Skip to contentSkip to conversation

Please pull NFS client updates for 4.17

GIT PULL Anna Schumaker 3 participants 4 messages Apr 10, 2018 – Apr 12, 2018

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Hi Linus,

The following changes since commit 661e50bc853209e41a5c14a290ca4decc43cbfd1:

Linux 4.16-rc4 (2018-03-04 14:54:11 -0800)

are available in the Git repository at:

git://git.linux-nfs.org/projects/anna/linux-nfs.git tags/nfs-for-4.17-1

for you to fetch changes up to 98de9ce6f6660d02aa72d7b9b17696fa68a2ed9b:

NFS: advance nfs_entry cookie only after decoding completes successfully (2018-04-10 16:06:22 -0400)

----------------------------------------------------------------
Stable bugfixes:
- xprtrdma: Fix corner cases when handling device removal # v4.12+
- xprtrdma: Fix latency regression on NUMA NFS/RDMA clients # v4.15+

Features:
- New sunrpc tracepoint for RPC pings
- Finer grained NFSv4 attribute checking
- Don't unnecessarily return NFS v4 delegations

Other bugfixes and cleanups:
- Several other small NFSoRDMA cleanups
- Improvements to the sunrpc RTT measurements
- A few sunrpc tracepoint cleanups
- Various fixes for NFS v4 lock notifications
- Various sunrpc and NFS v4 XDR encoding cleanups
- Switch to the ida_simple API
- Fix NFSv4.1 exclusive create
- Forget acl cache after setattr operation
- Don't advance the nfs_entry readdir cookie if xdr decoding fails

Cheers,
Anna

----------------------------------------------------------------
Chuck Lever (16):
xprtrdma: Fix latency regression on NUMA NFS/RDMA clients
xprtrdma: Remove arbitrary limit on initiator depth
xprtrdma: Remove xprt-specific connect cookie
xprtrdma: ->send_request returns -EAGAIN when there are no free MRs
xprtrdma: Reduce number of MRs created by rpcrdma_mrs_create
xprtrdma: "Support" call-only RPCs
xprtrdma: Chain Send to FastReg WRs
xprtrdma: Move creation of rl_rdmabuf to rpcrdma_create_req
SUNRPC: Move xprt_update_rtt callsite
SUNRPC: Make RTT measurement more precise (Receive)
SUNRPC: Make RTT measurement more precise (Send)
SUNRPC: Make num_reqs a non-atomic integer
sunrpc: Simplify synopsis of some trace points
sunrpc: Add static trace point to report RPC latency stats
sunrpc: Add static trace point to report result of RPC ping
xprtrdma: Fix corner cases when handling device removal

Frank Sorenson (1):
NFS: advance nfs_entry cookie only after decoding completes successfully

Jeff Layton (3):
nfs4: always reset notified flag to false before repolling for lock
nfs4: don't compare clientid in nfs4_wake_lock_waiter
nfs4: wake any lock waiters on successful RECLAIM_COMPLETE

Matthew Wilcox (1):
nfs: Use ida_simple API

Trond Myklebust (25):
NFSv4: Fix nfs4_return_incompatible_delegation
NFS: Move the delegation return down into nfs4_proc_link()
NFS: Move the delegation return down into nfs4_proc_remove()
NFS: Move delegation recall into the NFSv4 callback for rename_setup()
NFS: Add a delegation return into nfs4_proc_unlink_setup()
NFS: Move the delegation return down into _nfs4_do_setattr()
NFS: Remove the unused return_delegation() callback
NFSv4: Don't return the delegation when not needed by NFSv4.x (x>0)
NFS: Convert NFS_INO_INVALID flags to unsigned long
NFS: Don't force a revalidation of all attributes if change is missing
NFS: Don't redirty the attribute cache in nfs_wcc_update_inode()
NFS: Don't force unnecessary cache invalidation in nfs_update_inode()
NFS: More fine grained attribute tracking
NFSv4: Ignore change attribute invalidations if we hold a delegation
SUNRPC: Add helpers for decoding opaque and string types
SUNRPC: Add a helper for encoding opaque data inline
NFSv4: Allow GFP_NOIO sleeps in decode_attr_owner/decode_attr_group NFSv4; Clean up XDR encoding of type bitmap4
NFSv4: Clean up encode_attrs
NFSv4: Add a helper to encode/decode struct timespec
NFSv4: Don't ask for attributes when ACCESS is protected by a delegation
NFSv4: Clean up CB_GETATTR encoding
NFSv4: Fix the nfs_inode_set_delegation() arguments
NFSv4: Declare the size up to date after it was set. NFSv4.1: Fix exclusive create

chendt (1):
NFSv3/acl: forget acl cache after setattr

 fs/nfs/callback_xdr.c             |  37 ++----
 fs/nfs/delegation.c               |  52 ++++++--
 fs/nfs/delegation.h               |   7 +-
 fs/nfs/dir.c                      |  15 +--
 fs/nfs/inode.c                    | 138 +++++++++++----------
 fs/nfs/nfs3proc.c                 |  24 ++--
 fs/nfs/nfs3xdr.c                  |   7 +-
 fs/nfs/nfs4proc.c                 | 168 ++++++++++++++++++--------
 fs/nfs/nfs4state.c                |  22 ++--
 fs/nfs/nfs4xdr.c                  | 245 ++++++++++++++++++--------------------
 fs/nfs/proc.c                     |  19 ++-
 fs/nfs/unlink.c                   |   7 +-
 fs/nfs/write.c                    |   8 +-
 include/linux/nfs_fs.h            |  35 ++++--
 include/linux/nfs_xdr.h           |   9 +-
 include/linux/sunrpc/clnt.h       |   7 ++
 include/linux/sunrpc/xdr.h        |  94 +++++++++++++++
 include/linux/sunrpc/xprt.h       |   3 +-
 include/trace/events/sunrpc.h     | 106 ++++++++++++++---
 net/sunrpc/clnt.c                 |   8 +-
 net/sunrpc/sched.c                |  10 +-
 net/sunrpc/stats.c                |  16 ++-
 net/sunrpc/sunrpc.h               |   6 -
 net/sunrpc/xdr.c                  |  82 +++++++++++++
 net/sunrpc/xprt.c                 |  34 +++---
 net/sunrpc/xprtrdma/backchannel.c |   7 --
 net/sunrpc/xprtrdma/fmr_ops.c     |  13 +-
 net/sunrpc/xprtrdma/frwr_ops.c    |  53 ++++++---
 net/sunrpc/xprtrdma/rpc_rdma.c    |  32 +++--
 net/sunrpc/xprtrdma/transport.c   |  43 ++-----
 net/sunrpc/xprtrdma/verbs.c       |  44 ++++---
 net/sunrpc/xprtrdma/xprt_rdma.h   |   4 +-
 net/sunrpc/xprtsock.c             |   4 +
 33 files changed, 866 insertions(+), 493 deletions(-)
#1 lore raw

Hi Linus,

What's the status of this? I don't see the NFS changes in your tree yet, and I'm worried the pull request email got lost somewhere along the way.

Cheers,
Anna

Quoted 133 lines · Anna Schumaker

Hi Linus,

The following changes since commit 661e50bc853209e41a5c14a290ca4decc43cbfd1:

Linux 4.16-rc4 (2018-03-04 14:54:11 -0800)

are available in the Git repository at:

git://git.linux-nfs.org/projects/anna/linux-nfs.git tags/nfs-for-4.17-1

for you to fetch changes up to 98de9ce6f6660d02aa72d7b9b17696fa68a2ed9b:

NFS: advance nfs_entry cookie only after decoding completes successfully (2018-04-10 16:06:22 -0400)

----------------------------------------------------------------
Stable bugfixes:
- xprtrdma: Fix corner cases when handling device removal # v4.12+
- xprtrdma: Fix latency regression on NUMA NFS/RDMA clients # v4.15+

Features:
- New sunrpc tracepoint for RPC pings
- Finer grained NFSv4 attribute checking
- Don't unnecessarily return NFS v4 delegations

Other bugfixes and cleanups:
- Several other small NFSoRDMA cleanups
- Improvements to the sunrpc RTT measurements
- A few sunrpc tracepoint cleanups
- Various fixes for NFS v4 lock notifications
- Various sunrpc and NFS v4 XDR encoding cleanups
- Switch to the ida_simple API
- Fix NFSv4.1 exclusive create
- Forget acl cache after setattr operation
- Don't advance the nfs_entry readdir cookie if xdr decoding fails

Cheers,
Anna

----------------------------------------------------------------
Chuck Lever (16):
xprtrdma: Fix latency regression on NUMA NFS/RDMA clients
xprtrdma: Remove arbitrary limit on initiator depth
xprtrdma: Remove xprt-specific connect cookie
xprtrdma: ->send_request returns -EAGAIN when there are no free MRs
xprtrdma: Reduce number of MRs created by rpcrdma_mrs_create
xprtrdma: "Support" call-only RPCs
xprtrdma: Chain Send to FastReg WRs
xprtrdma: Move creation of rl_rdmabuf to rpcrdma_create_req
SUNRPC: Move xprt_update_rtt callsite
SUNRPC: Make RTT measurement more precise (Receive)
SUNRPC: Make RTT measurement more precise (Send)
SUNRPC: Make num_reqs a non-atomic integer
sunrpc: Simplify synopsis of some trace points
sunrpc: Add static trace point to report RPC latency stats
sunrpc: Add static trace point to report result of RPC ping
xprtrdma: Fix corner cases when handling device removal

Frank Sorenson (1):
NFS: advance nfs_entry cookie only after decoding completes successfully

Jeff Layton (3):
nfs4: always reset notified flag to false before repolling for lock
nfs4: don't compare clientid in nfs4_wake_lock_waiter
nfs4: wake any lock waiters on successful RECLAIM_COMPLETE

Matthew Wilcox (1):
nfs: Use ida_simple API

Trond Myklebust (25):
NFSv4: Fix nfs4_return_incompatible_delegation
NFS: Move the delegation return down into nfs4_proc_link()
NFS: Move the delegation return down into nfs4_proc_remove()
NFS: Move delegation recall into the NFSv4 callback for rename_setup()
NFS: Add a delegation return into nfs4_proc_unlink_setup()
NFS: Move the delegation return down into _nfs4_do_setattr()
NFS: Remove the unused return_delegation() callback
NFSv4: Don't return the delegation when not needed by NFSv4.x (x>0)
NFS: Convert NFS_INO_INVALID flags to unsigned long
NFS: Don't force a revalidation of all attributes if change is missing
NFS: Don't redirty the attribute cache in nfs_wcc_update_inode()
NFS: Don't force unnecessary cache invalidation in nfs_update_inode()
NFS: More fine grained attribute tracking
NFSv4: Ignore change attribute invalidations if we hold a delegation
SUNRPC: Add helpers for decoding opaque and string types
SUNRPC: Add a helper for encoding opaque data inline
NFSv4: Allow GFP_NOIO sleeps in decode_attr_owner/decode_attr_group NFSv4; Clean up XDR encoding of type bitmap4
NFSv4: Clean up encode_attrs
NFSv4: Add a helper to encode/decode struct timespec
NFSv4: Don't ask for attributes when ACCESS is protected by a delegation
NFSv4: Clean up CB_GETATTR encoding
NFSv4: Fix the nfs_inode_set_delegation() arguments
NFSv4: Declare the size up to date after it was set. NFSv4.1: Fix exclusive create

chendt (1):
NFSv3/acl: forget acl cache after setattr

 fs/nfs/callback_xdr.c             |  37 ++----
 fs/nfs/delegation.c               |  52 ++++++--
 fs/nfs/delegation.h               |   7 +-
 fs/nfs/dir.c                      |  15 +--
 fs/nfs/inode.c                    | 138 +++++++++++----------
 fs/nfs/nfs3proc.c                 |  24 ++--
 fs/nfs/nfs3xdr.c                  |   7 +-
 fs/nfs/nfs4proc.c                 | 168 ++++++++++++++++++--------
 fs/nfs/nfs4state.c                |  22 ++--
 fs/nfs/nfs4xdr.c                  | 245 ++++++++++++++++++--------------------
 fs/nfs/proc.c                     |  19 ++-
 fs/nfs/unlink.c                   |   7 +-
 fs/nfs/write.c                    |   8 +-
 include/linux/nfs_fs.h            |  35 ++++--
 include/linux/nfs_xdr.h           |   9 +-
 include/linux/sunrpc/clnt.h       |   7 ++
 include/linux/sunrpc/xdr.h        |  94 +++++++++++++++
 include/linux/sunrpc/xprt.h       |   3 +-
 include/trace/events/sunrpc.h     | 106 ++++++++++++++---
 net/sunrpc/clnt.c                 |   8 +-
 net/sunrpc/sched.c                |  10 +-
 net/sunrpc/stats.c                |  16 ++-
 net/sunrpc/sunrpc.h               |   6 -
 net/sunrpc/xdr.c                  |  82 +++++++++++++
 net/sunrpc/xprt.c                 |  34 +++---
 net/sunrpc/xprtrdma/backchannel.c |   7 --
 net/sunrpc/xprtrdma/fmr_ops.c     |  13 +-
 net/sunrpc/xprtrdma/frwr_ops.c    |  53 ++++++---
 net/sunrpc/xprtrdma/rpc_rdma.c    |  32 +++--
 net/sunrpc/xprtrdma/transport.c   |  43 ++-----
 net/sunrpc/xprtrdma/verbs.c       |  44 ++++---
 net/sunrpc/xprtrdma/xprt_rdma.h   |   4 +-
 net/sunrpc/xprtsock.c             |   4 +
 33 files changed, 866 insertions(+), 493 deletions(-)
#2 lore raw
Quoted 3 lines · Anna Schumaker

Hi Linus,

What's the status of this? I don't see the NFS changes in your tree yet, and I'm worried the pull request email got lost somewhere along the way.

No, it's still in my queue. I do my pulls in batches of mostly similar stuff, and the nfs pull just came in after I had done my last batch of FS pulls, so now it's waiting for the next one.

Which will be later today. In fact, I think I'm done with the "fixes" batch, and filesystems may be next.

Linus

#3 lore raw
Quoted 4 lines · Linus Torvalds
Quoted 2 lines · Anna Schumaker

Hi Linus,

Quoted 8 lines
Quoted 1 line

What's the status of this? I don't see the NFS changes in your tree yet, and I'm worried the pull request email got lost somewhere along the way.

No, it's still in my queue. I do my pulls in batches of mostly similar stuff, and the nfs pull just came in after I had done my last batch of FS pulls, so now it's waiting for the next one.

Which will be later today. In fact, I think I'm done with the "fixes" batch, and filesystems may be next.

That makes sense. Thanks for the update!

Anna

Quoted 3 lines

Linus