NFSoRDMA client updates for 5.1

New features:
- Convert rpc auth layer to use xdr_streams
- Config option to disable insecure enctypes
- Reduce size of RPC receive buffers

Bugfixes and cleanups:
- Fix sparse warnings
- Check inline size before providing a write chunk
- Reduce the receive doorbell rate
- Various tracepoint improvements

[Trond: Fix up merge conflicts]
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

If a bulk layout recall or a metadata server reboot coincides with a
umount, then holding a reference to an inode is unsafe unless we
also hold a reference to the super block.

Fixes: fd9a8d71 ("NFSv4.1: Fix bulk recall and destroy of layouts")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Fix a soft lockup when NFS client delegation recovery is attempted
but the inode is in the process of being freed. When the
igrab(inode) call fails, and we have to restart the recovery process,
we need to ensure that we won't attempt to recover the same delegation
again.

Fixes: 45870d69 ("NFSv4.1: Test delegation stateids when server...")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

A 'false retry' in NFSv4.1 occurs when the client attempts to transmit a
new RPC call using a slot+sequence number combination that references an
already cached one. Currently, the Linux NFS client will do this if a
user process interrupts an RPC call that is in progress.
The problem with doing so is that we defeat the main mechanism used by
the server to differentiate between a new call and a replayed one. Even
if the server is able to perfectly cache the arguments of the old call,
it cannot know if the client intended to replay or send a new call.

The obvious fix is to bump the sequence number pre-emptively if an
RPC call is interrupted, but in order to deal with the corner cases
where the interrupted call is not actually received and processed by
the server, we need to interpret the error NFS4ERR_SEQ_MISORDERED
as a sign that we need to either wait or locate a correct sequence
number that lies between the value we sent, and the last value that
was acked by a SEQUENCE call on that slot.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Tested-by: Jason Tibbitts <tibbs@math.uh.edu>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Now that we send the pages using a struct msghdr, instead of
using sendpage(), we no longer need to 'prime the socket' with
an address for unconnected UDP messages.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Simplify the page send code using iov_iter and bvecs.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Prepare to the socket transmission code to use iov_iter.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

If the client stream receive code receives an ESHUTDOWN error either
because the server closed the connection, or because it sent a
callback which cannot be processed, then we should shut down
the connection.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

If the message read completes, but the socket returned an error
condition, we should ensure to propagate that error.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

A zero length fragment is really a bug, but let's ensure we don't
go nuts when one turns up.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

To ensure that the receive worker has exclusive access to the stream record
info, we must not reset the contents other than when holding the
transport->recv_mutex.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

After setxattr, the nfsv3 cached the acl which set by user.

But at the backend, the shared file system (eg. ext4) will check
the acl, if it can merged with mode, it won't add acl to the file.
So, the nfsv3 cached acl is redundant.

Don't 'set_cached_acl' when setxattr.
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

As the block and SCSI layouts can only read/write fixed-length
blocks, we must perform read-modify-write when data to be written is
not aligned to a block boundary or smaller than the block size.
(612aa983 pnfs: add flag to force read-modify-write in ->write_begin)

The current code tries to see if we have to do read-modify-write
on block-oriented pNFS layouts by just checking !PageUptodate(page),
but the same condition also applies for overwriting of any uncached
potions of existing files, making such operations excessively slow
even it is block-aligned.

The change does not affect the optimization for modify-write-read
cases (38c73044 NFS: read-modify-write page updating),
because partial update of !PageUptodate() pages can only happen
in layouts that can do arbitrary length read/write and never
in block-based ones.

Testing results:

We ran fio on one of the pNFS clients running 4.20 kernel
(vanilla and patched) in this configuration to read/write/overwrite
files on the storage array, exported as pnfs share by the server.

 pNFS clients ---1G Ethernet--- pNFS server
 (HP DL360 G8)                  (HP DL360 G8)
       |                              |
       |                              |
       +------8G Fiber Channel--------+
                     |
               Storage Array
                 (HP P6350)

Throughput of overwrite (both buffered and O_SYNC) is noticeably
improved.

Ops.     |block size|   Throughput   |
         |  (KiB)   |    (MiB/s)     |
         |          |  4.20 | patched|
---------+----------+----------------+
buffered |         4|  21.3 |  232   |
overwrite|        32|  22.2 |  256   |
         |       512|  22.4 |  260   |
---------+----------+----------------+
O_SYNC   |         4|   3.84|    4.77|
overwrite|        32|  12.2 |   32.0 |
         |       512|  18.5 |  152   |
---------+----------+----------------+

Read and write (buffered and O_SYNC) by the same client remain unchanged
by the patch either negatively or positively, as they should do.

Ops.     |block size|   Throughput   |
         |  (KiB)   |    (MiB/s)     |
         |          |  4.20 | patched|
---------+----------+----------------+
read     |         4| 548   |  550   |
         |        32| 547   |  551   |
         |       512| 548   |  551   |
---------+----------+----------------+
buffered |         4| 237   |  244   |
write    |        32| 261   |  268   |
         |       512| 265   |  272   |
---------+----------+----------------+
O_SYNC   |         4|   0.46|    0.46|
write    |        32|   3.60|    3.57|
         |       512| 105   |  106   |
---------+----------+----------------+
Signed-off-by: Kazuo Ito <ito_kazuo_g3@lab.ntt.co.jp>
Tested-by: Hiroyuki Watanabe <watanabe.hiroyuki@lab.ntt.co.jp>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

nfs_want_read_modify_write() didn't check for !PagePrivate when pNFS
block or SCSI layout was in use, therefore we could lose data forever
if the page being written was filled by a read before completion.
Signed-off-by: Kazuo Ito <ito_kazuo_g3@lab.ntt.co.jp>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

This fixes the typo in comments of nfs_readdir_alloc_pages().
Because nfs_readdir_large_page and nfs_readdir_free_pagearray had been
renamed.
Signed-off-by: Liguang Zhang <zhangliguang@linux.alibaba.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

This removes redundant semicolon for ending code.

Fixes: c7944ebb ("NFSv4: Fix lookup revalidate of regular files")
Signed-off-by: Liguang Zhang <zhangliguang@linux.alibaba.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

When listing very large directories via NFS, clients may take a long
time to complete. There are about three factors involved:

First of all, ls and practically every other method of listing a
directory including python os.listdir and find rely on libc readdir().
However readdir() only reads 32K of directory entries at a time, which
means that if you have a lot of files in the same directory, it is going
to take an insanely long time to read all the directory entries.

Secondly, libc readdir() reads 32K of directory entries at a time, in
kernel space 32K buffer split into 8 pages. One NFS readdirplus rpc will
be called for one page, which introduces many readdirplus rpc calls.

Lastly, one NFS readdirplus rpc asks for 32K data (filled by nfs_dentry)
to fill one page (filled by dentry), we found that nearly one third of
data was wasted.

To solve above problems, pagecache mechanism was introduced. One NFS
readdirplus rpc will ask for a large data (more than 32k), the data can
fill more than one page, the cached pages can be used for next readdir
call. This can reduce many readdirplus rpc calls and improve readdirplus
performance.

TESTING:
When listing very large directories(include 300 thousand files) via NFS

time ls -l /nfs_mount | wc -l

without the patch:
300001
real    1m53.524s
user    0m2.314s
sys     0m2.599s

with the patch:
300001
real    0m23.487s
user    0m2.305s
sys     0m2.558s

Improved performance: 79.6%
readdirplus rpc calls decrease: 85%
Signed-off-by: Liguang Zhang <zhangliguang@linux.alibaba.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

In the rare and unsupported case of a hostname list nfs_parse_devname
will modify dev_name.  There is no need to modify dev_name as the all
that is being computed is the length of the hostname, so the computed
length can just be shorted.

Fixes: dc045898 ("NFS: Use common device name parsing logic for NFSv4 and NFSv2/v3")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

As reported by Dan Carpenter, this test for acred->cred being set is
inconsistent with the dereference of the pointer a few lines earlier.

An 'auth_cred' *always* has ->cred set - every place that creates one
initializes this field, often as the first thing done.

So remove this test.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Drop LIST_HEAD where the variable it declares has never
been used.

The semantic patch that fixes this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
identifier x;
@@
- LIST_HEAD(x);
  ... when != x
// </smpl>

Fixes: 0e20162e ("NFSv4.1 Use MDS auth flavor for data server connection")
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

When we resend a request, ensure that the 'rq_bytes_sent' is reset
to zero.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Because we clear XPRT_SOCK_DATA_READY before reading, we can end up
with a situation where new data arrives, causing xs_data_ready() to
queue up a second receive worker job for the same socket, which then
immediately gets stuck waiting on the transport receive mutex.
The fix is to only clear XPRT_SOCK_DATA_READY once we're done reading,
and then to use poll() to check if we might need to queue up a new
job in order to deal with any new data.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Set memalloc_nofs_save() on all the rpciod/xprtiod jobs so that we
ensure memory allocations for asynchronous rpc calls don't ever end
up recursing back to the NFS layer for memory reclaim.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Fix up some compiler warnings about function parameters, etc not being
correctly described or formatted.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

All the allocations that we can hit in the NFS layer and sunrpc layers
themselves are already marked as GFP_NOFS, but we need to ensure that
any calls to generic kernel functionality do the right thing as well.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

Allow the caller to pass error information when cleaning up a failed
I/O request so that we can conditionally take action to cancel the
request altogether if the error turned out to be fatal.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

In several places we're just moving the struct nfs_page from one list to
another by first removing from the existing list, then adding to the new
one.
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>

If the I/O completion failed with a fatal error, then we should just
exit nfs_pageio_complete_mirror() rather than try to recoalesce.

Fixes: a7d42ddb ("nfs: add mirroring support to pgio layer")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: stable@vger.kernel.org # v4.0+

Whether we need to exit early, or just reprocess the list, we
must not lost track of the request which failed to get recoalesced.

Fixes: 03d5eb65 ("NFS: Fix a memory leak in nfs_do_recoalesce")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: stable@vger.kernel.org # v4.0+

When we fail to add the request to the I/O queue, we currently leave it
to the caller to free the failed request. However since some of the
requests that fail are actually created by nfs_pageio_add_request()
itself, and are not passed back the caller, this leads to a leakage
issue, which can again cause page locks to leak.

This commit addresses the leakage by freeing the created requests on
error, using desc->pg_completion_ops->error_cleanup()
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Fixes: a7d42ddb ("nfs: add mirroring support to pgio layer")
Cc: stable@vger.kernel.org # v4.0: c18b96a1: nfs: clean up rest of reqs
Cc: stable@vger.kernel.org # v4.0: d600ad1f: NFS41: pop some layoutget
Cc: stable@vger.kernel.org # v4.0+

Pull sound fixes from Takashi Iwai:
 "Here are a few last-minute fixes for 5.0.

  The most significant one is the OF-node refcount fix for ASoC
  simple-card, which could be triggered on many boards. Another fix for
  ASoC core is for the error handling in topology, while others are
  device-specific fixes for Samsung and HD-audio"

* tag 'sound-5.0' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
  ASoC: simple-card: fixup refcount_t underflow
  ASoC: topology: free created components in tplg load error
  ALSA: hda/realtek: Disable PC beep in passthrough on alc285
  ALSA: hda/realtek - Headset microphone and internal speaker support for System76 oryp5
  ASoC: samsung: i2s: Fix prescaler setting for the secondary DAI

Pull pin control fixes from Linus Walleij:
 "Some final pin control fixes (I hope) to round off the v5.0 pin
  control development cycle.

  Only driver fixes, one for stable:

   - Meson8B fixup for the sdc pins

   - Fix SDC tile position for Qualcomm QCS404"

* tag 'pinctrl-v5.0-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
  pinctrl: meson: meson8b: fix the sdxc_a data 1..3 pins
  pinctrl: qcom: qcs404: Correct SDC tile

Pull GPIO fixes from Linus Walleij:
 "Two GPIO fixes for the v5.0 series:

   - Per-instance irqchip on the MT7621

   - Avoid direction setting using pin control on MMP2"

* tag 'gpio-v5.0-4' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
  gpio: pxa: avoid attempting to set pin direction via pinctrl on MMP2
  gpio: MT7621: use a per instance irq_chip structure

Pull MTD fixes from Boris Brezillon:

 - Don't add a digit to MTD-backed nvmem device names

 - Make sure powernv flash names are unique

* tag 'mtd/fixes-for-5.0-rc8' of git://git.infradead.org/linux-mtd:
  mtd: powernv_flash: Fix device registration error
  mtd: Use mtd->name when registering nvmem device

Merge branch 'fixes-v5.1-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security

Pull keys fixes from James Morris:

 - Handle quotas better, allowing full quota to be reached.

 - Fix the creation of shortcuts in the assoc_array internal
   representation when the index key needs to be an exact multiple of
   the machine word size.

 - Fix a dependency loop between the request_key contruction record and
   the request_key authentication key. The construction record isn't
   really necessary and can be dispensed with.

 - Set the timestamp on a new key rather than leaving it as 0. This
   would ordinarily be fine - provided the system clock is never set to
   a time before 1970

* 'fixes-v5.1-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security:
  keys: Timestamp new keys
  keys: Fix dependency loop between construction record and auth key
  assoc_array: Fix shortcut creation
  KEYS: allow reaching the keys quotas exactly

Pull networking fixes from David Miller:

 1) Fix suspend and resume in mt76x0u USB driver, from Stanislaw
    Gruszka.

 2) Missing memory barriers in xsk, from Magnus Karlsson.

 3) rhashtable fixes in mac80211 from Herbert Xu.

 4) 32-bit MIPS eBPF JIT fixes from Paul Burton.

 5) Fix for_each_netdev_feature() on big endian, from Hauke Mehrtens.

 6) GSO validation fixes from Willem de Bruijn.

 7) Endianness fix for dwmac4 timestamp handling, from Alexandre Torgue.

 8) More strict checks in tcp_v4_err(), from Eric Dumazet.

 9) af_alg_release should NULL out the sk after the sock_put(), from Mao
    Wenan.

10) Missing unlock in mac80211 mesh error path, from Wei Yongjun.

11) Missing device put in hns driver, from Salil Mehta.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (44 commits)
  sky2: Increase D3 delay again
  vhost: correctly check the return value of translate_desc() in log_used()
  net: netcp: Fix ethss driver probe issue
  net: hns: Fixes the missing put_device in positive leg for roce reset
  net: stmmac: Fix a race in EEE enable callback
  qed: Fix iWARP syn packet mac address validation.
  qed: Fix iWARP buffer size provided for syn packet processing.
  r8152: Add support for MAC address pass through on RTL8153-BD
  mac80211: mesh: fix missing unlock on error in table_path_del()
  net/mlx4_en: fix spelling mistake: "quiting" -> "quitting"
  net: crypto set sk to NULL when af_alg_release.
  net: Do not allocate page fragments that are not skb aligned
  mm: Use fixed constant in page_frag_alloc instead of size + 1
  tcp: tcp_v4_err() should be more careful
  tcp: clear icsk_backoff in tcp_write_queue_purge()
  net: mv643xx_eth: disable clk on error path in mv643xx_eth_shared_probe()
  qmi_wwan: apply SET_DTR quirk to Sierra WP7607
  net: stmmac: handle endianness in dwmac4_get_timestamp
  doc: Mention MSG_ZEROCOPY implementation for UDP
  mlxsw: __mlxsw_sp_port_headroom_set(): Fix a use of local variable
  ...