linux/net/ceph, branch v5.4

libceph: use ceph_kvmalloc() for osdmap arrays

2019-09-16T10:06:25Z

osdmap has a bunch of arrays that grow linearly with the number of OSDs. osd_state, osd_weight and osd_primary_affinity take 4 bytes per OSD. osd_addr takes 136 bytes per OSD because of sockaddr_storage. The CRUSH workspace area also grows linearly with the number of OSDs. Normally these arrays are allocated at client startup. The osdmap is usually updated in small incrementals, but once in a while a full map may need to be processed. For a cluster with 10000 OSDs, this means a bunch of 40K allocations followed by a 1.3M allocation, all of which are currently required to be physically contiguous. This results in sporadic ENOMEM errors, hanging the client. Go back to manually (re)allocating arrays and use ceph_kvmalloc() to fall back to non-contiguous allocation when necessary. Link: https://tracker.ceph.com/issues/40481 Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton

libceph: avoid a __vmalloc() deadlock in ceph_kvmalloc()

2019-09-16T10:06:25Z

The vmalloc allocator doesn't fully respect the specified gfp mask: while the actual pages are allocated as requested, the page table pages are always allocated with GFP_KERNEL. ceph_kvmalloc() may be called with GFP_NOFS and GFP_NOIO (for ceph and rbd respectively), so this may result in a deadlock. There is no real reason for the current PAGE_ALLOC_COSTLY_ORDER logic, it's just something that seemed sensible at the time (ceph_kvmalloc() predates kvmalloc()). kvmalloc() is smarter: in an attempt to reduce long term fragmentation, it first tries to kmalloc non-disruptively. Switch to kvmalloc() and set the respective PF_MEMALLOC_* flag using the scope API to avoid the deadlock. Note that kvmalloc() needs to be passed GFP_KERNEL to enable the fallback. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton

libceph: drop unused con parameter of calc_target()

2019-09-16T10:06:25Z

This bit was omitted from a561372405cf ("libceph: fix PG split vs OSD (re)connect race") to avoid backport conflicts. Signed-off-by: Ilya Dryomov

libceph: handle OSD op ceph_pagelist_append() errors

2019-09-16T10:06:25Z

osd_req_op_cls_init() and osd_req_op_xattr_init() currently propagate ceph_pagelist_alloc() ENOMEM errors but ignore ceph_pagelist_append() memory allocation failures. Add these checks and cleanup on error. Signed-off-by: David Disseldorp Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov

libceph: add function that clears osd client's abort_err

2019-09-16T10:06:23Z

Signed-off-by: "Yan, Zheng" Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov

libceph: add function that reset client's entity addr

2019-09-16T10:06:23Z

This function also re-open connections to OSD/MON, and re-send in-flight OSD requests after re-opening connections to OSD. Signed-off-by: "Yan, Zheng" Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov

libceph: don't call crypto_free_sync_skcipher() on a NULL tfm

2019-08-28T10:33:46Z

In set_secret(), key->tfm is assigned to NULL on line 55, and then ceph_crypto_key_destroy(key) is executed. ceph_crypto_key_destroy(key) crypto_free_sync_skcipher(key->tfm) crypto_free_skcipher(&tfm->base); This happens to work because crypto_sync_skcipher is a trivial wrapper around crypto_skcipher: &tfm->base is still 0 and crypto_free_skcipher() handles that. Let's not rely on the layout of crypto_sync_skcipher. This bug is found by a static analysis tool STCheck written by us. Fixes: 69d6302b65a8 ("libceph: Remove VLA usage of skcipher"). Signed-off-by: Jia-Ju Bai Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov

libceph: fix PG split vs OSD (re)connect race

2019-08-22T08:47:41Z

We can't rely on ->peer_features in calc_target() because it may be called both when the OSD session is established and open and when it's not. ->peer_features is not valid unless the OSD session is open. If this happens on a PG split (pg_num increase), that could mean we don't resend a request that should have been resent, hanging the client indefinitely. In userspace this was fixed by looking at require_osd_release and get_xinfo[osd].features fields of the osdmap. However these fields belong to the OSD section of the osdmap, which the kernel doesn't decode (only the client section is decoded). Instead, let's drop this feature check. It effectively checks for luminous, so only pre-luminous OSDs would be affected in that on a PG split the kernel might resend a request that should not have been resent. Duplicates can occur in other scenarios, so both sides should already be prepared for them: see dup/replay logic on the OSD side and retry_attempt check on the client side. Cc: stable@vger.kernel.org Fixes: 7de030d6b10a ("libceph: resend on PG splits if OSD has RESEND_ON_SPLIT") Link: https://tracker.ceph.com/issues/41162 Reported-by: Jerry Lee Signed-off-by: Ilya Dryomov Tested-by: Jerry Lee Reviewed-by: Jeff Layton

Merge tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client

2019-07-18T18:05:25Z

Pull ceph updates from Ilya Dryomov: "Lots of exciting things this time! - support for rbd object-map and fast-diff features (myself). This will speed up reads, discards and things like snap diffs on sparse images. - ceph.snap.btime vxattr to expose snapshot creation time (David Disseldorp). This will be used to integrate with "Restore Previous Versions" feature added in Windows 7 for folks who reexport ceph through SMB. - security xattrs for ceph (Zheng Yan). Only selinux is supported for now due to the limitations of ->dentry_init_security(). - support for MSG_ADDR2, FS_BTIME and FS_CHANGE_ATTR features (Jeff Layton). This is actually a single feature bit which was missing because of the filesystem pieces. With this in, the kernel client will finally be reported as "luminous" by "ceph features" -- it is still being reported as "jewel" even though all required Luminous features were implemented in 4.13. - stop NULL-terminating ceph vxattrs (Jeff Layton). The convention with xattrs is to not terminate and this was causing inconsistencies with ceph-fuse. - change filesystem time granularity from 1 us to 1 ns, again fixing an inconsistency with ceph-fuse (Luis Henriques). On top of this there are some additional dentry name handling and cap flushing fixes from Zheng. Finally, Jeff is formally taking over for Zheng as the filesystem maintainer" * tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client: (71 commits) ceph: fix end offset in truncate_inode_pages_range call ceph: use generic_delete_inode() for ->drop_inode ceph: use ceph_evict_inode to cleanup inode's resource ceph: initialize superblock s_time_gran to 1 MAINTAINERS: take over for Zheng as CephFS kernel client maintainer rbd: setallochint only if object doesn't exist rbd: support for object-map and fast-diff rbd: call rbd_dev_mapping_set() from rbd_dev_image_probe() libceph: export osd_req_op_data() macro libceph: change ceph_osdc_call() to take page vector for response libceph: bump CEPH_MSG_MAX_DATA_LEN (again) rbd: new exclusive lock wait/wake code rbd: quiescing lock should wait for image requests rbd: lock should be quiesced on reacquire rbd: introduce copyup state machine rbd: rename rbd_obj_setup_*() to rbd_obj_init_*() rbd: move OSD request allocation into object request state machines rbd: factor out __rbd_osd_setup_discard_ops() rbd: factor out rbd_osd_setup_copyup() rbd: introduce obj_req->osd_reqs list ...

Merge tag 'driver-core-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

2019-07-12T19:24:03Z

Pull driver core and debugfs updates from Greg KH: "Here is the "big" driver core and debugfs changes for 5.3-rc1 It's a lot of different patches, all across the tree due to some api changes and lots of debugfs cleanups. Other than the debugfs cleanups, in this set of changes we have: - bus iteration function cleanups - scripts/get_abi.pl tool to display and parse Documentation/ABI entries in a simple way - cleanups to Documenatation/ABI/ entries to make them parse easier due to typos and other minor things - default_attrs use for some ktype users - driver model documentation file conversions to .rst - compressed firmware file loading - deferred probe fixes All of these have been in linux-next for a while, with a bunch of merge issues that Stephen has been patient with me for" * tag 'driver-core-5.3-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (102 commits) debugfs: make error message a bit more verbose orangefs: fix build warning from debugfs cleanup patch ubifs: fix build warning after debugfs cleanup patch driver: core: Allow subsystems to continue deferring probe drivers: base: cacheinfo: Ensure cpu hotplug work is done before Intel RDT arch_topology: Remove error messages on out-of-memory conditions lib: notifier-error-inject: no need to check return value of debugfs_create functions swiotlb: no need to check return value of debugfs_create functions ceph: no need to check return value of debugfs_create functions sunrpc: no need to check return value of debugfs_create functions ubifs: no need to check return value of debugfs_create functions orangefs: no need to check return value of debugfs_create functions nfsd: no need to check return value of debugfs_create functions lib: 842: no need to check return value of debugfs_create functions debugfs: provide pr_fmt() macro debugfs: log errors when something goes wrong drivers: s390/cio: Fix compilation warning about const qualifiers drivers: Add generic helper to match by of_node driver_find_device: Unify the match function with class_find_device() bus_find_device: Unify the match callback with class_find_device ...