As flexfiles has FF_FLAGS_NO_READ_IO, there is a need to generically
support enforcing that a IOMODE_RW segment will not allow READ I/O.
Signed-off-by: NTom Haynes <loghyr@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

It can return NULL if layoutgets are blocked currently. Fix it to return
-EAGAIN in that case, so we can properly handle it in pnfs_update_layout.

Also, clean up and simplify the error handling -- eliminate "status" and
just use "lseg".
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

There are several problems in the way a stateid is selected for a
LAYOUTGET operation:

We pick a stateid to use in the RPC prepare op, but that makes
it difficult to serialize LAYOUTGETs that use the open stateid. That
serialization is done in pnfs_update_layout, which occurs well before
the rpc_prepare operation.

Between those two events, the i_lock is dropped and reacquired.
pnfs_update_layout can find that the list has lsegs in it and not do any
serialization, but then later pnfs_choose_layoutget_stateid ends up
choosing the open stateid.

This patch changes the client to select the stateid to use in the
LAYOUTGET earlier, when we're searching for a usable layout segment.
This way we can do it all while holding the i_lock the first time, and
ensure that we serialize any LAYOUTGET call that uses a non-layout
stateid.

This also means a rework of how LAYOUTGET replies are handled, as we
must now get the latest stateid if we want to retransmit in response
to a retryable error.

Most of those errors boil down to the fact that the layout state has
changed in some fashion. Thus, what we really want to do is to re-search
for a layout when it fails with a retryable error, so that we can avoid
reissuing the RPC at all if possible.

While the LAYOUTGET RPC is async, the initiating thread always waits for
it to complete, so it's effectively synchronous anyway. Currently, when
we need to retry a LAYOUTGET because of an error, we drive that retry
via the rpc state machine.

This means that once the call has been submitted, it runs until it
completes. So, we must move the error handling for this RPC out of the
rpc_call_done operation and into the caller.

In order to handle errors like NFS4ERR_DELAY properly, we must also
pass a pointer to the sliding timeout, which is now moved to the stack
in pnfs_update_layout.

The complicating errors are -NFS4ERR_RECALLCONFLICT and
-NFS4ERR_LAYOUTTRYLATER, as those involve a timeout after which we give
up and return NULL back to the caller. So, there is some special
handling for those errors to ensure that the layers driving the retries
can handle that appropriately.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

If we get back something like NFS4ERR_OLD_STATEID, that will be
translated into -EAGAIN, and the do/while loop in send_layoutget
will drive the call again.

This is not quite what we want, I think. An error like that is a
sign that something has changed. That something could have been a
concurrent LAYOUTGET that would give us a usable lseg.

Lift the retry logic into pnfs_update_layout instead. That allows
us to redo the layout search, and may spare us from having to issue
an RPC.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Currently, the code will clear the fail bit if we get back a fatal
error. I don't think that's correct -- we want to clear that bit
if we do not get a fatal error.

Fixes: 0bcbf039 (nfs: handle request add failure properly)
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

LAYOUTRETURN is "special" in that servers and clients are expected to
work with old stateids. When the client sends a LAYOUTRETURN with an old
stateid in it then the server is expected to only tear down layout
segments that were present when that seqid was current. Ensure that the
client handles its accounting accordingly.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

When we want to selectively do a LAYOUTRETURN, we need to specify a
stateid that represents most recent layout acquisition that is to be
returned.

When we mark a layout stateid to be returned, we update the return
sequence number in the layout header with that value, if it's newer
than the existing one. Then, when we go to do a LAYOUTRETURN on
layout header put, we overwrite the seqid in the stateid with the
saved one, and then zero it out.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

In later patches, we're going to teach the client to be more selective
about how it returns layouts. This means keeping a record of what the
stateid's seqid was at the time that the server handed out a layout
segment.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

Like other resend paths, mark the (old) hdr as NFS_IOHDR_REDO. This
ensures the hdr completion function will not count the (old) hdr
as good bytes.

Also, vector the error back through the hdr->task.tk_status like other
retry calls.

This fixes a bug with the FlexFiles layout where libaio was reporting more
bytes read than requested.
Signed-off-by: NWeston Andros Adamson <dros@primarydata.com>
Signed-off-by: NAnna Schumaker <Anna.Schumaker@Netapp.com>

PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.

This promise never materialized.  And unlikely will.

We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE.  And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.

Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.

Let's stop pretending that pages in page cache are special.  They are
not.

The changes are pretty straight-forward:

 - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};

 - page_cache_get() -> get_page();

 - page_cache_release() -> put_page();

This patch contains automated changes generated with coccinelle using
script below.  For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.

The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.

There are few places in the code where coccinelle didn't reach.  I'll
fix them manually in a separate patch.  Comments and documentation also
will be addressed with the separate patch.

virtual patch

@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT

@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE

@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK

@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)

@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)

@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Replace another case where the layout 'plh_block_lgets' can trigger
infinite loops in send_layoutget().
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If the server reboots while there is a layoutget outstanding, then
the call to pnfs_choose_layoutget_stateid() will fail with an EAGAIN
error, which causes an infinite loop in send_layoutget(). The reason
why we never break out of the loop is that the layout 'plh_block_lgets'
field is never cleared.

Fix is to replace plh_block_lgets with NFS_LAYOUT_INVALID_STID, which
can be reset after a new layoutget.

Fixes: ab7d763e ("pNFS: Ensure nfs4_layoutget_prepare returns...")
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

When setting the layout return mode, we must always also set the
NFS_LAYOUT_RETURN_REQUESTED flag to ensure that we send a layoutreturn.
Otherwise pnfs_error_mark_layout_for_return() could set the mode, but
fail to send the layoutreturn because another is already in flight.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

We don't need to schedule a layoutreturn if the layout segment can
be freed immediately.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

NFS_LAYOUT_RETURN_BEFORE_CLOSE is being used to signal that a
layoutreturn is needed, either due to a layout recall or to a
layout error. Rename it to NFS_LAYOUT_RETURN_REQUESTED in order
to clarify its purpose.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

The layoutreturn code currently relies on pnfs_put_lseg() to initiate the
RPC call when conditions are right. A problem arises when we want to
free the layout segment from inside an inode->i_lock section (e.g. in
pnfs_clear_request_commit()), since we cannot sleep.

The workaround is to move the actual call to pnfs_send_layoutreturn()
to pnfs_put_layout_hdr(), which doesn't have this restriction.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Make it more obvious what we're returning...
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Fix a bug whereby if all the layout segments could be immediately freed,
the call to pnfs_error_mark_layout_for_return() would never result in
a layoutreturn.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If pnfs_mark_matching_lsegs_return() needs to mark a layout segment for
return, then it must also set the return iomode.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

A stateid is a structure, pass it as a pointer.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If the layout segment is invalid, then we should not be adding more
write requests to the commit list. Instead, those writes should be
replayed after requesting a new layout.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If the client needs to delay the layout callback, then speed up the recall
process by marking the remaining layout segments to be actively returned
by the client.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

This ensures that we don't reuse the stateid if a layout return or
implied layout return means that we've returned all layout segments
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

In pNFS/flexfiles, we want to return the layout without necessarily marking
it as having completely failed. We therefore move the call to
pnfs_layout_io_set_failed() out of pnfs_error_mark_layout_for_return(),
and then ensura that pNFS/files layout calls it separately.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Fix a bug in which flexfiles clients are falling back to I/O through the
MDS even when the FF_FLAGS_NO_IO_THRU_MDS flag is set.

The flexfiles client will always report errors through the LAYOUTRETURN
and/or LAYOUTERROR mechanisms, so it should normally be safe for it
to retry the LAYOUTGET until it fails or succeeds.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

When we fail to queue a read page to IO descriptor,
we need to clean it up otherwise it is hanging around
preventing nfs module from being removed.

When we fail to queue a write page to IO descriptor,
we need to clean it up and also save the failure status
to open context. Then at file close, we can try to write
pages back again and drop the page if it fails to writeback
in .launder_page, which will be done in the next patch.
Signed-off-by: NPeng Tao <tao.peng@primarydata.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

In case we fail during setting things up for read/write IO, set
pg_error in IO descriptor and do the cleanup in nfs_pageio_add_request,
where we clean up all pages that are still hanging around on the IO
descriptor.
Signed-off-by: NPeng Tao <tao.peng@primarydata.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

For ERESTARTSYS/EIO/EROFS/ENOSPC/E2BIG in layoutget, we
should just bail out instead of hiding the error and
retrying inband IO.

Change all the call sites to pop the error all the way up.
Signed-off-by: NPeng Tao <tao.peng@primarydata.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Instead of displaying a layout segment pointer in these tracepoints,
let's use the layout stateid, now that Olga gave us a set of tools for
displaying them.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

pnfs_update_layout is really the "nexus" of layout handling. If it
returns NULL then we end up going through the MDS. This patch adds
some tracepoints to that function that allow us to determine the
cause when we end up going through the MDS unexpectedly.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Jan Stancek reported that I wrecked things for him by fixing things for
Vladimir :/

His report was due to an UNINTERRUPTIBLE wait getting -EINTR, which
should not be possible, however my previous patch made this possible by
unconditionally checking signal_pending().

We cannot use current->state as was done previously, because the
instruction after the store to that variable it can be changed.  We must
instead pass the initial state along and use that.

Fixes: 68985633 ("sched/wait: Fix signal handling in bit wait helpers")
Reported-by: NJan Stancek <jstancek@redhat.com>
Reported-by: NChris Mason <clm@fb.com>
Tested-by: NJan Stancek <jstancek@redhat.com>
Tested-by: NVladimir Murzin <vladimir.murzin@arm.com>
Tested-by: NChris Mason <clm@fb.com>
Reviewed-by: NPaul Turner <pjt@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: tglx@linutronix.de
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: hpa@zytor.com
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

pnfs_layout_process will check the returned layout stateid against what
the kernel has in-core. If it turns out that the stateid we received is
older, then we should resend the LAYOUTGET instead of falling back to
MDS I/O.
Signed-off-by: NJeff Layton <jeff.layton@primarydata.com>
Cc: stable@vger.kernel.org # 3.18+
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If non rpc-based layout driver return bad length of data, nfs retries
by calling rpc_restart_call_prepare() that cause an NULL reference panic.

This patch lets nfs retry through MDS for non rpc-based layout driver
return bad length of data.

[13034.883329] BUG: unable to handle kernel NULL pointer dereference at           (null)
[13034.884902] IP: [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc]
[13034.886558] PGD 0
[13034.888126] Oops: 0000 [#1] KASAN
[13034.889710] Modules linked in: blocklayoutdriver(OE) nfsv4(OE) nfs(OE) fscache(E) nfsd(OE) xfs libcrc32c coretemp btrfs crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev vmw_balloon auth_rpcgss shpchp nfs_acl lockd vmw_vmci parport_pc xor raid6_pq grace parport sunrpc i2c_piix4 vmwgfx drm_kms_helper ttm drm mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi [last unloaded: fscache]
[13034.898260] CPU: 0 PID: 10112 Comm: kworker/0:1 Tainted: G           OE   4.3.0-rc5+ #279
[13034.899932] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015
[13034.903342] Workqueue: events bl_read_cleanup [blocklayoutdriver]
[13034.905059] task: ffff88006a9148c0 ti: ffff880035e90000 task.ti: ffff880035e90000
[13034.906827] RIP: 0010:[<ffffffffa00db372>]  [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc]
[13034.910522] RSP: 0018:ffff880035e97b58  EFLAGS: 00010282
[13034.912378] RAX: fffffbfff04a5a94 RBX: ffff880068fe4858 RCX: 0000000000000003
[13034.914339] RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 0000000000000282
[13034.916236] RBP: ffff880035e97b68 R08: 0000000000000001 R09: 0000000000000001
[13034.918229] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
[13034.920007] R13: ffff880068fe4858 R14: ffff880068fe4a60 R15: 0000000000001000
[13034.921845] FS:  0000000000000000(0000) GS:ffffffff82247000(0000) knlGS:0000000000000000
[13034.923645] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[13034.925525] CR2: 0000000000000000 CR3: 00000000063dd000 CR4: 00000000001406f0
[13034.932808] Stack:
[13034.934813]  ffff880068fe4780 0000000000001000 ffff880035e97ba8 ffffffffa08800d2
[13034.936675]  ffffffffa088029d ffff880068fe4780 ffff880068fe4858 ffffffffa089c0a0
[13034.938593]  ffff880068fe47e0 ffff88005d59faf0 ffff880035e97be0 ffffffffa087e08f
[13034.940454] Call Trace:
[13034.942388]  [<ffffffffa08800d2>] nfs_readpage_result+0x112/0x200 [nfs]
[13034.944317]  [<ffffffffa088029d>] ? nfs_readpage_done+0xdd/0x160 [nfs]
[13034.946267]  [<ffffffffa087e08f>] nfs_pgio_result+0x9f/0x120 [nfs]
[13034.948166]  [<ffffffffa09266cc>] pnfs_ld_read_done+0x7c/0x1e0 [nfsv4]
[13034.950247]  [<ffffffffa03b07ee>] bl_read_cleanup+0x2e/0x60 [blocklayoutdriver]
[13034.952156]  [<ffffffff810ebf62>] process_one_work+0x412/0x870
[13034.954102]  [<ffffffff810ebe84>] ? process_one_work+0x334/0x870
[13034.955949]  [<ffffffff810ebb50>] ? queue_delayed_work_on+0x40/0x40
[13034.957985]  [<ffffffff810ec441>] worker_thread+0x81/0x6a0
[13034.959817]  [<ffffffff810ec3c0>] ? process_one_work+0x870/0x870
[13034.961785]  [<ffffffff810f43bd>] kthread+0x17d/0x1a0
[13034.963544]  [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330
[13034.965479]  [<ffffffff81100428>] ? finish_task_switch+0x88/0x220
[13034.967223]  [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330
[13034.968929]  [<ffffffff81b6ae5f>] ret_from_fork+0x3f/0x70
[13034.970534]  [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330
[13034.972176] Code: c7 43 50 40 84 0d a0 e8 3d fe 1c e1 48 8d 7b 58 c7 83 e4 00 00 00 00 00 00 00 e8 ca fe 1c e1 4c 8b 63 58 4c 89 e7 e8 be fe 1c e1 <49> 83 3c 24 00 74 12 48 c7 43 50 f0 a2 0e a0 b8 01 00 00 00 5b
[13034.977148] RIP  [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc]
[13034.978780]  RSP <ffff880035e97b58>
[13034.980399] CR2: 0000000000000000
Signed-off-by: NKinglong Mee <kinglongmee@gmail.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If we send a layoutreturn asynchronously before close, the close
might reach server first and layoutreturn would fail with BADSTATEID
because there is nothing keeping the layout stateid alive.

Also do not pretend sending layoutreturn if we are not.
Signed-off-by: NPeng Tao <tao.peng@primarydata.com>
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

If we have a read layout, then sanity check the minimal layout length
so that it does not extend beyond the end of file.
Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>

Signed-off-by: NTrond Myklebust <trond.myklebust@primarydata.com>