Certain versions of Sandisk x400 firmware can hang under extremely
heavly load of large I/Os for prolonged periods of time. Newer /
current versions work fine, and should be used where possible. Where
not possible, this quirk ensures that I/O requests are limited to 128k
to avoids the bug, even under extreme load. Since MAXPHYS is 128k,
only users with custom kernels are at risk on the older firmware.
Once all known users of the older firmware have upgraded, this quirk
will be removed.
Sponsored by: Netflix, Inc.
- Add ADA_Q_NO_TRIM quirk to be used with the device that falsely advertise TRIM support
- Add ADA_Q_NO_TRIM entry for KingDian S200 SSD
PR: 222802
Submitted by: Bertrand Petit <bsdpr@phoe.frmug.org>
MFC after: 1 week
Add a counter for the LBAs, Ranges and hardware commands so that we
can provide additional color to the statistics we provide to vendors.
Sponsored by: Netflix, Inc
The idea was to get the uncontroversial mechanical change out of the way,
then get the meatier functional changes reviewed subsequently. I had not
realized that the immediately adjacent issue was addressed in a different
direction in r334506 (see Warner's guidance in D15592).
Discussion continues, trying to determine if there is a secondary issue
still[1] and how best to fix it. With 12-related activities coming up,
while that is ongoing, just take this back for now.
[1]: Shutdown-time eventhandler events fire normally during panic's reboot
path. Driver callbacks that attempt to issue and wait on interrupt-
completed IO may never complete, hanging the system. This is particularly
obnoxious in the shutdown/panic path, as the debugger cannot be entered
anymore and the hang prevents reboot restoring availability.
(There's nothing CAM-specific about this problem -- any shutdown
event-triggered driver could do something like this during panic. But most
NICs, etc. don't try to send spin-down commands at shutdown. ;-))
Discussed with: imp, markj
No functional change.
Note that this change is careful to set the CCB header xflags after
foo_fill_bar() routines, which generally zero existing flags. An earlier
version of this patch mistakenly set the flag before the fill routines.
Submitted by: Scott Ferris <sferris AT isilon.com>, jhibbits@
Reviewed by: bdrewery@, markj@, and non-committer FreeBSD contributor Anton Rang
Sponsored by: Dell EMC Isilon
It's likely that the header was needed in the past for swi(9).
But now that code does not use swi(9) or any other interfaces defined
in sys/interrupt.h.
MFC after: 1 week
When a disk disappears and the periph is invalidated, any I/Os that
are pending with the controller can cause a crash when they
complete. Move to holding the softc reference count taken in dastart()
until the I/O is complete rather than only until xpt_action()
returns. (This approach was suggested by Ken Merry.) This extends
the method used in da to ada, nda, and mda.
Sponsored by: Netflix
Submitted by: Chuck Silvers
pointer. It's now unhelpful and misleading for callers to continue to set
it, so bring all callers into conformance. There's no real functional change,
but it makes reading the code a lot less confusing.
Sponsored by: Netflix
kern.cam.{,a,n}da.X.invalidate=1 forces *daX to detach by calling
cam_periph_invalidate on the underlying periph. This is for testing
purposes only. Include only with options CAM_TEST_FAILURE and rename
the former [AN]DA_TEST_FAILURE, and fix nda to compile with it set.
We're using it at work to harden geom and the buffer cache to be
resilient in the face of drive failure. Today, it far too often
results in a panic. While much work was done on SIM initiated removal
for the USB thumnb drive removal work, little has been done for periph
initiated removal. This simulates what *daerror() does for some errors
nicely: we get the same panics with it that we do with failing drives.
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D14581
Introduce flags word to describe the capacities of the peripheral.
First bit will describe if the periph driver allows multiple
outstanding TRIMS to be active in a device.
Modify the I/O scheduler so that the nda driver can queue trims
for a while after the first one arrives. We'll queue until we see
a I/O scheduler tick, then we'll schedule as many TRIMs as allowed
by other factors (currently this is slocts in the NVMe controller).
This mariginally helps the read latency issues we see with reads,
but sets the stage for the nda driver to do TRIM collapsing like the
da and ada drivers do today.
Sponsored by: Netflix
There's no compelling reason to return a cam_status type for this
function and doing so only creates confusion with normal C
coding practices. It's technically an API change, but the periph API
isn't widely used. No efffective change to operation.
Reviewed by: imp, mav, ken
Sponsored by: Netflix
Differential Revision: D14063
from the ada and da dump routines. This avoids difficult locking
problems from needing to be handled. While it might seem like this
would leave the periphs unprotected during dump, they were aleady
at risk of unexpected removal due to the dump functions not
keeping refcount state across the many calls that come in during
a dump. This is an exercise for future work.
Obtained from: Netflix
This reduces noise when kernel is compiled by newer GCC versions,
such as one used by external toolchain ports.
Reviewed by: kib, andrew(sys/arm and sys/arm64), emaste(partial), erj(partial)
Reviewed by: jhb (sys/dev/pci/* sys/kern/vfs_aio.c and sys/kern/kern_synch.c)
Differential Revision: https://reviews.freebsd.org/D10385
This provides a nice wrarpper around the XPT_PATH_INQ ccb creation and
calling.
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D13387
kernel scheduler is stopped, replace the by hand calling of
xpt_polled_action() with it.
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D13388
adagetparams contains a sign-extension error that will cause the sector
count to be incorrectly calculated for ATA disks of >=1TiB that still use
CHS addressing. Disks using LBA48 addressing are unaffected.
Reported by: Coverity
CID: 1007296
Reviewed by: ken
MFC after: 3 weeks
Sponsored by: Spectra Logic Corp
Differential Revision: https://reviews.freebsd.org/D13198
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using misidentified many licenses so this was mostly a manual - error
prone - task.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
Like its predecessor ST8000AS0002, this is a drive-managed SMR drive, but
doesn't declare that in its ATA identify data.
MFC after: 3 weeks
Sponsored by: Spectra Logic Corp
We must send either an IDLE IMMEDIATE or a STANDBY IMMEDIATE to drives
on warm boot so their SMART and other volatile data is
persisted. However, for a warm boot we don't want to send STANDBY
IMMEDIATE to some spinning drives because they will spin down. If
there's a lot of these drives on the system, that can cause a
thundering herd problem at startup time (that in extreme cases causes
timeout in device discovery).
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D12811
To save SMART data and for a drive to understand that it's been nicely
shutdown, we need to send a STANDBY IMMEDIATE. Modify adaspindown to
use a local CCB on the stack. When we're panicing, used
xpt_polled_action rather than cam_periph_runccb so that we can SEND
IMMEDIATE after we've shutdown the scheduler.
Sponsored by: Netflix
Reviewed by: scottl@, gallatin@
Differential Revision: https://reviews.freebsd.org/D12799
The attached patch lets adaasync() set ADA_STATE_WCACHE based on
ADA_FLAG_CAN_WCACHE instead of ADA_FLAG_CAN_RAHEAD.
This fixes a regression introduced in r300207 which changed
the flag names.
PR: 220948
Submitted by: Fabian Keil <fk@fabiankeil.de>
Obtained from: ElectroBSD
MFC after: 1 week
The motivation for this is two-fold.
1. Some old WD SATA disks may appear as if they need to be spun up
when they are already spinning. Those disks would respond with
an error to the spin-up request.
2. Even if we really fail to spin up the disk, we still can try to
proceed to the subsequent phases. If we fail later on, then no
difference. Otherwise we get a chance to communicate with the
disk which is better than completely ignoring it, because a user
can try to recover the disk.
Reviewed by: mav
MFC after: 3 weeks
Differential Revision: https://reviews.freebsd.org/D10896
using a driver-supplied sbuf for printing device discovery
announcements. This helps ensure that messages to the console
will be properly serialized (through sbuf_putbuf) and not be
truncated and interleaved with other messages. The
infrastructure mirrors the existing xpt_announce_periph()
entry point and is opt-in for now. No content or formatting
changes are visible to the operator other than the new coherency.
While here, eliminate the stack usage of the temporary
announcement buffer in some of the drivers. It's moved to the
softc for now, but future work will eliminate it entirely by
making the code flow more linear. Future work will also address
locking so that the sbufs can be dynamically sized.
The scsi_da, scs_cd, scsi_ses, and ata_da drivers are converted
at this point, other drivers can be converted at a later date.
A tunable+sysctl, kern.cam.announce_nosbuf, exists for testing
purposes but will be removed later.
TODO:
Eliminate all of the code duplication and temporary buffers. The
old printf-based methods will be retired, and xpt_announce_periph()
will just be a wrapper that uses a dynamically sized sbuf. This
requires that the register and deregister paths be made malloc-safe,
which they aren't currently.
Sponsored by: Netflix
Under kern.cam we have certain sysctls that are per-device, such as the
ones under kern.cam.ada.[0-9]+.*. Add a "device_index" label annotation
to such sysctls, so that the Prometheus metrics exporter will give all
of those metrics the same name. The device number will be added to the
metric name as the "device_index" label.
Reviewed by: cem
Differential Revision: https://reviews.freebsd.org/D8775
This eventhandler is mainly used by VMs, e.g. Hyper-V, whose disk
controllers share the disks with the simulated ATA controllers.
Submitted by: Hongjiang Zhang <honzhan microsoft com>
Discussed with: mav
MFC after: 1 week
Sponsored by: Microsoft
Differential Revision: https://reviews.freebsd.org/D7693
Uses of commas instead of a semicolons can easily go undetected. The comma
can serve as a statement separator but this shouldn't be abused when
statements are meant to be standalone.
Detected with devel/coccinelle following a hint from DragonFlyBSD.
MFC after: 1 month
per-protocol. This reduces the number scsi symbols references by
cam_xpt significantly, and eliminates all ata / nvme symbols. There's
still some NVME / ATA specific code for dealing with XPT_NVME_IO and
XPT_ATA_IO respectively, and a bunch of scsi-specific code, but this
is progress.
Differential Revision: https://reviews.freebsd.org/D7289
eliminates the need to special case everything in cam_xpt for new
transports. It is now a failure to not have a transport object when
registering the bus as well. You can still, however, create a
transport that's unspecified (XPT_)
Differential Revision: https://reviews.freebsd.org/D7289
In the case where cam_iosched_init() fails, the ada and da softcs were leaked.
Instead, free them.
Reported by: Coverity
CID: 1356039
Sponsored by: EMC / Isilon Storage Division
o Some Samsung drives do not support the ATA READ LOG EXT or READ
LOG DMA EXT commands, despite indicating that they do in their
IDENTIFY data. So, fix this in two ways:
1. Only start the log directory probe (ADA_STATE_LOGDIR) if
the drive claims to be an SMR drive in the first place.
We don't need to do the extra probing for other devices.
This will also serve to prevent problems with other
drives that have the same issue.
2. Add quirks for the two Samsung drives that have been
reported so far (thanks to Oleg Nauman and Alex Petrov).
If there is a reason to do a Read Log later on, we will
know that it doesn't work on these drives.
o Add a quirk entry to mark Seagate Lamarr Drive Managed drives as
drive managed. They don't report this in their Identify data.
sys/cam/ata/ata_da.c:
Add two new quirks:
1. ADA_Q_LOG_BROKEN, for drives that claim to support Read
Log but don't really.
2. ADA_Q_SMR_DM, for drives that are Drive Managed SMR, but
don't report it. This can matter for software that
wants to know when it should make an extra effort to
write sequentially.
Record two Samsung drives that don't support Read Log, and
one Seagate drive that doesn't report that it is a SMR drive.
The Seagate drive is already recorded in the da(4) driver.
We may have to come up with a similar solution in the da(4)
driver for SATA drives that don't properly support Read Log.
In adasetflags(), Dont' set the ADA_FLAG_CAN_LOG bit if the
device has the LOG_BROKEN quirk set. Also, look at the
SMR_DM quirk and set the device type accordingly if it is
actually a drive managed drive.
When deciding whether to go into the LOGDIR probe state,
look to see whether the device claims to be an SMR device.
If not, don't bother with the LOGDIR probe state.
Sponsored by: Spectra Logic
I broke broke the quirk in the ada(4) driver disabling NCQ trim support
in revision 300207. The support flags were set before the quirks were
loaded.
sys/cam/ata/ata_da.c:
Call adasetflags() after loading quirks, so that we'll set the
flags accurately.
Sponsored by: Spectra Logic
