diff options
Diffstat (limited to 'fs/ceph/xattr.c')
| -rw-r--r-- | fs/ceph/xattr.c | 721 |
1 files changed, 499 insertions, 222 deletions
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 316f6ad10644..ad1f30bea175 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -8,6 +8,7 @@ #include <linux/ceph/decode.h> #include <linux/xattr.h> +#include <linux/security.h> #include <linux/posix_acl_xattr.h> #include <linux/slab.h> @@ -17,26 +18,10 @@ static int __remove_xattr(struct ceph_inode_info *ci, struct ceph_inode_xattr *xattr); -static const struct xattr_handler ceph_other_xattr_handler; - -/* - * List of handlers for synthetic system.* attributes. Other - * attributes are handled directly. - */ -const struct xattr_handler *ceph_xattr_handlers[] = { -#ifdef CONFIG_CEPH_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif - &ceph_other_xattr_handler, - NULL, -}; - static bool ceph_is_valid_xattr(const char *name) { - return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) || - !strncmp(name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN) || + return !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || + !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) || !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN); } @@ -48,8 +33,8 @@ static bool ceph_is_valid_xattr(const char *name) struct ceph_vxattr { char *name; size_t name_size; /* strlen(name) + 1 (for '\0') */ - size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val, - size_t size); + ssize_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val, + size_t size); bool (*exists_cb)(struct ceph_inode_info *ci); unsigned int flags; }; @@ -57,6 +42,7 @@ struct ceph_vxattr { #define VXATTR_FLAG_READONLY (1<<0) #define VXATTR_FLAG_HIDDEN (1<<1) #define VXATTR_FLAG_RSTAT (1<<2) +#define VXATTR_FLAG_DIRSTAT (1<<3) /* layouts */ @@ -68,10 +54,11 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci) rcu_dereference_raw(fl->pool_ns) != NULL); } -static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, + size_t size) { - struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb); + struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb); + struct ceph_client *cl = fsc->client; struct ceph_osd_client *osdc = &fsc->client->osdc; struct ceph_string *pool_ns; s64 pool = ci->i_layout.pool_id; @@ -79,11 +66,11 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, const char *ns_field = " pool_namespace="; char buf[128]; size_t len, total_len = 0; - int ret; + ssize_t ret; pool_ns = ceph_try_get_string(ci->i_layout.pool_ns); - dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode); + doutc(cl, "%p\n", &ci->netfs.inode); down_read(&osdc->lock); pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool); if (pool_name) { @@ -96,18 +83,15 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, len = snprintf(buf, sizeof(buf), "stripe_unit=%u stripe_count=%u object_size=%u pool=%lld", ci->i_layout.stripe_unit, ci->i_layout.stripe_count, - ci->i_layout.object_size, (unsigned long long)pool); + ci->i_layout.object_size, pool); total_len = len; } if (pool_ns) total_len += strlen(ns_field) + pool_ns->len; - if (!size) { - ret = total_len; - } else if (total_len > size) { - ret = -ERANGE; - } else { + ret = total_len; + if (size >= total_len) { memcpy(val, buf, len); ret = len; if (pool_name) { @@ -128,50 +112,84 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val, return ret; } -static size_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci, - char *val, size_t size) +/* + * The convention with strings in xattrs is that they should not be NULL + * terminated, since we're returning the length with them. snprintf always + * NULL terminates however, so call it on a temporary buffer and then memcpy + * the result into place. + */ +static __printf(3, 4) +int ceph_fmt_xattr(char *val, size_t size, const char *fmt, ...) { - return snprintf(val, size, "%u", ci->i_layout.stripe_unit); + int ret; + va_list args; + char buf[96]; /* NB: reevaluate size if new vxattrs are added */ + + va_start(args, fmt); + ret = vsnprintf(buf, size ? sizeof(buf) : 0, fmt, args); + va_end(args); + + /* Sanity check */ + if (size && ret + 1 > sizeof(buf)) { + WARN_ONCE(true, "Returned length too big (%d)", ret); + return -E2BIG; + } + + if (ret <= size) + memcpy(val, buf, ret); + return ret; } -static size_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci, +static ssize_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci, char *val, size_t size) { - return snprintf(val, size, "%u", ci->i_layout.stripe_count); + return ceph_fmt_xattr(val, size, "%u", ci->i_layout.stripe_unit); } -static size_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci, - char *val, size_t size) +static ssize_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci, + char *val, size_t size) { - return snprintf(val, size, "%u", ci->i_layout.object_size); + return ceph_fmt_xattr(val, size, "%u", ci->i_layout.stripe_count); } -static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci, - char *val, size_t size) +static ssize_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci, + char *val, size_t size) { - int ret; - struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb); + return ceph_fmt_xattr(val, size, "%u", ci->i_layout.object_size); +} + +static ssize_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci, + char *val, size_t size) +{ + ssize_t ret; + struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb); struct ceph_osd_client *osdc = &fsc->client->osdc; s64 pool = ci->i_layout.pool_id; const char *pool_name; down_read(&osdc->lock); pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool); - if (pool_name) - ret = snprintf(val, size, "%s", pool_name); - else - ret = snprintf(val, size, "%lld", (unsigned long long)pool); + if (pool_name) { + ret = strlen(pool_name); + if (ret <= size) + memcpy(val, pool_name, ret); + } else { + ret = ceph_fmt_xattr(val, size, "%lld", pool); + } up_read(&osdc->lock); return ret; } -static size_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci, - char *val, size_t size) +static ssize_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci, + char *val, size_t size) { - int ret = 0; + ssize_t ret = 0; struct ceph_string *ns = ceph_try_get_string(ci->i_layout.pool_ns); + if (ns) { - ret = snprintf(val, size, "%.*s", (int)ns->len, ns->str); + ret = ns->len; + if (ret <= size) + memcpy(val, ns->str, ret); ceph_put_string(ns); } return ret; @@ -179,57 +197,74 @@ static size_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci, /* directories */ -static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val, + size_t size) +{ + return ceph_fmt_xattr(val, size, "%lld", ci->i_files + ci->i_subdirs); +} + +static ssize_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val, + size_t size) +{ + return ceph_fmt_xattr(val, size, "%lld", ci->i_files); +} + +static ssize_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs); + return ceph_fmt_xattr(val, size, "%lld", ci->i_subdirs); } -static size_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "%lld", ci->i_files); + return ceph_fmt_xattr(val, size, "%lld", + ci->i_rfiles + ci->i_rsubdirs); } -static size_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val, +static ssize_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val, size_t size) { - return snprintf(val, size, "%lld", ci->i_subdirs); + return ceph_fmt_xattr(val, size, "%lld", ci->i_rfiles); } -static size_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs); + return ceph_fmt_xattr(val, size, "%lld", ci->i_rsubdirs); } -static size_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_dir_rsnaps(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "%lld", ci->i_rfiles); + return ceph_fmt_xattr(val, size, "%lld", ci->i_rsnaps); } -static size_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "%lld", ci->i_rsubdirs); + return ceph_fmt_xattr(val, size, "%lld", ci->i_rbytes); } -static size_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "%lld", ci->i_rbytes); + return ceph_fmt_xattr(val, size, "%ptSp", &ci->i_rctime); } -static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val, - size_t size) +/* dir pin */ +static bool ceph_vxattrcb_dir_pin_exists(struct ceph_inode_info *ci) { - return snprintf(val, size, "%lld.09%ld", ci->i_rctime.tv_sec, - ci->i_rctime.tv_nsec); + return ci->i_dir_pin != -ENODATA; } -/* quotas */ +static ssize_t ceph_vxattrcb_dir_pin(struct ceph_inode_info *ci, char *val, + size_t size) +{ + return ceph_fmt_xattr(val, size, "%d", (int)ci->i_dir_pin); +} +/* quotas */ static bool ceph_vxattrcb_quota_exists(struct ceph_inode_info *ci) { bool ret = false; @@ -243,25 +278,97 @@ static bool ceph_vxattrcb_quota_exists(struct ceph_inode_info *ci) return ret; } -static size_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val, - size_t size) +static ssize_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val, + size_t size) { - return snprintf(val, size, "max_bytes=%llu max_files=%llu", - ci->i_max_bytes, ci->i_max_files); + return ceph_fmt_xattr(val, size, "max_bytes=%llu max_files=%llu", + ci->i_max_bytes, ci->i_max_files); } -static size_t ceph_vxattrcb_quota_max_bytes(struct ceph_inode_info *ci, - char *val, size_t size) +static ssize_t ceph_vxattrcb_quota_max_bytes(struct ceph_inode_info *ci, + char *val, size_t size) { - return snprintf(val, size, "%llu", ci->i_max_bytes); + return ceph_fmt_xattr(val, size, "%llu", ci->i_max_bytes); } -static size_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci, - char *val, size_t size) +static ssize_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci, + char *val, size_t size) { - return snprintf(val, size, "%llu", ci->i_max_files); + return ceph_fmt_xattr(val, size, "%llu", ci->i_max_files); } +/* snapshots */ +static bool ceph_vxattrcb_snap_btime_exists(struct ceph_inode_info *ci) +{ + return (ci->i_snap_btime.tv_sec != 0 || ci->i_snap_btime.tv_nsec != 0); +} + +static ssize_t ceph_vxattrcb_snap_btime(struct ceph_inode_info *ci, char *val, + size_t size) +{ + return ceph_fmt_xattr(val, size, "%ptSp", &ci->i_snap_btime); +} + +static ssize_t ceph_vxattrcb_cluster_fsid(struct ceph_inode_info *ci, + char *val, size_t size) +{ + struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb); + + return ceph_fmt_xattr(val, size, "%pU", &fsc->client->fsid); +} + +static ssize_t ceph_vxattrcb_client_id(struct ceph_inode_info *ci, + char *val, size_t size) +{ + struct ceph_fs_client *fsc = ceph_sb_to_fs_client(ci->netfs.inode.i_sb); + + return ceph_fmt_xattr(val, size, "client%lld", + ceph_client_gid(fsc->client)); +} + +static ssize_t ceph_vxattrcb_caps(struct ceph_inode_info *ci, char *val, + size_t size) +{ + int issued; + + spin_lock(&ci->i_ceph_lock); + issued = __ceph_caps_issued(ci, NULL); + spin_unlock(&ci->i_ceph_lock); + + return ceph_fmt_xattr(val, size, "%s/0x%x", + ceph_cap_string(issued), issued); +} + +static ssize_t ceph_vxattrcb_auth_mds(struct ceph_inode_info *ci, + char *val, size_t size) +{ + int ret; + + spin_lock(&ci->i_ceph_lock); + ret = ceph_fmt_xattr(val, size, "%d", + ci->i_auth_cap ? ci->i_auth_cap->session->s_mds : -1); + spin_unlock(&ci->i_ceph_lock); + return ret; +} + +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) +static bool ceph_vxattrcb_fscrypt_auth_exists(struct ceph_inode_info *ci) +{ + return ci->fscrypt_auth_len; +} + +static ssize_t ceph_vxattrcb_fscrypt_auth(struct ceph_inode_info *ci, + char *val, size_t size) +{ + if (size) { + if (size < ci->fscrypt_auth_len) + return -ERANGE; + memcpy(val, ci->fscrypt_auth, ci->fscrypt_auth_len); + } + return ci->fscrypt_auth_len; +} +#endif /* CONFIG_FS_ENCRYPTION */ + #define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name #define CEPH_XATTR_NAME2(_type, _name, _name2) \ XATTR_CEPH_PREFIX #_type "." #_name "." #_name2 @@ -276,6 +383,14 @@ static size_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci, } #define XATTR_RSTAT_FIELD(_type, _name) \ XATTR_NAME_CEPH(_type, _name, VXATTR_FLAG_RSTAT) +#define XATTR_RSTAT_FIELD_UPDATABLE(_type, _name) \ + { \ + .name = CEPH_XATTR_NAME(_type, _name), \ + .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \ + .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \ + .exists_cb = NULL, \ + .flags = VXATTR_FLAG_RSTAT, \ + } #define XATTR_LAYOUT_FIELD(_type, _name, _field) \ { \ .name = CEPH_XATTR_NAME2(_type, _name, _field), \ @@ -306,14 +421,22 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = { XATTR_LAYOUT_FIELD(dir, layout, object_size), XATTR_LAYOUT_FIELD(dir, layout, pool), XATTR_LAYOUT_FIELD(dir, layout, pool_namespace), - XATTR_NAME_CEPH(dir, entries, 0), - XATTR_NAME_CEPH(dir, files, 0), - XATTR_NAME_CEPH(dir, subdirs, 0), + XATTR_NAME_CEPH(dir, entries, VXATTR_FLAG_DIRSTAT), + XATTR_NAME_CEPH(dir, files, VXATTR_FLAG_DIRSTAT), + XATTR_NAME_CEPH(dir, subdirs, VXATTR_FLAG_DIRSTAT), XATTR_RSTAT_FIELD(dir, rentries), XATTR_RSTAT_FIELD(dir, rfiles), XATTR_RSTAT_FIELD(dir, rsubdirs), + XATTR_RSTAT_FIELD(dir, rsnaps), XATTR_RSTAT_FIELD(dir, rbytes), - XATTR_RSTAT_FIELD(dir, rctime), + XATTR_RSTAT_FIELD_UPDATABLE(dir, rctime), + { + .name = "ceph.dir.pin", + .name_size = sizeof("ceph.dir.pin"), + .getxattr_cb = ceph_vxattrcb_dir_pin, + .exists_cb = ceph_vxattrcb_dir_pin_exists, + .flags = VXATTR_FLAG_HIDDEN, + }, { .name = "ceph.quota", .name_size = sizeof("ceph.quota"), @@ -323,9 +446,22 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = { }, XATTR_QUOTA_FIELD(quota, max_bytes), XATTR_QUOTA_FIELD(quota, max_files), + { + .name = "ceph.snap.btime", + .name_size = sizeof("ceph.snap.btime"), + .getxattr_cb = ceph_vxattrcb_snap_btime, + .exists_cb = ceph_vxattrcb_snap_btime_exists, + .flags = VXATTR_FLAG_READONLY, + }, + { + .name = "ceph.caps", + .name_size = sizeof("ceph.caps"), + .getxattr_cb = ceph_vxattrcb_caps, + .exists_cb = NULL, + .flags = VXATTR_FLAG_HIDDEN, + }, { .name = NULL, 0 } /* Required table terminator */ }; -static size_t ceph_dir_vxattrs_name_size; /* total size of all names */ /* files */ @@ -342,9 +478,56 @@ static struct ceph_vxattr ceph_file_vxattrs[] = { XATTR_LAYOUT_FIELD(file, layout, object_size), XATTR_LAYOUT_FIELD(file, layout, pool), XATTR_LAYOUT_FIELD(file, layout, pool_namespace), + { + .name = "ceph.snap.btime", + .name_size = sizeof("ceph.snap.btime"), + .getxattr_cb = ceph_vxattrcb_snap_btime, + .exists_cb = ceph_vxattrcb_snap_btime_exists, + .flags = VXATTR_FLAG_READONLY, + }, + { + .name = "ceph.caps", + .name_size = sizeof("ceph.caps"), + .getxattr_cb = ceph_vxattrcb_caps, + .exists_cb = NULL, + .flags = VXATTR_FLAG_HIDDEN, + }, + { .name = NULL, 0 } /* Required table terminator */ +}; + +static struct ceph_vxattr ceph_common_vxattrs[] = { + { + .name = "ceph.cluster_fsid", + .name_size = sizeof("ceph.cluster_fsid"), + .getxattr_cb = ceph_vxattrcb_cluster_fsid, + .exists_cb = NULL, + .flags = VXATTR_FLAG_READONLY, + }, + { + .name = "ceph.client_id", + .name_size = sizeof("ceph.client_id"), + .getxattr_cb = ceph_vxattrcb_client_id, + .exists_cb = NULL, + .flags = VXATTR_FLAG_READONLY, + }, + { + .name = "ceph.auth_mds", + .name_size = sizeof("ceph.auth_mds"), + .getxattr_cb = ceph_vxattrcb_auth_mds, + .exists_cb = NULL, + .flags = VXATTR_FLAG_READONLY, + }, +#if IS_ENABLED(CONFIG_FS_ENCRYPTION) + { + .name = "ceph.fscrypt.auth", + .name_size = sizeof("ceph.fscrypt.auth"), + .getxattr_cb = ceph_vxattrcb_fscrypt_auth, + .exists_cb = ceph_vxattrcb_fscrypt_auth_exists, + .flags = VXATTR_FLAG_READONLY, + }, +#endif /* CONFIG_FS_ENCRYPTION */ { .name = NULL, 0 } /* Required table terminator */ }; -static size_t ceph_file_vxattrs_name_size; /* total size of all names */ static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode) { @@ -355,47 +538,6 @@ static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode) return NULL; } -static size_t ceph_vxattrs_name_size(struct ceph_vxattr *vxattrs) -{ - if (vxattrs == ceph_dir_vxattrs) - return ceph_dir_vxattrs_name_size; - if (vxattrs == ceph_file_vxattrs) - return ceph_file_vxattrs_name_size; - BUG_ON(vxattrs); - return 0; -} - -/* - * Compute the aggregate size (including terminating '\0') of all - * virtual extended attribute names in the given vxattr table. - */ -static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs) -{ - struct ceph_vxattr *vxattr; - size_t size = 0; - - for (vxattr = vxattrs; vxattr->name; vxattr++) { - if (!(vxattr->flags & VXATTR_FLAG_HIDDEN)) - size += vxattr->name_size; - } - - return size; -} - -/* Routines called at initialization and exit time */ - -void __init ceph_xattr_init(void) -{ - ceph_dir_vxattrs_name_size = vxattrs_name_size(ceph_dir_vxattrs); - ceph_file_vxattrs_name_size = vxattrs_name_size(ceph_file_vxattrs); -} - -void ceph_xattr_exit(void) -{ - ceph_dir_vxattrs_name_size = 0; - ceph_file_vxattrs_name_size = 0; -} - static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode, const char *name) { @@ -409,15 +551,26 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode, } } + vxattr = ceph_common_vxattrs; + while (vxattr->name) { + if (!strcmp(vxattr->name, name)) + return vxattr; + vxattr++; + } + return NULL; } +#define MAX_XATTR_VAL_PRINT_LEN 256 + static int __set_xattr(struct ceph_inode_info *ci, const char *name, int name_len, const char *val, int val_len, int flags, int update_xattr, struct ceph_inode_xattr **newxattr) { + struct inode *inode = &ci->netfs.inode; + struct ceph_client *cl = ceph_inode_to_client(inode); struct rb_node **p; struct rb_node *parent = NULL; struct ceph_inode_xattr *xattr = NULL; @@ -474,15 +627,15 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr->should_free_name = update_xattr; ci->i_xattrs.count++; - dout("__set_xattr count=%d\n", ci->i_xattrs.count); + doutc(cl, "count=%d\n", ci->i_xattrs.count); } else { kfree(*newxattr); *newxattr = NULL; if (xattr->should_free_val) - kfree((void *)xattr->val); + kfree(xattr->val); if (update_xattr) { - kfree((void *)name); + kfree(name); name = xattr->name; } ci->i_xattrs.names_size -= xattr->name_len; @@ -502,11 +655,13 @@ static int __set_xattr(struct ceph_inode_info *ci, if (new) { rb_link_node(&xattr->node, parent, p); rb_insert_color(&xattr->node, &ci->i_xattrs.index); - dout("__set_xattr_val p=%p\n", p); + doutc(cl, "p=%p\n", p); } - dout("__set_xattr_val added %llx.%llx xattr %p %s=%.*s\n", - ceph_vinop(&ci->vfs_inode), xattr, name, val_len, val); + doutc(cl, "added %p %llx.%llx xattr %p %.*s=%.*s%s\n", inode, + ceph_vinop(inode), xattr, name_len, name, min(val_len, + MAX_XATTR_VAL_PRINT_LEN), val, + val_len > MAX_XATTR_VAL_PRINT_LEN ? "..." : ""); return 0; } @@ -514,6 +669,7 @@ static int __set_xattr(struct ceph_inode_info *ci, static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci, const char *name) { + struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode); struct rb_node **p; struct rb_node *parent = NULL; struct ceph_inode_xattr *xattr = NULL; @@ -532,13 +688,15 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci, else if (c > 0) p = &(*p)->rb_right; else { - dout("__get_xattr %s: found %.*s\n", name, - xattr->val_len, xattr->val); + int len = min(xattr->val_len, MAX_XATTR_VAL_PRINT_LEN); + + doutc(cl, "%s found %.*s%s\n", name, len, xattr->val, + xattr->val_len > len ? "..." : ""); return xattr; } } - dout("__get_xattr %s: not found\n", name); + doutc(cl, "%s not found\n", name); return NULL; } @@ -548,9 +706,9 @@ static void __free_xattr(struct ceph_inode_xattr *xattr) BUG_ON(!xattr); if (xattr->should_free_name) - kfree((void *)xattr->name); + kfree(xattr->name); if (xattr->should_free_val) - kfree((void *)xattr->val); + kfree(xattr->val); kfree(xattr); } @@ -564,9 +722,9 @@ static int __remove_xattr(struct ceph_inode_info *ci, rb_erase(&xattr->node, &ci->i_xattrs.index); if (xattr->should_free_name) - kfree((void *)xattr->name); + kfree(xattr->name); if (xattr->should_free_val) - kfree((void *)xattr->val); + kfree(xattr->val); ci->i_xattrs.names_size -= xattr->name_len; ci->i_xattrs.vals_size -= xattr->val_len; @@ -579,19 +737,20 @@ static int __remove_xattr(struct ceph_inode_info *ci, static char *__copy_xattr_names(struct ceph_inode_info *ci, char *dest) { + struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode); struct rb_node *p; struct ceph_inode_xattr *xattr = NULL; p = rb_first(&ci->i_xattrs.index); - dout("__copy_xattr_names count=%d\n", ci->i_xattrs.count); + doutc(cl, "count=%d\n", ci->i_xattrs.count); while (p) { xattr = rb_entry(p, struct ceph_inode_xattr, node); memcpy(dest, xattr->name, xattr->name_len); dest[xattr->name_len] = '\0'; - dout("dest=%s %p (%s) (%d/%d)\n", dest, xattr, xattr->name, - xattr->name_len, ci->i_xattrs.names_size); + doutc(cl, "dest=%s %p (%s) (%d/%d)\n", dest, xattr, xattr->name, + xattr->name_len, ci->i_xattrs.names_size); dest += xattr->name_len + 1; p = rb_next(p); @@ -602,19 +761,19 @@ static char *__copy_xattr_names(struct ceph_inode_info *ci, void __ceph_destroy_xattrs(struct ceph_inode_info *ci) { + struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode); struct rb_node *p, *tmp; struct ceph_inode_xattr *xattr = NULL; p = rb_first(&ci->i_xattrs.index); - dout("__ceph_destroy_xattrs p=%p\n", p); + doutc(cl, "p=%p\n", p); while (p) { xattr = rb_entry(p, struct ceph_inode_xattr, node); tmp = p; p = rb_next(tmp); - dout("__ceph_destroy_xattrs next p=%p (%.*s)\n", p, - xattr->name_len, xattr->name); + doutc(cl, "next p=%p (%.*s)\n", p, xattr->name_len, xattr->name); rb_erase(tmp, &ci->i_xattrs.index); __free_xattr(xattr); @@ -631,19 +790,20 @@ static int __build_xattrs(struct inode *inode) __releases(ci->i_ceph_lock) __acquires(ci->i_ceph_lock) { + struct ceph_client *cl = ceph_inode_to_client(inode); u32 namelen; u32 numattr = 0; void *p, *end; u32 len; const char *name, *val; struct ceph_inode_info *ci = ceph_inode(inode); - int xattr_version; + u64 xattr_version; struct ceph_inode_xattr **xattrs = NULL; int err = 0; int i; - dout("__build_xattrs() len=%d\n", - ci->i_xattrs.blob ? (int)ci->i_xattrs.blob->vec.iov_len : 0); + doutc(cl, "len=%d\n", + ci->i_xattrs.blob ? (int)ci->i_xattrs.blob->vec.iov_len : 0); if (ci->i_xattrs.index_version >= ci->i_xattrs.version) return 0; /* already built */ @@ -718,6 +878,8 @@ bad: static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size, int val_size) { + struct ceph_client *cl = ceph_inode_to_client(&ci->netfs.inode); + /* * 4 bytes for the length, and additional 4 bytes per each xattr name, * 4 bytes per each value @@ -725,9 +887,8 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size, int size = 4 + ci->i_xattrs.count*(4 + 4) + ci->i_xattrs.names_size + ci->i_xattrs.vals_size; - dout("__get_required_blob_size c=%d names.size=%d vals.size=%d\n", - ci->i_xattrs.count, ci->i_xattrs.names_size, - ci->i_xattrs.vals_size); + doutc(cl, "c=%d names.size=%d vals.size=%d\n", ci->i_xattrs.count, + ci->i_xattrs.names_size, ci->i_xattrs.vals_size); if (name_size) size += 4 + 4 + name_size + val_size; @@ -736,16 +897,21 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size, } /* - * If there are dirty xattrs, reencode xattrs into the prealloc_blob - * and swap into place. + * If there are dirty xattrs, re-encode xattrs into the prealloc_blob + * and swap into place. It returns the old i_xattrs.blob (or NULL) so + * that it can be freed by the caller as the i_ceph_lock is likely to be + * held. */ -void __ceph_build_xattrs_blob(struct ceph_inode_info *ci) +struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci) { + struct inode *inode = &ci->netfs.inode; + struct ceph_client *cl = ceph_inode_to_client(inode); struct rb_node *p; struct ceph_inode_xattr *xattr = NULL; + struct ceph_buffer *old_blob = NULL; void *dest; - dout("__build_xattrs_blob %p\n", &ci->vfs_inode); + doutc(cl, "%p %llx.%llx\n", inode, ceph_vinop(inode)); if (ci->i_xattrs.dirty) { int need = __get_required_blob_size(ci, 0, 0); @@ -773,12 +939,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci) dest - ci->i_xattrs.prealloc_blob->vec.iov_base; if (ci->i_xattrs.blob) - ceph_buffer_put(ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = NULL; ci->i_xattrs.dirty = false; ci->i_xattrs.version++; } + + return old_blob; } static inline int __get_request_mask(struct inode *in) { @@ -801,11 +969,15 @@ static inline int __get_request_mask(struct inode *in) { ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, size_t size) { + struct ceph_client *cl = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_inode_xattr *xattr; - struct ceph_vxattr *vxattr = NULL; + struct ceph_vxattr *vxattr; int req_mask; - int err; + ssize_t err; + + if (strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN)) + goto handle_non_vxattrs; /* let's see if a virtual xattr was requested */ vxattr = ceph_match_vxattr(inode, name); @@ -813,30 +985,43 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, int mask = 0; if (vxattr->flags & VXATTR_FLAG_RSTAT) mask |= CEPH_STAT_RSTAT; + if (vxattr->flags & VXATTR_FLAG_DIRSTAT) + mask |= CEPH_CAP_FILE_SHARED; err = ceph_do_getattr(inode, mask, true); if (err) return err; err = -ENODATA; - if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) + if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) { err = vxattr->getxattr_cb(ci, value, size); + if (size && size < err) + err = -ERANGE; + } + return err; + } else { + err = ceph_do_getvxattr(inode, name, value, size); + /* this would happen with a new client and old server combo */ + if (err == -EOPNOTSUPP) + err = -ENODATA; return err; } - +handle_non_vxattrs: req_mask = __get_request_mask(inode); spin_lock(&ci->i_ceph_lock); - dout("getxattr %p ver=%lld index_ver=%lld\n", inode, - ci->i_xattrs.version, ci->i_xattrs.index_version); + doutc(cl, "%p %llx.%llx name '%s' ver=%lld index_ver=%lld\n", inode, + ceph_vinop(inode), name, ci->i_xattrs.version, + ci->i_xattrs.index_version); if (ci->i_xattrs.version == 0 || !((req_mask & CEPH_CAP_XATTR_SHARED) || - __ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1))) { + __ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1))) { spin_unlock(&ci->i_ceph_lock); /* security module gets xattr while filling trace */ if (current->journal_info) { - pr_warn_ratelimited("sync getxattr %p " - "during filling trace\n", inode); + pr_warn_ratelimited_client(cl, + "sync %p %llx.%llx during filling trace\n", + inode, ceph_vinop(inode)); return -EBUSY; } @@ -867,7 +1052,8 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, memcpy(value, xattr->val, xattr->val_len); if (current->journal_info && - !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) + !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && + security_ismaclabel(name + XATTR_SECURITY_PREFIX_LEN)) ci->i_ceph_flags |= CEPH_I_SEC_INITED; out: spin_unlock(&ci->i_ceph_lock); @@ -877,20 +1063,19 @@ out: ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size) { struct inode *inode = d_inode(dentry); + struct ceph_client *cl = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_vxattr *vxattrs = ceph_inode_vxattrs(inode); - u32 vir_namelen = 0; + bool len_only = (size == 0); u32 namelen; int err; - u32 len; - int i; spin_lock(&ci->i_ceph_lock); - dout("listxattr %p ver=%lld index_ver=%lld\n", inode, - ci->i_xattrs.version, ci->i_xattrs.index_version); + doutc(cl, "%p %llx.%llx ver=%lld index_ver=%lld\n", inode, + ceph_vinop(inode), ci->i_xattrs.version, + ci->i_xattrs.index_version); if (ci->i_xattrs.version == 0 || - !__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1)) { + !__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1)) { spin_unlock(&ci->i_ceph_lock); err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true); if (err) @@ -901,38 +1086,18 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size) err = __build_xattrs(inode); if (err < 0) goto out; - /* - * Start with virtual dir xattr names (if any) (including - * terminating '\0' characters for each). - */ - vir_namelen = ceph_vxattrs_name_size(vxattrs); - /* adding 1 byte per each variable due to the null termination */ + /* add 1 byte for each xattr due to the null termination */ namelen = ci->i_xattrs.names_size + ci->i_xattrs.count; - err = -ERANGE; - if (size && vir_namelen + namelen > size) - goto out; - - err = namelen + vir_namelen; - if (size == 0) - goto out; - - names = __copy_xattr_names(ci, names); - - /* virtual xattr names, too */ - err = namelen; - if (vxattrs) { - for (i = 0; vxattrs[i].name; i++) { - if (!(vxattrs[i].flags & VXATTR_FLAG_HIDDEN) && - !(vxattrs[i].exists_cb && - !vxattrs[i].exists_cb(ci))) { - len = sprintf(names, "%s", vxattrs[i].name); - names += len + 1; - err += len + 1; - } + if (!len_only) { + if (namelen > size) { + err = -ERANGE; + goto out; } + names = __copy_xattr_names(ci, names); + size -= namelen; } - + err = namelen; out: spin_unlock(&ci->i_ceph_lock); return err; @@ -941,10 +1106,12 @@ out: static int ceph_sync_setxattr(struct inode *inode, const char *name, const char *value, size_t size, int flags) { - struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); + struct ceph_fs_client *fsc = ceph_sb_to_fs_client(inode->i_sb); + struct ceph_client *cl = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req; struct ceph_mds_client *mdsc = fsc->mdsc; + struct ceph_osd_client *osdc = &fsc->client->osdc; struct ceph_pagelist *pagelist = NULL; int op = CEPH_MDS_OP_SETXATTR; int err; @@ -965,7 +1132,7 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name, flags |= CEPH_XATTR_REMOVE; } - dout("setxattr value=%.*s\n", (int)size, value); + doutc(cl, "name %s value size %zu\n", name, size); /* do request */ req = ceph_mdsc_create_request(mdsc, op, USE_AUTH_MDS); @@ -983,6 +1150,8 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name, if (op == CEPH_MDS_OP_SETXATTR) { req->r_args.setxattr.flags = cpu_to_le32(flags); + req->r_args.setxattr.osdmap_epoch = + cpu_to_le32(osdc->osdmap->epoch); req->r_pagelist = pagelist; pagelist = NULL; } @@ -992,10 +1161,10 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name, req->r_num_caps = 1; req->r_inode_drop = CEPH_CAP_XATTR_SHARED; - dout("xattr.ver (before): %lld\n", ci->i_xattrs.version); + doutc(cl, "xattr.ver (before): %lld\n", ci->i_xattrs.version); err = ceph_mdsc_do_request(mdsc, NULL, req); ceph_mdsc_put_request(req); - dout("xattr.ver (after): %lld\n", ci->i_xattrs.version); + doutc(cl, "xattr.ver (after): %lld\n", ci->i_xattrs.version); out: if (pagelist) @@ -1006,10 +1175,12 @@ out: int __ceph_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags) { + struct ceph_client *cl = ceph_inode_to_client(inode); struct ceph_vxattr *vxattr; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; + struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(inode->i_sb)->mdsc; struct ceph_cap_flush *prealloc_cf = NULL; + struct ceph_buffer *old_blob = NULL; int issued; int err; int dirty = 0; @@ -1060,8 +1231,14 @@ int __ceph_setxattr(struct inode *inode, const char *name, spin_lock(&ci->i_ceph_lock); retry: issued = __ceph_caps_issued(ci, NULL); - if (ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) + required_blob_size = __get_required_blob_size(ci, name_len, val_len); + if ((ci->i_xattrs.version == 0) || !(issued & CEPH_CAP_XATTR_EXCL) || + (required_blob_size > mdsc->mdsmap->m_max_xattr_size)) { + doutc(cl, "sync version: %llu size: %d max: %llu\n", + ci->i_xattrs.version, required_blob_size, + mdsc->mdsmap->m_max_xattr_size); goto do_sync; + } if (!lock_snap_rwsem && !ci->i_head_snapc) { lock_snap_rwsem = true; @@ -1073,23 +1250,25 @@ retry: } } - dout("setxattr %p issued %s\n", inode, ceph_cap_string(issued)); + doutc(cl, "%p %llx.%llx name '%s' issued %s\n", inode, + ceph_vinop(inode), name, ceph_cap_string(issued)); __build_xattrs(inode); - required_blob_size = __get_required_blob_size(ci, name_len, val_len); - if (!ci->i_xattrs.prealloc_blob || required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) { struct ceph_buffer *blob; spin_unlock(&ci->i_ceph_lock); - dout(" preaallocating new blob size=%d\n", required_blob_size); + ceph_buffer_put(old_blob); /* Shouldn't be required */ + doutc(cl, " pre-allocating new blob size=%d\n", + required_blob_size); blob = ceph_buffer_new(required_blob_size, GFP_NOFS); if (!blob) goto do_sync_unlocked; spin_lock(&ci->i_ceph_lock); + /* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) - ceph_buffer_put(ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; } @@ -1101,10 +1280,11 @@ retry: dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL, &prealloc_cf); ci->i_xattrs.dirty = true; - inode->i_ctime = current_time(inode); + inode_set_ctime_current(inode); } spin_unlock(&ci->i_ceph_lock); + ceph_buffer_put(old_blob); if (lock_snap_rwsem) up_read(&mdsc->snap_rwsem); if (dirty) @@ -1120,8 +1300,9 @@ do_sync_unlocked: /* security module set xattr while filling trace */ if (current->journal_info) { - pr_warn_ratelimited("sync setxattr %p " - "during filling trace\n", inode); + pr_warn_ratelimited_client(cl, + "sync %p %llx.%llx during filling trace\n", + inode, ceph_vinop(inode)); err = -EBUSY; } else { err = ceph_sync_setxattr(inode, name, value, size, flags); @@ -1153,6 +1334,7 @@ static int ceph_get_xattr_handler(const struct xattr_handler *handler, } static int ceph_set_xattr_handler(const struct xattr_handler *handler, + struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) @@ -1188,4 +1370,99 @@ bool ceph_security_xattr_deadlock(struct inode *in) spin_unlock(&ci->i_ceph_lock); return ret; } + +#ifdef CONFIG_CEPH_FS_SECURITY_LABEL +int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, + struct ceph_acl_sec_ctx *as_ctx) +{ + struct ceph_pagelist *pagelist = as_ctx->pagelist; + const char *name; + size_t name_len; + int err; + + err = security_dentry_init_security(dentry, mode, &dentry->d_name, + &name, &as_ctx->lsmctx); + if (err < 0) { + WARN_ON_ONCE(err != -EOPNOTSUPP); + err = 0; /* do nothing */ + goto out; + } + + err = -ENOMEM; + if (!pagelist) { + pagelist = ceph_pagelist_alloc(GFP_KERNEL); + if (!pagelist) + goto out; + err = ceph_pagelist_reserve(pagelist, PAGE_SIZE); + if (err) + goto out; + ceph_pagelist_encode_32(pagelist, 1); + } + + /* + * FIXME: Make security_dentry_init_security() generic. Currently + * It only supports single security module and only selinux has + * dentry_init_security hook. + */ + name_len = strlen(name); + err = ceph_pagelist_reserve(pagelist, + 4 * 2 + name_len + as_ctx->lsmctx.len); + if (err) + goto out; + + if (as_ctx->pagelist) { + /* update count of KV pairs */ + BUG_ON(pagelist->length <= sizeof(__le32)); + if (list_is_singular(&pagelist->head)) { + le32_add_cpu((__le32*)pagelist->mapped_tail, 1); + } else { + struct page *page = list_first_entry(&pagelist->head, + struct page, lru); + void *addr = kmap_atomic(page); + le32_add_cpu((__le32*)addr, 1); + kunmap_atomic(addr); + } + } else { + as_ctx->pagelist = pagelist; + } + + ceph_pagelist_encode_32(pagelist, name_len); + ceph_pagelist_append(pagelist, name, name_len); + + ceph_pagelist_encode_32(pagelist, as_ctx->lsmctx.len); + ceph_pagelist_append(pagelist, as_ctx->lsmctx.context, + as_ctx->lsmctx.len); + + err = 0; +out: + if (pagelist && !as_ctx->pagelist) + ceph_pagelist_release(pagelist); + return err; +} +#endif /* CONFIG_CEPH_FS_SECURITY_LABEL */ +#endif /* CONFIG_SECURITY */ + +void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) +{ +#ifdef CONFIG_CEPH_FS_POSIX_ACL + posix_acl_release(as_ctx->acl); + posix_acl_release(as_ctx->default_acl); +#endif +#ifdef CONFIG_CEPH_FS_SECURITY_LABEL + security_release_secctx(&as_ctx->lsmctx); +#endif +#ifdef CONFIG_FS_ENCRYPTION + kfree(as_ctx->fscrypt_auth); #endif + if (as_ctx->pagelist) + ceph_pagelist_release(as_ctx->pagelist); +} + +/* + * List of handlers for synthetic system.* attributes. Other + * attributes are handled directly. + */ +const struct xattr_handler * const ceph_xattr_handlers[] = { + &ceph_other_xattr_handler, + NULL, +}; |