ACS-4 defines a sense data reporting feature set.
This patch implements support for it.

tj: Cosmetic formatting updates.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Viking flash model VRFDFC22048UCHC-TE causes data corruption in MWDMA mode.

Cc: xe-kernel@external.cisco.com
Signed-off-by: NShikha Jain <shikjain@cisco.com>
Signed-off-by: NAnil Veliyankara Madam <aveliyan@cisco.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

The link resume logic uses a 200msec delay while debouncing
the SControl register. The rationale behind that delay is
to accommodate some PHYs that behave badly if their SStatus/
SControl registers are pounded immediately on resume.
The Broadcom STB SATA PHY does not seem to have this issue.
This patch introduces a new link flag that allows platforms
to skip the debounce delay if it isn't needed.
Signed-off-by: NDanesh Petigara <dpetigara@broadcom.com>
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Since msleep() may sleep longer than intended time for values less
than 20ms, this patch allows the use of usleep_range for waits less
that 20ms. usleep_range is a finer precision implementation of
msleep and is designed to be a drop-in replacement for udelay
where a precise sleep/busy-wait is unnecessary.

More details can be found at http://lkml.org/lkml/2007/8/3/250
and in Documentation/timers/timers-howto.txt.

This change has been done to improve the performace in PIO6 mode
which is used by viking flash.

Cc: xe-kernel@external.cisco.com
Signed-off-by: NAnil Veliyankara Madam <aveliyan@cisco.com>
Signed-off-by: NShikha Jain <shikjain@cisco.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

On my machine with single irq AHCI just the PCI id is printed as
description in /proc/interrupts.
I found a related discussion from beginning of this year:
http://www.gossamer-threads.com/lists/linux/kernel/2117335

Seems like 4f37b504 ("libata: Use dev_name() for request_irq() to
distinguish devices") tried to fix displaying a proper interrupt
description for one scenario but broke it for another one.

The mentioned discussion ended in the current situation being
considered as broken but w/o a patch to fix it.

The following patch is based on a proposal in this mail thread.
Now the interrupt is properly described as:
PCI-MSI 512000-edge      ahci[0000:00:1f.2]

By combining both values also the scenario that commit 4f37b504
("libata: Use dev_name() for request_irq() to distinguish devices")
refers to should still be fine. There it should look like this now:
ahci[20100000.ide]

Using managed memory allocation ensures that the irq description
lives at least as long as the interrupt.
Signed-off-by: NHeiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>

The Crucial M500 is known to have issues with queued TRIM commands, the
factory recertified SSDs use a different model number naming convention
which causes them to get ignored by the blacklist.

The new naming convention boils down to: s/Crucial_/FC/
Signed-off-by: NGuillermo A. Amaral <g@maral.me>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

Fix kernel-doc warning in libata-core.c:

Warning(..//drivers/ata/libata-core.c:4763): No description found for parameter 'tag'
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Signed-off-by: NTejun Heo <tj@kernel.org>

This reverts commit fe7173c2.

As implemented, ACS-4 sense reporting for ATA devices bypasses error
diagnosis and handling in libata degrading EH behavior significantly.
Revert the related changes for now.

ATA_ID_COMMAND_SET_3/4 constants are not reverted as they're used by
later changes.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org #v4.1+

This reverts commit a1524f22.

As implemented, ACS-4 sense reporting for ATA devices bypasses error
diagnosis and handling in libata degrading EH behavior significantly.
Revert the related changes for now.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Hannes Reinecke <hare@suse.de>
Cc: stable@vger.kernel.org #v4.1+

A new Micron drive was just announced, once again recycling the first
part of the model string. Add an underscore to the M510/M550 pattern to
avoid picking up the new DC drive.
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTejun Heo <tj@kernel.org>

I have a ST4000DM000 disk. If Linux is booted while the disk is spun down,
the command that sets transfer mode causes the disk to spin up. The
spin-up takes longer than the default 5s timeout, so the command fails and
timeout is reported.

Fix this by increasing the timeout to 15s, which is enough for the disk to
spin up.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: NTejun Heo <tj@kernel.org>

Since no longer limiting max_sectors to BLK_DEF_MAX_SECTORS (commit 34b48db6),
data corruption may occur on ST380013AS drive configured on 82801JI (ICH10 Family)
SATA controller. This patch will allow the driver to limit max_sectors as before

 # cat /sys/block/sdb/queue/max_sectors_kb
 512

I was able to double the max_sectors_kb value up to 16384 on linux-4.2.0-rc2
before seeing corruption, but seems safer to use previous limit. Without this
patch max_sectors_kb will be 32767.

tj: Minor comment update.
Reported-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NDavid Milburn <dmilburn@redhat.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org # v3.19 and later
Fixes: 34b48db6 ("block: remove artifical max_hw_sectors cap")

This device loses blocks, often the partition table area, on trim.
Disable TRIM.
http://pcengines.ch/msata16a.htmSigned-off-by: NArne Fitzenreiter <arne_f@ipfire.org>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

Enabling AA on HP 250GB SATA disk VB0250EAVER causes errors:

[    3.788362] ata3.00: failed to enable AA (error_mask=0x1)
[    3.789243] ata3.00: failed to enable AA (error_mask=0x1)

Add the ATA_HORKAGE_BROKEN_FPDMA_AA for this specific harddisk.

tj: Collected FPDMA_AA entries and updated comment.
Signed-off-by: NAleksei Mamlin <mamlinav@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

Queued TRIM got disabled on Micron M500DC drives thanks to the
"Micron_M500*" pattern we had in place to accommodate the previous
generation of this drive family. Tweak the blacklist entry slightly so
we only disable queued TRIM for the non-DC variants of M500 drives.
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: NTejun Heo <tj@kernel.org>

Just six days after this FIXME was added seven years ago, Sam Ravnborg
added the missing feature (37c514e3 "Add missing init section
definitions"), though it ended up being called __initconst.

Let's use it; better late than never.
Signed-off-by: NRasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: NTejun Heo <tj@kernel.org>

This patch fix a spelling typo found in libata.xml.
It is because libata.xml is generated from comments
in source, I have to fix it in libata-core.c
Signed-off-by: NMasanari Iida <standby24x7@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

We have started seeing SSD firmware updates introduce support for queued
TRIM. Sadly, in most cases this support is completely untested and can
lead to either errors or data corruption.

Add two libata force flags that can be used to either enable or disable
queued TRIM support.
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

The queued TRIM problems appear to be generic to Samsung's firmware and
not tied to a particular model. A recent update to the 840 EVO firmware
introduced the same issue as we saw on 850 Pro.

Blacklist queued TRIM on all 800-series drives while we work this issue
with Samsung.
Reported-by: NGünter Waller <g.wal@web.de>
Reported-by: NSven Köhler <sven.koehler@gmail.com>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: NTejun Heo <tj@kernel.org>

When the LPM policy is set to ATA_LPM_MAX_POWER, the device might
generate a spurious PHY event that cuases errors on the link.
Ignore this event if it occured within 10s after the policy change.

The timeout was chosen observing that on a Dell XPS13 9333 these
spurious events can occur up to roughly 6s after the policy change.

Link: http://lkml.kernel.org/g/3352987.ugV1Ipy7Z5@xps13Signed-off-by: NGabriele Mazzotta <gabriele.mzt@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

This is a preparation commit that will allow to add other criteria
according to which PHY events should be dropped.
Signed-off-by: NGabriele Mazzotta <gabriele.mzt@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

Blacklist queued TRIM on this drive for now.
Reported-by: NStefan Keller <linux-list@zahlenfresser.de>
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
CC: stable@vger.kernel.org
Signed-off-by: NTejun Heo <tj@kernel.org>

Micron has released an updated firmware (MU02) for M510/M550/MX100
drives to fix the issues with queued TRIM. Queued TRIM remains broken on
M500 but is working fine on later drives such as M600 and MX200.

Tweak our blacklist to reflect the above.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=71371Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: NTejun Heo <tj@kernel.org>

Add some tracepoints for ata_qc_issue, ata_qc_complete, and
ata_eh_link_autopsy.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

If NCQ autosense or the sense data reporting feature is enabled
the LBA of the offending command should be stored in the sense
data 'information' field.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

ACS-4 defines a sense data reporting feature set.
This patch implements support for it.
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

SAS controller has its own tag allocation, which doesn't directly match to ATA
tag, so SAS and SATA have different code path for ata tags. Originally we use
port->scsi_host (98bd4be1) to destinguish SAS controller, but libsas set
->scsi_host too, so we can't use it for the destinguish, we add a new flag for
this purpose.

Without this patch, the following oops can happen because scsi-mq uses
a host-wide tag map shared among all devices with some integer tag
values >= ATA_MAX_QUEUE.  These unexpectedly high tag values cause
__ata_qc_from_tag() to return NULL, which is then dereferenced in
ata_qc_new_init().

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000058
  IP: [<ffffffff804fd46e>] ata_qc_new_init+0x3e/0x120
  PGD 32adf0067 PUD 32adf1067 PMD 0
  Oops: 0002 [#1] SMP DEBUG_PAGEALLOC
  Modules linked in: iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi igb
  i2c_algo_bit ptp pps_core pm80xx libsas scsi_transport_sas sg coretemp
  eeprom w83795 i2c_i801
  CPU: 4 PID: 1450 Comm: cydiskbench Not tainted 4.0.0-rc3 #1
  Hardware name: Supermicro X8DTH-i/6/iF/6F/X8DTH, BIOS 2.1b       05/04/12
  task: ffff8800ba86d500 ti: ffff88032a064000 task.ti: ffff88032a064000
  RIP: 0010:[<ffffffff804fd46e>]  [<ffffffff804fd46e>] ata_qc_new_init+0x3e/0x120
  RSP: 0018:ffff88032a067858  EFLAGS: 00010046
  RAX: 0000000000000000 RBX: ffff8800ba0d2230 RCX: 000000000000002a
  RDX: ffffffff80505ae0 RSI: 0000000000000020 RDI: ffff8800ba0d2230
  RBP: ffff88032a067868 R08: 0000000000000201 R09: 0000000000000001
  R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800ba0d0000
  R13: ffff8800ba0d2230 R14: ffffffff80505ae0 R15: ffff8800ba0d0000
  FS:  0000000041223950(0063) GS:ffff88033e480000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
  CR2: 0000000000000058 CR3: 000000032a0a3000 CR4: 00000000000006e0
  Stack:
   ffff880329eee758 ffff880329eee758 ffff88032a0678a8 ffffffff80502dad
   ffff8800ba167978 ffff880329eee758 ffff88032bf9c520 ffff8800ba167978
   ffff88032bf9c520 ffff88032bf9a290 ffff88032a0678b8 ffffffff80506909
  Call Trace:
   [<ffffffff80502dad>] ata_scsi_translate+0x3d/0x1b0
   [<ffffffff80506909>] ata_sas_queuecmd+0x149/0x2a0
   [<ffffffffa0046650>] sas_queuecommand+0xa0/0x1f0 [libsas]
   [<ffffffff804ea544>] scsi_dispatch_cmd+0xd4/0x1a0
   [<ffffffff804eb50f>] scsi_queue_rq+0x66f/0x7f0
   [<ffffffff803e5098>] __blk_mq_run_hw_queue+0x208/0x3f0
   [<ffffffff803e54b8>] blk_mq_run_hw_queue+0x88/0xc0
   [<ffffffff803e5c74>] blk_mq_insert_request+0xc4/0x130
   [<ffffffff803e0b63>] blk_execute_rq_nowait+0x73/0x160
   [<ffffffffa0023fca>] sg_common_write+0x3da/0x720 [sg]
   [<ffffffffa0025100>] sg_new_write+0x250/0x360 [sg]
   [<ffffffffa0025feb>] sg_write+0x13b/0x450 [sg]
   [<ffffffff8032ec91>] vfs_write+0xd1/0x1b0
   [<ffffffff8032ee54>] SyS_write+0x54/0xc0
   [<ffffffff80689932>] system_call_fastpath+0x12/0x17

tj: updated description.

Fixes: 12cb5ce1 ("libata: use blk taging")
Reported-and-tested-by: NTony Battersby <tonyb@cybernetics.com>
Signed-off-by: NShaohua Li <shli@fb.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Basically move the sas ata tag allocation to libata-scsi.c to make it clear
these staffs are just for sas.
Signed-off-by: NShaohua Li <shli@fb.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

libata uses its own tag management which is duplication and the
implementation is poor. And if we switch to blk-mq, tag is build-in.
It's time to switch to generic taging.

The SAS driver has its own tag management, and looks we can't directly
map the host controler tag to SATA tag. So I just bypassed the SAS case.

I changed the code/variable name for the tag management of libata to
make it self contained. Only sas will use it. Later if libsas implements
its tag management, the tag management code in libata can be deleted
easily.

Cc: Jens Axboe <axboe@fb.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: NShaohua Li <shli@fb.com>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@fb.com>

Ronny reports: https://bugzilla.kernel.org/show_bug.cgi?id=87101
    "Since commit 8a4aeec8 "libata/ahci: accommodate tag ordered
    controllers" the access to the harddisk on the first SATA-port is
    failing on its first access. The access to the harddisk on the
    second port is working normal.

    When reverting the above commit, access to both harddisks is working
    fine again."

Maintain tag ordered submission as the default, but allow sata_sil24 to
continue with the old behavior.

Cc: <stable@vger.kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Reported-by: NRonny Hegewald <Ronny.Hegewald@online.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Remove the function ata_do_simple_cmd() that is not used anywhere.

This was partially found by using a static code analysis program called cppcheck.
Signed-off-by: NRickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: NTejun Heo <tj@kernel.org>

As defined, the DRAT (Deterministic Read After Trim) and RZAT (Return
Zero After Trim) flags in the ATA Command Set are unreliable in the
sense that they only define what happens if the device successfully
executed the DSM TRIM command. TRIM is only advisory, however, and the
device is free to silently ignore all or parts of the request.

In practice this renders the DRAT and RZAT flags completely useless and
because the results are unpredictable we decided to disable discard in
MD for 3.18 to avoid the risk of data corruption.

Hardware vendors in the real world obviously need better guarantees than
what the standards bodies provide. Unfortuntely those guarantees are
encoded in product requirements documents rather than somewhere we can
key off of them programatically. So we are compelled to disabling
discard_zeroes_data for all devices unless we explicitly have data to
support whitelisting them.

This patch whitelists SSDs from a few of the main vendors. None of the
whitelists are based on written guarantees. They are purely based on
empirical evidence collected from internal and external users that have
tested or qualified these drives in RAID deployments.

The whitelist is only meant as a starting point and is by no means
comprehensive:

   - All intel SSD models except for 510
   - Micron M5?0/M600
   - Samsung SSDs
   - Seagate SSDs
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

Add new ATA device type for ZAC devices.
Acked-by: NChristoph Hellwig <hch@lst.de>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NTejun Heo <tj@kernel.org>

lib/glob.c provides a new glob_match() function, with arguments in
(pattern, string) order.  It replaced a private function with arguments
in (string, pattern) order, but I didn't swap the call site...

The result was the entire ATA blacklist was effectively disabled.

The lesson for today is "I f***ed up *how* badly *how* many months ago?",
er, I mean "Nobody Tests RC Kernels On Legacy Hardware".

This was not a subtle break, but it made it through an entire RC
cycle unreported, presumably because all the people doing testing
have full-featured hardware.

(FWIW, the reason for the argument swap was because fnmatch() does it that
way, and for a while implementing a full fnmatch() was being considered.)

Fixes: 428ac5fc (libata: Use glob_match from lib/glob.c)
Reported-by: NSteven Honeyman <stevenhoneyman@gmail.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=71371#c21Signed-off-by: NGeorge Spelvin <linux@horizon.com>
Cc: <stable@vger.kernel.org> # 3.17
Tested-by: NSteven Honeyman <stevenhoneyman@gmail.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

The return value is not used by callers of these functions nor
by uses of all macros so change the functions to return void.
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NTejun Heo <tj@kernel.org>

Use dev_name() instead of driver name for request_irq().
This will help to distinguish between multiple identical devices.

Before:
 CPU0
 5:      34425  clps711x-intc   5  pata_of_platform
 6:       6778  clps711x-intc   6  pata_of_platform

After:
 CPU0
 5:       2182  clps711x-intc   5  20000000.ide
 6:      11024  clps711x-intc   6  20100000.ide
Signed-off-by: NAlexander Shiyan <shc_work@mail.ru>
Signed-off-by: NTejun Heo <tj@kernel.org>

Crucial M550 may cause data corruption on queued trims and is
blacklisted.  The pattern used for it fails to match 1TB one as the
capacity section will be four chars instead of three.  Widen the
pattern.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NCharles Reiss <woggling@gmail.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=81071
Cc: stable@vger.kernel.org

The function may be useful for other drivers, so export it.  (Suggested
by Tejun Heo.)

Note that I inverted the return value of glob_match; returning true on
match seemed to make more sense.
Signed-off-by: NGeorge Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

1871ee13 ("libata: support the ata host which implements a queue
depth less than 32") directly used ata_port->scsi_host->can_queue from
ata_qc_new() to determine the number of tags supported by the host;
unfortunately, SAS controllers doing SATA don't initialize ->scsi_host
leading to the following oops.

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000058
 IP: [<ffffffff814e0618>] ata_qc_new_init+0x188/0x1b0
 PGD 0
 Oops: 0002 [#1] SMP
 Modules linked in: isci libsas scsi_transport_sas mgag200 drm_kms_helper ttm
 CPU: 1 PID: 518 Comm: udevd Not tainted 3.16.0-rc6+ #62
 Hardware name: Intel Corporation S2600CO/S2600CO, BIOS SE5C600.86B.02.02.0002.122320131210 12/23/2013
 task: ffff880c1a00b280 ti: ffff88061a000000 task.ti: ffff88061a000000
 RIP: 0010:[<ffffffff814e0618>]  [<ffffffff814e0618>] ata_qc_new_init+0x188/0x1b0
 RSP: 0018:ffff88061a003ae8  EFLAGS: 00010012
 RAX: 0000000000000001 RBX: ffff88000241ca80 RCX: 00000000000000fa
 RDX: 0000000000000020 RSI: 0000000000000020 RDI: ffff8806194aa298
 RBP: ffff88061a003ae8 R08: ffff8806194a8000 R09: 0000000000000000
 R10: 0000000000000000 R11: ffff88000241ca80 R12: ffff88061ad58200
 R13: ffff8806194aa298 R14: ffffffff814e67a0 R15: ffff8806194a8000
 FS:  00007f3ad7fe3840(0000) GS:ffff880627620000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000058 CR3: 000000061a118000 CR4: 00000000001407e0
 Stack:
  ffff88061a003b20 ffffffff814e96e1 ffff88000241ca80 ffff88061ad58200
  ffff8800b6bf6000 ffff880c1c988000 ffff880619903850 ffff88061a003b68
  ffffffffa0056ce1 ffff88061a003b48 0000000013d6e6f8 ffff88000241ca80
 Call Trace:
  [<ffffffff814e96e1>] ata_sas_queuecmd+0xa1/0x430
  [<ffffffffa0056ce1>] sas_queuecommand+0x191/0x220 [libsas]
  [<ffffffff8149afee>] scsi_dispatch_cmd+0x10e/0x300
  [<ffffffff814a3bc5>] scsi_request_fn+0x2f5/0x550
  [<ffffffff81317613>] __blk_run_queue+0x33/0x40
  [<ffffffff8131781a>] queue_unplugged+0x2a/0x90
  [<ffffffff8131ceb4>] blk_flush_plug_list+0x1b4/0x210
  [<ffffffff8131d274>] blk_finish_plug+0x14/0x50
  [<ffffffff8117eaa8>] __do_page_cache_readahead+0x198/0x1f0
  [<ffffffff8117ee21>] force_page_cache_readahead+0x31/0x50
  [<ffffffff8117ee7e>] page_cache_sync_readahead+0x3e/0x50
  [<ffffffff81172ac6>] generic_file_read_iter+0x496/0x5a0
  [<ffffffff81219897>] blkdev_read_iter+0x37/0x40
  [<ffffffff811e307e>] new_sync_read+0x7e/0xb0
  [<ffffffff811e3734>] vfs_read+0x94/0x170
  [<ffffffff811e43c6>] SyS_read+0x46/0xb0
  [<ffffffff811e33d1>] ? SyS_lseek+0x91/0xb0
  [<ffffffff8171ee29>] system_call_fastpath+0x16/0x1b
 Code: 00 00 00 88 50 29 83 7f 08 01 19 d2 83 e2 f0 83 ea 50 88 50 34 c6 81 1d 02 00 00 40 c6 81 17 02 00 00 00 5d c3 66 0f 1f 44 00 00 <89> 14 25 58 00 00 00

Fix it by introducing ata_host->n_tags which is initialized to
ATA_MAX_QUEUE - 1 in ata_host_init() for SAS controllers and set to
scsi_host_template->can_queue in ata_host_register() for !SAS ones.
As SAS hosts are never registered, this will give them the same
ATA_MAX_QUEUE - 1 as before.  Note that we can't use
scsi_host->can_queue directly for SAS hosts anyway as they can go
higher than the libata maximum.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NMike Qiu <qiudayu@linux.vnet.ibm.com>
Reported-by: NJesse Brandeburg <jesse.brandeburg@gmail.com>
Reported-by: NPeter Hurley <peter@hurleysoftware.com>
Reported-by: NPeter Zijlstra <peterz@infradead.org>
Tested-by: NAlexey Kardashevskiy <aik@ozlabs.ru>
Fixes: 1871ee13 ("libata: support the ata host which implements a queue depth less than 32")
Cc: Kevin Hao <haokexin@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: stable@vger.kernel.org

The sata on fsl mpc8315e is broken after the commit 8a4aeec8
("libata/ahci: accommodate tag ordered controllers"). The reason is
that the ata controller on this SoC only implement a queue depth of
16. When issuing the commands in tag order, all the commands in tag
16 ~ 31 are mapped to tag 0 unconditionally and then causes the sata
malfunction. It makes no senses to use a 32 queue in software while
the hardware has less queue depth. So consider the queue depth
implemented by the hardware when requesting a command tag.

Fixes: 8a4aeec8 ("libata/ahci: accommodate tag ordered controllers")
Cc: stable@vger.kernel.org
Signed-off-by: NKevin Hao <haokexin@gmail.com>
Acked-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NTejun Heo <tj@kernel.org>