to #28991349

commit ed76e329d74a4b15ac0f5fd3adbd52ec0178a134 upstream

This is in preparation for allowing multiple sets of maps per
queue, if so desired.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Reviewed-by: NJoseph Qi <joseph.qi@linux.alibaba.com>

commit 3722e6a52174d7c3a00e6f5efd006ca093f346c1 upstream.

The virtio scsi spec defines struct virtio_scsi_ctrl_tmf as a set of
device-readable records and a single device-writable response entry:

    struct virtio_scsi_ctrl_tmf
    {
        // Device-readable part
        le32 type;
        le32 subtype;
        u8 lun[8];
        le64 id;
        // Device-writable part
        u8 response;
    }

The above should be organised as two descriptor entries (or potentially
more if using VIRTIO_F_ANY_LAYOUT), but without any extra data after "le64
id" or after "u8 response".

The Linux driver doesn't respect that, with virtscsi_abort() and
virtscsi_device_reset() setting cmd->sc before calling virtscsi_tmf().  It
results in the original scsi command payload (or writable buffers) added to
the tmf.

This fixes the problem by leaving cmd->sc zeroed out, which makes
virtscsi_kick_cmd() add the tmf to the control vq without any payload.

Cc: stable@vger.kernel.org
Signed-off-by: NFelipe Franciosi <felipe@nutanix.com>
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

When the underlying device is a 4 KiB logical block size device with a
protection interval exponent of 0, i.e. 4096 bytes data + 8 bytes PI, the
driver miscalculates the pi_bytes{out,in} by a factor of 8x (64 bytes).

This leads to errors on all reads and writes on 4 KiB logical block size
devices when CONFIG_BLK_DEV_INTEGRITY is enabled and the
VIRTIO_SCSI_F_T10_PI feature bit has been negotiated.

Fixes: e6dc783a ("virtio-scsi: Enable DIF/DIX modes in SCSI host LLD")
Acked-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NGreg Edwards <gedwards@ddn.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The kmalloc() function has a 2-factor argument form, kmalloc_array(). This
patch replaces cases of:

        kmalloc(a * b, gfp)

with:
        kmalloc_array(a * b, gfp)

as well as handling cases of:

        kmalloc(a * b * c, gfp)

with:

        kmalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kmalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kmalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The tools/ directory was manually excluded, since it has its own
implementation of kmalloc().

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kmalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kmalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kmalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kmalloc
+ kmalloc_array
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kmalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kmalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kmalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kmalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kmalloc(C1 * C2 * C3, ...)
|
  kmalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kmalloc(sizeof(THING) * C2, ...)
|
  kmalloc(sizeof(TYPE) * C2, ...)
|
  kmalloc(C1 * C2 * C3, ...)
|
  kmalloc(C1 * C2, ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	E1 * E2
+	E1, E2
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>

Now that virtio_scsi uses blk-mq exclusively, we can remove the
scsi_host_template and associated plumbing for the legacy I/O path.

[mkp: commit desc]

Cc: Omar Sandoval <osandov@fb.com>,
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>,
Cc: James Bottomley <james.bottomley@hansenpartnership.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Suggested-by: Christoph Hellwig <hch@lst.de>,
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Since commit 84676c1f ("genirq/affinity: assign vectors to all
possible CPUs") it is possible to end up in a scenario where only
offline CPUs are mapped to an interrupt vector.

This is only an issue for the legacy I/O path since with blk-mq/scsi-mq
an I/O can't be submitted to a hardware queue if the queue isn't mapped
to an online CPU.

Fix this issue by forcing virtio-scsi to use blk-mq.

[mkp: commit desc]

Cc: Omar Sandoval <osandov@fb.com>,
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>,
Cc: James Bottomley <james.bottomley@hansenpartnership.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: Don Brace <don.brace@microsemi.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Laurence Oberman <loberman@redhat.com>
Fixes: 84676c1f ("genirq/affinity: assign vectors to all possible CPUs")
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Since switching to blk-mq as the default in commit 5c279bd9
("scsi: default to scsi-mq"), virtio-scsi LUNs consume about 10x as
much kernel memory.

qemu currently allocates a fixed 128 entry virtqueue.  can_queue
currently is set to 1024.  But with indirect descriptors, each command
in the queue takes 1 virtqueue entry, so the number of commands which
can be queued is equal to the length of the virtqueue.

Note I intend to send a patch to qemu to allow the virtqueue size to be
configured from the qemu command line.
Signed-off-by: NRichard W.M. Jones <rjones@redhat.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Multi-queue virtio-scsi uses a different scsi_host_template struct.  Add
the .device_alloc field there, too.

Fixes: 25d1d50e
Cc: stable@vger.kernel.org
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NFam Zheng <famz@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

virtio_scsi tries to do exception handling after the default 30 seconds
timeout expires.  However, it's better to let the host control the
timeout, otherwise with a heavy I/O load it is likely that an abort will
also timeout.  This leads to fatal errors like filesystems going
offline.

Disable the 'sd' timeout and allow the host to do exception handling,
following the precedent of the storvsc driver.

Hannes has a proposal to introduce timeouts in virtio, but this provides
an immediate solution for stable kernels too.

[mkp: fixed typo]
Reported-by: NDouglas Miller <dougmill@linux.vnet.ibm.com>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: linux-scsi@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Since the SCSI core zeroes driver-private command data, remove
that code from the virtio driver.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

We are going to add more parameters to find_vqs, let's wrap the call so
we don't need to tweak all drivers every time.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Passed through SCSI targets may have transfer limits which come from the
host SCSI controller or something on the host side other than the target
itself.

To make this work properly, the hypervisor can adjust the target's VPD
information to advertise these limits.  But for that to work, the guest
has to look at the VPD pages, which we won't do by default if it is an
SPC-2 device, even if it does actually support it.

This adds a workaround to address this, forcing devices attached to a
virtio-scsi controller to always check the VPD pages.  This is modelled
on a similar workaround for the storvsc (Hyper-V) SCSI controller,
although that exists for slightly different reasons.

A specific case which causes this is a volume from IBM's IPR RAID
controller (which presents as an SPC-2 device, although it does support
VPD) passed through with qemu's 'scsi-block' device.

[mkp: fixed typo]
Signed-off-by: NDavid Gibson <david@gibson.dropbear.id.au>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Use automatic IRQ affinity assignment in the virtio layer if available,
and build the blk-mq queues based on it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Add a struct irq_affinity pointer to the find_vqs methods, which if set
is used to tell the PCI layer to create the MSI-X vectors for our I/O
virtqueues with the proper affinity from the start.  Compared to after
the fact affinity hints this gives us an instantly working setup and
allows to allocate the irq descritors node-local and avoid interconnect
traffic.  Last but not least this will allow blk-mq queues are created
based on the interrupt affinity for storage drivers.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

In the case of a graceful set of detaches, where the virtio-scsi-ccw
disk is removed from the guest prior to the controller, the guest
behaves quite normally.  Specifically, the detach gets us into
sd_sync_cache to issue a Synchronize Cache(10) command, which
immediately fails (and is retried a couple of times) because the device
has been removed.  Later, the removal of the controller sees two CRWs
presented, but there's no further indication of the removal from the
guest viewpoint.

 [   17.217458] sd 0:0:0:0: [sda] Synchronizing SCSI cache
 [   17.219257] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK
 [   21.449400] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2
 [   21.449406] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0

However, on s390, the SCSI disks can be removed "by surprise" when an
entire controller (host) is removed and all associated disks are removed
via the loop in scsi_forget_host.  The same call to sd_sync_cache is
made, but because the controller has already been removed, the
Synchronize Cache(10) command is neither issued (and then failed) nor
rejected.

That the I/O isn't returned means the guest cannot have other devices
added nor removed, and other tasks (such as shutdown or reboot) issued
by the guest will not complete either.  The virtio ring has already been
marked as broken (via virtio_break_device in virtio_ccw_remove), but we
still attempt to queue the command only to have it remain there.  The
calling sequence provides a bit of distinction for us:

  virtscsi_queuecommand()
   -> virtscsi_kick_cmd()
    -> virtscsi_add_cmd()
     -> virtqueue_add_sgs()
      -> virtqueue_add()
         if success
           return 0
         elseif vq->broken or vring_mapping_error()
           return -EIO
         else
           return -ENOSPC

A return of ENOSPC is generally a temporary condition, so returning
"host busy" from virtscsi_queuecommand makes sense here, to have it
redriven in a moment or two.  But the EIO return code is more of a
permanent error and so it would be wise to return the I/O itself and
allow the calling thread to finish gracefully.  The result is these four
kernel messages in the guest (the fourth one does not occur prior to
this patch):

 [   22.921562] crw_info : CRW reports slct=0, oflw=0, chn=1, rsc=3, anc=0, erc=4, rsid=2
 [   22.921580] crw_info : CRW reports slct=0, oflw=0, chn=0, rsc=3, anc=0, erc=4, rsid=0
 [   22.921978] sd 0:0:0:0: [sda] Synchronizing SCSI cache
 [   22.921993] sd 0:0:0:0: [sda] Synchronize Cache(10) failed: Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK

I opted to fill in the same response data that is returned from the more
graceful device detach, where the disk device is removed prior to the
controller device.
Signed-off-by: NEric Farman <farman@linux.vnet.ibm.com>
Reviewed-by: NFam Zheng <famz@redhat.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

Install the callbacks via the state machine. It uses the multi instance
infrastructure of the hotplug code to handle each interface.

virtscsi_set_affinity() is removed from virtscsi_init() because
virtscsi_cpu_notif_add() (the function which registers the instance) is invoked
right after it and the cpuhp_state_add_instance() functions invokes the startup
callback on all online CPUs.

The same thing can not be applied virtscsi_cpu_notif_remove() because
virtscsi_remove_vqs() invokes virtscsi_set_affinity() with affinity = false as
argument but the old CPU_DEAD state invoked the function with affinity = true
(which does not match the DEAD callback).
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: virtualization@lists.linux-foundation.org
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160906170457.32393-11-bigeasy@linutronix.deSigned-off-by: NThomas Gleixner <tglx@linutronix.de>

There is only one waiter for the completion, therefore there is no need
to use complete_all(). Let's make that clear by using complete() instead
of complete_all().

The usage pattern of the completion is:

waiter context                          waker context

virtscsi_tmf()
  DECLARE_COMPLETION_ONSTACK()
  virtscsi_kick_cmd()
  wait_for_completion()

                                        virtscsi_complete_free()
                                          complete()
Signed-off-by: NDaniel Wagner <daniel.wagner@bmw-carit.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/virtio_scsi.c: In function 'virtscsi_probe':
drivers/scsi/virtio_scsi.c:952:11: warning: unused variable 'host_prot' [-Wunused-variable]
  int err, host_prot;
           ^
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

T10 PI is just another optional feature, LLDDs should work without
the infrastructure.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NJames Bottomley <JBottomley@Odin.com>

Some devices might not implement config space access
(e.g. remoteproc used not to - before 3.9).
virtio/scsi needs config space access so make it
fail gracefully if not there.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Core activates this bit automatically now,
drop it from drivers that set it explicitly.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>

Note: for consistency, and to avoid sparse errors,
  convert all fields, even those no longer in use
  for virtio v1.0.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>

Drop the now unused reason argument from the ->change_queue_depth method.
Also add a return value to scsi_adjust_queue_depth, and rename it to
scsi_change_queue_depth now that it can be used as the default
->change_queue_depth implementation.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Reviewed-by: NHannes Reinecke <hare@suse.de>

All drivers use the implementation for ramping the queue up and down, so
instead of overloading the change_queue_depth method call the
implementation diretly if the driver opts into it by setting the
track_queue_depth flag in the host template.

Note that a few drivers validated the new queue depth in their
change_queue_depth method, but as we never go over the queue depth
set during slave_configure or the sysfs file this isn't nessecary
and can safely be removed.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NVenkatesh Srinivas <venkateshs@google.com>

Since virtio_scsi has supported multi virtqueue already,
it is natural to map the virtque to hw-queue of blk-mq.
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Remove the tagged argument from scsi_adjust_queue_depth, and just let it
handle the queue depth.  For most drivers those two are fairly separate,
given that most modern drivers don't care about the SCSI "tagged" status
of a command at all, and many old drivers allow queuing of multiple
untagged commands in the driver.

Instead we start out with the ->simple_tags flag set before calling
->slave_configure, which is how all drivers actually looking at
->simple_tags except for one worke anyway.  The one other case looks
broken, but I've kept the behavior as-is for now.

Except for that we only change ->simple_tags from the ->change_queue_type,
and when rejecting a tag message in a single driver, so keeping this
churn out of scsi_adjust_queue_depth is a clear win.

Now that the usage of scsi_adjust_queue_depth is more obvious we can
also remove all the trivial instances in ->slave_alloc or ->slave_configure
that just set it to the cmd_per_lun default.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMike Christie <michaelc@cs.wisc.edu>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>

Enable VQs early like we do for restore.
This makes it possible to drop the scan callback,
moving scanning into the probe function, and making
code simpler.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

We cancel event work on device removal, but an interrupt
could trigger immediately after this, and queue it
again.

To fix, set a flag.

Loosely based on patch by Paolo Bonzini
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

Michael S. Tsirkin noticed a race condition:
we reset device on freeze, but system WQ is still
running so it might try adding bufs to a VQ meanwhile.

To fix, switch to handling events from the freezable WQ.
Reported-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

virtio spec requires drivers to set DRIVER_OK before using VQs.
This is set automatically after restore returns, virtio scsi violated
this rule on restore by kicking event vq within restore.

To fix, call virtio_device_ready before using event queue.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

We currently kick event within virtscsi_init,
before host is fully initialized.

This can in theory confuse guest if device
consumes the buffers immediately.

To fix,  move virtscsi_kick_event_all out to scan/restore.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>

change_queue_depth allows changing per-target queue depth via sysfs.

It also allows the SCSI midlayer to ramp down the number of concurrent
inflight requests in response to a SCSI BUSY status response and allows
the midlayer to ramp the count back up to the device maximum when the
BUSY condition has resolved.
Signed-off-by: NVenkatesh Srinivas <venkateshs@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The spinlock of tgt_lock is only for serializing read and write
req_vq, one lockless seqcount is enough for the purpose.

On one 16core VM with vhost-scsi backend, the patch can improve
IOPS with 3% on random read test.
Signed-off-by: NMing Lei <ming.lei@canonical.com>
[Add initialization in virtscsi_target_alloc. - Paolo]
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Even though the virtio-scsi spec guarantees that all requests related
to the TMF will have been completed by the time the TMF itself completes,
the request queue's callback might not have run yet.  This causes requests
to be completed more than once, and as a result triggers a variety of
BUGs or oopses.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NVenkatesh Srinivas <venkateshs@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Calling the workqueue interface on uninitialized work items isn't a
good idea even if they're zeroed. It's not failing catastrophically only
through happy accidents.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This patch updates virtscsi_probe() to setup necessary Scsi_Host
level protection resources. (currently hardcoded to 1)

It changes virtscsi_add_cmd() to attach outgoing / incoming
protection SGLs preceeding the data payload, and is using the
new virtio_scsi_cmd_req_pi->pi_bytes[out,in] field to signal
to signal to vhost/scsi bytes to expect for protection data.

(Add missing #include <linux/blkdev.h> for blk_integrity - sfr + nab)
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Sagi Grimberg <sagig@dev.mellanox.co.il>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This triggers every time we do a SCSI abort:

virtscsi_tmf -> virtscsi_kick_cmd (grab lock and call) -> virtscsi_add_cmd
	-> virtqueue_add_sgs (GFP_NOIO)

Logs look like this:
 sd 0:0:0:0: [sda] abort
 BUG: sleeping function called from invalid context at mm/slub.c:966
 in_atomic(): 1, irqs_disabled(): 1, pid: 6, name: kworker/u2:0
 3 locks held by kworker/u2:0/6:
  #0:  ("scsi_tmf_%d"shost->host_no){......}, at: [<c0153180>] process_one_work+0xe0/0x3d0
  #1:  ((&(&cmd->abort_work)->work)){......}, at: [<c0153180>] process_one_work+0xe0/0x3d0
  #2:  (&(&virtscsi_vq->vq_lock)->rlock){......}, at: [<c043f508>] virtscsi_kick_cmd+0x18/0x1b0
 CPU: 0 PID: 6 Comm: kworker/u2:0 Not tainted 3.15.0-rc5+ #110
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-rc1-0-gb1d4dc9-20140515_140003-nilsson.home.kraxel.org 04/01/2014
 Workqueue: scsi_tmf_0 scmd_eh_abort_handler
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>

Taken almost entirely from Nicholas Bellinger's scsi-mq conversion.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NNicholas Bellinger <nab@linux-iscsi.org>

Access to tgt->req_vq is strictly serialized by spin_lock
of tgt->tgt_lock, so the ACCESS_ONCE() isn't necessary.

smp_read_barrier_depends() in virtscsi_req_done was introduced
to order reading req_vq and decreasing tgt->reqs, but it isn't
needed now because req_vq is read from
scsi->req_vqs[vq->index - VIRTIO_SCSI_VQ_BASE] instead of
tgt->req_vq, so remove the unnecessary barrier.

Also remove related comment about the barrier.
Signed-off-by: NMing Lei <tom.leiming@gmail.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

virtscsi_init calls virtscsi_remove_vqs on err, even before initializing
the vqs. The latter calls virtscsi_set_affinity, so let's check the
pointer there before setting affinity on it.

This fixes a panic when setting device's num_queues=2 on RHEL 6.5:

qemu-system-x86_64 ... \
-device virtio-scsi-pci,id=scsi0,addr=0x13,...,num_queues=2 \
-drive file=/stor/vm/dummy.raw,id=drive-scsi-disk,... \
-device scsi-hd,drive=drive-scsi-disk,...

[    0.354734] scsi0 : Virtio SCSI HBA
[    0.379504] BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
[    0.380141] IP: [<ffffffff814741ef>] __virtscsi_set_affinity+0x4f/0x120
[    0.380141] PGD 0
[    0.380141] Oops: 0000 [#1] SMP
[    0.380141] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.14.0+ #5
[    0.380141] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2007
[    0.380141] task: ffff88003c9f0000 ti: ffff88003c9f8000 task.ti: ffff88003c9f8000
[    0.380141] RIP: 0010:[<ffffffff814741ef>]  [<ffffffff814741ef>] __virtscsi_set_affinity+0x4f/0x120
[    0.380141] RSP: 0000:ffff88003c9f9c08  EFLAGS: 00010256
[    0.380141] RAX: 0000000000000000 RBX: ffff88003c3a9d40 RCX: 0000000000001070
[    0.380141] RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000000
[    0.380141] RBP: ffff88003c9f9c28 R08: 00000000000136c0 R09: ffff88003c801c00
[    0.380141] R10: ffffffff81475229 R11: 0000000000000008 R12: 0000000000000000
[    0.380141] R13: ffffffff81cc7ca8 R14: ffff88003cac3d40 R15: ffff88003cac37a0
[    0.380141] FS:  0000000000000000(0000) GS:ffff88003e400000(0000) knlGS:0000000000000000
[    0.380141] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[    0.380141] CR2: 0000000000000020 CR3: 0000000001c0e000 CR4: 00000000000006f0
[    0.380141] Stack:
[    0.380141]  ffff88003c3a9d40 0000000000000000 ffff88003cac3d80 ffff88003cac3d40
[    0.380141]  ffff88003c9f9c48 ffffffff814742e8 ffff88003c26d000 ffff88003c26d000
[    0.380141]  ffff88003c9f9c68 ffffffff81474321 ffff88003c26d000 ffff88003c3a9d40
[    0.380141] Call Trace:
[    0.380141]  [<ffffffff814742e8>] virtscsi_set_affinity+0x28/0x40
[    0.380141]  [<ffffffff81474321>] virtscsi_remove_vqs+0x21/0x50
[    0.380141]  [<ffffffff81475231>] virtscsi_init+0x91/0x240
[    0.380141]  [<ffffffff81365290>] ? vp_get+0x50/0x70
[    0.380141]  [<ffffffff81475544>] virtscsi_probe+0xf4/0x280
[    0.380141]  [<ffffffff81363ea5>] virtio_dev_probe+0xe5/0x140
[    0.380141]  [<ffffffff8144c669>] driver_probe_device+0x89/0x230
[    0.380141]  [<ffffffff8144c8ab>] __driver_attach+0x9b/0xa0
[    0.380141]  [<ffffffff8144c810>] ? driver_probe_device+0x230/0x230
[    0.380141]  [<ffffffff8144c810>] ? driver_probe_device+0x230/0x230
[    0.380141]  [<ffffffff8144ac1c>] bus_for_each_dev+0x8c/0xb0
[    0.380141]  [<ffffffff8144c499>] driver_attach+0x19/0x20
[    0.380141]  [<ffffffff8144bf28>] bus_add_driver+0x198/0x220
[    0.380141]  [<ffffffff8144ce9f>] driver_register+0x5f/0xf0
[    0.380141]  [<ffffffff81d27c91>] ? spi_transport_init+0x79/0x79
[    0.380141]  [<ffffffff8136403b>] register_virtio_driver+0x1b/0x30
[    0.380141]  [<ffffffff81d27d19>] init+0x88/0xd6
[    0.380141]  [<ffffffff81d27c18>] ? scsi_init_procfs+0x5b/0x5b
[    0.380141]  [<ffffffff81ce88a7>] do_one_initcall+0x7f/0x10a
[    0.380141]  [<ffffffff81ce8aa7>] kernel_init_freeable+0x14a/0x1de
[    0.380141]  [<ffffffff81ce8b3b>] ? kernel_init_freeable+0x1de/0x1de
[    0.380141]  [<ffffffff817dec20>] ? rest_init+0x80/0x80
[    0.380141]  [<ffffffff817dec29>] kernel_init+0x9/0xf0
[    0.380141]  [<ffffffff817e68fc>] ret_from_fork+0x7c/0xb0
[    0.380141]  [<ffffffff817dec20>] ? rest_init+0x80/0x80
[    0.380141] RIP  [<ffffffff814741ef>] __virtscsi_set_affinity+0x4f/0x120
[    0.380141]  RSP <ffff88003c9f9c08>
[    0.380141] CR2: 0000000000000020
[    0.380141] ---[ end trace 8074b70c3d5e1d73 ]---
[    0.475018] Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009
[    0.475018]
[    0.475068] Kernel Offset: 0x0 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffff9fffffff)
[    0.475068] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009

[jejb: checkpatch fixes]
Signed-off-by: NFam Zheng <famz@redhat.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: NJames Bottomley <JBottomley@Parallels.com>