linux/net/ceph, branch v4.0

Revert "libceph: use memalloc flags for net IO"

2015-04-07T16:08:35Z

This reverts commit 89baaa570ab0b476db09408d209578cfed700e9f. Dirty page throttling should be sufficient for us in the general case so there is no need to use __GFP_MEMALLOC - it would be needed only in the swap-over-rbd case, which we currently don't support. (It would probably take approximately the commit that is being reverted to add that support, but we would also need the "swap" option to distinguish from the general case and make sure swap ceph_client-s aren't shared with anything else.) See ceph-devel threads [1] and [2] for the details of why enabling pfmemalloc reserves for all cases is a bad thing. On top of potential system lockups related to drained emergency reserves, this turned out to cause ceph lockups in case peers are on the same host and communicating via loopback due to sk_filter() dropping pfmemalloc skbs on the receiving side because the receiving loopback socket is not tagged with SOCK_MEMALLOC. [1] "SOCK_MEMALLOC vs loopback" http://www.spinics.net/lists/ceph-devel/msg22998.html [2] "[PATCH] libceph: don't set memalloc flags in loopback case" http://www.spinics.net/lists/ceph-devel/msg23392.html Conflicts: net/ceph/messenger.c [ context: tcp_nodelay option ] Cc: Mike Christie Cc: Mel Gorman Cc: Sage Weil Cc: stable@vger.kernel.org # 3.18+, needs backporting Signed-off-by: Ilya Dryomov Acked-by: Mike Christie Acked-by: Mel Gorman

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

2015-02-19T22:14:42Z

Pull Ceph changes from Sage Weil: "On the RBD side, there is a conversion to blk-mq from Christoph, several long-standing bug fixes from Ilya, and some cleanup from Rickard Strandqvist. On the CephFS side there is a long list of fixes from Zheng, including improved session handling, a few IO path fixes, some dcache management correctness fixes, and several blocking while !TASK_RUNNING fixes. The core code gets a few cleanups and Chaitanya has added support for TCP_NODELAY (which has been used on the server side for ages but we somehow missed on the kernel client). There is also an update to MAINTAINERS to fix up some email addresses and reflect that Ilya and Zheng are doing most of the maintenance for RBD and CephFS these days. Do not be surprised to see a pull request come from one of them in the future if I am unavailable for some reason" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (27 commits) MAINTAINERS: update Ceph and RBD maintainers libceph: kfree() in put_osd() shouldn't depend on authorizer libceph: fix double __remove_osd() problem rbd: convert to blk-mq ceph: return error for traceless reply race ceph: fix dentry leaks ceph: re-send requests when MDS enters reconnecting stage ceph: show nocephx_require_signatures and notcp_nodelay options libceph: tcp_nodelay support rbd: do not treat standalone as flatten ceph: fix atomic_open snapdir ceph: properly mark empty directory as complete client: include kernel version in client metadata ceph: provide seperate {inode,file}_operations for snapdir ceph: fix request time stamp encoding ceph: fix reading inline data when i_size > PAGE_SIZE ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_close_sessions) ceph: avoid block operation when !TASK_RUNNING (ceph_get_caps) ceph: avoid block operation when !TASK_RUNNING (ceph_mdsc_sync) rbd: fix error paths in rbd_dev_refresh() ...

libceph: kfree() in put_osd() shouldn't depend on authorizer

2015-02-19T11:27:51Z

a255651d4cad ("ceph: ensure auth ops are defined before use") made kfree() in put_osd() conditional on the authorizer. A mechanical mistake most likely - fix it. Cc: Alex Elder Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil Reviewed-by: Alex Elder

libceph: fix double __remove_osd() problem

2015-02-19T11:27:50Z

It turns out it's possible to get __remove_osd() called twice on the same OSD. That doesn't sit well with rb_erase() - depending on the shape of the tree we can get a NULL dereference, a soft lockup or a random crash at some point in the future as we end up touching freed memory. One scenario that I was able to reproduce is as follows: con_fault_finish() osd_reset() ceph_osdc_handle_map() kick_requests() reset_changed_osds() __reset_osd() __remove_osd() __kick_osd_requests() __reset_osd() __remove_osd() <-- !!! A case can be made that osd refcounting is imperfect and reworking it would be a proper resolution, but for now Sage and I decided to fix this by adding a safe guard around __remove_osd(). Fixes: http://tracker.ceph.com/issues/8087 Cc: Sage Weil Cc: stable@vger.kernel.org # 3.9+: 7c6e6fc53e73: libceph: assert both regular and lingering lists in __remove_osd() Cc: stable@vger.kernel.org # 3.9+: cc9f1f518cec: libceph: change from BUG to WARN for __remove_osd() asserts Cc: stable@vger.kernel.org # 3.9+ Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil Reviewed-by: Alex Elder

libceph: tcp_nodelay support

2015-02-19T10:31:40Z

TCP_NODELAY socket option set on connection sockets, disables Nagle’s algorithm and improves latency characteristics. tcp_nodelay(default)/notcp_nodelay option flags provided to enable/disable setting the socket option. Signed-off-by: Chaitanya Huilgol [idryomov@redhat.com: NO_TCP_NODELAY -> TCP_NODELAY, minor adjustments] Signed-off-by: Ilya Dryomov

libceph: use mon_client.c/put_generic_request() more

2015-02-19T10:31:37Z

Signed-off-by: Ilya Dryomov

libceph: nuke pool op infrastructure

2015-02-19T10:31:37Z

On Mon, Dec 22, 2014 at 5:35 PM, Sage Weil wrote: > On Mon, 22 Dec 2014, Ilya Dryomov wrote: >> Actually, pool op stuff has been unused for over two years - looks like >> it was added for rbd create_snap and that got ripped out in 2012. It's >> unlikely we'd ever need to manage pools or snaps from the kernel client >> so I think it makes sense to nuke it. Sage? > > Yep! Signed-off-by: Ilya Dryomov

mm: gup: use get_user_pages_unlocked

2015-02-12T01:06:05Z

This allows those get_user_pages calls to pass FAULT_FLAG_ALLOW_RETRY to the page fault in order to release the mmap_sem during the I/O. Signed-off-by: Andrea Arcangeli Reviewed-by: Kirill A. Shutemov Cc: Andres Lagar-Cavilla Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

libceph: fix sparse endianness warnings

2015-01-08T17:36:57Z

The only real issue is the one in auth_x.c and it came with 3.19-rc1 merge. Signed-off-by: Ilya Dryomov

libceph: specify position of extent operation

2014-12-17T17:09:52Z

allow specifying position of extent operation in multi-operations osd request. This is required for cephfs to convert inline data to normal data (compare xattr, then write object). Signed-off-by: Yan, Zheng Reviewed-by: Ilya Dryomov