[GIT PULL] Please pull NFS client changes for 4.14

From: Trond Myklebust
Date: Mon Sep 11 2017 - 16:54:59 EST

Next message: Rob Herring: "Re: [PATCH v3 2/3] dt-bindings: mt8173-xhci: add generic compatible and rename file"
Previous message: David Rientjes: "Re: [v8 1/4] mm, oom: refactor the oom_kill_process() function"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Hi Linus,

The following changes since commit ef954844c7ace62f773f4f23e28d2d915adc419f:

Linux 4.13-rc5 (2017-08-13 16:01:32 -0700)

are available in the git repository at:

git://git.linux-nfs.org/projects/trondmy/linux-nfs.git tags/nfs-for-4.14-1

for you to fetch changes up to 1bd5d6d08ea7ed0794c8a3908383d6d6fc202cdd:

NFS: Count the bytes of skipped subrequests in nfs_lock_and_join_requests() (2017-09-09 16:43:09 -0400)

----------------------------------------------------------------
NFS client updates for Linux 4.14

Hightlights include:

Stable bugfixes:
- Fix mirror allocation in the writeback code to avoid a use after free
- Fix the O_DSYNC writes to use the correct byte range
- Fix 2 use after free issues in the I/O code

Features:
- Writeback fixes to split up the inode->i_lock in order to reduce contention
- RPC client receive fixes to reduce the amount of time the
xprt->transport_lock is held when receiving data from a socket into am
XDR buffer.
- Ditto fixes to reduce contention between call side users of the rdma
rb_lock, and its use in rpcrdma_reply_handler.
- Re-arrange rdma stats to reduce false cacheline sharing.
- Various rdma cleanups and optimisations.
- Refactor the NFSv4.1 exchange id code and clean up the code.
- Const-ify all instances of struct rpc_xprt_ops

Bugfixes:
- Fix the NFSv2 'sec=' mount option.
- NFSv4.1: don't use machine credentials for CLOSE when using 'sec=sys'
- Fix the NFSv3 GRANT callback when the port changes on the server.
- Fix livelock issues with COMMIT
- NFSv4: Use correct inode in _nfs4_opendata_to_nfs4_state() when doing
and NFSv4.1 open by filehandle.

----------------------------------------------------------------
Chuck Lever (18):
sunrpc: Const-ify all instances of struct rpc_xprt_ops
xprtrdma: Add xdr_init_decode to rpcrdma_reply_handler()
xprtrdma: Harden backchannel call decoding
xprtrdma: Refactor rpcrdma_reply_handler()
xprtrdma: Replace rpcrdma_count_chunks()
xprtrdma: Remove opcode check in Receive completion handler
xprtrdma: Remove rpcrdma_rep::rr_len
xprtrdma: Clean up XDR decoding in rpcrdma_update_granted_credits()
xprtrdma: Clean up rpcrdma_marshal_req() synopsis
xprtrdma: Remove rpclen from rpcrdma_marshal_req
xprtrdma: Set up an xdr_stream in rpcrdma_marshal_req()
xprtrdma: Harden chunk list encoding against send buffer overflow
xprtrdma: Clean up rpcrdma_bc_marshal_reply()
xprtrdma: Remove imul instructions from rpcrdma_convert_iovs()
xprtrdma: Remove imul instructions from chunk list encoders
NFS: Fix NFSv2 security settings
xprtrdma: Re-arrange struct rx_stats
xprtrdma: Use xprt_pin_rqst in rpcrdma_reply_handler

Markus Elfring (1):
lockd: Delete an error message for a failed memory allocation in reclaimer()

NeilBrown (6):
SUNRPC: ECONNREFUSED should cause a rebind.
NFSv4.1: don't use machine credentials for CLOSE when using 'sec=sys'
NFS: don't expect errors from mempool_alloc().
SUNRPC: remove some dead code.
NFS: flush data when locking a file to ensure cache coherence for mmap.
NFS: remove jiffies field from access cache

Trond Myklebust (48):
NFSv4: Refactor _nfs4_proc_exchange_id()
NFSv4.1: Ensure we clear the SP4_MACH_CRED flags in nfs4_sp4_select_mode()
NFSv4: Cleanup setting of the migration flags.
Merge branch 'exchange_id'
NFSv4: Use correct inode in _nfs4_opendata_to_nfs4_state()
NFSv4: Use the nfs4_state being recovered in _nfs4_opendata_to_nfs4_state()
Merge branch 'open_state'
NFS: Simplify page writeback
NFS: Reduce lock contention in nfs_page_find_head_request()
NFS: Reduce lock contention in nfs_try_to_update_request()
NFS: Ensure we always dereference the page head last
NFS: Fix a reference and lock leak in nfs_lock_and_join_requests()
NFS: Fix an ABBA issue in nfs_lock_and_join_requests()
NFS: Don't check request offset and size without holding a lock
NFS: Don't unlock writebacks before declaring PG_WB_END
NFS: Fix the inode request accounting when pages have subrequests
NFS: Teach nfs_try_to_update_request() to deal with request page_groups
NFS: Remove page group limit in nfs_flush_incompatible()
NFS: Reduce inode->i_lock contention in nfs_lock_and_join_requests()
NFS: Further optimise nfs_lock_and_join_requests()
NFS: Fix nfs_page_group_destroy() and nfs_lock_and_join_requests() race cases
NFS: Remove nfs_page_group_clear_bits()
NFS: Remove unuse function nfs_page_group_lock_wait()
NFS: Remove unused parameter from nfs_page_group_lock()
NFS: Fix up nfs_page_group_covers_page()
NFSv4: Convert nfs_lock_and_join_requests() to use nfs_page_find_head_request()
NFS: Refactor nfs_page_find_head_request()
NFSv4: Use a mutex to protect the per-inode commit lists
NFS: Use an atomic_long_t to count the number of requests
NFS: Use an atomic_long_t to count the number of commits
NFS: Switch to using mapping->private_lock for page writeback lookups.
NFSv4/pnfs: Replace pnfs_put_lseg_locked() with pnfs_put_lseg()
NFS: Wait for requests that are locked on the commit list
SUNRPC: Don't hold the transport lock across socket copy operations
SUNRPC: Don't hold the transport lock when receiving backchannel data
SUNRPC: Don't loop forever in xs_tcp_data_receive()
SUNRPC: Cleanup xs_tcp_read_common()
SUNRPC: Add a separate spinlock to protect the RPC request receive list
Merge branch 'writeback'
NFSv4: Fix up mirror allocation
NFS: Remove unused parameter gfp_flags from nfs_pageio_init()
Merge branch 'bugfixes'
Merge tag 'nfs-rdma-for-4.14-1' of git://git.linux-nfs.org/projects/anna/linux-nfs into linux-next
NFS: Fix 2 use after free issues in the I/O code
NFS: nfs_lock_and_join_requests and nfs_scan_commit_list can deadlock
NFS: Remove pnfs_generic_transfer_commit_list()
NFS: Don't hold the group lock when calling nfs_release_request()
NFS: Count the bytes of skipped subrequests in nfs_lock_and_join_requests()

tarangg@xxxxxxxxxx (1):
NFS: Sync the correct byte range during synchronous writes

fs/lockd/clntlock.c | 6 +-
fs/nfs/callback_proc.c | 2 +-
fs/nfs/delegation.c | 2 +-
fs/nfs/dir.c | 4 -
fs/nfs/direct.c | 4 +-
fs/nfs/file.c | 17 +-
fs/nfs/inode.c | 10 +-
fs/nfs/internal.h | 1 -
fs/nfs/nfs4_fs.h | 11 +
fs/nfs/nfs4proc.c | 274 +++++----
fs/nfs/pagelist.c | 170 +++---
fs/nfs/pnfs.c | 43 --
fs/nfs/pnfs.h | 2 -
fs/nfs/pnfs_nfs.c | 44 +-
fs/nfs/read.c | 2 +-
fs/nfs/super.c | 12 +-
fs/nfs/write.c | 457 +++++++--------
include/linux/nfs_fs.h | 6 +-
include/linux/nfs_page.h | 6 +-
include/linux/nfs_xdr.h | 2 +-
include/linux/sunrpc/sched.h | 2 +
include/linux/sunrpc/xdr.h | 13 +
include/linux/sunrpc/xprt.h | 5 +-
net/sunrpc/backchannel_rqst.c | 4 +-
net/sunrpc/clnt.c | 12 +-
net/sunrpc/svcsock.c | 6 +-
net/sunrpc/xprt.c | 57 +-
net/sunrpc/xprtrdma/backchannel.c | 71 +--
net/sunrpc/xprtrdma/fmr_ops.c | 10 +-
net/sunrpc/xprtrdma/frwr_ops.c | 12 +-
net/sunrpc/xprtrdma/rpc_rdma.c | 902 +++++++++++++++++------------
net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 9 +-
net/sunrpc/xprtrdma/transport.c | 8 +-
net/sunrpc/xprtrdma/verbs.c | 22 +-
net/sunrpc/xprtrdma/xprt_rdma.h | 63 +-
net/sunrpc/xprtsock.c | 90 +--
36 files changed, 1228 insertions(+), 1133 deletions(-)
--
Trond Myklebust
Linux NFS client maintainer, PrimaryData
trond.myklebust@xxxxxxxxxxxxxxx

Next message: Rob Herring: "Re: [PATCH v3 2/3] dt-bindings: mt8173-xhci: add generic compatible and rename file"
Previous message: David Rientjes: "Re: [v8 1/4] mm, oom: refactor the oom_kill_process() function"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]