The patch fixes a bug in the default configuration which
prevented a software bridge loaded on the PF interface from
working correctly because broadcast packets are incorrectly
looped back.

Fix the general case, by loading the driver in VEPA mode Until a
VF or VMDq VSI is added. This way loopback on the Main VSI is
turned off until needed and can resolve the issue of unnecessary
reflection for users that do not have VF or VMDq VSIs setup.

The driver must now coordinate the loopback setting for the Flow
Director (FDIR) VSI to make sure it is in sync with the current
VEB or VEPA mode setting.

The user can still switch bridge modes from the bridge commands and
choose to be in VEPA mode with VF VSIs. Because of hardware
requirements, the call to switch to VEB mode when no VF/VMDqs are
present will be rejected.

NOTE: This patch uses BIT_ULL as that is preferred going forward,
a followup patch in the lower priority queue to net-next will fix
up the remaining 1 << usages.

Change-ID: Ib121ddb18fe4b3c4f52e9deda6fcbeb9105683d1
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch fixes a bug where the i40e Tx queue will hang if this
skb is passed to the driver.

With mixed size fragments while using TSO there was a corner case
where we needed to linearize but we were not. This was seen with
iSCSI traffic and could be reproduced with a frag list that looks
like this:

num_frags = 17, gso_segs = 17, hdr_len = 66,
skb_shinfo(skb)->gso_size = 1448
size = 3002, j = 1, frag_size = 2936, num_frags = 17
size = 4268, j = 1, frag_size = 4096, num_frags = 16
size = 5534, j = 1, frag_size = 4096, num_frags = 15
size = 5352, j = 1, frag_size = 4096, num_frags = 14
size = 5170, j = 1, frag_size = 4096, num_frags = 13
size = 3468, j = 1, frag_size = 2576, num_frags = 12
size = 750, j = 1, frag_size = 112, num_frags = 11
size = 862, j = 2, frag_size = 112, num_frags = 10
size = 974, j = 3, frag_size = 112, num_frags = 9
size = 1126, j = 4, frag_size = 152, num_frags = 8
size = 1330, j = 5, frag_size = 204, num_frags = 7
size = 1534, j = 6, frag_size = 204, num_frags = 6
size = 356, j = 1, frag_size = 204, num_frags = 5
size = 560, j = 2, frag_size = 204, num_frags = 4
size = 764, j = 3, frag_size = 204, num_frags = 3
size = 968, j = 4, frag_size = 204, num_frags = 2
size = 1140, j = 5, frag_size = 172, num_frags = 1
result: linearize = 0, j = 6

Change-ID: I79bb1aeab0af255fe2ce28e93672a85d85bf47e8
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Commit dff173de ("bnx2x: Fix statistics locking scheme") changed the
bnx2x locking around statistics state into using a mutex - but the lock
is being accessed via a timer which is forbidden.

[If compiled with CONFIG_DEBUG_MUTEXES, logs show a warning about
accessing the mutex in interrupt context]

This moves the implementation into using a semaphore [with size '1']
instead.
Signed-off-by: NYuval Mintz <Yuval.Mintz@qlogic.com>
Signed-off-by: NAriel Elior <Ariel.Elior@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When we come to tear things down in netback_remove() and generate the
uevent it is possible that the xenstore directory has already been
removed (details below).

In such cases netback_uevent() won't be able to read the hotplug
script and will write a xenstore error node.

A recent change to the hypervisor exposed this race such that we now
sometimes lose it (where apparently we didn't ever before).

Instead read the hotplug script configuration during setup and use it
for the lifetime of the backend device.

The apparently more obvious fix of moving the transition to
state=Closed in netback_remove() to after the uevent does not work
because it is possible that we are already in state=Closed (in
reaction to the guest having disconnected as it shutdown). Being
already in Closed means the toolstack is at liberty to start tearing
down the xenstore directories. In principal it might be possible to
arrange to unregister the device sooner (e.g on transition to Closing)
such that xenstore would still be there but this state machine is
fragile and prone to anger...

A modern Xen system only relies on the hotplug uevent for driver
domains, when the backend is in the same domain as the toolstack it
will run the necessary setup/teardown directly in the correct sequence
wrt xenstore changes.
Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Acked-by: NWei Liu <wei.liu2@citrix.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/xen-netback/netback.c: In function ‘xenvif_tx_build_gops’:
drivers/net/xen-netback/netback.c:1253:8: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 5 has type ‘int’ [-Wformat=]
        (txreq.offset&~PAGE_MASK) + txreq.size);
        ^

PAGE_MASK's type can vary by arch, so a cast is needed.
Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
----
v2: Cast to unsigned long, since PAGE_MASK can vary by arch.
Acked-by: NWei Liu <wei.liu2@citrix.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When Rx packet data must be dropped, all the buffers
associated with that Rx packet must be freed. Extend
and rename efx_free_rx_buffer() to efx_free_rx_buffers()
and loop through all the fragments.
By doing so this patch fixes a possible memory leak.
Signed-off-by: NShradha Shah <sshah@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bug in the driver initialization causes soft-lockup if firmware
initialization timeout is reached. Polling function bfa_ioc_poll_fwinit()
incorrectly calls bfa_nw_iocpf_timeout() when the timeout is reached.
The problem is that bfa_nw_iocpf_timeout() calls again
bfa_ioc_poll_fwinit()... etc. The bfa_ioc_poll_fwinit() should directly
send timeout event for iocpf and the same should be done if firmware
download into HW fails.

Cc: Rasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Driver starts iocpf timer prior bnad_ioceth_enable() call and this is
unreasonable. This piece of code probably originates from Brocade/Qlogic
out-of-box driver during initial import into upstream. This driver uses
only one timer and queue to implement multiple timers and this timer is
started at this place. The upstream driver uses multiple timers instead
of this.

Cc: Rasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Firmware required by bna is stored in appropriate files as sequence
of LE32 integers. After loading by request_firmware() they need to be
byte-swapped on big-endian arches. Without this conversion the NIC
is unusable on big-endian machines.

Cc: Rasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We don't assign pi_ctx to desc->pi_ctx until we're certain to succeed
in the function.  That means the cleanup path should use the local
pi_ctx variable, not desc->pi_ctx.

This was detected by Coverity (CID 1260062).
Signed-off-by: NRoland Dreier <roland@purestorage.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

It seems like we only care if a transport is passthrough or not. Convert
transport_type to a flags field and replace TRANSPORT_PLUGIN_* with a
flag, TRANSPORT_FLAG_PASSTHROUGH.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Aside from whether they handle BIDI ops or not, parsing of the CDB by
kernel and user SCSI passthrough modules should be identical. Move this
into a new passthrough_parse_cdb() and call it from tcm-pscsi and tcm-user.
Reported-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NAndy Grover <agrover@redhat.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

After much discussion, give up on only passing a subset of SCSI commands
to userspace and pass them all. Based on what pscsi is doing, make sure
to set SCF_SCSI_DATA_CDB for I/O ops, and define attributes identical to
pscsi.

Make hw_block_size configurable via dev param.

Remove mention of command filtering from tcmu-design.txt.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

See https://bugzilla.redhat.com/show_bug.cgi?id=1025672

We need to put() the reference to the scsi host that we got in
pscsi_configure_device(). In VIRTUAL_HOST mode it is associated with
the dev_virt, not the hba_virt.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Cc: stable@vger.kernel.org # 2.6.38+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

There is just one configfs subsystem in the target code, so we might as
well add two helpers to reference / unreference it from the core code
instead of passing pointers to it around.

This fixes a regression introduced for v4.1-rc1 with commit 9ac8928e,
where configfs_depend_item() callers using se_tpg_tfo->tf_subsys would
fail, because the assignment from the original target_core_subsystem[]
is no longer happening at target_register_template() time.

(Fix target_core_exit_configfs pointer dereference - Sagi)
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NHimanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The following error message is seen when loading the nct6683 driver
with DEBUG_LOCK_ALLOC enabled.

BUG: key ffff88040b2f0030 not in .data!
------------[ cut here ]------------
WARNING: CPU: 0 PID: 186 at kernel/locking/lockdep.c:2988
				lockdep_init_map+0x469/0x630()
DEBUG_LOCKS_WARN_ON(1)

Caused by a missing call to sysfs_attr_init() when initializing
sysfs attributes.
Reported-by: NAlexey Orishko <alexey.orishko@gmail.com>
Reviewed-by: NJean Delvare <jdelvare@suse.de>
Cc: stable@vger.kernel.org # v3.18+
Signed-off-by: NGuenter Roeck <linux@roeck-us.net>

The following error message is seen when loading the nct6775 driver
with DEBUG_LOCK_ALLOC enabled.

BUG: key ffff88040b2f0030 not in .data!
------------[ cut here ]------------
WARNING: CPU: 0 PID: 186 at kernel/locking/lockdep.c:2988
				lockdep_init_map+0x469/0x630()
DEBUG_LOCKS_WARN_ON(1)

Caused by a missing call to sysfs_attr_init() when initializing
sysfs attributes.
Reported-by: NAlexey Orishko <alexey.orishko@gmail.com>
Reviewed-by: NJean Delvare <jdelvare@suse.de>
Cc: stable@vger.kernel.org # v3.12+
Signed-off-by: NGuenter Roeck <linux@roeck-us.net>

I2C address 0x37 may be used by EEPROMs, which can result in false
positives. Do not attempt to detect a chip at this address.
Reviewed-by: NJean Delvare <jdelvare@suse.de>
Cc: stable@vger.kernel.org # v4.0+
Signed-off-by: NGuenter Roeck <linux@roeck-us.net>

dm_merge_bvec() was originally added in f6fccb ("dm: introduce
merge_bvec_fn").  In that commit a value in sectors is converted to
bytes using << 9, and then assigned to an int.  This code made
assumptions about the value of BIO_MAX_SECTORS.

A later commit 148e51 ("dm: improve documentation and code clarity in
dm_merge_bvec") was meant to have no functional change but it removed
the use of BIO_MAX_SECTORS in favor of using queue_max_sectors().  At
this point the cast from sector_t to int resulted in a zero value.  The
fallout being dm_merge_bvec() would only allow a single page to be added
to a bio.

This interim fix is minimal for the benefit of stable@ because the more
comprehensive cleanup of passing a sector_t to all DM targets' merge
function will impact quite a few DM targets.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 3.19+

dm-multipath accepts 0 path mapping.

  # echo '0 2097152 multipath 0 0 0 0' | dmsetup create newdev

Such a mapping can be used to release underlying devices while still
holding requests in its queue until working paths come back.

However, once the multipath device is created over blk-mq devices,
it rejects reloading of 0 path mapping:

  # echo '0 2097152 multipath 0 0 1 1 queue-length 0 1 1 /dev/sda 1' \
      | dmsetup create mpath1
  # echo '0 2097152 multipath 0 0 0 0' | dmsetup load mpath1
  device-mapper: reload ioctl on mpath1 failed: Invalid argument
  Command failed

With following kernel message:
  device-mapper: ioctl: can't change device type after initial table load.

DM tries to inherit the current table type using dm_table_set_type()
but it doesn't work as expected because of unnecessary check about
whether the target type is hybrid or not.

Hybrid type is for targets that work as either request-based or bio-based
and not required for blk-mq or non blk-mq checking.

Fixes: 65803c20 ("dm table: train hybrid target type detection to select blk-mq if appropriate")
Signed-off-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

When stacking request-based dm device on non blk-mq device and
device-mapper target could not map the request (error target is used,
multipath target with all paths down, etc), the WARN_ON_ONCE() in
free_rq_clone() will trigger when it shouldn't.

The warning was added by commit aa6df8dd ("dm: fix free_rq_clone() NULL
pointer when requeueing unmapped request").  But free_rq_clone() with
clone->q == NULL is valid usage for the case where
dm_kill_unmapped_request() initiates request cleanup.

Fix this false warning by just removing the WARN_ON -- it only generated
false positives and was never useful in catching the intended case
(completing clone request not being mapped e.g. clone->q being NULL).

Fixes: aa6df8dd ("dm: fix free_rq_clone() NULL pointer when requeueing unmapped request")
Reported-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reported-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: NMike Snitzer <snitzer@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Should fix fdo#89558
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

And also more generic, so it can be used on newer chipsets.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Commit 3740c825 ("drm/nouveau/gr/gf100-: add symbolic names for
classes") introduced a wrong macro definition causing acceleration setup
to fail. Fix it.
Signed-off-by: NLars Seipel <ls@slrz.net>
Fixes: 3740c825 ("drm/nouveau/gr/gf100-: add symbolic names for classes")
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

We have that bug for years and some users report side effects when fixing it on older hardware.

So revert it for VM_CONTEXT0_PAGE_TABLE_END_ADDR, but keep it for VM 1-15.
Signed-off-by: NChristian König <christian.koenig@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The function brcmf_msgbuf_get_pktid() may return a NULL pointer so
the callers should check the return pointer before accessing it to
avoid the crash below (see [1]):

brcmfmac: brcmf_msgbuf_get_pktid: Invalid packet id 273 (not in use)
BUG: unable to handle kernel NULL pointer dereference at 0000000000000080
IP: [<ffffffff8145b225>] skb_pull+0x5/0x50
PGD 0
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: pci_stub vboxpci(O) vboxnetflt(O) vboxnetadp(O) vboxdrv(O)
 snd_hda_codec_hdmi bnep mousedev hid_generic ushwmon msr ext4 crc16 mbcache
 jbd2 sd_mod uas usb_storage ahci libahci libata scsi_mod xhci_pci xhci_hcd
 usbcore usb_common
CPU: 0 PID: 1661 Comm: irq/61-brcmf_pc Tainted: G O    4.0.1-MacbookPro-ARCH #1
Hardware name: Apple Inc. MacBookPro12,1/Mac-E43C1C25D4880AD6,
 BIOS MBP121.88Z.0167.B02.1503241251 03/24/2015
task: ffff880264203cc0 ti: ffff88025ffe4000 task.ti: ffff88025ffe4000
RIP: 0010:[<ffffffff8145b225>]  [<ffffffff8145b225>] skb_pull+0x5/0x50
RSP: 0018:ffff88025ffe7d40  EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff88008a33c000 RCX: 0000000000000044
RDX: 0000000000000000 RSI: 000000000000004a RDI: 0000000000000000
RBP: ffff88025ffe7da8 R08: 0000000000000096 R09: 000000000000004a
R10: 0000000000000000 R11: 000000000000048e R12: ffff88025ff14f00
R13: 0000000000000000 R14: ffff880263b48200 R15: ffff88008a33c000
FS:  0000000000000000(0000) GS:ffff88026ec00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000080 CR3: 000000000180b000 CR4: 00000000003407f0
Stack:
 ffffffffa06aed74 ffff88025ffe7dc8 ffff880263b48270 ffff880263b48278
 05ea88020000004a 0002ffff81014635 000000001720b2f6 ffff88026ec116c0
 ffff880263b48200 0000000000010000 ffff880263b4ae00 ffff880264203cc0
Call Trace:
 [<ffffffffa06aed74>] ? brcmf_msgbuf_process_rx+0x404/0x480 [brcmfmac]
 [<ffffffff810cea60>] ? irq_finalize_oneshot.part.30+0xf0/0xf0
 [<ffffffffa06afb55>] brcmf_proto_msgbuf_rx_trigger+0x35/0xf0 [brcmfmac]
 [<ffffffffa06baf2a>] brcmf_pcie_isr_thread_v2+0x8a/0x130 [brcmfmac]
 [<ffffffff810cea80>] irq_thread_fn+0x20/0x50
 [<ffffffff810ceddf>] irq_thread+0x13f/0x170
 [<ffffffff810cebf0>] ? wake_threads_waitq+0x30/0x30
 [<ffffffff810ceca0>] ? irq_thread_dtor+0xb0/0xb0
 [<ffffffff81092a08>] kthread+0xd8/0xf0
 [<ffffffff81092930>] ? kthread_create_on_node+0x1c0/0x1c0
 [<ffffffff8156d898>] ret_from_fork+0x58/0x90
 [<ffffffff81092930>] ? kthread_create_on_node+0x1c0/0x1c0
Code: 01 83 e2 f7 88 50 01 48 83 c4 08 5b 5d f3 c3 0f 1f 80 00 00 00 00 83 e2
 f7 88 50 01 c3 66 0f 1f 84 00 00 00 00 00 0f 1f
RIP  [<ffffffff8145b225>] skb_pull+0x5/0x50
 RSP <ffff88025ffe7d40>
CR2: 0000000000000080
---[ end trace b074c0f90e7c997d ]---

[1] http://mid.gmane.org/20150430193259.GA5630@googlemail.com

Cc: <stable@vger.kernel.org> # v3.18, v3.19, v4.0, v4.1
Reported-by: NMichael Hornung <mhornung.linux@gmail.com>
Reviewed-by: NHante Meuleman <meuleman@broadcom.com>
Reviewed-by: NPieter-Paul Giesberts <pieterpg@broadcom.com>
Signed-off-by: NArend van Spriel <arend@broadcom.com>
Signed-off-by: NKalle Valo <kvalo@codeaurora.org>

The radio cfg DWORD was taken from the wrong place in the
8000 HW family, after a line in the code was wrongly changed
by mistake. This broke several 8260 devices.

Fixes: 5dd9c68a ("iwlwifi: drop support for early versions of 8000")
Signed-off-by: NLiad Kaufman <liad.kaufman@intel.com>
Reviewed-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NEmmanuel Grumbach <emmanuel.grumbach@intel.com>

The cmd_in_flight tracking was introduced to workaround faulty
power management hardware, by having the driver keep the NIC
awake as long as there are commands in flight. However, some of
the code handling this workaround was unconditionally executed,
which resulted with an inconsistent state where the driver assumed
that the NIC was awake although it wasn't.

Fix this by renaming 'cmd_in_flight' to 'cmd_hold_nic_awake' and
handling the NIC requested awake state only for hardwares for
which the workaround is needed.
Signed-off-by: NIlan Peer <ilan.peer@intel.com>
Signed-off-by: NEmmanuel Grumbach <emmanuel.grumbach@intel.com>

A recent change removed the need for locking around writing
to "sync_action" (and various other places), but introduced a
subtle race.
When e.g. setting 'reshape' on a 'frozen' array, the 'frozen'
flag is cleared before 'reshape' is set, so the md thread can
get in and start trying recovery - which isn't wanted.

So instead of clearing MD_RECOVERY_FROZEN for any command
except 'frozen', only clear it when each specific command
is parsed.  This allows the handling of 'reshape' to clear
the bit while a lock is held.

Also remove some places where we set MD_RECOVERY_NEEDED,
as it is always set on non-error exit of the function.
Signed-off-by: NNeilBrown <neilb@suse.de>
Fixes: 6791875e ("md: make reconfig_mutex optional for writes to md sysfs files.")

Once the array has too much failure, we need to break
stripe-batches up so they can all be dealt with.
Signed-off-by: NNeilBrown <neilb@suse.de>

Now that the code in break_stripe_batch_list() is nearly identical
to the end of handle_stripe_clean_event, replace the later
with a function call.

The only remaining difference of any interest is the masking that is
applieds to dev[i].flags copied from head_sh.
R5_WriteError certainly isn't wanted as it is set per-stripe, not
per-patch.  R5_Overlap isn't wanted as it is explicitly handled.
Signed-off-by: NNeilBrown <neilb@suse.de>

When a batch of stripes is broken up, we keep some of the flags
that were per-stripe, and copy other flags from the head to all
others.

This only happens while a stripe is being handled, so many of the
flags are irrelevant.

The "SYNC_FLAGS" (which I've renamed to make it clear there are
several) and STRIPE_DEGRADED are set per-stripe and so need to be
preserved.  STRIPE_INSYNC is the only flag that is set on the head
that needs to be propagated to all others.

For safety, add a WARN_ON if others are set, except:
 STRIPE_HANDLE - this is safe and per-stripe and we are going to set
      in several cases anyway
 STRIPE_INSYNC
 STRIPE_IO_STARTED - this is just a hint and doesn't hurt.
 STRIPE_ON_PLUG_LIST
 STRIPE_ON_RELEASE_LIST - It is a point pointless for a batched
           stripe to be on one of these lists, but it can happen
           as can be safely ignored.
Signed-off-by: NNeilBrown <neilb@suse.de>

When we break a stripe_batch_list we sometimes want to set
STRIPE_HANDLE on the individual stripes, and sometimes not.

So pass a 'handle_flags' arg.  If it is zero, always set STRIPE_HANDLE
(on non-head stripes).  If not zero, only set it if any of the given
flags are present.
Signed-off-by: NNeilBrown <neilb@suse.de>

break_stripe_batch list didn't clear head_sh->batch_head.
This was probably a bug.

Also clear all R5_Overlap flags and if any were cleared, wake up
'wait_for_overlap'.
This isn't always necessary but the worst effect is a little
extra checking for code that is waiting on wait_for_overlap.

Also, don't use wake_up_nr() because that does the wrong thing
if 'nr' is zero, and it number of flags cleared doesn't
strongly correlate with the number of threads to wake.
Signed-off-by: NNeilBrown <neilb@suse.de>

handle_stripe_clean_event() contains a chunk of code very
similar to check_break_stripe_batch_list().
If we make the latter more like the former, we can end up
with just one copy of this code.

This  first step removed the condition (and the 'check_') part
of the name.  This has the added advantage of making it clear
what check is being performed at the point where the function is
called.
Signed-off-by: NNeilBrown <neilb@suse.de>

If a stripe is a member of a batch, but not the head, it must
not be handled separately from the rest of the batch.

'clear_batch_ready()' handles this requirement to some
extent but not completely.  If a member is passed to handle_stripe()
a second time it returns '0' indicating the stripe can be handled,
which is wrong.
So add an extra test.
Signed-off-by: NNeilBrown <neilb@suse.de>

da91309e (cpumask: Utility function to set n'th cpu...) created a
genuinely weird function.  I never saw it before, it went through DaveM.
(He only does this to make us other maintainers feel better about our own
mistakes.)

cpumask_set_cpu_local_first's purpose is say "I need to spread things
across N online cpus, choose the ones on this numa node first"; you call
it in a loop.

It can fail.  One of the two callers ignores this, the other aborts and
fails the device open.

It can fail in two ways: allocating the off-stack cpumask, or through a
convoluted codepath which AFAICT can only occur if cpu_online_mask
changes.  Which shouldn't happen, because if cpu_online_mask can change
while you call this, it could return a now-offline cpu anyway.

It contains a nonsensical test "!cpumask_of_node(numa_node)".  This was
drawn to my attention by Geert, who said this causes a warning on Sparc.
It sets a single bit in a cpumask instead of returning a cpu number,
because that's what the callers want.

It could be made more efficient by passing the previous cpu rather than
an index, but that would be more invasive to the callers.

Fixes: da91309e
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (then rebased)
Tested-by: NAmir Vadai <amirv@mellanox.com>
Acked-by: NAmir Vadai <amirv@mellanox.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>

When we add a write to a stripe we need to make sure the bitmap
bit is set.  While doing that the stripe is not locked so it could
be added to a batch after which further changes to STRIPE_BIT_DELAY
and ->bm_seq are ineffective.

So we need to hold off adding to a stripe until bitmap_startwrite has
completed at least once, and we need to avoid further changes to
STRIPE_BIT_DELAY once the stripe has been added to a batch.

If a bitmap_startwrite() completes after the stripe was added to a
batch, it will not have set the bit, only incremented a counter, so no
extra delay of the stripe is needed.
Reported-by: NShaohua Li <shli@kernel.org>
Signed-off-by: NNeilBrown <neilb@suse.de>

When we add a stripe to a batch, we need to be sure that
head stripe will wait for the bitmap update required for the new
stripe.
Signed-off-by: NNeilBrown <neilb@suse.de>