From 74da4a0f574d11ed60dbe50a1e5e942e20476590 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 3 Mar 2017 18:16:07 +0100 Subject: libceph, ceph: always advertise all supported features No reason to hide CephFS-specific features in the rbd case. Recent feature bits mix RADOS and CephFS-specific stuff together anyway. Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_features.h | 4 ++++ include/linux/ceph/libceph.h | 5 +---- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index ae2f66833762..fd8b2953c78f 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -105,8 +105,10 @@ static inline u64 ceph_sanitize_features(u64 features) */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_FLOCK | \ CEPH_FEATURE_SUBSCRIBE2 | \ CEPH_FEATURE_RECONNECT_SEQ | \ + CEPH_FEATURE_DIRLAYOUTHASH | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ @@ -114,11 +116,13 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_MSG_AUTH | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ + CEPH_FEATURE_MDSENC | \ CEPH_FEATURE_OSDHASHPSPOOL | \ CEPH_FEATURE_OSD_CACHEPOOL | \ CEPH_FEATURE_CRUSH_V2 | \ CEPH_FEATURE_EXPORT_PEER | \ CEPH_FEATURE_OSDMAP_ENC | \ + CEPH_FEATURE_MDS_INLINE_DATA | \ CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 88cd5dc8e238..cecbf5a26e5a 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -262,10 +262,7 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client); extern void ceph_destroy_options(struct ceph_options *opt); extern int ceph_compare_options(struct ceph_options *new_opt, struct ceph_client *client); -extern struct ceph_client *ceph_create_client(struct ceph_options *opt, - void *private, - u64 supported_features, - u64 required_features); +struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private); struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client); u64 ceph_client_gid(struct ceph_client *client); extern void ceph_destroy_client(struct ceph_client *client); -- cgit v1.2.3 From 06dfa96399a9a3280dd81e47f8696aa89f1783e7 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 17 Mar 2017 14:10:27 +0200 Subject: libceph: convert ceph_snap_context.nref from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index cecbf5a26e5a..3229ae6c7846 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -161,7 +162,7 @@ struct ceph_client { * dirtied. */ struct ceph_snap_context { - atomic_t nref; + refcount_t nref; u64 seq; u32 num_snaps; u64 snaps[]; -- cgit v1.2.3 From 02113a0f14e20bd8e675d7cec16db6eaaf2b2380 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 17 Mar 2017 14:10:28 +0200 Subject: libceph: convert ceph_osd.o_ref from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index c125b5d9e13c..d6a625e75040 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -27,7 +28,7 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *); /* a given osd we're communicating with */ struct ceph_osd { - atomic_t o_ref; + refcount_t o_ref; struct ceph_osd_client *o_osdc; int o_osd; int o_incarnation; -- cgit v1.2.3 From 0e1a5ee6577e43e5be55369d398107080b360941 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 17 Mar 2017 14:10:29 +0200 Subject: libceph: convert ceph_pagelist.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: Ilya Dryomov --- include/linux/ceph/pagelist.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index 13d71fe18b0c..75a7db21457d 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -2,7 +2,7 @@ #define __FS_CEPH_PAGELIST_H #include -#include +#include #include #include @@ -13,7 +13,7 @@ struct ceph_pagelist { size_t room; struct list_head free_list; size_t num_pages_free; - atomic_t refcnt; + refcount_t refcnt; }; struct ceph_pagelist_cursor { @@ -30,7 +30,7 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl) pl->room = 0; INIT_LIST_HEAD(&pl->free_list); pl->num_pages_free = 0; - atomic_set(&pl->refcnt, 1); + refcount_set(&pl->refcnt, 1); } extern void ceph_pagelist_release(struct ceph_pagelist *pl); -- cgit v1.2.3 From 76201b6354bb3aa31c7ba2bd42b9cbb8dda71c44 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 28 Mar 2017 17:04:13 +0800 Subject: ceph: allow connecting to mds whose rank >= mdsmap::m_max_mds mdsmap::m_max_mds is the expected count of active mds. It's not the max rank of active mds. User can decrease mdsmap::m_max_mds, but does not stop mds whose rank >= mdsmap::m_max_mds. Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/mdsmap.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h index 8ed5dc505fbb..d5f783f3226a 100644 --- a/include/linux/ceph/mdsmap.h +++ b/include/linux/ceph/mdsmap.h @@ -25,6 +25,7 @@ struct ceph_mdsmap { u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; u32 m_max_mds; /* size of m_addr, m_state arrays */ + int m_num_mds; struct ceph_mds_info *m_info; /* which object pools file data can be stored in */ @@ -40,7 +41,7 @@ struct ceph_mdsmap { static inline struct ceph_entity_addr * ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) { - if (w >= m->m_max_mds) + if (w >= m->m_num_mds) return NULL; return &m->m_info[w].addr; } @@ -48,14 +49,14 @@ ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w) static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w) { BUG_ON(w < 0); - if (w >= m->m_max_mds) + if (w >= m->m_num_mds) return CEPH_MDS_STATE_DNE; return m->m_info[w].state; } static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w) { - if (w >= 0 && w < m->m_max_mds) + if (w >= 0 && w < m->m_num_mds) return m->m_info[w].laggy; return false; } -- cgit v1.2.3 From 79162547b76e4979b21ef80c9629ada94a51a59b Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Wed, 5 Apr 2017 12:54:05 -0400 Subject: ceph: make seeky readdir more efficient Current cephfs client uses string to indicate start position of readdir. The string is last entry of previous readdir reply. This approach does not work for seeky readdir because we can not easily convert the new postion to a string. For seeky readdir, mds needs to return dentries from the beginning. Client keeps retrying if the reply does not contain the dentry it wants. In current version of ceph, mds sorts CDentry in its cache in hash order. Client also uses dentry hash to compose dir postion. For seeky readdir, if client passes the hash part of dir postion to mds. mds can avoid replying useless dentries. Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index f4b2ee18f38c..1787e4a8e251 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -365,6 +365,7 @@ extern const char *ceph_mds_op_name(int op); #define CEPH_READDIR_FRAG_END (1<<0) #define CEPH_READDIR_FRAG_COMPLETE (1<<8) #define CEPH_READDIR_HASH_ORDER (1<<9) +#define CEPH_READDIR_OFFSET_HASH (1<<10) union ceph_mds_request_args { struct { @@ -384,6 +385,7 @@ union ceph_mds_request_args { __le32 max_entries; /* how many dentries to grab */ __le32 max_bytes; __le16 flags; + __le32 offset_hash; } __attribute__ ((packed)) readdir; struct { __le32 mode; -- cgit v1.2.3 From aa26d662b9d44e7f5b0d109e892e537a23471863 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 4 Apr 2017 08:39:36 -0400 Subject: libceph: remove req->r_replay_version Nothing uses this anymore with the removal of the ack vs. commit code. Remove the field and just encode zeroes into place in the request encoding. Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index d6a625e75040..3fc9e7754a9b 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -192,7 +192,6 @@ struct ceph_osd_request { unsigned long r_stamp; /* jiffies, send or check time */ unsigned long r_start_stamp; /* jiffies */ int r_attempts; - struct ceph_eversion r_replay_version; /* aka reassert_version */ u32 r_last_force_resend; u32 r_map_dne_bound; -- cgit v1.2.3 From a1f4020aab10a6bddb2d061c960ebe52cdfa30b5 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 4 Apr 2017 08:39:37 -0400 Subject: libceph: allow requests to return immediately on full conditions if caller wishes Usually, when the osd map is flagged as full or the pool is at quota, write requests just hang. This is not what we want for cephfs, where it would be better to simply report -ENOSPC back to userland instead of stalling. If the caller knows that it will want an immediate error return instead of blocking on a full or at-quota error condition then allow it to set a flag to request that behavior. Set that flag in ceph_osdc_new_request (since ceph.ko is the only caller), and on any other write request from ceph.ko. A later patch will deal with requests that were submitted before the new map showing the full condition came in. Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3fc9e7754a9b..8cf644197b1a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -187,6 +187,7 @@ struct ceph_osd_request { struct timespec r_mtime; /* ditto */ u64 r_data_offset; /* ditto */ bool r_linger; /* don't resend on failure */ + bool r_abort_on_full; /* return ENOSPC when full */ /* internal */ unsigned long r_stamp; /* jiffies, send or check time */ -- cgit v1.2.3 From 58eb7932ae4d671d2a2377a1779eda96a2789b11 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 18 Apr 2017 09:21:16 -0400 Subject: libceph: add an epoch_barrier field to struct ceph_osd_client Cephfs can get cap update requests that contain a new epoch barrier in them. When that happens we want to pause all OSD traffic until the right map epoch arrives. Add an epoch_barrier field to ceph_osd_client that is protected by the osdc->lock rwsem. When the barrier is set, and the current OSD map epoch is below that, pause the request target when submitting the request or when revisiting it. Add a way for upper layers (cephfs) to update the epoch_barrier as well. If we get a new map, compare the new epoch against the barrier before kicking requests and request another map if the map epoch is still lower than the one we want. If we get a map with a full pool, or at quota condition, then set the barrier to the current epoch value. Signed-off-by: Jeff Layton Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 8cf644197b1a..85650b415e73 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -267,6 +267,7 @@ struct ceph_osd_client { struct rb_root osds; /* osds */ struct list_head osd_lru; /* idle osds */ spinlock_t osd_lru_lock; + u32 epoch_barrier; struct ceph_osd homeless_osd; atomic64_t last_tid; /* tid of last request */ u64 last_linger_id; @@ -305,6 +306,7 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg); extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); +void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); extern void osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); -- cgit v1.2.3 From 14bb211d324d6c8140167bd6b2b8a80757348a2f Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 13 Apr 2017 12:17:38 +0200 Subject: rbd: support updating the lock cookie without releasing the lock As we no longer release the lock before potentially raising BLACKLISTED in rbd_reregister_watch(), the "either locked or blacklisted" assert in rbd_queue_workfn() needs to go: we can be both locked and blacklisted at that point now. Signed-off-by: Ilya Dryomov Reviewed-by: Jason Dillaman --- include/linux/ceph/cls_lock_client.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/cls_lock_client.h b/include/linux/ceph/cls_lock_client.h index 84884d8d4710..0594d3bba774 100644 --- a/include/linux/ceph/cls_lock_client.h +++ b/include/linux/ceph/cls_lock_client.h @@ -37,6 +37,11 @@ int ceph_cls_break_lock(struct ceph_osd_client *osdc, struct ceph_object_locator *oloc, char *lock_name, char *cookie, struct ceph_entity_name *locker); +int ceph_cls_set_cookie(struct ceph_osd_client *osdc, + struct ceph_object_id *oid, + struct ceph_object_locator *oloc, + char *lock_name, u8 type, char *old_cookie, + char *tag, char *new_cookie); void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers); -- cgit v1.2.3 From f775ff7d89f33fc9ba63f6f70df3bcc98c2d9828 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Thu, 27 Apr 2017 18:34:00 +0200 Subject: ceph: fix file open flags on ppc64 The file open flags (O_foo) are platform specific and should never go out to an interface that is not local to the system. Unfortunately these flags have leaked out onto the wire in the cephfs implementation. That lead to bogus flags getting transmitted on ppc64. This patch converts the kernel view of flags to the ceph view of file open flags. Fixes: 124e68e74 ("ceph: file operations") Signed-off-by: Alexander Graf Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 1787e4a8e251..ad078ebe25d6 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -367,6 +367,18 @@ extern const char *ceph_mds_op_name(int op); #define CEPH_READDIR_HASH_ORDER (1<<9) #define CEPH_READDIR_OFFSET_HASH (1<<10) +/* + * open request flags + */ +#define CEPH_O_RDONLY 00000000 +#define CEPH_O_WRONLY 00000001 +#define CEPH_O_RDWR 00000002 +#define CEPH_O_CREAT 00000100 +#define CEPH_O_EXCL 00000200 +#define CEPH_O_TRUNC 00001000 +#define CEPH_O_DIRECTORY 00200000 +#define CEPH_O_NOFOLLOW 00400000 + union ceph_mds_request_args { struct { __le32 mask; /* CEPH_CAP_* */ -- cgit v1.2.3