From 97a385e558292ba0851906783642239865670a5f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 May 2019 16:40:32 -0400 Subject: libceph: remove ceph_get_direct_page_vector() This function is entirely unused. Signed-off-by: Christoph Hellwig Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 337d5049ff93..a3cddf5f0e60 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -299,10 +299,6 @@ int ceph_wait_for_latest_osdmap(struct ceph_client *client, /* pagevec.c */ extern void ceph_release_page_vector(struct page **pages, int num_pages); - -extern struct page **ceph_get_direct_page_vector(const void __user *data, - int num_pages, - bool write_page); extern void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); -- cgit From 6c37f0e64173571914a443f74d36e5a22dabfc05 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 3 Jun 2019 14:45:16 -0400 Subject: libceph: add ceph_decode_entity_addr Add a function for decoding an entity_addr_t. Once CEPH_FEATURE_MSG_ADDR2 is enabled, the server daemons will start encoding entity_addr_t differently. Add a new helper function that can handle either format. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index a6c2a48d42e0..1c0a665bfc03 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -230,6 +230,8 @@ static inline void ceph_decode_addr(struct ceph_entity_addr *a) WARN_ON(a->in_addr.ss_family == 512); } +extern int ceph_decode_entity_addr(void **p, void *end, + struct ceph_entity_addr *addr); /* * encoders */ -- cgit From 0bfb0f288992adbf8d1f0d5f22f0fd398b146316 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 31 May 2019 15:32:28 -0400 Subject: libceph: ADDR2 support for monmap Switch the MonMap decoder to use the new decoding routine for entity_addr_t's. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/mon_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index 3a4688af7455..b4d134d3312a 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -104,7 +104,6 @@ struct ceph_mon_client { #endif }; -extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end); extern int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr); -- cgit From d3c3c0a841d5dafc5395be363996d619255a732f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 17 Jun 2019 06:57:25 -0400 Subject: libceph: use TYPE_LEGACY for entity addrs instead of TYPE_NONE Going forward, we'll have different address types so let's use the addr2 TYPE_LEGACY for internal tracking rather than TYPE_NONE. Also, make ceph_pr_addr print the address type value as well. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 1c0a665bfc03..ce488d95be89 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -218,16 +218,23 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv, /* * sockaddr_storage <-> ceph_sockaddr */ +#define CEPH_ENTITY_ADDR_TYPE_NONE 0 +#define CEPH_ENTITY_ADDR_TYPE_LEGACY __cpu_to_le32(1) + static inline void ceph_encode_addr(struct ceph_entity_addr *a) { __be16 ss_family = htons(a->in_addr.ss_family); a->in_addr.ss_family = *(__u16 *)&ss_family; + + /* Banner addresses require TYPE_NONE */ + a->type = CEPH_ENTITY_ADDR_TYPE_NONE; } static inline void ceph_decode_addr(struct ceph_entity_addr *a) { __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; a->in_addr.ss_family = ntohs(ss_family); WARN_ON(a->in_addr.ss_family == 512); + a->type = CEPH_ENTITY_ADDR_TYPE_LEGACY; } extern int ceph_decode_entity_addr(void **p, void *end, -- cgit From 2c66de560fa2dda0a600e908897116914db8f500 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 17 Jun 2019 09:24:31 -0400 Subject: libceph: rename ceph_encode_addr to ceph_encode_banner_addr ...ditto for the decode function. We only use these functions to fix up banner addresses now, so let's name them more appropriately. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index ce488d95be89..450384fe487c 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -221,7 +221,7 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv, #define CEPH_ENTITY_ADDR_TYPE_NONE 0 #define CEPH_ENTITY_ADDR_TYPE_LEGACY __cpu_to_le32(1) -static inline void ceph_encode_addr(struct ceph_entity_addr *a) +static inline void ceph_encode_banner_addr(struct ceph_entity_addr *a) { __be16 ss_family = htons(a->in_addr.ss_family); a->in_addr.ss_family = *(__u16 *)&ss_family; @@ -229,7 +229,7 @@ static inline void ceph_encode_addr(struct ceph_entity_addr *a) /* Banner addresses require TYPE_NONE */ a->type = CEPH_ENTITY_ADDR_TYPE_NONE; } -static inline void ceph_decode_addr(struct ceph_entity_addr *a) +static inline void ceph_decode_banner_addr(struct ceph_entity_addr *a) { __be16 ss_family = *(__be16 *)&a->in_addr.ss_family; a->in_addr.ss_family = ntohs(ss_family); -- cgit From 6adaaafdd81d5c01875fe233ab73deb81b34caa1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 31 May 2019 12:24:22 -0400 Subject: libceph: turn on CEPH_FEATURE_MSG_ADDR2 Now that the client can handle either address formatting, advertise to the peer that we can support it. Signed-off-by: Jeff Layton Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_features.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 65a38c4a02a1..39e6f4c57580 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -211,6 +211,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ + CEPH_FEATURE_MSG_ADDR2 | \ CEPH_FEATURE_CEPHX_V2) #define CEPH_FEATURES_REQUIRED_DEFAULT 0 -- cgit From 49ada6e8dc9f64ad1e8dd6f7b453c9e584e9f897 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 20 Jun 2019 12:09:08 +0800 Subject: ceph: more precise CEPH_CLIENT_CAPS_PENDING_CAPSNAP Client uses this flag to tell mds if there is more cap snap need to flush. It's mainly for the case that client needs to re-send cap/snap flushes after mds failover, but CEPH_CAP_ANY_FILE_WR on corresponding inodes are all released before mds failover. Signed-off-by: "Yan, Zheng" Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 3ac0feaf2b5e..cb21c5cf12c3 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -682,7 +682,7 @@ extern const char *ceph_cap_op_name(int op); /* flags field in client cap messages (version >= 10) */ #define CEPH_CLIENT_CAPS_SYNC (1<<0) #define CEPH_CLIENT_CAPS_NO_CAPSNAP (1<<1) -#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2); +#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2) /* * caps message, used for capability callbacks, acks, requests, etc. -- cgit From 94e85771881027e62afdddadd31e3eec73025990 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 8 Jul 2019 12:50:09 +0200 Subject: libceph: rename r_unsafe_item to r_private_item This list item remained from when we had safe and unsafe replies (commit vs ack). It has since become a private list item for use by clients. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2294f963dab7..024f6fed0ac5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -198,9 +198,9 @@ struct ceph_osd_request { bool r_mempool; struct completion r_completion; /* private to osd_client.c */ ceph_osdc_callback_t r_callback; - struct list_head r_unsafe_item; struct inode *r_inode; /* for use by callbacks */ + struct list_head r_private_item; /* ditto */ void *r_priv; /* ditto */ /* set by submitter */ -- cgit From ef83171b49c66d851a1a0dc6da5b4a4d8ee6ce9a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 8 Apr 2019 14:16:05 +0200 Subject: libceph: bump CEPH_MSG_MAX_DATA_LEN (again) This time for rbd object map. Object maps are limited in size to 256000000 objects, two bits per object. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang --- include/linux/ceph/libceph.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index a3cddf5f0e60..82156da3c650 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -84,11 +84,13 @@ struct ceph_options { #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) /* - * Handle the largest possible rbd object in one message. + * The largest possible rbd data object is 32M. + * The largest possible rbd object map object is 64M. + * * There is no limit on the size of cephfs objects, but it has to obey * rsize and wsize mount options anyway. */ -#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) +#define CEPH_MSG_MAX_DATA_LEN (64*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit From 68ada915eea10f36760ffe414810390a104df093 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 14 Jun 2019 18:16:51 +0200 Subject: libceph: change ceph_osdc_call() to take page vector for response This will be used for loading object map. rbd_obj_read_sync() isn't suitable because object map must be accessed through class methods. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 024f6fed0ac5..c567cfa4f107 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -497,7 +497,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc, const char *class, const char *method, unsigned int flags, struct page *req_page, size_t req_len, - struct page *resp_page, size_t *resp_len); + struct page **resp_pages, size_t *resp_len); extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, struct ceph_vino vino, -- cgit From 4cf3e6dff7ea517544e1da7810a0b3ebba380d2c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 14 Jun 2019 18:00:19 +0200 Subject: libceph: export osd_req_op_data() macro We already have one exported wrapper around it for extent.osd_data and rbd_object_map_update_finish() needs another one for cls.request_data. Signed-off-by: Ilya Dryomov Reviewed-by: Dongsheng Yang Reviewed-by: Jeff Layton --- include/linux/ceph/osd_client.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index c567cfa4f107..ad7fe5d10dcd 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -389,6 +389,14 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err); +#define osd_req_op_data(oreq, whch, typ, fld) \ +({ \ + struct ceph_osd_request *__oreq = (oreq); \ + unsigned int __whch = (whch); \ + BUG_ON(__whch >= __oreq->r_num_ops); \ + &__oreq->r_ops[__whch].typ.fld; \ +}) + extern void osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags); -- cgit From 22e8bd51bb0469d1a524130a057f894ff632376a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 5 Jun 2019 19:25:11 +0200 Subject: rbd: support for object-map and fast-diff Speed up reads, discards and zeroouts through RBD_OBJ_FLAG_MAY_EXIST and RBD_OBJ_FLAG_NOOP_FOR_NONEXISTENT based on object map. Invalid object maps are not trusted, but still updated. Note that we never iterate, resize or invalidate object maps. If object-map feature is enabled but object map fails to load, we just fail the requester (either "rbd map" or I/O, by way of post-acquire action). Signed-off-by: Ilya Dryomov --- include/linux/ceph/cls_lock_client.h | 3 +++ include/linux/ceph/striper.h | 2 ++ 2 files 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 bea6c77d2093..17bc7584d1fe 100644 --- a/include/linux/ceph/cls_lock_client.h +++ b/include/linux/ceph/cls_lock_client.h @@ -52,4 +52,7 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc, char *lock_name, u8 *type, char **tag, struct ceph_locker **lockers, u32 *num_lockers); +int ceph_cls_assert_locked(struct ceph_osd_request *req, int which, + char *lock_name, u8 type, char *cookie, char *tag); + #endif diff --git a/include/linux/ceph/striper.h b/include/linux/ceph/striper.h index cbd0d24b7148..3486636c0e6e 100644 --- a/include/linux/ceph/striper.h +++ b/include/linux/ceph/striper.h @@ -66,4 +66,6 @@ int ceph_extent_to_file(struct ceph_file_layout *l, struct ceph_file_extent **file_extents, u32 *num_file_extents); +u64 ceph_get_num_objects(struct ceph_file_layout *l, u64 size); + #endif -- cgit