summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-10-15 06:46:01 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2014-10-15 06:46:01 +0200
commit6b0490816671b2f4126a99998c9bf3c8c0472de2 (patch)
tree016543455c2bdbe47b422fed6a3b4ffb991c97d6 /include
parentce9d7f7b45930ed16c512aabcfe651d44f1c8619 (diff)
parent0bc62284ee3f2a228c64902ed818b6ba8e04159b (diff)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
Pull Ceph updates from Sage Weil: "There is the long-awaited discard support for RBD (Guangliang Zhao, Josh Durgin), a pile of RBD bug fixes that didn't belong in late -rc's (Ilya Dryomov, Li RongQing), a pile of fs/ceph bug fixes and performance and debugging improvements (Yan, Zheng, John Spray), and a smattering of cleanups (Chao Yu, Fabian Frederick, Joe Perches)" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (40 commits) ceph: fix divide-by-zero in __validate_layout() rbd: rbd workqueues need a resque worker libceph: ceph-msgr workqueue needs a resque worker ceph: fix bool assignments libceph: separate multiple ops with commas in debugfs output libceph: sync osd op definitions in rados.h libceph: remove redundant declaration ceph: additional debugfs output ceph: export ceph_session_state_name function ceph: include the initial ACL in create/mkdir/mknod MDS requests ceph: use pagelist to present MDS request data libceph: reference counting pagelist ceph: fix llistxattr on symlink ceph: send client metadata to MDS ceph: remove redundant code for max file size verification ceph: remove redundant io_iter_advance() ceph: move ceph_find_inode() outside the s_mutex ceph: request xattrs if xattr_version is zero rbd: set the remaining discard properties to enable support rbd: use helpers to handle discard for layered images correctly ...
Diffstat (limited to 'include')
-rw-r--r--include/linux/ceph/libceph.h1
-rw-r--r--include/linux/ceph/pagelist.h5
-rw-r--r--include/linux/ceph/rados.h225
3 files changed, 133 insertions, 98 deletions
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 279b0afac1c..07bc359b88a 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -211,7 +211,6 @@ extern struct page **ceph_get_direct_page_vector(const void __user *data,
bool write_page);
extern void ceph_put_page_vector(struct page **pages, int num_pages,
bool dirty);
-extern void ceph_release_page_vector(struct page **pages, int num_pages);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
extern int ceph_copy_user_to_page_vector(struct page **pages,
const void __user *data,
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 9660d6b0a35..5f871d84ddc 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -2,6 +2,7 @@
#define __FS_CEPH_PAGELIST_H
#include <linux/list.h>
+#include <linux/atomic.h>
struct ceph_pagelist {
struct list_head head;
@@ -10,6 +11,7 @@ struct ceph_pagelist {
size_t room;
struct list_head free_list;
size_t num_pages_free;
+ atomic_t refcnt;
};
struct ceph_pagelist_cursor {
@@ -26,9 +28,10 @@ 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);
}
-extern int ceph_pagelist_release(struct ceph_pagelist *pl);
+extern void ceph_pagelist_release(struct ceph_pagelist *pl);
extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index f20e0d8a215..2f822dca104 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -172,6 +172,7 @@ extern const char *ceph_osd_state_name(int s);
#define CEPH_OSD_OP_MODE_WR 0x2000
#define CEPH_OSD_OP_MODE_RMW 0x3000
#define CEPH_OSD_OP_MODE_SUB 0x4000
+#define CEPH_OSD_OP_MODE_CACHE 0x8000
#define CEPH_OSD_OP_TYPE 0x0f00
#define CEPH_OSD_OP_TYPE_LOCK 0x0100
@@ -181,103 +182,135 @@ extern const char *ceph_osd_state_name(int s);
#define CEPH_OSD_OP_TYPE_PG 0x0500
#define CEPH_OSD_OP_TYPE_MULTI 0x0600 /* multiobject */
+#define __CEPH_OSD_OP1(mode, nr) \
+ (CEPH_OSD_OP_MODE_##mode | (nr))
+
+#define __CEPH_OSD_OP(mode, type, nr) \
+ (CEPH_OSD_OP_MODE_##mode | CEPH_OSD_OP_TYPE_##type | (nr))
+
+#define __CEPH_FORALL_OSD_OPS(f) \
+ /** data **/ \
+ /* read */ \
+ f(READ, __CEPH_OSD_OP(RD, DATA, 1), "read") \
+ f(STAT, __CEPH_OSD_OP(RD, DATA, 2), "stat") \
+ f(MAPEXT, __CEPH_OSD_OP(RD, DATA, 3), "mapext") \
+ \
+ /* fancy read */ \
+ f(MASKTRUNC, __CEPH_OSD_OP(RD, DATA, 4), "masktrunc") \
+ f(SPARSE_READ, __CEPH_OSD_OP(RD, DATA, 5), "sparse-read") \
+ \
+ f(NOTIFY, __CEPH_OSD_OP(RD, DATA, 6), "notify") \
+ f(NOTIFY_ACK, __CEPH_OSD_OP(RD, DATA, 7), "notify-ack") \
+ \
+ /* versioning */ \
+ f(ASSERT_VER, __CEPH_OSD_OP(RD, DATA, 8), "assert-version") \
+ \
+ f(LIST_WATCHERS, __CEPH_OSD_OP(RD, DATA, 9), "list-watchers") \
+ \
+ f(LIST_SNAPS, __CEPH_OSD_OP(RD, DATA, 10), "list-snaps") \
+ \
+ /* sync */ \
+ f(SYNC_READ, __CEPH_OSD_OP(RD, DATA, 11), "sync_read") \
+ \
+ /* write */ \
+ f(WRITE, __CEPH_OSD_OP(WR, DATA, 1), "write") \
+ f(WRITEFULL, __CEPH_OSD_OP(WR, DATA, 2), "writefull") \
+ f(TRUNCATE, __CEPH_OSD_OP(WR, DATA, 3), "truncate") \
+ f(ZERO, __CEPH_OSD_OP(WR, DATA, 4), "zero") \
+ f(DELETE, __CEPH_OSD_OP(WR, DATA, 5), "delete") \
+ \
+ /* fancy write */ \
+ f(APPEND, __CEPH_OSD_OP(WR, DATA, 6), "append") \
+ f(STARTSYNC, __CEPH_OSD_OP(WR, DATA, 7), "startsync") \
+ f(SETTRUNC, __CEPH_OSD_OP(WR, DATA, 8), "settrunc") \
+ f(TRIMTRUNC, __CEPH_OSD_OP(WR, DATA, 9), "trimtrunc") \
+ \
+ f(TMAPUP, __CEPH_OSD_OP(RMW, DATA, 10), "tmapup") \
+ f(TMAPPUT, __CEPH_OSD_OP(WR, DATA, 11), "tmapput") \
+ f(TMAPGET, __CEPH_OSD_OP(RD, DATA, 12), "tmapget") \
+ \
+ f(CREATE, __CEPH_OSD_OP(WR, DATA, 13), "create") \
+ f(ROLLBACK, __CEPH_OSD_OP(WR, DATA, 14), "rollback") \
+ \
+ f(WATCH, __CEPH_OSD_OP(WR, DATA, 15), "watch") \
+ \
+ /* omap */ \
+ f(OMAPGETKEYS, __CEPH_OSD_OP(RD, DATA, 17), "omap-get-keys") \
+ f(OMAPGETVALS, __CEPH_OSD_OP(RD, DATA, 18), "omap-get-vals") \
+ f(OMAPGETHEADER, __CEPH_OSD_OP(RD, DATA, 19), "omap-get-header") \
+ f(OMAPGETVALSBYKEYS, __CEPH_OSD_OP(RD, DATA, 20), "omap-get-vals-by-keys") \
+ f(OMAPSETVALS, __CEPH_OSD_OP(WR, DATA, 21), "omap-set-vals") \
+ f(OMAPSETHEADER, __CEPH_OSD_OP(WR, DATA, 22), "omap-set-header") \
+ f(OMAPCLEAR, __CEPH_OSD_OP(WR, DATA, 23), "omap-clear") \
+ f(OMAPRMKEYS, __CEPH_OSD_OP(WR, DATA, 24), "omap-rm-keys") \
+ f(OMAP_CMP, __CEPH_OSD_OP(RD, DATA, 25), "omap-cmp") \
+ \
+ /* tiering */ \
+ f(COPY_FROM, __CEPH_OSD_OP(WR, DATA, 26), "copy-from") \
+ f(COPY_GET_CLASSIC, __CEPH_OSD_OP(RD, DATA, 27), "copy-get-classic") \
+ f(UNDIRTY, __CEPH_OSD_OP(WR, DATA, 28), "undirty") \
+ f(ISDIRTY, __CEPH_OSD_OP(RD, DATA, 29), "isdirty") \
+ f(COPY_GET, __CEPH_OSD_OP(RD, DATA, 30), "copy-get") \
+ f(CACHE_FLUSH, __CEPH_OSD_OP(CACHE, DATA, 31), "cache-flush") \
+ f(CACHE_EVICT, __CEPH_OSD_OP(CACHE, DATA, 32), "cache-evict") \
+ f(CACHE_TRY_FLUSH, __CEPH_OSD_OP(CACHE, DATA, 33), "cache-try-flush") \
+ \
+ /* convert tmap to omap */ \
+ f(TMAP2OMAP, __CEPH_OSD_OP(RMW, DATA, 34), "tmap2omap") \
+ \
+ /* hints */ \
+ f(SETALLOCHINT, __CEPH_OSD_OP(WR, DATA, 35), "set-alloc-hint") \
+ \
+ /** multi **/ \
+ f(CLONERANGE, __CEPH_OSD_OP(WR, MULTI, 1), "clonerange") \
+ f(ASSERT_SRC_VERSION, __CEPH_OSD_OP(RD, MULTI, 2), "assert-src-version") \
+ f(SRC_CMPXATTR, __CEPH_OSD_OP(RD, MULTI, 3), "src-cmpxattr") \
+ \
+ /** attrs **/ \
+ /* read */ \
+ f(GETXATTR, __CEPH_OSD_OP(RD, ATTR, 1), "getxattr") \
+ f(GETXATTRS, __CEPH_OSD_OP(RD, ATTR, 2), "getxattrs") \
+ f(CMPXATTR, __CEPH_OSD_OP(RD, ATTR, 3), "cmpxattr") \
+ \
+ /* write */ \
+ f(SETXATTR, __CEPH_OSD_OP(WR, ATTR, 1), "setxattr") \
+ f(SETXATTRS, __CEPH_OSD_OP(WR, ATTR, 2), "setxattrs") \
+ f(RESETXATTRS, __CEPH_OSD_OP(WR, ATTR, 3), "resetxattrs") \
+ f(RMXATTR, __CEPH_OSD_OP(WR, ATTR, 4), "rmxattr") \
+ \
+ /** subop **/ \
+ f(PULL, __CEPH_OSD_OP1(SUB, 1), "pull") \
+ f(PUSH, __CEPH_OSD_OP1(SUB, 2), "push") \
+ f(BALANCEREADS, __CEPH_OSD_OP1(SUB, 3), "balance-reads") \
+ f(UNBALANCEREADS, __CEPH_OSD_OP1(SUB, 4), "unbalance-reads") \
+ f(SCRUB, __CEPH_OSD_OP1(SUB, 5), "scrub") \
+ f(SCRUB_RESERVE, __CEPH_OSD_OP1(SUB, 6), "scrub-reserve") \
+ f(SCRUB_UNRESERVE, __CEPH_OSD_OP1(SUB, 7), "scrub-unreserve") \
+ f(SCRUB_STOP, __CEPH_OSD_OP1(SUB, 8), "scrub-stop") \
+ f(SCRUB_MAP, __CEPH_OSD_OP1(SUB, 9), "scrub-map") \
+ \
+ /** lock **/ \
+ f(WRLOCK, __CEPH_OSD_OP(WR, LOCK, 1), "wrlock") \
+ f(WRUNLOCK, __CEPH_OSD_OP(WR, LOCK, 2), "wrunlock") \
+ f(RDLOCK, __CEPH_OSD_OP(WR, LOCK, 3), "rdlock") \
+ f(RDUNLOCK, __CEPH_OSD_OP(WR, LOCK, 4), "rdunlock") \
+ f(UPLOCK, __CEPH_OSD_OP(WR, LOCK, 5), "uplock") \
+ f(DNLOCK, __CEPH_OSD_OP(WR, LOCK, 6), "dnlock") \
+ \
+ /** exec **/ \
+ /* note: the RD bit here is wrong; see special-case below in helper */ \
+ f(CALL, __CEPH_OSD_OP(RD, EXEC, 1), "call") \
+ \
+ /** pg **/ \
+ f(PGLS, __CEPH_OSD_OP(RD, PG, 1), "pgls") \
+ f(PGLS_FILTER, __CEPH_OSD_OP(RD, PG, 2), "pgls-filter") \
+ f(PG_HITSET_LS, __CEPH_OSD_OP(RD, PG, 3), "pg-hitset-ls") \
+ f(PG_HITSET_GET, __CEPH_OSD_OP(RD, PG, 4), "pg-hitset-get")
+
enum {
- /** data **/
- /* read */
- CEPH_OSD_OP_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
- CEPH_OSD_OP_STAT = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,
- CEPH_OSD_OP_MAPEXT = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 3,
-
- /* fancy read */
- CEPH_OSD_OP_MASKTRUNC = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,
- CEPH_OSD_OP_SPARSE_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 5,
-
- CEPH_OSD_OP_NOTIFY = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 6,
- CEPH_OSD_OP_NOTIFY_ACK = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 7,
-
- /* versioning */
- CEPH_OSD_OP_ASSERT_VER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 8,
-
- /* write */
- CEPH_OSD_OP_WRITE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
- CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
- CEPH_OSD_OP_TRUNCATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
- CEPH_OSD_OP_ZERO = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
- CEPH_OSD_OP_DELETE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,
-
- /* fancy write */
- CEPH_OSD_OP_APPEND = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
- CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
- CEPH_OSD_OP_SETTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
- CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,
-
- CEPH_OSD_OP_TMAPUP = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
- CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
- CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,
-
- CEPH_OSD_OP_CREATE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,
- CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14,
-
- CEPH_OSD_OP_WATCH = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15,
-
- /* omap */
- CEPH_OSD_OP_OMAPGETKEYS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 17,
- CEPH_OSD_OP_OMAPGETVALS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 18,
- CEPH_OSD_OP_OMAPGETHEADER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 19,
- CEPH_OSD_OP_OMAPGETVALSBYKEYS =
- CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 20,
- CEPH_OSD_OP_OMAPSETVALS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 21,
- CEPH_OSD_OP_OMAPSETHEADER = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 22,
- CEPH_OSD_OP_OMAPCLEAR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 23,
- CEPH_OSD_OP_OMAPRMKEYS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
- CEPH_OSD_OP_OMAP_CMP = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
-
- /* hints */
- CEPH_OSD_OP_SETALLOCHINT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 35,
-
- /** multi **/
- CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
- CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
- CEPH_OSD_OP_SRC_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 3,
-
- /** attrs **/
- /* read */
- CEPH_OSD_OP_GETXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
- CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,
- CEPH_OSD_OP_CMPXATTR = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3,
-
- /* write */
- CEPH_OSD_OP_SETXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
- CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
- CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
- CEPH_OSD_OP_RMXATTR = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,
-
- /** subop **/
- CEPH_OSD_OP_PULL = CEPH_OSD_OP_MODE_SUB | 1,
- CEPH_OSD_OP_PUSH = CEPH_OSD_OP_MODE_SUB | 2,
- CEPH_OSD_OP_BALANCEREADS = CEPH_OSD_OP_MODE_SUB | 3,
- CEPH_OSD_OP_UNBALANCEREADS = CEPH_OSD_OP_MODE_SUB | 4,
- CEPH_OSD_OP_SCRUB = CEPH_OSD_OP_MODE_SUB | 5,
- CEPH_OSD_OP_SCRUB_RESERVE = CEPH_OSD_OP_MODE_SUB | 6,
- CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7,
- CEPH_OSD_OP_SCRUB_STOP = CEPH_OSD_OP_MODE_SUB | 8,
- CEPH_OSD_OP_SCRUB_MAP = CEPH_OSD_OP_MODE_SUB | 9,
-
- /** lock **/
- CEPH_OSD_OP_WRLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
- CEPH_OSD_OP_WRUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
- CEPH_OSD_OP_RDLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
- CEPH_OSD_OP_RDUNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
- CEPH_OSD_OP_UPLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
- CEPH_OSD_OP_DNLOCK = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,
-
- /** exec **/
- /* note: the RD bit here is wrong; see special-case below in helper */
- CEPH_OSD_OP_CALL = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,
-
- /** pg **/
- CEPH_OSD_OP_PGLS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
- CEPH_OSD_OP_PGLS_FILTER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 2,
+#define GENERATE_ENUM_ENTRY(op, opcode, str) CEPH_OSD_OP_##op = (opcode),
+__CEPH_FORALL_OSD_OPS(GENERATE_ENUM_ENTRY)
+#undef GENERATE_ENUM_ENTRY
};
static inline int ceph_osd_op_type_lock(int op)