This patch checks to see if an ATA device supports NCQ command priorities.
If so and the user has specified an iocontext that indicates
IO_PRIO_CLASS_RT then we build a tf with a high priority command.

This is done to improve the tail latency of commands that are high
priority by passing priority to the device.

tj: Removed trivial ata_ncq_prio_enabled() and open-coded the test.
Signed-off-by: NAdam Manzanares <adam.manzanares@hgst.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Ls1046a is a new introduced soc which supports ATA3.0.
Signed-off-by: NTang Yuantian <yuantian.tang@nxp.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

This reverts commit 64084729 ("ahci: qoriq: Disable NCQ
on ls2080a SoC")

The erratum has been fixed in ls2080a v2.0 and later soc.
In reality, customer will not get any ls2080a v1.0 soc. Neither apply
to any products. So reverting this commit won't create any side effect.

Blacklisting v2.0 could also be a option, but that needs to check the
soc version which is not suitable in the driver.
Signed-off-by: NTang Yuantian <yuantian.tang@nxp.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Signed-off-by: NHarman Kalra <harman4linux@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Replace BUG() with BUG_ON().
Caught by coccinelle.
Signed-off-by: NHarman Kalra <harman4linux@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Replacing dma_pool_alloc and memset with a single call to dma_pool_zalloc
Signed-off-by: NHarman Kalra <harman4linux@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Restrict support SCT Write Same to devices which also support ZAC where
support is required.
Reported-by: NMike Krinkin <krinkin.m.u@gmail.com>
Signed-off-by: NShaun Tancheff <shaun.tancheff@seagate.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Use the new pci_alloc_irq_vectors API to allocate MSI-X and MSI vectors.
The big advantage over the old code is that we can use the same API for
MSI and MSI-X, and that we don't need to store the MSI-X vector mapping
in driver-private data structures.

This first conversion keeps the probe order as-is: MSI-X multi vector,
MSI multi vector, MSI single vector, MSI-X single vector and last a
single least legacy interrupt line.  There is one small change of
behavior: we now check the "MSI Revert to Single Message" flag for
MSI-X in addition to MSI.

Because the API to find the Linux IRQ number for a MSI/MSI-X vector
is PCI specific, but libahaci is bus-agnostic I had to a
get_irq_vector function pointer to struct ahci_host_priv.  The
alternative would be to move the multi-vector case of ahci_host_activate
to ahci.c and just call ata_host_activate directly from the others
users of ahci_host_activate.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Ninja32 needs to set some flags to indicate it does 32bit IO. However it currently assigns this which
loses the initializing flag and causes a warning spew. Fix it to use a logical or as is intended.
Signed-off-by: NAlan Cox <alan@linux.intel.com>
Tested-by: NEllmar Stelnberger <estellnb@elstel.org>
Signed-off-by: NTejun Heo <tj@kernel.org>

Use non DMA write log when ATA_DFLAG_PIO is set.
Signed-off-by: NShaun Tancheff <shaun.tancheff@seagate.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Acked-by: NTejun Heo <tj@kernel.org>

Correct handling of devices with sector_size other that 512 bytes.

In the case of a 4Kn device sector_size it is possible to describe a much
larger DSM Trim than the current fixed default of 512 bytes.

This patch assumes the minimum descriptor is sector_size and fills out
the descriptor accordingly.

The ACS-2 specification is quite clear that the DSM command payload is
sized as number of 512 byte transfers so a 4Kn device will operate
correctly without this patch.
Signed-off-by: NShaun Tancheff <shaun.tancheff@seagate.com>
Acked-by: NTejun Heo <tj@kernel.org>

SATA drives may support write same via SCT. This is useful
for setting the drive contents to a specific pattern (0's).

Translate a SCSI WRITE SAME 16 command to be either a DSM TRIM
command or an SCT Write Same command.

Based on the UNMAP flag:
  - When set translate to DSM TRIM
  - When not set translate to SCT Write Same
Signed-off-by: NShaun Tancheff <shaun.tancheff@seagate.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Acked-by: NTejun Heo <tj@kernel.org>

Safely overwriting the attached page to ATA format from the SCSI formatted
variant.
Signed-off-by: NShaun Tancheff <shaun.tancheff@seagate.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Acked-by: NTejun Heo <tj@kernel.org>

irq already contains the interrupt number for the port, don't add the
port index to it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>
Fixes: d684a90d ("ahci: per-port msix support")
Cc: stable@vger.kernel.org v4.5+

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Despite ST AHCI version = 1.3, reading HOST_PORTS_IMPL
returns 0. So force_port_map to 1 by using ports-implemented
DT property.
Signed-off-by: NPatrice Chotard <patrice.chotard@st.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

By default the SATA IP on the qoriq SoCs does not generating
coherent/snoopable transactions.  This patch enable it in the
sata axicc register.
In addition, the dma-coherent property must be set on the
SATA controller nodes.
Signed-off-by: NTang Yuantian <yuantian.tang@nxp.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

The default values for Port Phy2Cfg register and
Port Phy3Cfg register are better, no need to overwrite them.
Signed-off-by: NTang Yuantian <yuantian.tang@nxp.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

scsi_done() was called repeatedly and apparently because of that,
the kernel would call trace when we touch the Control mode page:

Call Trace:
 [<ffffffff812ea0d2>] dump_stack+0x63/0x81
 [<ffffffff81079cfb>] __warn+0xcb/0xf0
 [<ffffffff81079e2d>] warn_slowpath_null+0x1d/0x20
 [<ffffffffa00f51b0>] ata_eh_finish+0xe0/0xf0 [libata]
 [<ffffffffa00fb830>] sata_pmp_error_handler+0x640/0xa50 [libata]
 [<ffffffffa00470ed>] ahci_error_handler+0x1d/0x70 [libahci]
 [<ffffffffa00f55f0>] ata_scsi_port_error_handler+0x430/0x770 [libata]
 [<ffffffffa00eff8d>] ? ata_scsi_cmd_error_handler+0xdd/0x160 [libata]
 [<ffffffffa00f59d7>] ata_scsi_error+0xa7/0xf0 [libata]
 [<ffffffffa00913ba>] scsi_error_handler+0xaa/0x560 [scsi_mod]
 [<ffffffffa0091310>] ? scsi_eh_get_sense+0x180/0x180 [scsi_mod]
 [<ffffffff81098eb8>] kthread+0xd8/0xf0
 [<ffffffff815d913f>] ret_from_fork+0x1f/0x40
 [<ffffffff81098de0>] ? kthread_worker_fn+0x170/0x170
---[ end trace 8b7501047e928a17 ]---

Removed the unnecessary code and let ata_scsi_translate() do the job.

Also, since ata_mselect_control() has no ATA command to send to the
device, ata_scsi_mode_select_xlat() should return 1 for it, so that
ata_scsi_translate() will finish early to avoid ata_qc_issue().
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

ata_mselect_*() would initialize a char array for storing a copy of
the current mode page. However, char could be signed char. In that
case, bytes larger than 127 would be converted to negative number.

For example, 0xff from def_control_mpage[] would become -1. This
prevented ata_mselect_control() from working at all, since when it
did the read-only bits check, there would always be a mismatch.
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

`changeable` is the "version" of mode page requested by the user.
It will be less confusing/misleading if we do not check it
"together" with the setting bits of the drive.

Not to mention that we currently have ata_mselect_*() implemented
in a way that each of them will serve exclusively a particular bit
on each page. The old style will hence make the condition look even
more unnecessarily arcane if the ata_msense_*() is reflecting more
than one bit.
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Due to PCI subsystem behaviour, unloading AHCI driver will disable
MSI and enable INTx. When HBA supports MSIx or Multiple MSI, Driver's
irq handler doesn't clear GHC.IS register. It works well when reading or
writing data and GHC.IS is always non-zero. But when unloading driver
(or any other operation which causes disable MSIx and enable INTx), PCI
 subsystem uses config write(Rx04.bit10) to enable INTx. Because
GHC.IS is non-zero, HBA will falsely assume some port needs interrupt
service. Then it asserts INTx. To make things worse, when AHCI controller
shares the same interrupt pin with other PCI device, that PCI device's ISR
will be called and nobody de-asserts previous INTx.
This patch clears GHC.IS in ahci_port_stop() even when using MSIx or
MMSI to prevent this case. It ensures GHC.IS is zero before PCI subsystem
enables INTx.

tj: Minor updates to the comment.
Signed-off-by: NRaymond Pang <raymond_rule@hotmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

There is a error message within devm_ioremap_resource
already, so remove the dev_err call to avoid redundant
error message.
Signed-off-by: NWei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: NTejun Heo <tj@kernel.org>

This avoid the need to always translate between the two in ata_prot_flags
and generally cleans up the taskfile protocol usage.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

The only caller can just check for !ata_is_data instead.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Since 34b48db6 ("block: remove artifical max_hw_sectors cap"),
max_sectors is no longer limited to BLK_DEF_MAX_SECTORS and LITE-ON
CX1-JB256-HP keeps timing out with higher max_sectors.  Revert it to
the previous value.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: dgerasimov@gmail.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=121671
Cc: stable@vger.kernel.org # v3.19+
Fixes: 34b48db6 ("block: remove artifical max_hw_sectors cap")
Signed-off-by: NTejun Heo <tj@kernel.org>

The reset_all variable name is misleading as this bit is also applicable to
open, close, and finish actions. So rename that variable to "all" and remove
the unnecessary mask operation that's already done earlier.
Signed-off-by: NDamien Le Moal <damien.lemoal@hgst.com>
[hch: split from the previous patch]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

The subcommand for NCQ NON-DATA must be specified in the feature
(low byte), not the high-order count byte.  Also make sure to properly
cast the all bit to a u16 before shiting it by 8 to avoid undefined
behavior.
Signed-off-by: NDamien Le Moal <damien.lemoal@hgst.com>
[hch: split the original patch into two, updated changelog]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Include reporting options when translating REPORT ZONES commmand to
ATA NCQ, and make sure we only look at the actually specified bits
in the CDB for the options.
Signed-off-by: NDamien Le Moal <damien.lemoal@hgst.com>
[hch: update patch description]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Add a new taskfile protocol ATA_PROT_NCQ_NODATA to handle
ATA NCQ NO-DATA commands correctly.
And fixup ata_scsi_zbc_out_xlat() to use it.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Some taskfile protocol values where missing in ata_eh_link_report().
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

The taskfile protocol is a numeric value, and can not be ORed.  Currently
this is harmless as the protocol is always zeroed before, but if it ever
has a non-zero value the ORing would create incorrect results.
Signed-off-by: NHannes Reinecke <hare@suse.de>
[hch: updated patch description]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Use accessor functions instead of the raw value.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Currently libata statically allows only 1-block (512-byte) payload
for each TRIM command. Each payload can carry 64 TRIM ranges since
each range requires 8 bytes.

It is silly to keep doing the calculation (512 / 8) in different
places. Hence, define the new ATA_MAX_TRIM_RNUM for the result.
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Currently if a WRITE SAME (16) command is issued to the SATL with
"number of blocks" that is larger than the "Maximum write same length"
(which is the maximum number of blocks per TRIM command allowed in
libata, currently 65535 * 512 / 8 blocks), the SATL will accept the
command and translate it to a TRIM command with the upper limit.

However, according to SBC (as of sbc4r11.pdf), the "device server"
should terminate the command with "Invalid field in CDB" in that case.
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

To make it consistent with the recently added ata_mselect_control().
We probably shouldn't have the word "mode" in its name anyway, since
that's not the case for other ata_msense_*() / ata_mselect_*() either.
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

The bit should always be set to 1 when the requested version of
page is "changeable" because we've made it so in ata_mselect_control().
Also, it should always be set to 1 if ATA_DFLAG_D_SENSE is set (when
the requested version of page is "current" or "default").
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

According to the HPT366 data sheet, PCI config space dword 0x40-0x43
bits 11:8 specify the primary drive cmd_high_time, however,
currently just 3 bits of the 4 are being used because the mask
is 0x700 and not 0x0f00.  Fix the mask, allowing for the 40MHz clock
to be detected.
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

The comment suggests we should be having an SPC-3 version descriptor
but the 0260h is the code for "SPC-2 (no version claimed)". Correct
it to 0300h so that it has the "SPC-3 (no version claimed)" descriptor.

Note that we are claiming SPC-3 version compatibility in the VERSION
field of the standard INQUIRY data. Therefore, I assume the typo was
on the code but not on the comment.
Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Avoid performance bottleneck when being SCSI pass-through'd to
virtual machines with other OSes (e.g. Windows) via virtio-scsi
and scsi-block in qemu.

Ref.: https://github.com/YanVugenfirer/kvm-guest-drivers-windows/issues/63Signed-off-by: NTom Yan <tom.ty89@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>