diff options
Diffstat (limited to 'fs/ceph/mds_client.h')
| -rw-r--r-- | fs/ceph/mds_client.h | 323 |
1 files changed, 275 insertions, 48 deletions
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index db57ae98ed34..0428a5eaf28c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FS_CEPH_MDS_CLIENT_H #define _FS_CEPH_MDS_CLIENT_H @@ -8,12 +9,53 @@ #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/refcount.h> +#include <linux/utsname.h> +#include <linux/ktime.h> #include <linux/ceph/types.h> #include <linux/ceph/messenger.h> -#include <linux/ceph/mdsmap.h> #include <linux/ceph/auth.h> +#include "mdsmap.h" +#include "metric.h" +#include "super.h" + +/* The first 8 bits are reserved for old ceph releases */ +enum ceph_feature_type { + CEPHFS_FEATURE_MIMIC = 8, + CEPHFS_FEATURE_REPLY_ENCODING, + CEPHFS_FEATURE_RECLAIM_CLIENT, + CEPHFS_FEATURE_LAZY_CAP_WANTED, + CEPHFS_FEATURE_MULTI_RECONNECT, + CEPHFS_FEATURE_DELEG_INO, + CEPHFS_FEATURE_METRIC_COLLECT, + CEPHFS_FEATURE_ALTERNATE_NAME, + CEPHFS_FEATURE_NOTIFY_SESSION_STATE, + CEPHFS_FEATURE_OP_GETVXATTR, + CEPHFS_FEATURE_32BITS_RETRY_FWD, + CEPHFS_FEATURE_NEW_SNAPREALM_INFO, + CEPHFS_FEATURE_HAS_OWNER_UIDGID, + CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, + + CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, +}; + +#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \ + 0, 1, 2, 3, 4, 5, 6, 7, \ + CEPHFS_FEATURE_MIMIC, \ + CEPHFS_FEATURE_REPLY_ENCODING, \ + CEPHFS_FEATURE_LAZY_CAP_WANTED, \ + CEPHFS_FEATURE_MULTI_RECONNECT, \ + CEPHFS_FEATURE_DELEG_INO, \ + CEPHFS_FEATURE_METRIC_COLLECT, \ + CEPHFS_FEATURE_ALTERNATE_NAME, \ + CEPHFS_FEATURE_NOTIFY_SESSION_STATE, \ + CEPHFS_FEATURE_OP_GETVXATTR, \ + CEPHFS_FEATURE_32BITS_RETRY_FWD, \ + CEPHFS_FEATURE_HAS_OWNER_UIDGID, \ + CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, \ +} + /* * Some lock dependencies: * @@ -31,6 +73,24 @@ struct ceph_fs_client; struct ceph_cap; +#define MDS_AUTH_UID_ANY -1 + +struct ceph_mds_cap_match { + s64 uid; /* default to MDS_AUTH_UID_ANY */ + u32 num_gids; + u32 *gids; /* use these GIDs */ + char *path; /* require path to be child of this + (may be "" or "/" for any) */ + char *fs_name; + bool root_squash; /* default to false */ +}; + +struct ceph_mds_cap_auth { + struct ceph_mds_cap_match match; + bool readable; + bool writeable; +}; + /* * parsed info about a single inode. pointers are into the encoded * on-wire structures within the mds reply message payload. @@ -47,16 +107,34 @@ struct ceph_mds_reply_info_in { char *inline_data; u32 pool_ns_len; char *pool_ns_data; + u64 max_bytes; + u64 max_files; + s32 dir_pin; + struct ceph_timespec btime; + struct ceph_timespec snap_btime; + u8 *fscrypt_auth; + u8 *fscrypt_file; + u32 fscrypt_auth_len; + u32 fscrypt_file_len; + u64 rsnaps; + u64 change_attr; }; struct ceph_mds_reply_dir_entry { + bool is_nokey; char *name; u32 name_len; + u32 raw_hash; struct ceph_mds_reply_lease *lease; struct ceph_mds_reply_info_in inode; loff_t offset; }; +struct ceph_mds_reply_xattr { + char *xattr_value; + size_t xattr_value_len; +}; + /* * parsed info about an mds reply, including information about * either: 1) the target inode and/or its parent directory and dentry, @@ -70,8 +148,11 @@ struct ceph_mds_reply_info_parsed { struct ceph_mds_reply_info_in diri, targeti; struct ceph_mds_reply_dirfrag *dirfrag; char *dname; + u8 *altname; u32 dname_len; + u32 altname_len; struct ceph_mds_reply_lease *dlease; + struct ceph_mds_reply_xattr xattr_info; /* extra */ union { @@ -123,10 +204,11 @@ enum { CEPH_MDS_SESSION_OPENING = 2, CEPH_MDS_SESSION_OPEN = 3, CEPH_MDS_SESSION_HUNG = 4, - CEPH_MDS_SESSION_CLOSING = 5, - CEPH_MDS_SESSION_RESTARTING = 6, - CEPH_MDS_SESSION_RECONNECTING = 7, - CEPH_MDS_SESSION_REJECTED = 8, + CEPH_MDS_SESSION_RESTARTING = 5, + CEPH_MDS_SESSION_RECONNECTING = 6, + CEPH_MDS_SESSION_CLOSING = 7, + CEPH_MDS_SESSION_CLOSED = 8, + CEPH_MDS_SESSION_REJECTED = 9, }; struct ceph_mds_session { @@ -134,6 +216,7 @@ struct ceph_mds_session { int s_mds; int s_state; unsigned long s_ttl; /* time until mds kills us */ + unsigned long s_features; u64 s_seq; /* incoming msg seq # */ struct mutex s_mutex; /* serialize session messages */ @@ -141,29 +224,33 @@ struct ceph_mds_session { struct ceph_auth_handshake s_auth; - /* protected by s_gen_ttl_lock */ - spinlock_t s_gen_ttl_lock; - u32 s_cap_gen; /* inc each time we get mds stale msg */ - unsigned long s_cap_ttl; /* when session caps expire */ + atomic_t s_cap_gen; /* inc each time we get mds stale msg */ + unsigned long s_cap_ttl; /* when session caps expire. protected by s_mutex */ /* protected by s_cap_lock */ spinlock_t s_cap_lock; + refcount_t s_ref; struct list_head s_caps; /* all caps issued by this session */ - int s_nr_caps, s_trim_caps; + struct ceph_cap *s_cap_iterator; + int s_nr_caps; int s_num_cap_releases; int s_cap_reconnect; int s_readonly; struct list_head s_cap_releases; /* waiting cap_release messages */ - struct ceph_cap *s_cap_iterator; + struct work_struct s_cap_release_work; - /* protected by mutex */ + /* See ceph_inode_info->i_dirty_item. */ + struct list_head s_cap_dirty; /* inodes w/ dirty caps */ + + /* See ceph_inode_info->i_flushing_item. */ struct list_head s_cap_flushing; /* inodes w/ flushing caps */ + unsigned long s_renew_requested; /* last time we sent a renew req */ u64 s_renew_seq; - refcount_t s_ref; struct list_head s_waiting; /* waiting requests */ struct list_head s_unsafe; /* unsafe requests */ + struct xarray s_delegated_inos; }; /* @@ -197,6 +284,7 @@ struct ceph_mds_request { struct rb_node r_node; struct ceph_mds_client *r_mdsc; + struct kref r_kref; int r_op; /* mds op code */ /* operation on what? */ @@ -209,6 +297,9 @@ struct ceph_mds_request { struct inode *r_parent; /* parent dir inode */ struct inode *r_target_inode; /* resulting inode */ + struct inode *r_new_inode; /* new inode (for creates) */ + + const struct qstr *r_dname; /* stable name (for ->d_revalidate) */ #define CEPH_MDS_R_DIRECT_IS_HASH (1) /* r_direct_hash is valid */ #define CEPH_MDS_R_ABORTED (2) /* call was aborted */ @@ -217,15 +308,25 @@ struct ceph_mds_request { #define CEPH_MDS_R_GOT_RESULT (5) /* got a result */ #define CEPH_MDS_R_DID_PREPOPULATE (6) /* prepopulated readdir */ #define CEPH_MDS_R_PARENT_LOCKED (7) /* is r_parent->i_rwsem wlocked? */ +#define CEPH_MDS_R_ASYNC (8) /* async request */ +#define CEPH_MDS_R_FSCRYPT_FILE (9) /* must marshal fscrypt_file field */ unsigned long r_req_flags; struct mutex r_fill_mutex; union ceph_mds_request_args r_args; + + struct ceph_fscrypt_auth *r_fscrypt_auth; + u64 r_fscrypt_file; + + u8 *r_altname; /* fscrypt binary crypttext for long filenames */ + u32 r_altname_len; /* length of r_altname */ + int r_fmode; /* file mode, if expecting cap */ - kuid_t r_uid; - kgid_t r_gid; - struct timespec r_stamp; + int r_request_release_offset; + const struct cred *r_cred; + struct mnt_idmap *r_mnt_idmap; + struct timespec64 r_stamp; /* for choosing which mds to send this request to */ int r_direct_mode; @@ -242,14 +343,19 @@ struct ceph_mds_request { int r_old_inode_drop, r_old_inode_unless; struct ceph_msg *r_request; /* original request */ - int r_request_release_offset; struct ceph_msg *r_reply; struct ceph_mds_reply_info_parsed r_reply_info; - struct page *r_locked_page; int r_err; + u32 r_readdir_offset; + + struct page *r_locked_page; + int r_dir_caps; + int r_num_caps; unsigned long r_timeout; /* optional. jiffies, 0 is "wait forever" */ unsigned long r_started; /* start time to measure timeout against */ + unsigned long r_start_latency; /* start time to measure latency */ + unsigned long r_end_latency; /* finish time to measure latency */ unsigned long r_request_started; /* start time for mds request only, used to measure lease durations */ @@ -266,22 +372,21 @@ struct ceph_mds_request { int r_num_fwd; /* number of forward attempts */ int r_resend_mds; /* mds to resend to next, if any*/ u32 r_sent_on_mseq; /* cap mseq request was sent at*/ + u64 r_deleg_ino; - struct kref r_kref; struct list_head r_wait; struct completion r_completion; struct completion r_safe_completion; ceph_mds_request_callback_t r_callback; - ceph_mds_request_wait_callback_t r_wait_for_completion; struct list_head r_unsafe_item; /* per-session unsafe list item */ long long r_dir_release_cnt; long long r_dir_ordered_cnt; int r_readdir_cache_idx; - u32 r_readdir_offset; + + int r_feature_needed; struct ceph_cap_reservation r_caps_reservation; - int r_num_caps; }; struct ceph_pool_perm { @@ -292,6 +397,45 @@ struct ceph_pool_perm { char pool_ns[]; }; +struct ceph_snapid_map { + struct rb_node node; + struct list_head lru; + atomic_t ref; + dev_t dev; + u64 snap; + unsigned long last_used; +}; + +/* + * node for list of quotarealm inodes that are not visible from the filesystem + * mountpoint, but required to handle, e.g. quotas. + */ +struct ceph_quotarealm_inode { + struct rb_node node; + u64 ino; + unsigned long timeout; /* last time a lookup failed for this inode */ + struct mutex mutex; + struct inode *inode; +}; + +#ifdef CONFIG_DEBUG_FS + +struct cap_wait { + struct list_head list; + u64 ino; + pid_t tgid; + int need; + int want; +}; + +#endif + +enum { + CEPH_MDSC_STOPPING_BEGIN = 1, + CEPH_MDSC_STOPPING_FLUSHING = 2, + CEPH_MDSC_STOPPING_FLUSHED = 3, +}; + /* * mds client state */ @@ -307,8 +451,23 @@ struct ceph_mds_client { struct ceph_mds_session **sessions; /* NULL for mds if no session */ atomic_t num_sessions; - int max_sessions; /* len of s_mds_sessions */ - int stopping; /* true if shutting down */ + int max_sessions; /* len of sessions array */ + + spinlock_t stopping_lock; /* protect snap_empty */ + int stopping; /* the stage of shutting down */ + atomic_t stopping_blockers; + struct completion stopping_waiter; + + atomic64_t dirty_folios; + wait_queue_head_t flush_end_wq; + + atomic64_t quotarealms_count; /* # realms with quota */ + /* + * We keep a list of inodes we don't see in the mountpoint but that we + * need to track quota realms. + */ + struct rb_root quotarealms_inodes; + struct mutex quotarealms_inodes_mutex; /* * snap_rwsem will cover cap linkage into snaprealms, and @@ -321,6 +480,7 @@ struct ceph_mds_client { struct rw_semaphore snap_rwsem; struct rb_root snap_realms; struct list_head snap_empty; + int num_snap_realms; spinlock_t snap_empty_lock; /* protect snap_empty */ u64 last_tid; /* most recent mds request */ @@ -330,18 +490,23 @@ struct ceph_mds_client { struct delayed_work delayed_work; /* delayed work */ unsigned long last_renew_caps; /* last time we renewed our caps */ struct list_head cap_delay_list; /* caps with delayed release */ - spinlock_t cap_delay_lock; /* protects cap_delay_list */ + struct list_head cap_unlink_delay_list; /* caps with delayed release for unlink */ + spinlock_t cap_delay_lock; /* protects cap_delay_list and cap_unlink_delay_list */ struct list_head snap_flush_list; /* cap_snaps ready to flush */ spinlock_t snap_flush_lock; u64 last_cap_flush_tid; struct list_head cap_flush_list; - struct list_head cap_dirty; /* inodes with dirty caps */ struct list_head cap_dirty_migrating; /* ...that are migration... */ int num_cap_flushing; /* # caps we are flushing */ spinlock_t cap_dirty_lock; /* protects above items */ wait_queue_head_t cap_flushing_wq; + struct work_struct cap_reclaim_work; + atomic_t cap_reclaim_pending; + + struct work_struct cap_unlink_work; + /* * Cap reservations * @@ -356,39 +521,49 @@ struct ceph_mds_client { spinlock_t caps_list_lock; struct list_head caps_list; /* unused (reserved or unreserved) */ +#ifdef CONFIG_DEBUG_FS + struct list_head cap_wait_list; +#endif int caps_total_count; /* total caps allocated */ int caps_use_count; /* in use */ + int caps_use_max; /* max used caps */ int caps_reserve_count; /* unused, reserved */ int caps_avail_count; /* unused, unreserved */ int caps_min_count; /* keep at least this many (unreserved) */ - spinlock_t dentry_lru_lock; - struct list_head dentry_lru; - int num_dentry; + spinlock_t dentry_list_lock; + struct list_head dentry_leases; /* fifo list */ + struct list_head dentry_dir_leases; /* lru list */ + + struct ceph_client_metric metric; + + spinlock_t snapid_map_lock; + struct rb_root snapid_map_tree; + struct list_head snapid_map_lru; struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + + u32 s_cap_auths_num; + struct ceph_mds_cap_auth *s_cap_auths; + + char nodename[__NEW_UTS_LEN + 1]; }; extern const char *ceph_mds_op_name(int op); +extern bool check_session_state(struct ceph_mds_session *s); +void inc_session_sequence(struct ceph_mds_session *s); + extern struct ceph_mds_session * __ceph_lookup_mds_session(struct ceph_mds_client *, int mds); -static inline struct ceph_mds_session * -ceph_get_mds_session(struct ceph_mds_session *s) -{ - refcount_inc(&s->s_ref); - return s; -} - extern const char *ceph_session_state_name(int s); +extern struct ceph_mds_session * +ceph_get_mds_session(struct ceph_mds_session *s); extern void ceph_put_mds_session(struct ceph_mds_session *s); -extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc, - struct ceph_msg *msg, int mds); - extern int ceph_mdsc_init(struct ceph_fs_client *fsc); extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc); extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc); @@ -401,11 +576,17 @@ extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, struct inode *dir); extern struct ceph_mds_request * ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode); -extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, - struct ceph_mds_request *req); +extern int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, + struct inode *dir, + struct ceph_mds_request *req); +int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req, + ceph_mds_request_wait_callback_t wait_func); extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req); +extern void ceph_mdsc_release_dir_caps(struct ceph_mds_request *req); +extern void ceph_mdsc_release_dir_caps_async(struct ceph_mds_request *req); static inline void ceph_mdsc_get_request(struct ceph_mds_request *req) { kref_get(&req->r_kref); @@ -416,17 +597,48 @@ static inline void ceph_mdsc_put_request(struct ceph_mds_request *req) kref_put(&req->r_kref, ceph_mdsc_release_request); } -extern void ceph_send_cap_releases(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session); +extern void send_flush_mdlog(struct ceph_mds_session *s); +extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc, + void (*cb)(struct ceph_mds_session *), + bool check_state); +extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq); +extern void __ceph_queue_cap_release(struct ceph_mds_session *session, + struct ceph_cap *cap); +extern void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session); +extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); +extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); +extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc); +extern int ceph_iterate_session_caps(struct ceph_mds_session *session, + int (*cb)(struct inode *, int mds, void *), + void *arg); +extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, + int mask); extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); -extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, - int stop_on_nosnap); +/* + * Structure to group path-related output parameters for build_*_path functions + */ +struct ceph_path_info { + const char *path; + int pathlen; + struct ceph_vino vino; + bool freepath; +}; + +static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info) +{ + if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path)) + __putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen)); +} + +extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, + struct dentry *dentry, struct ceph_path_info *path_info, + int for_wire); extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry); extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session, - struct inode *inode, struct dentry *dentry, char action, u32 seq); @@ -437,7 +649,22 @@ extern void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, extern struct ceph_mds_session * ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target); -extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session); +extern int ceph_trim_caps(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session, + int max_caps); + +static inline int ceph_wait_on_async_create(struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + + return wait_on_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT, + TASK_KILLABLE); +} + +extern int ceph_wait_on_conflict_unlink(struct dentry *dentry); +extern u64 ceph_get_deleg_ino(struct ceph_mds_session *session); +extern int ceph_restore_deleg_ino(struct ceph_mds_session *session, u64 ino); + +extern bool enable_unsafe_idmap; #endif |