diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-07-31 23:35:28 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-07-31 23:35:28 +0200 |
commit | cc8362b1f6d724e46f515121d442779924b19fec (patch) | |
tree | 86fb5c3767e538ec9ded57dd7b3ce5d69dcde691 /net/ceph/osdmap.c | |
parent | Merge tag 'writeback-proportions' of git://git.kernel.org/pub/scm/linux/kerne... (diff) | |
parent | rbd: create rbd_refresh_helper() (diff) | |
download | linux-cc8362b1f6d724e46f515121d442779924b19fec.tar.xz linux-cc8362b1f6d724e46f515121d442779924b19fec.zip |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client
Pull Ceph changes from Sage Weil:
"Lots of stuff this time around:
- lots of cleanup and refactoring in the libceph messenger code, and
many hard to hit races and bugs closed as a result.
- lots of cleanup and refactoring in the rbd code from Alex Elder,
mostly in preparation for the layering functionality that will be
coming in 3.7.
- some misc rbd cleanups from Josh Durgin that are finally going
upstream
- support for CRUSH tunables (used by newer clusters to improve the
data placement)
- some cleanup in our use of d_parent that Al brought up a while back
- a random collection of fixes across the tree
There is another patch coming that fixes up our ->atomic_open()
behavior, but I'm going to hammer on it a bit more before sending it."
Fix up conflicts due to commits that were already committed earlier in
drivers/block/rbd.c, net/ceph/{messenger.c, osd_client.c}
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (132 commits)
rbd: create rbd_refresh_helper()
rbd: return obj version in __rbd_refresh_header()
rbd: fixes in rbd_header_from_disk()
rbd: always pass ops array to rbd_req_sync_op()
rbd: pass null version pointer in add_snap()
rbd: make rbd_create_rw_ops() return a pointer
rbd: have __rbd_add_snap_dev() return a pointer
libceph: recheck con state after allocating incoming message
libceph: change ceph_con_in_msg_alloc convention to be less weird
libceph: avoid dropping con mutex before fault
libceph: verify state after retaking con lock after dispatch
libceph: revoke mon_client messages on session restart
libceph: fix handling of immediate socket connect failure
ceph: update MAINTAINERS file
libceph: be less chatty about stray replies
libceph: clear all flags on con_close
libceph: clean up con flags
libceph: replace connection state bits with states
libceph: drop unnecessary CLOSED check in socket state change callback
libceph: close socket directly from ceph_con_close()
...
Diffstat (limited to 'net/ceph/osdmap.c')
-rw-r--r-- | net/ceph/osdmap.c | 59 |
1 files changed, 53 insertions, 6 deletions
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 81e3b84a77ef..3124b71a8883 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -135,6 +135,21 @@ bad: return -EINVAL; } +static int skip_name_map(void **p, void *end) +{ + int len; + ceph_decode_32_safe(p, end, len ,bad); + while (len--) { + int strlen; + *p += sizeof(u32); + ceph_decode_32_safe(p, end, strlen, bad); + *p += strlen; +} + return 0; +bad: + return -EINVAL; +} + static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; @@ -143,6 +158,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) void **p = &pbyval; void *start = pbyval; u32 magic; + u32 num_name_maps; dout("crush_decode %p to %p len %d\n", *p, end, (int)(end - *p)); @@ -150,6 +166,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end) if (c == NULL) return ERR_PTR(-ENOMEM); + /* set tunables to default values */ + c->choose_local_tries = 2; + c->choose_local_fallback_tries = 5; + c->choose_total_tries = 19; + ceph_decode_need(p, end, 4*sizeof(u32), bad); magic = ceph_decode_32(p); if (magic != CRUSH_MAGIC) { @@ -297,7 +318,25 @@ static struct crush_map *crush_decode(void *pbyval, void *end) } /* ignore trailing name maps. */ + for (num_name_maps = 0; num_name_maps < 3; num_name_maps++) { + err = skip_name_map(p, end); + if (err < 0) + goto done; + } + + /* tunables */ + ceph_decode_need(p, end, 3*sizeof(u32), done); + c->choose_local_tries = ceph_decode_32(p); + c->choose_local_fallback_tries = ceph_decode_32(p); + c->choose_total_tries = ceph_decode_32(p); + dout("crush decode tunable choose_local_tries = %d", + c->choose_local_tries); + dout("crush decode tunable choose_local_fallback_tries = %d", + c->choose_local_fallback_tries); + dout("crush decode tunable choose_total_tries = %d", + c->choose_total_tries); +done: dout("crush_decode success\n"); return c; @@ -488,15 +527,16 @@ static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) ceph_decode_32_safe(p, end, pool, bad); ceph_decode_32_safe(p, end, len, bad); dout(" pool %d len %d\n", pool, len); + ceph_decode_need(p, end, len, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) { + char *name = kstrndup(*p, len, GFP_NOFS); + + if (!name) + return -ENOMEM; kfree(pi->name); - pi->name = kmalloc(len + 1, GFP_NOFS); - if (pi->name) { - memcpy(pi->name, *p, len); - pi->name[len] = '\0'; - dout(" name is %s\n", pi->name); - } + pi->name = name; + dout(" name is %s\n", pi->name); } *p += len; } @@ -666,6 +706,9 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad); ceph_decode_copy(p, &pgid, sizeof(pgid)); n = ceph_decode_32(p); + err = -EINVAL; + if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) + goto bad; ceph_decode_need(p, end, n * sizeof(u32), bad); err = -ENOMEM; pg = kmalloc(sizeof(*pg) + n*sizeof(u32), GFP_NOFS); @@ -889,6 +932,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, (void) __remove_pg_mapping(&map->pg_temp, pgid); /* insert */ + if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) { + err = -EINVAL; + goto bad; + } pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); if (!pg) { err = -ENOMEM; |