_open_none_delegation4(struct xdr_stream *xdr, + struct nfsd4_open *open) +{ + __be32 status = nfs_ok; + + /* ond_why */ + if (xdr_stream_encode_u32(xdr, open->op_why_no_deleg) != XDR_UNIT) return nfserr_resource; + switch (open->op_why_no_deleg) { + case WND4_CONTENTION: + /* ond_server_will_push_deleg */ + status = nfsd4_encode_bool(xdr, false); + break; + case WND4_RESOURCE: + /* ond_server_will_signal_avail */ + status = nfsd4_encode_bool(xdr, false); + } + return status; +} + +static __be32 +nfsd4_encode_open_delegation4(struct xdr_stream *xdr, struct nfsd4_open *open) +{ + __be32 status; - *p++ = cpu_to_be32(open->op_delegate_type); + /* delegation_type */ + if (xdr_stream_encode_u32(xdr, open->op_delegate_type) != XDR_UNIT) + return nfserr_resource; switch (open->op_delegate_type) { case NFS4_OPEN_DELEGATE_NONE: + status = nfs_ok; break; case NFS4_OPEN_DELEGATE_READ: - nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_recall); - - /* - * TODO: ACE's in delegations - */ - *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ + /* read */ + status = nfsd4_encode_open_read_delegation4(xdr, open); break; case NFS4_OPEN_DELEGATE_WRITE: - nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); - if (nfserr) - return nfserr; - - p = xdr_reserve_space(xdr, XDR_UNIT * 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_recall); - - /* - * Always flush on close - * - * TODO: space_limit's in delegations - */ - *p++ = cpu_to_be32(NFS4_LIMIT_SIZE); - *p++ = xdr_zero; - *p++ = xdr_zero; - - /* - * TODO: ACE's in delegations - */ - *p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); /* XXX: is NULL principal ok? */ + /* write */ + status = nfsd4_encode_open_write_delegation4(xdr, open); break; - case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */ - switch (open->op_why_no_deleg) { - case WND4_CONTENTION: - case WND4_RESOURCE: - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_why_no_deleg); - /* deleg signaling not supported yet: */ - *p++ = cpu_to_be32(0); - break; - default: - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(open->op_why_no_deleg); - } + case NFS4_OPEN_DELEGATE_NONE_EXT: + /* od_whynone */ + status = nfsd4_encode_open_none_delegation4(xdr, open); break; default: - BUG(); + status = nfserr_serverfault; } - /* XXX save filehandle here */ - return 0; + + return status; +} + +static __be32 +nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_open *open = &u->open; + struct xdr_stream *xdr = resp->xdr; + + /* stateid */ + nfserr = nfsd4_encode_stateid4(xdr, &open->op_stateid); + if (nfserr != nfs_ok) + return nfserr; + /* cinfo */ + nfserr = nfsd4_encode_change_info4(xdr, &open->op_cinfo); + if (nfserr != nfs_ok) + return nfserr; + /* rflags */ + nfserr = nfsd4_encode_uint32_t(xdr, open->op_rflags); + if (nfserr != nfs_ok) + return nfserr; + /* attrset */ + nfserr = nfsd4_encode_bitmap4(xdr, open->op_bmval[0], + open->op_bmval[1], open->op_bmval[2]); + if (nfserr != nfs_ok) + return nfserr; + /* delegation */ + return nfsd4_encode_open_delegation4(xdr, open); } static __be32 @@ -4033,7 +4269,8 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc = &u->open_confirm; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); + /* open_stateid */ + return nfsd4_encode_stateid4(xdr, &oc->oc_resp_stateid); } static __be32 @@ -4043,7 +4280,8 @@ nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od = &u->open_downgrade; struct xdr_stream *xdr = resp->xdr; - return nfsd4_encode_stateid(xdr, &od->od_stateid); + /* open_stateid */ + return nfsd4_encode_stateid4(xdr, &od->od_stateid); } /* @@ -4113,6 +4351,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, struct file *file, unsigned long maxcount) { struct xdr_stream *xdr = resp->xdr; + unsigned int base = xdr->buf->page_len & ~PAGE_MASK; unsigned int starting_len = xdr->buf->len; __be32 zero = xdr_zero; __be32 nfserr; @@ -4121,8 +4360,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, return nfserr_resource; nfserr = nfsd_iter_read(resp->rqstp, read->rd_fhp, file, - read->rd_offset, &maxcount, - xdr->buf->page_len & ~PAGE_MASK, + read->rd_offset, &maxcount, base, &read->rd_eof); read->rd_length = maxcount; if (nfserr) @@ -4227,90 +4465,83 @@ out_err: return nfserr; } -static __be32 -nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +static __be32 nfsd4_encode_dirlist4(struct xdr_stream *xdr, + struct nfsd4_readdir *readdir, + u32 max_payload) { - struct nfsd4_readdir *readdir = &u->readdir; - int maxcount; - int bytes_left; + int bytes_left, maxcount, starting_len = xdr->buf->len; loff_t offset; - __be64 wire_offset; - struct xdr_stream *xdr = resp->xdr; - int starting_len = xdr->buf->len; - __be32 *p; - - nfserr = nfsd4_encode_verifier4(xdr, &readdir->rd_verf); - if (nfserr != nfs_ok) - return nfserr; + __be32 status; /* * Number of bytes left for directory entries allowing for the - * final 8 bytes of the readdir and a following failed op: + * final 8 bytes of the readdir and a following failed op. */ - bytes_left = xdr->buf->buflen - xdr->buf->len - - COMPOUND_ERR_SLACK_SPACE - 8; - if (bytes_left < 0) { - nfserr = nfserr_resource; - goto err_no_verf; - } - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(u32, readdir->rd_maxcount, maxcount); + bytes_left = xdr->buf->buflen - xdr->buf->len - + COMPOUND_ERR_SLACK_SPACE - XDR_UNIT * 2; + if (bytes_left < 0) + return nfserr_resource; + maxcount = min_t(u32, readdir->rd_maxcount, max_payload); + /* - * Note the rfc defines rd_maxcount as the size of the - * READDIR4resok structure, which includes the verifier above - * and the 8 bytes encoded at the end of this function: + * The RFC defines rd_maxcount as the size of the + * READDIR4resok structure, which includes the verifier + * and the 8 bytes encoded at the end of this function. */ - if (maxcount < 16) { - nfserr = nfserr_toosmall; - goto err_no_verf; - } - maxcount = min_t(int, maxcount-16, bytes_left); + if (maxcount < XDR_UNIT * 4) + return nfserr_toosmall; + maxcount = min_t(int, maxcount - XDR_UNIT * 4, bytes_left); - /* RFC 3530 14.2.24 allows us to ignore dircount when it's 0: */ + /* RFC 3530 14.2.24 allows us to ignore dircount when it's 0 */ if (!readdir->rd_dircount) - readdir->rd_dircount = svc_max_payload(resp->rqstp); + readdir->rd_dircount = max_payload; + /* *entries */ readdir->xdr = xdr; readdir->rd_maxcount = maxcount; readdir->common.err = 0; readdir->cookie_offset = 0; - offset = readdir->rd_cookie; - nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp, - &offset, - &readdir->common, nfsd4_encode_dirent); - if (nfserr == nfs_ok && - readdir->common.err == nfserr_toosmall && - xdr->buf->len == starting_len + 8) { - /* nothing encoded; which limit did we hit?: */ - if (maxcount - 16 < bytes_left) - /* It was the fault of rd_maxcount: */ - nfserr = nfserr_toosmall; - else - /* We ran out of buffer space: */ - nfserr = nfserr_resource; + status = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp, &offset, + &readdir->common, nfsd4_encode_entry4); + if (status) + return status; + if (readdir->common.err == nfserr_toosmall && + xdr->buf->len == starting_len) { + /* No entries were encoded. Which limit did we hit? */ + if (maxcount - XDR_UNIT * 4 < bytes_left) + /* It was the fault of rd_maxcount */ + return nfserr_toosmall; + /* We ran out of buffer space */ + return nfserr_resource; } - if (nfserr) - goto err_no_verf; + /* Encode the final entry's cookie value */ + nfsd4_encode_entry4_nfs_cookie4(readdir, offset); + /* No entries follow */ + if (xdr_stream_encode_item_absent(xdr) != XDR_UNIT) + return nfserr_resource; - if (readdir->cookie_offset) { - wire_offset = cpu_to_be64(offset); - write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset, - &wire_offset, 8); - } + /* eof */ + return nfsd4_encode_bool(xdr, readdir->common.err == nfserr_eof); +} - p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - goto err_no_verf; - } - *p++ = 0; /* no more entries */ - *p++ = htonl(readdir->common.err == nfserr_eof); +static __be32 +nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_readdir *readdir = &u->readdir; + struct xdr_stream *xdr = resp->xdr; + int starting_len = xdr->buf->len; - return 0; -err_no_verf: - xdr_truncate_encode(xdr, starting_len); + /* cookieverf */ + nfserr = nfsd4_encode_verifier4(xdr, &readdir->rd_verf); + if (nfserr != nfs_ok) + return nfserr; + + /* reply */ + nfserr = nfsd4_encode_dirlist4(xdr, readdir, svc_max_payload(resp->rqstp)); + if (nfserr != nfs_ok) + xdr_truncate_encode(xdr, starting_len); return nfserr; } @@ -4338,13 +4569,34 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 +nfsd4_encode_rpcsec_gss_info(struct xdr_stream *xdr, + struct rpcsec_gss_info *info) +{ + __be32 status; + + /* oid */ + if (xdr_stream_encode_opaque(xdr, info->oid.data, info->oid.len) < 0) + return nfserr_resource; + /* qop */ + status = nfsd4_encode_qop4(xdr, info->qop); + if (status != nfs_ok) + return status; + /* service */ + if (xdr_stream_encode_u32(xdr, info->service) != XDR_UNIT) + return nfserr_resource; + + return nfs_ok; +} + +static __be32 nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) { u32 i, nflavs, supported; struct exp_flavor_info *flavs; struct exp_flavor_info def_flavs[2]; - __be32 *p, *flavorsp; static bool report = true; + __be32 *flavorsp; + __be32 status; if (exp->ex_nflavors) { flavs = exp->ex_flavors; @@ -4367,10 +4619,9 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) } supported = 0; - p = xdr_reserve_space(xdr, 4); - if (!p) + flavorsp = xdr_reserve_space(xdr, XDR_UNIT); + if (!flavorsp) return nfserr_resource; - flavorsp = p++; /* to be backfilled later */ for (i = 0; i < nflavs; i++) { rpc_authflavor_t pf = flavs[i].pseudoflavor; @@ -4378,20 +4629,22 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) if (rpcauth_get_gssinfo(pf, &info) == 0) { supported++; - p = xdr_reserve_space(xdr, 4 + 4 + - XDR_LEN(info.oid.len) + 4 + 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(RPC_AUTH_GSS); - p = xdr_encode_opaque(p, info.oid.data, info.oid.len); - *p++ = cpu_to_be32(info.qop); - *p++ = cpu_to_be32(info.service); + + /* flavor */ + status = nfsd4_encode_uint32_t(xdr, RPC_AUTH_GSS); + if (status != nfs_ok) + return status; + /* flavor_info */ + status = nfsd4_encode_rpcsec_gss_info(xdr, &info); + if (status != nfs_ok) + return status; } else if (pf < RPC_AUTH_MAXFLAVOR) { supported++; - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(pf); + + /* flavor */ + status = nfsd4_encode_uint32_t(xdr, pf); + if (status != nfs_ok) + return status; } else { if (report) pr_warn("NFS: SECINFO: security flavor %u " @@ -4401,7 +4654,7 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) if (nflavs != supported) report = false; - *flavorsp = htonl(supported); + *flavorsp = cpu_to_be32(supported); return 0; } @@ -4425,34 +4678,25 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); } -/* - * The SETATTR encode routine is special -- it always encodes a bitmap, - * regardless of the error status. - */ static __be32 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_setattr *setattr = &u->setattr; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; + __be32 status; - p = xdr_reserve_space(xdr, 16); - if (!p) - return nfserr_resource; - if (nfserr) { - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - *p++ = cpu_to_be32(0); - } - else { - *p++ = cpu_to_be32(3); - *p++ = cpu_to_be32(setattr->sa_bmval[0]); - *p++ = cpu_to_be32(setattr->sa_bmval[1]); - *p++ = cpu_to_be32(setattr->sa_bmval[2]); + switch (nfserr) { + case nfs_ok: + /* attrsset */ + status = nfsd4_encode_bitmap4(resp->xdr, setattr->sa_bmval[0], + setattr->sa_bmval[1], + setattr->sa_bmval[2]); + break; + default: + /* attrsset */ + status = nfsd4_encode_bitmap4(resp->xdr, 0, 0, 0); } - return nfserr; + return status != nfs_ok ? status : nfserr; } static __be32 @@ -4488,86 +4732,148 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_write *write = &u->write; + struct xdr_stream *xdr = resp->xdr; - if (xdr_stream_encode_u32(resp->xdr, write->wr_bytes_written) < 0) - return nfserr_resource; - if (xdr_stream_encode_u32(resp->xdr, write->wr_how_written) < 0) + /* count */ + nfserr = nfsd4_encode_count4(xdr, write->wr_bytes_written); + if (nfserr) + return nfserr; + /* committed */ + if (xdr_stream_encode_u32(xdr, write->wr_how_written) != XDR_UNIT) return nfserr_resource; - return nfsd4_encode_verifier4(resp->xdr, &write->wr_verifier); + /* writeverf */ + return nfsd4_encode_verifier4(xdr, &write->wr_verifier); } static __be32 -nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_state_protect_ops4(struct xdr_stream *xdr, + struct nfsd4_exchange_id *exid) { - struct nfsd4_exchange_id *exid = &u->exchange_id; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - char *major_id; - char *server_scope; - int major_id_sz; - int server_scope_sz; - uint64_t minor_id = 0; - struct nfsd_net *nn = net_generic(SVC_NET(resp->rqstp), nfsd_net_id); + __be32 status; - major_id = nn->nfsd_name; - major_id_sz = strlen(nn->nfsd_name); - server_scope = nn->nfsd_name; - server_scope_sz = strlen(nn->nfsd_name); + /* spo_must_enforce */ + status = nfsd4_encode_bitmap4(xdr, exid->spo_must_enforce[0], + exid->spo_must_enforce[1], + exid->spo_must_enforce[2]); + if (status != nfs_ok) + return status; + /* spo_must_allow */ + return nfsd4_encode_bitmap4(xdr, exid->spo_must_allow[0], + exid->spo_must_allow[1], + exid->spo_must_allow[2]); +} - if (nfsd4_encode_clientid4(xdr, &exid->clientid) != nfs_ok) - return nfserr_resource; - if (xdr_stream_encode_u32(xdr, exid->seqid) < 0) - return nfserr_resource; - if (xdr_stream_encode_u32(xdr, exid->flags) < 0) - return nfserr_resource; +static __be32 +nfsd4_encode_state_protect4_r(struct xdr_stream *xdr, struct nfsd4_exchange_id *exid) +{ + __be32 status; - if (xdr_stream_encode_u32(xdr, exid->spa_how) < 0) + if (xdr_stream_encode_u32(xdr, exid->spa_how) != XDR_UNIT) return nfserr_resource; switch (exid->spa_how) { case SP4_NONE: + status = nfs_ok; break; case SP4_MACH_CRED: - /* spo_must_enforce bitmap: */ - nfserr = nfsd4_encode_bitmap(xdr, - exid->spo_must_enforce[0], - exid->spo_must_enforce[1], - exid->spo_must_enforce[2]); - if (nfserr) - return nfserr; - /* spo_must_allow bitmap: */ - nfserr = nfsd4_encode_bitmap(xdr, - exid->spo_must_allow[0], - exid->spo_must_allow[1], - exid->spo_must_allow[2]); - if (nfserr) - return nfserr; + /* spr_mach_ops */ + status = nfsd4_encode_state_protect_ops4(xdr, exid); break; default: - WARN_ON_ONCE(1); + status = nfserr_serverfault; } + return status; +} - p = xdr_reserve_space(xdr, - 8 /* so_minor_id */ + - 4 /* so_major_id.len */ + - (XDR_QUADLEN(major_id_sz) * 4) + - 4 /* eir_server_scope.len */ + - (XDR_QUADLEN(server_scope_sz) * 4) + - 4 /* eir_server_impl_id.count (0) */); - if (!p) +static __be32 +nfsd4_encode_server_owner4(struct xdr_stream *xdr, struct svc_rqst *rqstp) +{ + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + __be32 status; + + /* so_minor_id */ + status = nfsd4_encode_uint64_t(xdr, 0); + if (status != nfs_ok) + return status; + /* so_major_id */ + return nfsd4_encode_opaque(xdr, nn->nfsd_name, strlen(nn->nfsd_name)); +} + +static __be32 +nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd_net *nn = net_generic(SVC_NET(resp->rqstp), nfsd_net_id); + struct nfsd4_exchange_id *exid = &u->exchange_id; + struct xdr_stream *xdr = resp->xdr; + + /* eir_clientid */ + nfserr = nfsd4_encode_clientid4(xdr, &exid->clientid); + if (nfserr != nfs_ok) + return nfserr; + /* eir_sequenceid */ + nfserr = nfsd4_encode_sequenceid4(xdr, exid->seqid); + if (nfserr != nfs_ok) + return nfserr; + /* eir_flags */ + nfserr = nfsd4_encode_uint32_t(xdr, exid->flags); + if (nfserr != nfs_ok) + return nfserr; + /* eir_state_protect */ + nfserr = nfsd4_encode_state_protect4_r(xdr, exid); + if (nfserr != nfs_ok) + return nfserr; + /* eir_server_owner */ + nfserr = nfsd4_encode_server_owner4(xdr, resp->rqstp); + if (nfserr != nfs_ok) + return nfserr; + /* eir_server_scope */ + nfserr = nfsd4_encode_opaque(xdr, nn->nfsd_name, + strlen(nn->nfsd_name)); + if (nfserr != nfs_ok) + return nfserr; + /* eir_server_impl_id<1> */ + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) return nfserr_resource; - /* The server_owner struct */ - p = xdr_encode_hyper(p, minor_id); /* Minor id */ - /* major id */ - p = xdr_encode_opaque(p, major_id, major_id_sz); + return nfs_ok; +} - /* Server scope */ - p = xdr_encode_opaque(p, server_scope, server_scope_sz); +static __be32 +nfsd4_encode_channel_attrs4(struct xdr_stream *xdr, + const struct nfsd4_channel_attrs *attrs) +{ + __be32 status; - /* Implementation id */ - *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */ - return 0; + /* ca_headerpadsize */ + status = nfsd4_encode_count4(xdr, 0); + if (status != nfs_ok) + return status; + /* ca_maxrequestsize */ + status = nfsd4_encode_count4(xdr, attrs->maxreq_sz); + if (status != nfs_ok) + return status; + /* ca_maxresponsesize */ + status = nfsd4_encode_count4(xdr, attrs->maxresp_sz); + if (status != nfs_ok) + return status; + /* ca_maxresponsesize_cached */ + status = nfsd4_encode_count4(xdr, attrs->maxresp_cached); + if (status != nfs_ok) + return status; + /* ca_maxoperations */ + status = nfsd4_encode_count4(xdr, attrs->maxops); + if (status != nfs_ok) + return status; + /* ca_maxrequests */ + status = nfsd4_encode_count4(xdr, attrs->maxreqs); + if (status != nfs_ok) + return status; + /* ca_rdma_ird<1> */ + if (xdr_stream_encode_u32(xdr, attrs->nr_rdma_attrs) != XDR_UNIT) + return nfserr_resource; + if (attrs->nr_rdma_attrs) + return nfsd4_encode_uint32_t(xdr, attrs->rdma_attrs); + return nfs_ok; } static __be32 @@ -4576,52 +4882,25 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_create_session *sess = &u->create_session; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - - p = xdr_reserve_space(xdr, 24); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, sess->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(sess->seqid); - *p++ = cpu_to_be32(sess->flags); - p = xdr_reserve_space(xdr, 28); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(0); /* headerpadsz */ - *p++ = cpu_to_be32(sess->fore_channel.maxreq_sz); - *p++ = cpu_to_be32(sess->fore_channel.maxresp_sz); - *p++ = cpu_to_be32(sess->fore_channel.maxresp_cached); - *p++ = cpu_to_be32(sess->fore_channel.maxops); - *p++ = cpu_to_be32(sess->fore_channel.maxreqs); - *p++ = cpu_to_be32(sess->fore_channel.nr_rdma_attrs); - - if (sess->fore_channel.nr_rdma_attrs) { - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(sess->fore_channel.rdma_attrs); - } - - p = xdr_reserve_space(xdr, 28); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(0); /* headerpadsz */ - *p++ = cpu_to_be32(sess->back_channel.maxreq_sz); - *p++ = cpu_to_be32(sess->back_channel.maxresp_sz); - *p++ = cpu_to_be32(sess->back_channel.maxresp_cached); - *p++ = cpu_to_be32(sess->back_channel.maxops); - *p++ = cpu_to_be32(sess->back_channel.maxreqs); - *p++ = cpu_to_be32(sess->back_channel.nr_rdma_attrs); - - if (sess->back_channel.nr_rdma_attrs) { - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(sess->back_channel.rdma_attrs); - } - return 0; + /* csr_sessionid */ + nfserr = nfsd4_encode_sessionid4(xdr, &sess->sessionid); + if (nfserr != nfs_ok) + return nfserr; + /* csr_sequence */ + nfserr = nfsd4_encode_sequenceid4(xdr, sess->seqid); + if (nfserr != nfs_ok) + return nfserr; + /* csr_flags */ + nfserr = nfsd4_encode_uint32_t(xdr, sess->flags); + if (nfserr != nfs_ok) + return nfserr; + /* csr_fore_chan_attrs */ + nfserr = nfsd4_encode_channel_attrs4(xdr, &sess->fore_channel); + if (nfserr != nfs_ok) + return nfserr; + /* csr_back_chan_attrs */ + return nfsd4_encode_channel_attrs4(xdr, &sess->back_channel); } static __be32 @@ -4630,22 +4909,35 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_sequence *seq = &u->sequence; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, seq->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(seq->seqid); - *p++ = cpu_to_be32(seq->slotid); + /* sr_sessionid */ + nfserr = nfsd4_encode_sessionid4(xdr, &seq->sessionid); + if (nfserr != nfs_ok) + return nfserr; + /* sr_sequenceid */ + nfserr = nfsd4_encode_sequenceid4(xdr, seq->seqid); + if (nfserr != nfs_ok) + return nfserr; + /* sr_slotid */ + nfserr = nfsd4_encode_slotid4(xdr, seq->slotid); + if (nfserr != nfs_ok) + return nfserr; /* Note slotid's are numbered from zero: */ - *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_highest_slotid */ - *p++ = cpu_to_be32(seq->maxslots - 1); /* sr_target_highest_slotid */ - *p++ = cpu_to_be32(seq->status_flags); + /* sr_highest_slotid */ + nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1); + if (nfserr != nfs_ok) + return nfserr; + /* sr_target_highest_slotid */ + nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1); + if (nfserr != nfs_ok) + return nfserr; + /* sr_status_flags */ + nfserr = nfsd4_encode_uint32_t(xdr, seq->status_flags); + if (nfserr != nfs_ok) + return nfserr; resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */ - return 0; + return nfs_ok; } static __be32 @@ -4653,125 +4945,132 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_test_stateid *test_stateid = &u->test_stateid; - struct xdr_stream *xdr = resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; - __be32 *p; + struct xdr_stream *xdr = resp->xdr; - p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids)); - if (!p) + /* tsr_status_codes<> */ + if (xdr_stream_encode_u32(xdr, test_stateid->ts_num_ids) != XDR_UNIT) return nfserr_resource; - *p++ = htonl(test_stateid->ts_num_ids); - - list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) { - *p++ = stateid->ts_id_status; + list_for_each_entry_safe(stateid, next, + &test_stateid->ts_stateid_list, ts_id_list) { + if (xdr_stream_encode_be32(xdr, stateid->ts_id_status) != XDR_UNIT) + return nfserr_resource; } - - return 0; + return nfs_ok; } #ifdef CONFIG_NFSD_PNFS static __be32 -nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_device_addr4(struct xdr_stream *xdr, + const struct nfsd4_getdeviceinfo *gdev) { - struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; - struct xdr_stream *xdr = resp->xdr; + u32 needed_len, starting_len = xdr->buf->len; const struct nfsd4_layout_ops *ops; - u32 starting_len = xdr->buf->len, needed_len; - __be32 *p; + __be32 status; - p = xdr_reserve_space(xdr, 4); - if (!p) + /* da_layout_type */ + if (xdr_stream_encode_u32(xdr, gdev->gd_layout_type) != XDR_UNIT) return nfserr_resource; - - *p++ = cpu_to_be32(gdev->gd_layout_type); - + /* da_addr_body */ ops = nfsd4_layout_ops[gdev->gd_layout_type]; - nfserr = ops->encode_getdeviceinfo(xdr, gdev); - if (nfserr) { + status = ops->encode_getdeviceinfo(xdr, gdev); + if (status != nfs_ok) { /* - * We don't bother to burden the layout drivers with - * enforcing gd_maxcount, just tell the client to - * come back with a bigger buffer if it's not enough. + * Don't burden the layout drivers with enforcing + * gd_maxcount. Just tell the client to come back + * with a bigger buffer if it's not enough. */ - if (xdr->buf->len + 4 > gdev->gd_maxcount) + if (xdr->buf->len + XDR_UNIT > gdev->gd_maxcount) goto toosmall; - return nfserr; + return status; } - if (gdev->gd_notify_types) { - p = xdr_reserve_space(xdr, 4 + 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(1); /* bitmap length */ - *p++ = cpu_to_be32(gdev->gd_notify_types); - } else { - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = 0; - } + return nfs_ok; - return 0; toosmall: - dprintk("%s: maxcount too small\n", __func__); - needed_len = xdr->buf->len + 4 /* notifications */; + needed_len = xdr->buf->len + XDR_UNIT; /* notifications */ xdr_truncate_encode(xdr, starting_len); - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(needed_len); + + status = nfsd4_encode_count4(xdr, needed_len); + if (status != nfs_ok) + return status; return nfserr_toosmall; } static __be32 -nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, +nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { - struct nfsd4_layoutget *lgp = &u->layoutget; + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; struct xdr_stream *xdr = resp->xdr; - const struct nfsd4_layout_ops *ops; - __be32 *p; - - p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t)); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(1); /* we always set return-on-close */ - *p++ = cpu_to_be32(lgp->lg_sid.si_generation); - p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque, - sizeof(stateid_opaque_t)); + /* gdir_device_addr */ + nfserr = nfsd4_encode_device_addr4(xdr, gdev); + if (nfserr) + return nfserr; + /* gdir_notification */ + return nfsd4_encode_bitmap4(xdr, gdev->gd_notify_types, 0, 0); +} - *p++ = cpu_to_be32(1); /* we always return a single layout */ - p = xdr_encode_hyper(p, lgp->lg_seg.offset); - p = xdr_encode_hyper(p, lgp->lg_seg.length); - *p++ = cpu_to_be32(lgp->lg_seg.iomode); - *p++ = cpu_to_be32(lgp->lg_layout_type); +static __be32 +nfsd4_encode_layout4(struct xdr_stream *xdr, const struct nfsd4_layoutget *lgp) +{ + const struct nfsd4_layout_ops *ops = nfsd4_layout_ops[lgp->lg_layout_type]; + __be32 status; - ops = nfsd4_layout_ops[lgp->lg_layout_type]; + /* lo_offset */ + status = nfsd4_encode_offset4(xdr, lgp->lg_seg.offset); + if (status != nfs_ok) + return status; + /* lo_length */ + status = nfsd4_encode_length4(xdr, lgp->lg_seg.length); + if (status != nfs_ok) + return status; + /* lo_iomode */ + if (xdr_stream_encode_u32(xdr, lgp->lg_seg.iomode) != XDR_UNIT) + return nfserr_resource; + /* lo_content */ + if (xdr_stream_encode_u32(xdr, lgp->lg_layout_type) != XDR_UNIT) + return nfserr_resource; return ops->encode_layoutget(xdr, lgp); } static __be32 +nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) +{ + struct nfsd4_layoutget *lgp = &u->layoutget; + struct xdr_stream *xdr = resp->xdr; + + /* logr_return_on_close */ + nfserr = nfsd4_encode_bool(xdr, true); + if (nfserr != nfs_ok) + return nfserr; + /* logr_stateid */ + nfserr = nfsd4_encode_stateid4(xdr, &lgp->lg_sid); + if (nfserr != nfs_ok) + return nfserr; + /* logr_layout<> */ + if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT) + return nfserr_resource; + return nfsd4_encode_layout4(xdr, lgp); +} + +static __be32 nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_layoutcommit *lcp = &u->layoutcommit; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(lcp->lc_size_chg); - if (lcp->lc_size_chg) { - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - p = xdr_encode_hyper(p, lcp->lc_newsize); - } - - return 0; + /* ns_sizechanged */ + nfserr = nfsd4_encode_bool(xdr, lcp->lc_size_chg); + if (nfserr != nfs_ok) + return nfserr; + if (lcp->lc_size_chg) + /* ns_size */ + return nfsd4_encode_length4(xdr, lcp->lc_newsize); + return nfs_ok; } static __be32 @@ -4780,103 +5079,108 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(lrp->lrs_present); + /* lrs_present */ + nfserr = nfsd4_encode_bool(xdr, lrp->lrs_present); + if (nfserr != nfs_ok) + return nfserr; if (lrp->lrs_present) - return nfsd4_encode_stateid(xdr, &lrp->lr_sid); - return 0; + /* lrs_stateid */ + return nfsd4_encode_stateid4(xdr, &lrp->lr_sid); + return nfs_ok; } #endif /* CONFIG_NFSD_PNFS */ static __be32 -nfsd42_encode_write_res(struct nfsd4_compoundres *resp, - struct nfsd42_write_res *write, bool sync) +nfsd4_encode_write_response4(struct xdr_stream *xdr, + const struct nfsd4_copy *copy) { - __be32 *p; - p = xdr_reserve_space(resp->xdr, 4); - if (!p) - return nfserr_resource; + const struct nfsd42_write_res *write = ©->cp_res; + u32 count = nfsd4_copy_is_sync(copy) ? 0 : 1; + __be32 status; - if (sync) - *p++ = cpu_to_be32(0); - else { - __be32 nfserr; - *p++ = cpu_to_be32(1); - nfserr = nfsd4_encode_stateid(resp->xdr, &write->cb_stateid); - if (nfserr) - return nfserr; + /* wr_callback_id<1> */ + if (xdr_stream_encode_u32(xdr, count) != XDR_UNIT) + return nfserr_resource; + if (count) { + status = nfsd4_encode_stateid4(xdr, &write->cb_stateid); + if (status != nfs_ok) + return status; } - p = xdr_reserve_space(resp->xdr, 8 + 4 + NFS4_VERIFIER_SIZE); - if (!p) + + /* wr_count */ + status = nfsd4_encode_length4(xdr, write->wr_bytes_written); + if (status != nfs_ok) + return status; + /* wr_committed */ + if (xdr_stream_encode_u32(xdr, write->wr_stable_how) != XDR_UNIT) return nfserr_resource; + /* wr_writeverf */ + return nfsd4_encode_verifier4(xdr, &write->wr_verifier); +} - p = xdr_encode_hyper(p, write->wr_bytes_written); - *p++ = cpu_to_be32(write->wr_stable_how); - p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, - NFS4_VERIFIER_SIZE); - return nfs_ok; +static __be32 nfsd4_encode_copy_requirements4(struct xdr_stream *xdr, + const struct nfsd4_copy *copy) +{ + __be32 status; + + /* cr_consecutive */ + status = nfsd4_encode_bool(xdr, true); + if (status != nfs_ok) + return status; + /* cr_synchronous */ + return nfsd4_encode_bool(xdr, nfsd4_copy_is_sync(copy)); } static __be32 -nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns) +nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { - struct xdr_stream *xdr = resp->xdr; - struct nfs42_netaddr *addr; - __be32 *p; + struct nfsd4_copy *copy = &u->copy; - p = xdr_reserve_space(xdr, 4); - *p++ = cpu_to_be32(ns->nl4_type); + nfserr = nfsd4_encode_write_response4(resp->xdr, copy); + if (nfserr != nfs_ok) + return nfserr; + return nfsd4_encode_copy_requirements4(resp->xdr, copy); +} +static __be32 +nfsd4_encode_netloc4(struct xdr_stream *xdr, const struct nl4_server *ns) +{ + __be32 status; + + if (xdr_stream_encode_u32(xdr, ns->nl4_type) != XDR_UNIT) + return nfserr_resource; switch (ns->nl4_type) { case NL4_NETADDR: - addr = &ns->u.nl4_addr; - - /* netid_len, netid, uaddr_len, uaddr (port included - * in RPCBIND_MAXUADDRLEN) - */ - p = xdr_reserve_space(xdr, - 4 /* netid len */ + - (XDR_QUADLEN(addr->netid_len) * 4) + - 4 /* uaddr len */ + - (XDR_QUADLEN(addr->addr_len) * 4)); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(addr->netid_len); - p = xdr_encode_opaque_fixed(p, addr->netid, - addr->netid_len); - *p++ = cpu_to_be32(addr->addr_len); - p = xdr_encode_opaque_fixed(p, addr->addr, - addr->addr_len); + /* nl_addr */ + status = nfsd4_encode_netaddr4(xdr, &ns->u.nl4_addr); break; default: - WARN_ON_ONCE(ns->nl4_type != NL4_NETADDR); - return nfserr_inval; + status = nfserr_serverfault; } - - return 0; + return status; } static __be32 -nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) +nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { - struct nfsd4_copy *copy = &u->copy; - __be32 *p; + struct nfsd4_copy_notify *cn = &u->copy_notify; + struct xdr_stream *xdr = resp->xdr; - nfserr = nfsd42_encode_write_res(resp, ©->cp_res, - nfsd4_copy_is_sync(copy)); + /* cnr_lease_time */ + nfserr = nfsd4_encode_nfstime4(xdr, &cn->cpn_lease_time); if (nfserr) return nfserr; - - p = xdr_reserve_space(resp->xdr, 4 + 4); - *p++ = xdr_one; /* cr_consecutive */ - *p = nfsd4_copy_is_sync(copy) ? xdr_one : xdr_zero; - return 0; + /* cnr_stateid */ + nfserr = nfsd4_encode_stateid4(xdr, &cn->cpn_cnr_stateid); + if (nfserr) + return nfserr; + /* cnr_source_server<> */ + if (xdr_stream_encode_u32(xdr, 1) != XDR_UNIT) + return nfserr_resource; + return nfsd4_encode_netloc4(xdr, cn->cpn_src); } static __be32 @@ -4885,14 +5189,15 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, { struct nfsd4_offload_status *os = &u->offload_status; struct xdr_stream *xdr = resp->xdr; - __be32 *p; - p = xdr_reserve_space(xdr, 8 + 4); - if (!p) + /* osr_count */ + nfserr = nfsd4_encode_length4(xdr, os->count); + if (nfserr != nfs_ok) + return nfserr; + /* osr_complete<1> */ + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) return nfserr_resource; - p = xdr_encode_hyper(p, os->count); - *p++ = cpu_to_be32(0); - return nfserr; + return nfs_ok; } static __be32 @@ -4970,53 +5275,18 @@ out: } static __be32 -nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, - union nfsd4_op_u *u) -{ - struct nfsd4_copy_notify *cn = &u->copy_notify; - struct xdr_stream *xdr = resp->xdr; - __be32 *p; - - if (nfserr) - return nfserr; - - /* 8 sec, 4 nsec */ - p = xdr_reserve_space(xdr, 12); - if (!p) - return nfserr_resource; - - /* cnr_lease_time */ - p = xdr_encode_hyper(p, cn->cpn_sec); - *p++ = cpu_to_be32(cn->cpn_nsec); - - /* cnr_stateid */ - nfserr = nfsd4_encode_stateid(xdr, &cn->cpn_cnr_stateid); - if (nfserr) - return nfserr; - - /* cnr_src.nl_nsvr */ - p = xdr_reserve_space(xdr, 4); - if (!p) - return nfserr_resource; - - *p++ = cpu_to_be32(1); - - nfserr = nfsd42_encode_nl4_server(resp, cn->cpn_src); - return nfserr; -} - -static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, union nfsd4_op_u *u) { struct nfsd4_seek *seek = &u->seek; - __be32 *p; - - p = xdr_reserve_space(resp->xdr, 4 + 8); - *p++ = cpu_to_be32(seek->seek_eof); - p = xdr_encode_hyper(p, seek->seek_pos); + struct xdr_stream *xdr = resp->xdr; - return 0; + /* sr_eof */ + nfserr = nfsd4_encode_bool(xdr, seek->seek_eof); + if (nfserr != nfs_ok) + return nfserr; + /* sr_offset */ + return nfsd4_encode_offset4(xdr, seek->seek_pos); } static __be32 diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7ed02fb88a36..3e15b72f421d 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -26,6 +26,7 @@ #include "pnfs.h" #include "filecache.h" #include "trace.h" +#include "netlink.h" /* * We have a single directory with several nodes in it. @@ -1132,7 +1133,7 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode) /* Following advice from simple_fill_super documentation: */ inode->i_ino = iunique(sb, NFSD_MaxReserved); inode->i_mode = mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); switch (mode & S_IFMT) { case S_IFDIR: inode->i_fop = &simple_dir_operations; @@ -1496,6 +1497,203 @@ static int create_proc_exports_entry(void) unsigned int nfsd_net_id; /** + * nfsd_nl_rpc_status_get_start - Prepare rpc_status_get dumpit + * @cb: netlink metadata and command arguments + * + * Return values: + * %0: The rpc_status_get command may proceed + * %-ENODEV: There is no NFSD running in this namespace + */ +int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb) +{ + struct nfsd_net *nn = net_generic(sock_net(cb->skb->sk), nfsd_net_id); + int ret = -ENODEV; + + mutex_lock(&nfsd_mutex); + if (nn->nfsd_serv) { + svc_get(nn->nfsd_serv); + ret = 0; + } + mutex_unlock(&nfsd_mutex); + + return ret; +} + +static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, + struct netlink_callback *cb, + struct nfsd_genl_rqstp *rqstp) +{ + void *hdr; + u32 i; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &nfsd_nl_family, 0, NFSD_CMD_RPC_STATUS_GET); + if (!hdr) + return -ENOBUFS; + + if (nla_put_be32(skb, NFSD_A_RPC_STATUS_XID, rqstp->rq_xid) || + nla_put_u32(skb, NFSD_A_RPC_STATUS_FLAGS, rqstp->rq_flags) || + nla_put_u32(skb, NFSD_A_RPC_STATUS_PROG, rqstp->rq_prog) || + nla_put_u32(skb, NFSD_A_RPC_STATUS_PROC, rqstp->rq_proc) || + nla_put_u8(skb, NFSD_A_RPC_STATUS_VERSION, rqstp->rq_vers) || + nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME, + ktime_to_us(rqstp->rq_stime), + NFSD_A_RPC_STATUS_PAD)) + return -ENOBUFS; + + switch (rqstp->rq_saddr.sa_family) { + case AF_INET: { + const struct sockaddr_in *s_in, *d_in; + + s_in = (const struct sockaddr_in *)&rqstp->rq_saddr; + d_in = (const struct sockaddr_in *)&rqstp->rq_daddr; + if (nla_put_in_addr(skb, NFSD_A_RPC_STATUS_SADDR4, + s_in->sin_addr.s_addr) || + nla_put_in_addr(skb, NFSD_A_RPC_STATUS_DADDR4, + d_in->sin_addr.s_addr) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT, + s_in->sin_port) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, + d_in->sin_port)) + return -ENOBUFS; + break; + } + case AF_INET6: { + const struct sockaddr_in6 *s_in, *d_in; + + s_in = (const struct sockaddr_in6 *)&rqstp->rq_saddr; + d_in = (const struct sockaddr_in6 *)&rqstp->rq_daddr; + if (nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_SADDR6, + &s_in->sin6_addr) || + nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_DADDR6, + &d_in->sin6_addr) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT, + s_in->sin6_port) || + nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, + d_in->sin6_port)) + return -ENOBUFS; + break; + } + } + + for (i = 0; i < rqstp->rq_opcnt; i++) + if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS, + rqstp->rq_opnum[i])) + return -ENOBUFS; + + genlmsg_end(skb, hdr); + return 0; +} + +/** + * nfsd_nl_rpc_status_get_dumpit - Handle rpc_status_get dumpit + * @skb: reply buffer + * @cb: netlink metadata and command arguments + * + * Returns the size of the reply or a negative errno. + */ +int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id); + int i, ret, rqstp_index = 0; + + rcu_read_lock(); + + for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) { + struct svc_rqst *rqstp; + + if (i < cb->args[0]) /* already consumed */ + continue; + + rqstp_index = 0; + list_for_each_entry_rcu(rqstp, + &nn->nfsd_serv->sv_pools[i].sp_all_threads, + rq_all) { + struct nfsd_genl_rqstp genl_rqstp; + unsigned int status_counter; + + if (rqstp_index++ < cb->args[1]) /* already consumed */ + continue; + /* + * Acquire rq_status_counter before parsing the rqst + * fields. rq_status_counter is set to an odd value in + * order to notify the consumers the rqstp fields are + * meaningful. + */ + status_counter = + smp_load_acquire(&rqstp->rq_status_counter); + if (!(status_counter & 1)) + continue; + + genl_rqstp.rq_xid = rqstp->rq_xid; + genl_rqstp.rq_flags = rqstp->rq_flags; + genl_rqstp.rq_vers = rqstp->rq_vers; + genl_rqstp.rq_prog = rqstp->rq_prog; + genl_rqstp.rq_proc = rqstp->rq_proc; + genl_rqstp.rq_stime = rqstp->rq_stime; + genl_rqstp.rq_opcnt = 0; + memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp), + sizeof(struct sockaddr)); + memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp), + sizeof(struct sockaddr)); + +#ifdef CONFIG_NFSD_V4 + if (rqstp->rq_vers == NFS4_VERSION && + rqstp->rq_proc == NFSPROC4_COMPOUND) { + /* NFSv4 compound */ + struct nfsd4_compoundargs *args; + int j; + + args = rqstp->rq_argp; + genl_rqstp.rq_opcnt = args->opcnt; + for (j = 0; j < genl_rqstp.rq_opcnt; j++) + genl_rqstp.rq_opnum[j] = + args->ops[j].opnum; + } +#endif /* CONFIG_NFSD_V4 */ + + /* + * Acquire rq_status_counter before reporting the rqst + * fields to the user. + */ + if (smp_load_acquire(&rqstp->rq_status_counter) != + status_counter) + continue; + + ret = nfsd_genl_rpc_status_compose_msg(skb, cb, + &genl_rqstp); + if (ret) + goto out; + } + } + + cb->args[0] = i; + cb->args[1] = rqstp_index; + ret = skb->len; +out: + rcu_read_unlock(); + + return ret; +} + +/** + * nfsd_nl_rpc_status_get_done - rpc_status_get dumpit post-processing + * @cb: netlink metadata and command arguments + * + * Return values: + * %0: Success + */ +int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb) +{ + mutex_lock(&nfsd_mutex); + nfsd_put(sock_net(cb->skb->sk)); + mutex_unlock(&nfsd_mutex); + + return 0; +} + +/** * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace * @net: a freshly-created network namespace * @@ -1589,6 +1787,10 @@ static int __init init_nfsd(void) retval = register_filesystem(&nfsd_fs_type); if (retval) goto out_free_all; + retval = genl_register_family(&nfsd_nl_family); + if (retval) + goto out_free_all; + return 0; out_free_all: nfsd4_destroy_laundry_wq(); @@ -1613,6 +1815,7 @@ out_free_slabs: static void __exit exit_nfsd(void) { + genl_unregister_family(&nfsd_nl_family); unregister_filesystem(&nfsd_fs_type); nfsd4_destroy_laundry_wq(); unregister_cld_notifier(); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 11c14faa6c67..f5ff42f41ee7 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -62,6 +62,23 @@ struct readdir_cd { __be32 err; /* 0, nfserr, or nfserr_eof */ }; +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 50 + +struct nfsd_genl_rqstp { + struct sockaddr rq_daddr; + struct sockaddr rq_saddr; + unsigned long rq_flags; + ktime_t rq_stime; + __be32 rq_xid; + u32 rq_vers; + u32 rq_prog; + u32 rq_proc; + + /* NFSv4 compound */ + u32 rq_opcnt; + u32 rq_opnum[NFSD_MAX_OPS_PER_COMPOUND]; +}; extern struct svc_program nfsd_program; extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 355bf0db3235..dbfa0ac13564 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -771,7 +771,7 @@ enum fsid_source fsid_source(const struct svc_fh *fhp) * assume that the new change attr is always logged to stable storage in some * fashion before the results can be seen. */ -u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode) +u64 nfsd4_change_attribute(const struct kstat *stat, const struct inode *inode) { u64 chattr; diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 40426f899e76..6ebdf7ea27bf 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -293,7 +293,8 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) fhp->fh_pre_saved = false; } -u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode); +u64 nfsd4_change_attribute(const struct kstat *stat, + const struct inode *inode); __be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp); __be32 fh_fill_post_attrs(struct svc_fh *fhp); __be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c7af1095f6b5..d6122bb2d167 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -572,7 +572,6 @@ static void nfsd_last_thread(struct net *net) return; nfsd_shutdown_net(net); - pr_info("nfsd: last server has exited, flushing export cache\n"); nfsd_export_flush(net); } @@ -713,14 +712,13 @@ int nfsd_nrpools(struct net *net) int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) { - int i = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv = nn->nfsd_serv; + int i; - if (nn->nfsd_serv != NULL) { - for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++) - nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads; - } - + if (serv) + for (i = 0; i < serv->sv_nrpools && i < n; i++) + nthreads[i] = atomic_read(&serv->sv_pools[i].sp_nrthreads); return 0; } @@ -787,7 +785,6 @@ int nfsd_svc(int nrservs, struct net *net, const struct cred *cred) { int error; - bool nfsd_up_before; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv; @@ -807,8 +804,6 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) error = nfsd_create_serv(net); if (error) goto out; - - nfsd_up_before = nn->nfsd_net_up; serv = nn->nfsd_serv; error = nfsd_startup_net(net, cred); @@ -816,17 +811,15 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) goto out_put; error = svc_set_num_threads(serv, NULL, nrservs); if (error) - goto out_shutdown; + goto out_put; error = serv->sv_nrthreads; - if (error == 0) - nfsd_last_thread(net); -out_shutdown: - if (error < 0 && !nfsd_up_before) - nfsd_shutdown_net(net); out_put: /* Threads now hold service active */ if (xchg(&nn->keep_active, 0)) svc_put(serv); + + if (serv->sv_nrthreads == 0) + nfsd_last_thread(net); svc_put(serv); out: mutex_unlock(&nfsd_mutex); @@ -957,7 +950,7 @@ nfsd(void *vrqstp) /* * The main request loop */ - while (!kthread_should_stop()) { + while (!svc_thread_should_stop(rqstp)) { /* Update sv_maxconn if it has changed */ rqstp->rq_server->sv_maxconn = nn->max_connections; @@ -998,6 +991,15 @@ int nfsd_dispatch(struct svc_rqst *rqstp) if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; + /* + * Release rq_status_counter setting it to an odd value after the rpc + * request has been properly parsed. rq_status_counter is used to + * notify the consumers if the rqstp fields are stable + * (rq_status_counter is odd) or not meaningful (rq_status_counter + * is even). + */ + smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1); + rp = NULL; switch (nfsd_cache_lookup(rqstp, &rp)) { case RC_DOIT: @@ -1015,6 +1017,12 @@ int nfsd_dispatch(struct svc_rqst *rqstp) if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; + /* + * Release rq_status_counter setting it to an even value after the rpc + * request has been properly processed. + */ + smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1); + nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1); out_cached_reply: return 1; diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h index 4f4282d4eeca..de1e0dfed06a 100644 --- a/fs/nfsd/pnfs.h +++ b/fs/nfsd/pnfs.h @@ -27,12 +27,12 @@ struct nfsd4_layout_ops { struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdevp); __be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr, - struct nfsd4_getdeviceinfo *gdevp); + const struct nfsd4_getdeviceinfo *gdevp); __be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp, struct nfsd4_layoutget *lgp); - __be32 (*encode_layoutget)(struct xdr_stream *, - struct nfsd4_layoutget *lgp); + __be32 (*encode_layoutget)(struct xdr_stream *xdr, + const struct nfsd4_layoutget *lgp); __be32 (*proc_layoutcommit)(struct inode *inode, struct nfsd4_layoutcommit *lcp); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index cbddcf484dba..f96eaa8e9413 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -117,6 +117,24 @@ struct nfs4_cpntf_state { time64_t cpntf_time; /* last time stateid used */ }; +struct nfs4_cb_fattr { + struct nfsd4_callback ncf_getattr; + u32 ncf_cb_status; + u32 ncf_cb_bmap[1]; + + /* from CB_GETATTR reply */ + u64 ncf_cb_change; + u64 ncf_cb_fsize; + + unsigned long ncf_cb_flags; + bool ncf_file_modified; + u64 ncf_initial_cinfo; + u64 ncf_cur_fsize; +}; + +/* bits for ncf_cb_flags */ +#define CB_GETATTR_BUSY 0 + /* * Represents a delegation stateid. The nfs4_client holds references to these * and they are put when it is being destroyed or when the delegation is @@ -150,6 +168,9 @@ struct nfs4_delegation { int dl_retries; struct nfsd4_callback dl_recall; bool dl_recalled; + + /* for CB_GETATTR */ + struct nfs4_cb_fattr dl_cb_fattr; }; #define cb_to_delegation(cb) \ @@ -174,8 +195,6 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) /* Maximum number of slots per session. 160 is useful for long haul TCP */ #define NFSD_MAX_SLOTS_PER_SESSION 160 -/* Maximum number of operations per session compound */ -#define NFSD_MAX_OPS_PER_COMPOUND 50 /* Maximum session per slot cache size */ #define NFSD_SLOT_CACHE_SIZE 2048 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */ @@ -642,6 +661,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, NFSPROC4_CLNT_CB_RECALL_ANY, + NFSPROC4_CLNT_CB_GETATTR, }; /* Returns true iff a is later than b: */ @@ -734,5 +754,6 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) } extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, - struct inode *inode); + struct inode *inode, bool *file_modified, u64 *size); +extern void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf); #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 63797635e1c3..12d79f5d4eb1 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -60,7 +60,7 @@ static int nfsd_show(struct seq_file *seq, void *v) #ifdef CONFIG_NFSD_V4 /* Show count for individual nfsv4 operations */ /* Writing operation numbers 0 1 2 also for maintaining uniformity */ - seq_printf(seq,"proc4ops %u", LAST_NFS4_OP + 1); + seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1); for (i = 0; i <= LAST_NFS4_OP; i++) { seq_printf(seq, " %lld", percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)])); @@ -76,7 +76,7 @@ static int nfsd_show(struct seq_file *seq, void *v) DEFINE_PROC_SHOW_ATTRIBUTE(nfsd); -int nfsd_percpu_counters_init(struct percpu_counter counters[], int num) +int nfsd_percpu_counters_init(struct percpu_counter *counters, int num) { int i, err = 0; diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index cf5524e7ca06..14f50c660b61 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -37,9 +37,9 @@ extern struct nfsd_stats nfsdstats; extern struct svc_stat nfsd_svcstats; -int nfsd_percpu_counters_init(struct percpu_counter counters[], int num); -void nfsd_percpu_counters_reset(struct percpu_counter counters[], int num); -void nfsd_percpu_counters_destroy(struct percpu_counter counters[], int num); +int nfsd_percpu_counters_init(struct percpu_counter *counters, int num); +void nfsd_percpu_counters_reset(struct percpu_counter *counters, int num); +void nfsd_percpu_counters_destroy(struct percpu_counter *counters, int num); int nfsd_stat_init(void); void nfsd_stat_shutdown(void); @@ -61,22 +61,22 @@ static inline void nfsd_stats_rc_nocache_inc(void) static inline void nfsd_stats_fh_stale_inc(struct svc_export *exp) { percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_FH_STALE]); - if (exp) - percpu_counter_inc(&exp->ex_stats.counter[EXP_STATS_FH_STALE]); + if (exp && exp->ex_stats) + percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]); } static inline void nfsd_stats_io_read_add(struct svc_export *exp, s64 amount) { percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_READ], amount); - if (exp) - percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_READ], amount); + if (exp && exp->ex_stats) + percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_READ], amount); } static inline void nfsd_stats_io_write_add(struct svc_export *exp, s64 amount) { percpu_counter_add(&nfsdstats.counter[NFSD_STATS_IO_WRITE], amount); - if (exp) - percpu_counter_add(&exp->ex_stats.counter[EXP_STATS_IO_WRITE], amount); + if (exp && exp->ex_stats) + percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_WRITE], amount); } static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn) diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 803904348871..fbc0ccb40424 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1863,6 +1863,93 @@ TRACE_EVENT(nfsd_end_grace, ) ); +DECLARE_EVENT_CLASS(nfsd_copy_class, + TP_PROTO( + const struct nfsd4_copy *copy + ), + TP_ARGS(copy), + TP_STRUCT__entry( + __field(bool, intra) + __field(bool, async) + __field(u32, src_cl_boot) + __field(u32, src_cl_id) + __field(u32, src_so_id) + __field(u32, src_si_generation) + __field(u32, dst_cl_boot) + __field(u32, dst_cl_id) + __field(u32, dst_so_id) + __field(u32, dst_si_generation) + __field(u64, src_cp_pos) + __field(u64, dst_cp_pos) + __field(u64, cp_count) + __sockaddr(addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + const stateid_t *src_stp = ©->cp_src_stateid; + const stateid_t *dst_stp = ©->cp_dst_stateid; + + __entry->intra = test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); + __entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + __entry->src_cl_boot = src_stp->si_opaque.so_clid.cl_boot; + __entry->src_cl_id = src_stp->si_opaque.so_clid.cl_id; + __entry->src_so_id = src_stp->si_opaque.so_id; + __entry->src_si_generation = src_stp->si_generation; + __entry->dst_cl_boot = dst_stp->si_opaque.so_clid.cl_boot; + __entry->dst_cl_id = dst_stp->si_opaque.so_clid.cl_id; + __entry->dst_so_id = dst_stp->si_opaque.so_id; + __entry->dst_si_generation = dst_stp->si_generation; + __entry->src_cp_pos = copy->cp_src_pos; + __entry->dst_cp_pos = copy->cp_dst_pos; + __entry->cp_count = copy->cp_count; + __assign_sockaddr(addr, ©->cp_clp->cl_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("client=%pISpc intra=%d async=%d " + "src_stateid[si_generation:0x%x cl_boot:0x%x cl_id:0x%x so_id:0x%x] " + "dst_stateid[si_generation:0x%x cl_boot:0x%x cl_id:0x%x so_id:0x%x] " + "cp_src_pos=%llu cp_dst_pos=%llu cp_count=%llu", + __get_sockaddr(addr), __entry->intra, __entry->async, + __entry->src_si_generation, __entry->src_cl_boot, + __entry->src_cl_id, __entry->src_so_id, + __entry->dst_si_generation, __entry->dst_cl_boot, + __entry->dst_cl_id, __entry->dst_so_id, + __entry->src_cp_pos, __entry->dst_cp_pos, __entry->cp_count + ) +); + +#define DEFINE_COPY_EVENT(name) \ +DEFINE_EVENT(nfsd_copy_class, nfsd_copy_##name, \ + TP_PROTO(const struct nfsd4_copy *copy), \ + TP_ARGS(copy)) + +DEFINE_COPY_EVENT(inter); +DEFINE_COPY_EVENT(intra); +DEFINE_COPY_EVENT(do_async); + +TRACE_EVENT(nfsd_copy_done, + TP_PROTO( + const struct nfsd4_copy *copy, + __be32 status + ), + TP_ARGS(copy, status), + TP_STRUCT__entry( + __field(int, status) + __field(bool, intra) + __field(bool, async) + __sockaddr(addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->status = be32_to_cpu(status); + __entry->intra = test_bit(NFSD4_COPY_F_INTRA, ©->cp_flags); + __entry->async = !test_bit(NFSD4_COPY_F_SYNCHRONOUS, ©->cp_flags); + __assign_sockaddr(addr, ©->cp_clp->cl_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc status=%d intra=%d async=%d ", + __get_sockaddr(addr), __entry->status, __entry->intra, __entry->async + ) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 48260cf68fde..fbbea7498f02 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -337,6 +337,24 @@ out: return err; } +static void +commit_reset_write_verifier(struct nfsd_net *nn, struct svc_rqst *rqstp, + int err) +{ + switch (err) { + case -EAGAIN: + case -ESTALE: + /* + * Neither of these are the result of a problem with + * durable storage, so avoid a write verifier reset. + */ + break; + default: + nfsd_reset_write_verifier(nn); + trace_nfsd_writeverf_reset(nn, rqstp, err); + } +} + /* * Commit metadata changes to stable storage. */ @@ -520,7 +538,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_sanitize_attrs(inode, iap); - if (check_guard && guardtime != inode_get_ctime(inode).tv_sec) + if (check_guard && guardtime != inode_get_ctime_sec(inode)) return nfserr_notsync; /* @@ -647,8 +665,7 @@ __be32 nfsd4_clone_file_range(struct svc_rqst *rqstp, &nfsd4_get_cstate(rqstp)->current_fh, dst_pos, count, status); - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, status); + commit_reset_write_verifier(nn, rqstp, status); ret = nfserrno(status); } } @@ -823,7 +840,7 @@ int nfsd_open_break_lease(struct inode *inode, int access) * and additional flags. * N.B. After this call fhp needs an fh_put */ -static __be32 +static int __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { @@ -831,14 +848,12 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, struct inode *inode; struct file *file; int flags = O_RDONLY|O_LARGEFILE; - __be32 err; - int host_err = 0; + int host_err = -EPERM; path.mnt = fhp->fh_export->ex_path.mnt; path.dentry = fhp->fh_dentry; inode = d_inode(path.dentry); - err = nfserr_perm; if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE)) goto out; @@ -847,7 +862,7 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, host_err = nfsd_open_break_lease(inode, may_flags); if (host_err) /* NOMEM or WOULDBLOCK */ - goto out_nfserr; + goto out; if (may_flags & NFSD_MAY_WRITE) { if (may_flags & NFSD_MAY_READ) @@ -859,13 +874,13 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, file = dentry_open(&path, flags, current_cred()); if (IS_ERR(file)) { host_err = PTR_ERR(file); - goto out_nfserr; + goto out; } host_err = ima_file_check(file, may_flags); if (host_err) { fput(file); - goto out_nfserr; + goto out; } if (may_flags & NFSD_MAY_64BIT_COOKIE) @@ -874,10 +889,8 @@ __nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, file->f_mode |= FMODE_32BITHASH; *filp = file; -out_nfserr: - err = nfserrno(host_err); out: - return err; + return host_err; } __be32 @@ -885,6 +898,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { __be32 err; + int host_err; bool retried = false; validate_process_creds(); @@ -904,12 +918,13 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, retry: err = fh_verify(rqstp, fhp, type, may_flags); if (!err) { - err = __nfsd_open(rqstp, fhp, type, may_flags, filp); - if (err == nfserr_stale && !retried) { + host_err = __nfsd_open(rqstp, fhp, type, may_flags, filp); + if (host_err == -EOPENSTALE && !retried) { retried = true; fh_put(fhp); goto retry; } + err = nfserrno(host_err); } validate_process_creds(); return err; @@ -922,13 +937,13 @@ retry: * @may_flags: internal permission flags * @filp: OUT: open "struct file *" * - * Returns an nfsstat value in network byte order. + * Returns zero on success, or a negative errno value. */ -__be32 +int nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, struct file **filp) { - __be32 err; + int err; validate_process_creds(); err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); @@ -1172,8 +1187,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, host_err = vfs_iter_write(file, &iter, &pos, flags); file_end_write(file); if (host_err < 0) { - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, host_err); + commit_reset_write_verifier(nn, rqstp, host_err); goto out_nfserr; } *cnt = host_err; @@ -1185,10 +1199,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, if (stable && use_wgather) { host_err = wait_for_concurrent_writes(file); - if (host_err < 0) { - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, host_err); - } + if (host_err < 0) + commit_reset_write_verifier(nn, rqstp, host_err); } out_nfserr: @@ -1331,8 +1343,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, err = nfserr_notsupp; break; default: - nfsd_reset_write_verifier(nn); - trace_nfsd_writeverf_reset(nn, rqstp, err2); + commit_reset_write_verifier(nn, rqstp, err2); err = nfserrno(err2); } } else @@ -1788,6 +1799,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev; + if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) + goto out; + if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) + goto out; + retry: host_err = fh_want_write(ffhp); if (host_err) { @@ -1823,12 +1840,6 @@ retry: if (ndentry == trap) goto out_dput_new; - host_err = -EXDEV; - if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) - goto out_dput_new; - if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) - goto out_dput_new; - if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && nfsd_has_cached_files(ndentry)) { close_cached = true; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index a6890ea7b765..e3c29596f4df 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -104,8 +104,8 @@ __be32 nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int nfsd_open_break_lease(struct inode *, int); __be32 nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t, int, struct file **); -__be32 nfsd_open_verified(struct svc_rqst *, struct svc_fh *, - int, struct file **); +int nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, + int may_flags, struct file **filp); __be32 nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, unsigned long *count, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 9d918a79dc16..80e859dc84d8 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -50,6 +50,134 @@ #define HAS_CSTATE_FLAG(c, f) ((c)->sid_flags & (f)) #define CLEAR_CSTATE_FLAG(c, f) ((c)->sid_flags &= ~(f)) +/** + * nfsd4_encode_bool - Encode an XDR bool type result + * @xdr: target XDR stream + * @val: boolean value to encode + * + * Return values: + * %nfs_ok: @val encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_bool(struct xdr_stream *xdr, bool val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(p == NULL)) + return nfserr_resource; + *p = val ? xdr_one : xdr_zero; + return nfs_ok; +} + +/** + * nfsd4_encode_uint32_t - Encode an XDR uint32_t type result + * @xdr: target XDR stream + * @val: integer value to encode + * + * Return values: + * %nfs_ok: @val encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_uint32_t(struct xdr_stream *xdr, u32 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT); + + if (unlikely(p == NULL)) + return nfserr_resource; + *p = cpu_to_be32(val); + return nfs_ok; +} + +#define nfsd4_encode_aceflag4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_acemask4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_acetype4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_count4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_mode4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_nfs_lease4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_qop4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_sequenceid4(x, v) nfsd4_encode_uint32_t(x, v) +#define nfsd4_encode_slotid4(x, v) nfsd4_encode_uint32_t(x, v) + +/** + * nfsd4_encode_uint64_t - Encode an XDR uint64_t type result + * @xdr: target XDR stream + * @val: integer value to encode + * + * Return values: + * %nfs_ok: @val encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_uint64_t(struct xdr_stream *xdr, u64 val) +{ + __be32 *p = xdr_reserve_space(xdr, XDR_UNIT * 2); + + if (unlikely(p == NULL)) + return nfserr_resource; + put_unaligned_be64(val, p); + return nfs_ok; +} + +#define nfsd4_encode_changeid4(x, v) nfsd4_encode_uint64_t(x, v) +#define nfsd4_encode_nfs_cookie4(x, v) nfsd4_encode_uint64_t(x, v) +#define nfsd4_encode_length4(x, v) nfsd4_encode_uint64_t(x, v) +#define nfsd4_encode_offset4(x, v) nfsd4_encode_uint64_t(x, v) + +/** + * nfsd4_encode_opaque_fixed - Encode a fixed-length XDR opaque type result + * @xdr: target XDR stream + * @data: pointer to data + * @size: length of data in bytes + * + * Return values: + * %nfs_ok: @data encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_opaque_fixed(struct xdr_stream *xdr, const void *data, + size_t size) +{ + __be32 *p = xdr_reserve_space(xdr, xdr_align_size(size)); + size_t pad = xdr_pad_size(size); + + if (unlikely(p == NULL)) + return nfserr_resource; + memcpy(p, data, size); + if (pad) + memset((char *)p + size, 0, pad); + return nfs_ok; +} + +/** + * nfsd4_encode_opaque - Encode a variable-length XDR opaque type result + * @xdr: target XDR stream + * @data: pointer to data + * @size: length of data in bytes + * + * Return values: + * %nfs_ok: @data encoded; @xdr advanced to next position + * %nfserr_resource: stream buffer space exhausted + */ +static __always_inline __be32 +nfsd4_encode_opaque(struct xdr_stream *xdr, const void *data, size_t size) +{ + size_t pad = xdr_pad_size(size); + __be32 *p; + + p = xdr_reserve_space(xdr, XDR_UNIT + xdr_align_size(size)); + if (unlikely(p == NULL)) + return nfserr_resource; + *p++ = cpu_to_be32(size); + memcpy(p, data, size); + if (pad) + memset((char *)p + size, 0, pad); + return nfs_ok; +} + +#define nfsd4_encode_component4(x, d, s) nfsd4_encode_opaque(x, d, s) + struct nfsd4_compound_state { struct svc_fh current_fh; struct svc_fh save_fh; @@ -170,12 +298,8 @@ struct nfsd4_lock { } v; /* response */ - union { - struct { - stateid_t stateid; - } ok; - struct nfsd4_lock_denied denied; - } u; + stateid_t lk_resp_stateid; + struct nfsd4_lock_denied lk_denied; }; #define lk_new_open_seqid v.new.open_seqid #define lk_new_open_stateid v.new.open_stateid @@ -185,20 +309,15 @@ struct nfsd4_lock { #define lk_old_lock_stateid v.old.lock_stateid #define lk_old_lock_seqid v.old.lock_seqid -#define lk_resp_stateid u.ok.stateid -#define lk_denied u.denied - - struct nfsd4_lockt { u32 lt_type; clientid_t lt_clientid; struct xdr_netobj lt_owner; u64 lt_offset; u64 lt_length; - struct nfsd4_lock_denied lt_denied; + struct nfsd4_lock_denied lt_denied; }; - struct nfsd4_locku { u32 lu_type; u32 lu_seqid; @@ -267,9 +386,9 @@ struct nfsd4_open { u32 op_deleg_want; /* request */ stateid_t op_stateid; /* response */ __be32 op_xdr_error; /* see nfsd4_open_omfg() */ - u32 op_recall; /* recall */ struct nfsd4_change_info op_cinfo; /* response */ u32 op_rflags; /* response */ + bool op_recall; /* response */ bool op_truncate; /* used during processing */ bool op_created; /* used during processing */ struct nfs4_openowner *op_openowner; /* used during processing */ @@ -496,7 +615,7 @@ struct nfsd4_layoutcommit { u32 lc_layout_type; /* request */ u32 lc_up_len; /* layout length */ void *lc_up_layout; /* decoded by callback */ - u32 lc_size_chg; /* boolean for response */ + bool lc_size_chg; /* response */ u64 lc_newsize; /* response */ }; @@ -508,7 +627,7 @@ struct nfsd4_layoutreturn { u32 lrf_body_len; /* request */ void *lrf_body; /* request */ stateid_t lr_sid; /* request/response */ - u32 lrs_present; /* response */ + bool lrs_present; /* response */ }; struct nfsd4_fallocate { @@ -626,8 +745,7 @@ struct nfsd4_copy_notify { /* response */ stateid_t cpn_cnr_stateid; - u64 cpn_sec; - u32 cpn_nsec; + struct timespec64 cpn_lease_time; struct nl4_server *cpn_src; }; @@ -820,8 +938,10 @@ extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern void nfsd4_lock_release(union nfsd4_op_u *u); extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern void nfsd4_lockt_release(union nfsd4_op_u *u); extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 0d39af1b00a0..e8b00309c449 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -54,3 +54,21 @@ #define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) + +/* + * 1: CB_GETATTR opcode (32-bit) + * N: file_handle + * 1: number of entry in attribute array (32-bit) + * 1: entry 0 in attribute array (32-bit) + */ +#define NFS4_enc_cb_getattr_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + enc_nfs4_fh_sz + 1 + 1) +/* + * 4: fattr_bitmap_maxsz + * 1: attribute array len + * 2: change attr (64-bit) + * 2: size (64-bit) + */ +#define NFS4_dec_cb_getattr_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz) diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index bce734b68f08..de2073c47651 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -429,7 +429,7 @@ void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, nilfs_set_de_type(de, inode); nilfs_commit_chunk(page, mapping, from, to); nilfs_put_page(page); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } /* @@ -519,7 +519,7 @@ got_it: de->inode = cpu_to_le64(inode->i_ino); nilfs_set_de_type(de, inode); nilfs_commit_chunk(page, page->mapping, from, to); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); nilfs_mark_inode_dirty(dir); /* OFFSET_CACHE */ out_put: @@ -567,7 +567,7 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page) pde->rec_len = nilfs_rec_len_to_disk(to - from); dir->inode = 0; nilfs_commit_chunk(page, mapping, from, to); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); out: nilfs_put_page(page); return err; diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 48fe71d309cb..8beb2730929d 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, struct the_nilfs *nilfs = inode->i_sb->s_fs_info; err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn); - if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */ - brelse(bh); + if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */ goto failed; - } } lock_buffer(bh); @@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, failed: unlock_page(bh->b_page); put_page(bh->b_page); + if (unlikely(err)) + brelse(bh); return err; } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1a8bd5993476..f861f3a0bf5c 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -366,7 +366,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode) atomic64_inc(&root->inodes_count); inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = ino; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { err = nilfs_bmap_read(ii->i_bmap, NULL); @@ -449,12 +449,12 @@ int nilfs_read_inode_common(struct inode *inode, i_gid_write(inode, le32_to_cpu(raw_inode->i_gid)); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le64_to_cpu(raw_inode->i_size); - inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime); + inode_set_atime(inode, le64_to_cpu(raw_inode->i_mtime), + le32_to_cpu(raw_inode->i_mtime_nsec)); inode_set_ctime(inode, le64_to_cpu(raw_inode->i_ctime), le32_to_cpu(raw_inode->i_ctime_nsec)); - inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime); - inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); - inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); + inode_set_mtime(inode, le64_to_cpu(raw_inode->i_mtime), + le32_to_cpu(raw_inode->i_mtime_nsec)); if (nilfs_is_metadata_file_inode(inode) && !S_ISREG(inode->i_mode)) return -EIO; /* this inode is for metadata and corrupted */ if (inode->i_nlink == 0) @@ -768,10 +768,10 @@ void nilfs_write_inode_common(struct inode *inode, raw_inode->i_gid = cpu_to_le32(i_gid_read(inode)); raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); raw_inode->i_size = cpu_to_le64(inode->i_size); - raw_inode->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec); - raw_inode->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); - raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + raw_inode->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + raw_inode->i_mtime = cpu_to_le64(inode_get_mtime_sec(inode)); + raw_inode->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); + raw_inode->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); raw_inode->i_blocks = cpu_to_le64(inode->i_blocks); raw_inode->i_flags = cpu_to_le32(ii->i_flags); @@ -875,7 +875,7 @@ void nilfs_truncate(struct inode *inode) nilfs_truncate_bmap(ii, blkoff); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (IS_SYNC(inode)) nilfs_set_transaction_flag(NILFS_TI_SYNC); diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index ebdcc25df0f7..869b016014d2 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -265,7 +265,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; - struct file *f; + struct file *f = NULL; int destroy = 0, error = 0; __u32 mask; @@ -345,7 +345,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) } rcu_read_lock(); - f = lookup_fd_rcu(fd); + f = lookup_fdget_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread @@ -392,6 +392,8 @@ out_err: fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); + if (f) + fput(f); return error; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index f69c451018e3..62fe0b679e58 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1585,16 +1585,25 @@ static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) } /* Check if filesystem can encode a unique fid */ -static int fanotify_test_fid(struct dentry *dentry) +static int fanotify_test_fid(struct dentry *dentry, unsigned int flags) { + unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + const struct export_operations *nop = dentry->d_sb->s_export_op; + + /* + * We need to make sure that the filesystem supports encoding of + * file handles so user can use name_to_handle_at() to compare fids + * reported with events to the file handle of watched objects. + */ + if (!nop) + return -EOPNOTSUPP; + /* - * We need to make sure that the file system supports at least - * encoding a file handle so user can use name_to_handle_at() to - * compare fid returned with event to the file handle of watched - * objects. However, even the relaxed AT_HANDLE_FID flag requires - * at least empty export_operations for ecoding unique file ids. + * For sb/mount mark, we also need to make sure that the filesystem + * supports decoding file handles, so user has a way to map back the + * reported fids to filesystem objects. */ - if (!dentry->d_sb->s_export_op) + if (mark_type != FAN_MARK_INODE && !nop->fh_to_dentry) return -EOPNOTSUPP; return 0; @@ -1812,7 +1821,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (ret) goto path_put_and_out; - ret = fanotify_test_fid(path.dentry); + ret = fanotify_test_fid(path.dentry, flags); if (ret) goto path_put_and_out; diff --git a/fs/nsfs.c b/fs/nsfs.c index 647a22433bd8..9a4b228d42fa 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -84,7 +84,7 @@ slow: return -ENOMEM; } inode->i_ino = ns->inum; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_flags |= S_IMMUTABLE; inode->i_mode = S_IFREG | S_IRUGO; inode->i_fop = &ns_file_operations; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 99ac6ea277c4..aba1e22db4e9 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -648,7 +648,7 @@ static int ntfs_read_locked_inode(struct inode *vi) * mtime is the last change of the data within the file. Not changed * when only metadata is changed, e.g. a rename doesn't affect mtime. */ - vi->i_mtime = ntfs2utc(si->last_data_change_time); + inode_set_mtime_to_ts(vi, ntfs2utc(si->last_data_change_time)); /* * ctime is the last change of the metadata of the file. This obviously * always changes, when mtime is changed. ctime can be changed on its @@ -659,7 +659,7 @@ static int ntfs_read_locked_inode(struct inode *vi) * Last access to the data within the file. Not changed during a rename * for example but changed whenever the file is written to. */ - vi->i_atime = ntfs2utc(si->last_access_time); + inode_set_atime_to_ts(vi, ntfs2utc(si->last_access_time)); /* Find the attribute list attribute if present. */ ntfs_attr_reinit_search_ctx(ctx); @@ -1217,9 +1217,9 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; set_nlink(vi, base_vi->i_nlink); - vi->i_mtime = base_vi->i_mtime; + inode_set_mtime_to_ts(vi, inode_get_mtime(base_vi)); inode_set_ctime_to_ts(vi, inode_get_ctime(base_vi)); - vi->i_atime = base_vi->i_atime; + inode_set_atime_to_ts(vi, inode_get_atime(base_vi)); vi->i_generation = ni->seq_no = base_ni->seq_no; /* Set inode type to zero but preserve permissions. */ @@ -1483,9 +1483,9 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; set_nlink(vi, base_vi->i_nlink); - vi->i_mtime = base_vi->i_mtime; + inode_set_mtime_to_ts(vi, inode_get_mtime(base_vi)); inode_set_ctime_to_ts(vi, inode_get_ctime(base_vi)); - vi->i_atime = base_vi->i_atime; + inode_set_atime_to_ts(vi, inode_get_atime(base_vi)); vi->i_generation = ni->seq_no = base_ni->seq_no; /* Set inode type to zero but preserve permissions. */ vi->i_mode = base_vi->i_mode & ~S_IFMT; @@ -2805,13 +2805,14 @@ done: if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) { struct timespec64 now = current_time(VFS_I(base_ni)); struct timespec64 ctime = inode_get_ctime(VFS_I(base_ni)); + struct timespec64 mtime = inode_get_mtime(VFS_I(base_ni)); int sync_it = 0; - if (!timespec64_equal(&VFS_I(base_ni)->i_mtime, &now) || + if (!timespec64_equal(&mtime, &now) || !timespec64_equal(&ctime, &now)) sync_it = 1; inode_set_ctime_to_ts(VFS_I(base_ni), now); - VFS_I(base_ni)->i_mtime = now; + inode_set_mtime_to_ts(VFS_I(base_ni), now); if (sync_it) mark_inode_dirty_sync(VFS_I(base_ni)); @@ -2925,9 +2926,9 @@ int ntfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, } } if (ia_valid & ATTR_ATIME) - vi->i_atime = attr->ia_atime; + inode_set_atime_to_ts(vi, attr->ia_atime); if (ia_valid & ATTR_MTIME) - vi->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(vi, attr->ia_mtime); if (ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(vi, attr->ia_ctime); mark_inode_dirty(vi); @@ -2996,7 +2997,7 @@ int __ntfs_write_inode(struct inode *vi, int sync) si = (STANDARD_INFORMATION*)((u8*)ctx->attr + le16_to_cpu(ctx->attr->data.resident.value_offset)); /* Update the access times if they have changed. */ - nt = utc2ntfs(vi->i_mtime); + nt = utc2ntfs(inode_get_mtime(vi)); if (si->last_data_change_time != nt) { ntfs_debug("Updating mtime for inode 0x%lx: old = 0x%llx, " "new = 0x%llx", vi->i_ino, (long long) @@ -3014,7 +3015,7 @@ int __ntfs_write_inode(struct inode *vi, int sync) si->last_mft_change_time = nt; modified = true; } - nt = utc2ntfs(vi->i_atime); + nt = utc2ntfs(inode_get_atime(vi)); if (si->last_access_time != nt) { ntfs_debug("Updating atime for inode 0x%lx: old = 0x%llx, " "new = 0x%llx", vi->i_ino, diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index ad1a8f72da22..6fd1dc4b08c8 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -2682,7 +2682,7 @@ mft_rec_already_initialized: vi->i_mode &= ~S_IWUGO; /* Set the inode times to the current time. */ - vi->i_atime = vi->i_mtime = inode_set_ctime_current(vi); + simple_inode_init_ts(vi); /* * Set the file size to 0, the ntfs inode sizes are set to 0 by * the call to ntfs_init_big_inode() below. diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index a9d82bbb4729..63f70259edc0 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1106,10 +1106,10 @@ repack: } } - /* + /* * The code below may require additional cluster (to extend attribute list) - * and / or one MFT record - * It is too complex to undo operations if -ENOSPC occurs deep inside + * and / or one MFT record + * It is too complex to undo operations if -ENOSPC occurs deep inside * in 'ni_insert_nonresident'. * Return in advance -ENOSPC here if there are no free cluster and no free MFT. */ @@ -1736,10 +1736,8 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) { - err = -ENOENT; - goto out; - } + if (!attr_b) + return -ENOENT; attr = attr_b; le = le_b; diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 42631b31adf1..7c01735d1219 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -52,7 +52,8 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (!attr->non_res) { lsize = le32_to_cpu(attr->res.data_size); - le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); + /* attr is resident: lsize < record_size (1K or 4K) */ + le = kvmalloc(al_aligned(lsize), GFP_KERNEL); if (!le) { err = -ENOMEM; goto out; @@ -80,7 +81,17 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (err < 0) goto out; - le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); + /* attr is nonresident. + * The worst case: + * 1T (2^40) extremely fragmented file. + * cluster = 4K (2^12) => 2^28 fragments + * 2^9 fragments per one record => 2^19 records + * 2^5 bytes of ATTR_LIST_ENTRY per one record => 2^24 bytes. + * + * the result is 16M bytes per attribute list. + * Use kvmalloc to allocate in range [several Kbytes - dozen Mbytes] + */ + le = kvmalloc(al_aligned(lsize), GFP_KERNEL); if (!le) { err = -ENOMEM; goto out; diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 107e808e06ea..63f14a0232f6 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -125,6 +125,7 @@ void wnd_close(struct wnd_bitmap *wnd) struct rb_node *node, *next; kfree(wnd->free_bits); + wnd->free_bits = NULL; run_close(&wnd->run); node = rb_first(&wnd->start_tree); @@ -659,7 +660,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) wnd->bits_last = wbits; wnd->free_bits = - kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN); + kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO); + if (!wnd->free_bits) return -ENOMEM; diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 063a6654199b..ec0566b322d5 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,7 +309,11 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ + if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) + dt_type = DT_LNK; + else + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 962f12ce6c0a..ad4a70b5d432 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -342,7 +342,7 @@ static int ntfs_extend(struct inode *inode, loff_t pos, size_t count, err = 0; } - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); if (IS_SYNC(inode)) { @@ -400,7 +400,7 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size) ni_unlock(ni); ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE; - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (!IS_DIRSYNC(inode)) { dirty = 1; } else { @@ -642,7 +642,7 @@ out: filemap_invalidate_unlock(mapping); if (!err) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); } @@ -745,8 +745,8 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags) + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct inode *inode = in->f_mapping->host; struct ntfs_inode *ni = ntfs_i(inode); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 2b85cb10f0be..3df2d9e34b91 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2148,7 +2148,7 @@ out1: for (i = 0; i < pages_per_frame; i++) { pg = pages[i]; - if (i == idx) + if (i == idx || !pg) continue; unlock_page(pg); put_page(pg); @@ -3208,6 +3208,12 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup, if (!fname || !memcmp(&fname->dup, dup, sizeof(fname->dup))) continue; + /* Check simple case when parent inode equals current inode. */ + if (ino_get(&fname->home) == ni->vfs_inode.i_ino) { + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + continue; + } + /* ntfs_iget5 may sleep. */ dir = ntfs_iget5(sb, &fname->home, NULL); if (IS_ERR(dir)) { @@ -3265,7 +3271,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) if (is_rec_inuse(ni->mi.mrec) && !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) { bool modified = false; - struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 ts; /* Update times in standard attribute. */ std = ni_std(ni); @@ -3275,19 +3281,22 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) } /* Update the access times if they have changed. */ - dup.m_time = kernel2nt(&inode->i_mtime); + ts = inode_get_mtime(inode); + dup.m_time = kernel2nt(&ts); if (std->m_time != dup.m_time) { std->m_time = dup.m_time; modified = true; } - dup.c_time = kernel2nt(&ctime); + ts = inode_get_mtime(inode); + dup.c_time = kernel2nt(&ts); if (std->c_time != dup.c_time) { std->c_time = dup.c_time; modified = true; } - dup.a_time = kernel2nt(&inode->i_atime); + ts = inode_get_atime(inode); + dup.a_time = kernel2nt(&ts); if (std->a_time != dup.a_time) { std->a_time = dup.a_time; modified = true; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 12f28cdf5c83..98ccb6650858 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -2168,8 +2168,10 @@ file_is_valid: if (!page) { page = kmalloc(log->page_size, GFP_NOFS); - if (!page) - return -ENOMEM; + if (!page) { + err = -ENOMEM; + goto out; + } } /* diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 33afee0f5559..fbfe21dbb425 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -983,18 +983,11 @@ out: if (err) return err; - mark_inode_dirty(&ni->vfs_inode); + mark_inode_dirty_sync(&ni->vfs_inode); /* verify(!ntfs_update_mftmirr()); */ - /* - * If we used wait=1, sync_inode_metadata waits for the io for the - * inode to finish. It hangs when media is removed. - * So wait=0 is sent down to sync_inode_metadata - * and filemap_fdatawrite is used for the data blocks. - */ - err = sync_inode_metadata(&ni->vfs_inode, 0); - if (!err) - err = filemap_fdatawrite(ni->vfs_inode.i_mapping); + /* write mft record on disk. */ + err = _ni_write_inode(&ni->vfs_inode, 1); return err; } @@ -2461,10 +2454,12 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) { CLST end, i, zone_len, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; + bool dirty = false; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); if (!wnd_is_used(wnd, lcn, len)) { - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + /* mark volume as dirty out of wnd->rw_lock */ + dirty = true; end = lcn + len; len = 0; @@ -2518,6 +2513,8 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) out: up_write(&wnd->rw_lock); + if (dirty) + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } /* diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 124c6e822623..cf92b2433f7a 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -729,6 +729,9 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx, u32 total = le32_to_cpu(hdr->total); u16 offs[128]; + if (unlikely(!cmp)) + return NULL; + fill_table: if (end > total) return NULL; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index eb2ed0701495..5e3d71374918 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -44,7 +44,7 @@ static struct inode *ntfs_read_mft(struct inode *inode, u64 t64; struct MFT_REC *rec; struct runs_tree *run; - struct timespec64 ctime; + struct timespec64 ts; inode->i_op = NULL; /* Setup 'uid' and 'gid' */ @@ -169,10 +169,12 @@ next_attr: #ifdef STATX_BTIME nt2kernel(std5->cr_time, &ni->i_crtime); #endif - nt2kernel(std5->a_time, &inode->i_atime); - ctime = inode_get_ctime(inode); - nt2kernel(std5->c_time, &ctime); - nt2kernel(std5->m_time, &inode->i_mtime); + nt2kernel(std5->a_time, &ts); + inode_set_atime_to_ts(inode, ts); + nt2kernel(std5->c_time, &ts); + inode_set_ctime_to_ts(inode, ts); + nt2kernel(std5->m_time, &ts); + inode_set_mtime_to_ts(inode, ts); ni->std_fa = std5->fa; @@ -960,7 +962,8 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, if (err >= 0) { if (!(ni->std_fa & FILE_ATTRIBUTE_ARCHIVE)) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE; dirty = true; } @@ -1660,8 +1663,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, d_instantiate(dentry, inode); /* Set original time. inode times (i_ctime) may be changed in ntfs_init_acl. */ - inode->i_atime = inode->i_mtime = inode_set_ctime_to_ts(inode, ni->i_crtime); - dir->i_mtime = inode_set_ctime_to_ts(dir, ni->i_crtime); + inode_set_atime_to_ts(inode, ni->i_crtime); + inode_set_ctime_to_ts(inode, ni->i_crtime); + inode_set_mtime_to_ts(inode, ni->i_crtime); + inode_set_mtime_to_ts(dir, ni->i_crtime); + inode_set_ctime_to_ts(dir, ni->i_crtime); mark_inode_dirty(dir); mark_inode_dirty(inode); @@ -1767,7 +1773,7 @@ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry) if (!err) { drop_nlink(inode); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); if (inode->i_nlink) diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index ad430d50bd79..ee3093be5170 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -156,8 +156,8 @@ static int ntfs_link(struct dentry *ode, struct inode *dir, struct dentry *de) err = ntfs_link_inode(inode, de); if (!err) { - dir->i_mtime = inode_set_ctime_to_ts(inode, - inode_set_ctime_current(dir)); + inode_set_ctime_current(inode); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(inode); mark_inode_dirty(dir); d_instantiate(de, inode); @@ -373,7 +373,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, #ifdef CONFIG_NTFS3_FS_POSIX_ACL if (IS_POSIXACL(dir)) { - /* + /* * Load in cache current acl to avoid ni_lock(dir): * ntfs_create_inode -> ntfs_init_acl -> posix_acl_create -> * ntfs_get_acl -> ntfs_get_acl_ex -> ni_lock diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 98b76d1b09e7..86aecbb01a92 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -847,7 +847,7 @@ struct OBJECT_ID { // Birth Volume Id is the Object Id of the Volume on. // which the Object Id was allocated. It never changes. struct GUID BirthVolumeId; //0x10: - + // Birth Object Id is the first Object Id that was // ever assigned to this MFT Record. I.e. If the Object Id // is changed for some reason, this field will reflect the diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 629403ede6e5..f6706143d14b 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -42,9 +42,11 @@ enum utf16_endian; #define MINUS_ONE_T ((size_t)(-1)) /* Biggest MFT / smallest cluster */ #define MAXIMUM_BYTES_PER_MFT 4096 +#define MAXIMUM_SHIFT_BYTES_PER_MFT 12 #define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) #define MAXIMUM_BYTES_PER_INDEX 4096 +#define MAXIMUM_SHIFT_BYTES_PER_INDEX 12 #define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) /* NTFS specific error code when fixup failed. */ @@ -495,8 +497,6 @@ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len); int ntfs_file_open(struct inode *inode, struct file *file); int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); @@ -872,7 +872,7 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); -extern const struct xattr_handler *ntfs_xattr_handlers[]; +extern const struct xattr_handler * const ntfs_xattr_handlers[]; int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size); void ntfs_get_wsl_perm(struct inode *inode); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index c12ebffc94da..53629b1f65e9 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -189,12 +189,19 @@ out: return err; } +/* + * mi_enum_attr - start/continue attributes enumeration in record. + * + * NOTE: mi->mrec - memory of size sbi->record_size + * here we sure that mi->mrec->total == sbi->record_size (see mi_read) + */ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) { const struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); - u32 t32, off, asize; + u32 t32, off, asize, prev_type; u16 t16; + u64 data_size, alloc_size, tot_size; if (!attr) { u32 total = le32_to_cpu(rec->total); @@ -213,6 +220,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if (!is_rec_inuse(rec)) return NULL; + prev_type = 0; attr = Add2Ptr(rec, off); } else { /* Check if input attr inside record. */ @@ -226,11 +234,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* Overflow check. */ + /* Overflow check. */ + if (off + asize < off) return NULL; - } + prev_type = le32_to_cpu(attr->type); attr = Add2Ptr(attr, asize); off += asize; } @@ -250,7 +258,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* 0x100 is last known attribute for now. */ t32 = le32_to_cpu(attr->type); - if ((t32 & 0xf) || (t32 > 0x100)) + if (!t32 || (t32 & 0xf) || (t32 > 0x100)) + return NULL; + + /* attributes in record must be ordered by type */ + if (t32 < prev_type) return NULL; /* Check overflow and boundary. */ @@ -259,16 +271,15 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* Check size of attribute. */ if (!attr->non_res) { + /* Check resident fields. */ if (asize < SIZEOF_RESIDENT) return NULL; t16 = le16_to_cpu(attr->res.data_off); - if (t16 > asize) return NULL; - t32 = le32_to_cpu(attr->res.data_size); - if (t16 + t32 > asize) + if (t16 + le32_to_cpu(attr->res.data_size) > asize) return NULL; t32 = sizeof(short) * attr->name_len; @@ -278,21 +289,52 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return attr; } - /* Check some nonresident fields. */ - if (attr->name_len && - le16_to_cpu(attr->name_off) + sizeof(short) * attr->name_len > - le16_to_cpu(attr->nres.run_off)) { + /* Check nonresident fields. */ + if (attr->non_res != 1) + return NULL; + + t16 = le16_to_cpu(attr->nres.run_off); + if (t16 > asize) + return NULL; + + t32 = sizeof(short) * attr->name_len; + if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) + return NULL; + + /* Check start/end vcn. */ + if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1) return NULL; - } - if (attr->nres.svcn || !is_attr_ext(attr)) { + data_size = le64_to_cpu(attr->nres.data_size); + if (le64_to_cpu(attr->nres.valid_size) > data_size) + return NULL; + + alloc_size = le64_to_cpu(attr->nres.alloc_size); + if (data_size > alloc_size) + return NULL; + + t32 = mi->sbi->cluster_mask; + if (alloc_size & t32) + return NULL; + + if (!attr->nres.svcn && is_attr_ext(attr)) { + /* First segment of sparse/compressed attribute */ + if (asize + 8 < SIZEOF_NONRESIDENT_EX) + return NULL; + + tot_size = le64_to_cpu(attr->nres.total_size); + if (tot_size & t32) + return NULL; + + if (tot_size > alloc_size) + return NULL; + } else { if (asize + 8 < SIZEOF_NONRESIDENT) return NULL; if (attr->nres.c_unit) return NULL; - } else if (asize + 8 < SIZEOF_NONRESIDENT_EX) - return NULL; + } return attr; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index cfec5e0c7f66..f763e3256ccc 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -453,15 +453,23 @@ static struct proc_dir_entry *proc_info_root; * ntfs3.1 * cluster size * number of clusters + * total number of mft records + * number of used mft records ~= number of files + folders + * real state of ntfs "dirty"/"clean" + * current state of ntfs "dirty"/"clean" */ static int ntfs3_volinfo(struct seq_file *m, void *o) { struct super_block *sb = m->private; struct ntfs_sb_info *sbi = sb->s_fs_info; - seq_printf(m, "ntfs%d.%d\n%u\n%zu\n", sbi->volume.major_ver, - sbi->volume.minor_ver, sbi->cluster_size, - sbi->used.bitmap.nbits); + seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n", + sbi->volume.major_ver, sbi->volume.minor_ver, + sbi->cluster_size, sbi->used.bitmap.nbits, + sbi->mft.bitmap.nbits, + sbi->mft.bitmap.nbits - wnd_zeroes(&sbi->mft.bitmap), + sbi->volume.real_dirty ? "dirty" : "clean", + (sbi->volume.flags & VOLUME_FLAG_DIRTY) ? "dirty" : "clean"); return 0; } @@ -488,9 +496,13 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, { int err; struct super_block *sb = pde_data(file_inode(file)); - struct ntfs_sb_info *sbi = sb->s_fs_info; ssize_t ret = count; - u8 *label = kmalloc(count, GFP_NOFS); + u8 *label; + + if (sb_rdonly(sb)) + return -EROFS; + + label = kmalloc(count, GFP_NOFS); if (!label) return -ENOMEM; @@ -502,7 +514,7 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, while (ret > 0 && label[ret - 1] == '\n') ret -= 1; - err = ntfs_set_label(sbi, label, ret); + err = ntfs_set_label(sb->s_fs_info, label, ret); if (err < 0) { ntfs_err(sb, "failed (%d) to write label", err); @@ -576,20 +588,30 @@ static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi) wnd_close(&sbi->mft.bitmap); wnd_close(&sbi->used.bitmap); - if (sbi->mft.ni) + if (sbi->mft.ni) { iput(&sbi->mft.ni->vfs_inode); + sbi->mft.ni = NULL; + } - if (sbi->security.ni) + if (sbi->security.ni) { iput(&sbi->security.ni->vfs_inode); + sbi->security.ni = NULL; + } - if (sbi->reparse.ni) + if (sbi->reparse.ni) { iput(&sbi->reparse.ni->vfs_inode); + sbi->reparse.ni = NULL; + } - if (sbi->objid.ni) + if (sbi->objid.ni) { iput(&sbi->objid.ni->vfs_inode); + sbi->objid.ni = NULL; + } - if (sbi->volume.ni) + if (sbi->volume.ni) { iput(&sbi->volume.ni->vfs_inode); + sbi->volume.ni = NULL; + } ntfs_update_mftmirr(sbi, 0); @@ -836,7 +858,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, struct ntfs_sb_info *sbi = sb->s_fs_info; int err; u32 mb, gb, boot_sector_size, sct_per_clst, record_size; - u64 sectors, clusters, mlcn, mlcn2; + u64 sectors, clusters, mlcn, mlcn2, dev_size0; struct NTFS_BOOT *boot; struct buffer_head *bh; struct MFT_REC *rec; @@ -845,6 +867,9 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, u32 boot_off = 0; const char *hint = "Primary boot"; + /* Save original dev_size. Used with alternative boot. */ + dev_size0 = dev_size; + sbi->volume.blocks = dev_size >> PAGE_SHIFT; bh = ntfs_bread(sb, 0); @@ -853,6 +878,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, check_boot: err = -EINVAL; + + /* Corrupted image; do not read OOB */ + if (bh->b_size - sizeof(*boot) < boot_off) + goto out; + boot = (struct NTFS_BOOT *)Add2Ptr(bh->b_data, boot_off); if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) { @@ -899,9 +929,17 @@ check_boot: goto out; } - sbi->record_size = record_size = - boot->record_size < 0 ? 1 << (-boot->record_size) : - (u32)boot->record_size << cluster_bits; + if (boot->record_size >= 0) { + record_size = (u32)boot->record_size << cluster_bits; + } else if (-boot->record_size <= MAXIMUM_SHIFT_BYTES_PER_MFT) { + record_size = 1u << (-boot->record_size); + } else { + ntfs_err(sb, "%s: invalid record size %d.", hint, + boot->record_size); + goto out; + } + + sbi->record_size = record_size; sbi->record_bits = blksize_bits(record_size); sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes @@ -918,9 +956,15 @@ check_boot: goto out; } - sbi->index_size = boot->index_size < 0 ? - 1u << (-boot->index_size) : - (u32)boot->index_size << cluster_bits; + if (boot->index_size >= 0) { + sbi->index_size = (u32)boot->index_size << cluster_bits; + } else if (-boot->index_size <= MAXIMUM_SHIFT_BYTES_PER_INDEX) { + sbi->index_size = 1u << (-boot->index_size); + } else { + ntfs_err(sb, "%s: invalid index size %d.", hint, + boot->index_size); + goto out; + } /* Check index record size. */ if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) { @@ -1055,17 +1099,17 @@ check_boot: if (bh->b_blocknr && !sb_rdonly(sb)) { /* - * Alternative boot is ok but primary is not ok. - * Do not update primary boot here 'cause it may be faked boot. - * Let ntfs to be mounted and update boot later. - */ + * Alternative boot is ok but primary is not ok. + * Do not update primary boot here 'cause it may be faked boot. + * Let ntfs to be mounted and update boot later. + */ *boot2 = kmemdup(boot, sizeof(*boot), GFP_NOFS | __GFP_NOWARN); } out: - if (err == -EINVAL && !bh->b_blocknr && dev_size > PAGE_SHIFT) { + if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) { u32 block_size = min_t(u32, sector_size, PAGE_SIZE); - u64 lbo = dev_size - sizeof(*boot); + u64 lbo = dev_size0 - sizeof(*boot); /* * Try alternative boot (last sector) @@ -1079,6 +1123,7 @@ out: boot_off = lbo & (block_size - 1); hint = "Alternative boot"; + dev_size = dev_size0; /* restore original size. */ goto check_boot; } brelse(bh); @@ -1367,7 +1412,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) } bytes = inode->i_size; - sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN); + sbi->def_table = t = kvmalloc(bytes, GFP_KERNEL); if (!t) { err = -ENOMEM; goto put_inode_out; @@ -1521,9 +1566,9 @@ load_root: if (boot2) { /* - * Alternative boot is ok but primary is not ok. - * Volume is recognized as NTFS. Update primary boot. - */ + * Alternative boot is ok but primary is not ok. + * Volume is recognized as NTFS. Update primary boot. + */ struct buffer_head *bh0 = sb_getblk(sb, 0); if (bh0) { if (buffer_locked(bh0)) @@ -1562,7 +1607,9 @@ load_root: put_inode_out: iput(inode); out: + ntfs3_put_sbi(sbi); kfree(boot2); + ntfs3_put_sbi(sbi); return err; } @@ -1756,7 +1803,6 @@ static int __init init_ntfs_fs(void) if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS)) pr_info("ntfs3: Read-only LZX/Xpress compression included\n"); - #ifdef CONFIG_PROC_FS /* Create "/proc/fs/ntfs3" */ proc_info_root = proc_mkdir("fs/ntfs3", NULL); @@ -1798,7 +1844,6 @@ static void __exit exit_ntfs_fs(void) if (proc_info_root) remove_proc_entry("fs/ntfs3", NULL); #endif - } MODULE_LICENSE("GPL"); diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 29fd391899e5..4274b6f31cfa 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -211,7 +211,8 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, size = le32_to_cpu(info->size); /* Enumerate all xattrs. */ - for (ret = 0, off = 0; off < size; off += ea_size) { + ret = 0; + for (off = 0; off + sizeof(struct EA_FULL) < size; off += ea_size) { ea = Add2Ptr(ea_all, off); ea_size = unpacked_ea_size(ea); @@ -219,6 +220,10 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, break; if (buffer) { + /* Check if we can use field ea->name */ + if (off + ea_size > size) + break; + if (ret + ea->name_len + 1 > bytes_per_buffer) { err = -ERANGE; goto out; @@ -1016,7 +1021,7 @@ static const struct xattr_handler ntfs_other_xattr_handler = { .list = ntfs_xattr_user_list, }; -const struct xattr_handler *ntfs_xattr_handlers[] = { +const struct xattr_handler * const ntfs_xattr_handlers[] = { &ntfs_other_xattr_handler, NULL, }; diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index e75137a8e7cb..62464d194da3 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -193,8 +193,8 @@ static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh, inode->i_mode = new_mode; inode_set_ctime_current(inode); di->i_mode = cpu_to_le16(inode->i_mode); - di->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - di->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + di->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index aef58f1395c8..f0937902f7b4 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7436,10 +7436,10 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, } inode->i_blocks = ocfs2_inode_sector_count(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime_sec(inode)); + di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 0fdba30740ab..6ab03494fc6e 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2048,9 +2048,9 @@ out_write_size: } inode->i_blocks = ocfs2_inode_sector_count(inode); di->i_size = cpu_to_le64((u64)i_size_read(inode)); - inode->i_mtime = inode_set_ctime_current(inode); - di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); - di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + di->i_mtime = di->i_ctime = cpu_to_le64(inode_get_mtime_sec(inode)); + di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); if (handle) ocfs2_update_inode_fsync_trans(handle, inode, 1); } diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 21472e3ed182..4d7efefa98c5 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -213,7 +213,7 @@ struct o2hb_region { unsigned int hr_num_pages; struct page **hr_slot_data; - struct block_device *hr_bdev; + struct bdev_handle *hr_bdev_handle; struct o2hb_disk_slot *hr_slots; /* live node map of this region */ @@ -261,6 +261,11 @@ struct o2hb_region { int hr_last_hb_status; }; +static inline struct block_device *reg_bdev(struct o2hb_region *reg) +{ + return reg->hr_bdev_handle ? reg->hr_bdev_handle->bdev : NULL; +} + struct o2hb_bio_wait_ctxt { atomic_t wc_num_reqs; struct completion wc_io_complete; @@ -286,7 +291,7 @@ static void o2hb_write_timeout(struct work_struct *work) hr_write_timeout_work.work); mlog(ML_ERROR, "Heartbeat write timeout to device %pg after %u " - "milliseconds\n", reg->hr_bdev, + "milliseconds\n", reg_bdev(reg), jiffies_to_msecs(jiffies - reg->hr_last_timeout_start)); if (o2hb_global_heartbeat_active()) { @@ -383,7 +388,7 @@ static void o2hb_nego_timeout(struct work_struct *work) if (!test_bit(master_node, reg->hr_nego_node_bitmap)) { printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg).\n", o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); set_bit(master_node, reg->hr_nego_node_bitmap); } if (!bitmap_equal(reg->hr_nego_node_bitmap, live_node_bitmap, @@ -398,7 +403,8 @@ static void o2hb_nego_timeout(struct work_struct *work) } printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%pg) is down.\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), + reg_bdev(reg)); /* approve negotiate timeout request. */ o2hb_arm_timeout(reg); @@ -419,7 +425,7 @@ static void o2hb_nego_timeout(struct work_struct *work) /* negotiate timeout with master node. */ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg), negotiate timeout with node %d.\n", o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(®->hr_item), - reg->hr_bdev, master_node); + reg_bdev(reg), master_node); ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG, master_node); if (ret) @@ -436,7 +442,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data, nego_msg = (struct o2hb_nego_msg *)msg->buf; printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%pg).\n", - nego_msg->node_num, config_item_name(®->hr_item), reg->hr_bdev); + nego_msg->node_num, config_item_name(®->hr_item), + reg_bdev(reg)); if (nego_msg->node_num < O2NM_MAX_NODES) set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap); else @@ -451,7 +458,7 @@ static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data, struct o2hb_region *reg = data; printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%pg).\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); o2hb_arm_timeout(reg); return 0; } @@ -515,7 +522,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, * GFP_KERNEL that the local node can get fenced. It would be * nicest if we could pre-allocate these bios and avoid this * all together. */ - bio = bio_alloc(reg->hr_bdev, 16, opf, GFP_ATOMIC); + bio = bio_alloc(reg_bdev(reg), 16, opf, GFP_ATOMIC); if (!bio) { mlog(ML_ERROR, "Could not alloc slots BIO!\n"); bio = ERR_PTR(-ENOMEM); @@ -687,7 +694,7 @@ static int o2hb_check_own_slot(struct o2hb_region *reg) errstr = ERRSTR3; mlog(ML_ERROR, "%s (%pg): expected(%u:0x%llx, 0x%llx), " - "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_bdev, + "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg_bdev(reg), slot->ds_node_num, (unsigned long long)slot->ds_last_generation, (unsigned long long)slot->ds_last_time, hb_block->hb_node, (unsigned long long)le64_to_cpu(hb_block->hb_generation), @@ -861,7 +868,7 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg) goto unlock; printk(KERN_NOTICE "o2hb: Region %s (%pg) is now a quorum device\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap); @@ -920,7 +927,7 @@ static int o2hb_check_slot(struct o2hb_region *reg, * consider it a transient miss but don't populate any * other values as they may be junk. */ mlog(ML_ERROR, "Node %d has written a bad crc to %pg\n", - slot->ds_node_num, reg->hr_bdev); + slot->ds_node_num, reg_bdev(reg)); o2hb_dump_slot(hb_block); slot->ds_equal_samples++; @@ -1003,8 +1010,8 @@ fire_callbacks: "of %u ms, but our count is %u ms.\n" "Please double check your configuration values " "for 'O2CB_HEARTBEAT_THRESHOLD'\n", - slot->ds_node_num, reg->hr_bdev, slot_dead_ms, - dead_ms); + slot->ds_node_num, reg_bdev(reg), + slot_dead_ms, dead_ms); } goto out; } @@ -1143,7 +1150,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) * can't be sure that the new block ever made it to * disk */ mlog(ML_ERROR, "Write error %d on device \"%pg\"\n", - write_wc.wc_error, reg->hr_bdev); + write_wc.wc_error, reg_bdev(reg)); ret = write_wc.wc_error; goto bail; } @@ -1169,7 +1176,7 @@ bail: printk(KERN_NOTICE "o2hb: Unable to stabilize " "heartbeat on region %s (%pg)\n", config_item_name(®->hr_item), - reg->hr_bdev); + reg_bdev(reg)); atomic_set(®->hr_steady_iterations, 0); reg->hr_aborted_start = 1; wake_up(&o2hb_steady_queue); @@ -1489,7 +1496,7 @@ static void o2hb_region_release(struct config_item *item) struct page *page; struct o2hb_region *reg = to_o2hb_region(item); - mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg->hr_bdev); + mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg_bdev(reg)); kfree(reg->hr_tmp_block); @@ -1502,8 +1509,8 @@ static void o2hb_region_release(struct config_item *item) kfree(reg->hr_slot_data); } - if (reg->hr_bdev) - blkdev_put(reg->hr_bdev, NULL); + if (reg->hr_bdev_handle) + bdev_release(reg->hr_bdev_handle); kfree(reg->hr_slots); @@ -1562,7 +1569,7 @@ static ssize_t o2hb_region_block_bytes_store(struct config_item *item, unsigned long block_bytes; unsigned int block_bits; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) return -EINVAL; status = o2hb_read_block_input(reg, page, &block_bytes, @@ -1591,7 +1598,7 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item, char *p = (char *)page; ssize_t ret; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) return -EINVAL; ret = kstrtoull(p, 0, &tmp); @@ -1616,7 +1623,7 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item, unsigned long tmp; char *p = (char *)page; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) return -EINVAL; tmp = simple_strtoul(p, &p, 0); @@ -1635,8 +1642,8 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page) { unsigned int ret = 0; - if (to_o2hb_region(item)->hr_bdev) - ret = sprintf(page, "%pg\n", to_o2hb_region(item)->hr_bdev); + if (to_o2hb_region(item)->hr_bdev_handle) + ret = sprintf(page, "%pg\n", reg_bdev(to_o2hb_region(item))); return ret; } @@ -1745,7 +1752,10 @@ out: return ret; } -/* this is acting as commit; we set up all of hr_bdev and hr_task or nothing */ +/* + * this is acting as commit; we set up all of hr_bdev_handle and hr_task or + * nothing + */ static ssize_t o2hb_region_dev_store(struct config_item *item, const char *page, size_t count) @@ -1759,7 +1769,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, ssize_t ret = -EINVAL; int live_threshold; - if (reg->hr_bdev) + if (reg->hr_bdev_handle) goto out; /* We can't heartbeat without having had our node number @@ -1785,16 +1795,15 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, if (!S_ISBLK(f.file->f_mapping->host->i_mode)) goto out2; - reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev, - BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, - NULL); - if (IS_ERR(reg->hr_bdev)) { - ret = PTR_ERR(reg->hr_bdev); - reg->hr_bdev = NULL; + reg->hr_bdev_handle = bdev_open_by_dev(f.file->f_mapping->host->i_rdev, + BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL); + if (IS_ERR(reg->hr_bdev_handle)) { + ret = PTR_ERR(reg->hr_bdev_handle); + reg->hr_bdev_handle = NULL; goto out2; } - sectsize = bdev_logical_block_size(reg->hr_bdev); + sectsize = bdev_logical_block_size(reg_bdev(reg)); if (sectsize != reg->hr_block_bytes) { mlog(ML_ERROR, "blocksize %u incorrect for device, expected %d", @@ -1890,12 +1899,12 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, if (hb_task && o2hb_global_heartbeat_active()) printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%pg)\n", - config_item_name(®->hr_item), reg->hr_bdev); + config_item_name(®->hr_item), reg_bdev(reg)); out3: if (ret < 0) { - blkdev_put(reg->hr_bdev, NULL); - reg->hr_bdev = NULL; + bdev_release(reg->hr_bdev_handle); + reg->hr_bdev_handle = NULL; } out2: fdput(f); @@ -2085,7 +2094,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%pg)\n", ((atomic_read(®->hr_steady_iterations) == 0) ? "stopped" : "start aborted"), config_item_name(item), - reg->hr_bdev); + reg_bdev(reg)); } /* diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 8b123d543e6e..a14c8fee6ee5 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1658,7 +1658,8 @@ int __ocfs2_add_entry(handle_t *handle, offset, ocfs2_dir_trailer_blk_off(dir->i_sb)); if (ocfs2_dirent_would_fit(de, rec_len)) { - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, + inode_set_ctime_current(dir)); retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh); if (retval < 0) { mlog_errno(retval); @@ -2962,11 +2963,11 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, ocfs2_dinode_new_extent_list(dir, di); i_size_write(dir, sb->s_blocksize); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); di->i_size = cpu_to_le64(sb->s_blocksize); - di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime(dir).tv_sec); - di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime(dir).tv_nsec); + di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime_sec(dir)); + di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime_nsec(dir)); ocfs2_update_inode_fsync_trans(handle, dir, 1); /* diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 81265123ce6c..9b57d012fd5c 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -337,7 +337,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inc_nlink(inode); inode->i_fop = &simple_dir_operations; @@ -360,7 +360,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, inode->i_ino = get_next_ino(); inode_init_owner(&nop_mnt_idmap, inode, parent, mode); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); ip = DLMFS_I(inode); ip->ip_conn = DLMFS_I(parent)->ip_conn; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index c3e2961ee5db..64a6ef638495 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2162,7 +2162,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres; struct ocfs2_meta_lvb *lvb; - struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 ts; lvb = ocfs2_dlm_lvb(&lockres->l_lksb); @@ -2183,12 +2183,12 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) lvb->lvb_igid = cpu_to_be32(i_gid_read(inode)); lvb->lvb_imode = cpu_to_be16(inode->i_mode); lvb->lvb_inlink = cpu_to_be16(inode->i_nlink); - lvb->lvb_iatime_packed = - cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime)); - lvb->lvb_ictime_packed = - cpu_to_be64(ocfs2_pack_timespec(&ctime)); - lvb->lvb_imtime_packed = - cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime)); + ts = inode_get_atime(inode); + lvb->lvb_iatime_packed = cpu_to_be64(ocfs2_pack_timespec(&ts)); + ts = inode_get_ctime(inode); + lvb->lvb_ictime_packed = cpu_to_be64(ocfs2_pack_timespec(&ts)); + ts = inode_get_mtime(inode); + lvb->lvb_imtime_packed = cpu_to_be64(ocfs2_pack_timespec(&ts)); lvb->lvb_iattr = cpu_to_be32(oi->ip_attr); lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features); lvb->lvb_igeneration = cpu_to_be32(inode->i_generation); @@ -2209,7 +2209,7 @@ static int ocfs2_refresh_inode_from_lvb(struct inode *inode) struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres; struct ocfs2_meta_lvb *lvb; - struct timespec64 ctime; + struct timespec64 ts; mlog_meta_lvb(0, lockres); @@ -2236,13 +2236,12 @@ static int ocfs2_refresh_inode_from_lvb(struct inode *inode) i_gid_write(inode, be32_to_cpu(lvb->lvb_igid)); inode->i_mode = be16_to_cpu(lvb->lvb_imode); set_nlink(inode, be16_to_cpu(lvb->lvb_inlink)); - ocfs2_unpack_timespec(&inode->i_atime, - be64_to_cpu(lvb->lvb_iatime_packed)); - ocfs2_unpack_timespec(&inode->i_mtime, - be64_to_cpu(lvb->lvb_imtime_packed)); - ocfs2_unpack_timespec(&ctime, - be64_to_cpu(lvb->lvb_ictime_packed)); - inode_set_ctime_to_ts(inode, ctime); + ocfs2_unpack_timespec(&ts, be64_to_cpu(lvb->lvb_iatime_packed)); + inode_set_atime_to_ts(inode, ts); + ocfs2_unpack_timespec(&ts, be64_to_cpu(lvb->lvb_imtime_packed)); + inode_set_mtime_to_ts(inode, ts); + ocfs2_unpack_timespec(&ts, be64_to_cpu(lvb->lvb_ictime_packed)); + inode_set_ctime_to_ts(inode, ts); spin_unlock(&oi->ip_lock); return 0; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index c45596c25c66..94e2a1244442 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -233,16 +233,18 @@ int ocfs2_should_update_atime(struct inode *inode, if (vfsmnt->mnt_flags & MNT_RELATIME) { struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 atime = inode_get_atime(inode); + struct timespec64 mtime = inode_get_mtime(inode); - if ((timespec64_compare(&inode->i_atime, &inode->i_mtime) <= 0) || - (timespec64_compare(&inode->i_atime, &ctime) <= 0)) + if ((timespec64_compare(&atime, &mtime) <= 0) || + (timespec64_compare(&atime, &ctime) <= 0)) return 1; return 0; } now = current_time(inode); - if ((now.tv_sec - inode->i_atime.tv_sec <= osb->s_atime_quantum)) + if ((now.tv_sec - inode_get_atime_sec(inode) <= osb->s_atime_quantum)) return 0; else return 1; @@ -275,9 +277,9 @@ int ocfs2_update_inode_atime(struct inode *inode, * have i_rwsem to guard against concurrent changes to other * inode fields. */ - inode->i_atime = current_time(inode); - di->i_atime = cpu_to_le64(inode->i_atime.tv_sec); - di->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); + inode_set_atime_to_ts(inode, current_time(inode)); + di->i_atime = cpu_to_le64(inode_get_atime_sec(inode)); + di->i_atime_nsec = cpu_to_le32(inode_get_atime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, bh); @@ -296,7 +298,7 @@ int ocfs2_set_inode_size(handle_t *handle, i_size_write(inode, new_i_size); inode->i_blocks = ocfs2_inode_sector_count(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); status = ocfs2_mark_inode_dirty(handle, inode, fe_bh); if (status < 0) { @@ -417,12 +419,12 @@ static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb, } i_size_write(inode, new_i_size); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); di = (struct ocfs2_dinode *) fe_bh->b_data; di->i_size = cpu_to_le64(new_i_size); - di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime_sec(inode)); + di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); @@ -821,9 +823,9 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, i_size_write(inode, abs_to); inode->i_blocks = ocfs2_inode_sector_count(inode); di->i_size = cpu_to_le64((u64)i_size_read(inode)); - inode->i_mtime = inode_set_ctime_current(inode); - di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); - di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + di->i_mtime = di->i_ctime = cpu_to_le64(inode_get_mtime_sec(inode)); + di->i_ctime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); di->i_mtime_nsec = di->i_ctime_nsec; if (handle) { ocfs2_journal_dirty(handle, di_bh); @@ -2040,7 +2042,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, goto out_inode_unlock; } - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); if (ret < 0) mlog_errno(ret); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index e8771600b930..999111bfc271 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -302,10 +302,10 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, inode->i_blocks = ocfs2_inode_sector_count(inode); inode->i_mapping->a_ops = &ocfs2_aops; } - inode->i_atime.tv_sec = le64_to_cpu(fe->i_atime); - inode->i_atime.tv_nsec = le32_to_cpu(fe->i_atime_nsec); - inode->i_mtime.tv_sec = le64_to_cpu(fe->i_mtime); - inode->i_mtime.tv_nsec = le32_to_cpu(fe->i_mtime_nsec); + inode_set_atime(inode, le64_to_cpu(fe->i_atime), + le32_to_cpu(fe->i_atime_nsec)); + inode_set_mtime(inode, le64_to_cpu(fe->i_mtime), + le32_to_cpu(fe->i_mtime_nsec)); inode_set_ctime(inode, le64_to_cpu(fe->i_ctime), le32_to_cpu(fe->i_ctime_nsec)); @@ -1312,12 +1312,12 @@ int ocfs2_mark_inode_dirty(handle_t *handle, fe->i_uid = cpu_to_le32(i_uid_read(inode)); fe->i_gid = cpu_to_le32(i_gid_read(inode)); fe->i_mode = cpu_to_le16(inode->i_mode); - fe->i_atime = cpu_to_le64(inode->i_atime.tv_sec); - fe->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); - fe->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); - fe->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec); - fe->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + fe->i_atime = cpu_to_le64(inode_get_atime_sec(inode)); + fe->i_atime_nsec = cpu_to_le32(inode_get_atime_nsec(inode)); + fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); + fe->i_mtime = cpu_to_le64(inode_get_mtime_sec(inode)); + fe->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); ocfs2_journal_dirty(handle, bh); ocfs2_update_inode_fsync_trans(handle, inode, 1); @@ -1348,10 +1348,10 @@ void ocfs2_refresh_inode(struct inode *inode, inode->i_blocks = 0; else inode->i_blocks = ocfs2_inode_sector_count(inode); - inode->i_atime.tv_sec = le64_to_cpu(fe->i_atime); - inode->i_atime.tv_nsec = le32_to_cpu(fe->i_atime_nsec); - inode->i_mtime.tv_sec = le64_to_cpu(fe->i_mtime); - inode->i_mtime.tv_nsec = le32_to_cpu(fe->i_mtime_nsec); + inode_set_atime(inode, le64_to_cpu(fe->i_atime), + le32_to_cpu(fe->i_atime_nsec)); + inode_set_mtime(inode, le64_to_cpu(fe->i_mtime), + le32_to_cpu(fe->i_mtime_nsec)); inode_set_ctime(inode, le64_to_cpu(fe->i_ctime), le32_to_cpu(fe->i_ctime_nsec)); diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 05d67968a3a9..1f9ed117e78b 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -951,8 +951,8 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context) di = (struct ocfs2_dinode *)di_bh->b_data; inode_set_ctime_current(inode); - di->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - di->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + di->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 5cd6d7771cea..681e9501cdd3 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -795,8 +795,8 @@ static int ocfs2_link(struct dentry *old_dentry, inc_nlink(inode); inode_set_ctime_current(inode); ocfs2_set_links_count(fe, inode->i_nlink); - fe->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_journal_dirty(handle, fe_bh); err = ocfs2_add_entry(handle, dentry, inode, @@ -995,7 +995,7 @@ static int ocfs2_unlink(struct inode *dir, ocfs2_set_links_count(fe, inode->i_nlink); ocfs2_journal_dirty(handle, fe_bh); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (S_ISDIR(inode->i_mode)) drop_nlink(dir); @@ -1550,8 +1550,8 @@ static int ocfs2_rename(struct mnt_idmap *idmap, if (status >= 0) { old_di = (struct ocfs2_dinode *) old_inode_bh->b_data; - old_di->i_ctime = cpu_to_le64(inode_get_ctime(old_inode).tv_sec); - old_di->i_ctime_nsec = cpu_to_le32(inode_get_ctime(old_inode).tv_nsec); + old_di->i_ctime = cpu_to_le64(inode_get_ctime_sec(old_inode)); + old_di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(old_inode)); ocfs2_journal_dirty(handle, old_inode_bh); } else mlog_errno(status); @@ -1592,7 +1592,7 @@ static int ocfs2_rename(struct mnt_idmap *idmap, drop_nlink(new_inode); inode_set_ctime_current(new_inode); } - old_dir->i_mtime = inode_set_ctime_current(old_dir); + inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (update_dot_dot) { status = ocfs2_update_entry(old_inode, handle, @@ -1614,8 +1614,8 @@ static int ocfs2_rename(struct mnt_idmap *idmap, if (old_dir != new_dir) { /* Keep the same times on both directories.*/ - new_dir->i_mtime = inode_set_ctime_to_ts(new_dir, - inode_get_ctime(old_dir)); + inode_set_mtime_to_ts(new_dir, + inode_set_ctime_to_ts(new_dir, inode_get_ctime(old_dir))); /* * This will also pick up the i_nlink change from the diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 25c8ec3c8c3a..3f80a56d0d60 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3751,8 +3751,8 @@ static int ocfs2_change_ctime(struct inode *inode, } inode_set_ctime_current(inode); - di->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - di->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + di->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_journal_dirty(handle, di_bh); @@ -4075,10 +4075,10 @@ static int ocfs2_complete_reflink(struct inode *s_inode, */ inode_set_ctime_current(t_inode); - di->i_ctime = cpu_to_le64(inode_get_ctime(t_inode).tv_sec); - di->i_ctime_nsec = cpu_to_le32(inode_get_ctime(t_inode).tv_nsec); + di->i_ctime = cpu_to_le64(inode_get_ctime_sec(t_inode)); + di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(t_inode)); - t_inode->i_mtime = s_inode->i_mtime; + inode_set_mtime_to_ts(t_inode, inode_get_mtime(s_inode)); di->i_mtime = s_di->i_mtime; di->i_mtime_nsec = s_di->i_mtime_nsec; } @@ -4456,7 +4456,7 @@ int ocfs2_reflink_update_dest(struct inode *dest, if (newlen > i_size_read(dest)) i_size_write(dest, newlen); spin_unlock(&OCFS2_I(dest)->ip_lock); - dest->i_mtime = inode_set_ctime_current(dest); + inode_set_mtime_to_ts(dest, inode_set_ctime_current(dest)); ret = ocfs2_mark_inode_dirty(handle, dest, d_bh); if (ret) { diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 6510ad783c91..3b81213ed7b8 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -87,14 +87,14 @@ static struct ocfs2_xattr_def_value_root def_xv = { .xv.xr_list.l_count = cpu_to_le16(1), }; -const struct xattr_handler *ocfs2_xattr_handlers[] = { +const struct xattr_handler * const ocfs2_xattr_handlers[] = { &ocfs2_xattr_user_handler, &ocfs2_xattr_trusted_handler, &ocfs2_xattr_security_handler, NULL }; -static const struct xattr_handler *ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = { +static const struct xattr_handler * const ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = { [OCFS2_XATTR_INDEX_USER] = &ocfs2_xattr_user_handler, [OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, [OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, @@ -3422,8 +3422,8 @@ static int __ocfs2_xattr_set_handle(struct inode *inode, } inode_set_ctime_current(inode); - di->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec); - di->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); + di->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); + di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_journal_dirty(ctxt->handle, xis->inode_bh); } out: diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index 00308b57f64f..65e9aa743919 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -30,7 +30,7 @@ struct ocfs2_security_xattr_info { extern const struct xattr_handler ocfs2_xattr_user_handler; extern const struct xattr_handler ocfs2_xattr_trusted_handler; extern const struct xattr_handler ocfs2_xattr_security_handler; -extern const struct xattr_handler *ocfs2_xattr_handlers[]; +extern const struct xattr_handler * const ocfs2_xattr_handlers[]; ssize_t ocfs2_listxattr(struct dentry *, char *, size_t); int ocfs2_xattr_get_nolock(struct inode *, struct buffer_head *, int, diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 2f8c1882f45c..d6cd81163030 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -51,7 +51,7 @@ struct inode *omfs_new_inode(struct inode *dir, umode_t mode) inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_mapping->a_ops = &omfs_aops; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); switch (mode & S_IFMT) { case S_IFDIR: inode->i_op = &omfs_dir_inops; @@ -134,8 +134,8 @@ static int __omfs_write_inode(struct inode *inode, int wait) oi->i_head.h_magic = OMFS_IMAGIC; oi->i_size = cpu_to_be64(inode->i_size); - ctime = inode_get_ctime(inode).tv_sec * 1000LL + - ((inode_get_ctime(inode).tv_nsec + 999)/1000); + ctime = inode_get_ctime_sec(inode) * 1000LL + + ((inode_get_ctime_nsec(inode) + 999)/1000); oi->i_ctime = cpu_to_be64(ctime); omfs_update_checksums(oi); @@ -230,11 +230,9 @@ struct inode *omfs_iget(struct super_block *sb, ino_t ino) ctime = be64_to_cpu(oi->i_ctime); nsecs = do_div(ctime, 1000) * 1000L; - inode->i_atime.tv_sec = ctime; - inode->i_mtime.tv_sec = ctime; + inode_set_atime(inode, ctime, nsecs); + inode_set_mtime(inode, ctime, nsecs); inode_set_ctime(inode, ctime, nsecs); - inode->i_atime.tv_nsec = nsecs; - inode->i_mtime.tv_nsec = nsecs; inode->i_mapping->a_ops = &omfs_aops; diff --git a/fs/open.c b/fs/open.c index 98f6601fbac6..02dc608d40d8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -870,6 +870,30 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) return ksys_fchown(fd, user, group); } +static inline int file_get_write_access(struct file *f) +{ + int error; + + error = get_write_access(f->f_inode); + if (unlikely(error)) + return error; + error = mnt_get_write_access(f->f_path.mnt); + if (unlikely(error)) + goto cleanup_inode; + if (unlikely(f->f_mode & FMODE_BACKING)) { + error = mnt_get_write_access(backing_file_user_path(f)->mnt); + if (unlikely(error)) + goto cleanup_mnt; + } + return 0; + +cleanup_mnt: + mnt_put_write_access(f->f_path.mnt); +cleanup_inode: + put_write_access(f->f_inode); + return error; +} + static int do_dentry_open(struct file *f, struct inode *inode, int (*open)(struct inode *, struct file *)) @@ -892,14 +916,9 @@ static int do_dentry_open(struct file *f, if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_inc(inode); } else if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { - error = get_write_access(inode); + error = file_get_write_access(f); if (unlikely(error)) goto cleanup_file; - error = __mnt_want_write(f->f_path.mnt); - if (unlikely(error)) { - put_write_access(inode); - goto cleanup_file; - } f->f_mode |= FMODE_WRITER; } @@ -1163,20 +1182,19 @@ EXPORT_SYMBOL_GPL(kernel_file_open); /** * backing_file_open - open a backing file for kernel internal use - * @path: path of the file to open + * @user_path: path that the user reuqested to open * @flags: open flags * @real_path: path of the backing file * @cred: credentials for open * * Open a backing file for a stackable filesystem (e.g., overlayfs). - * @path may be on the stackable filesystem and backing inode on the - * underlying filesystem. In this case, we want to be able to return - * the @real_path of the backing inode. This is done by embedding the - * returned file into a container structure that also stores the path of - * the backing inode on the underlying filesystem, which can be - * retrieved using backing_file_real_path(). + * @user_path may be on the stackable filesystem and @real_path on the + * underlying filesystem. In this case, we want to be able to return the + * @user_path of the stackable filesystem. This is done by embedding the + * returned file into a container structure that also stores the stacked + * file's path, which can be retrieved using backing_file_user_path(). */ -struct file *backing_file_open(const struct path *path, int flags, +struct file *backing_file_open(const struct path *user_path, int flags, const struct path *real_path, const struct cred *cred) { @@ -1187,9 +1205,9 @@ struct file *backing_file_open(const struct path *path, int flags, if (IS_ERR(f)) return f; - f->f_path = *path; - path_get(real_path); - *backing_file_real_path(f) = *real_path; + path_get(user_path); + *backing_file_user_path(f) = *user_path; + f->f_path = *real_path; error = do_dentry_open(f, d_inode(real_path->dentry), NULL); if (error) { fput(f); diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index b2457cb97fa0..c4b65a6d41cc 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -237,7 +237,7 @@ found: if (IS_ERR(inode)) return ERR_CAST(inode); if (inode->i_state & I_NEW) { - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); ent_oi = OP_I(inode); ent_oi->type = ent_type; ent_oi->u = ent_data; @@ -387,7 +387,7 @@ static int openprom_fill_super(struct super_block *s, struct fs_context *fc) goto out_no_root; } - root_inode->i_mtime = root_inode->i_atime = inode_set_ctime_current(root_inode); + simple_inode_init_ts(root_inode); root_inode->i_op = &openprom_inode_operations; root_inode->i_fop = &openprom_operations; root_inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index b711654ca18a..926d9c0a428a 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -103,7 +103,7 @@ enum orangefs_vfs_op_states { #define ORANGEFS_CACHE_CREATE_FLAGS 0 #endif -extern const struct xattr_handler *orangefs_xattr_handlers[]; +extern const struct xattr_handler * const orangefs_xattr_handlers[]; extern struct posix_acl *orangefs_get_acl(struct inode *inode, int type, bool rcu); extern int orangefs_set_acl(struct mnt_idmap *idmap, diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 0a9fcfdf552f..0fdceb00ca07 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -155,14 +155,14 @@ static inline void copy_attributes_from_inode(struct inode *inode, if (orangefs_inode->attr_valid & ATTR_ATIME) { attrs->mask |= ORANGEFS_ATTR_SYS_ATIME; if (orangefs_inode->attr_valid & ATTR_ATIME_SET) { - attrs->atime = (time64_t)inode->i_atime.tv_sec; + attrs->atime = (time64_t) inode_get_atime_sec(inode); attrs->mask |= ORANGEFS_ATTR_SYS_ATIME_SET; } } if (orangefs_inode->attr_valid & ATTR_MTIME) { attrs->mask |= ORANGEFS_ATTR_SYS_MTIME; if (orangefs_inode->attr_valid & ATTR_MTIME_SET) { - attrs->mtime = (time64_t)inode->i_mtime.tv_sec; + attrs->mtime = (time64_t) inode_get_mtime_sec(inode); attrs->mask |= ORANGEFS_ATTR_SYS_MTIME_SET; } } @@ -357,15 +357,15 @@ again2: downcall.resp.getattr.attributes.owner); inode->i_gid = make_kgid(&init_user_ns, new_op-> downcall.resp.getattr.attributes.group); - inode->i_atime.tv_sec = (time64_t)new_op-> - downcall.resp.getattr.attributes.atime; - inode->i_mtime.tv_sec = (time64_t)new_op-> - downcall.resp.getattr.attributes.mtime; + inode_set_atime(inode, + (time64_t)new_op->downcall.resp.getattr.attributes.atime, + 0); + inode_set_mtime(inode, + (time64_t)new_op->downcall.resp.getattr.attributes.mtime, + 0); inode_set_ctime(inode, (time64_t)new_op->downcall.resp.getattr.attributes.ctime, 0); - inode->i_atime.tv_nsec = 0; - inode->i_mtime.tv_nsec = 0; /* special case: mark the root inode as sticky */ inode->i_mode = type | (is_root_handle(inode) ? S_ISVTX : 0) | diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 68b62689a63e..74ef75586f38 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -554,7 +554,7 @@ static const struct xattr_handler orangefs_xattr_default_handler = { .set = orangefs_xattr_set_default, }; -const struct xattr_handler *orangefs_xattr_handlers[] = { +const struct xattr_handler * const orangefs_xattr_handlers[] = { &orangefs_xattr_default_handler, NULL }; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index d1761ec5866a..ada3fcc9c6d5 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -337,7 +337,7 @@ static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry, { struct iattr attr = { .ia_valid = - ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index c8c8588bd98c..26b782c53910 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -188,7 +188,7 @@ static int ovl_check_encode_origin(struct dentry *dentry) /* Lower file handle for non-upper non-decodable */ if (!ovl_dentry_upper(dentry) && !decodable) - return 0; + return 1; /* Upper file handle for pure upper */ if (!ovl_dentry_lower(dentry)) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4193633c4c7a..ec3671ca140c 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -239,6 +239,7 @@ static void ovl_file_accessed(struct file *file) { struct inode *inode, *upperinode; struct timespec64 ctime, uctime; + struct timespec64 mtime, umtime; if (file->f_flags & O_NOATIME) return; @@ -251,9 +252,11 @@ static void ovl_file_accessed(struct file *file) ctime = inode_get_ctime(inode); uctime = inode_get_ctime(upperinode); - if ((!timespec64_equal(&inode->i_mtime, &upperinode->i_mtime) || - !timespec64_equal(&ctime, &uctime))) { - inode->i_mtime = upperinode->i_mtime; + mtime = inode_get_mtime(inode); + umtime = inode_get_mtime(upperinode); + if ((!timespec64_equal(&mtime, &umtime)) || + !timespec64_equal(&ctime, &uctime)) { + inode_set_mtime_to_ts(inode, inode_get_mtime(upperinode)); inode_set_ctime_to_ts(inode, uctime); } @@ -341,7 +344,6 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (!aio_req) goto out; - real.flags = 0; aio_req->orig_iocb = iocb; kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_complete = ovl_aio_rw_complete; @@ -391,6 +393,12 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); + /* + * Overlayfs doesn't support deferred completions, don't copy + * this property in case it is set by the issuer. + */ + ifl &= ~IOCB_DIO_CALLER_COMP; + old_cred = ovl_override_creds(file_inode(file)->i_sb); if (is_sync_kiocb(iocb)) { file_start_write(real.file); @@ -407,7 +415,6 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (!aio_req) goto out; - real.flags = 0; aio_req->orig_iocb = iocb; kiocb_clone(&aio_req->iocb, iocb, get_file(real.file)); aio_req->iocb.ki_flags = ifl; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 83ef66644c21..b6e98a7d36ce 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -704,7 +704,8 @@ int ovl_update_time(struct inode *inode, int flags) if (upperpath.dentry) { touch_atime(&upperpath); - inode->i_atime = d_inode(upperpath.dentry)->i_atime; + inode_set_atime_to_ts(inode, + inode_get_atime(d_inode(upperpath.dentry))); } } return 0; diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index e9539f98e86a..d82d2a043da2 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -8,6 +8,7 @@ struct ovl_config { char *upperdir; char *workdir; + char **lowerdirs; bool default_permissions; int redirect_mode; int verity_mode; @@ -39,17 +40,8 @@ struct ovl_layer { int idx; /* One fsid per unique underlying sb (upper fsid == 0) */ int fsid; - char *name; }; -/* - * ovl_free_fs() relies on @mnt being the first member when unmounting - * the private mounts created for each layer. Let's check both the - * offset and type. - */ -static_assert(offsetof(struct ovl_layer, mnt) == 0); -static_assert(__same_type(typeof_member(struct ovl_layer, mnt), struct vfsmount *)); - struct ovl_path { const struct ovl_layer *layer; struct dentry *dentry; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index b9355bb6d75a..f6ff23fd101c 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -157,6 +157,34 @@ const struct fs_parameter_spec ovl_parameter_spec[] = { {} }; +static char *ovl_next_opt(char **s) +{ + char *sbegin = *s; + char *p; + + if (sbegin == NULL) + return NULL; + + for (p = sbegin; *p; p++) { + if (*p == '\\') { + p++; + if (!*p) + break; + } else if (*p == ',') { + *p = '\0'; + *s = p + 1; + return sbegin; + } + } + *s = NULL; + return sbegin; +} + +static int ovl_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, ovl_next_opt); +} + static ssize_t ovl_parse_param_split_lowerdirs(char *str) { ssize_t nr_layers = 1, nr_colons = 0; @@ -164,7 +192,8 @@ static ssize_t ovl_parse_param_split_lowerdirs(char *str) for (s = d = str;; s++, d++) { if (*s == '\\') { - s++; + /* keep esc chars in split lowerdir */ + *d++ = *s++; } else if (*s == ':') { bool next_colon = (*(s + 1) == ':'); @@ -239,7 +268,7 @@ static void ovl_unescape(char *s) } } -static int ovl_mount_dir(const char *name, struct path *path) +static int ovl_mount_dir(const char *name, struct path *path, bool upper) { int err = -ENOMEM; char *tmp = kstrdup(name, GFP_KERNEL); @@ -248,7 +277,7 @@ static int ovl_mount_dir(const char *name, struct path *path) ovl_unescape(tmp); err = ovl_mount_dir_noesc(tmp, path); - if (!err && path->dentry->d_flags & DCACHE_OP_REAL) { + if (!err && upper && path->dentry->d_flags & DCACHE_OP_REAL) { pr_err("filesystem on '%s' not supported as upperdir\n", tmp); path_put_init(path); @@ -269,7 +298,7 @@ static int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, struct path path; char *dup; - err = ovl_mount_dir(name, &path); + err = ovl_mount_dir(name, &path, true); if (err) return err; @@ -321,12 +350,6 @@ static void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx) * Set "/lower1", "/lower2", and "/lower3" as lower layers and * "/data1" and "/data2" as data lower layers. Any existing lower * layers are replaced. - * (2) lowerdir=:/lower4 - * Append "/lower4" to current stack of lower layers. This requires - * that there already is at least one lower layer configured. - * (3) lowerdir=::/lower5 - * Append data "/lower5" as data lower layer. This requires that - * there's at least one regular lower layer present. */ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) { @@ -348,49 +371,9 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) return 0; } - if (strncmp(name, "::", 2) == 0) { - /* - * This is a data layer. - * There must be at least one regular lower layer - * specified. - */ - if (ctx->nr == 0) { - pr_err("data lower layers without regular lower layers not allowed"); - return -EINVAL; - } - - /* Skip the leading "::". */ - name += 2; - data_layer = true; - /* - * A data layer is automatically an append as there - * must've been at least one regular lower layer. - */ - append = true; - } else if (*name == ':') { - /* - * This is a regular lower layer. - * If users want to append a layer enforce that they - * have already specified a first layer before. It's - * better to be strict. - */ - if (ctx->nr == 0) { - pr_err("cannot append layer if no previous layer has been specified"); - return -EINVAL; - } - - /* - * Once a sequence of data layers has started regular - * lower layers are forbidden. - */ - if (ctx->nr_data > 0) { - pr_err("regular lower layers cannot follow data lower layers"); - return -EINVAL; - } - - /* Skip the leading ":". */ - name++; - append = true; + if (*name == ':') { + pr_err("cannot append lower layer"); + return -EINVAL; } dup = kstrdup(name, GFP_KERNEL); @@ -472,7 +455,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) l = &ctx->lower[nr]; memset(l, 0, sizeof(*l)); - err = ovl_mount_dir_noesc(dup_iter, &l->path); + err = ovl_mount_dir(dup_iter, &l->path, false); if (err) goto out_put; @@ -682,6 +665,7 @@ static int ovl_reconfigure(struct fs_context *fc) } static const struct fs_context_operations ovl_context_ops = { + .parse_monolithic = ovl_parse_monolithic, .parse_param = ovl_parse_param, .get_tree = ovl_get_tree, .reconfigure = ovl_reconfigure, @@ -752,12 +736,12 @@ void ovl_free_fs(struct ovl_fs *ofs) if (ofs->upperdir_locked) ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root); - /* Hack! Reuse ofs->layers as a vfsmount array before freeing it */ - mounts = (struct vfsmount **) ofs->layers; + /* Reuse ofs->config.lowerdirs as a vfsmount array before freeing it */ + mounts = (struct vfsmount **) ofs->config.lowerdirs; for (i = 0; i < ofs->numlayer; i++) { iput(ofs->layers[i].trap); + kfree(ofs->config.lowerdirs[i]); mounts[i] = ofs->layers[i].mnt; - kfree(ofs->layers[i].name); } kern_unmount_array(mounts, ofs->numlayer); kfree(ofs->layers); @@ -765,6 +749,7 @@ void ovl_free_fs(struct ovl_fs *ofs) free_anon_bdev(ofs->fs[i].pseudo_dev); kfree(ofs->fs); + kfree(ofs->config.lowerdirs); kfree(ofs->config.upperdir); kfree(ofs->config.workdir); if (ofs->creator_cred) @@ -949,16 +934,23 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) struct super_block *sb = dentry->d_sb; struct ovl_fs *ofs = OVL_FS(sb); size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer; - const struct ovl_layer *data_layers = &ofs->layers[nr_merged_lower]; - - /* ofs->layers[0] is the upper layer */ - seq_printf(m, ",lowerdir=%s", ofs->layers[1].name); - /* dump regular lower layers */ - for (nr = 2; nr < nr_merged_lower; nr++) - seq_printf(m, ":%s", ofs->layers[nr].name); - /* dump data lower layers */ - for (nr = 0; nr < ofs->numdatalayer; nr++) - seq_printf(m, "::%s", data_layers[nr].name); + + /* + * lowerdirs[] starts from offset 1, then + * >= 0 regular lower layers prefixed with : and + * >= 0 data-only lower layers prefixed with :: + * + * we need to escase comma and space like seq_show_option() does and + * we also need to escape the colon separator from lowerdir paths. + */ + seq_puts(m, ",lowerdir="); + for (nr = 1; nr < ofs->numlayer; nr++) { + if (nr > 1) + seq_putc(m, ':'); + if (nr >= nr_merged_lower) + seq_putc(m, ':'); + seq_escape(m, ofs->config.lowerdirs[nr], ":, \t\n\\"); + } if (ofs->config.upperdir) { seq_show_option(m, "upperdir", ofs->config.upperdir); seq_show_option(m, "workdir", ofs->config.workdir); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index def266b5e2a3..6cd949c59fed 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -34,14 +34,22 @@ static struct dentry *ovl_d_real(struct dentry *dentry, struct dentry *real = NULL, *lower; int err; - /* It's an overlay file */ + /* + * vfs is only expected to call d_real() with NULL from d_real_inode() + * and with overlay inode from file_dentry() on an overlay file. + * + * TODO: remove @inode argument from d_real() API, remove code in this + * function that deals with non-NULL @inode and remove d_real() call + * from file_dentry(). + */ if (inode && d_inode(dentry) == inode) return dentry; + else if (inode) + goto bug; if (!d_is_reg(dentry)) { - if (!inode || inode == d_inode(dentry)) - return dentry; - goto bug; + /* d_real_inode() is only relevant for regular files */ + return dentry; } real = ovl_dentry_upper(dentry); @@ -104,8 +112,8 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak) static int ovl_dentry_revalidate_common(struct dentry *dentry, unsigned int flags, bool weak) { - struct ovl_entry *oe = OVL_E(dentry); - struct ovl_path *lowerstack = ovl_lowerstack(oe); + struct ovl_entry *oe; + struct ovl_path *lowerstack; struct inode *inode = d_inode_rcu(dentry); struct dentry *upper; unsigned int i; @@ -115,6 +123,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, if (!inode) return -ECHILD; + oe = OVL_I_E(inode); + lowerstack = ovl_lowerstack(oe); upper = ovl_i_dentry_upper(inode); if (upper) ret = ovl_revalidate_real(upper, flags, weak); @@ -167,6 +177,7 @@ static void ovl_free_inode(struct inode *inode) struct ovl_inode *oi = OVL_I(inode); kfree(oi->redirect); + kfree(oi->oe); mutex_destroy(&oi->lock); kmem_cache_free(ovl_inode_cachep, oi); } @@ -176,7 +187,7 @@ static void ovl_destroy_inode(struct inode *inode) struct ovl_inode *oi = OVL_I(inode); dput(oi->__upperdentry); - ovl_free_entry(oi->oe); + ovl_stack_put(ovl_lowerstack(oi->oe), ovl_numlower(oi->oe)); if (S_ISDIR(inode->i_mode)) ovl_dir_cache_free(inode); else @@ -484,13 +495,13 @@ static const struct xattr_handler ovl_other_xattr_handler = { .set = ovl_other_xattr_set, }; -static const struct xattr_handler *ovl_trusted_xattr_handlers[] = { +static const struct xattr_handler * const ovl_trusted_xattr_handlers[] = { &ovl_own_trusted_xattr_handler, &ovl_other_xattr_handler, NULL }; -static const struct xattr_handler *ovl_user_xattr_handlers[] = { +static const struct xattr_handler * const ovl_user_xattr_handlers[] = { &ovl_own_user_xattr_handler, &ovl_other_xattr_handler, NULL @@ -569,11 +580,6 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs, upper_layer->idx = 0; upper_layer->fsid = 0; - err = -ENOMEM; - upper_layer->name = kstrdup(ofs->config.upperdir, GFP_KERNEL); - if (!upper_layer->name) - goto out; - /* * Inherit SB_NOSEC flag from upperdir. * @@ -1122,7 +1128,8 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs, layers[ofs->numlayer].idx = ofs->numlayer; layers[ofs->numlayer].fsid = fsid; layers[ofs->numlayer].fs = &ofs->fs[fsid]; - layers[ofs->numlayer].name = l->name; + /* Store for printing lowerdir=... in ovl_show_options() */ + ofs->config.lowerdirs[ofs->numlayer] = l->name; l->name = NULL; ofs->numlayer++; ofs->fs[fsid].is_lower = true; @@ -1367,8 +1374,16 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) if (!layers) goto out_err; + ofs->config.lowerdirs = kcalloc(ctx->nr + 1, sizeof(char *), GFP_KERNEL); + if (!ofs->config.lowerdirs) { + kfree(layers); + goto out_err; + } ofs->layers = layers; - /* Layer 0 is reserved for upper even if there's no upper */ + /* + * Layer 0 is reserved for upper even if there's no upper. + * For consistency, config.lowerdirs[0] is NULL. + */ ofs->numlayer = 1; sb->s_stack_depth = 0; @@ -1481,8 +1496,16 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_xattr = ofs->config.userxattr ? ovl_user_xattr_handlers : ovl_trusted_xattr_handlers; sb->s_fs_info = ofs; +#ifdef CONFIG_FS_POSIX_ACL sb->s_flags |= SB_POSIXACL; +#endif sb->s_iflags |= SB_I_SKIP_SYNC | SB_I_IMA_UNVERIFIABLE_SIGNATURE; + /* + * Ensure that umask handling is done by the filesystems used + * for the the upper layer instead of overlayfs as that would + * lead to unexpected results. + */ + sb->s_iflags |= SB_I_NOUMASK; err = -ENOMEM; root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 89e0d60d35b6..868afd8834c3 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -1409,8 +1409,8 @@ void ovl_copyattr(struct inode *inode) inode->i_uid = vfsuid_into_kuid(vfsuid); inode->i_gid = vfsgid_into_kgid(vfsgid); inode->i_mode = realinode->i_mode; - inode->i_atime = realinode->i_atime; - inode->i_mtime = realinode->i_mtime; + inode_set_atime_to_ts(inode, inode_get_atime(realinode)); + inode_set_mtime_to_ts(inode, inode_get_mtime(realinode)); inode_set_ctime_to_ts(inode, inode_get_ctime(realinode)); i_size_write(inode, i_size_read(realinode)); } diff --git a/fs/pipe.c b/fs/pipe.c index 6c1a9b1db907..8916c455a469 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -227,6 +227,36 @@ static inline bool pipe_readable(const struct pipe_inode_info *pipe) return !pipe_empty(head, tail) || !writers; } +static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, + struct pipe_buffer *buf, + unsigned int tail) +{ + pipe_buf_release(pipe, buf); + + /* + * If the pipe has a watch_queue, we need additional protection + * by the spinlock because notifications get posted with only + * this spinlock, no mutex + */ + if (pipe_has_watch_queue(pipe)) { + spin_lock_irq(&pipe->rd_wait.lock); +#ifdef CONFIG_WATCH_QUEUE + if (buf->flags & PIPE_BUF_FLAG_LOSS) + pipe->note_loss = true; +#endif + pipe->tail = ++tail; + spin_unlock_irq(&pipe->rd_wait.lock); + return tail; + } + + /* + * Without a watch_queue, we can simply increment the tail + * without the spinlock - the mutex is enough. + */ + pipe->tail = ++tail; + return tail; +} + static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { @@ -320,17 +350,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) buf->len = 0; } - if (!buf->len) { - pipe_buf_release(pipe, buf); - spin_lock_irq(&pipe->rd_wait.lock); -#ifdef CONFIG_WATCH_QUEUE - if (buf->flags & PIPE_BUF_FLAG_LOSS) - pipe->note_loss = true; -#endif - tail++; - pipe->tail = tail; - spin_unlock_irq(&pipe->rd_wait.lock); - } + if (!buf->len) + tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ @@ -437,12 +458,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe_has_watch_queue(pipe)) { ret = -EXDEV; goto out; } -#endif /* * If it wasn't empty we try to merge new data into @@ -507,16 +526,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * it, either the reader will consume it or it'll still * be there for the next write. */ - spin_lock_irq(&pipe->rd_wait.lock); - - head = pipe->head; - if (pipe_full(head, pipe->tail, pipe->max_usage)) { - spin_unlock_irq(&pipe->rd_wait.lock); - continue; - } - pipe->head = head + 1; - spin_unlock_irq(&pipe->rd_wait.lock); /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; @@ -537,7 +547,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) break; } ret += copied; - buf->offset = 0; buf->len = copied; if (!iov_iter_count(from)) @@ -899,7 +908,7 @@ static struct inode * get_pipe_inode(void) inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); return inode; @@ -1325,10 +1334,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) unsigned int nr_slots, size; long ret = 0; -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) + if (pipe_has_watch_queue(pipe)) return -EBUSY; -#endif size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; @@ -1380,10 +1387,8 @@ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) if (file->f_op != &pipefifo_fops || !pipe) return NULL; -#ifdef CONFIG_WATCH_QUEUE - if (for_splice && pipe->watch_queue) + if (for_splice && pipe_has_watch_queue(pipe)) return NULL; -#endif return pipe; } diff --git a/fs/proc/base.c b/fs/proc/base.c index ffd54617c354..83396ab14998 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1902,7 +1902,7 @@ struct inode *proc_pid_make_inode(struct super_block *sb, ei = PROC_I(inode); inode->i_mode = mode; inode->i_ino = get_next_ino(); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &proc_def_inode_operations; /* @@ -2218,7 +2218,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) rc = -ENOENT; vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { - *path = vma->vm_file->f_path; + *path = *file_user_path(vma->vm_file); path_get(path); rc = 0; } diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6276b3938842..6e72e5ad42bc 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -113,10 +113,12 @@ static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode) struct file *file; rcu_read_lock(); - file = task_lookup_fd_rcu(task, fd); - if (file) - *mode = file->f_mode; + file = task_lookup_fdget_rcu(task, fd); rcu_read_unlock(); + if (file) { + *mode = file->f_mode; + fput(file); + } return !!file; } @@ -259,12 +261,13 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, char name[10 + 1]; unsigned int len; - f = task_lookup_next_fd_rcu(p, &fd); + f = task_lookup_next_fdget_rcu(p, &fd); ctx->pos = fd + 2LL; if (!f) break; data.mode = f->f_mode; rcu_read_unlock(); + fput(f); data.fd = fd; len = snprintf(name, sizeof(name), "%u", fd); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 532dc9d240f7..592ed2516f47 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -660,7 +660,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) inode->i_private = de->data; inode->i_ino = de->low_ino; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); PROC_I(inode)->pde = de; if (is_empty_pde(de)) { make_empty_dir_inode(inode); diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 4d3493579458..c6e7ebc63756 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -58,7 +58,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region) if (file) { seq_pad(m, ' '); - seq_file_path(m, file, ""); + seq_path(m, file_user_path(file), ""); } seq_putc(m, '\n'); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c88854df0b62..bc9a2db89cfa 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -465,7 +465,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, head->count++; spin_unlock(&sysctl_lock); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mode = table->mode; if (!S_ISDIR(table->mode)) { inode->i_mode |= S_IFREG; diff --git a/fs/proc/self.c b/fs/proc/self.c index ecc4da8d265e..b46fbfd22681 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -46,7 +46,7 @@ int proc_setup_self(struct super_block *s) struct inode *inode = new_inode(s); if (inode) { inode->i_ino = self_inum; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3dd5be96691b..1593940ca01e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -296,7 +296,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) if (anon_name) seq_printf(m, "[anon_shmem:%s]", anon_name->name); else - seq_file_path(m, file, "\n"); + seq_path(m, file_user_path(file), "\n"); goto done; } @@ -1967,7 +1967,7 @@ static int show_numa_map(struct seq_file *m, void *v) if (file) { seq_puts(m, " file="); - seq_file_path(m, file, "\n\t= "); + seq_path(m, file_user_path(file), "\n\t= "); } else if (vma_is_initial_heap(vma)) { seq_puts(m, " heap"); } else if (vma_is_initial_stack(vma)) { diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 7cebd397cc26..bce674533000 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -157,7 +157,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) if (file) { seq_pad(m, ' '); - seq_file_path(m, file, ""); + seq_path(m, file_user_path(file), ""); } else if (mm && vma_is_initial_stack(vma)) { seq_pad(m, ' '); seq_puts(m, "[stack]"); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index 63ac1f93289f..0e5050d6ab64 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -46,7 +46,7 @@ int proc_setup_thread_self(struct super_block *s) struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 585360706b33..d41c20d1b5e8 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -223,7 +223,7 @@ static struct inode *pstore_get_inode(struct super_block *sb) struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } return inode; } @@ -390,7 +390,8 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) inode->i_private = private; if (record->time.tv_sec) - inode->i_mtime = inode_set_ctime_to_ts(inode, record->time); + inode_set_mtime_to_ts(inode, + inode_set_ctime_to_ts(inode, record->time)); d_add(dentry, inode); diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index a7171f5532a1..6eb9bb369b57 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -301,10 +301,8 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino) i_gid_write(inode, (gid_t)le16_to_cpu(raw_inode->di_gid)); set_nlink(inode, le16_to_cpu(raw_inode->di_nlink)); inode->i_size = le32_to_cpu(raw_inode->di_size); - inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->di_mtime); - inode->i_mtime.tv_nsec = 0; - inode->i_atime.tv_sec = le32_to_cpu(raw_inode->di_atime); - inode->i_atime.tv_nsec = 0; + inode_set_mtime(inode, le32_to_cpu(raw_inode->di_mtime), 0); + inode_set_atime(inode, le32_to_cpu(raw_inode->di_atime), 0); inode_set_ctime(inode, le32_to_cpu(raw_inode->di_ctime), 0); inode->i_blocks = le32_to_cpu(raw_inode->di_first_xtnt.xtnt_size); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 21f90d519f1a..a286c545717f 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -558,10 +558,8 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) i_uid_write(inode, (uid_t)fs32_to_cpu(sbi, raw_inode->di_uid)); i_gid_write(inode, (gid_t)fs32_to_cpu(sbi, raw_inode->di_gid)); inode->i_size = fs64_to_cpu(sbi, raw_inode->di_size); - inode->i_mtime.tv_sec = fs32_to_cpu(sbi, raw_inode->di_mtime); - inode->i_mtime.tv_nsec = 0; - inode->i_atime.tv_sec = fs32_to_cpu(sbi, raw_inode->di_atime); - inode->i_atime.tv_nsec = 0; + inode_set_mtime(inode, fs32_to_cpu(sbi, raw_inode->di_mtime), 0); + inode_set_atime(inode, fs32_to_cpu(sbi, raw_inode->di_atime), 0); inode_set_ctime(inode, fs32_to_cpu(sbi, raw_inode->di_ctime), 0); /* calc blocks based on 512 byte blocksize */ diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 9e72bfe8bbad..31e897ad5e6a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -233,19 +233,18 @@ static void put_quota_format(struct quota_format_type *fmt) * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * - * When the last reference of a dquot will be dropped, the dquot will be - * added to releasing_dquots. We'd then queue work item which would call + * When the last reference of a dquot is dropped, the dquot is added to + * releasing_dquots. We'll then queue work item which will call * synchronize_srcu() and after that perform the final cleanup of all the - * dquots on the list. Both releasing_dquots and free_dquots use the - * dq_free list_head in the dquot struct. When a dquot is removed from - * releasing_dquots, a reference count is always subtracted, and if - * dq_count == 0 at that point, the dquot will be added to the free_dquots. + * dquots on the list. Each cleaned up dquot is moved to free_dquots list. + * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot + * struct. * - * Unused dquots (dq_count == 0) are added to the free_dquots list when freed, - * and this list is searched whenever we need an available dquot. Dquots are - * removed from the list as soon as they are used again, and - * dqstats.free_dquots gives the number of dquots on the list. When - * dquot is invalidated it's completely released from memory. + * Unused and cleaned up dquots are in the free_dquots list and this list is + * searched whenever we need an available dquot. Dquots are removed from the + * list as soon as they are used again and dqstats.free_dquots gives the number + * of dquots on the list. When dquot is invalidated it's completely released + * from memory. * * Dirty dquots are added to the dqi_dirty_list of quota_info when mark * dirtied, and this list is searched when writing dirty dquots back to @@ -321,6 +320,7 @@ static inline void put_dquot_last(struct dquot *dquot) static inline void put_releasing_dquots(struct dquot *dquot) { list_add_tail(&dquot->dq_free, &releasing_dquots); + set_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void remove_free_dquot(struct dquot *dquot) @@ -328,8 +328,10 @@ static inline void remove_free_dquot(struct dquot *dquot) if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); - if (!atomic_read(&dquot->dq_count)) + if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags)) dqstats_dec(DQST_FREE_DQUOTS); + else + clear_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void put_inuse(struct dquot *dquot) @@ -581,12 +583,6 @@ restart: continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { - /* dquot in releasing_dquots, flush and retry */ - if (!list_empty(&dquot->dq_free)) { - spin_unlock(&dq_list_lock); - goto restart; - } - atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* @@ -606,6 +602,15 @@ restart: goto restart; } /* + * The last user already dropped its reference but dquot didn't + * get fully cleaned up yet. Restart the scan which flushes the + * work cleaning up released dquots. + */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + goto restart; + } + /* * Quota now has no users and it has been written on last * dqput() */ @@ -696,6 +701,13 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dq_dirty); WARN_ON(!dquot_active(dquot)); + /* If the dquot is releasing we should not touch it */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); + continue; + } /* Now we have active dquot from which someone is * holding reference so we can safely just increase @@ -809,18 +821,18 @@ static void quota_release_workfn(struct work_struct *work) /* Exchange the list head to avoid livelock. */ list_replace_init(&releasing_dquots, &rls_head); spin_unlock(&dq_list_lock); + synchronize_srcu(&dquot_srcu); restart: - synchronize_srcu(&dquot_srcu); spin_lock(&dq_list_lock); while (!list_empty(&rls_head)) { dquot = list_first_entry(&rls_head, struct dquot, dq_free); - /* Dquot got used again? */ - if (atomic_read(&dquot->dq_count) > 1) { - remove_free_dquot(dquot); - atomic_dec(&dquot->dq_count); - continue; - } + WARN_ON_ONCE(atomic_read(&dquot->dq_count)); + /* + * Note that DQ_RELEASING_B protects us from racing with + * invalidate_dquots() calls so we are safe to work with the + * dquot even after we drop dq_list_lock. + */ if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); /* Commit dquot before releasing */ @@ -834,7 +846,6 @@ restart: } /* Dquot is inactive and clean, now move it to free list */ remove_free_dquot(dquot); - atomic_dec(&dquot->dq_count); put_dquot_last(dquot); } spin_unlock(&dq_list_lock); @@ -875,6 +886,7 @@ void dqput(struct dquot *dquot) BUG_ON(!list_empty(&dquot->dq_free)); #endif put_releasing_dquots(dquot); + atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); queue_delayed_work(system_unbound_wq, "a_release_work, 1); } @@ -963,7 +975,7 @@ we_slept: dqstats_inc(DQST_LOOKUPS); } /* Wait for dq_lock - after this we know that either dquot_release() is - * already finished or it will be canceled due to dq_count > 1 test */ + * already finished or it will be canceled due to dq_count > 0 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ if (!dquot_active(dquot)) { diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 18e8387cab41..4ac05a9e25bc 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -65,7 +65,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, inode->i_mapping->a_ops = &ram_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); @@ -105,7 +105,7 @@ ramfs_mknod(struct mnt_idmap *idmap, struct inode *dir, d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ error = 0; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); } return error; } @@ -138,7 +138,8 @@ static int ramfs_symlink(struct mnt_idmap *idmap, struct inode *dir, if (!error) { d_instantiate(dentry, inode); dget(dentry); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, + inode_set_ctime_current(dir)); } else iput(inode); } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 86e55d4bb10d..c8572346556f 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1257,11 +1257,9 @@ static void init_inode(struct inode *inode, struct treepath *path) i_uid_write(inode, sd_v1_uid(sd)); i_gid_write(inode, sd_v1_gid(sd)); inode->i_size = sd_v1_size(sd); - inode->i_atime.tv_sec = sd_v1_atime(sd); - inode->i_mtime.tv_sec = sd_v1_mtime(sd); + inode_set_atime(inode, sd_v1_atime(sd), 0); + inode_set_mtime(inode, sd_v1_mtime(sd), 0); inode_set_ctime(inode, sd_v1_ctime(sd), 0); - inode->i_atime.tv_nsec = 0; - inode->i_mtime.tv_nsec = 0; inode->i_blocks = sd_v1_blocks(sd); inode->i_generation = le32_to_cpu(INODE_PKEY(inode)->k_dir_id); @@ -1311,11 +1309,9 @@ static void init_inode(struct inode *inode, struct treepath *path) i_uid_write(inode, sd_v2_uid(sd)); inode->i_size = sd_v2_size(sd); i_gid_write(inode, sd_v2_gid(sd)); - inode->i_mtime.tv_sec = sd_v2_mtime(sd); - inode->i_atime.tv_sec = sd_v2_atime(sd); + inode_set_mtime(inode, sd_v2_mtime(sd), 0); + inode_set_atime(inode, sd_v2_atime(sd), 0); inode_set_ctime(inode, sd_v2_ctime(sd), 0); - inode->i_mtime.tv_nsec = 0; - inode->i_atime.tv_nsec = 0; inode->i_blocks = sd_v2_blocks(sd); rdev = sd_v2_rdev(sd); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) @@ -1370,9 +1366,9 @@ static void inode2sd(void *sd, struct inode *inode, loff_t size) set_sd_v2_uid(sd_v2, i_uid_read(inode)); set_sd_v2_size(sd_v2, size); set_sd_v2_gid(sd_v2, i_gid_read(inode)); - set_sd_v2_mtime(sd_v2, inode->i_mtime.tv_sec); - set_sd_v2_atime(sd_v2, inode->i_atime.tv_sec); - set_sd_v2_ctime(sd_v2, inode_get_ctime(inode).tv_sec); + set_sd_v2_mtime(sd_v2, inode_get_mtime_sec(inode)); + set_sd_v2_atime(sd_v2, inode_get_atime_sec(inode)); + set_sd_v2_ctime(sd_v2, inode_get_ctime_sec(inode)); set_sd_v2_blocks(sd_v2, to_fake_used_blocks(inode, SD_V2_SIZE)); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) set_sd_v2_rdev(sd_v2, new_encode_dev(inode->i_rdev)); @@ -1391,9 +1387,9 @@ static void inode2sd_v1(void *sd, struct inode *inode, loff_t size) set_sd_v1_gid(sd_v1, i_gid_read(inode)); set_sd_v1_nlink(sd_v1, inode->i_nlink); set_sd_v1_size(sd_v1, size); - set_sd_v1_atime(sd_v1, inode->i_atime.tv_sec); - set_sd_v1_ctime(sd_v1, inode_get_ctime(inode).tv_sec); - set_sd_v1_mtime(sd_v1, inode->i_mtime.tv_sec); + set_sd_v1_atime(sd_v1, inode_get_atime_sec(inode)); + set_sd_v1_ctime(sd_v1, inode_get_ctime_sec(inode)); + set_sd_v1_mtime(sd_v1, inode_get_mtime_sec(inode)); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) set_sd_v1_rdev(sd_v1, new_encode_dev(inode->i_rdev)); @@ -1984,7 +1980,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, /* uid and gid must already be set by the caller for quota init */ - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_size = i_size; inode->i_blocks = 0; inode->i_bytes = 0; diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 015bfe4e4524..171c912af50f 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -90,8 +90,7 @@ static int flush_commit_list(struct super_block *s, static int can_dirty(struct reiserfs_journal_cnode *cn); static int journal_join(struct reiserfs_transaction_handle *th, struct super_block *sb); -static void release_journal_dev(struct super_block *super, - struct reiserfs_journal *journal); +static void release_journal_dev(struct reiserfs_journal *journal); static void dirty_one_transaction(struct super_block *s, struct reiserfs_journal_list *jl); static void flush_async_commits(struct work_struct *work); @@ -1893,7 +1892,7 @@ static void free_journal_ram(struct super_block *sb) * j_header_bh is on the journal dev, make sure * not to release the journal dev until we brelse j_header_bh */ - release_journal_dev(sb, journal); + release_journal_dev(journal); vfree(journal); } @@ -2387,7 +2386,7 @@ static int journal_read(struct super_block *sb) cur_dblock = SB_ONDISK_JOURNAL_1st_BLOCK(sb); reiserfs_info(sb, "checking transaction log (%pg)\n", - journal->j_dev_bd); + journal->j_bdev_handle->bdev); start = ktime_get_seconds(); /* @@ -2448,7 +2447,7 @@ static int journal_read(struct super_block *sb) * device and journal device to be the same */ d_bh = - reiserfs_breada(journal->j_dev_bd, cur_dblock, + reiserfs_breada(journal->j_bdev_handle->bdev, cur_dblock, sb->s_blocksize, SB_ONDISK_JOURNAL_1st_BLOCK(sb) + SB_ONDISK_JOURNAL_SIZE(sb)); @@ -2587,17 +2586,11 @@ static void journal_list_init(struct super_block *sb) SB_JOURNAL(sb)->j_current_jl = alloc_journal_list(sb); } -static void release_journal_dev(struct super_block *super, - struct reiserfs_journal *journal) +static void release_journal_dev(struct reiserfs_journal *journal) { - if (journal->j_dev_bd != NULL) { - void *holder = NULL; - - if (journal->j_dev_bd->bd_dev != super->s_dev) - holder = journal; - - blkdev_put(journal->j_dev_bd, holder); - journal->j_dev_bd = NULL; + if (journal->j_bdev_handle) { + bdev_release(journal->j_bdev_handle); + journal->j_bdev_handle = NULL; } } @@ -2612,7 +2605,7 @@ static int journal_init_dev(struct super_block *super, result = 0; - journal->j_dev_bd = NULL; + journal->j_bdev_handle = NULL; jdev = SB_ONDISK_JOURNAL_DEVICE(super) ? new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev; @@ -2623,36 +2616,37 @@ static int journal_init_dev(struct super_block *super, if ((!jdev_name || !jdev_name[0])) { if (jdev == super->s_dev) holder = NULL; - journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, holder, - NULL); - if (IS_ERR(journal->j_dev_bd)) { - result = PTR_ERR(journal->j_dev_bd); - journal->j_dev_bd = NULL; + journal->j_bdev_handle = bdev_open_by_dev(jdev, blkdev_mode, + holder, NULL); + if (IS_ERR(journal->j_bdev_handle)) { + result = PTR_ERR(journal->j_bdev_handle); + journal->j_bdev_handle = NULL; reiserfs_warning(super, "sh-458", "cannot init journal device unknown-block(%u,%u): %i", MAJOR(jdev), MINOR(jdev), result); return result; } else if (jdev != super->s_dev) - set_blocksize(journal->j_dev_bd, super->s_blocksize); + set_blocksize(journal->j_bdev_handle->bdev, + super->s_blocksize); return 0; } - journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, holder, - NULL); - if (IS_ERR(journal->j_dev_bd)) { - result = PTR_ERR(journal->j_dev_bd); - journal->j_dev_bd = NULL; + journal->j_bdev_handle = bdev_open_by_path(jdev_name, blkdev_mode, + holder, NULL); + if (IS_ERR(journal->j_bdev_handle)) { + result = PTR_ERR(journal->j_bdev_handle); + journal->j_bdev_handle = NULL; reiserfs_warning(super, "sh-457", "journal_init_dev: Cannot open '%s': %i", jdev_name, result); return result; } - set_blocksize(journal->j_dev_bd, super->s_blocksize); + set_blocksize(journal->j_bdev_handle->bdev, super->s_blocksize); reiserfs_info(super, "journal_init_dev: journal device: %pg\n", - journal->j_dev_bd); + journal->j_bdev_handle->bdev); return 0; } @@ -2810,7 +2804,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name, "journal header magic %x (device %pg) does " "not match to magic found in super block %x", jh->jh_journal.jp_journal_magic, - journal->j_dev_bd, + journal->j_bdev_handle->bdev, sb_jp_journal_magic(rs)); brelse(bhjh); goto free_and_return; @@ -2834,7 +2828,7 @@ int journal_init(struct super_block *sb, const char *j_dev_name, reiserfs_info(sb, "journal params: device %pg, size %u, " "journal first block %u, max trans len %u, max batch %u, " "max commit age %u, max trans age %u\n", - journal->j_dev_bd, + journal->j_bdev_handle->bdev, SB_ONDISK_JOURNAL_SIZE(sb), SB_ONDISK_JOURNAL_1st_BLOCK(sb), journal->j_trans_max, diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 9c5704be2435..994d6e6995ab 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -572,7 +572,7 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th, } dir->i_size += paste_size; - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (!S_ISDIR(inode->i_mode) && visible) /* reiserfs_mkdir or reiserfs_rename will do that by itself */ reiserfs_update_sd(th, dir); @@ -966,8 +966,8 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry) inode->i_nlink); clear_nlink(inode); - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); reiserfs_update_sd(&th, inode); DEC_DIR_INODE_NLINK(dir) @@ -1075,7 +1075,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) reiserfs_update_sd(&th, inode); dir->i_size -= (de.de_entrylen + DEH_SIZE); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); reiserfs_update_sd(&th, dir); if (!savelink) diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 3dba8acf4e83..83cb9402e0f9 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -354,7 +354,7 @@ static int show_journal(struct seq_file *m, void *unused) "prepare: \t%12lu\n" "prepare_retry: \t%12lu\n", DJP(jp_journal_1st_block), - SB_JOURNAL(sb)->j_dev_bd, + SB_JOURNAL(sb)->j_bdev_handle->bdev, DJP(jp_journal_dev), DJP(jp_journal_size), DJP(jp_journal_trans_max), diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index b81749492ef9..725667880e62 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -299,7 +299,7 @@ struct reiserfs_journal { /* oldest journal block. start here for traverse */ struct reiserfs_journal_cnode *j_first; - struct block_device *j_dev_bd; + struct bdev_handle *j_bdev_handle; /* first block on s_dev of reserved area journal */ int j_1st_reserved_block; @@ -1165,7 +1165,7 @@ static inline int bmap_would_wrap(unsigned bmap_nr) return bmap_nr > ((1LL << 16) - 1); } -extern const struct xattr_handler *reiserfs_xattr_handlers[]; +extern const struct xattr_handler * const reiserfs_xattr_handlers[]; /* * this says about version of key of all items (but stat data) the @@ -2699,7 +2699,7 @@ struct reiserfs_iget_args { #define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12) #define journal_trans_half(blocksize) \ - ((blocksize - sizeof (struct reiserfs_journal_desc) + sizeof (__u32) - 12) / sizeof (__u32)) + ((blocksize - sizeof(struct reiserfs_journal_desc) - 12) / sizeof(__u32)) /* journal.c see journal.c for all the comments here */ @@ -2711,7 +2711,7 @@ struct reiserfs_journal_desc { __le32 j_len; __le32 j_mount_id; /* mount id of this trans */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_desc_trans_id(d) le32_to_cpu((d)->j_trans_id) @@ -2726,7 +2726,7 @@ struct reiserfs_journal_desc { struct reiserfs_journal_commit { __le32 j_trans_id; /* must match j_trans_id from the desc block */ __le32 j_len; /* ditto */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_commit_trans_id(c) le32_to_cpu((c)->j_trans_id) @@ -2809,9 +2809,12 @@ struct reiserfs_journal_header { #define journal_hash(t,sb,block) ((t)[_jhashfn((sb),(block)) & JBH_HASH_MASK]) /* We need these to make journal.c code more readable */ -#define journal_find_get_block(s, block) __find_get_block(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize) -#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize) -#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize) +#define journal_find_get_block(s, block) __find_get_block(\ + SB_JOURNAL(s)->j_bdev_handle->bdev, block, s->s_blocksize) +#define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_bdev_handle->bdev,\ + block, s->s_blocksize) +#define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_bdev_handle->bdev,\ + block, s->s_blocksize) enum reiserfs_bh_state_bits { BH_JDirty = BH_PrivateStart, /* buffer is in current transaction */ diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 3676e02a0232..2138ee7d271d 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -2003,7 +2003,8 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th, pathrelse(&s_search_path); if (update_timestamps) { - inode->i_mtime = current_time(inode); + inode_set_mtime_to_ts(inode, + current_time(inode)); inode_set_ctime_current(inode); } reiserfs_update_sd(th, inode); @@ -2028,7 +2029,7 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th, update_and_out: if (update_timestamps) { /* this is truncate, not file closing */ - inode->i_mtime = current_time(inode); + inode_set_mtime_to_ts(inode, current_time(inode)); inode_set_ctime_current(inode); } reiserfs_update_sd(th, inode); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 7eaf36b3de12..67b5510beded 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2587,7 +2587,7 @@ out: return err; if (inode->i_size < off + len - towrite) i_size_write(inode, off + len - towrite); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); return len - towrite; } diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 6000964c2b80..998035a6388e 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -780,7 +780,7 @@ static inline bool reiserfs_posix_acl_list(const char *name, } /* This is the implementation for the xattr plugin infrastructure */ -static inline bool reiserfs_xattr_list(const struct xattr_handler **handlers, +static inline bool reiserfs_xattr_list(const struct xattr_handler * const *handlers, const char *name, struct dentry *dentry) { if (handlers) { @@ -911,7 +911,7 @@ static int create_privroot(struct dentry *dentry) { return 0; } #endif /* Actual operations that are exported to VFS-land */ -const struct xattr_handler *reiserfs_xattr_handlers[] = { +const struct xattr_handler * const reiserfs_xattr_handlers[] = { #ifdef CONFIG_REISERFS_FS_XATTR &reiserfs_xattr_user_handler, &reiserfs_xattr_trusted_handler, diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 5c35f6c76037..545ad44f96b8 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -322,7 +322,8 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) set_nlink(i, 1); /* Hard to decide.. */ i->i_size = be32_to_cpu(ri.size); - i->i_mtime = i->i_atime = inode_set_ctime(i, 0, 0); + inode_set_mtime_to_ts(i, + inode_set_atime_to_ts(i, inode_set_ctime(i, 0, 0))); /* set up mode and ops */ mode = romfs_modemap[nextfh & ROMFH_TYPE]; @@ -593,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb) #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); - blkdev_put(sb->s_bdev, sb); + bdev_release(sb->s_bdev_handle); } #endif } diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index e2be8aedb26e..fe1bf5b6e0cb 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -15,6 +15,7 @@ static struct cached_fid *init_cached_dir(const char *path); static void free_cached_dir(struct cached_fid *cfid); static void smb2_close_cached_fid(struct kref *ref); +static void cfids_laundromat_worker(struct work_struct *work); static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, const char *path, @@ -169,15 +170,18 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, return -ENOENT; } /* - * At this point we either have a lease already and we can just - * return it. If not we are guaranteed to be the only thread accessing - * this cfid. + * Return cached fid if it has a lease. Otherwise, it is either a new + * entry or laundromat worker removed it from @cfids->entries. Caller + * will put last reference if the latter. */ + spin_lock(&cfids->cfid_list_lock); if (cfid->has_lease) { + spin_unlock(&cfids->cfid_list_lock); *ret_cfid = cfid; kfree(utf16_path); return 0; } + spin_unlock(&cfids->cfid_list_lock); /* * Skip any prefix paths in @path as lookup_positive_unlocked() ends up @@ -294,9 +298,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, goto oshr_free; } } + spin_lock(&cfids->cfid_list_lock); cfid->dentry = dentry; cfid->time = jiffies; cfid->has_lease = true; + spin_unlock(&cfids->cfid_list_lock); oshr_free: kfree(utf16_path); @@ -305,24 +311,28 @@ oshr_free: free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); spin_lock(&cfids->cfid_list_lock); - if (rc && !cfid->has_lease) { - if (cfid->on_list) { - list_del(&cfid->entry); - cfid->on_list = false; - cfids->num_entries--; + if (!cfid->has_lease) { + if (rc) { + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + } + rc = -ENOENT; + } else { + /* + * We are guaranteed to have two references at this + * point. One for the caller and one for a potential + * lease. Release the Lease-ref so that the directory + * will be closed when the caller closes the cached + * handle. + */ + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); + goto out; } - rc = -ENOENT; } spin_unlock(&cfids->cfid_list_lock); - if (!rc && !cfid->has_lease) { - /* - * We are guaranteed to have two references at this point. - * One for the caller and one for a potential lease. - * Release the Lease-ref so that the directory will be closed - * when the caller closes the cached handle. - */ - kref_put(&cfid->refcount, smb2_close_cached_fid); - } if (rc) { if (cfid->is_open) SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, @@ -330,7 +340,7 @@ oshr_free: free_cached_dir(cfid); cfid = NULL; } - +out: if (rc == 0) { *ret_cfid = cfid; atomic_inc(&tcon->num_remote_opens); @@ -572,53 +582,51 @@ static void free_cached_dir(struct cached_fid *cfid) kfree(cfid); } -static int -cifs_cfids_laundromat_thread(void *p) +static void cfids_laundromat_worker(struct work_struct *work) { - struct cached_fids *cfids = p; + struct cached_fids *cfids; struct cached_fid *cfid, *q; - struct list_head entry; + LIST_HEAD(entry); - while (!kthread_should_stop()) { - ssleep(1); - INIT_LIST_HEAD(&entry); - if (kthread_should_stop()) - return 0; - spin_lock(&cfids->cfid_list_lock); - list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { - if (time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) { - list_del(&cfid->entry); - list_add(&cfid->entry, &entry); - cfids->num_entries--; - } - } - spin_unlock(&cfids->cfid_list_lock); + cfids = container_of(work, struct cached_fids, laundromat_work.work); - list_for_each_entry_safe(cfid, q, &entry, entry) { + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + if (cfid->time && + time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) { cfid->on_list = false; - list_del(&cfid->entry); + list_move(&cfid->entry, &entry); + cfids->num_entries--; + /* To prevent race with smb2_cached_lease_break() */ + kref_get(&cfid->refcount); + } + } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + list_del(&cfid->entry); + /* + * Cancel and wait for the work to finish in case we are racing + * with it. + */ + cancel_work_sync(&cfid->lease_break); + if (cfid->has_lease) { /* - * Cancel, and wait for the work to finish in - * case we are racing with it. + * Our lease has not yet been cancelled from the server + * so we need to drop the reference. */ - cancel_work_sync(&cfid->lease_break); - if (cfid->has_lease) { - /* - * We lease has not yet been cancelled from - * the server so we need to drop the reference. - */ - spin_lock(&cfids->cfid_list_lock); - cfid->has_lease = false; - spin_unlock(&cfids->cfid_list_lock); - kref_put(&cfid->refcount, smb2_close_cached_fid); - } + spin_lock(&cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); } + /* Drop the extra reference opened above */ + kref_put(&cfid->refcount, smb2_close_cached_fid); } - - return 0; + queue_delayed_work(cifsiod_wq, &cfids->laundromat_work, + dir_cache_timeout * HZ); } - struct cached_fids *init_cached_dirs(void) { struct cached_fids *cfids; @@ -629,19 +637,10 @@ struct cached_fids *init_cached_dirs(void) spin_lock_init(&cfids->cfid_list_lock); INIT_LIST_HEAD(&cfids->entries); - /* - * since we're in a cifs function already, we know that - * this will succeed. No need for try_module_get(). - */ - __module_get(THIS_MODULE); - cfids->laundromat = kthread_run(cifs_cfids_laundromat_thread, - cfids, "cifsd-cfid-laundromat"); - if (IS_ERR(cfids->laundromat)) { - cifs_dbg(VFS, "Failed to start cfids laundromat thread.\n"); - kfree(cfids); - module_put(THIS_MODULE); - return NULL; - } + INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker); + queue_delayed_work(cifsiod_wq, &cfids->laundromat_work, + dir_cache_timeout * HZ); + return cfids; } @@ -657,11 +656,7 @@ void free_cached_dirs(struct cached_fids *cfids) if (cfids == NULL) return; - if (cfids->laundromat) { - kthread_stop(cfids->laundromat); - cfids->laundromat = NULL; - module_put(THIS_MODULE); - } + cancel_delayed_work_sync(&cfids->laundromat_work); spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h index a82ff2cea789..81ba0fd5cc16 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -57,7 +57,7 @@ struct cached_fids { spinlock_t cfid_list_lock; int num_entries; struct list_head entries; - struct task_struct *laundromat; + struct delayed_work laundromat_work; }; extern struct cached_fids *init_cached_dirs(void); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 41daebd220ff..8ca3d7606bb4 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -127,7 +127,7 @@ extern int cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, const char *symname); #ifdef CONFIG_CIFS_XATTR -extern const struct xattr_handler *cifs_xattr_handlers[]; +extern const struct xattr_handler * const cifs_xattr_handlers[]; extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); #else # define cifs_xattr_handlers NULL diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 3902e90dca6b..7b923e36501b 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2474,8 +2474,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) static struct cifs_tcon * cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) { - int rc, xid; struct cifs_tcon *tcon; + bool nohandlecache; + int rc, xid; tcon = cifs_find_tcon(ses, ctx); if (tcon) { @@ -2493,14 +2494,17 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) goto out_fail; } - if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) - tcon = tcon_info_alloc(true); + if (ses->server->dialect >= SMB20_PROT_ID && + (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)) + nohandlecache = ctx->nohandlecache; else - tcon = tcon_info_alloc(false); + nohandlecache = true; + tcon = tcon_info_alloc(!nohandlecache); if (tcon == NULL) { rc = -ENOMEM; goto out_fail; } + tcon->nohandlecache = nohandlecache; if (ctx->snapshot_time) { if (ses->server->vals->protocol_id == 0) { @@ -2662,10 +2666,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) tcon->nocase = ctx->nocase; tcon->broken_sparse_sup = ctx->no_sparse; tcon->max_cached_dirs = ctx->max_cached_dirs; - if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) - tcon->nohandlecache = ctx->nohandlecache; - else - tcon->nohandlecache = true; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); @@ -2895,9 +2895,9 @@ bind_socket(struct TCP_Server_Info *server) if (server->srcaddr.ss_family != AF_UNSPEC) { /* Bind to the specified local IP address */ struct socket *socket = server->ssocket; - rc = socket->ops->bind(socket, - (struct sockaddr *) &server->srcaddr, - sizeof(server->srcaddr)); + rc = kernel_bind(socket, + (struct sockaddr *) &server->srcaddr, + sizeof(server->srcaddr)); if (rc < 0) { struct sockaddr_in *saddr4; struct sockaddr_in6 *saddr6; @@ -3046,8 +3046,8 @@ generic_ip_connect(struct TCP_Server_Info *server) socket->sk->sk_sndbuf, socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo); - rc = socket->ops->connect(socket, saddr, slen, - server->noblockcnt ? O_NONBLOCK : 0); + rc = kernel_connect(socket, saddr, slen, + server->noblockcnt ? O_NONBLOCK : 0); /* * When mounting SMB root file systems, we do not want to block in * connect. Otherwise bail out and then let cifs_reconnect() perform diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 2108b3b40ce9..cf17e3dd703e 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1085,7 +1085,8 @@ int cifs_close(struct inode *inode, struct file *file) !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && dclose) { if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); } spin_lock(&cinode->deferred_lock); cifs_add_deferred_close(cfile, dclose); @@ -2596,7 +2597,7 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) write_data, to - from, &offset); cifsFileInfo_put(open_file); /* Does mm or vfs already set times? */ - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); if ((bytes_written > 0) && (offset)) rc = 0; else if (bytes_written < 0) @@ -4647,11 +4648,13 @@ static void cifs_readahead(struct readahead_control *ractl) static int cifs_readpage_worker(struct file *file, struct page *page, loff_t *poffset) { + struct inode *inode = file_inode(file); + struct timespec64 atime, mtime; char *read_data; int rc; /* Is the page cached? */ - rc = cifs_readpage_from_fscache(file_inode(file), page); + rc = cifs_readpage_from_fscache(inode, page); if (rc == 0) goto read_complete; @@ -4666,11 +4669,10 @@ static int cifs_readpage_worker(struct file *file, struct page *page, cifs_dbg(FYI, "Bytes read %d\n", rc); /* we do not want atime to be less than mtime, it broke some apps */ - file_inode(file)->i_atime = current_time(file_inode(file)); - if (timespec64_compare(&(file_inode(file)->i_atime), &(file_inode(file)->i_mtime))) - file_inode(file)->i_atime = file_inode(file)->i_mtime; - else - file_inode(file)->i_atime = current_time(file_inode(file)); + atime = inode_set_atime_to_ts(inode, current_time(inode)); + mtime = inode_get_mtime(inode); + if (timespec64_compare(&atime, &mtime)) + inode_set_atime_to_ts(inode, inode_get_mtime(inode)); if (PAGE_SIZE > rc) memset(read_data + rc, 0, PAGE_SIZE - rc); diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index e45ce31bbda7..a3493da12ad1 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1541,6 +1541,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_parse_mount_err: kfree_sensitive(ctx->password); + ctx->password = NULL; return -EINVAL; } diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index 84f3b09367d2..a3d73720914f 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -49,12 +49,12 @@ static inline void cifs_fscache_fill_coherency(struct inode *inode, struct cifs_fscache_inode_coherency_data *cd) { - struct cifsInodeInfo *cifsi = CIFS_I(inode); struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 mtime = inode_get_mtime(inode); memset(cd, 0, sizeof(*cd)); - cd->last_write_time_sec = cpu_to_le64(cifsi->netfs.inode.i_mtime.tv_sec); - cd->last_write_time_nsec = cpu_to_le32(cifsi->netfs.inode.i_mtime.tv_nsec); + cd->last_write_time_sec = cpu_to_le64(mtime.tv_sec); + cd->last_write_time_nsec = cpu_to_le32(mtime.tv_nsec); cd->last_change_time_sec = cpu_to_le64(ctime.tv_sec); cd->last_change_time_nsec = cpu_to_le32(ctime.tv_nsec); } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index d7c302442c1e..3abfe77bfa46 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -82,6 +82,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) { struct cifs_fscache_inode_coherency_data cd; struct cifsInodeInfo *cifs_i = CIFS_I(inode); + struct timespec64 mtime; cifs_dbg(FYI, "%s: revalidating inode %llu\n", __func__, cifs_i->uniqueid); @@ -101,7 +102,8 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) /* revalidate if mtime or size have changed */ fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); - if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) && + mtime = inode_get_mtime(inode); + if (timespec64_equal(&mtime, &fattr->cf_mtime) && cifs_i->server_eof == fattr->cf_eof) { cifs_dbg(FYI, "%s: inode %llu is unchanged\n", __func__, cifs_i->uniqueid); @@ -164,10 +166,10 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) fattr->cf_ctime = timestamp_truncate(fattr->cf_ctime, inode); /* we do not want atime to be less than mtime, it broke some apps */ if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime) < 0) - inode->i_atime = fattr->cf_mtime; + inode_set_atime_to_ts(inode, fattr->cf_mtime); else - inode->i_atime = fattr->cf_atime; - inode->i_mtime = fattr->cf_mtime; + inode_set_atime_to_ts(inode, fattr->cf_atime); + inode_set_mtime_to_ts(inode, fattr->cf_mtime); inode_set_ctime_to_ts(inode, fattr->cf_ctime); inode->i_rdev = fattr->cf_rdev; cifs_nlink_fattr_to_inode(inode, fattr); @@ -1816,7 +1818,7 @@ out_reval: when needed */ inode_set_ctime_current(inode); } - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); cifs_inode = CIFS_I(dir); CIFS_I(dir)->time = 0; /* force revalidate of dir as well */ unlink_out: @@ -2131,7 +2133,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) cifsInode->time = 0; inode_set_ctime_current(d_inode(direntry)); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); rmdir_exit: free_dentry_path(page); @@ -2337,9 +2339,6 @@ unlink_target: /* force revalidate to go get info when needed */ CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; - source_dir->i_mtime = target_dir->i_mtime = inode_set_ctime_to_ts(source_dir, - inode_set_ctime_current(target_dir)); - cifs_rename_exit: kfree(info_buf_source); free_dentry_path(page2); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 9aeecee6b91b..f4849a8ad40b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1403,12 +1403,14 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* Creation time should not need to be updated on close */ if (file_inf.LastWriteTime) - inode->i_mtime = cifs_NTtimeToUnix(file_inf.LastWriteTime); + inode_set_mtime_to_ts(inode, + cifs_NTtimeToUnix(file_inf.LastWriteTime)); if (file_inf.ChangeTime) inode_set_ctime_to_ts(inode, cifs_NTtimeToUnix(file_inf.ChangeTime)); if (file_inf.LastAccessTime) - inode->i_atime = cifs_NTtimeToUnix(file_inf.LastAccessTime); + inode_set_atime_to_ts(inode, + cifs_NTtimeToUnix(file_inf.LastAccessTime)); /* * i_blocks is not related to (i_size / i_blksize), diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c index 4ad5531686d8..ac199160bce6 100644 --- a/fs/smb/client/xattr.c +++ b/fs/smb/client/xattr.c @@ -478,7 +478,7 @@ static const struct xattr_handler smb3_ntsd_full_xattr_handler = { .set = cifs_xattr_set, }; -const struct xattr_handler *cifs_xattr_handlers[] = { +const struct xattr_handler * const cifs_xattr_handlers[] = { &cifs_user_xattr_handler, &cifs_os2_xattr_handler, &cifs_cifs_acl_xattr_handler, diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 0d990c2f33cd..4b38c3a285f6 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -84,6 +84,8 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) spin_lock_init(&conn->llist_lock); INIT_LIST_HEAD(&conn->lock_list); + init_rwsem(&conn->session_lock); + down_write(&conn_list_lock); list_add(&conn->conns_list, &conn_list); up_write(&conn_list_lock); @@ -197,6 +199,9 @@ int ksmbd_conn_write(struct ksmbd_work *work) if (work->send_no_response) return 0; + if (!work->iov_idx) + return -EINVAL; + ksmbd_conn_lock(conn); sent = conn->transport->ops->writev(conn->transport, work->iov, work->iov_cnt, diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index ab2583f030ce..3c005246a32e 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -50,6 +50,7 @@ struct ksmbd_conn { struct nls_table *local_nls; struct unicode_map *um; struct list_head conns_list; + struct rw_semaphore session_lock; /* smb session 1 per user */ struct xarray sessions; unsigned long last_active; diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index 408cddf2f094..d2c81a8a11dd 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -73,7 +73,10 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, tree_conn->user = sess->user; tree_conn->share_conf = sc; + tree_conn->t_state = TREE_NEW; status.tree_conn = tree_conn; + atomic_set(&tree_conn->refcount, 1); + init_waitqueue_head(&tree_conn->refcount_q); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, GFP_KERNEL)); @@ -93,14 +96,33 @@ out_error: return status; } +void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon) +{ + /* + * Checking waitqueue to releasing tree connect on + * tree disconnect. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&tcon->refcount) && + waitqueue_active(&tcon->refcount_q)) + wake_up(&tcon->refcount_q); +} + int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn) { int ret; + write_lock(&sess->tree_conns_lock); + xa_erase(&sess->tree_conns, tree_conn->id); + write_unlock(&sess->tree_conns_lock); + + if (!atomic_dec_and_test(&tree_conn->refcount)) + wait_event(tree_conn->refcount_q, + atomic_read(&tree_conn->refcount) == 0); + ret = ksmbd_ipc_tree_disconnect_request(sess->id, tree_conn->id); ksmbd_release_tree_conn_id(sess, tree_conn->id); - xa_erase(&sess->tree_conns, tree_conn->id); ksmbd_share_config_put(tree_conn->share_conf); kfree(tree_conn); return ret; @@ -111,11 +133,15 @@ struct ksmbd_tree_connect *ksmbd_tree_conn_lookup(struct ksmbd_session *sess, { struct ksmbd_tree_connect *tcon; + read_lock(&sess->tree_conns_lock); tcon = xa_load(&sess->tree_conns, id); if (tcon) { - if (test_bit(TREE_CONN_EXPIRE, &tcon->status)) + if (tcon->t_state != TREE_CONNECTED) + tcon = NULL; + else if (!atomic_inc_not_zero(&tcon->refcount)) tcon = NULL; } + read_unlock(&sess->tree_conns_lock); return tcon; } @@ -129,8 +155,18 @@ int ksmbd_tree_conn_session_logoff(struct ksmbd_session *sess) if (!sess) return -EINVAL; - xa_for_each(&sess->tree_conns, id, tc) + xa_for_each(&sess->tree_conns, id, tc) { + write_lock(&sess->tree_conns_lock); + if (tc->t_state == TREE_DISCONNECTED) { + write_unlock(&sess->tree_conns_lock); + ret = -ENOENT; + continue; + } + tc->t_state = TREE_DISCONNECTED; + write_unlock(&sess->tree_conns_lock); + ret |= ksmbd_tree_conn_disconnect(sess, tc); + } xa_destroy(&sess->tree_conns); return ret; } diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 562d647ad9fa..6377a70b811c 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -14,7 +14,11 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; -#define TREE_CONN_EXPIRE 1 +enum { + TREE_NEW = 0, + TREE_CONNECTED, + TREE_DISCONNECTED +}; struct ksmbd_tree_connect { int id; @@ -27,7 +31,9 @@ struct ksmbd_tree_connect { int maximal_access; bool posix_extensions; - unsigned long status; + atomic_t refcount; + wait_queue_head_t refcount_q; + unsigned int t_state; }; struct ksmbd_tree_conn_status { @@ -46,6 +52,7 @@ struct ksmbd_session; struct ksmbd_tree_conn_status ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, const char *share_name); +void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 8a5dcab05614..15f68ee05089 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -174,7 +174,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) unsigned long id; struct ksmbd_session *sess; - down_write(&sessions_table_lock); + down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { if (sess->state != SMB2_SESSION_VALID || time_after(jiffies, @@ -185,7 +185,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) continue; } } - up_write(&sessions_table_lock); + up_write(&conn->session_lock); } int ksmbd_session_register(struct ksmbd_conn *conn, @@ -227,7 +227,9 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) } } } + up_write(&sessions_table_lock); + down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { unsigned long chann_id; struct channel *chann; @@ -244,7 +246,7 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) ksmbd_session_destroy(sess); } } - up_write(&sessions_table_lock); + up_write(&conn->session_lock); } struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, @@ -252,9 +254,11 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, { struct ksmbd_session *sess; + down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); if (sess) sess->last_active = jiffies; + up_read(&conn->session_lock); return sess; } @@ -351,6 +355,7 @@ static struct ksmbd_session *__session_create(int protocol) xa_init(&sess->ksmbd_chann_list); xa_init(&sess->rpc_handle_list); sess->sequence_number = 1; + rwlock_init(&sess->tree_conns_lock); ret = __init_smb2_session(sess); if (ret) diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f99d475b28db..63cb08fffde8 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -60,6 +60,7 @@ struct ksmbd_session { struct ksmbd_file_table file_table; unsigned long last_active; + rwlock_t tree_conns_lock; }; static inline int test_session_flag(struct ksmbd_session *sess, int bit) diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 5ab2f52f9b35..3079e607c5fe 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -115,8 +115,10 @@ static int __process_request(struct ksmbd_work *work, struct ksmbd_conn *conn, if (check_conn_state(work)) return SERVER_HANDLER_CONTINUE; - if (ksmbd_verify_smb_message(work)) + if (ksmbd_verify_smb_message(work)) { + conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); return SERVER_HANDLER_ABORT; + } command = conn->ops->get_cmd_val(work); *cmd = command; @@ -239,6 +241,8 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, } while (is_chained == true); send: + if (work->tcon) + ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index e881df1d10cb..23bd3d1209df 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -440,10 +440,8 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) validate_credit: if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) && - smb2_validate_credit_charge(work->conn, hdr)) { - work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER); + smb2_validate_credit_charge(work->conn, hdr)) return 1; - } return 0; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 544022dd6d20..658209839729 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -231,11 +231,12 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) { struct smb2_hdr *rsp_hdr; - if (work->next_smb2_rcv_hdr_off) - rsp_hdr = ksmbd_resp_buf_next(work); - else - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Status = err; + + work->iov_idx = 0; + work->iov_cnt = 0; + work->next_smb2_rcv_hdr_off = 0; smb2_set_err_rsp(work); } @@ -1993,6 +1994,9 @@ int smb2_tree_connect(struct ksmbd_work *work) if (conn->posix_ext_supported) status.tree_conn->posix_extensions = true; + write_lock(&sess->tree_conns_lock); + status.tree_conn->t_state = TREE_CONNECTED; + write_unlock(&sess->tree_conns_lock); rsp->StructureSize = cpu_to_le16(16); out_err1: rsp->Capabilities = 0; @@ -2122,27 +2126,50 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_debug(SMB, "request\n"); + if (!tcon) { + ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); + + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + err = -ENOENT; + goto err_out; + } + + ksmbd_close_tree_conn_fds(work); + + write_lock(&sess->tree_conns_lock); + if (tcon->t_state == TREE_DISCONNECTED) { + write_unlock(&sess->tree_conns_lock); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + err = -ENOENT; + goto err_out; + } + + WARN_ON_ONCE(atomic_dec_and_test(&tcon->refcount)); + tcon->t_state = TREE_DISCONNECTED; + write_unlock(&sess->tree_conns_lock); + + err = ksmbd_tree_conn_disconnect(sess, tcon); + if (err) { + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + goto err_out; + } + + work->tcon = NULL; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_disconnect_rsp)); if (err) { rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; - smb2_set_err_rsp(work); - return err; + goto err_out; } - if (!tcon || test_and_set_bit(TREE_CONN_EXPIRE, &tcon->status)) { - ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); + return 0; - rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; - smb2_set_err_rsp(work); - return -ENOENT; - } +err_out: + smb2_set_err_rsp(work); + return err; - ksmbd_close_tree_conn_fds(work); - ksmbd_tree_conn_disconnect(sess, tcon); - work->tcon = NULL; - return 0; } /** @@ -2164,17 +2191,17 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_debug(SMB, "request\n"); - sess_id = le64_to_cpu(req->hdr.SessionId); - - rsp->StructureSize = cpu_to_le16(4); - err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); - if (err) { - rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + ksmbd_conn_lock(conn); + if (!ksmbd_conn_good(conn)) { + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return err; + return -ENOENT; } - + sess_id = le64_to_cpu(req->hdr.SessionId); ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_RECONNECT); + ksmbd_conn_unlock(conn); + ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn, sess_id); @@ -2196,6 +2223,14 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_free_user(sess->user); sess->user = NULL; ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE); + + rsp->StructureSize = cpu_to_le16(4); + err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); + if (err) { + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + smb2_set_err_rsp(work); + return err; + } return 0; } @@ -3370,8 +3405,10 @@ err_out: } ksmbd_revert_fsids(work); err_out1: - if (!rc) + if (!rc) { + ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED); rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); + } if (rc) { if (rc == -EINVAL) rsp->hdr.Status = STATUS_INVALID_PARAMETER; @@ -4797,9 +4834,9 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info = (struct smb311_posix_qinfo *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode->i_atime); + time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); file_info->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode->i_mtime); + time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); file_info->LastWriteTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); file_info->ChangeTime = cpu_to_le64(time); @@ -5406,9 +5443,9 @@ int smb2_close(struct ksmbd_work *work) rsp->EndOfFile = cpu_to_le64(inode->i_size); rsp->Attributes = fp->f_ci->m_fattr; rsp->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode->i_atime); + time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); rsp->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode->i_mtime); + time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); rsp->LastWriteTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); rsp->ChangeTime = cpu_to_le64(time); @@ -6115,12 +6152,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; - kvfree(rpc_resp); err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); if (err) goto out; + kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer)); @@ -7028,10 +7065,6 @@ skip: ksmbd_debug(SMB, "would have to wait for getting lock\n"); - spin_lock(&work->conn->llist_lock); - list_add_tail(&smb_lock->clist, - &work->conn->lock_list); - spin_unlock(&work->conn->llist_lock); list_add(&smb_lock->llist, &rollback_list); argv = kmalloc(sizeof(void *), GFP_KERNEL); @@ -7062,9 +7095,6 @@ skip: if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); locks_free_lock(flock); if (work->state == KSMBD_WORK_CANCELLED) { @@ -7084,19 +7114,16 @@ skip: } list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); release_async_work(work); goto retry; } else if (!rc) { + list_add(&smb_lock->llist, &rollback_list); spin_lock(&work->conn->llist_lock); list_add_tail(&smb_lock->clist, &work->conn->lock_list); list_add_tail(&smb_lock->flist, &fp->lock_list); spin_unlock(&work->conn->llist_lock); - list_add(&smb_lock->llist, &rollback_list); ksmbd_debug(SMB, "successful in taking lock\n"); } else { goto out; @@ -8036,10 +8063,10 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) goto err_out; } - opinfo_put(opinfo); - ksmbd_fd_put(work, fp); opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); + opinfo_put(opinfo); + ksmbd_fd_put(work, fp); rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index f41f8d6108ce..c91eac6514dd 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -106,7 +106,7 @@ int ksmbd_query_inode_status(struct inode *inode) ci = __ksmbd_inode_lookup(inode); if (ci) { ret = KSMBD_INODE_STATUS_OK; - if (ci->m_flags & S_DEL_PENDING) + if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) ret = KSMBD_INODE_STATUS_PENDING_DELETE; atomic_dec(&ci->m_count); } @@ -116,7 +116,7 @@ int ksmbd_query_inode_status(struct inode *inode) bool ksmbd_inode_pending_delete(struct ksmbd_file *fp) { - return (fp->f_ci->m_flags & S_DEL_PENDING); + return (fp->f_ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)); } void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp) @@ -333,6 +333,9 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) static struct ksmbd_file *ksmbd_fp_get(struct ksmbd_file *fp) { + if (fp->f_state != FP_INITED) + return NULL; + if (!atomic_inc_not_zero(&fp->refcount)) return NULL; return fp; @@ -382,15 +385,20 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) return 0; ft = &work->sess->file_table; - read_lock(&ft->lock); + write_lock(&ft->lock); fp = idr_find(ft->idr, id); if (fp) { set_close_state_blocked_works(fp); - if (!atomic_dec_and_test(&fp->refcount)) + if (fp->f_state != FP_INITED) fp = NULL; + else { + fp->f_state = FP_CLOSED; + if (!atomic_dec_and_test(&fp->refcount)) + fp = NULL; + } } - read_unlock(&ft->lock); + write_unlock(&ft->lock); if (!fp) return -EINVAL; @@ -570,6 +578,7 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) fp->tcon = work->tcon; fp->volatile_id = KSMBD_NO_FID; fp->persistent_id = KSMBD_NO_FID; + fp->f_state = FP_NEW; fp->f_ci = ksmbd_inode_get(fp); if (!fp->f_ci) { @@ -591,6 +600,17 @@ err_out: return ERR_PTR(ret); } +void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state) +{ + if (!fp) + return; + + write_lock(&ft->lock); + fp->f_state = state; + write_unlock(&ft->lock); +} + static int __close_file_table_ids(struct ksmbd_file_table *ft, struct ksmbd_tree_connect *tcon, diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index fcb13413fa8d..03d0bf941216 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -60,6 +60,12 @@ struct ksmbd_inode { __le32 m_fattr; }; +enum { + FP_NEW = 0, + FP_INITED, + FP_CLOSED +}; + struct ksmbd_file { struct file *filp; u64 persistent_id; @@ -98,6 +104,7 @@ struct ksmbd_file { /* if ls is happening on directory, below is valid*/ struct ksmbd_readdir_data readdir_data; int dot_dotdot[2]; + unsigned int f_state; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -142,6 +149,8 @@ int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); void ksmbd_set_fd_limit(unsigned long limit); +void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state); /* * INODE hash diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index c6e626b00546..aa3411354e66 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -59,9 +59,9 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); - inode->i_mtime.tv_sec = le32_to_cpu(sqsh_ino->mtime); - inode->i_atime.tv_sec = inode->i_mtime.tv_sec; - inode_set_ctime(inode, inode->i_mtime.tv_sec, 0); + inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0); + inode_set_atime(inode, inode_get_mtime_sec(inode), 0); + inode_set_ctime(inode, inode_get_mtime_sec(inode), 0); inode->i_mode = le16_to_cpu(sqsh_ino->mode); inode->i_size = 0; diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index a6164fdf9435..5a756e6790b5 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -111,4 +111,4 @@ extern const struct address_space_operations squashfs_symlink_aops; extern const struct inode_operations squashfs_symlink_inode_ops; /* xattr.c */ -extern const struct xattr_handler *squashfs_xattr_handlers[]; +extern const struct xattr_handler * const squashfs_xattr_handlers[]; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index e1e3f3dd5a06..ce6608cabd49 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -262,7 +262,7 @@ static const struct xattr_handler *squashfs_xattr_handler(int type) } } -const struct xattr_handler *squashfs_xattr_handlers[] = { +const struct xattr_handler * const squashfs_xattr_handlers[] = { &squashfs_xattr_user_handler, &squashfs_xattr_trusted_handler, &squashfs_xattr_security_handler, diff --git a/fs/stack.c b/fs/stack.c index b5e01bdb5f5f..f18920119944 100644 --- a/fs/stack.c +++ b/fs/stack.c @@ -66,8 +66,8 @@ void fsstack_copy_attr_all(struct inode *dest, const struct inode *src) dest->i_uid = src->i_uid; dest->i_gid = src->i_gid; dest->i_rdev = src->i_rdev; - dest->i_atime = src->i_atime; - dest->i_mtime = src->i_mtime; + inode_set_atime_to_ts(dest, inode_get_atime(src)); + inode_set_mtime_to_ts(dest, inode_get_mtime(src)); inode_set_ctime_to_ts(dest, inode_get_ctime(src)); dest->i_blkbits = src->i_blkbits; dest->i_flags = src->i_flags; diff --git a/fs/stat.c b/fs/stat.c index d43a5cc1bfa4..24bb0209e459 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -57,8 +57,8 @@ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, stat->gid = vfsgid_into_kgid(vfsgid); stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); - stat->atime = inode->i_atime; - stat->mtime = inode->i_mtime; + stat->atime = inode_get_atime(inode); + stat->mtime = inode_get_mtime(inode); stat->ctime = inode_get_ctime(inode); stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; diff --git a/fs/super.c b/fs/super.c index 2d762ce67f6e..c7b452e12e4c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1419,32 +1419,48 @@ EXPORT_SYMBOL(sget_dev); #ifdef CONFIG_BLOCK /* - * Lock a super block that the callers holds a reference to. + * Lock the superblock that is holder of the bdev. Returns the superblock + * pointer if we successfully locked the superblock and it is alive. Otherwise + * we return NULL and just unlock bdev->bd_holder_lock. * - * The caller needs to ensure that the super_block isn't being freed while - * calling this function, e.g. by holding a lock over the call to this function - * and the place that clears the pointer to the superblock used by this function - * before freeing the superblock. + * The function must be called with bdev->bd_holder_lock and releases it. */ -static bool super_lock_shared_active(struct super_block *sb) +static struct super_block *bdev_super_lock_shared(struct block_device *bdev) + __releases(&bdev->bd_holder_lock) { - bool born = super_lock_shared(sb); + struct super_block *sb = bdev->bd_holder; + bool born; + + lockdep_assert_held(&bdev->bd_holder_lock); + lockdep_assert_not_held(&sb->s_umount); + lockdep_assert_not_held(&bdev->bd_disk->open_mutex); + + /* Make sure sb doesn't go away from under us */ + spin_lock(&sb_lock); + sb->s_count++; + spin_unlock(&sb_lock); + mutex_unlock(&bdev->bd_holder_lock); + born = super_lock_shared(sb); if (!born || !sb->s_root || !(sb->s_flags & SB_ACTIVE)) { super_unlock_shared(sb); - return false; + put_super(sb); + return NULL; } - return true; + /* + * The superblock is active and we hold s_umount, we can drop our + * temporary reference now. + */ + put_super(sb); + return sb; } static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { - struct super_block *sb = bdev->bd_holder; - - /* bd_holder_lock ensures that the sb isn't freed */ - lockdep_assert_held(&bdev->bd_holder_lock); + struct super_block *sb; - if (!super_lock_shared_active(sb)) + sb = bdev_super_lock_shared(bdev); + if (!sb) return; if (!surprise) @@ -1459,11 +1475,10 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) static void fs_bdev_sync(struct block_device *bdev) { - struct super_block *sb = bdev->bd_holder; - - lockdep_assert_held(&bdev->bd_holder_lock); + struct super_block *sb; - if (!super_lock_shared_active(sb)) + sb = bdev_super_lock_shared(bdev); + if (!sb) return; sync_filesystem(sb); super_unlock_shared(sb); @@ -1479,14 +1494,16 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc) { blk_mode_t mode = sb_open_mode(sb_flags); + struct bdev_handle *bdev_handle; struct block_device *bdev; - bdev = blkdev_get_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); - if (IS_ERR(bdev)) { + bdev_handle = bdev_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); + if (IS_ERR(bdev_handle)) { if (fc) errorf(fc, "%s: Can't open blockdev", fc->source); - return PTR_ERR(bdev); + return PTR_ERR(bdev_handle); } + bdev = bdev_handle->bdev; /* * This really should be in blkdev_get_by_dev, but right now can't due @@ -1494,7 +1511,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, * writable from userspace even for a read-only block device. */ if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return -EACCES; } @@ -1510,10 +1527,11 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, mutex_unlock(&bdev->bd_fsfreeze_mutex); if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - blkdev_put(bdev, sb); + bdev_release(bdev_handle); return -EBUSY; } spin_lock(&sb_lock); + sb->s_bdev_handle = bdev_handle; sb->s_bdev = bdev; sb->s_bdi = bdi_get(bdev->bd_disk->bdi); if (bdev_stable_writes(bdev)) @@ -1646,7 +1664,7 @@ void kill_block_super(struct super_block *sb) generic_shutdown_super(sb); if (bdev) { sync_blockdev(bdev); - blkdev_put(bdev, sb); + bdev_release(sb->s_bdev_handle); } } diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 2f5ead88d00b..2e126d72d619 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -224,7 +224,7 @@ got_it: memset (de->name + namelen, 0, SYSV_DIRSIZE - namelen - 2); de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino); dir_commit_chunk(page, pos, SYSV_DIRSIZE); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); err = sysv_handle_dirsync(dir); out_page: @@ -249,7 +249,7 @@ int sysv_delete_entry(struct sysv_dir_entry *de, struct page *page) } de->inode = 0; dir_commit_chunk(page, pos, SYSV_DIRSIZE); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); return sysv_handle_dirsync(inode); } @@ -346,7 +346,7 @@ int sysv_set_link(struct sysv_dir_entry *de, struct page *page, } de->inode = cpu_to_fs16(SYSV_SB(inode->i_sb), inode->i_ino); dir_commit_chunk(page, pos, SYSV_DIRSIZE); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); return sysv_handle_dirsync(inode); } diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 6719da5889d9..269df6d49815 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -165,7 +165,7 @@ struct inode * sysv_new_inode(const struct inode * dir, umode_t mode) dirty_sb(sb); inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_ino = fs16_to_cpu(sbi, ino); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_blocks = 0; memset(SYSV_I(inode)->i_data, 0, sizeof(SYSV_I(inode)->i_data)); SYSV_I(inode)->i_dir_start_lookup = 0; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 0aa3827d8178..5a915b2e68f5 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -200,11 +200,9 @@ struct inode *sysv_iget(struct super_block *sb, unsigned int ino) i_gid_write(inode, (gid_t)fs16_to_cpu(sbi, raw_inode->i_gid)); set_nlink(inode, fs16_to_cpu(sbi, raw_inode->i_nlink)); inode->i_size = fs32_to_cpu(sbi, raw_inode->i_size); - inode->i_atime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_atime); - inode->i_mtime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_mtime); + inode_set_atime(inode, fs32_to_cpu(sbi, raw_inode->i_atime), 0); + inode_set_mtime(inode, fs32_to_cpu(sbi, raw_inode->i_mtime), 0); inode_set_ctime(inode, fs32_to_cpu(sbi, raw_inode->i_ctime), 0); - inode->i_atime.tv_nsec = 0; - inode->i_mtime.tv_nsec = 0; inode->i_blocks = 0; si = SYSV_I(inode); @@ -253,9 +251,9 @@ static int __sysv_write_inode(struct inode *inode, int wait) raw_inode->i_gid = cpu_to_fs16(sbi, fs_high2lowgid(i_gid_read(inode))); raw_inode->i_nlink = cpu_to_fs16(sbi, inode->i_nlink); raw_inode->i_size = cpu_to_fs32(sbi, inode->i_size); - raw_inode->i_atime = cpu_to_fs32(sbi, inode->i_atime.tv_sec); - raw_inode->i_mtime = cpu_to_fs32(sbi, inode->i_mtime.tv_sec); - raw_inode->i_ctime = cpu_to_fs32(sbi, inode_get_ctime(inode).tv_sec); + raw_inode->i_atime = cpu_to_fs32(sbi, inode_get_atime_sec(inode)); + raw_inode->i_mtime = cpu_to_fs32(sbi, inode_get_mtime_sec(inode)); + raw_inode->i_ctime = cpu_to_fs32(sbi, inode_get_ctime_sec(inode)); si = SYSV_I(inode); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index edb94e55de8e..725981474e5f 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -423,7 +423,7 @@ do_indirects: } n++; } - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (IS_SYNC(inode)) sysv_sync_inode (inode); else diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 5f1714089884..8c8d64e76103 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -421,7 +421,7 @@ static int eventfs_release(struct inode *inode, struct file *file) if (WARN_ON_ONCE(!dlist)) return -EINVAL; - for (i = 0; dlist->dentries[i]; i++) { + for (i = 0; dlist->dentries && dlist->dentries[i]; i++) { dput(dlist->dentries[i]); } diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 891653ba9cf3..429603d865a9 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -152,7 +152,7 @@ struct inode *tracefs_get_inode(struct super_block *sb) struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); } return inode; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index eef9e527d9ff..d013c5b3f1ed 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -237,14 +237,14 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode) pr_err("\tuid %u\n", (unsigned int)i_uid_read(inode)); pr_err("\tgid %u\n", (unsigned int)i_gid_read(inode)); pr_err("\tatime %u.%u\n", - (unsigned int)inode->i_atime.tv_sec, - (unsigned int)inode->i_atime.tv_nsec); + (unsigned int) inode_get_atime_sec(inode), + (unsigned int) inode_get_atime_nsec(inode)); pr_err("\tmtime %u.%u\n", - (unsigned int)inode->i_mtime.tv_sec, - (unsigned int)inode->i_mtime.tv_nsec); + (unsigned int) inode_get_mtime_sec(inode), + (unsigned int) inode_get_mtime_nsec(inode)); pr_err("\tctime %u.%u\n", - (unsigned int) inode_get_ctime(inode).tv_sec, - (unsigned int) inode_get_ctime(inode).tv_nsec); + (unsigned int) inode_get_ctime_sec(inode), + (unsigned int) inode_get_ctime_nsec(inode)); pr_err("\tcreat_sqnum %llu\n", ui->creat_sqnum); pr_err("\txattr_size %u\n", ui->xattr_size); pr_err("\txattr_cnt %u\n", ui->xattr_cnt); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 2f48c58d47cd..7af442de44c3 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -96,7 +96,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, inode->i_flags |= S_NOCMTIME; inode_init_owner(&nop_mnt_idmap, inode, dir, mode); - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_mapping->nrpages = 0; if (!is_xattr) { @@ -324,7 +324,8 @@ static int ubifs_create(struct mnt_idmap *idmap, struct inode *dir, mutex_lock(&dir_ui->ui_mutex); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0); if (err) goto out_cancel; @@ -767,7 +768,8 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, inode_set_ctime_current(inode); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0); if (err) goto out_cancel; @@ -841,7 +843,8 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry) drop_nlink(inode); dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0); if (err) goto out_cancel; @@ -944,7 +947,8 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry) drop_nlink(dir); dir->i_size -= sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 1, 0); if (err) goto out_cancel; @@ -1018,7 +1022,8 @@ static int ubifs_mkdir(struct mnt_idmap *idmap, struct inode *dir, inc_nlink(dir); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0); if (err) { ubifs_err(c, "cannot create directory, error %d", err); @@ -1109,7 +1114,8 @@ static int ubifs_mknod(struct mnt_idmap *idmap, struct inode *dir, mutex_lock(&dir_ui->ui_mutex); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0); if (err) goto out_cancel; @@ -1209,7 +1215,8 @@ static int ubifs_symlink(struct mnt_idmap *idmap, struct inode *dir, mutex_lock(&dir_ui->ui_mutex); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; - dir->i_mtime = inode_set_ctime_to_ts(dir, inode_get_ctime(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_get_ctime(inode))); err = ubifs_jnl_update(c, dir, &nm, inode, 0, 0); if (err) goto out_cancel; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index e5382f0b2587..2e65fd2dbdc3 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1088,9 +1088,9 @@ static void do_attr_changes(struct inode *inode, const struct iattr *attr) if (attr->ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (attr->ia_valid & ATTR_ATIME) - inode->i_atime = attr->ia_atime; + inode_set_atime_to_ts(inode, attr->ia_atime); if (attr->ia_valid & ATTR_MTIME) - inode->i_mtime = attr->ia_mtime; + inode_set_mtime_to_ts(inode, attr->ia_mtime); if (attr->ia_valid & ATTR_CTIME) inode_set_ctime_to_ts(inode, attr->ia_ctime); if (attr->ia_valid & ATTR_MODE) { @@ -1192,7 +1192,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode, mutex_lock(&ui->ui_mutex); ui->ui_size = inode->i_size; /* Truncation changes inode [mc]time */ - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); /* Other attributes may be changed at the same time as well */ do_attr_changes(inode, attr); err = ubifs_jnl_truncate(c, inode, old_size, new_size); @@ -1239,7 +1239,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode, mutex_lock(&ui->ui_mutex); if (attr->ia_valid & ATTR_SIZE) { /* Truncation changes inode [mc]time */ - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); /* 'truncate_setsize()' changed @i_size, update @ui_size */ ui->ui_size = inode->i_size; } @@ -1365,9 +1365,9 @@ static inline int mctime_update_needed(const struct inode *inode, const struct timespec64 *now) { struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 mtime = inode_get_mtime(inode); - if (!timespec64_equal(&inode->i_mtime, now) || - !timespec64_equal(&ctime, now)) + if (!timespec64_equal(&mtime, now) || !timespec64_equal(&ctime, now)) return 1; return 0; } @@ -1429,7 +1429,7 @@ static int update_mctime(struct inode *inode) return err; mutex_lock(&ui->ui_mutex); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); release = ui->dirty; mark_inode_dirty_sync(inode); mutex_unlock(&ui->ui_mutex); @@ -1567,7 +1567,7 @@ static vm_fault_t ubifs_vm_page_mkwrite(struct vm_fault *vmf) struct ubifs_inode *ui = ubifs_inode(inode); mutex_lock(&ui->ui_mutex); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); release = ui->dirty; mark_inode_dirty_sync(inode); mutex_unlock(&ui->ui_mutex); diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index ffc9beee7be6..d69d2154645b 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -452,12 +452,12 @@ static void pack_inode(struct ubifs_info *c, struct ubifs_ino_node *ino, ino->ch.node_type = UBIFS_INO_NODE; ino_key_init_flash(c, &ino->key, inode->i_ino); ino->creat_sqnum = cpu_to_le64(ui->creat_sqnum); - ino->atime_sec = cpu_to_le64(inode->i_atime.tv_sec); - ino->atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); - ino->ctime_sec = cpu_to_le64(inode_get_ctime(inode).tv_sec); - ino->ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec); - ino->mtime_sec = cpu_to_le64(inode->i_mtime.tv_sec); - ino->mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + ino->atime_sec = cpu_to_le64(inode_get_atime_sec(inode)); + ino->atime_nsec = cpu_to_le32(inode_get_atime_nsec(inode)); + ino->ctime_sec = cpu_to_le64(inode_get_ctime_sec(inode)); + ino->ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); + ino->mtime_sec = cpu_to_le64(inode_get_mtime_sec(inode)); + ino->mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); ino->uid = cpu_to_le32(i_uid_read(inode)); ino->gid = cpu_to_le32(i_gid_read(inode)); ino->mode = cpu_to_le32(inode->i_mode); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b08fb28d16b5..366941d4a18a 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -142,10 +142,10 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) set_nlink(inode, le32_to_cpu(ino->nlink)); i_uid_write(inode, le32_to_cpu(ino->uid)); i_gid_write(inode, le32_to_cpu(ino->gid)); - inode->i_atime.tv_sec = (int64_t)le64_to_cpu(ino->atime_sec); - inode->i_atime.tv_nsec = le32_to_cpu(ino->atime_nsec); - inode->i_mtime.tv_sec = (int64_t)le64_to_cpu(ino->mtime_sec); - inode->i_mtime.tv_nsec = le32_to_cpu(ino->mtime_nsec); + inode_set_atime(inode, (int64_t)le64_to_cpu(ino->atime_sec), + le32_to_cpu(ino->atime_nsec)); + inode_set_mtime(inode, (int64_t)le64_to_cpu(ino->mtime_sec), + le32_to_cpu(ino->mtime_nsec)); inode_set_ctime(inode, (int64_t)le64_to_cpu(ino->ctime_sec), le32_to_cpu(ino->ctime_nsec)); inode->i_mode = le32_to_cpu(ino->mode); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index ebb3ad6b5e7e..62633816d7d0 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -2043,7 +2043,7 @@ ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, size_t size); #ifdef CONFIG_UBIFS_FS_XATTR -extern const struct xattr_handler *ubifs_xattr_handlers[]; +extern const struct xattr_handler * const ubifs_xattr_handlers[]; ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size); void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum); int ubifs_purge_xattrs(struct inode *host); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 406c82eab513..0847db521984 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -735,7 +735,7 @@ static const struct xattr_handler ubifs_security_xattr_handler = { }; #endif -const struct xattr_handler *ubifs_xattr_handlers[] = { +const struct xattr_handler * const ubifs_xattr_handlers[] = { &ubifs_user_xattr_handler, &ubifs_trusted_xattr_handler, #ifdef CONFIG_UBIFS_FS_SECURITY diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index 6b558cbbeb6b..5f1f969f4134 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -100,8 +100,8 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); - iinfo->i_crtime = inode->i_mtime; + simple_inode_init_ts(inode); + iinfo->i_crtime = inode_get_mtime(inode); if (unlikely(insert_inode_locked(inode) < 0)) { make_bad_inode(inode); iput(inode); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index a17a6184cc39..d8493449d4c5 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1296,7 +1296,7 @@ set_size: goto out_unlock; } update_time: - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (IS_SYNC(inode)) udf_sync_inode(inode); else @@ -1327,7 +1327,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode) int bs = inode->i_sb->s_blocksize; int ret = -EIO; uint32_t uid, gid; - struct timespec64 ctime; + struct timespec64 ts; reread: if (iloc->partitionReferenceNum >= sbi->s_partitions) { @@ -1504,10 +1504,12 @@ reread: inode->i_blocks = le64_to_cpu(fe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); - udf_disk_stamp_to_time(&inode->i_atime, fe->accessTime); - udf_disk_stamp_to_time(&inode->i_mtime, fe->modificationTime); - udf_disk_stamp_to_time(&ctime, fe->attrTime); - inode_set_ctime_to_ts(inode, ctime); + udf_disk_stamp_to_time(&ts, fe->accessTime); + inode_set_atime_to_ts(inode, ts); + udf_disk_stamp_to_time(&ts, fe->modificationTime); + inode_set_mtime_to_ts(inode, ts); + udf_disk_stamp_to_time(&ts, fe->attrTime); + inode_set_ctime_to_ts(inode, ts); iinfo->i_unique = le64_to_cpu(fe->uniqueID); iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr); @@ -1519,11 +1521,13 @@ reread: inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); - udf_disk_stamp_to_time(&inode->i_atime, efe->accessTime); - udf_disk_stamp_to_time(&inode->i_mtime, efe->modificationTime); + udf_disk_stamp_to_time(&ts, efe->accessTime); + inode_set_atime_to_ts(inode, ts); + udf_disk_stamp_to_time(&ts, efe->modificationTime); + inode_set_mtime_to_ts(inode, ts); + udf_disk_stamp_to_time(&ts, efe->attrTime); + inode_set_ctime_to_ts(inode, ts); udf_disk_stamp_to_time(&iinfo->i_crtime, efe->createTime); - udf_disk_stamp_to_time(&ctime, efe->attrTime); - inode_set_ctime_to_ts(inode, ctime); iinfo->i_unique = le64_to_cpu(efe->uniqueID); iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr); @@ -1798,8 +1802,8 @@ static int udf_update_inode(struct inode *inode, int do_sync) inode->i_sb->s_blocksize - sizeof(struct fileEntry)); fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); - udf_time_to_disk_stamp(&fe->accessTime, inode->i_atime); - udf_time_to_disk_stamp(&fe->modificationTime, inode->i_mtime); + udf_time_to_disk_stamp(&fe->accessTime, inode_get_atime(inode)); + udf_time_to_disk_stamp(&fe->modificationTime, inode_get_mtime(inode)); udf_time_to_disk_stamp(&fe->attrTime, inode_get_ctime(inode)); memset(&(fe->impIdent), 0, sizeof(struct regid)); strcpy(fe->impIdent.ident, UDF_ID_DEVELOPER); @@ -1829,12 +1833,14 @@ static int udf_update_inode(struct inode *inode, int do_sync) cpu_to_le32(inode->i_sb->s_blocksize); } - udf_adjust_time(iinfo, inode->i_atime); - udf_adjust_time(iinfo, inode->i_mtime); + udf_adjust_time(iinfo, inode_get_atime(inode)); + udf_adjust_time(iinfo, inode_get_mtime(inode)); udf_adjust_time(iinfo, inode_get_ctime(inode)); - udf_time_to_disk_stamp(&efe->accessTime, inode->i_atime); - udf_time_to_disk_stamp(&efe->modificationTime, inode->i_mtime); + udf_time_to_disk_stamp(&efe->accessTime, + inode_get_atime(inode)); + udf_time_to_disk_stamp(&efe->modificationTime, + inode_get_mtime(inode)); udf_time_to_disk_stamp(&efe->createTime, iinfo->i_crtime); udf_time_to_disk_stamp(&efe->attrTime, inode_get_ctime(inode)); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index ae55ab8859b6..3508ac484da3 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -365,7 +365,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode) *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); udf_fiiter_write_fi(&iter, NULL); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); udf_fiiter_release(&iter); udf_add_fid_counter(dir->i_sb, false, 1); @@ -471,7 +471,7 @@ static int udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, udf_fiiter_release(&iter); udf_add_fid_counter(dir->i_sb, true, 1); inc_nlink(dir); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); d_instantiate_new(dentry, inode); @@ -523,8 +523,8 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry) inode->i_size = 0; inode_dec_link_count(dir); udf_add_fid_counter(dir->i_sb, true, -1); - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); mark_inode_dirty(dir); ret = 0; end_rmdir: @@ -555,7 +555,7 @@ static int udf_unlink(struct inode *dir, struct dentry *dentry) set_nlink(inode, 1); } udf_fiiter_delete_entry(&iter); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); inode_dec_link_count(inode); udf_add_fid_counter(dir->i_sb, false, -1); @@ -748,7 +748,7 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, udf_add_fid_counter(dir->i_sb, false, 1); inode_set_ctime_current(inode); mark_inode_dirty(inode); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); ihold(inode); d_instantiate(dentry, inode); @@ -866,8 +866,8 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, udf_add_fid_counter(old_dir->i_sb, S_ISDIR(new_inode->i_mode), -1); } - old_dir->i_mtime = inode_set_ctime_current(old_dir); - new_dir->i_mtime = inode_set_ctime_current(new_dir); + inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); + inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); mark_inode_dirty(old_dir); mark_inode_dirty(new_dir); diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index fd57f03b6c93..27c85d92d1dc 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -107,7 +107,7 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, ufs_commit_chunk(page, pos, len); ufs_put_page(page); if (update_times) - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); ufs_handle_dirsync(dir); } @@ -397,7 +397,7 @@ got_it: ufs_set_de_type(sb, de, inode->i_mode); ufs_commit_chunk(page, pos, rec_len); - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); err = ufs_handle_dirsync(dir); @@ -539,7 +539,7 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir, pde->d_reclen = cpu_to_fs16(sb, to - from); dir->d_ino = 0; ufs_commit_chunk(page, pos, to - from); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); err = ufs_handle_dirsync(inode); out: diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index a1e7bd9d1f98..73531827ecee 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -292,7 +292,7 @@ cg_found: inode_init_owner(&nop_mnt_idmap, inode, dir, mode); inode->i_blocks = 0; inode->i_generation = 0; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); ufsi->i_flags = UFS_I(dir)->i_flags; ufsi->i_lastfrag = 0; ufsi->i_shadow = 0; diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 21a4779a2de5..338e4b97312f 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -579,13 +579,15 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode) i_gid_write(inode, ufs_get_inode_gid(sb, ufs_inode)); inode->i_size = fs64_to_cpu(sb, ufs_inode->ui_size); - inode->i_atime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_atime.tv_sec); + inode_set_atime(inode, + (signed)fs32_to_cpu(sb, ufs_inode->ui_atime.tv_sec), + 0); inode_set_ctime(inode, (signed)fs32_to_cpu(sb, ufs_inode->ui_ctime.tv_sec), 0); - inode->i_mtime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_mtime.tv_sec); - inode->i_mtime.tv_nsec = 0; - inode->i_atime.tv_nsec = 0; + inode_set_mtime(inode, + (signed)fs32_to_cpu(sb, ufs_inode->ui_mtime.tv_sec), + 0); inode->i_blocks = fs32_to_cpu(sb, ufs_inode->ui_blocks); inode->i_generation = fs32_to_cpu(sb, ufs_inode->ui_gen); ufsi->i_flags = fs32_to_cpu(sb, ufs_inode->ui_flags); @@ -626,12 +628,12 @@ static int ufs2_read_inode(struct inode *inode, struct ufs2_inode *ufs2_inode) i_gid_write(inode, fs32_to_cpu(sb, ufs2_inode->ui_gid)); inode->i_size = fs64_to_cpu(sb, ufs2_inode->ui_size); - inode->i_atime.tv_sec = fs64_to_cpu(sb, ufs2_inode->ui_atime); + inode_set_atime(inode, fs64_to_cpu(sb, ufs2_inode->ui_atime), + fs32_to_cpu(sb, ufs2_inode->ui_atimensec)); inode_set_ctime(inode, fs64_to_cpu(sb, ufs2_inode->ui_ctime), fs32_to_cpu(sb, ufs2_inode->ui_ctimensec)); - inode->i_mtime.tv_sec = fs64_to_cpu(sb, ufs2_inode->ui_mtime); - inode->i_atime.tv_nsec = fs32_to_cpu(sb, ufs2_inode->ui_atimensec); - inode->i_mtime.tv_nsec = fs32_to_cpu(sb, ufs2_inode->ui_mtimensec); + inode_set_mtime(inode, fs64_to_cpu(sb, ufs2_inode->ui_mtime), + fs32_to_cpu(sb, ufs2_inode->ui_mtimensec)); inode->i_blocks = fs64_to_cpu(sb, ufs2_inode->ui_blocks); inode->i_generation = fs32_to_cpu(sb, ufs2_inode->ui_gen); ufsi->i_flags = fs32_to_cpu(sb, ufs2_inode->ui_flags); @@ -725,12 +727,14 @@ static void ufs1_update_inode(struct inode *inode, struct ufs_inode *ufs_inode) ufs_set_inode_gid(sb, ufs_inode, i_gid_read(inode)); ufs_inode->ui_size = cpu_to_fs64(sb, inode->i_size); - ufs_inode->ui_atime.tv_sec = cpu_to_fs32(sb, inode->i_atime.tv_sec); + ufs_inode->ui_atime.tv_sec = cpu_to_fs32(sb, + inode_get_atime_sec(inode)); ufs_inode->ui_atime.tv_usec = 0; ufs_inode->ui_ctime.tv_sec = cpu_to_fs32(sb, - inode_get_ctime(inode).tv_sec); + inode_get_ctime_sec(inode)); ufs_inode->ui_ctime.tv_usec = 0; - ufs_inode->ui_mtime.tv_sec = cpu_to_fs32(sb, inode->i_mtime.tv_sec); + ufs_inode->ui_mtime.tv_sec = cpu_to_fs32(sb, + inode_get_mtime_sec(inode)); ufs_inode->ui_mtime.tv_usec = 0; ufs_inode->ui_blocks = cpu_to_fs32(sb, inode->i_blocks); ufs_inode->ui_flags = cpu_to_fs32(sb, ufsi->i_flags); @@ -770,13 +774,15 @@ static void ufs2_update_inode(struct inode *inode, struct ufs2_inode *ufs_inode) ufs_inode->ui_gid = cpu_to_fs32(sb, i_gid_read(inode)); ufs_inode->ui_size = cpu_to_fs64(sb, inode->i_size); - ufs_inode->ui_atime = cpu_to_fs64(sb, inode->i_atime.tv_sec); - ufs_inode->ui_atimensec = cpu_to_fs32(sb, inode->i_atime.tv_nsec); - ufs_inode->ui_ctime = cpu_to_fs64(sb, inode_get_ctime(inode).tv_sec); + ufs_inode->ui_atime = cpu_to_fs64(sb, inode_get_atime_sec(inode)); + ufs_inode->ui_atimensec = cpu_to_fs32(sb, + inode_get_atime_nsec(inode)); + ufs_inode->ui_ctime = cpu_to_fs64(sb, inode_get_ctime_sec(inode)); ufs_inode->ui_ctimensec = cpu_to_fs32(sb, - inode_get_ctime(inode).tv_nsec); - ufs_inode->ui_mtime = cpu_to_fs64(sb, inode->i_mtime.tv_sec); - ufs_inode->ui_mtimensec = cpu_to_fs32(sb, inode->i_mtime.tv_nsec); + inode_get_ctime_nsec(inode)); + ufs_inode->ui_mtime = cpu_to_fs64(sb, inode_get_mtime_sec(inode)); + ufs_inode->ui_mtimensec = cpu_to_fs32(sb, + inode_get_mtime_nsec(inode)); ufs_inode->ui_blocks = cpu_to_fs64(sb, inode->i_blocks); ufs_inode->ui_flags = cpu_to_fs32(sb, ufsi->i_flags); @@ -1208,7 +1214,7 @@ static int ufs_truncate(struct inode *inode, loff_t size) truncate_setsize(inode, size); ufs_truncate_blocks(inode); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); out: UFSD("EXIT: err %d\n", err); diff --git a/fs/vboxsf/utils.c b/fs/vboxsf/utils.c index 83f20dd15522..72ac9320e6a3 100644 --- a/fs/vboxsf/utils.c +++ b/fs/vboxsf/utils.c @@ -126,12 +126,12 @@ int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode, do_div(allocated, 512); inode->i_blocks = allocated; - inode->i_atime = ns_to_timespec64( - info->access_time.ns_relative_to_unix_epoch); + inode_set_atime_to_ts(inode, + ns_to_timespec64(info->access_time.ns_relative_to_unix_epoch)); inode_set_ctime_to_ts(inode, ns_to_timespec64(info->change_time.ns_relative_to_unix_epoch)); - inode->i_mtime = ns_to_timespec64( - info->modification_time.ns_relative_to_unix_epoch); + inode_set_mtime_to_ts(inode, + ns_to_timespec64(info->modification_time.ns_relative_to_unix_epoch)); return 0; } @@ -194,7 +194,7 @@ int vboxsf_inode_revalidate(struct dentry *dentry) struct vboxsf_sbi *sbi; struct vboxsf_inode *sf_i; struct shfl_fsobjinfo info; - struct timespec64 prev_mtime; + struct timespec64 mtime, prev_mtime; struct inode *inode; int err; @@ -202,7 +202,7 @@ int vboxsf_inode_revalidate(struct dentry *dentry) return -EINVAL; inode = d_inode(dentry); - prev_mtime = inode->i_mtime; + prev_mtime = inode_get_mtime(inode); sf_i = VBOXSF_I(inode); sbi = VBOXSF_SBI(dentry->d_sb); if (!sf_i->force_restat) { @@ -225,7 +225,8 @@ int vboxsf_inode_revalidate(struct dentry *dentry) * page-cache for it. Note this also gets triggered by our own writes, * this is unavoidable. */ - if (timespec64_compare(&inode->i_mtime, &prev_mtime) > 0) + mtime = inode_get_mtime(inode); + if (timespec64_compare(&mtime, &prev_mtime) > 0) invalidate_inode_pages2(inode->i_mapping); return 0; diff --git a/fs/xattr.c b/fs/xattr.c index efd4736bc94b..09d927603433 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -56,7 +56,7 @@ strcmp_prefix(const char *a, const char *a_prefix) static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { - const struct xattr_handler **handlers = inode->i_sb->s_xattr; + const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { @@ -162,7 +162,7 @@ xattr_permission(struct mnt_idmap *idmap, struct inode *inode, int xattr_supports_user_prefix(struct inode *inode) { - const struct xattr_handler **handlers = inode->i_sb->s_xattr; + const struct xattr_handler * const *handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { @@ -999,7 +999,7 @@ int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { - const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr; + const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr; ssize_t remaining_size = buffer_size; int err = 0; diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index e9cc481b4ddf..f9f4d694640d 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -1001,6 +1001,12 @@ xfs_ag_shrink_space( error = -ENOSPC; goto resv_init_out; } + + /* Update perag geometry */ + pag->block_count -= delta; + __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, + &pag->agino_max); + xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH); xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH); return 0; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index a35781577cad..543f3748c2a3 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -220,8 +220,10 @@ xfs_inode_from_disk( * a time before epoch is converted to a time long after epoch * on 64 bit systems. */ - inode->i_atime = xfs_inode_from_disk_ts(from, from->di_atime); - inode->i_mtime = xfs_inode_from_disk_ts(from, from->di_mtime); + inode_set_atime_to_ts(inode, + xfs_inode_from_disk_ts(from, from->di_atime)); + inode_set_mtime_to_ts(inode, + xfs_inode_from_disk_ts(from, from->di_mtime)); inode_set_ctime_to_ts(inode, xfs_inode_from_disk_ts(from, from->di_ctime)); @@ -315,8 +317,8 @@ xfs_inode_to_disk( to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff); to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16); - to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime); - to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime); + to->di_atime = xfs_inode_to_disk_ts(ip, inode_get_atime(inode)); + to->di_mtime = xfs_inode_to_disk_ts(ip, inode_get_mtime(inode)); to->di_ctime = xfs_inode_to_disk_ts(ip, inode_get_ctime(inode)); to->di_nlink = cpu_to_be32(inode->i_nlink); to->di_gen = cpu_to_be32(inode->i_generation); diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index fa180ab66b73..396648acb5be 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -970,6 +970,7 @@ xfs_rtfree_extent( xfs_mount_t *mp; /* file system mount structure */ xfs_fsblock_t sb; /* summary file block number */ struct xfs_buf *sumbp = NULL; /* summary file block buffer */ + struct timespec64 atime; mp = tp->t_mountp; @@ -999,7 +1000,10 @@ xfs_rtfree_extent( mp->m_sb.sb_rextents) { if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM; - *(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0; + + atime = inode_get_atime(VFS_I(mp->m_rbmip)); + *((uint64_t *)&atime) = 0; + inode_set_atime_to_ts(VFS_I(mp->m_rbmip), atime); xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); } return 0; diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 6b2296ff248a..70e97ea6eee7 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -65,7 +65,7 @@ xfs_trans_ichgtime( tv = current_time(inode); if (flags & XFS_ICHGTIME_MOD) - inode->i_mtime = tv; + inode_set_mtime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CHG) inode_set_ctime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CREATE) diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c index d98e8e77c684..090c3ead43fd 100644 --- a/fs/xfs/scrub/xfile.c +++ b/fs/xfs/scrub/xfile.c @@ -10,7 +10,6 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_format.h" #include "scrub/xfile.h" #include "scrub/xfarray.h" #include "scrub/scrub.h" diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index fcefab687285..40e0a1f1f753 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1644,7 +1644,7 @@ xfs_swap_extents( uint64_t f; int resblks = 0; unsigned int flags = 0; - struct timespec64 ctime; + struct timespec64 ctime, mtime; /* * Lock the inodes against other IO, page faults and truncate to @@ -1758,10 +1758,11 @@ xfs_swap_extents( * under it. */ ctime = inode_get_ctime(VFS_I(ip)); + mtime = inode_get_mtime(VFS_I(ip)); if ((sbp->bs_ctime.tv_sec != ctime.tv_sec) || (sbp->bs_ctime.tv_nsec != ctime.tv_nsec) || - (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) || - (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) { + (sbp->bs_mtime.tv_sec != mtime.tv_sec) || + (sbp->bs_mtime.tv_nsec != mtime.tv_nsec)) { error = -EBUSY; goto out_trans_cancel; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index c1ece4a08ff4..003e157241da 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1945,8 +1945,6 @@ void xfs_free_buftarg( struct xfs_buftarg *btp) { - struct block_device *bdev = btp->bt_bdev; - unregister_shrinker(&btp->bt_shrinker); ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0); percpu_counter_destroy(&btp->bt_io_count); @@ -1954,8 +1952,8 @@ xfs_free_buftarg( fs_put_dax(btp->bt_daxdev, btp->bt_mount); /* the main block device is closed by kill_block_super */ - if (bdev != btp->bt_mount->m_super->s_bdev) - blkdev_put(bdev, btp->bt_mount->m_super); + if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev) + bdev_release(btp->bt_bdev_handle); kmem_free(btp); } @@ -1990,16 +1988,15 @@ xfs_setsize_buftarg( */ STATIC int xfs_setsize_buftarg_early( - xfs_buftarg_t *btp, - struct block_device *bdev) + xfs_buftarg_t *btp) { - return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev)); + return xfs_setsize_buftarg(btp, bdev_logical_block_size(btp->bt_bdev)); } struct xfs_buftarg * xfs_alloc_buftarg( struct xfs_mount *mp, - struct block_device *bdev) + struct bdev_handle *bdev_handle) { xfs_buftarg_t *btp; const struct dax_holder_operations *ops = NULL; @@ -2010,9 +2007,10 @@ xfs_alloc_buftarg( btp = kmem_zalloc(sizeof(*btp), KM_NOFS); btp->bt_mount = mp; - btp->bt_dev = bdev->bd_dev; - btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, + btp->bt_bdev_handle = bdev_handle; + btp->bt_dev = bdev_handle->bdev->bd_dev; + btp->bt_bdev = bdev_handle->bdev; + btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off, mp, ops); /* @@ -2022,7 +2020,7 @@ xfs_alloc_buftarg( ratelimit_state_init(&btp->bt_ioerror_rl, 30 * HZ, DEFAULT_RATELIMIT_BURST); - if (xfs_setsize_buftarg_early(btp, bdev)) + if (xfs_setsize_buftarg_early(btp)) goto error_free; if (list_lru_init(&btp->bt_lru)) diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index df8f47953bb4..ada9d310b7d3 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -98,6 +98,7 @@ typedef unsigned int xfs_buf_flags_t; */ typedef struct xfs_buftarg { dev_t bt_dev; + struct bdev_handle *bt_bdev_handle; struct block_device *bt_bdev; struct dax_device *bt_daxdev; u64 bt_dax_part_off; @@ -364,7 +365,7 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) * Handling of buftargs. */ struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp, - struct block_device *bdev); + struct bdev_handle *bdev_handle); extern void xfs_free_buftarg(struct xfs_buftarg *); extern void xfs_buftarg_wait(struct xfs_buftarg *); extern void xfs_buftarg_drain(struct xfs_buftarg *); diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index afc4c78b9eed..d5787991bb5b 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (C) 2010 Red Hat, Inc. + * Copyright (C) 2010, 2023 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" @@ -19,21 +19,147 @@ #include "xfs_log.h" #include "xfs_ag.h" -STATIC int -xfs_trim_extents( +/* + * Notes on an efficient, low latency fstrim algorithm + * + * We need to walk the filesystem free space and issue discards on the free + * space that meet the search criteria (size and location). We cannot issue + * discards on extents that might be in use, or are so recently in use they are + * still marked as busy. To serialise against extent state changes whilst we are + * gathering extents to trim, we must hold the AGF lock to lock out other + * allocations and extent free operations that might change extent state. + * + * However, we cannot just hold the AGF for the entire AG free space walk whilst + * we issue discards on each free space that is found. Storage devices can have + * extremely slow discard implementations (e.g. ceph RBD) and so walking a + * couple of million free extents and issuing synchronous discards on each + * extent can take a *long* time. Whilst we are doing this walk, nothing else + * can access the AGF, and we can stall transactions and hence the log whilst + * modifications wait for the AGF lock to be released. This can lead hung tasks + * kicking the hung task timer and rebooting the system. This is bad. + * + * Hence we need to take a leaf from the bulkstat playbook. It takes the AGI + * lock, gathers a range of inode cluster buffers that are allocated, drops the + * AGI lock and then reads all the inode cluster buffers and processes them. It + * loops doing this, using a cursor to keep track of where it is up to in the AG + * for each iteration to restart the INOBT lookup from. + * + * We can't do this exactly with free space - once we drop the AGF lock, the + * state of the free extent is out of our control and we cannot run a discard + * safely on it in this situation. Unless, of course, we've marked the free + * extent as busy and undergoing a discard operation whilst we held the AGF + * locked. + * + * This is exactly how online discard works - free extents are marked busy when + * they are freed, and once the extent free has been committed to the journal, + * the busy extent record is marked as "undergoing discard" and the discard is + * then issued on the free extent. Once the discard completes, the busy extent + * record is removed and the extent is able to be allocated again. + * + * In the context of fstrim, if we find a free extent we need to discard, we + * don't have to discard it immediately. All we need to do it record that free + * extent as being busy and under discard, and all the allocation routines will + * now avoid trying to allocate it. Hence if we mark the extent as busy under + * the AGF lock, we can safely discard it without holding the AGF lock because + * nothing will attempt to allocate that free space until the discard completes. + * + * This also allows us to issue discards asynchronously like we do with online + * discard, and so for fast devices fstrim will run much faster as we can have + * multiple discard operations in flight at once, as well as pipeline the free + * extent search so that it overlaps in flight discard IO. + */ + +struct workqueue_struct *xfs_discard_wq; + +static void +xfs_discard_endio_work( + struct work_struct *work) +{ + struct xfs_busy_extents *extents = + container_of(work, struct xfs_busy_extents, endio_work); + + xfs_extent_busy_clear(extents->mount, &extents->extent_list, false); + kmem_free(extents->owner); +} + +/* + * Queue up the actual completion to a thread to avoid IRQ-safe locking for + * pagb_lock. + */ +static void +xfs_discard_endio( + struct bio *bio) +{ + struct xfs_busy_extents *extents = bio->bi_private; + + INIT_WORK(&extents->endio_work, xfs_discard_endio_work); + queue_work(xfs_discard_wq, &extents->endio_work); + bio_put(bio); +} + +/* + * Walk the discard list and issue discards on all the busy extents in the + * list. We plug and chain the bios so that we only need a single completion + * call to clear all the busy extents once the discards are complete. + */ +int +xfs_discard_extents( + struct xfs_mount *mp, + struct xfs_busy_extents *extents) +{ + struct xfs_extent_busy *busyp; + struct bio *bio = NULL; + struct blk_plug plug; + int error = 0; + + blk_start_plug(&plug); + list_for_each_entry(busyp, &extents->extent_list, list) { + trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, + busyp->length); + + error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, + XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), + XFS_FSB_TO_BB(mp, busyp->length), + GFP_NOFS, &bio); + if (error && error != -EOPNOTSUPP) { + xfs_info(mp, + "discard failed for extent [0x%llx,%u], error %d", + (unsigned long long)busyp->bno, + busyp->length, + error); + break; + } + } + + if (bio) { + bio->bi_private = extents; + bio->bi_end_io = xfs_discard_endio; + submit_bio(bio); + } else { + xfs_discard_endio_work(&extents->endio_work); + } + blk_finish_plug(&plug); + + return error; +} + + +static int +xfs_trim_gather_extents( struct xfs_perag *pag, xfs_daddr_t start, xfs_daddr_t end, xfs_daddr_t minlen, + struct xfs_alloc_rec_incore *tcur, + struct xfs_busy_extents *extents, uint64_t *blocks_trimmed) { struct xfs_mount *mp = pag->pag_mount; - struct block_device *bdev = mp->m_ddev_targp->bt_bdev; struct xfs_btree_cur *cur; struct xfs_buf *agbp; - struct xfs_agf *agf; int error; int i; + int batch = 100; /* * Force out the log. This means any transactions that might have freed @@ -45,20 +171,28 @@ xfs_trim_extents( error = xfs_alloc_read_agf(pag, NULL, 0, &agbp); if (error) return error; - agf = agbp->b_addr; cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT); /* - * Look up the longest btree in the AGF and start with it. + * Look up the extent length requested in the AGF and start with it. */ - error = xfs_alloc_lookup_ge(cur, 0, be32_to_cpu(agf->agf_longest), &i); + if (tcur->ar_startblock == NULLAGBLOCK) + error = xfs_alloc_lookup_ge(cur, 0, tcur->ar_blockcount, &i); + else + error = xfs_alloc_lookup_le(cur, tcur->ar_startblock, + tcur->ar_blockcount, &i); if (error) goto out_del_cursor; + if (i == 0) { + /* nothing of that length left in the AG, we are done */ + tcur->ar_blockcount = 0; + goto out_del_cursor; + } /* * Loop until we are done with all extents that are large - * enough to be worth discarding. + * enough to be worth discarding or we hit batch limits. */ while (i) { xfs_agblock_t fbno; @@ -73,7 +207,16 @@ xfs_trim_extents( error = -EFSCORRUPTED; break; } - ASSERT(flen <= be32_to_cpu(agf->agf_longest)); + + if (--batch <= 0) { + /* + * Update the cursor to point at this extent so we + * restart the next batch from this extent. + */ + tcur->ar_startblock = fbno; + tcur->ar_blockcount = flen; + break; + } /* * use daddr format for all range/len calculations as that is @@ -88,6 +231,7 @@ xfs_trim_extents( */ if (dlen < minlen) { trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen); + tcur->ar_blockcount = 0; break; } @@ -110,29 +254,103 @@ xfs_trim_extents( goto next_extent; } - trace_xfs_discard_extent(mp, pag->pag_agno, fbno, flen); - error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS); - if (error) - break; + xfs_extent_busy_insert_discard(pag, fbno, flen, + &extents->extent_list); *blocks_trimmed += flen; - next_extent: error = xfs_btree_decrement(cur, 0, &i); if (error) break; - if (fatal_signal_pending(current)) { - error = -ERESTARTSYS; - break; - } + /* + * If there's no more records in the tree, we are done. Set the + * cursor block count to 0 to indicate to the caller that there + * is no more extents to search. + */ + if (i == 0) + tcur->ar_blockcount = 0; } + /* + * If there was an error, release all the gathered busy extents because + * we aren't going to issue a discard on them any more. + */ + if (error) + xfs_extent_busy_clear(mp, &extents->extent_list, false); out_del_cursor: xfs_btree_del_cursor(cur, error); xfs_buf_relse(agbp); return error; } +static bool +xfs_trim_should_stop(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + +/* + * Iterate the free list gathering extents and discarding them. We need a cursor + * for the repeated iteration of gather/discard loop, so use the longest extent + * we found in the last batch as the key to start the next. + */ +static int +xfs_trim_extents( + struct xfs_perag *pag, + xfs_daddr_t start, + xfs_daddr_t end, + xfs_daddr_t minlen, + uint64_t *blocks_trimmed) +{ + struct xfs_alloc_rec_incore tcur = { + .ar_blockcount = pag->pagf_longest, + .ar_startblock = NULLAGBLOCK, + }; + int error = 0; + + do { + struct xfs_busy_extents *extents; + + extents = kzalloc(sizeof(*extents), GFP_KERNEL); + if (!extents) { + error = -ENOMEM; + break; + } + + extents->mount = pag->pag_mount; + extents->owner = extents; + INIT_LIST_HEAD(&extents->extent_list); + + error = xfs_trim_gather_extents(pag, start, end, minlen, + &tcur, extents, blocks_trimmed); + if (error) { + kfree(extents); + break; + } + + /* + * We hand the extent list to the discard function here so the + * discarded extents can be removed from the busy extent list. + * This allows the discards to run asynchronously with gathering + * the next round of extents to discard. + * + * However, we must ensure that we do not reference the extent + * list after this function call, as it may have been freed by + * the time control returns to us. + */ + error = xfs_discard_extents(pag->pag_mount, extents); + if (error) + break; + + if (xfs_trim_should_stop()) + break; + + } while (tcur.ar_blockcount != 0); + + return error; + +} + /* * trim a range of the filesystem. * @@ -195,12 +413,12 @@ xfs_ioc_trim( for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) { error = xfs_trim_extents(pag, start, end, minlen, &blocks_trimmed); - if (error) { + if (error) last_error = error; - if (error == -ERESTARTSYS) { - xfs_perag_rele(pag); - break; - } + + if (xfs_trim_should_stop()) { + xfs_perag_rele(pag); + break; } } diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h index de92d9cc958f..2b1a85223a56 100644 --- a/fs/xfs/xfs_discard.h +++ b/fs/xfs/xfs_discard.h @@ -3,8 +3,10 @@ #define XFS_DISCARD_H 1 struct fstrim_range; -struct list_head; +struct xfs_mount; +struct xfs_busy_extents; -extern int xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *); +int xfs_discard_extents(struct xfs_mount *mp, struct xfs_busy_extents *busy); +int xfs_ioc_trim(struct xfs_mount *mp, struct fstrim_range __user *fstrim); #endif /* XFS_DISCARD_H */ diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index f71ea786a6d2..7cd09c3a82cb 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -146,10 +146,18 @@ xfs_nfs_get_inode( return ERR_PTR(error); } - error = xfs_inode_reload_unlinked(ip); - if (error) { - xfs_irele(ip); - return ERR_PTR(error); + /* + * Reload the incore unlinked list to avoid failure in inodegc. + * Use an unlocked check here because unrecovered unlinked inodes + * should be somewhat rare. + */ + if (xfs_inode_unlinked_incomplete(ip)) { + error = xfs_inode_reload_unlinked(ip); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + xfs_irele(ip); + return ERR_PTR(error); + } } if (VFS_I(ip)->i_generation != generation) { diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 7c2fdc71e42d..9ecfdcdc752f 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -19,13 +19,13 @@ #include "xfs_log.h" #include "xfs_ag.h" -void -xfs_extent_busy_insert( - struct xfs_trans *tp, +static void +xfs_extent_busy_insert_list( struct xfs_perag *pag, xfs_agblock_t bno, xfs_extlen_t len, - unsigned int flags) + unsigned int flags, + struct list_head *busy_list) { struct xfs_extent_busy *new; struct xfs_extent_busy *busyp; @@ -40,7 +40,7 @@ xfs_extent_busy_insert( new->flags = flags; /* trace before insert to be able to see failed inserts */ - trace_xfs_extent_busy(tp->t_mountp, pag->pag_agno, bno, len); + trace_xfs_extent_busy(pag->pag_mount, pag->pag_agno, bno, len); spin_lock(&pag->pagb_lock); rbp = &pag->pagb_tree.rb_node; @@ -62,10 +62,33 @@ xfs_extent_busy_insert( rb_link_node(&new->rb_node, parent, rbp); rb_insert_color(&new->rb_node, &pag->pagb_tree); - list_add(&new->list, &tp->t_busy); + /* always process discard lists in fifo order */ + list_add_tail(&new->list, busy_list); spin_unlock(&pag->pagb_lock); } +void +xfs_extent_busy_insert( + struct xfs_trans *tp, + struct xfs_perag *pag, + xfs_agblock_t bno, + xfs_extlen_t len, + unsigned int flags) +{ + xfs_extent_busy_insert_list(pag, bno, len, flags, &tp->t_busy); +} + +void +xfs_extent_busy_insert_discard( + struct xfs_perag *pag, + xfs_agblock_t bno, + xfs_extlen_t len, + struct list_head *busy_list) +{ + xfs_extent_busy_insert_list(pag, bno, len, XFS_EXTENT_BUSY_DISCARDED, + busy_list); +} + /* * Search for a busy extent within the range of the extent we are about to * allocate. You need to be holding the busy extent tree lock when calling diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index c37bf87e6781..0639aab336f3 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -16,9 +16,6 @@ struct xfs_alloc_arg; /* * Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that * have been freed but whose transactions aren't committed to disk yet. - * - * Note that we use the transaction ID to record the transaction, not the - * transaction structure itself. See xfs_extent_busy_insert() for details. */ struct xfs_extent_busy { struct rb_node rb_node; /* ag by-bno indexed search tree */ @@ -31,11 +28,32 @@ struct xfs_extent_busy { #define XFS_EXTENT_BUSY_SKIP_DISCARD 0x02 /* do not discard */ }; +/* + * List used to track groups of related busy extents all the way through + * to discard completion. + */ +struct xfs_busy_extents { + struct xfs_mount *mount; + struct list_head extent_list; + struct work_struct endio_work; + + /* + * Owner is the object containing the struct xfs_busy_extents to free + * once the busy extents have been processed. If only the + * xfs_busy_extents object needs freeing, then point this at itself. + */ + void *owner; +}; + void xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_perag *pag, xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags); void +xfs_extent_busy_insert_discard(struct xfs_perag *pag, xfs_agblock_t bno, + xfs_extlen_t len, struct list_head *busy_list); + +void xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list, bool do_discard); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index f94f7b374041..36f5cf802c07 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -844,8 +844,8 @@ xfs_init_new_inode( ASSERT(ip->i_nblocks == 0); tv = inode_set_ctime_current(inode); - inode->i_mtime = tv; - inode->i_atime = tv; + inode_set_mtime_to_ts(inode, tv); + inode_set_atime_to_ts(inode, tv); ip->i_extsize = 0; ip->i_diflags = 0; @@ -1743,6 +1743,14 @@ xfs_inactive( truncate = 1; if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { + /* + * If this inode is being inactivated during a quotacheck and + * has not yet been scanned by quotacheck, we /must/ remove + * the dquots from the inode before inactivation changes the + * block and inode counts. Most probably this is a result of + * reloading the incore iunlinked list to purge unrecovered + * unlinked inodes. + */ xfs_qm_dqdetach(ip); } else { error = xfs_qm_dqattach(ip); @@ -3641,6 +3649,16 @@ xfs_inode_reload_unlinked_bucket( if (error) return error; + /* + * We've taken ILOCK_SHARED and the AGI buffer lock to stabilize the + * incore unlinked list pointers for this inode. Check once more to + * see if we raced with anyone else to reload the unlinked list. + */ + if (!xfs_inode_unlinked_incomplete(ip)) { + foundit = true; + goto out_agibp; + } + bucket = agino % XFS_AGI_UNLINKED_BUCKETS; agi = agibp->b_addr; @@ -3655,25 +3673,27 @@ xfs_inode_reload_unlinked_bucket( while (next_agino != NULLAGINO) { struct xfs_inode *next_ip = NULL; + /* Found this caller's inode, set its backlink. */ if (next_agino == agino) { - /* Found this inode, set its backlink. */ next_ip = ip; next_ip->i_prev_unlinked = prev_agino; foundit = true; + goto next_inode; } - if (!next_ip) { - /* Inode already in memory. */ - next_ip = xfs_iunlink_lookup(pag, next_agino); - } - if (!next_ip) { - /* Inode not in memory, reload. */ - error = xfs_iunlink_reload_next(tp, agibp, prev_agino, - next_agino); - if (error) - break; - next_ip = xfs_iunlink_lookup(pag, next_agino); - } + /* Try in-memory lookup first. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); + if (next_ip) + goto next_inode; + + /* Inode not in memory, try reloading it. */ + error = xfs_iunlink_reload_next(tp, agibp, prev_agino, + next_agino); + if (error) + break; + + /* Grab the reloaded inode. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); if (!next_ip) { /* No incore inode at all? We reloaded it... */ ASSERT(next_ip != NULL); @@ -3681,10 +3701,12 @@ xfs_inode_reload_unlinked_bucket( break; } +next_inode: prev_agino = next_agino; next_agino = next_ip->i_next_unlinked; } +out_agibp: xfs_trans_brelse(tp, agibp); /* Should have found this inode somewhere in the iunlinked bucket. */ if (!error && !foundit) diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 127b2410eb20..17c51804f9c6 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -526,8 +526,8 @@ xfs_inode_to_log_dinode( to->di_projid_hi = ip->i_projid >> 16; memset(to->di_pad3, 0, sizeof(to->di_pad3)); - to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode->i_atime); - to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode->i_mtime); + to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode_get_atime(inode)); + to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode_get_mtime(inode)); to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode_get_ctime(inode)); to->di_nlink = inode->i_nlink; to->di_gen = inode->i_generation; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 1c1e6171209d..fdfda4fba12b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -572,8 +572,8 @@ xfs_vn_getattr( stat->uid = vfsuid_into_kuid(vfsuid); stat->gid = vfsgid_into_kgid(vfsgid); stat->ino = ip->i_ino; - stat->atime = inode->i_atime; - stat->mtime = inode->i_mtime; + stat->atime = inode_get_atime(inode); + stat->mtime = inode_get_mtime(inode); stat->ctime = inode_get_ctime(inode); stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks); @@ -584,6 +584,11 @@ xfs_vn_getattr( } } + if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { + stat->change_cookie = inode_query_iversion(inode); + stat->result_mask |= STATX_CHANGE_COOKIE; + } + /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. @@ -1062,9 +1067,9 @@ xfs_vn_update_time( now = current_time(inode); if (flags & S_MTIME) - inode->i_mtime = now; + inode_set_mtime_to_ts(inode, now); if (flags & S_ATIME) - inode->i_atime = now; + inode_set_atime_to_ts(inode, now); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, log_flags); diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index ccf0c4ff4490..14462614fcc8 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -80,10 +80,12 @@ xfs_bulkstat_one_int( if (error) goto out; + /* Reload the incore unlinked list to avoid failure in inodegc. */ if (xfs_inode_unlinked_incomplete(ip)) { error = xfs_inode_reload_unlinked_bucket(tp, ip); if (error) { xfs_iunlock(ip, XFS_ILOCK_SHARED); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); xfs_irele(ip); return error; } @@ -105,12 +107,12 @@ xfs_bulkstat_one_int( buf->bs_size = ip->i_disk_size; buf->bs_nlink = inode->i_nlink; - buf->bs_atime = inode->i_atime.tv_sec; - buf->bs_atime_nsec = inode->i_atime.tv_nsec; - buf->bs_mtime = inode->i_mtime.tv_sec; - buf->bs_mtime_nsec = inode->i_mtime.tv_nsec; - buf->bs_ctime = inode_get_ctime(inode).tv_sec; - buf->bs_ctime_nsec = inode_get_ctime(inode).tv_nsec; + buf->bs_atime = inode_get_atime_sec(inode); + buf->bs_atime_nsec = inode_get_atime_nsec(inode); + buf->bs_mtime = inode_get_mtime_sec(inode); + buf->bs_mtime_nsec = inode_get_mtime_nsec(inode); + buf->bs_ctime = inode_get_ctime_sec(inode); + buf->bs_ctime_nsec = inode_get_ctime_nsec(inode); buf->bs_gen = inode->i_generation; buf->bs_mode = inode->i_mode; diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index ebc70aaa299c..67a99d94701e 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -16,8 +16,7 @@ #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" - -struct workqueue_struct *xfs_discard_wq; +#include "xfs_discard.h" /* * Allocate a new ticket. Failing to get a new ticket makes it really hard to @@ -103,7 +102,7 @@ xlog_cil_ctx_alloc(void) ctx = kmem_zalloc(sizeof(*ctx), KM_NOFS); INIT_LIST_HEAD(&ctx->committing); - INIT_LIST_HEAD(&ctx->busy_extents); + INIT_LIST_HEAD(&ctx->busy_extents.extent_list); INIT_LIST_HEAD(&ctx->log_items); INIT_LIST_HEAD(&ctx->lv_chain); INIT_WORK(&ctx->push_work, xlog_cil_push_work); @@ -132,7 +131,7 @@ xlog_cil_push_pcp_aggregate( if (!list_empty(&cilpcp->busy_extents)) { list_splice_init(&cilpcp->busy_extents, - &ctx->busy_extents); + &ctx->busy_extents.extent_list); } if (!list_empty(&cilpcp->log_items)) list_splice_init(&cilpcp->log_items, &ctx->log_items); @@ -708,76 +707,6 @@ xlog_cil_free_logvec( } } -static void -xlog_discard_endio_work( - struct work_struct *work) -{ - struct xfs_cil_ctx *ctx = - container_of(work, struct xfs_cil_ctx, discard_endio_work); - struct xfs_mount *mp = ctx->cil->xc_log->l_mp; - - xfs_extent_busy_clear(mp, &ctx->busy_extents, false); - kmem_free(ctx); -} - -/* - * Queue up the actual completion to a thread to avoid IRQ-safe locking for - * pagb_lock. Note that we need a unbounded workqueue, otherwise we might - * get the execution delayed up to 30 seconds for weird reasons. - */ -static void -xlog_discard_endio( - struct bio *bio) -{ - struct xfs_cil_ctx *ctx = bio->bi_private; - - INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work); - queue_work(xfs_discard_wq, &ctx->discard_endio_work); - bio_put(bio); -} - -static void -xlog_discard_busy_extents( - struct xfs_mount *mp, - struct xfs_cil_ctx *ctx) -{ - struct list_head *list = &ctx->busy_extents; - struct xfs_extent_busy *busyp; - struct bio *bio = NULL; - struct blk_plug plug; - int error = 0; - - ASSERT(xfs_has_discard(mp)); - - blk_start_plug(&plug); - list_for_each_entry(busyp, list, list) { - trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, - busyp->length); - - error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, - XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), - XFS_FSB_TO_BB(mp, busyp->length), - GFP_NOFS, &bio); - if (error && error != -EOPNOTSUPP) { - xfs_info(mp, - "discard failed for extent [0x%llx,%u], error %d", - (unsigned long long)busyp->bno, - busyp->length, - error); - break; - } - } - - if (bio) { - bio->bi_private = ctx; - bio->bi_end_io = xlog_discard_endio; - submit_bio(bio); - } else { - xlog_discard_endio_work(&ctx->discard_endio_work); - } - blk_finish_plug(&plug); -} - /* * Mark all items committed and clear busy extents. We free the log vector * chains in a separate pass so that we unpin the log items as quickly as @@ -807,8 +736,8 @@ xlog_cil_committed( xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain, ctx->start_lsn, abort); - xfs_extent_busy_sort(&ctx->busy_extents); - xfs_extent_busy_clear(mp, &ctx->busy_extents, + xfs_extent_busy_sort(&ctx->busy_extents.extent_list); + xfs_extent_busy_clear(mp, &ctx->busy_extents.extent_list, xfs_has_discard(mp) && !abort); spin_lock(&ctx->cil->xc_push_lock); @@ -817,10 +746,14 @@ xlog_cil_committed( xlog_cil_free_logvec(&ctx->lv_chain); - if (!list_empty(&ctx->busy_extents)) - xlog_discard_busy_extents(mp, ctx); - else - kmem_free(ctx); + if (!list_empty(&ctx->busy_extents.extent_list)) { + ctx->busy_extents.mount = mp; + ctx->busy_extents.owner = ctx; + xfs_discard_extents(mp, &ctx->busy_extents); + return; + } + + kmem_free(ctx); } void diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index af87648331d5..fa3ad1d7b31c 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -6,6 +6,8 @@ #ifndef __XFS_LOG_PRIV_H__ #define __XFS_LOG_PRIV_H__ +#include "xfs_extent_busy.h" /* for struct xfs_busy_extents */ + struct xfs_buf; struct xlog; struct xlog_ticket; @@ -223,12 +225,11 @@ struct xfs_cil_ctx { struct xlog_in_core *commit_iclog; struct xlog_ticket *ticket; /* chkpt ticket */ atomic_t space_used; /* aggregate size of regions */ - struct list_head busy_extents; /* busy extents in chkpt */ + struct xfs_busy_extents busy_extents; struct list_head log_items; /* log items in chkpt */ struct list_head lv_chain; /* logvecs being pushed */ struct list_head iclog_entry; struct list_head committing; /* ctx committing list */ - struct work_struct discard_endio_work; struct work_struct push_work; atomic_t order_id; diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 4a9bbd3fe120..a7daa522e00f 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -126,8 +126,8 @@ xfs_dax_notify_ddev_failure( struct xfs_rmap_irec ri_low = { }; struct xfs_rmap_irec ri_high; struct xfs_agf *agf; - xfs_agblock_t agend; struct xfs_perag *pag; + xfs_agblock_t range_agend; pag = xfs_perag_get(mp, agno); error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); @@ -148,10 +148,10 @@ xfs_dax_notify_ddev_failure( ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); agf = agf_bp->b_addr; - agend = min(be32_to_cpu(agf->agf_length), + range_agend = min(be32_to_cpu(agf->agf_length) - 1, ri_high.rm_startblock); notify.startblock = ri_low.rm_startblock; - notify.blockcount = agend - ri_low.rm_startblock; + notify.blockcount = range_agend + 1 - ri_low.rm_startblock; error = xfs_rmap_query_range(cur, &ri_low, &ri_high, xfs_dax_failure_fn, ¬ify); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 7256090c3895..086e78a6143a 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1160,9 +1160,18 @@ xfs_qm_dqusage_adjust( if (error) return error; - error = xfs_inode_reload_unlinked(ip); - if (error) - goto error0; + /* + * Reload the incore unlinked list to avoid failure in inodegc. + * Use an unlocked check here because unrecovered unlinked inodes + * should be somewhat rare. + */ + if (xfs_inode_unlinked_incomplete(ip)) { + error = xfs_inode_reload_unlinked(ip); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + goto error0; + } + } ASSERT(ip->i_delayed_blks == 0); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 16534e9873f6..2e1a4e5cd03d 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1420,25 +1420,26 @@ xfs_rtunmount_inodes( */ int /* error */ xfs_rtpick_extent( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_extlen_t len, /* allocation length (rtextents) */ - xfs_rtblock_t *pick) /* result rt extent */ -{ - xfs_rtblock_t b; /* result block */ - int log2; /* log of sequence number */ - uint64_t resid; /* residual after log removed */ - uint64_t seq; /* sequence number of file creation */ - uint64_t *seqp; /* pointer to seqno in inode */ + xfs_mount_t *mp, /* file system mount point */ + xfs_trans_t *tp, /* transaction pointer */ + xfs_extlen_t len, /* allocation length (rtextents) */ + xfs_rtblock_t *pick) /* result rt extent */ + { + xfs_rtblock_t b; /* result block */ + int log2; /* log of sequence number */ + uint64_t resid; /* residual after log removed */ + uint64_t seq; /* sequence number of file creation */ + struct timespec64 ts; /* temporary timespec64 storage */ ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL)); - seqp = (uint64_t *)&VFS_I(mp->m_rbmip)->i_atime; if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) { mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM; - *seqp = 0; + seq = 0; + } else { + ts = inode_get_atime(VFS_I(mp->m_rbmip)); + seq = (uint64_t)ts.tv_sec; } - seq = *seqp; if ((log2 = xfs_highbit64(seq)) == -1) b = 0; else { @@ -1450,7 +1451,8 @@ xfs_rtpick_extent( if (b + len > mp->m_sb.sb_rextents) b = mp->m_sb.sb_rextents - len; } - *seqp = seq + 1; + ts.tv_sec = (time64_t)seq + 1; + inode_set_atime_to_ts(VFS_I(mp->m_rbmip), ts); xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); *pick = b; return 0; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 819a3568b28f..f0ae07828153 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -361,14 +361,15 @@ STATIC int xfs_blkdev_get( xfs_mount_t *mp, const char *name, - struct block_device **bdevp) + struct bdev_handle **handlep) { int error = 0; - *bdevp = blkdev_get_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, - mp->m_super, &fs_holder_ops); - if (IS_ERR(*bdevp)) { - error = PTR_ERR(*bdevp); + *handlep = bdev_open_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, + mp->m_super, &fs_holder_ops); + if (IS_ERR(*handlep)) { + error = PTR_ERR(*handlep); + *handlep = NULL; xfs_warn(mp, "Invalid device [%s], error=%d", name, error); } @@ -433,7 +434,7 @@ xfs_open_devices( { struct super_block *sb = mp->m_super; struct block_device *ddev = sb->s_bdev; - struct block_device *logdev = NULL, *rtdev = NULL; + struct bdev_handle *logdev_handle = NULL, *rtdev_handle = NULL; int error; /* @@ -446,17 +447,19 @@ xfs_open_devices( * Open real time and log devices - order is important. */ if (mp->m_logname) { - error = xfs_blkdev_get(mp, mp->m_logname, &logdev); + error = xfs_blkdev_get(mp, mp->m_logname, &logdev_handle); if (error) goto out_relock; } if (mp->m_rtname) { - error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev); + error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev_handle); if (error) goto out_close_logdev; - if (rtdev == ddev || rtdev == logdev) { + if (rtdev_handle->bdev == ddev || + (logdev_handle && + rtdev_handle->bdev == logdev_handle->bdev)) { xfs_warn(mp, "Cannot mount filesystem with identical rtdev and ddev/logdev."); error = -EINVAL; @@ -468,22 +471,25 @@ xfs_open_devices( * Setup xfs_mount buffer target pointers */ error = -ENOMEM; - mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev); + mp->m_ddev_targp = xfs_alloc_buftarg(mp, sb->s_bdev_handle); if (!mp->m_ddev_targp) goto out_close_rtdev; - if (rtdev) { - mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev); + if (rtdev_handle) { + mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev_handle); if (!mp->m_rtdev_targp) goto out_free_ddev_targ; } - if (logdev && logdev != ddev) { - mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev); + if (logdev_handle && logdev_handle->bdev != ddev) { + mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev_handle); if (!mp->m_logdev_targp) goto out_free_rtdev_targ; } else { mp->m_logdev_targp = mp->m_ddev_targp; + /* Handle won't be used, drop it */ + if (logdev_handle) + bdev_release(logdev_handle); } error = 0; @@ -497,11 +503,11 @@ out_relock: out_free_ddev_targ: xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: - if (rtdev) - blkdev_put(rtdev, sb); + if (rtdev_handle) + bdev_release(rtdev_handle); out_close_logdev: - if (logdev && logdev != ddev) - blkdev_put(logdev, sb); + if (logdev_handle) + bdev_release(logdev_handle); goto out_relock; } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index a3975f325f4e..987843f84d03 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -186,7 +186,7 @@ static const struct xattr_handler xfs_xattr_security_handler = { .set = xfs_xattr_set, }; -const struct xattr_handler *xfs_xattr_handlers[] = { +const struct xattr_handler * const xfs_xattr_handlers[] = { &xfs_xattr_user_handler, &xfs_xattr_trusted_handler, &xfs_xattr_security_handler, diff --git a/fs/xfs/xfs_xattr.h b/fs/xfs/xfs_xattr.h index 2b09133b1b9b..cec766cad26c 100644 --- a/fs/xfs/xfs_xattr.h +++ b/fs/xfs/xfs_xattr.h @@ -8,6 +8,6 @@ int xfs_attr_change(struct xfs_da_args *args); -extern const struct xattr_handler *xfs_xattr_handlers[]; +extern const struct xattr_handler * const xfs_xattr_handlers[]; #endif /* __XFS_XATTR_H__ */ diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 9d1a9808fbbb..e6a75401677d 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -658,8 +658,8 @@ static struct inode *zonefs_get_file_inode(struct inode *dir, inode->i_ino = ino; inode->i_mode = z->z_mode; - inode->i_mtime = inode->i_atime = inode_set_ctime_to_ts(inode, - inode_get_ctime(dir)); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, inode_get_ctime(dir)))); inode->i_uid = z->z_uid; inode->i_gid = z->z_gid; inode->i_size = z->z_wpoffset; @@ -695,8 +695,8 @@ static struct inode *zonefs_get_zgroup_inode(struct super_block *sb, inode->i_ino = ino; inode_init_owner(&nop_mnt_idmap, inode, root, S_IFDIR | 0555); inode->i_size = sbi->s_zgroup[ztype].g_nr_zones; - inode->i_mtime = inode->i_atime = inode_set_ctime_to_ts(inode, - inode_get_ctime(root)); + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime_to_ts(inode, inode_get_ctime(root)))); inode->i_private = &sbi->s_zgroup[ztype]; set_nlink(inode, 2); @@ -1319,7 +1319,7 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent) inode->i_ino = bdev_nr_zones(sb->s_bdev); inode->i_mode = S_IFDIR | 0555; - inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &zonefs_dir_inode_operations; inode->i_fop = &zonefs_dir_operations; inode->i_size = 2; |