linux-stable.git/fs/ceph, branch linux-6.10.y

ceph: fix cap ref leak via netfs init_request

2024-10-10T10:01:06+00:00

commit ccda9910d8490f4fb067131598e4b2e986faa5a0 upstream.

Log recovered from a user's cluster:

    <7>[ 5413.970692] ceph:  get_cap_refs 00000000958c114b ret 1 got Fr
    <7>[ 5413.970695] ceph:  start_read 00000000958c114b, no cache cap
    ...
    <7>[ 5473.934609] ceph:   my wanted = Fr, used = Fr, dirty -
    <7>[ 5473.934616] ceph:  revocation: pAsLsXsFr -> pAsLsXs (revoking Fr)
    <7>[ 5473.934632] ceph:  __ceph_caps_issued 00000000958c114b cap 00000000f7784259 issued pAsLsXs
    <7>[ 5473.934638] ceph:  check_caps 10000000e68.fffffffffffffffe file_want - used Fr dirty - flushing - issued pAsLsXs revoking Fr retain pAsLsXsFsr  AUTHONLY NOINVAL FLUSH_FORCE

The MDS subsequently complains that the kernel client is late releasing
caps.

Approximately, a series of changes to this code by commits 49870056005c
("ceph: convert ceph_readpages to ceph_readahead"), 2de160417315
("netfs: Change ->init_request() to return an error code") and
a5c9dc445139 ("ceph: Make ceph_init_request() check caps on readahead")
resulted in subtle resource cleanup to be missed. The main culprit is
the change in error handling in 2de160417315 which meant that a failure
in init_request() would no longer cause cleanup to be called. That
would prevent the ceph_put_cap_refs() call which would cleanup the
leaked cap ref.

Cc: stable@vger.kernel.org
Fixes: a5c9dc445139 ("ceph: Make ceph_init_request() check caps on readahead")
Link: https://tracker.ceph.com/issues/67008
Signed-off-by: Patrick Donnelly 
Reviewed-by: Ilya Dryomov 
Signed-off-by: Ilya Dryomov 
Signed-off-by: Greg Kroah-Hartman

ceph: remove the incorrect Fw reference check when dirtying pages

2024-10-10T10:00:04+00:00

[ Upstream commit c08dfb1b49492c09cf13838c71897493ea3b424e ]

When doing the direct-io reads it will also try to mark pages dirty,
but for the read path it won't hold the Fw caps and there is case
will it get the Fw reference.

Fixes: 5dda377cf0a6 ("ceph: set i_head_snapc when getting CEPH_CAP_FILE_WR reference")
Signed-off-by: Xiubo Li 
Reviewed-by: Patrick Donnelly 
Signed-off-by: Ilya Dryomov 
Signed-off-by: Sasha Levin

ceph: fix a memory leak on cap_auths in MDS client

2024-10-10T10:00:04+00:00

[ Upstream commit d97079e97eab20e08afc507f2bed4501e2824717 ]

The cap_auths that are allocated during an MDS session opening are never
released, causing a memory leak detected by kmemleak.  Fix this by freeing
the memory allocated when shutting down the MDS client.

Fixes: 1d17de9534cb ("ceph: save cap_auths in MDS client when session is opened")
Signed-off-by: Luis Henriques (SUSE) 
Reviewed-by: Xiubo Li 
Signed-off-by: Ilya Dryomov 
Signed-off-by: Sasha Levin

netfs, ceph: Partially revert "netfs: Replace PG_fscache by setting folio->private and marking dirty"

2024-09-04T11:29:57+00:00

commit 92764e8822d4e7f8efb5ad959fac195a7f8ea0c6 upstream.

This partially reverts commit 2ff1e97587f4d398686f52c07afde3faf3da4e5c.

In addition to reverting the removal of PG_private_2 wrangling from the
buffered read code[1][2], the removal of the waits for PG_private_2 from
netfs_release_folio() and netfs_invalidate_folio() need reverting too.

It also adds a wait into ceph_evict_inode() to wait for netfs read and
copy-to-cache ops to complete.

Fixes: 2ff1e97587f4 ("netfs: Replace PG_fscache by setting folio->private and marking dirty")
Signed-off-by: David Howells 
Link: https://lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk [1]
Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=8e5ced7804cb9184c4a23f8054551240562a8eda [2]
Link: https://lore.kernel.org/r/20240814203850.2240469-2-dhowells@redhat.com
cc: Max Kellermann 
cc: Ilya Dryomov 
cc: Xiubo Li 
cc: Jeff Layton 
cc: Matthew Wilcox 
cc: ceph-devel@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
Signed-off-by: Christian Brauner 
Signed-off-by: Greg Kroah-Hartman

netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag"

2024-08-29T15:35:34+00:00

commit 8e5ced7804cb9184c4a23f8054551240562a8eda upstream.

This reverts commit ae678317b95e760607c7b20b97c9cd4ca9ed6e1a.

Revert the patch that removes the deprecated use of PG_private_2 in
netfslib for the moment as Ceph is actually still using this to track
data copied to the cache.

Fixes: ae678317b95e ("netfs: Remove deprecated use of PG_private_2 as a second writeback flag")
Reported-by: Max Kellermann 
Signed-off-by: David Howells 
cc: Ilya Dryomov 
cc: Xiubo Li 
cc: Jeff Layton 
cc: Matthew Wilcox 
cc: ceph-devel@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
https: //lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk
Signed-off-by: Christian Brauner 
Signed-off-by: Greg Kroah-Hartman

ceph: force sending a cap update msg back to MDS for revoke op

2024-08-11T10:57:57+00:00

commit 31634d7597d8c57894b6c98eeefc9e58cf842993 upstream.

If a client sends out a cap update dropping caps with the prior 'seq'
just before an incoming cap revoke request, then the client may drop
the revoke because it believes it's already released the requested
capabilities.

This causes the MDS to wait indefinitely for the client to respond
to the revoke. It's therefore always a good idea to ack the cap
revoke request with the bumped up 'seq'.

Currently if the cap->issued equals to the newcaps the check_caps()
will do nothing, we should force flush the caps.

Cc: stable@vger.kernel.org
Link: https://tracker.ceph.com/issues/61782
Signed-off-by: Xiubo Li 
Reviewed-by: Venky Shankar 
Signed-off-by: Ilya Dryomov 
Signed-off-by: Greg Kroah-Hartman

ceph: fix incorrect kmalloc size of pagevec mempool

2024-08-03T07:01:07+00:00

[ Upstream commit 03230edb0bd831662a7c08b6fef66b2a9a817774 ]

The kmalloc size of pagevec mempool is incorrectly calculated.
It misses the size of page pointer and only accounts the number for the array.

Fixes: a0102bda5bc0 ("ceph: move sb->wb_pagevec_pool to be a global mempool")
Signed-off-by: ethanwu 
Reviewed-by: Xiubo Li 
Signed-off-by: Ilya Dryomov 
Signed-off-by: Sasha Levin

Merge tag 'ceph-for-6.10-rc1' of https://github.com/ceph/ceph-client

2024-05-25T21:23:58+00:00

Pull ceph updates from Ilya Dryomov:
 "A series from Xiubo that adds support for additional access checks
  based on MDS auth caps which were recently made available to clients.

  This is needed to prevent scenarios where the MDS quietly discards
  updates that a UID-restricted client previously (wrongfully) acked to
  the user.

  Other than that, just a documentation fixup"

* tag 'ceph-for-6.10-rc1' of https://github.com/ceph/ceph-client:
  doc: ceph: update userspace command to get CephFS metadata
  ceph: add CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK feature bit
  ceph: check the cephx mds auth access for async dirop
  ceph: check the cephx mds auth access for open
  ceph: check the cephx mds auth access for setattr
  ceph: add ceph_mds_check_access() helper
  ceph: save cap_auths in MDS client when session is opened

ceph: add CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK feature bit

2024-05-23T08:35:47+00:00

Since we have support checking the mds auth cap in kclient, just
set the feature bit.

Link: https://tracker.ceph.com/issues/61333
Signed-off-by: Xiubo Li 
Reviewed-by: Milind Changire 
Signed-off-by: Ilya Dryomov

ceph: check the cephx mds auth access for async dirop

2024-05-23T08:35:47+00:00

Before doing the op locally we need to check the cephx access.

Link: https://tracker.ceph.com/issues/61333
Signed-off-by: Xiubo Li 
Reviewed-by: Milind Changire 
Signed-off-by: Ilya Dryomov