user/sven/linux.git/include/linux/ceph, branch v3.16.46

libceph: make authorizer destruction independent of ceph_auth_client

2016-06-15T20:29:27Z

commit 6c1ea260f89709e0021d2c59f8fd2a104b5b1123 upstream. Starting the kernel client with cephx disabled and then enabling cephx and restarting userspace daemons can result in a crash: [262671.478162] BUG: unable to handle kernel paging request at ffffebe000000000 [262671.531460] IP: [] kfree+0x5a/0x130 [262671.584334] PGD 0 [262671.635847] Oops: 0000 [#1] SMP [262672.055841] CPU: 22 PID: 2961272 Comm: kworker/22:2 Not tainted 4.2.0-34-generic #39~14.04.1-Ubuntu [262672.162338] Hardware name: Dell Inc. PowerEdge R720/068CDY, BIOS 2.4.3 07/09/2014 [262672.268937] Workqueue: ceph-msgr con_work [libceph] [262672.322290] task: ffff88081c2d0dc0 ti: ffff880149ae8000 task.ti: ffff880149ae8000 [262672.428330] RIP: 0010:[] [] kfree+0x5a/0x130 [262672.535880] RSP: 0018:ffff880149aeba58 EFLAGS: 00010286 [262672.589486] RAX: 000001e000000000 RBX: 0000000000000012 RCX: ffff8807e7461018 [262672.695980] RDX: 000077ff80000000 RSI: ffff88081af2be04 RDI: 0000000000000012 [262672.803668] RBP: ffff880149aeba78 R08: 0000000000000000 R09: 0000000000000000 [262672.912299] R10: ffffebe000000000 R11: ffff880819a60e78 R12: ffff8800aec8df40 [262673.021769] R13: ffffffffc035f70f R14: ffff8807e5b138e0 R15: ffff880da9785840 [262673.131722] FS: 0000000000000000(0000) GS:ffff88081fac0000(0000) knlGS:0000000000000000 [262673.245377] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [262673.303281] CR2: ffffebe000000000 CR3: 0000000001c0d000 CR4: 00000000001406e0 [262673.417556] Stack: [262673.472943] ffff880149aeba88 ffff88081af2be04 ffff8800aec8df40 ffff88081af2be04 [262673.583767] ffff880149aeba98 ffffffffc035f70f ffff880149aebac8 ffff8800aec8df00 [262673.694546] ffff880149aebac8 ffffffffc035c89e ffff8807e5b138e0 ffff8805b047f800 [262673.805230] Call Trace: [262673.859116] [] ceph_x_destroy_authorizer+0x1f/0x50 [libceph] [262673.968705] [] ceph_auth_destroy_authorizer+0x3e/0x60 [libceph] [262674.078852] [] put_osd+0x45/0x80 [libceph] [262674.134249] [] remove_osd+0xae/0x140 [libceph] [262674.189124] [] __reset_osd+0x103/0x150 [libceph] [262674.243749] [] kick_requests+0x223/0x460 [libceph] [262674.297485] [] ceph_osdc_handle_map+0x282/0x5e0 [libceph] [262674.350813] [] dispatch+0x4e/0x720 [libceph] [262674.403312] [] try_read+0x3d1/0x1090 [libceph] [262674.454712] [] ? dequeue_entity+0x152/0x690 [262674.505096] [] con_work+0xcb/0x1300 [libceph] [262674.555104] [] process_one_work+0x14e/0x3d0 [262674.604072] [] worker_thread+0x11a/0x470 [262674.652187] [] ? rescuer_thread+0x310/0x310 [262674.699022] [] kthread+0xd2/0xf0 [262674.744494] [] ? kthread_create_on_node+0x1c0/0x1c0 [262674.789543] [] ret_from_fork+0x3f/0x70 [262674.834094] [] ? kthread_create_on_node+0x1c0/0x1c0 What happens is the following: (1) new MON session is established (2) old "none" ac is destroyed (3) new "cephx" ac is constructed ... (4) old OSD session (w/ "none" authorizer) is put ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer) osd->o_auth.authorizer in the "none" case is just a bare pointer into ac, which contains a single static copy for all services. By the time we get to (4), "none" ac, freed in (2), is long gone. On top of that, a new vtable installed in (3) points us at ceph_x_destroy_authorizer(), so we end up trying to destroy a "none" authorizer with a "cephx" destructor operating on invalid memory! To fix this, decouple authorizer destruction from ac and do away with a single static "none" authorizer by making a copy for each OSD or MDS session. Authorizers themselves are independent of ac and so there is no reason for destroy_authorizer() to be an ac op. Make it an op on the authorizer itself by turning ceph_authorizer into a real struct. Fixes: http://tracker.ceph.com/issues/15447 Reported-by: Alan Zhang Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil [bwh: Backported to 3.16: - Implementation of ceph_x_destroy_authorizer() is different - Adjust context] Signed-off-by: Ben Hutchings

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

2014-06-13T06:06:23Z

Pull Ceph updates from Sage Weil: "This has a mix of bug fixes and cleanups. Alex's patch fixes a rare race in RBD. Ilya's patches fix an ENOENT check when a second rbd image is mapped and a couple memory leaks. Zheng fixes several issues with fragmented directories and multiple MDSs. Josh fixes a spin/sleep issue, and Josh and Guangliang's patches fix setting and unsetting RBD images read-only. Naturally there are several other cleanups mixed in for good measure" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (23 commits) rbd: only set disk to read-only once rbd: move calls that may sleep out of spin lock range rbd: add ioctl for rbd ceph: use truncate_pagecache() instead of truncate_inode_pages() ceph: include time stamp in every MDS request rbd: fix ida/idr memory leak rbd: use reference counts for image requests rbd: fix osd_request memory leak in __rbd_dev_header_watch_sync() rbd: make sure we have latest osdmap on 'rbd map' libceph: add ceph_monc_wait_osdmap() libceph: mon_get_version request infrastructure libceph: recognize poolop requests in debugfs ceph: refactor readpage_nounlock() to make the logic clearer mds: check cap ID when handling cap export message ceph: remember subtree root dirfrag's auth MDS ceph: introduce ceph_fill_fragtree() ceph: handle cap import atomically ceph: pre-allocate ceph_cap struct for ceph_add_cap() ceph: update inode fields according to issued caps rbd: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO ...

libceph: add ceph_monc_wait_osdmap()

2014-06-06T01:29:57Z

Add ceph_monc_wait_osdmap(), which will block until the osdmap with the specified epoch is received or timeout occurs. Export both of these as they are going to be needed by rbd. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil

libceph: mon_get_version request infrastructure

2014-06-06T01:29:57Z

Add support for mon_get_version requests to libceph. This reuses much of the ceph_mon_generic_request infrastructure, with one exception. Older OSDs don't set mon_get_version reply hdr->tid even if the original request had a non-zero tid, which makes it impossible to lookup ceph_mon_generic_request contexts by tid in get_generic_reply() for such replies. As a workaround, we allocate a reply message on the reply path. This can probably interfere with revoke, but I don't see a better way. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil

ceph: update inode fields according to issued caps

2014-06-06T01:29:52Z

Cap message and request reply from non-auth MDS may carry stale information (corresponding locks are in LOCK states) even they have the newest inode version. So client should update inode fields according to issued caps. Signed-off-by: Yan, Zheng

ceph_sync_read: stop poking into iov_iter guts

2014-05-06T21:39:42Z

Signed-off-by: Al Viro

libceph: enable PRIMARY_AFFINITY feature bit

2014-04-05T04:08:20Z

Announce our support for osdmaps with non-default primary affinity values. Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder

libceph: return primary from ceph_calc_pg_acting()

2014-04-05T04:08:14Z

In preparation for adding support for primary_temp, stop assuming primaryness: add a primary out parameter to ceph_calc_pg_acting() and change call sites accordingly. Primary is now specified separately from the order of osds in the set. Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder

libceph: switch ceph_calc_pg_acting() to new helpers

2014-04-05T04:08:13Z

Switch ceph_calc_pg_acting() to new helpers: pg_to_raw_osds(), raw_to_up_osds() and apply_temps(). Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder

libceph: ceph_can_shift_osds(pool) and pool type defines

2014-04-05T04:08:08Z

Bring in pg_pool_t::can_shift_osds() counterpart along with pool type defines. Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder