From fbc0b970ddfab4b35dad27ebaae712af680bdc7e Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Feb 2014 13:01:19 +0800 Subject: [PATCH 1/8] ceph: properly handle XATTR_CREATE and XATTR_REPLACE return -EEXIST if XATTR_CREATE is set and xattr alread exists. return -ENODATA if XATTR_REPLACE is set but xattr does not exist. Signed-off-by: Yan, Zheng --- fs/ceph/xattr.c | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 898b6565ad3e..28f9793b9167 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -319,8 +319,7 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode, static int __set_xattr(struct ceph_inode_info *ci, const char *name, int name_len, const char *val, int val_len, - int dirty, - int should_free_name, int should_free_val, + int flags, int update_xattr, struct ceph_inode_xattr **newxattr) { struct rb_node **p; @@ -349,12 +348,25 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr = NULL; } + if (update_xattr) { + int err = 0; + if (xattr && (flags & XATTR_CREATE)) + err = -EEXIST; + else if (!xattr && (flags & XATTR_REPLACE)) + err = -ENODATA; + if (err) { + kfree(name); + kfree(val); + return err; + } + } + if (!xattr) { new = 1; xattr = *newxattr; xattr->name = name; xattr->name_len = name_len; - xattr->should_free_name = should_free_name; + xattr->should_free_name = update_xattr; ci->i_xattrs.count++; dout("__set_xattr count=%d\n", ci->i_xattrs.count); @@ -364,7 +376,7 @@ static int __set_xattr(struct ceph_inode_info *ci, if (xattr->should_free_val) kfree((void *)xattr->val); - if (should_free_name) { + if (update_xattr) { kfree((void *)name); name = xattr->name; } @@ -379,8 +391,8 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr->val = ""; xattr->val_len = val_len; - xattr->dirty = dirty; - xattr->should_free_val = (val && should_free_val); + xattr->dirty = update_xattr; + xattr->should_free_val = (val && update_xattr); if (new) { rb_link_node(&xattr->node, parent, p); @@ -588,7 +600,7 @@ start: p += len; err = __set_xattr(ci, name, namelen, val, len, - 0, 0, 0, &xattrs[numattr]); + 0, 0, &xattrs[numattr]); if (err < 0) goto bad; @@ -892,7 +904,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name, struct ceph_inode_info *ci = ceph_inode(inode); int issued; int err; - int dirty; + int dirty = 0; int name_len = strlen(name); int val_len = size; char *newname = NULL; @@ -954,11 +966,13 @@ retry: } err = __set_xattr(ci, newname, name_len, newval, - val_len, 1, 1, 1, &xattr); + val_len, flags, 1, &xattr); - dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); - ci->i_xattrs.dirty = true; - inode->i_ctime = CURRENT_TIME; + if (!err) { + dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); + ci->i_xattrs.dirty = true; + inode->i_ctime = CURRENT_TIME; + } spin_unlock(&ci->i_ceph_lock); if (dirty) From bcdfeb2eb4e42b811950b9cd226109291051732a Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Feb 2014 13:04:19 +0800 Subject: [PATCH 2/8] ceph: remove xattr when null value is given to setxattr() For the setxattr request, introduce a new flag CEPH_XATTR_REMOVE to distinguish null value case from the zero-length value case. Signed-off-by: Yan, Zheng --- fs/ceph/xattr.c | 16 ++++++++++++++-- include/linux/ceph/ceph_fs.h | 5 +++-- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 28f9793b9167..231c02b16c0c 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -12,6 +12,9 @@ #define XATTR_CEPH_PREFIX "ceph." #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1) +static int __remove_xattr(struct ceph_inode_info *ci, + struct ceph_inode_xattr *xattr); + /* * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. @@ -359,6 +362,12 @@ static int __set_xattr(struct ceph_inode_info *ci, kfree(val); return err; } + if (update_xattr < 0) { + if (xattr) + __remove_xattr(ci, xattr); + kfree(name); + return 0; + } } if (!xattr) { @@ -862,6 +871,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name, dout("setxattr value=%.*s\n", (int)size, value); + if (!value) + flags |= CEPH_XATTR_REMOVE; + /* do request */ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR, USE_AUTH_MDS); @@ -965,8 +977,8 @@ retry: goto retry; } - err = __set_xattr(ci, newname, name_len, newval, - val_len, flags, 1, &xattr); + err = __set_xattr(ci, newname, name_len, newval, val_len, + flags, value ? 1 : -1, &xattr); if (!err) { dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 2623cffc73a1..25bfb0eff772 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -373,8 +373,9 @@ extern const char *ceph_mds_op_name(int op); /* * Ceph setxattr request flags. */ -#define CEPH_XATTR_CREATE 1 -#define CEPH_XATTR_REPLACE 2 +#define CEPH_XATTR_CREATE (1 << 0) +#define CEPH_XATTR_REPLACE (1 << 1) +#define CEPH_XATTR_REMOVE (1 << 31) union ceph_mds_request_args { struct { From 524186ace6c4dcc83975b858622a66888b018fd0 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Feb 2014 13:23:09 +0800 Subject: [PATCH 3/8] ceph: fix ceph_removexattr() Signed-off-by: Yan, Zheng --- fs/ceph/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 231c02b16c0c..a55ec37378c6 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -463,7 +463,7 @@ static int __remove_xattr(struct ceph_inode_info *ci, struct ceph_inode_xattr *xattr) { if (!xattr) - return -EOPNOTSUPP; + return -ENODATA; rb_erase(&xattr->node, &ci->i_xattrs.index); From 7a92d64760541e66bf5d1131f029b82773ce3922 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Feb 2014 13:08:51 +0800 Subject: [PATCH 4/8] ceph: fix ceph_set_acl() If acl is equivalent to file mode permission bits, ceph_set_acl() needs to remove any existing acl xattr. Use __ceph_setxattr() to handle both setting and removing acl xattr cases, it doesn't return -ENODATA when there is no acl xattr. Signed-off-by: Yan, Zheng --- fs/ceph/acl.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 4c2d452c4bfc..accc9f28bc10 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -160,11 +160,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) goto out_dput; } - if (value) - ret = __ceph_setxattr(dentry, name, value, size, 0); - else - ret = __ceph_removexattr(dentry, name); - + ret = __ceph_setxattr(dentry, name, value, size, 0); if (ret) { if (new_mode != old_mode) { newattrs.ia_mode = old_mode; From b20a95a0dd47c56c5d20e1c9e260293d0b87abe0 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Feb 2014 12:55:05 +0800 Subject: [PATCH 5/8] ceph: add missing init_acl() for mkdir() and atomic_open() Signed-off-by: Yan, Zheng --- fs/ceph/dir.c | 13 ++++++++----- fs/ceph/file.c | 1 + 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 6da4df84ba30..2e3b30dcfc94 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -695,9 +695,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry, ceph_mdsc_put_request(req); if (!err) - err = ceph_init_acl(dentry, dentry->d_inode, dir); - - if (err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } @@ -735,7 +734,9 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, if (!err && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); ceph_mdsc_put_request(req); - if (err) + if (!err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } @@ -776,7 +777,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) err = ceph_handle_notrace_create(dir, dentry); ceph_mdsc_put_request(req); out: - if (err < 0) + if (!err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index dfd2ce3419f8..09c7afe32e49 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -286,6 +286,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, } else { dout("atomic_open finish_open on dn %p\n", dn); if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) { + ceph_init_acl(dentry, dentry->d_inode, dir); *opened |= FILE_CREATED; } err = finish_open(file, dentry, ceph_open, opened); From c969d9bf91e1868d823351993216cd64dfab6a4c Mon Sep 17 00:00:00 2001 From: Guangliang Zhao Date: Sun, 16 Feb 2014 08:35:52 -0800 Subject: [PATCH 6/8] ceph: make ceph_forget_all_cached_acls() static inline Signed-off-by: Guangliang Zhao Reviewed-by: Alex Elder Signed-off-by: Sage Weil --- fs/ceph/acl.c | 5 ----- fs/ceph/super.h | 7 ++++++- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index accc9f28bc10..21887d63dad5 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -54,11 +54,6 @@ static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode, return acl; } -void ceph_forget_all_cached_acls(struct inode *inode) -{ - forget_all_cached_acls(inode); -} - struct posix_acl *ceph_get_acl(struct inode *inode, int type) { int size; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 19793b56d0a7..d8801a95b685 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -743,7 +744,11 @@ extern const struct xattr_handler *ceph_xattr_handlers[]; struct posix_acl *ceph_get_acl(struct inode *, int); int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type); int ceph_init_acl(struct dentry *, struct inode *, struct inode *); -void ceph_forget_all_cached_acls(struct inode *inode); + +static inline void ceph_forget_all_cached_acls(struct inode *inode) +{ + forget_all_cached_acls(inode); +} #else From 45195e42c78ea91135108207dbcaf75e5556a309 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Sun, 16 Feb 2014 10:05:29 -0800 Subject: [PATCH 7/8] ceph: add acl, noacl options for cephfs mount Make the 'acl' option dependent on having ACL support compiled in. Make the 'noacl' option work even without it so that one can always ask it to be off and not error out on mount when it is not supported. Signed-off-by: Guangliang Zhao Signed-off-by: Sage Weil --- fs/ceph/super.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 2df963f1cf5a..10a4ccbf38da 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -144,7 +144,11 @@ enum { Opt_ino32, Opt_noino32, Opt_fscache, - Opt_nofscache + Opt_nofscache, +#ifdef CONFIG_CEPH_FS_POSIX_ACL + Opt_acl, +#endif + Opt_noacl }; static match_table_t fsopt_tokens = { @@ -172,6 +176,10 @@ static match_table_t fsopt_tokens = { {Opt_noino32, "noino32"}, {Opt_fscache, "fsc"}, {Opt_nofscache, "nofsc"}, +#ifdef CONFIG_CEPH_FS_POSIX_ACL + {Opt_acl, "acl"}, +#endif + {Opt_noacl, "noacl"}, {-1, NULL} }; @@ -271,6 +279,14 @@ static int parse_fsopt_token(char *c, void *private) case Opt_nofscache: fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; break; +#ifdef CONFIG_CEPH_FS_POSIX_ACL + case Opt_acl: + fsopt->sb_flags |= MS_POSIXACL; + break; +#endif + case Opt_noacl: + fsopt->sb_flags &= ~MS_POSIXACL; + break; default: BUG_ON(token); } @@ -438,6 +454,13 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) else seq_puts(m, ",nofsc"); +#ifdef CONFIG_CEPH_FS_POSIX_ACL + if (fsopt->sb_flags & MS_POSIXACL) + seq_puts(m, ",acl"); + else + seq_puts(m, ",noacl"); +#endif + if (fsopt->wsize) seq_printf(m, ",wsize=%d", fsopt->wsize); if (fsopt->rsize != CEPH_RSIZE_DEFAULT) @@ -819,9 +842,6 @@ static int ceph_set_super(struct super_block *s, void *data) s->s_flags = fsc->mount_options->sb_flags; s->s_maxbytes = 1ULL << 40; /* temp value until we get mdsmap */ -#ifdef CONFIG_CEPH_FS_POSIX_ACL - s->s_flags |= MS_POSIXACL; -#endif s->s_xattr = ceph_xattr_handlers; s->s_fs_info = fsc; @@ -911,6 +931,10 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, struct ceph_options *opt = NULL; dout("ceph_mount\n"); + +#ifdef CONFIG_CEPH_FS_POSIX_ACL + flags |= MS_POSIXACL; +#endif err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path); if (err < 0) { res = ERR_PTR(err); From 4d5f5df673ee673851986b5a492a9752fbb39dc5 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 13 Feb 2014 19:40:26 +0800 Subject: [PATCH 8/8] ceph: fix __dcache_readdir() If directory is fragmented, readdir() read its dirfrags one by one. After reading all dirfrags, the corresponding dentries are sorted in (frag_t, off) order in the dcache. If dentries of a directory are all cached, __dcache_readdir() can use the cached dentries to satisfy readdir syscall. But when checking if a given dentry is after the position of readdir, __dcache_readdir() compares numerical value of frag_t directly. This is wrong, it should use ceph_frag_compare(). Signed-off-by: Yan, Zheng --- fs/ceph/dir.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 2e3b30dcfc94..45eda6d7a40c 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p) return p & 0xffffffff; } +static int fpos_cmp(loff_t l, loff_t r) +{ + int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r)); + if (v) + return v; + return (int)(fpos_off(l) - fpos_off(r)); +} + /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on @@ -156,7 +164,7 @@ more: if (!d_unhashed(dentry) && dentry->d_inode && ceph_snap(dentry->d_inode) != CEPH_SNAPDIR && ceph_ino(dentry->d_inode) != CEPH_INO_CEPH && - ctx->pos <= di->offset) + fpos_cmp(ctx->pos, di->offset) <= 0) break; dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry, dentry->d_name.len, dentry->d_name.name, di->offset,