diff options
Diffstat (limited to 'fs')
76 files changed, 1480 insertions, 776 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 77e9c4387c1d..a020a8f00a1a 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -438,8 +438,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, v9ses->flags &= ~V9FS_ACCESS_MASK; v9ses->flags |= V9FS_ACCESS_USER; } - /*FIXME !! */ - /* for legacy mode, fall back to V9FS_ACCESS_ANY */ + /* FIXME: for legacy mode, fall back to V9FS_ACCESS_ANY */ if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) && ((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) { @@ -450,7 +449,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, if (!v9fs_proto_dotl(v9ses) || !((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) { /* - * We support ACL checks on clinet only if the protocol is + * We support ACL checks on client only if the protocol is * 9P2000.L and access is V9FS_ACCESS_CLIENT. */ v9ses->flags &= ~V9FS_ACL_MASK; @@ -561,7 +560,7 @@ static ssize_t caches_show(struct kobject *kobj, spin_lock(&v9fs_sessionlist_lock); list_for_each_entry(v9ses, &v9fs_sessionlist, slist) { if (v9ses->cachetag) { - n = snprintf(buf, limit, "%s\n", v9ses->cachetag); + n = snprintf(buf + count, limit, "%s\n", v9ses->cachetag); if (n < 0) { count = n; break; @@ -597,13 +596,16 @@ static const struct attribute_group v9fs_attr_group = { static int __init v9fs_sysfs_init(void) { + int ret; + v9fs_kobj = kobject_create_and_add("9p", fs_kobj); if (!v9fs_kobj) return -ENOMEM; - if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) { + ret = sysfs_create_group(v9fs_kobj, &v9fs_attr_group); + if (ret) { kobject_put(v9fs_kobj); - return -ENOMEM; + return ret; } return 0; @@ -669,7 +671,7 @@ static int __init init_v9fs(void) int err; pr_info("Installing v9fs 9p2000 file system support\n"); - /* TODO: Setup list of registered trasnport modules */ + /* TODO: Setup list of registered transport modules */ err = v9fs_init_inode_cache(); if (err < 0) { diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index 04795508a795..f3248a3e5402 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -66,6 +66,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct p9_fid *fid; struct inode *inode; struct v9fs_inode *v9inode; + unsigned int cached; if (flags & LOOKUP_RCU) return -ECHILD; @@ -75,13 +76,22 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) goto out_valid; v9inode = V9FS_I(inode); - if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); + + cached = v9ses->cache & (CACHE_META | CACHE_LOOSE); + + if (!cached || v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { int retval; struct v9fs_session_info *v9ses; fid = v9fs_fid_lookup(dentry); - if (IS_ERR(fid)) + if (IS_ERR(fid)) { + p9_debug( + P9_DEBUG_VFS, + "v9fs_fid_lookup: dentry = %pd (%p), got error %pe\n", + dentry, dentry, fid); return PTR_ERR(fid); + } v9ses = v9fs_inode2v9ses(inode); if (v9fs_proto_dotl(v9ses)) @@ -90,12 +100,25 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) retval = v9fs_refresh_inode(fid, inode); p9_fid_put(fid); - if (retval == -ENOENT) + if (retval == -ENOENT) { + p9_debug(P9_DEBUG_VFS, "dentry: %pd (%p) invalidated due to ENOENT\n", + dentry, dentry); + return 0; + } + if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { + p9_debug(P9_DEBUG_VFS, "dentry: %pd (%p) invalidated due to type change\n", + dentry, dentry); return 0; - if (retval < 0) + } + if (retval < 0) { + p9_debug(P9_DEBUG_VFS, + "refresh inode: dentry = %pd (%p), got error %pe\n", + dentry, dentry, ERR_PTR(retval)); return retval; + } } out_valid: + p9_debug(P9_DEBUG_VFS, "dentry: %pd (%p) is valid\n", dentry, dentry); return 1; } @@ -127,6 +150,8 @@ const struct dentry_operations v9fs_cached_dentry_operations = { }; const struct dentry_operations v9fs_dentry_operations = { + .d_revalidate = v9fs_lookup_revalidate, + .d_weak_revalidate = __v9fs_lookup_revalidate, .d_release = v9fs_dentry_release, .d_unalias_trylock = v9fs_dentry_unalias_trylock, .d_unalias_unlock = v9fs_dentry_unalias_unlock, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index d0c77ec31b1d..69f378a83775 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1339,8 +1339,14 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) * Don't update inode if the file type is different */ umode = p9mode2unixmode(v9ses, st, &rdev); - if (inode_wrong_type(inode, umode)) + if (inode_wrong_type(inode, umode)) { + /* + * Do this as a way of letting the caller know the inode should not + * be reused + */ + v9fs_invalidate_inode_attr(inode); goto out; + } /* * We don't want to refresh inode->i_size, diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index be297e335468..0b404e8484d2 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -897,8 +897,14 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) /* * Don't update inode if the file type is different */ - if (inode_wrong_type(inode, st->st_mode)) + if (inode_wrong_type(inode, st->st_mode)) { + /* + * Do this as a way of letting the caller know the inode should not + * be reused + */ + v9fs_invalidate_inode_attr(inode); goto out; + } /* * We don't want to refresh inode->i_size, diff --git a/fs/attr.c b/fs/attr.c index 5425c1dbbff9..795f231d00e8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -286,20 +286,12 @@ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr) unsigned int ia_valid = attr->ia_valid; struct timespec64 now; - if (ia_valid & ATTR_CTIME) { - /* - * In the case of an update for a write delegation, we must respect - * the value in ia_ctime and not use the current time. - */ - if (ia_valid & ATTR_DELEG) - now = inode_set_ctime_deleg(inode, attr->ia_ctime); - else - now = inode_set_ctime_current(inode); - } else { - /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */ - WARN_ON_ONCE(ia_valid & ATTR_MTIME); + if (ia_valid & ATTR_CTIME_SET) + now = inode_set_ctime_deleg(inode, attr->ia_ctime); + else if (ia_valid & ATTR_CTIME) + now = inode_set_ctime_current(inode); + else now = current_time(inode); - } if (ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); @@ -359,12 +351,11 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, attr->ia_mtime); - if (ia_valid & ATTR_CTIME) { - if (ia_valid & ATTR_DELEG) - inode_set_ctime_deleg(inode, attr->ia_ctime); - else - inode_set_ctime_to_ts(inode, attr->ia_ctime); - } + + if (ia_valid & ATTR_CTIME_SET) + inode_set_ctime_deleg(inode, attr->ia_ctime); + else if (ia_valid & ATTR_CTIME) + inode_set_ctime_to_ts(inode, attr->ia_ctime); } EXPORT_SYMBOL(setattr_copy); @@ -463,15 +454,18 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, now = current_time(inode); - attr->ia_ctime = now; - if (!(ia_valid & ATTR_ATIME_SET)) - attr->ia_atime = now; - else + if (ia_valid & ATTR_ATIME_SET) attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); - if (!(ia_valid & ATTR_MTIME_SET)) - attr->ia_mtime = now; else + attr->ia_atime = now; + if (ia_valid & ATTR_CTIME_SET) + attr->ia_ctime = timestamp_truncate(attr->ia_ctime, inode); + else + attr->ia_ctime = now; + if (ia_valid & ATTR_MTIME_SET) attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); + else + attr->ia_mtime = now; if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ebbf55f8864b..0aa7e5d1b05f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3397,7 +3397,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (fs_info->sectorsize > PAGE_SIZE) btrfs_warn(fs_info, - "support for block size %u with page size %zu is experimental, some features may be missing", + "support for block size %u with page size %lu is experimental, some features may be missing", fs_info->sectorsize, PAGE_SIZE); /* * Handle the space caching options appropriately now that we have the diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index d062ac521051..230d9326b685 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -23,7 +23,11 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, int type; if (parent && (len < BTRFS_FID_SIZE_CONNECTABLE)) { - *max_len = BTRFS_FID_SIZE_CONNECTABLE; + if (btrfs_root_id(BTRFS_I(inode)->root) != + btrfs_root_id(BTRFS_I(parent)->root)) + *max_len = BTRFS_FID_SIZE_CONNECTABLE_ROOT; + else + *max_len = BTRFS_FID_SIZE_CONNECTABLE; return FILEID_INVALID; } else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) { *max_len = BTRFS_FID_SIZE_NON_CONNECTABLE; @@ -45,6 +49,8 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, parent_root_id = btrfs_root_id(BTRFS_I(parent)->root); if (parent_root_id != fid->root_objectid) { + if (*max_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) + return FILEID_INVALID; fid->parent_root_objectid = parent_root_id; len = BTRFS_FID_SIZE_CONNECTABLE_ROOT; type = FILEID_BTRFS_WITH_PARENT_ROOT; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 32973c62c1a2..d18c0eaef9b7 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1260,8 +1260,7 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, spin_unlock(&fsc->async_unlink_conflict_lock); spin_lock(&dentry->d_lock); - di->flags &= ~CEPH_DENTRY_ASYNC_UNLINK; - wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_UNLINK_BIT); + clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_UNLINK_BIT, &di->flags); spin_unlock(&dentry->d_lock); synchronize_rcu(); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 978acd3d4b32..99b30f784ee2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -579,8 +579,7 @@ static void wake_async_create_waiters(struct inode *inode, spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { - ci->i_ceph_flags &= ~CEPH_I_ASYNC_CREATE; - wake_up_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT); + clear_and_wake_up_bit(CEPH_ASYNC_CREATE_BIT, &ci->i_ceph_flags); if (ci->i_ceph_flags & CEPH_I_ASYNC_CHECK_CAPS) { ci->i_ceph_flags &= ~CEPH_I_ASYNC_CHECK_CAPS; @@ -762,8 +761,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode, } spin_lock(&dentry->d_lock); - di->flags &= ~CEPH_DENTRY_ASYNC_CREATE; - wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT); + clear_and_wake_up_bit(CEPH_DENTRY_ASYNC_CREATE_BIT, &di->flags); spin_unlock(&dentry->d_lock); return ret; @@ -2121,10 +2119,10 @@ again: if (ceph_inode_is_shutdown(inode)) return -ESTALE; - if (direct_lock) - ceph_start_io_direct(inode); - else - ceph_start_io_read(inode); + ret = direct_lock ? ceph_start_io_direct(inode) : + ceph_start_io_read(inode); + if (ret) + return ret; if (!(fi->flags & CEPH_F_SYNC) && !direct_lock) want |= CEPH_CAP_FILE_CACHE; @@ -2277,7 +2275,9 @@ static ssize_t ceph_splice_read(struct file *in, loff_t *ppos, (fi->flags & CEPH_F_SYNC)) return copy_splice_read(in, ppos, pipe, len, flags); - ceph_start_io_read(inode); + ret = ceph_start_io_read(inode); + if (ret) + return ret; want = CEPH_CAP_FILE_CACHE; if (fi->fmode & CEPH_FILE_MODE_LAZY) @@ -2356,10 +2356,10 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) direct_lock = true; retry_snap: - if (direct_lock) - ceph_start_io_direct(inode); - else - ceph_start_io_write(inode); + err = direct_lock ? ceph_start_io_direct(inode) : + ceph_start_io_write(inode); + if (err) + goto out_unlocked; if (iocb->ki_flags & IOCB_APPEND) { err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false); @@ -2878,7 +2878,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off struct ceph_object_id src_oid, dst_oid; struct ceph_osd_client *osdc; struct ceph_osd_request *req; - size_t bytes = 0; + ssize_t bytes = 0; u64 src_objnum, src_objoff, dst_objnum, dst_objoff; u32 src_objlen, dst_objlen; u32 object_size = src_ci->i_layout.object_size; @@ -2928,7 +2928,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off "OSDs don't support copy-from2; disabling copy offload\n"); } doutc(cl, "returned %d\n", ret); - if (!bytes) + if (bytes <= 0) bytes = ret; goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 949f0badc944..a6e260d9e420 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1794,6 +1794,11 @@ retry_lookup: goto done; } + if (unlikely(!in)) { + err = -EINVAL; + goto done; + } + /* attach proper inode */ if (d_really_is_negative(dn)) { ceph_dir_clear_ordered(dir); @@ -1829,6 +1834,12 @@ retry_lookup: doutc(cl, " linking snapped dir %p to dn %p\n", in, req->r_dentry); ceph_dir_clear_ordered(dir); + + if (unlikely(!in)) { + err = -EINVAL; + goto done; + } + ihold(in); err = splice_dentry(&req->r_dentry, in); if (err < 0) diff --git a/fs/ceph/io.c b/fs/ceph/io.c index c456509b31c3..2d10f49c93a9 100644 --- a/fs/ceph/io.c +++ b/fs/ceph/io.c @@ -21,14 +21,23 @@ /* Call with exclusively locked inode->i_rwsem */ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode) { + bool is_odirect; + lockdep_assert_held_write(&inode->i_rwsem); - if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) { - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags &= ~CEPH_I_ODIRECT; - spin_unlock(&ci->i_ceph_lock); - inode_dio_wait(inode); + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + if (is_odirect) { + clear_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags); + /* ensure modified bit is visible */ + smp_mb__after_atomic(); } + spin_unlock(&ci->i_ceph_lock); + + if (is_odirect) + inode_dio_wait(inode); } /** @@ -47,20 +56,35 @@ static void ceph_block_o_direct(struct ceph_inode_info *ci, struct inode *inode) * Note that buffered writes and truncates both take a write lock on * inode->i_rwsem, meaning that those are serialised w.r.t. the reads. */ -void -ceph_start_io_read(struct inode *inode) +int ceph_start_io_read(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); + bool is_odirect; + int err; /* Be an optimist! */ - down_read(&inode->i_rwsem); - if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) - return; + err = down_read_killable(&inode->i_rwsem); + if (err) + return err; + + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + spin_unlock(&ci->i_ceph_lock); + if (!is_odirect) + return 0; up_read(&inode->i_rwsem); + /* Slow path.... */ - down_write(&inode->i_rwsem); + err = down_write_killable(&inode->i_rwsem); + if (err) + return err; + ceph_block_o_direct(ci, inode); downgrade_write(&inode->i_rwsem); + + return 0; } /** @@ -83,11 +107,12 @@ ceph_end_io_read(struct inode *inode) * Declare that a buffered write operation is about to start, and ensure * that we block all direct I/O. */ -void -ceph_start_io_write(struct inode *inode) +int ceph_start_io_write(struct inode *inode) { - down_write(&inode->i_rwsem); - ceph_block_o_direct(ceph_inode(inode), inode); + int err = down_write_killable(&inode->i_rwsem); + if (!err) + ceph_block_o_direct(ceph_inode(inode), inode); + return err; } /** @@ -106,12 +131,22 @@ ceph_end_io_write(struct inode *inode) /* Call with exclusively locked inode->i_rwsem */ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode) { + bool is_odirect; + lockdep_assert_held_write(&inode->i_rwsem); - if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT)) { - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags |= CEPH_I_ODIRECT; - spin_unlock(&ci->i_ceph_lock); + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + if (!is_odirect) { + set_bit(CEPH_I_ODIRECT_BIT, &ci->i_ceph_flags); + /* ensure modified bit is visible */ + smp_mb__after_atomic(); + } + spin_unlock(&ci->i_ceph_lock); + + if (!is_odirect) { /* FIXME: unmap_mapping_range? */ filemap_write_and_wait(inode->i_mapping); } @@ -133,20 +168,35 @@ static void ceph_block_buffered(struct ceph_inode_info *ci, struct inode *inode) * Note that buffered writes and truncates both take a write lock on * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT. */ -void -ceph_start_io_direct(struct inode *inode) +int ceph_start_io_direct(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); + bool is_odirect; + int err; /* Be an optimist! */ - down_read(&inode->i_rwsem); - if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT) - return; + err = down_read_killable(&inode->i_rwsem); + if (err) + return err; + + spin_lock(&ci->i_ceph_lock); + /* ensure that bit state is consistent */ + smp_mb__before_atomic(); + is_odirect = READ_ONCE(ci->i_ceph_flags) & CEPH_I_ODIRECT; + spin_unlock(&ci->i_ceph_lock); + if (is_odirect) + return 0; up_read(&inode->i_rwsem); + /* Slow path.... */ - down_write(&inode->i_rwsem); + err = down_write_killable(&inode->i_rwsem); + if (err) + return err; + ceph_block_buffered(ci, inode); downgrade_write(&inode->i_rwsem); + + return 0; } /** diff --git a/fs/ceph/io.h b/fs/ceph/io.h index fa594cd77348..79029825e8b8 100644 --- a/fs/ceph/io.h +++ b/fs/ceph/io.h @@ -2,11 +2,13 @@ #ifndef _FS_CEPH_IO_H #define _FS_CEPH_IO_H -void ceph_start_io_read(struct inode *inode); +#include <linux/compiler_attributes.h> + +int __must_check ceph_start_io_read(struct inode *inode); void ceph_end_io_read(struct inode *inode); -void ceph_start_io_write(struct inode *inode); +int __must_check ceph_start_io_write(struct inode *inode); void ceph_end_io_write(struct inode *inode); -void ceph_start_io_direct(struct inode *inode); +int __must_check ceph_start_io_direct(struct inode *inode); void ceph_end_io_direct(struct inode *inode); #endif /* FS_CEPH_IO_H */ diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index e861de3c79b9..15cde055f3da 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -246,21 +246,28 @@ static long ceph_ioctl_lazyio(struct file *file) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc; struct ceph_client *cl = mdsc->fsc->client; + bool is_file_already_lazy = false; + spin_lock(&ci->i_ceph_lock); if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) { - spin_lock(&ci->i_ceph_lock); fi->fmode |= CEPH_FILE_MODE_LAZY; ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++; __ceph_touch_fmode(ci, mdsc, fi->fmode); - spin_unlock(&ci->i_ceph_lock); + } else { + is_file_already_lazy = true; + } + spin_unlock(&ci->i_ceph_lock); + + if (is_file_already_lazy) { + doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode, + ceph_vinop(inode)); + } else { doutc(cl, "file %p %p %llx.%llx marked lazy\n", file, inode, ceph_vinop(inode)); ceph_check_caps(ci, 0); - } else { - doutc(cl, "file %p %p %llx.%llx already lazy\n", file, inode, - ceph_vinop(inode)); } + return 0; } diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index ebf4ac0055dd..dd764f9c64b9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -221,7 +221,10 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, if (err && err != -ERESTARTSYS) return err; - wait_for_completion_killable(&req->r_safe_completion); + err = wait_for_completion_killable(&req->r_safe_completion); + if (err) + return err; + return 0; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 73da2648fa0f..1740047aef0f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -979,14 +979,15 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, if (mds >= mdsc->max_sessions) { int newmax = 1 << get_count_order(mds + 1); struct ceph_mds_session **sa; + size_t ptr_size = sizeof(struct ceph_mds_session *); doutc(cl, "realloc to %d\n", newmax); - sa = kcalloc(newmax, sizeof(void *), GFP_NOFS); + sa = kcalloc(newmax, ptr_size, GFP_NOFS); if (!sa) goto fail_realloc; if (mdsc->sessions) { memcpy(sa, mdsc->sessions, - mdsc->max_sessions * sizeof(void *)); + mdsc->max_sessions * ptr_size); kfree(mdsc->sessions); } mdsc->sessions = sa; @@ -2532,6 +2533,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, struct ceph_mount_options *opt = req->r_mdsc->fsc->mount_options; size_t size = sizeof(struct ceph_mds_reply_dir_entry); unsigned int num_entries; + u64 bytes_count; int order; spin_lock(&ci->i_ceph_lock); @@ -2540,7 +2542,11 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, num_entries = max(num_entries, 1U); num_entries = min(num_entries, opt->max_readdir); - order = get_order(size * num_entries); + bytes_count = (u64)size * num_entries; + if (unlikely(bytes_count > ULONG_MAX)) + bytes_count = ULONG_MAX; + + order = get_order((unsigned long)bytes_count); while (order >= 0) { rinfo->dir_entries = (void*)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | @@ -2550,7 +2556,7 @@ int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, break; order--; } - if (!rinfo->dir_entries) + if (!rinfo->dir_entries || unlikely(order < 0)) return -ENOMEM; num_entries = (PAGE_SIZE << order) / size; @@ -5649,11 +5655,19 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, u32 caller_uid = from_kuid(&init_user_ns, cred->fsuid); u32 caller_gid = from_kgid(&init_user_ns, cred->fsgid); struct ceph_client *cl = mdsc->fsc->client; + const char *fs_name = mdsc->fsc->mount_options->mds_namespace; const char *spath = mdsc->fsc->mount_options->server_path; bool gid_matched = false; u32 gid, tlen, len; int i, j; + doutc(cl, "fsname check fs_name=%s match.fs_name=%s\n", + fs_name, auth->match.fs_name ? auth->match.fs_name : ""); + if (auth->match.fs_name && strcmp(auth->match.fs_name, fs_name)) { + /* fsname mismatch, try next one */ + return 0; + } + doutc(cl, "match.uid %lld\n", auth->match.uid); if (auth->match.uid != MDS_AUTH_UID_ANY) { if (auth->match.uid != caller_uid) diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 8109aba66e02..2c7b151a7c95 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -353,10 +353,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, __decode_and_drop_type(p, end, u8, bad_ext); } if (mdsmap_ev >= 8) { + u32 fsname_len; /* enabled */ ceph_decode_8_safe(p, end, m->m_enabled, bad_ext); /* fs_name */ - ceph_decode_skip_string(p, end, bad_ext); + ceph_decode_32_safe(p, end, fsname_len, bad_ext); + + /* validate fsname against mds_namespace */ + if (!namespace_equals(mdsc->fsc->mount_options, *p, + fsname_len)) { + pr_warn_client(cl, "fsname %*pE doesn't match mds_namespace %s\n", + (int)fsname_len, (char *)*p, + mdsc->fsc->mount_options->mds_namespace); + goto bad; + } + /* skip fsname after validation */ + ceph_decode_skip_n(p, end, fsname_len, bad); } /* damaged */ if (mdsmap_ev >= 9) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index db6c2db68f96..ad0cf177e75a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -246,20 +246,6 @@ static void canonicalize_path(char *path) path[j] = '\0'; } -/* - * Check if the mds namespace in ceph_mount_options matches - * the passed in namespace string. First time match (when - * ->mds_namespace is NULL) is treated specially, since - * ->mds_namespace needs to be initialized by the caller. - */ -static int namespace_equals(struct ceph_mount_options *fsopt, - const char *namespace, size_t len) -{ - return !(fsopt->mds_namespace && - (strlen(fsopt->mds_namespace) != len || - strncmp(fsopt->mds_namespace, namespace, len))); -} - static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end, struct fs_context *fc) { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 25d8bacbcf44..a1f781c46b41 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -104,6 +104,20 @@ struct ceph_mount_options { struct fscrypt_dummy_policy dummy_enc_policy; }; +/* + * Check if the mds namespace in ceph_mount_options matches + * the passed in namespace string. First time match (when + * ->mds_namespace is NULL) is treated specially, since + * ->mds_namespace needs to be initialized by the caller. + */ +static inline int namespace_equals(struct ceph_mount_options *fsopt, + const char *namespace, size_t len) +{ + return !(fsopt->mds_namespace && + (strlen(fsopt->mds_namespace) != len || + strncmp(fsopt->mds_namespace, namespace, len))); +} + /* mount state */ enum { CEPH_MOUNT_MOUNTING, @@ -639,7 +653,8 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */ #define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */ #define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */ -#define CEPH_I_ODIRECT (1 << 11) /* inode in direct I/O mode */ +#define CEPH_I_ODIRECT_BIT (11) /* inode in direct I/O mode */ +#define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) #define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) #define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index b3e9b7bd7978..a0e66bc10093 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -280,9 +280,16 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, bh, is_metadata, inode->i_mode, test_opt(inode->i_sb, DATA_FLAGS)); - /* In the no journal case, we can just do a bforget and return */ + /* + * In the no journal case, we should wait for the ongoing buffer + * to complete and do a forget. + */ if (!ext4_handle_valid(handle)) { - bforget(bh); + if (bh) { + clear_buffer_dirty(bh); + wait_on_buffer(bh); + __bforget(bh); + } return 0; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f9e4ac87211e..e99306a8f47c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5319,6 +5319,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, } ei->i_flags = le32_to_cpu(raw_inode->i_flags); ext4_set_inode_flags(inode, true); + /* Detect invalid flag combination - can't have both inline data and extents */ + if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + ext4_error_inode(inode, function, line, 0, + "inode has both inline data and extents flags"); + ret = -EFSCORRUPTED; + goto bad_inode; + } inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 33c3a89396b1..82d5e7501455 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -513,7 +513,7 @@ void ext4_release_orphan_info(struct super_block *sb) return; for (i = 0; i < oi->of_blocks; i++) brelse(oi->of_binfo[i].ob_bh); - kfree(oi->of_binfo); + kvfree(oi->of_binfo); } static struct ext4_orphan_block_tail *ext4_orphan_block_tail( @@ -637,7 +637,7 @@ int ext4_init_orphan_info(struct super_block *sb) out_free: for (i--; i >= 0; i--) brelse(oi->of_binfo[i].ob_bh); - kfree(oi->of_binfo); + kvfree(oi->of_binfo); out_put: iput(inode); return ret; diff --git a/fs/hpfs/anode.c b/fs/hpfs/anode.c index c14c9a035ee0..a4f5321eafae 100644 --- a/fs/hpfs/anode.c +++ b/fs/hpfs/anode.c @@ -27,7 +27,7 @@ secno hpfs_bplus_lookup(struct super_block *s, struct inode *inode, a = le32_to_cpu(btree->u.internal[i].down); brelse(bh); if (!(anode = hpfs_map_anode(s, a, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); goto go_down; } hpfs_error(s, "sector %08x not found in internal anode %08x", sec, a); @@ -69,12 +69,13 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi int n; unsigned fs; int c1, c2 = 0; + if (fnod) { if (!(fnode = hpfs_map_fnode(s, node, &bh))) return -1; - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } else { if (!(anode = hpfs_map_anode(s, node, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } a = node; go_down: @@ -91,7 +92,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi if (hpfs_sb(s)->sb_chk) if (hpfs_stop_cycles(s, a, &c1, &c2, "hpfs_add_sector_to_btree #1")) return -1; if (!(anode = hpfs_map_anode(s, a, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); goto go_down; } if (n >= 0) { @@ -151,7 +152,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi } brelse(bh); bh = bh1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } btree->n_free_nodes--; n = btree->n_used_nodes++; le16_add_cpu(&btree->first_free, 12); @@ -168,10 +169,10 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi if (hpfs_stop_cycles(s, up, &c1, &c2, "hpfs_add_sector_to_btree #2")) return -1; if (up != node || !fnod) { if (!(anode = hpfs_map_anode(s, up, &bh))) return -1; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } else { if (!(fnode = hpfs_map_fnode(s, up, &bh))) return -1; - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } if (btree->n_free_nodes) { btree->n_free_nodes--; n = btree->n_used_nodes++; @@ -206,8 +207,8 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi anode->btree.n_used_nodes = 1; anode->btree.n_free_nodes = 59; anode->btree.first_free = cpu_to_le16(16); - anode->btree.u.internal[0].down = cpu_to_le32(a); - anode->btree.u.internal[0].file_secno = cpu_to_le32(-1); + GET_BTREE_PTR(&anode->btree)->u.internal[0].down = cpu_to_le32(a); + GET_BTREE_PTR(&anode->btree)->u.internal[0].file_secno = cpu_to_le32(-1); mark_buffer_dirty(bh); brelse(bh); if ((anode = hpfs_map_anode(s, a, &bh))) { @@ -229,20 +230,20 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi brelse(bh2); return -1; } - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } else { if (!(fnode = hpfs_map_fnode(s, node, &bh))) { brelse(bh2); return -1; } - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } ranode->up = cpu_to_le32(node); memcpy(&ranode->btree, btree, le16_to_cpu(btree->first_free)); if (fnod) ranode->btree.flags |= BP_fnode_parent; - ranode->btree.n_free_nodes = (bp_internal(&ranode->btree) ? 60 : 40) - ranode->btree.n_used_nodes; - if (bp_internal(&ranode->btree)) for (n = 0; n < ranode->btree.n_used_nodes; n++) { + GET_BTREE_PTR(&ranode->btree)->n_free_nodes = (bp_internal(GET_BTREE_PTR(&ranode->btree)) ? 60 : 40) - GET_BTREE_PTR(&ranode->btree)->n_used_nodes; + if (bp_internal(GET_BTREE_PTR(&ranode->btree))) for (n = 0; n < GET_BTREE_PTR(&ranode->btree)->n_used_nodes; n++) { struct anode *unode; if ((unode = hpfs_map_anode(s, le32_to_cpu(ranode->u.internal[n].down), &bh1))) { unode->up = cpu_to_le32(ra); @@ -291,7 +292,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree) if (hpfs_stop_cycles(s, ano, &d1, &d2, "hpfs_remove_btree #1")) return; if (!(anode = hpfs_map_anode(s, ano, &bh))) return; - btree1 = &anode->btree; + btree1 = GET_BTREE_PTR(&anode->btree); level++; pos = 0; } @@ -307,7 +308,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree) ano = le32_to_cpu(anode->up); if (--level) { if (!(anode = hpfs_map_anode(s, ano, &bh))) return; - btree1 = &anode->btree; + btree1 = GET_BTREE_PTR(&anode->btree); } else btree1 = btree; for (i = 0; i < btree1->n_used_nodes; i++) { if (le32_to_cpu(btree1->u.internal[i].down) == oano) { @@ -332,7 +333,7 @@ static secno anode_lookup(struct super_block *s, anode_secno a, unsigned sec) struct anode *anode; struct buffer_head *bh; if (!(anode = hpfs_map_anode(s, a, &bh))) return -1; - return hpfs_bplus_lookup(s, NULL, &anode->btree, sec, bh); + return hpfs_bplus_lookup(s, NULL, GET_BTREE_PTR(&anode->btree), sec, bh); } int hpfs_ea_read(struct super_block *s, secno a, int ano, unsigned pos, @@ -388,7 +389,7 @@ void hpfs_ea_remove(struct super_block *s, secno a, int ano, unsigned len) struct buffer_head *bh; if (ano) { if (!(anode = hpfs_map_anode(s, a, &bh))) return; - hpfs_remove_btree(s, &anode->btree); + hpfs_remove_btree(s, GET_BTREE_PTR(&anode->btree)); brelse(bh); hpfs_free_sectors(s, a, 1); } else hpfs_free_sectors(s, a, (len + 511) >> 9); @@ -407,10 +408,10 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs) int c1, c2 = 0; if (fno) { if (!(fnode = hpfs_map_fnode(s, f, &bh))) return; - btree = &fnode->btree; + btree = GET_BTREE_PTR(&fnode->btree); } else { if (!(anode = hpfs_map_anode(s, f, &bh))) return; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } if (!secs) { hpfs_remove_btree(s, btree); @@ -448,7 +449,7 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs) if (hpfs_stop_cycles(s, node, &c1, &c2, "hpfs_truncate_btree")) return; if (!(anode = hpfs_map_anode(s, node, &bh))) return; - btree = &anode->btree; + btree = GET_BTREE_PTR(&anode->btree); } nodes = btree->n_used_nodes + btree->n_free_nodes; for (i = 0; i < btree->n_used_nodes; i++) @@ -485,7 +486,7 @@ void hpfs_remove_fnode(struct super_block *s, fnode_secno fno) struct extended_attribute *ea; struct extended_attribute *ea_end; if (!(fnode = hpfs_map_fnode(s, fno, &bh))) return; - if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, &fnode->btree); + if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, GET_BTREE_PTR(&fnode->btree)); else hpfs_remove_dtree(s, le32_to_cpu(fnode->u.external[0].disk_secno)); ea_end = fnode_end_ea(fnode); for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea)) diff --git a/fs/hpfs/ea.c b/fs/hpfs/ea.c index 102ba18e561f..2149d3ca530b 100644 --- a/fs/hpfs/ea.c +++ b/fs/hpfs/ea.c @@ -41,7 +41,7 @@ void hpfs_ea_ext_remove(struct super_block *s, secno a, int ano, unsigned len) struct buffer_head *bh; struct anode *anode; if ((anode = hpfs_map_anode(s, a, &bh))) { - hpfs_remove_btree(s, &anode->btree); + hpfs_remove_btree(s, GET_BTREE_PTR(&anode->btree)); brelse(bh); hpfs_free_sectors(s, a, 1); } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 263b5bbe1849..29e876705369 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -51,7 +51,9 @@ static secno hpfs_bmap(struct inode *inode, unsigned file_secno, unsigned *n_sec return hpfs_inode->i_disk_sec + n; } if (!(fnode = hpfs_map_fnode(inode->i_sb, inode->i_ino, &bh))) return 0; - disk_secno = hpfs_bplus_lookup(inode->i_sb, inode, &fnode->btree, file_secno, bh); + disk_secno = hpfs_bplus_lookup(inode->i_sb, inode, + GET_BTREE_PTR(&fnode->btree), + file_secno, bh); if (disk_secno == -1) return 0; if (hpfs_chk_sectors(inode->i_sb, disk_secno, 1, "bmap")) return 0; n = file_secno - hpfs_inode->i_file_sec; diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h index 281dec8f636b..353f73c914d9 100644 --- a/fs/hpfs/hpfs.h +++ b/fs/hpfs/hpfs.h @@ -394,27 +394,45 @@ enum { BP_binary_search = 0x40, BP_internal = 0x80 }; + +/** + * GET_BTREE_PTR() - Get a pointer to struct bplus_header + * + * Wrapper around container_of() to retrieve a pointer to struct + * bplus_header from a pointer to struct bplus_header_fixed. + * + * @ptr: Pointer to struct bplus_header_fixed. + * + */ +#define GET_BTREE_PTR(ptr) \ + container_of(ptr, struct bplus_header, __hdr) + struct bplus_header { - u8 flags; /* bit 0 - high bit of first free entry offset + /* New members MUST be added within the struct_group() macro below. */ + struct_group_tagged(bplus_header_fixed, __hdr, + u8 flags; /* bit 0 - high bit of first free entry offset bit 5 - we're pointed to by an fnode, the data btree or some ea or the main ea bootage pointer ea_secno bit 6 - suggest binary search (unused) bit 7 - 1 -> (internal) tree of anodes 0 -> (leaf) list of extents */ - u8 fill[3]; - u8 n_free_nodes; /* free nodes in following array */ - u8 n_used_nodes; /* used nodes in following array */ - __le16 first_free; /* offset from start of header to + u8 fill[3]; + u8 n_free_nodes; /* free nodes in following array */ + u8 n_used_nodes; /* used nodes in following array */ + __le16 first_free; /* offset from start of header to first free node in array */ - union { - /* (internal) 2-word entries giving subtree pointers */ - DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal); - /* (external) 3-word entries giving sector runs */ - DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external); - } u; + ); + union { + /* (internal) 2-word entries giving subtree pointers */ + DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal); + /* (external) 3-word entries giving sector runs */ + DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external); + } u; }; +static_assert(offsetof(struct bplus_header, u.internal) == sizeof(struct bplus_header_fixed), + "struct member likely outside of struct_group_tagged()"); static inline bool bp_internal(struct bplus_header *bp) { @@ -453,7 +471,7 @@ struct fnode __le16 flags; /* bit 1 set -> ea_secno is an anode */ /* bit 8 set -> directory. first & only extent points to dnode. */ - struct bplus_header btree; /* b+ tree, 8 extents or 12 subtrees */ + struct bplus_header_fixed btree; /* b+ tree, 8 extents or 12 subtrees */ union { struct bplus_leaf_node external[8]; struct bplus_internal_node internal[12]; @@ -495,7 +513,7 @@ struct anode __le32 self; /* pointer to this anode */ __le32 up; /* parent anode or fnode */ - struct bplus_header btree; /* b+tree, 40 extents or 60 subtrees */ + struct bplus_header_fixed btree; /* b+tree, 40 extents or 60 subtrees */ union { struct bplus_leaf_node external[40]; struct bplus_internal_node internal[60]; diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index ecd9fccd1663..be73233502f8 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -178,14 +178,14 @@ struct fnode *hpfs_map_fnode(struct super_block *s, ino_t ino, struct buffer_hea } if (!fnode_is_dir(fnode)) { if ((unsigned)fnode->btree.n_used_nodes + (unsigned)fnode->btree.n_free_nodes != - (bp_internal(&fnode->btree) ? 12 : 8)) { + (bp_internal(GET_BTREE_PTR(&fnode->btree)) ? 12 : 8)) { hpfs_error(s, "bad number of nodes in fnode %08lx", (unsigned long)ino); goto bail; } if (le16_to_cpu(fnode->btree.first_free) != - 8 + fnode->btree.n_used_nodes * (bp_internal(&fnode->btree) ? 8 : 12)) { + 8 + fnode->btree.n_used_nodes * (bp_internal(GET_BTREE_PTR(&fnode->btree)) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in fnode %08lx", (unsigned long)ino); @@ -233,12 +233,12 @@ struct anode *hpfs_map_anode(struct super_block *s, anode_secno ano, struct buff goto bail; } if ((unsigned)anode->btree.n_used_nodes + (unsigned)anode->btree.n_free_nodes != - (bp_internal(&anode->btree) ? 60 : 40)) { + (bp_internal(GET_BTREE_PTR(&anode->btree)) ? 60 : 40)) { hpfs_error(s, "bad number of nodes in anode %08x", ano); goto bail; } if (le16_to_cpu(anode->btree.first_free) != - 8 + anode->btree.n_used_nodes * (bp_internal(&anode->btree) ? 8 : 12)) { + 8 + anode->btree.n_used_nodes * (bp_internal(GET_BTREE_PTR(&anode->btree)) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in anode %08x", ano); goto bail; } diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index e3cdc421dfba..353e13a615f5 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -52,8 +52,10 @@ static struct dentry *hpfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, dee.fnode = cpu_to_le32(fno); dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail2; + } hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; @@ -153,9 +155,10 @@ static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; - + } hpfs_init_inode(result); result->i_ino = fno; result->i_mode |= S_IFREG; @@ -239,9 +242,10 @@ static int hpfs_mknod(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; - + } hpfs_init_inode(result); result->i_ino = fno; hpfs_i(result)->i_parent_dir = dir->i_ino; @@ -314,8 +318,10 @@ static int hpfs_symlink(struct mnt_idmap *idmap, struct inode *dir, dee.creation_date = dee.write_date = dee.read_date = cpu_to_le32(local_get_seconds(dir->i_sb)); result = new_inode(dir->i_sb); - if (!result) + if (!result) { + err = -ENOMEM; goto bail1; + } result->i_ino = fno; hpfs_init_inode(result); hpfs_i(result)->i_parent_dir = dir->i_ino; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 42b779b4d87f..8ab85e7ac91e 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -404,15 +404,11 @@ static int hpfs_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_timeshift: { - int m = 1; char *rhs = param->string; int timeshift; - if (*rhs == '-') m = -1; - if (*rhs == '+' || *rhs == '-') rhs++; - timeshift = simple_strtoul(rhs, &rhs, 0) * m; - if (*rhs) - return -EINVAL; + if (kstrtoint(rhs, 0, ×hift)) + return -EINVAL; ctx->timeshift = timeshift; break; } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 9802b2cc29bb..5d5d63efbd57 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -433,7 +433,8 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; - ret = bio_iov_iter_get_bdev_pages(bio, dio->submit.iter, iomap->bdev); + ret = bio_iov_iter_get_pages(bio, dio->submit.iter, + bdev_logical_block_size(iomap->bdev) - 1); if (unlikely(ret)) { /* * We have to stop part way through an IO. We must fall diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index c7867139af69..3e510564de6e 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1659,6 +1659,7 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) int drop_reserve = 0; int err = 0; int was_modified = 0; + int wait_for_writeback = 0; if (is_handle_aborted(handle)) return -EROFS; @@ -1782,18 +1783,22 @@ int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) } /* - * The buffer is still not written to disk, we should - * attach this buffer to current transaction so that the - * buffer can be checkpointed only after the current - * transaction commits. + * The buffer has not yet been written to disk. We should + * either clear the buffer or ensure that the ongoing I/O + * is completed, and attach this buffer to current + * transaction so that the buffer can be checkpointed only + * after the current transaction commits. */ clear_buffer_dirty(bh); + wait_for_writeback = 1; __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); spin_unlock(&journal->j_list_lock); } drop: __brelse(bh); spin_unlock(&jh->b_state_lock); + if (wait_for_writeback) + wait_on_buffer(bh); jbd2_journal_put_journal_head(jh); if (drop_reserve) { /* no need to reserve log space for this block -bzzz */ diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index c1315df4b350..a31dc9588eb8 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -980,7 +980,7 @@ nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status) struct file_lock *fl; int error; - dprintk("grant_reply: looking for cookie %x, s=%d \n", + dprintk("grant_reply: looking for cookie %x, s=%d\n", *(unsigned int *)(cookie->data), status); if (!(block = nlmsvc_find_block(cookie))) return; diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 879e0b104d1c..e134dce45e35 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -5,6 +5,7 @@ config NFSD depends on FILE_LOCKING depends on FSNOTIFY select CRC32 + select CRYPTO_LIB_SHA256 if NFSD_V4 select LOCKD select SUNRPC select EXPORTFS @@ -77,7 +78,6 @@ config NFSD_V4 select FS_POSIX_ACL select RPCSEC_GSS_KRB5 select CRYPTO - select CRYPTO_LIB_SHA256 select CRYPTO_MD5 select GRACE_PERIOD select NFS_V4_2_SSC_HELPER if NFS_V4_2 diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 19078a043e85..fde5539cf6a6 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -18,8 +18,8 @@ static __be32 -nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, - struct nfsd4_layoutget *args) +nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode, + const struct svc_fh *fhp, struct nfsd4_layoutget *args) { struct nfsd4_layout_seg *seg = &args->lg_seg; struct super_block *sb = inode->i_sb; @@ -29,6 +29,9 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, u32 device_generation = 0; int error; + if (locks_in_grace(SVC_NET(rqstp))) + return nfserr_grace; + if (seg->offset & (block_size - 1)) { dprintk("pnfsd: I/O misaligned\n"); goto out_layoutunavailable; @@ -118,7 +121,6 @@ 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; @@ -128,9 +130,9 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp, iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME; iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime; - if (new_size > i_size_read(inode)) { + if (lcp->lc_size_chg) { iattr.ia_valid |= ATTR_SIZE; - iattr.ia_size = new_size; + iattr.ia_size = lcp->lc_newsize; } error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps, @@ -173,16 +175,18 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb, } static __be32 -nfsd4_block_proc_layoutcommit(struct inode *inode, +nfsd4_block_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp, struct nfsd4_layoutcommit *lcp) { struct iomap *iomaps; int nr_iomaps; __be32 nfserr; - nfserr = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, &nr_iomaps, - i_blocksize(inode)); + rqstp->rq_arg = lcp->lc_up_layout; + svcxdr_init_decode(rqstp); + + nfserr = nfsd4_block_decode_layoutupdate(&rqstp->rq_arg_stream, + &iomaps, &nr_iomaps, i_blocksize(inode)); if (nfserr != nfs_ok) return nfserr; @@ -313,16 +317,18 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb, return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp)); } static __be32 -nfsd4_scsi_proc_layoutcommit(struct inode *inode, +nfsd4_scsi_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp, struct nfsd4_layoutcommit *lcp) { struct iomap *iomaps; int nr_iomaps; __be32 nfserr; - nfserr = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout, - lcp->lc_up_len, &iomaps, &nr_iomaps, - i_blocksize(inode)); + rqstp->rq_arg = lcp->lc_up_layout; + svcxdr_init_decode(rqstp); + + nfserr = nfsd4_scsi_decode_layoutupdate(&rqstp->rq_arg_stream, + &iomaps, &nr_iomaps, i_blocksize(inode)); if (nfserr != nfs_ok) return nfserr; diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index bcf21fde9120..e50afe340737 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -29,8 +29,7 @@ nfsd4_block_encode_layoutget(struct xdr_stream *xdr, *p++ = cpu_to_be32(len); *p++ = cpu_to_be32(1); /* we always return a single extent */ - p = xdr_encode_opaque_fixed(p, &b->vol_id, - sizeof(struct nfsd4_deviceid)); + p = svcxdr_encode_deviceid4(p, &b->vol_id); p = xdr_encode_hyper(p, b->foff); p = xdr_encode_hyper(p, b->len); p = xdr_encode_hyper(p, b->soff); @@ -114,8 +113,7 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, /** * nfsd4_block_decode_layoutupdate - decode the block layout extent array - * @p: pointer to the xdr data - * @len: number of bytes to decode + * @xdr: subbuf set to the encoded array * @iomapp: pointer to store the decoded extent array * @nr_iomapsp: pointer to store the number of extents * @block_size: alignment of extent offset and length @@ -128,25 +126,24 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, * * Return values: * %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid - * %nfserr_bad_xdr: The encoded array in @p is invalid + * %nfserr_bad_xdr: The encoded array in @xdr is invalid * %nfserr_inval: An unaligned extent found * %nfserr_delay: Failed to allocate memory for @iomapp */ __be32 -nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, +nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp, int *nr_iomapsp, u32 block_size) { struct iomap *iomaps; - u32 nr_iomaps, i; + u32 nr_iomaps, expected, len, i; + __be32 nfserr; - if (len < sizeof(u32)) - return nfserr_bad_xdr; - len -= sizeof(u32); - if (len % PNFS_BLOCK_EXTENT_SIZE) + if (xdr_stream_decode_u32(xdr, &nr_iomaps)) return nfserr_bad_xdr; - nr_iomaps = be32_to_cpup(p++); - if (nr_iomaps != len / PNFS_BLOCK_EXTENT_SIZE) + len = sizeof(__be32) + xdr_stream_remaining(xdr); + expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE; + if (len != expected) return nfserr_bad_xdr; iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL); @@ -156,23 +153,44 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, for (i = 0; i < nr_iomaps; i++) { struct pnfs_block_extent bex; - memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid)); - p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid)); + if (nfsd4_decode_deviceid4(xdr, &bex.vol_id)) { + nfserr = nfserr_bad_xdr; + goto fail; + } - p = xdr_decode_hyper(p, &bex.foff); + if (xdr_stream_decode_u64(xdr, &bex.foff)) { + nfserr = nfserr_bad_xdr; + goto fail; + } if (bex.foff & (block_size - 1)) { + nfserr = nfserr_inval; + goto fail; + } + + if (xdr_stream_decode_u64(xdr, &bex.len)) { + nfserr = nfserr_bad_xdr; goto fail; } - p = xdr_decode_hyper(p, &bex.len); if (bex.len & (block_size - 1)) { + nfserr = nfserr_inval; + goto fail; + } + + if (xdr_stream_decode_u64(xdr, &bex.soff)) { + nfserr = nfserr_bad_xdr; goto fail; } - p = xdr_decode_hyper(p, &bex.soff); if (bex.soff & (block_size - 1)) { + nfserr = nfserr_inval; + goto fail; + } + + if (xdr_stream_decode_u32(xdr, &bex.es)) { + nfserr = nfserr_bad_xdr; goto fail; } - bex.es = be32_to_cpup(p++); if (bex.es != PNFS_BLOCK_READWRITE_DATA) { + nfserr = nfserr_inval; goto fail; } @@ -185,13 +203,12 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, return nfs_ok; fail: kfree(iomaps); - return nfserr_inval; + return nfserr; } /** * nfsd4_scsi_decode_layoutupdate - decode the scsi layout extent array - * @p: pointer to the xdr data - * @len: number of bytes to decode + * @xdr: subbuf set to the encoded array * @iomapp: pointer to store the decoded extent array * @nr_iomapsp: pointer to store the number of extents * @block_size: alignment of extent offset and length @@ -203,21 +220,22 @@ fail: * * Return values: * %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid - * %nfserr_bad_xdr: The encoded array in @p is invalid + * %nfserr_bad_xdr: The encoded array in @xdr is invalid * %nfserr_inval: An unaligned extent found * %nfserr_delay: Failed to allocate memory for @iomapp */ __be32 -nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, +nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp, int *nr_iomapsp, u32 block_size) { struct iomap *iomaps; - u32 nr_iomaps, expected, i; + u32 nr_iomaps, expected, len, i; + __be32 nfserr; - if (len < sizeof(u32)) + if (xdr_stream_decode_u32(xdr, &nr_iomaps)) return nfserr_bad_xdr; - nr_iomaps = be32_to_cpup(p++); + len = sizeof(__be32) + xdr_stream_remaining(xdr); expected = sizeof(__be32) + nr_iomaps * PNFS_SCSI_RANGE_SIZE; if (len != expected) return nfserr_bad_xdr; @@ -229,14 +247,22 @@ nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, for (i = 0; i < nr_iomaps; i++) { u64 val; - p = xdr_decode_hyper(p, &val); + if (xdr_stream_decode_u64(xdr, &val)) { + nfserr = nfserr_bad_xdr; + goto fail; + } if (val & (block_size - 1)) { + nfserr = nfserr_inval; goto fail; } iomaps[i].offset = val; - p = xdr_decode_hyper(p, &val); + if (xdr_stream_decode_u64(xdr, &val)) { + nfserr = nfserr_bad_xdr; + goto fail; + } if (val & (block_size - 1)) { + nfserr = nfserr_inval; goto fail; } iomaps[i].length = val; @@ -247,5 +273,5 @@ nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, return nfs_ok; fail: kfree(iomaps); - return nfserr_inval; + return nfserr; } diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h index 15b3569f3d9a..7d25ef689671 100644 --- a/fs/nfsd/blocklayoutxdr.h +++ b/fs/nfsd/blocklayoutxdr.h @@ -54,9 +54,9 @@ __be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, const struct nfsd4_getdeviceinfo *gdp); __be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr, const struct nfsd4_layoutget *lgp); -__be32 nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, +__be32 nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp, int *nr_iomapsp, u32 block_size); -__be32 nfsd4_scsi_decode_layoutupdate(__be32 *p, u32 len, +__be32 nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp, int *nr_iomapsp, u32 block_size); #endif /* _NFSD_BLOCKLAYOUTXDR_H */ diff --git a/fs/nfsd/debugfs.c b/fs/nfsd/debugfs.c index 84b0c8b559dc..ed2b9e066206 100644 --- a/fs/nfsd/debugfs.c +++ b/fs/nfsd/debugfs.c @@ -26,12 +26,99 @@ static int nfsd_dsr_get(void *data, u64 *val) static int nfsd_dsr_set(void *data, u64 val) { - nfsd_disable_splice_read = (val > 0) ? true : false; + nfsd_disable_splice_read = (val > 0); + if (!nfsd_disable_splice_read) { + /* + * Must use buffered I/O if splice_read is enabled. + */ + nfsd_io_cache_read = NFSD_IO_BUFFERED; + } return 0; } DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n"); +/* + * /sys/kernel/debug/nfsd/io_cache_read + * + * Contents: + * %0: NFS READ will use buffered IO + * %1: NFS READ will use dontcache (buffered IO w/ dropbehind) + * + * This setting takes immediate effect for all NFS versions, + * all exports, and in all NFSD net namespaces. + */ + +static int nfsd_io_cache_read_get(void *data, u64 *val) +{ + *val = nfsd_io_cache_read; + return 0; +} + +static int nfsd_io_cache_read_set(void *data, u64 val) +{ + int ret = 0; + + switch (val) { + case NFSD_IO_BUFFERED: + nfsd_io_cache_read = NFSD_IO_BUFFERED; + break; + case NFSD_IO_DONTCACHE: + /* + * Must disable splice_read when enabling + * NFSD_IO_DONTCACHE. + */ + nfsd_disable_splice_read = true; + nfsd_io_cache_read = val; + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get, + nfsd_io_cache_read_set, "%llu\n"); + +/* + * /sys/kernel/debug/nfsd/io_cache_write + * + * Contents: + * %0: NFS WRITE will use buffered IO + * %1: NFS WRITE will use dontcache (buffered IO w/ dropbehind) + * + * This setting takes immediate effect for all NFS versions, + * all exports, and in all NFSD net namespaces. + */ + +static int nfsd_io_cache_write_get(void *data, u64 *val) +{ + *val = nfsd_io_cache_write; + return 0; +} + +static int nfsd_io_cache_write_set(void *data, u64 val) +{ + int ret = 0; + + switch (val) { + case NFSD_IO_BUFFERED: + case NFSD_IO_DONTCACHE: + nfsd_io_cache_write = val; + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get, + nfsd_io_cache_write_set, "%llu\n"); + void nfsd_debugfs_exit(void) { debugfs_remove_recursive(nfsd_top_dir); @@ -44,4 +131,10 @@ void nfsd_debugfs_init(void) debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO, nfsd_top_dir, NULL, &nfsd_dsr_fops); + + debugfs_create_file("io_cache_read", 0644, nfsd_top_dir, NULL, + &nfsd_io_cache_read_fops); + + debugfs_create_file("io_cache_write", 0644, nfsd_top_dir, NULL, + &nfsd_io_cache_write_fops); } diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index caa695c06efb..9d55512d0cc9 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1082,50 +1082,62 @@ static struct svc_export *exp_find(struct cache_detail *cd, } /** - * check_nfsd_access - check if access to export is allowed. + * check_xprtsec_policy - check if access to export is allowed by the + * xprtsec policy * @exp: svc_export that is being accessed. - * @rqstp: svc_rqst attempting to access @exp (will be NULL for LOCALIO). - * @may_bypass_gss: reduce strictness of authorization check + * @rqstp: svc_rqst attempting to access @exp. + * + * Helper function for check_nfsd_access(). Note that callers should be + * using check_nfsd_access() instead of calling this function directly. The + * one exception is __fh_verify() since it has logic that may result in one + * or both of the helpers being skipped. * * Return values: * %nfs_ok if access is granted, or * %nfserr_wrongsec if access is denied */ -__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp, - bool may_bypass_gss) +__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp) { - struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors; - struct svc_xprt *xprt; - - /* - * If rqstp is NULL, this is a LOCALIO request which will only - * ever use a filehandle/credential pair for which access has - * been affirmed (by ACCESS or OPEN NFS requests) over the - * wire. So there is no need for further checks here. - */ - if (!rqstp) - return nfs_ok; - - xprt = rqstp->rq_xprt; + struct svc_xprt *xprt = rqstp->rq_xprt; if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) { if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) - goto ok; + return nfs_ok; } if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_TLS) { if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) && !test_bit(XPT_PEER_AUTH, &xprt->xpt_flags)) - goto ok; + return nfs_ok; } if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_MTLS) { if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) && test_bit(XPT_PEER_AUTH, &xprt->xpt_flags)) - goto ok; + return nfs_ok; } - if (!may_bypass_gss) - goto denied; + return nfserr_wrongsec; +} + +/** + * check_security_flavor - check if access to export is allowed by the + * security flavor + * @exp: svc_export that is being accessed. + * @rqstp: svc_rqst attempting to access @exp. + * @may_bypass_gss: reduce strictness of authorization check + * + * Helper function for check_nfsd_access(). Note that callers should be + * using check_nfsd_access() instead of calling this function directly. The + * one exception is __fh_verify() since it has logic that may result in one + * or both of the helpers being skipped. + * + * Return values: + * %nfs_ok if access is granted, or + * %nfserr_wrongsec if access is denied + */ +__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss) +{ + struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors; -ok: /* legacy gss-only clients are always OK: */ if (exp->ex_client == rqstp->rq_gssclient) return nfs_ok; @@ -1167,10 +1179,30 @@ ok: } } -denied: return nfserr_wrongsec; } +/** + * check_nfsd_access - check if access to export is allowed. + * @exp: svc_export that is being accessed. + * @rqstp: svc_rqst attempting to access @exp. + * @may_bypass_gss: reduce strictness of authorization check + * + * Return values: + * %nfs_ok if access is granted, or + * %nfserr_wrongsec if access is denied + */ +__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss) +{ + __be32 status; + + status = check_xprtsec_policy(exp, rqstp); + if (status != nfs_ok) + return status; + return check_security_flavor(exp, rqstp, may_bypass_gss); +} + /* * Uses rq_client and rq_gssclient to find an export; uses rq_client (an * auth_unix client) if it's available and has secinfo information; diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index cb36e6cce829..d2b09cd76145 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -101,6 +101,9 @@ struct svc_expkey { struct svc_cred; int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp); +__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp); +__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp, + bool may_bypass_gss); __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp, bool may_bypass_gss); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index e010d90aeb27..a238b6725008 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -395,27 +395,6 @@ nfsd_file_put_local(struct nfsd_file __rcu **pnf) } /** - * nfsd_file_get_local - get nfsd_file reference and reference to net - * @nf: nfsd_file of which to put the reference - * - * Get reference to both the nfsd_file and nf->nf_net. - */ -struct nfsd_file * -nfsd_file_get_local(struct nfsd_file *nf) -{ - struct net *net = nf->nf_net; - - if (nfsd_net_try_get(net)) { - nf = nfsd_file_get(nf); - if (!nf) - nfsd_net_put(net); - } else { - nf = NULL; - } - return nf; -} - -/** * nfsd_file_file - get the backing file of an nfsd_file * @nf: nfsd_file of which to access the backing file. * diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 237a05c74211..e3d6ca2b6030 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -67,7 +67,6 @@ int nfsd_file_cache_start_net(struct net *net); void nfsd_file_cache_shutdown_net(struct net *net); void nfsd_file_put(struct nfsd_file *nf); struct net *nfsd_file_put_local(struct nfsd_file __rcu **nf); -struct nfsd_file *nfsd_file_get_local(struct nfsd_file *nf); struct nfsd_file *nfsd_file_get(struct nfsd_file *nf); struct file *nfsd_file_file(struct nfsd_file *nf); void nfsd_file_close_inode_sync(struct inode *inode); diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index 3ca5304440ff..0f1a35400cd5 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -20,8 +20,8 @@ #define NFSDDBG_FACILITY NFSDDBG_PNFS static __be32 -nfsd4_ff_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, - struct nfsd4_layoutget *args) +nfsd4_ff_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode, + const struct svc_fh *fhp, struct nfsd4_layoutget *args) { struct nfsd4_layout_seg *seg = &args->lg_seg; u32 device_generation = 0; @@ -125,6 +125,13 @@ nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp, return 0; } +static __be32 +nfsd4_ff_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp, + struct nfsd4_layoutcommit *lcp) +{ + return nfs_ok; +} + const struct nfsd4_layout_ops ff_layout_ops = { .notify_types = NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE, @@ -133,4 +140,5 @@ const struct nfsd4_layout_ops ff_layout_ops = { .encode_getdeviceinfo = nfsd4_ff_encode_getdeviceinfo, .proc_layoutget = nfsd4_ff_proc_layoutget, .encode_layoutget = nfsd4_ff_encode_layoutget, + .proc_layoutcommit = nfsd4_ff_proc_layoutcommit, }; diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index aeb71c10ff1b..f9f7e38cba13 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -54,8 +54,7 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, *p++ = cpu_to_be32(1); /* single mirror */ *p++ = cpu_to_be32(1); /* single data server */ - p = xdr_encode_opaque_fixed(p, &fl->deviceid, - sizeof(struct nfsd4_deviceid)); + p = svcxdr_encode_deviceid4(p, &fl->deviceid); *p++ = cpu_to_be32(1); /* efficiency */ diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index 9e0a37cd29d8..be710d809a3b 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -132,7 +132,6 @@ static const struct nfsd_localio_operations nfsd_localio_ops = { .nfsd_net_put = nfsd_net_put, .nfsd_open_local_fh = nfsd_open_local_fh, .nfsd_file_put_local = nfsd_file_put_local, - .nfsd_file_get_local = nfsd_file_get_local, .nfsd_file_file = nfsd_file_file, .nfsd_file_dio_alignment = nfsd_file_dio_alignment, }; diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index edc9f75dc75c..c774ce9aa296 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -57,7 +57,20 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp, switch (nfserr) { case nfs_ok: return 0; - case nfserr_dropit: + case nfserr_jukebox: + /* this error can indicate a presence of a conflicting + * delegation to an NLM lock request. Options are: + * (1) For now, drop this request and make the client + * retry. When delegation is returned, client's lock retry + * will complete. + * (2) NLM4_DENIED as per "spec" signals to the client + * that the lock is unavailable now but client can retry. + * Linux client implementation does not. It treats + * NLM4_DENIED same as NLM4_FAILED and errors the request. + * (3) For the future, treat this as blocked lock and try + * to callback when the delegation is returned but might + * not have a proper lock request to block on. + */ return nlm_drop_reply; case nfserr_stale: return nlm_stale_fh; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index aea905fcaf87..683bd1130afe 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -120,7 +120,6 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, id->fsid_idx = fhp->fh_export->ex_devid_map->idx; id->generation = device_generation; - id->pad = 0; return 0; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 71b428efcbb5..e466cf52d7d7 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1133,6 +1133,35 @@ nfsd4_secinfo_no_name_release(union nfsd4_op_u *u) exp_put(u->secinfo_no_name.sin_exp); } +/* + * Validate that the requested timestamps are within the acceptable range. If + * timestamp appears to be in the future, then it will be clamped to + * current_time(). + */ +static void +vet_deleg_attrs(struct nfsd4_setattr *setattr, struct nfs4_delegation *dp) +{ + struct timespec64 now = current_time(dp->dl_stid.sc_file->fi_inode); + struct iattr *iattr = &setattr->sa_iattr; + + if ((setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) && + !nfsd4_vet_deleg_time(&iattr->ia_atime, &dp->dl_atime, &now)) + iattr->ia_valid &= ~(ATTR_ATIME | ATTR_ATIME_SET); + + if (setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) { + if (nfsd4_vet_deleg_time(&iattr->ia_mtime, &dp->dl_mtime, &now)) { + iattr->ia_ctime = iattr->ia_mtime; + if (nfsd4_vet_deleg_time(&iattr->ia_ctime, &dp->dl_ctime, &now)) + dp->dl_setattr = true; + else + iattr->ia_valid &= ~(ATTR_CTIME | ATTR_CTIME_SET); + } else { + iattr->ia_valid &= ~(ATTR_CTIME | ATTR_CTIME_SET | + ATTR_MTIME | ATTR_MTIME_SET); + } + } +} + static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -1170,8 +1199,10 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_delegation *dp = delegstateid(st); /* Only for *_ATTRS_DELEG flavors */ - if (deleg_attrs_deleg(dp->dl_type)) + if (deleg_attrs_deleg(dp->dl_type)) { + vet_deleg_attrs(setattr, dp); status = nfs_ok; + } } } if (st) @@ -1209,12 +1240,26 @@ out: return status; } +static void nfsd4_file_mark_deleg_written(struct nfs4_file *fi) +{ + spin_lock(&fi->fi_lock); + if (!list_empty(&fi->fi_delegations)) { + struct nfs4_delegation *dp = list_first_entry(&fi->fi_delegations, + struct nfs4_delegation, dl_perfile); + + if (dp->dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG) + dp->dl_written = true; + } + spin_unlock(&fi->fi_lock); +} + static __be32 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_write *write = &u->write; stateid_t *stateid = &write->wr_stateid; + struct nfs4_stid *stid = NULL; struct nfsd_file *nf = NULL; __be32 status = nfs_ok; unsigned long cnt; @@ -1227,10 +1272,15 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, trace_nfsd_write_start(rqstp, &cstate->current_fh, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, - stateid, WR_STATE, &nf, NULL); + stateid, WR_STATE, &nf, &stid); if (status) return status; + if (stid) { + nfsd4_file_mark_deleg_written(stid->sc_file); + nfs4_put_stid(stid); + } + write->wr_how_written = write->wr_stable_how; status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf, write->wr_offset, &write->wr_payload, @@ -1469,7 +1519,7 @@ try_again: return 0; } if (work) { - strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr) - 1); + strscpy(work->nsui_ipaddr, ipaddr, sizeof(work->nsui_ipaddr)); refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); @@ -2447,7 +2497,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp, if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls)) goto out_put_stid; - nfserr = ops->proc_layoutget(d_inode(current_fh->fh_dentry), + nfserr = ops->proc_layoutget(rqstp, d_inode(current_fh->fh_dentry), current_fh, lgp); if (nfserr) goto out_put_stid; @@ -2471,11 +2521,11 @@ static __be32 nfsd4_layoutcommit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct net *net = SVC_NET(rqstp); struct nfsd4_layoutcommit *lcp = &u->layoutcommit; const struct nfsd4_layout_seg *seg = &lcp->lc_seg; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; - loff_t new_size = lcp->lc_last_wr + 1; struct inode *inode; struct nfs4_layout_stateid *ls; __be32 nfserr; @@ -2491,43 +2541,50 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, goto out; inode = d_inode(current_fh->fh_dentry); - nfserr = nfserr_inval; - if (new_size <= seg->offset) { - dprintk("pnfsd: last write before layout segment\n"); - goto out; + lcp->lc_size_chg = false; + if (lcp->lc_newoffset) { + loff_t new_size = lcp->lc_last_wr + 1; + + nfserr = nfserr_inval; + if (new_size <= seg->offset) + goto out; + if (new_size > seg->offset + seg->length) + goto out; + + if (new_size > i_size_read(inode)) { + lcp->lc_size_chg = true; + lcp->lc_newsize = new_size; + } } - if (new_size > seg->offset + seg->length) { - dprintk("pnfsd: last write beyond layout segment\n"); + + nfserr = nfserr_grace; + if (locks_in_grace(net) && !lcp->lc_reclaim) goto out; - } - if (!lcp->lc_newoffset && new_size > i_size_read(inode)) { - dprintk("pnfsd: layoutcommit beyond EOF\n"); + nfserr = nfserr_no_grace; + if (!locks_in_grace(net) && lcp->lc_reclaim) goto out; - } - nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid, - false, lcp->lc_layout_type, - &ls); - if (nfserr) { - trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid); - /* fixup error code as per RFC5661 */ - if (nfserr == nfserr_bad_stateid) - nfserr = nfserr_badlayout; - goto out; + if (!lcp->lc_reclaim) { + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, + &lcp->lc_sid, false, lcp->lc_layout_type, &ls); + if (nfserr) { + trace_nfsd_layout_commit_lookup_fail(&lcp->lc_sid); + /* fixup error code as per RFC5661 */ + if (nfserr == nfserr_bad_stateid) + nfserr = nfserr_badlayout; + goto out; + } + + /* LAYOUTCOMMIT does not require any serialization */ + mutex_unlock(&ls->ls_mutex); } - /* LAYOUTCOMMIT does not require any serialization */ - mutex_unlock(&ls->ls_mutex); + nfserr = ops->proc_layoutcommit(inode, rqstp, lcp); - if (new_size > i_size_read(inode)) { - lcp->lc_size_chg = true; - lcp->lc_newsize = new_size; - } else { - lcp->lc_size_chg = false; + if (!lcp->lc_reclaim) { + nfsd4_file_mark_deleg_written(ls->ls_stid.sc_file); + nfs4_put_stid(&ls->ls_stid); } - - nfserr = ops->proc_layoutcommit(inode, lcp); - nfs4_put_stid(&ls->ls_stid); out: return nfserr; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 2231192ec33f..e2b9472e5c78 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -92,24 +92,10 @@ nfs4_reset_creds(const struct cred *original) put_cred(revert_creds(original)); } -static void -md5_to_hex(char *out, char *md5) -{ - int i; - - for (i=0; i<16; i++) { - unsigned char c = md5[i]; - - *out++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1); - *out++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1); - } - *out = '\0'; -} - static int -nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname) +nfs4_make_rec_clidname(char dname[HEXDIR_LEN], const struct xdr_netobj *clname) { - struct xdr_netobj cksum; + u8 digest[MD5_DIGEST_SIZE]; struct crypto_shash *tfm; int status; @@ -121,23 +107,16 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname) goto out_no_tfm; } - cksum.len = crypto_shash_digestsize(tfm); - cksum.data = kmalloc(cksum.len, GFP_KERNEL); - if (cksum.data == NULL) { - status = -ENOMEM; - goto out; - } - status = crypto_shash_tfm_digest(tfm, clname->data, clname->len, - cksum.data); + digest); if (status) goto out; - md5_to_hex(dname, cksum.data); + static_assert(HEXDIR_LEN == 2 * MD5_DIGEST_SIZE + 1); + sprintf(dname, "%*phN", MD5_DIGEST_SIZE, digest); status = 0; out: - kfree(cksum.data); crypto_free_shash(tfm); out_no_tfm: return status; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 88c347957da5..81fa7cc6c77b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1222,6 +1222,42 @@ static void put_deleg_file(struct nfs4_file *fp) nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); } +static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) +{ + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct inode *inode = file_inode(f); + int ret; + + /* don't do anything if FMODE_NOCMTIME isn't set */ + if ((READ_ONCE(f->f_mode) & FMODE_NOCMTIME) == 0) + return; + + spin_lock(&f->f_lock); + f->f_mode &= ~FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + + /* was it never written? */ + if (!dp->dl_written) + return; + + /* did it get a setattr for the timestamps at some point? */ + if (dp->dl_setattr) + return; + + /* Stamp everything to "now" */ + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &ia, NULL); + inode_unlock(inode); + if (ret) { + struct inode *inode = file_inode(f); + + pr_notice_ratelimited("Unable to update timestamps on inode %02x:%02x:%lu: %d\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino, ret); + } +} + static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; @@ -1229,6 +1265,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) WARN_ON_ONCE(!fp->fi_delegees); + nfsd4_finalize_deleg_timestamps(dp, nf->nf_file); kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } @@ -6157,7 +6194,8 @@ nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh, path.dentry = file_dentry(nf->nf_file); rc = vfs_getattr(&path, stat, - (STATX_MODE | STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE), + STATX_MODE | STATX_SIZE | STATX_ATIME | + STATX_MTIME | STATX_CTIME | STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT); nfsd_file_put(nf); @@ -6264,6 +6302,8 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file; + if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) || !nfs4_delegation_stat(dp, currentfh, &stat)) { nfs4_put_stid(&dp->dl_stid); @@ -6274,10 +6314,17 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, OPEN_DELEGATE_WRITE; dp->dl_cb_fattr.ncf_cur_fsize = stat.size; dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); + dp->dl_atime = stat.atime; + dp->dl_ctime = stat.ctime; + dp->dl_mtime = stat.mtime; + spin_lock(&f->f_lock); + f->f_mode |= FMODE_NOCMTIME; + spin_unlock(&f->f_lock); trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); } else { - open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : - OPEN_DELEGATE_READ; + open->op_delegate_type = deleg_ts && nfs4_delegation_stat(dp, currentfh, &stat) ? + OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + dp->dl_atime = stat.atime; trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); } nfs4_put_stid(&dp->dl_stid); @@ -9130,25 +9177,25 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, } /** - * set_cb_time - vet and set the timespec for a cb_getattr update - * @cb: timestamp from the CB_GETATTR response + * nfsd4_vet_deleg_time - vet and set the timespec for a delegated timestamp update + * @req: timestamp from the client * @orig: original timestamp in the inode * @now: current time * - * Given a timestamp in a CB_GETATTR response, check it against the + * Given a timestamp from the client response, check it against the * current timestamp in the inode and the current time. Returns true * if the inode's timestamp needs to be updated, and false otherwise. - * @cb may also be changed if the timestamp needs to be clamped. + * @req may also be changed if the timestamp needs to be clamped. */ -static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig, - const struct timespec64 *now) +bool nfsd4_vet_deleg_time(struct timespec64 *req, const struct timespec64 *orig, + const struct timespec64 *now) { /* * "When the time presented is before the original time, then the * update is ignored." Also no need to update if there is no change. */ - if (timespec64_compare(cb, orig) <= 0) + if (timespec64_compare(req, orig) <= 0) return false; /* @@ -9156,10 +9203,8 @@ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig, * clamp the new time to the current time, or it may * return NFS4ERR_DELAY to the client, allowing it to retry." */ - if (timespec64_compare(cb, now) > 0) { - /* clamp it */ - *cb = *now; - } + if (timespec64_compare(req, now) > 0) + *req = *now; return true; } @@ -9167,28 +9212,27 @@ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig, static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp) { struct inode *inode = d_inode(dentry); - struct timespec64 now = current_time(inode); struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; struct iattr attrs = { }; int ret; if (deleg_attrs_deleg(dp->dl_type)) { - struct timespec64 atime = inode_get_atime(inode); - struct timespec64 mtime = inode_get_mtime(inode); + struct timespec64 now = current_time(inode); attrs.ia_atime = ncf->ncf_cb_atime; attrs.ia_mtime = ncf->ncf_cb_mtime; - if (set_cb_time(&attrs.ia_atime, &atime, &now)) + if (nfsd4_vet_deleg_time(&attrs.ia_atime, &dp->dl_atime, &now)) attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; - if (set_cb_time(&attrs.ia_mtime, &mtime, &now)) { - attrs.ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET; + if (nfsd4_vet_deleg_time(&attrs.ia_mtime, &dp->dl_mtime, &now)) { + attrs.ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; attrs.ia_ctime = attrs.ia_mtime; + if (nfsd4_vet_deleg_time(&attrs.ia_ctime, &dp->dl_ctime, &now)) + attrs.ia_valid |= ATTR_CTIME | ATTR_CTIME_SET; } } else { attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME; - attrs.ia_mtime = attrs.ia_ctime = now; } if (!attrs.ia_valid) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index ea91bad4eee2..c0a3c6a7c8bb 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -538,8 +538,9 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, iattr->ia_mtime.tv_sec = modify.seconds; iattr->ia_mtime.tv_nsec = modify.nseconds; iattr->ia_ctime.tv_sec = modify.seconds; - iattr->ia_ctime.tv_nsec = modify.seconds; - iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG; + iattr->ia_ctime.tv_nsec = modify.nseconds; + iattr->ia_valid |= ATTR_CTIME | ATTR_CTIME_SET | + ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG; } /* request sanity: did attrlist4 contain the expected number of words? */ @@ -587,23 +588,13 @@ nfsd4_decode_state_owner4(struct nfsd4_compoundargs *argp, } #ifdef CONFIG_NFSD_PNFS -static __be32 -nfsd4_decode_deviceid4(struct nfsd4_compoundargs *argp, - struct nfsd4_deviceid *devid) -{ - __be32 *p; - - p = xdr_inline_decode(argp->xdr, NFS4_DEVICEID4_SIZE); - if (!p) - return nfserr_bad_xdr; - memcpy(devid, p, sizeof(*devid)); - return nfs_ok; -} static __be32 nfsd4_decode_layoutupdate4(struct nfsd4_compoundargs *argp, struct nfsd4_layoutcommit *lcp) { + u32 len; + if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_layout_type) < 0) return nfserr_bad_xdr; if (lcp->lc_layout_type < LAYOUT_NFSV4_1_FILES) @@ -611,13 +602,10 @@ nfsd4_decode_layoutupdate4(struct nfsd4_compoundargs *argp, if (lcp->lc_layout_type >= LAYOUT_TYPE_MAX) return nfserr_bad_xdr; - if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_up_len) < 0) + if (xdr_stream_decode_u32(argp->xdr, &len) < 0) + return nfserr_bad_xdr; + if (!xdr_stream_subsegment(argp->xdr, &lcp->lc_up_layout, len)) return nfserr_bad_xdr; - if (lcp->lc_up_len > 0) { - lcp->lc_up_layout = xdr_inline_decode(argp->xdr, lcp->lc_up_len); - if (!lcp->lc_up_layout) - return nfserr_bad_xdr; - } return nfs_ok; } @@ -1783,7 +1771,7 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, __be32 status; memset(gdev, 0, sizeof(*gdev)); - status = nfsd4_decode_deviceid4(argp, &gdev->gd_devid); + status = nfsd4_decode_deviceid4(argp->xdr, &gdev->gd_devid); if (status) return status; if (xdr_stream_decode_u32(argp->xdr, &gdev->gd_layout_type) < 0) @@ -1814,7 +1802,7 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, status = nfsd4_decode_stateid4(argp, &lcp->lc_sid); if (status) return status; - if (xdr_stream_decode_u32(argp->xdr, &lcp->lc_newoffset) < 0) + if (xdr_stream_decode_bool(argp->xdr, &lcp->lc_newoffset) < 0) return nfserr_bad_xdr; if (lcp->lc_newoffset) { if (xdr_stream_decode_u64(argp->xdr, &lcp->lc_last_wr) < 0) diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index ba9d326b3de6..ab13ee9c7fd8 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -27,7 +27,7 @@ * cache size, the idea being that when the cache is at its maximum number * of entries, then this should be the average number of entries per bucket. */ -#define TARGET_BUCKET_SIZE 64 +#define TARGET_BUCKET_SIZE 8 struct nfsd_drc_bucket { struct rb_root rb_head; @@ -237,10 +237,6 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) } -/* - * Move cache entry to end of LRU list, and queue the cleaner to run if it's - * not already scheduled. - */ static void lru_put_end(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp) { @@ -272,13 +268,6 @@ nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, /* The bucket LRU is ordered oldest-first. */ list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) { - /* - * Don't free entries attached to calls that are still - * in-progress, but do keep scanning the list. - */ - if (rp->c_state == RC_INPROG) - continue; - if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries && time_before(expiry, rp->c_timestamp)) break; @@ -453,8 +442,6 @@ out: nn->longest_chain_cachesize, atomic_read(&nn->num_drc_entries)); } - - lru_put_end(b, ret); return ret; } diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 1cd0bed57bc2..ea87b42894dd 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -153,6 +153,15 @@ static inline void nfsd_debugfs_exit(void) {} extern bool nfsd_disable_splice_read __read_mostly; +enum { + /* Any new NFSD_IO enum value must be added at the end */ + NFSD_IO_BUFFERED, + NFSD_IO_DONTCACHE, +}; + +extern u64 nfsd_io_cache_read __read_mostly; +extern u64 nfsd_io_cache_write __read_mostly; + extern int nfsd_max_blksize; static inline int nfsd_v4client(struct svc_rqst *rq) @@ -335,14 +344,8 @@ void nfsd_lockd_shutdown(void); * cannot conflict with any existing be32 nfserr value. */ enum { - NFSERR_DROPIT = NFS4ERR_FIRST_FREE, -/* if a request fails due to kmalloc failure, it gets dropped. - * Client should resend eventually - */ -#define nfserr_dropit cpu_to_be32(NFSERR_DROPIT) - /* end-of-file indicator in readdir */ - NFSERR_EOF, + NFSERR_EOF = NFS4ERR_FIRST_FREE, #define nfserr_eof cpu_to_be32(NFSERR_EOF) /* replay detected */ diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 74cf1f4de174..3eb724ec9566 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -364,10 +364,30 @@ __fh_verify(struct svc_rqst *rqstp, if (error) goto out; + /* + * If rqstp is NULL, this is a LOCALIO request which will only + * ever use a filehandle/credential pair for which access has + * been affirmed (by ACCESS or OPEN NFS requests) over the + * wire. Skip both the xprtsec policy and the security flavor + * checks. + */ + if (!rqstp) + goto check_permissions; + if ((access & NFSD_MAY_NLM) && (exp->ex_flags & NFSEXP_NOAUTHNLM)) /* NLM is allowed to fully bypass authentication */ goto out; + /* + * NLM is allowed to bypass the xprtsec policy check because lockd + * doesn't support xprtsec. + */ + if (!(access & NFSD_MAY_NLM)) { + error = check_xprtsec_policy(exp, rqstp); + if (error) + goto out; + } + if (access & NFSD_MAY_BYPASS_GSS) may_bypass_gss = true; /* @@ -379,13 +399,13 @@ __fh_verify(struct svc_rqst *rqstp, && exp->ex_path.dentry == dentry) may_bypass_gss = true; - error = check_nfsd_access(exp, rqstp, may_bypass_gss); + error = check_security_flavor(exp, rqstp, may_bypass_gss); if (error) goto out; - /* During LOCALIO call to fh_verify will be called with a NULL rqstp */ - if (rqstp) - svc_xprt_set_valid(rqstp->rq_xprt); + svc_xprt_set_valid(rqstp->rq_xprt); + +check_permissions: /* Finally, check access permissions. */ error = nfsd_permission(cred, exp, dentry, access); out: @@ -663,6 +683,33 @@ out_negative: } /** + * fh_getattr - Retrieve attributes on a local file + * @fhp: File handle of target file + * @stat: Caller-supplied kstat buffer to be filled in + * + * Returns nfs_ok on success, otherwise an NFS status code is + * returned. + */ +__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat) +{ + struct path p = { + .mnt = fhp->fh_export->ex_path.mnt, + .dentry = fhp->fh_dentry, + }; + struct inode *inode = d_inode(p.dentry); + u32 request_mask = STATX_BASIC_STATS; + + if (S_ISREG(inode->i_mode)) + request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN); + + if (fhp->fh_maxsize == NFS4_FHSIZE) + request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); + + return nfserrno(vfs_getattr(&p, stat, request_mask, + AT_STATX_SYNC_AS_STAT)); +} + +/** * fh_fill_pre_attrs - Fill in pre-op attributes * @fhp: file handle to be updated * diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 1cf979722521..5ef7191f8ad8 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -14,6 +14,8 @@ #include <linux/exportfs.h> #include <linux/nfs4.h> +#include "export.h" + /* * The file handle starts with a sequence of four-byte words. * The first word contains a version number (1) and three descriptor bytes @@ -220,6 +222,7 @@ extern char * SVCFH_fmt(struct svc_fh *fhp); __be32 fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int); __be32 fh_verify_local(struct net *, struct svc_cred *, struct auth_domain *, struct svc_fh *, umode_t, int); +__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat); __be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *); __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); @@ -272,6 +275,41 @@ static inline bool fh_fsid_match(const struct knfsd_fh *fh1, } /** + * fh_want_write - Get write access to an export + * @fhp: File handle of file to be written + * + * Caller must invoke fh_drop_write() when its write operation + * is complete. + * + * Returns 0 if the file handle's export can be written to. Otherwise + * the export is not prepared for updates, and the returned negative + * errno value reflects the reason for the failure. + */ +static inline int fh_want_write(struct svc_fh *fhp) +{ + int ret; + + if (fhp->fh_want_write) + return 0; + ret = mnt_want_write(fhp->fh_export->ex_path.mnt); + if (!ret) + fhp->fh_want_write = true; + return ret; +} + +/** + * fh_drop_write - Release write access on an export + * @fhp: File handle of file on which fh_want_write() was previously called + */ +static inline void fh_drop_write(struct svc_fh *fhp) +{ + if (fhp->fh_want_write) { + fhp->fh_want_write = false; + mnt_drop_write(fhp->fh_export->ex_path.mnt); + } +} + +/** * knfsd_fh_hash - calculate the crc32 hash for the filehandle * @fh - pointer to filehandle * diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h index 925817f66917..db9af780438b 100644 --- a/fs/nfsd/pnfs.h +++ b/fs/nfsd/pnfs.h @@ -29,12 +29,13 @@ struct nfsd4_layout_ops { __be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr, const struct nfsd4_getdeviceinfo *gdevp); - __be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp, - struct nfsd4_layoutget *lgp); + __be32 (*proc_layoutget)(struct svc_rqst *rqstp, struct inode *inode, + const struct svc_fh *fhp, struct nfsd4_layoutget *lgp); __be32 (*encode_layoutget)(struct xdr_stream *xdr, const struct nfsd4_layoutget *lgp); __be32 (*proc_layoutcommit)(struct inode *inode, + struct svc_rqst *rqstp, struct nfsd4_layoutcommit *lcp); void (*fence_client)(struct nfs4_layout_stateid *ls, diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 8adc2550129e..1e736f402426 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -35,6 +35,7 @@ #ifndef _NFSD4_STATE_H #define _NFSD4_STATE_H +#include <crypto/md5.h> #include <linux/idr.h> #include <linux/refcount.h> #include <linux/sunrpc/svc_xprt.h> @@ -217,13 +218,20 @@ struct nfs4_delegation { struct nfs4_clnt_odstate *dl_clnt_odstate; time64_t dl_time; u32 dl_type; -/* For recall: */ + /* For recall: */ int dl_retries; struct nfsd4_callback dl_recall; bool dl_recalled; + bool dl_written; + bool dl_setattr; /* for CB_GETATTR */ struct nfs4_cb_fattr dl_cb_fattr; + + /* For delegated timestamps */ + struct timespec64 dl_atime; + struct timespec64 dl_mtime; + struct timespec64 dl_ctime; }; static inline bool deleg_is_read(u32 dl_type) @@ -242,6 +250,9 @@ static inline bool deleg_attrs_deleg(u32 dl_type) dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG; } +bool nfsd4_vet_deleg_time(struct timespec64 *cb, const struct timespec64 *orig, + const struct timespec64 *now); + #define cb_to_delegation(cb) \ container_of(cb, struct nfs4_delegation, dl_recall) @@ -381,7 +392,8 @@ struct nfsd4_sessionid { u32 reserved; }; -#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */ +/* Length of MD5 digest as hex, plus terminating '\0' */ +#define HEXDIR_LEN (2 * MD5_DIGEST_SIZE + 1) /* * State Meaning Where set diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index aa4a95713a48..9cb20d4aeab1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -49,6 +49,8 @@ #define NFSDDBG_FACILITY NFSDDBG_FILEOP bool nfsd_disable_splice_read __read_mostly; +u64 nfsd_io_cache_read __read_mostly = NFSD_IO_BUFFERED; +u64 nfsd_io_cache_write __read_mostly = NFSD_IO_BUFFERED; /** * nfserrno - Map Linux errnos to NFS errnos @@ -467,7 +469,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) return 0; } - if (!iap->ia_valid) + if ((iap->ia_valid & ~ATTR_DELEG) == 0) return 0; /* @@ -1099,6 +1101,16 @@ __be32 nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp, size_t len; init_sync_kiocb(&kiocb, file); + + switch (nfsd_io_cache_read) { + case NFSD_IO_BUFFERED: + break; + case NFSD_IO_DONTCACHE: + if (file->f_op->fop_flags & FOP_DONTCACHE) + kiocb.ki_flags = IOCB_DONTCACHE; + break; + } + kiocb.ki_pos = offset; v = 0; @@ -1224,6 +1236,15 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, since = READ_ONCE(file->f_wb_err); if (verf) nfsd_copy_write_verifier(verf, nn); + + switch (nfsd_io_cache_write) { + case NFSD_IO_BUFFERED: + break; + case NFSD_IO_DONTCACHE: + if (file->f_op->fop_flags & FOP_DONTCACHE) + kiocb.ki_flags |= IOCB_DONTCACHE; + break; + } host_err = vfs_iocb_iter_write(file, &kiocb, &iter); if (host_err < 0) { commit_reset_write_verifier(nn, rqstp, host_err); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index fde3e0c11dba..0c0292611c6d 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -160,41 +160,4 @@ __be32 nfsd_permission(struct svc_cred *cred, struct svc_export *exp, void nfsd_filp_close(struct file *fp); -static inline int fh_want_write(struct svc_fh *fh) -{ - int ret; - - if (fh->fh_want_write) - return 0; - ret = mnt_want_write(fh->fh_export->ex_path.mnt); - if (!ret) - fh->fh_want_write = true; - return ret; -} - -static inline void fh_drop_write(struct svc_fh *fh) -{ - if (fh->fh_want_write) { - fh->fh_want_write = false; - mnt_drop_write(fh->fh_export->ex_path.mnt); - } -} - -static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat) -{ - u32 request_mask = STATX_BASIC_STATS; - struct path p = {.mnt = fh->fh_export->ex_path.mnt, - .dentry = fh->fh_dentry}; - struct inode *inode = d_inode(p.dentry); - - if (S_ISREG(inode->i_mode)) - request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN); - - if (fh->fh_maxsize == NFS4_FHSIZE) - request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); - - return nfserrno(vfs_getattr(&p, stat, request_mask, - AT_STATX_SYNC_AS_STAT)); -} - #endif /* LINUX_NFSD_VFS_H */ diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index a23bc56051ca..d4b48602b2b0 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -595,9 +595,43 @@ struct nfsd4_reclaim_complete { struct nfsd4_deviceid { u64 fsid_idx; u32 generation; - u32 pad; }; +static inline __be32 * +svcxdr_encode_deviceid4(__be32 *p, const struct nfsd4_deviceid *devid) +{ + __be64 *q = (__be64 *)p; + + *q = (__force __be64)devid->fsid_idx; + p += 2; + *p++ = (__force __be32)devid->generation; + *p++ = xdr_zero; + return p; +} + +static inline __be32 * +svcxdr_decode_deviceid4(__be32 *p, struct nfsd4_deviceid *devid) +{ + __be64 *q = (__be64 *)p; + + devid->fsid_idx = (__force u64)(*q); + p += 2; + devid->generation = (__force u32)(*p++); + p++; /* NFSD does not use the remaining octets */ + return p; +} + +static inline __be32 +nfsd4_decode_deviceid4(struct xdr_stream *xdr, struct nfsd4_deviceid *devid) +{ + __be32 *p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE); + + if (unlikely(!p)) + return nfserr_bad_xdr; + svcxdr_decode_deviceid4(p, devid); + return nfs_ok; +} + struct nfsd4_layout_seg { u32 iomode; u64 offset; @@ -630,8 +664,7 @@ struct nfsd4_layoutcommit { u64 lc_last_wr; /* request */ struct timespec64 lc_mtime; /* request */ u32 lc_layout_type; /* request */ - u32 lc_up_len; /* layout length */ - void *lc_up_layout; /* decoded by callback */ + struct xdr_buf lc_up_layout; /* decoded by callback */ bool lc_size_chg; /* response */ u64 lc_newsize; /* response */ }; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index b36f9f9340f0..b8ac7b7faf61 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -562,8 +562,8 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) /* * Mark all the cfids as closed, and move them to the cfids->dying list. - * They'll be cleaned up later by cfids_invalidation_worker. Take - * a reference to each cfid during this process. + * They'll be cleaned up by laundromat. Take a reference to each cfid + * during this process. */ spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { @@ -580,12 +580,11 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) } else kref_get(&cfid->refcount); } - /* - * Queue dropping of the dentries once locks have been dropped - */ - if (!list_empty(&cfids->dying)) - queue_work(cfid_put_wq, &cfids->invalidation_work); spin_unlock(&cfids->cfid_list_lock); + + /* run laundromat unconditionally now as there might have been previously queued work */ + mod_delayed_work(cfid_put_wq, &cfids->laundromat_work, 0); + flush_delayed_work(&cfids->laundromat_work); } static void @@ -715,25 +714,6 @@ static void free_cached_dir(struct cached_fid *cfid) kfree(cfid); } -static void cfids_invalidation_worker(struct work_struct *work) -{ - struct cached_fids *cfids = container_of(work, struct cached_fids, - invalidation_work); - struct cached_fid *cfid, *q; - LIST_HEAD(entry); - - spin_lock(&cfids->cfid_list_lock); - /* move cfids->dying to the local list */ - list_cut_before(&entry, &cfids->dying, &cfids->dying); - spin_unlock(&cfids->cfid_list_lock); - - list_for_each_entry_safe(cfid, q, &entry, entry) { - list_del(&cfid->entry); - /* Drop the ref-count acquired in invalidate_all_cached_dirs */ - kref_put(&cfid->refcount, smb2_close_cached_fid); - } -} - static void cfids_laundromat_worker(struct work_struct *work) { struct cached_fids *cfids; @@ -743,6 +723,9 @@ static void cfids_laundromat_worker(struct work_struct *work) cfids = container_of(work, struct cached_fids, laundromat_work.work); spin_lock(&cfids->cfid_list_lock); + /* move cfids->dying to the local list */ + list_cut_before(&entry, &cfids->dying, &cfids->dying); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { if (cfid->last_access_time && time_after(jiffies, cfid->last_access_time + HZ * dir_cache_timeout)) { @@ -796,7 +779,6 @@ struct cached_fids *init_cached_dirs(void) INIT_LIST_HEAD(&cfids->entries); INIT_LIST_HEAD(&cfids->dying); - INIT_WORK(&cfids->invalidation_work, cfids_invalidation_worker); INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker); queue_delayed_work(cfid_put_wq, &cfids->laundromat_work, dir_cache_timeout * HZ); @@ -820,7 +802,6 @@ void free_cached_dirs(struct cached_fids *cfids) return; cancel_delayed_work_sync(&cfids->laundromat_work); - cancel_work_sync(&cfids->invalidation_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 31339dc32719..1e383db7c337 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -62,7 +62,6 @@ struct cached_fids { int num_entries; struct list_head entries; struct list_head dying; - struct work_struct invalidation_work; struct delayed_work laundromat_work; /* aggregate accounting for all cached dirents under this tcon */ atomic_long_t total_dirents_entries; diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 43b86fa4d695..9891f55bac1e 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -24,20 +24,14 @@ static const struct cred *spnego_cred; static int cifs_spnego_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { - char *payload; - int ret; + char *payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL); - ret = -ENOMEM; - payload = kmemdup(prep->data, prep->datalen, GFP_KERNEL); if (!payload) - goto error; + return -ENOMEM; /* attach the data */ key->payload.data[0] = payload; - ret = 0; - -error: - return ret; + return 0; } static void diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c index 7233c6a7e6d7..68a1f87c446d 100644 --- a/fs/smb/client/cifs_swn.c +++ b/fs/smb/client/cifs_swn.c @@ -82,10 +82,8 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg) int ret; skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb == NULL) { - ret = -ENOMEM; - goto fail; - } + if (!skb) + return -ENOMEM; hdr = genlmsg_put(skb, 0, 0, &cifs_genl_family, 0, CIFS_GENL_CMD_SWN_REGISTER); if (hdr == NULL) { @@ -172,7 +170,6 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg) nlmsg_fail: genlmsg_cancel(skb, hdr); nlmsg_free(skb); -fail: return ret; } @@ -313,17 +310,15 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) reg = cifs_find_swn_reg(tcon); if (!IS_ERR(reg)) { kref_get(®->ref_count); - mutex_unlock(&cifs_swnreg_idr_mutex); - return reg; + goto unlock; } else if (PTR_ERR(reg) != -EEXIST) { - mutex_unlock(&cifs_swnreg_idr_mutex); - return reg; + goto unlock; } reg = kmalloc(sizeof(struct cifs_swn_reg), GFP_ATOMIC); if (reg == NULL) { - mutex_unlock(&cifs_swnreg_idr_mutex); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto fail_unlock; } kref_init(®->ref_count); @@ -354,7 +349,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon) reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT); reg->tcon = tcon; - +unlock: mutex_unlock(&cifs_swnreg_idr_mutex); return reg; @@ -365,6 +360,7 @@ fail_idr: idr_remove(&cifs_swnreg_idr, reg->id); fail: kfree(reg); +fail_unlock: mutex_unlock(&cifs_swnreg_idr_mutex); return ERR_PTR(ret); } diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 1775c2b7528f..05b1fa76e8cc 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -392,11 +392,27 @@ static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct TCP_Server_Info *server = tcon->ses->server; + struct inode *inode = file_inode(file); + int rc; + + if (!server->ops->fallocate) + return -EOPNOTSUPP; + + rc = inode_lock_killable(inode); + if (rc) + return rc; + + netfs_wait_for_outstanding_io(inode); - if (server->ops->fallocate) - return server->ops->fallocate(file, tcon, mode, off, len); + rc = file_modified(file); + if (rc) + goto out_unlock; + + rc = server->ops->fallocate(file, tcon, mode, off, len); - return -EOPNOTSUPP; +out_unlock: + inode_unlock(inode); + return rc; } static int cifs_permission(struct mnt_idmap *idmap, diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 3ce7c614ccc0..e9534258d1ef 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -145,6 +145,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 56 -#define CIFS_VERSION "2.56" +#define SMB3_PRODUCT_BUILD 57 +#define CIFS_VERSION "2.57" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 3ac254e123dc..8f6f567d7474 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1566,6 +1566,11 @@ struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr, bool offload); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); +int cifs_file_flush(const unsigned int xid, struct inode *inode, + struct cifsFileInfo *cfile); +int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, + const char *full_path, struct cifsFileInfo *open_file, + loff_t size); #define CIFS_CACHE_READ_FLG 1 #define CIFS_CACHE_HANDLE_FLG 2 diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index d20766f664c4..2881efcbe09a 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1163,7 +1163,7 @@ OldOpenRetry: cpu_to_le64(le32_to_cpu(pSMBr->EndOfFile)); pfile_info->EndOfFile = pfile_info->AllocationSize; pfile_info->NumberOfLinks = cpu_to_le32(1); - pfile_info->DeletePending = 0; + pfile_info->DeletePending = 0; /* successful open = not delete pending */ } } @@ -1288,7 +1288,7 @@ openRetry: buf->AllocationSize = rsp->AllocationSize; buf->EndOfFile = rsp->EndOfFile; buf->NumberOfLinks = cpu_to_le32(1); - buf->DeletePending = 0; + buf->DeletePending = 0; /* successful open = not delete pending */ } cifs_buf_release(req); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index fc67a6441c96..da5597dbf5b9 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -200,8 +200,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { - free_dentry_path(page); - return PTR_ERR(full_path); + rc = PTR_ERR(full_path); + goto out; } /* If we're caching, we need to be able to fill in around partial writes. */ @@ -678,7 +678,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, const char *full_path; void *page; int retry_count = 0; - struct cached_fid *cfid = NULL; + struct dentry *de; xid = get_xid(); @@ -690,16 +690,15 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, cifs_sb = CIFS_SB(parent_dir_inode->i_sb); tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { - free_xid(xid); - return ERR_CAST(tlink); + de = ERR_CAST(tlink); + goto free_xid; } pTcon = tlink_tcon(tlink); rc = check_name(direntry, pTcon); if (unlikely(rc)) { - cifs_put_tlink(tlink); - free_xid(xid); - return ERR_PTR(rc); + de = ERR_PTR(rc); + goto put_tlink; } /* can not grab the rename sem here since it would @@ -708,15 +707,15 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, page = alloc_dentry_path(); full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { - cifs_put_tlink(tlink); - free_xid(xid); - free_dentry_path(page); - return ERR_CAST(full_path); + de = ERR_CAST(full_path); + goto free_dentry_path; } if (d_really_is_positive(direntry)) { cifs_dbg(FYI, "non-NULL inode in lookup\n"); } else { + struct cached_fid *cfid = NULL; + cifs_dbg(FYI, "NULL inode in lookup\n"); /* @@ -775,25 +774,27 @@ again: } out: + de = d_splice_alias(newInode, direntry); +free_dentry_path: free_dentry_path(page); +put_tlink: cifs_put_tlink(tlink); +free_xid: free_xid(xid); - return d_splice_alias(newInode, direntry); + return de; } static int cifs_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *direntry, unsigned int flags) { - struct inode *inode = NULL; - struct cached_fid *cfid; - int rc; - if (flags & LOOKUP_RCU) return -ECHILD; if (d_really_is_positive(direntry)) { - inode = d_inode(direntry); + int rc; + struct inode *inode = d_inode(direntry); + if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode))) CIFS_I(inode)->time = 0; /* force reval */ @@ -836,6 +837,7 @@ cifs_d_revalidate(struct inode *dir, const struct qstr *name, } else { struct cifs_sb_info *cifs_sb = CIFS_SB(dir->i_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + struct cached_fid *cfid; if (!open_cached_dir_by_dentry(tcon, direntry->d_parent, &cfid)) { /* diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index a5ed742afa00..474dadeb1593 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -952,6 +952,66 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, } } +int cifs_file_flush(const unsigned int xid, struct inode *inode, + struct cifsFileInfo *cfile) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_tcon *tcon; + int rc; + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC) + return 0; + + if (cfile && (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE)) { + tcon = tlink_tcon(cfile->tlink); + return tcon->ses->server->ops->flush(xid, tcon, + &cfile->fid); + } + rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); + if (!rc) { + tcon = tlink_tcon(cfile->tlink); + rc = tcon->ses->server->ops->flush(xid, tcon, &cfile->fid); + cifsFileInfo_put(cfile); + } else if (rc == -EBADF) { + rc = 0; + } + return rc; +} + +static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) +{ + struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry)); + struct inode *inode = d_inode(dentry); + struct cifsFileInfo *cfile = NULL; + struct TCP_Server_Info *server; + struct cifs_tcon *tcon; + int rc; + + rc = filemap_write_and_wait(inode->i_mapping); + if (is_interrupt_error(rc)) + return -ERESTARTSYS; + mapping_set_error(inode->i_mapping, rc); + + cfile = find_writable_file(cinode, FIND_WR_FSUID_ONLY); + rc = cifs_file_flush(xid, inode, cfile); + if (!rc) { + if (cfile) { + tcon = tlink_tcon(cfile->tlink); + server = tcon->ses->server; + rc = server->ops->set_file_size(xid, tcon, + cfile, 0, false); + } + if (!rc) { + netfs_resize_file(&cinode->netfs, 0, true); + cifs_setsize(inode, 0); + inode->i_blocks = 0; + } + } + if (cfile) + cifsFileInfo_put(cfile); + return rc; +} + int cifs_open(struct inode *inode, struct file *file) { @@ -1004,6 +1064,12 @@ int cifs_open(struct inode *inode, struct file *file) file->f_op = &cifs_file_direct_ops; } + if (file->f_flags & O_TRUNC) { + rc = cifs_do_truncate(xid, file_dentry(file)); + if (rc) + goto out; + } + /* Get the cached handle as SMB2 close is deferred */ if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { rc = cifs_get_writable_path(tcon, full_path, @@ -2685,13 +2751,10 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - unsigned int xid; - int rc = 0; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; struct inode *inode = file_inode(file); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + unsigned int xid; + int rc; rc = file_write_and_wait_range(file, start, end); if (rc) { @@ -2699,39 +2762,15 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, return rc; } - xid = get_xid(); - - cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n", - file, datasync); + cifs_dbg(FYI, "%s: name=%pD datasync=0x%x\n", __func__, file, datasync); if (!CIFS_CACHE_READ(CIFS_I(inode))) { rc = cifs_zap_mapping(inode); - if (rc) { - cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc); - rc = 0; /* don't care about it in fsync */ - } + cifs_dbg(FYI, "%s: invalidate mapping: rc = %d\n", __func__, rc); } - tcon = tlink_tcon(smbfile->tlink); - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { - server = tcon->ses->server; - if (server->ops->flush == NULL) { - rc = -ENOSYS; - goto strict_fsync_exit; - } - - if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) { - smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY); - if (smbfile) { - rc = server->ops->flush(xid, tcon, &smbfile->fid); - cifsFileInfo_put(smbfile); - } else - cifs_dbg(FYI, "ignore fsync for file not open for write\n"); - } else - rc = server->ops->flush(xid, tcon, &smbfile->fid); - } - -strict_fsync_exit: + xid = get_xid(); + rc = cifs_file_flush(xid, inode, smbfile); free_xid(xid); return rc; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 8bb544be401e..239dd84a336f 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3007,28 +3007,25 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, void cifs_setsize(struct inode *inode, loff_t offset) { - struct cifsInodeInfo *cifs_i = CIFS_I(inode); - spin_lock(&inode->i_lock); i_size_write(inode, offset); spin_unlock(&inode->i_lock); - - /* Cached inode must be refreshed on truncate */ - cifs_i->time = 0; + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); truncate_pagecache(inode, offset); + netfs_wait_for_outstanding_io(inode); } -static int -cifs_set_file_size(struct inode *inode, struct iattr *attrs, - unsigned int xid, const char *full_path, struct dentry *dentry) +int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, + const char *full_path, struct cifsFileInfo *open_file, + loff_t size) { - int rc; - struct cifsFileInfo *open_file; - struct cifsInodeInfo *cifsInode = CIFS_I(inode); + struct inode *inode = d_inode(dentry); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct tcon_link *tlink = NULL; struct cifs_tcon *tcon = NULL; struct TCP_Server_Info *server; + int rc = -EINVAL; /* * To avoid spurious oplock breaks from server, in the case of @@ -3039,19 +3036,25 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, * writebehind data than the SMB timeout for the SetPathInfo * request would allow */ - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); - if (open_file) { + if (open_file && (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE)) { tcon = tlink_tcon(open_file->tlink); server = tcon->ses->server; - if (server->ops->set_file_size) - rc = server->ops->set_file_size(xid, tcon, open_file, - attrs->ia_size, false); - else - rc = -ENOSYS; - cifsFileInfo_put(open_file); - cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc); - } else - rc = -EINVAL; + rc = server->ops->set_file_size(xid, tcon, + open_file, + size, false); + cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); + } else { + open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + if (open_file) { + tcon = tlink_tcon(open_file->tlink); + server = tcon->ses->server; + rc = server->ops->set_file_size(xid, tcon, + open_file, + size, false); + cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); + cifsFileInfo_put(open_file); + } + } if (!rc) goto set_size_out; @@ -3069,20 +3072,15 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs, * valid, writeable file handle for it was found or because there was * an error setting it by handle. */ - if (server->ops->set_path_size) - rc = server->ops->set_path_size(xid, tcon, full_path, - attrs->ia_size, cifs_sb, false, dentry); - else - rc = -ENOSYS; - cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc); - - if (tlink) - cifs_put_tlink(tlink); + rc = server->ops->set_path_size(xid, tcon, full_path, size, + cifs_sb, false, dentry); + cifs_dbg(FYI, "%s: SetEOF by path (setattrs) rc = %d\n", __func__, rc); + cifs_put_tlink(tlink); set_size_out: if (rc == 0) { - netfs_resize_file(&cifsInode->netfs, attrs->ia_size, true); - cifs_setsize(inode, attrs->ia_size); + netfs_resize_file(&cifsInode->netfs, size, true); + cifs_setsize(inode, size); /* * i_blocks is not related to (i_size / i_blksize), but instead * 512 byte (2**9) size is required for calculating num blocks. @@ -3090,15 +3088,7 @@ set_size_out: * this is best estimate we have for blocks allocated for a file * Number of blocks must be rounded up so size 1 is not 0 blocks */ - inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9; - - /* - * The man page of truncate says if the size changed, - * then the st_ctime and st_mtime fields for the file - * are updated. - */ - attrs->ia_ctime = attrs->ia_mtime = current_time(inode); - attrs->ia_valid |= ATTR_CTIME | ATTR_MTIME; + inode->i_blocks = (512 - 1 + size) >> 9; } return rc; @@ -3118,7 +3108,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) struct tcon_link *tlink; struct cifs_tcon *pTcon; struct cifs_unix_set_info_args *args = NULL; - struct cifsFileInfo *open_file; + struct cifsFileInfo *open_file = NULL; cifs_dbg(FYI, "setattr_unix on file %pd attrs->ia_valid=0x%x\n", direntry, attrs->ia_valid); @@ -3132,6 +3122,9 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if (rc < 0) goto out; + if (attrs->ia_valid & ATTR_FILE) + open_file = attrs->ia_file->private_data; + full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { rc = PTR_ERR(full_path); @@ -3159,9 +3152,16 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) rc = 0; if (attrs->ia_valid & ATTR_SIZE) { - rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry); + rc = cifs_file_set_size(xid, direntry, full_path, + open_file, attrs->ia_size); if (rc != 0) goto out; + /* + * Avoid setting timestamps on the server for ftruncate(2) to + * prevent it from disabling automatic timestamp updates as per + * MS-FSA 2.1.4.17. + */ + attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME); } /* skip mode change if it's just for clearing setuid/setgid */ @@ -3206,14 +3206,24 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) args->ctime = NO_CHANGE_64; args->device = 0; - open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); - if (open_file) { - u16 nfid = open_file->fid.netfid; - u32 npid = open_file->pid; + rc = -EINVAL; + if (open_file && (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE)) { pTcon = tlink_tcon(open_file->tlink); - rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, nfid, npid); - cifsFileInfo_put(open_file); + rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, + open_file->fid.netfid, + open_file->pid); } else { + open_file = find_writable_file(cifsInode, FIND_WR_FSUID_ONLY); + if (open_file) { + pTcon = tlink_tcon(open_file->tlink); + rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, + open_file->fid.netfid, + open_file->pid); + cifsFileInfo_put(open_file); + } + } + + if (rc) { tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { rc = PTR_ERR(tlink); @@ -3221,8 +3231,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) } pTcon = tlink_tcon(tlink); rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); + cifs_sb->local_nls, + cifs_remap(cifs_sb)); cifs_put_tlink(tlink); } @@ -3264,8 +3274,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) struct inode *inode = d_inode(direntry); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cifsInode = CIFS_I(inode); - struct cifsFileInfo *wfile; - struct cifs_tcon *tcon; + struct cifsFileInfo *cfile = NULL; const char *full_path; void *page = alloc_dentry_path(); int rc = -EACCES; @@ -3285,6 +3294,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (rc < 0) goto cifs_setattr_exit; + if (attrs->ia_valid & ATTR_FILE) + cfile = attrs->ia_file->private_data; + full_path = build_path_from_dentry(direntry, page); if (IS_ERR(full_path)) { rc = PTR_ERR(full_path); @@ -3311,25 +3323,23 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) rc = 0; - if ((attrs->ia_valid & ATTR_MTIME) && - !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { - rc = cifs_get_writable_file(cifsInode, FIND_WR_ANY, &wfile); - if (!rc) { - tcon = tlink_tcon(wfile->tlink); - rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); - cifsFileInfo_put(wfile); - if (rc) - goto cifs_setattr_exit; - } else if (rc != -EBADF) + if (attrs->ia_valid & ATTR_MTIME) { + rc = cifs_file_flush(xid, inode, cfile); + if (rc) goto cifs_setattr_exit; - else - rc = 0; } if (attrs->ia_valid & ATTR_SIZE) { - rc = cifs_set_file_size(inode, attrs, xid, full_path, direntry); + rc = cifs_file_set_size(xid, direntry, full_path, + cfile, attrs->ia_size); if (rc != 0) goto cifs_setattr_exit; + /* + * Avoid setting timestamps on the server for ftruncate(2) to + * prevent it from disabling automatic timestamp updates as per + * MS-FSA 2.1.4.17. + */ + attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME); } if (attrs->ia_valid & ATTR_UID) @@ -3459,6 +3469,13 @@ cifs_setattr(struct mnt_idmap *idmap, struct dentry *direntry, if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; + /* + * Avoid setting [cm]time with O_TRUNC to prevent the server from + * disabling automatic timestamp updates as specified in + * MS-FSA 2.1.4.17. + */ + if (attrs->ia_valid & ATTR_OPEN) + return 0; do { #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index a02d41d1ce4a..ca8f3dd7ff63 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -652,13 +652,71 @@ static int cifs_query_path_info(const unsigned int xid, #ifdef CONFIG_CIFS_XATTR /* + * For non-symlink WSL reparse points it is required to fetch + * EA $LXMOD which contains in its S_DT part the mandatory file type. + */ + if (!rc && data->reparse_point) { + struct smb2_file_full_ea_info *ea; + u32 next = 0; + + ea = (struct smb2_file_full_ea_info *)data->wsl.eas; + do { + ea = (void *)((u8 *)ea + next); + next = le32_to_cpu(ea->next_entry_offset); + } while (next); + if (le16_to_cpu(ea->ea_value_length)) { + ea->next_entry_offset = cpu_to_le32(ALIGN(sizeof(*ea) + + ea->ea_name_length + 1 + + le16_to_cpu(ea->ea_value_length), 4)); + ea = (void *)((u8 *)ea + le32_to_cpu(ea->next_entry_offset)); + } + + rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_MODE, + &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1], + SMB2_WSL_XATTR_MODE_SIZE, cifs_sb); + if (rc == SMB2_WSL_XATTR_MODE_SIZE) { + ea->next_entry_offset = cpu_to_le32(0); + ea->flags = 0; + ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN; + ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_MODE_SIZE); + memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_MODE, SMB2_WSL_XATTR_NAME_LEN + 1); + data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + + SMB2_WSL_XATTR_MODE_SIZE, 4); + rc = 0; + } else if (rc >= 0) { + /* It is an error if EA $LXMOD has wrong size. */ + rc = -EINVAL; + } else { + /* + * In all other cases ignore error if fetching + * of EA $LXMOD failed. It is needed only for + * non-symlink WSL reparse points and wsl_to_fattr() + * handle the case when EA is missing. + */ + rc = 0; + } + } + + /* * For WSL CHR and BLK reparse points it is required to fetch * EA $LXDEV which contains major and minor device numbers. */ if (!rc && data->reparse_point) { struct smb2_file_full_ea_info *ea; + u32 next = 0; ea = (struct smb2_file_full_ea_info *)data->wsl.eas; + do { + ea = (void *)((u8 *)ea + next); + next = le32_to_cpu(ea->next_entry_offset); + } while (next); + if (le16_to_cpu(ea->ea_value_length)) { + ea->next_entry_offset = cpu_to_le32(ALIGN(sizeof(*ea) + + ea->ea_name_length + 1 + + le16_to_cpu(ea->ea_value_length), 4)); + ea = (void *)((u8 *)ea + le32_to_cpu(ea->next_entry_offset)); + } + rc = CIFSSMBQAllEAs(xid, tcon, full_path, SMB2_WSL_XATTR_DEV, &ea->ea_data[SMB2_WSL_XATTR_NAME_LEN + 1], SMB2_WSL_XATTR_DEV_SIZE, cifs_sb); @@ -668,8 +726,8 @@ static int cifs_query_path_info(const unsigned int xid, ea->ea_name_length = SMB2_WSL_XATTR_NAME_LEN; ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE); memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1); - data->wsl.eas_len = sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + - SMB2_WSL_XATTR_DEV_SIZE; + data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + + SMB2_WSL_XATTR_MODE_SIZE, 4); rc = 0; } else if (rc >= 0) { /* It is an error if EA $LXDEV has wrong size. */ @@ -818,6 +876,11 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path, info.Attributes = cpu_to_le32(dosattrs); rc = CIFSSMBSetPathInfo(xid, tcon, full_path, &info, cifs_sb->local_nls, cifs_sb); + if (rc == -EOPNOTSUPP || rc == -EINVAL) + rc = SMBSetInformation(xid, tcon, full_path, + info.Attributes, + 0 /* do not change write time */, + cifs_sb->local_nls, cifs_sb); if (rc == 0) cifsInode->cifsAttrs = dosattrs; } @@ -974,7 +1037,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, .tcon = tcon, .cifs_sb = cifs_sb, .desired_access = SYNCHRONIZE | FILE_WRITE_ATTRIBUTES, - .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR), + .create_options = cifs_create_options(cifs_sb, 0), .disposition = FILE_OPEN, .path = full_path, .fid = &fid, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 0985db9f86e5..09e3fc81d7cb 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -676,7 +676,7 @@ finished: idata->fi.EndOfFile = create_rsp->EndofFile; if (le32_to_cpu(idata->fi.NumberOfLinks) == 0) idata->fi.NumberOfLinks = cpu_to_le32(1); /* dummy value */ - idata->fi.DeletePending = 0; + idata->fi.DeletePending = 0; /* successful open = not delete pending */ idata->fi.Directory = !!(le32_to_cpu(create_rsp->FileAttributes) & ATTR_DIRECTORY); /* smb2_parse_contexts() fills idata->fi.IndexNumber */ @@ -1382,31 +1382,33 @@ int smb2_set_file_info(struct inode *inode, const char *full_path, FILE_BASIC_INFO *buf, const unsigned int xid) { - struct cifs_open_parms oparms; + struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), }; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifsFileInfo *cfile = NULL; + struct cifs_open_parms oparms; struct tcon_link *tlink; struct cifs_tcon *tcon; - struct cifsFileInfo *cfile; - struct kvec in_iov = { .iov_base = buf, .iov_len = sizeof(*buf), }; - int rc; - - if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && - (buf->LastWriteTime == 0) && (buf->ChangeTime == 0) && - (buf->Attributes == 0)) - return 0; /* would be a no op, no sense sending this */ + int rc = 0; tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); - cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) && + (buf->LastWriteTime == 0) && (buf->ChangeTime == 0)) { + if (buf->Attributes == 0) + goto out; /* would be a no op, no sense sending this */ + cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); + } + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, 0, ACL_NO_MODE); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, &in_iov, &(int){SMB2_OP_SET_INFO}, 1, cfile, NULL, NULL, NULL); +out: cifs_put_tlink(tlink); return rc; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 058050f744c0..7c392cf5940b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1803,140 +1803,226 @@ free_vars: return rc; } +/** + * calc_chunk_count - calculates the number chunks to be filled in the Chunks[] + * array of struct copychunk_ioctl + * + * @tcon: destination file tcon + * @bytes_left: how many bytes are left to copy + * + * Return: maximum number of chunks with which Chunks[] can be filled. + */ +static inline u32 +calc_chunk_count(struct cifs_tcon *tcon, u64 bytes_left) +{ + u32 max_chunks = READ_ONCE(tcon->max_chunks); + u32 max_bytes_copy = READ_ONCE(tcon->max_bytes_copy); + u32 max_bytes_chunk = READ_ONCE(tcon->max_bytes_chunk); + u64 need; + u32 allowed; + + if (!max_bytes_chunk || !max_bytes_copy || !max_chunks) + return 0; + + /* chunks needed for the remaining bytes */ + need = DIV_ROUND_UP_ULL(bytes_left, max_bytes_chunk); + /* chunks allowed per cc request */ + allowed = DIV_ROUND_UP(max_bytes_copy, max_bytes_chunk); + + return (u32)umin(need, umin(max_chunks, allowed)); +} + +/** + * smb2_copychunk_range - server-side copy of data range + * + * @xid: transaction id + * @src_file: source file + * @dst_file: destination file + * @src_off: source file byte offset + * @len: number of bytes to copy + * @dst_off: destination file byte offset + * + * Obtains a resume key for @src_file and issues FSCTL_SRV_COPYCHUNK_WRITE + * IOCTLs, splitting the request into chunks limited by tcon->max_*. + * + * Return: @len on success; negative errno on failure. + */ static ssize_t smb2_copychunk_range(const unsigned int xid, - struct cifsFileInfo *srcfile, - struct cifsFileInfo *trgtfile, u64 src_off, - u64 len, u64 dest_off) + struct cifsFileInfo *src_file, + struct cifsFileInfo *dst_file, + u64 src_off, + u64 len, + u64 dst_off) { - int rc; - unsigned int ret_data_len; - struct copychunk_ioctl *pcchunk; - struct copychunk_ioctl_rsp *retbuf = NULL; + int rc = 0; + unsigned int ret_data_len = 0; + struct copychunk_ioctl *cc_req = NULL; + struct copychunk_ioctl_rsp *cc_rsp = NULL; struct cifs_tcon *tcon; - int chunks_copied = 0; - bool chunk_sizes_updated = false; - ssize_t bytes_written, total_bytes_written = 0; + struct copychunk *chunk; + u32 chunks, chunk_count, chunk_bytes; + u32 copy_bytes, copy_bytes_left; + u32 chunks_written, bytes_written; + u64 total_bytes_left = len; + u64 src_off_prev, dst_off_prev; + u32 retries = 0; + + tcon = tlink_tcon(dst_file->tlink); + + trace_smb3_copychunk_enter(xid, src_file->fid.volatile_fid, + dst_file->fid.volatile_fid, tcon->tid, + tcon->ses->Suid, src_off, dst_off, len); + +retry: + chunk_count = calc_chunk_count(tcon, total_bytes_left); + if (!chunk_count) { + rc = -EOPNOTSUPP; + goto out; + } - pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); - if (pcchunk == NULL) - return -ENOMEM; + cc_req = kzalloc(struct_size(cc_req, Chunks, chunk_count), GFP_KERNEL); + if (!cc_req) { + rc = -ENOMEM; + goto out; + } - cifs_dbg(FYI, "%s: about to call request res key\n", __func__); /* Request a key from the server to identify the source of the copy */ - rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink), - srcfile->fid.persistent_fid, - srcfile->fid.volatile_fid, pcchunk); + rc = SMB2_request_res_key(xid, + tlink_tcon(src_file->tlink), + src_file->fid.persistent_fid, + src_file->fid.volatile_fid, + cc_req); - /* Note: request_res_key sets res_key null only if rc !=0 */ + /* Note: request_res_key sets res_key null only if rc != 0 */ if (rc) - goto cchunk_out; + goto out; + + while (total_bytes_left > 0) { + + /* Store previous offsets to allow rewind */ + src_off_prev = src_off; + dst_off_prev = dst_off; - /* For now array only one chunk long, will make more flexible later */ - pcchunk->ChunkCount = cpu_to_le32(1); - pcchunk->Reserved = 0; - pcchunk->Reserved2 = 0; + chunks = 0; + copy_bytes = 0; + copy_bytes_left = umin(total_bytes_left, tcon->max_bytes_copy); + while (copy_bytes_left > 0 && chunks < chunk_count) { + chunk = &cc_req->Chunks[chunks++]; - tcon = tlink_tcon(trgtfile->tlink); + chunk->SourceOffset = cpu_to_le64(src_off); + chunk->TargetOffset = cpu_to_le64(dst_off); - trace_smb3_copychunk_enter(xid, srcfile->fid.volatile_fid, - trgtfile->fid.volatile_fid, tcon->tid, - tcon->ses->Suid, src_off, dest_off, len); + chunk_bytes = umin(copy_bytes_left, tcon->max_bytes_chunk); - while (len > 0) { - pcchunk->SourceOffset = cpu_to_le64(src_off); - pcchunk->TargetOffset = cpu_to_le64(dest_off); - pcchunk->Length = - cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); + chunk->Length = cpu_to_le32(chunk_bytes); + /* Buffer is zeroed, no need to set chunk->Reserved = 0 */ + + src_off += chunk_bytes; + dst_off += chunk_bytes; + + copy_bytes_left -= chunk_bytes; + copy_bytes += chunk_bytes; + } + + cc_req->ChunkCount = cpu_to_le32(chunks); + /* Buffer is zeroed, no need to set cc_req->Reserved = 0 */ /* Request server copy to target from src identified by key */ - kfree(retbuf); - retbuf = NULL; - rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, - trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, - (char *)pcchunk, sizeof(struct copychunk_ioctl), - CIFSMaxBufSize, (char **)&retbuf, &ret_data_len); + kfree(cc_rsp); + cc_rsp = NULL; + rc = SMB2_ioctl(xid, tcon, dst_file->fid.persistent_fid, + dst_file->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, + (char *)cc_req, struct_size(cc_req, Chunks, chunks), + CIFSMaxBufSize, (char **)&cc_rsp, &ret_data_len); + + if (rc && rc != -EINVAL) + goto out; + + if (unlikely(ret_data_len != sizeof(*cc_rsp))) { + cifs_tcon_dbg(VFS, "Copychunk invalid response: size %u/%zu\n", + ret_data_len, sizeof(*cc_rsp)); + rc = -EIO; + goto out; + } + + bytes_written = le32_to_cpu(cc_rsp->TotalBytesWritten); + chunks_written = le32_to_cpu(cc_rsp->ChunksWritten); + chunk_bytes = le32_to_cpu(cc_rsp->ChunkBytesWritten); + if (rc == 0) { - if (ret_data_len != - sizeof(struct copychunk_ioctl_rsp)) { - cifs_tcon_dbg(VFS, "Invalid cchunk response size\n"); - rc = -EIO; - goto cchunk_out; - } - if (retbuf->TotalBytesWritten == 0) { - cifs_dbg(FYI, "no bytes copied\n"); + /* Check if server claimed to write more than we asked */ + if (unlikely(!bytes_written || bytes_written > copy_bytes || + !chunks_written || chunks_written > chunks)) { + cifs_tcon_dbg(VFS, "Copychunk invalid response: bytes written %u/%u, chunks written %u/%u\n", + bytes_written, copy_bytes, chunks_written, chunks); rc = -EIO; - goto cchunk_out; - } - /* - * Check if server claimed to write more than we asked - */ - if (le32_to_cpu(retbuf->TotalBytesWritten) > - le32_to_cpu(pcchunk->Length)) { - cifs_tcon_dbg(VFS, "Invalid copy chunk response\n"); - rc = -EIO; - goto cchunk_out; + goto out; } - if (le32_to_cpu(retbuf->ChunksWritten) != 1) { - cifs_tcon_dbg(VFS, "Invalid num chunks written\n"); - rc = -EIO; - goto cchunk_out; + + /* Partial write: rewind */ + if (bytes_written < copy_bytes) { + u32 delta = copy_bytes - bytes_written; + + src_off -= delta; + dst_off -= delta; } - chunks_copied++; - - bytes_written = le32_to_cpu(retbuf->TotalBytesWritten); - src_off += bytes_written; - dest_off += bytes_written; - len -= bytes_written; - total_bytes_written += bytes_written; - - cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n", - le32_to_cpu(retbuf->ChunksWritten), - le32_to_cpu(retbuf->ChunkBytesWritten), - bytes_written); - trace_smb3_copychunk_done(xid, srcfile->fid.volatile_fid, - trgtfile->fid.volatile_fid, tcon->tid, - tcon->ses->Suid, src_off, dest_off, len); - } else if (rc == -EINVAL) { - if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) - goto cchunk_out; - - cifs_dbg(FYI, "MaxChunks %d BytesChunk %d MaxCopy %d\n", - le32_to_cpu(retbuf->ChunksWritten), - le32_to_cpu(retbuf->ChunkBytesWritten), - le32_to_cpu(retbuf->TotalBytesWritten)); - /* - * Check if this is the first request using these sizes, - * (ie check if copy succeed once with original sizes - * and check if the server gave us different sizes after - * we already updated max sizes on previous request). - * if not then why is the server returning an error now - */ - if ((chunks_copied != 0) || chunk_sizes_updated) - goto cchunk_out; - - /* Check that server is not asking us to grow size */ - if (le32_to_cpu(retbuf->ChunkBytesWritten) < - tcon->max_bytes_chunk) - tcon->max_bytes_chunk = - le32_to_cpu(retbuf->ChunkBytesWritten); - else - goto cchunk_out; /* server gave us bogus size */ + total_bytes_left -= bytes_written; + continue; + } - /* No need to change MaxChunks since already set to 1 */ - chunk_sizes_updated = true; - } else - goto cchunk_out; + /* + * Check if server is not asking us to reduce size. + * + * Note: As per MS-SMB2 2.2.32.1, the values returned + * in cc_rsp are not strictly lower than what existed + * before. + */ + if (bytes_written < tcon->max_bytes_copy) { + cifs_tcon_dbg(FYI, "Copychunk MaxBytesCopy updated: %u -> %u\n", + tcon->max_bytes_copy, bytes_written); + tcon->max_bytes_copy = bytes_written; + } + + if (chunks_written < tcon->max_chunks) { + cifs_tcon_dbg(FYI, "Copychunk MaxChunks updated: %u -> %u\n", + tcon->max_chunks, chunks_written); + tcon->max_chunks = chunks_written; + } + + if (chunk_bytes < tcon->max_bytes_chunk) { + cifs_tcon_dbg(FYI, "Copychunk MaxBytesChunk updated: %u -> %u\n", + tcon->max_bytes_chunk, chunk_bytes); + tcon->max_bytes_chunk = chunk_bytes; + } + + /* reset to last offsets */ + if (retries++ < 2) { + src_off = src_off_prev; + dst_off = dst_off_prev; + kfree(cc_req); + cc_req = NULL; + goto retry; + } + + break; } -cchunk_out: - kfree(pcchunk); - kfree(retbuf); - if (rc) +out: + kfree(cc_req); + kfree(cc_rsp); + if (rc) { + trace_smb3_copychunk_err(xid, src_file->fid.volatile_fid, + dst_file->fid.volatile_fid, tcon->tid, + tcon->ses->Suid, src_off, dst_off, len, rc); return rc; - else - return total_bytes_written; + } else { + trace_smb3_copychunk_done(xid, src_file->fid.volatile_fid, + dst_file->fid.volatile_fid, tcon->tid, + tcon->ses->Suid, src_off, dst_off, len); + return len; + } } static int @@ -3281,7 +3367,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); - inode_lock(inode); filemap_invalidate_lock(inode->i_mapping); i_size = i_size_read(inode); @@ -3299,6 +3384,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, * first, otherwise the data may be inconsistent with the server. */ truncate_pagecache_range(inode, offset, offset + len - 1); + netfs_wait_for_outstanding_io(inode); /* if file not oplocked can't be sure whether asking to extend size */ rc = -EOPNOTSUPP; @@ -3327,7 +3413,6 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, zero_range_exit: filemap_invalidate_unlock(inode->i_mapping); - inode_unlock(inode); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid, @@ -3351,7 +3436,6 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode_lock(inode); /* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) { @@ -3365,6 +3449,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, * caches first, otherwise the data may be inconsistent with the server. */ truncate_pagecache_range(inode, offset, offset + len - 1); + netfs_wait_for_outstanding_io(inode); cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); @@ -3399,7 +3484,6 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, unlock: filemap_invalidate_unlock(inode->i_mapping); out: - inode_unlock(inode); free_xid(xid); return rc; } @@ -3663,8 +3747,6 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode_lock(inode); - old_eof = i_size_read(inode); if ((off >= old_eof) || off + len >= old_eof) { @@ -3679,6 +3761,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, truncate_pagecache_range(inode, off, old_eof); ictx->zero_point = old_eof; + netfs_wait_for_outstanding_io(inode); rc = smb2_copychunk_range(xid, cfile, cfile, off + len, old_eof - off - len, off); @@ -3699,8 +3782,7 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, fscache_resize_cookie(cifs_inode_cookie(inode), new_eof); out_2: filemap_invalidate_unlock(inode->i_mapping); - out: - inode_unlock(inode); +out: free_xid(xid); return rc; } @@ -3717,8 +3799,6 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, xid = get_xid(); - inode_lock(inode); - old_eof = i_size_read(inode); if (off >= old_eof) { rc = -EINVAL; @@ -3733,6 +3813,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, if (rc < 0) goto out_2; truncate_pagecache_range(inode, off, old_eof); + netfs_wait_for_outstanding_io(inode); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, new_eof); @@ -3755,8 +3836,7 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, rc = 0; out_2: filemap_invalidate_unlock(inode->i_mapping); - out: - inode_unlock(inode); +out: free_xid(xid); return rc; } @@ -4650,7 +4730,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, unsigned int pad_len; struct cifs_io_subrequest *rdata = mid->callback_data; struct smb2_hdr *shdr = (struct smb2_hdr *)buf; - int length; + size_t copied; bool use_rdma_mr = false; if (shdr->Command != SMB2_READ) { @@ -4763,10 +4843,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ WARN_ONCE(buffer, "read data can be either in buf or in buffer"); - length = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); - if (length < 0) - return length; - rdata->got_bytes = data_len; + copied = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter); + if (copied == 0) + return -EIO; + rdata->got_bytes = copied; } else { /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 42e2d4ea344d..b0739a2661bf 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3277,7 +3277,7 @@ replay_again: buf->EndOfFile = rsp->EndofFile; buf->Attributes = rsp->FileAttributes; buf->NumberOfLinks = cpu_to_le32(1); - buf->DeletePending = 0; + buf->DeletePending = 0; /* successful open = not delete pending */ } diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 3c09a58dfd07..101024f8f725 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -201,16 +201,20 @@ struct resume_key_req { char Context[]; /* ignored, Windows sets to 4 bytes of zero */ } __packed; + +struct copychunk { + __le64 SourceOffset; + __le64 TargetOffset; + __le32 Length; + __le32 Reserved; +} __packed; + /* this goes in the ioctl buffer when doing a copychunk request */ struct copychunk_ioctl { char SourceKey[COPY_CHUNK_RES_KEY_SIZE]; - __le32 ChunkCount; /* we are only sending 1 */ + __le32 ChunkCount; __le32 Reserved; - /* array will only be one chunk long for us */ - __le64 SourceOffset; - __le64 TargetOffset; - __le32 Length; /* how many bytes to copy */ - __u32 Reserved2; + struct copychunk Chunks[]; } __packed; struct copychunk_ioctl_rsp { diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index bc0e92eb2b64..33f33013b392 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -240,11 +240,6 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) return NULL; } tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); - if (!tcon) { - spin_unlock(&cifs_tcp_ses_lock); - cifs_put_smb_ses(ses); - return NULL; - } spin_unlock(&cifs_tcp_ses_lock); /* tcon already has a ref to ses, so we don't need ses anymore */ cifs_put_smb_ses(ses); diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index fd650e2afc76..28e00c34df1c 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -266,7 +266,7 @@ DEFINE_EVENT(smb3_copy_range_err_class, smb3_##name, \ TP_ARGS(xid, src_fid, target_fid, tid, sesid, src_offset, target_offset, len, rc)) DEFINE_SMB3_COPY_RANGE_ERR_EVENT(clone_err); -/* TODO: Add SMB3_COPY_RANGE_ERR_EVENT(copychunk_err) */ +DEFINE_SMB3_COPY_RANGE_ERR_EVENT(copychunk_err); DECLARE_EVENT_CLASS(smb3_copy_range_done_class, TP_PROTO(unsigned int xid, |