can handle it, and add the code to add it to the FIS that's sent to
the drive. The mvs driver is the only other ATA driver in the system,
and its hardware doesn't appear to support setting the Auxiliary
register.
Differential Revision: https://reviews.freebsd.org/D5598
as before. The common scheduling bits have moved from inline code in
each of the CAM periph drivers into a library that implements the
default scheduling.
In addition, a number of rate-limiting and I/O preference options can
be enabled by adding CAM_IOSCHED_NETFLIX to your config file. A number
of extra stats are also maintained. CAM_IOSCHED_NETFLIX isn't on by
default because it uses a separate BIO_READ and BIO_WRITE queue, so
doesn't honor BIO_ORDERED between these two types of operations. We
already didn't honor it for BIO_DELETE, and we don't depend on
BIO_ORDERED between reads and writes anywhere in the system (it is
currently used with BIO_FLUSH in ZFS to make sure some writes are
complete before others start and as a poor-man's soft dependency in
one place in UFS where we won't be issuing READs until after the
operation completes). However, out of an abundance of caution, it
isn't enabled by default.
Plus, this also brings in NCQ TRIM support for those SSDs that support
it. A black list is also provided for known rogues that use NCQ trim
as an excuse to corrupt the drive. It was difficult to separate out
into a separate commit.
This code has run in production at Netflix for over a year now.
Sponsored by: Netflix, Inc
Differential Revision: https://reviews.freebsd.org/D4609
Changes introduced to AHCI code adding support for MSI-x
caused interrupt storm on Alpine boards.
This is unintended behaviour so added quirk to omit this functionality.
Reviewed by: mav
Submitted by: Marcin Mazurek <mma@semihalf.com>
Obtained from: Semihalf
Sponsored by: Annapurna Labs
Differential Revision: https://reviews.freebsd.org/D4301
ahci.c had one signed long, which was passed into rman, rather than u_long.
After the switch of rman_res_t from size u_long to size uintmax_t, the sign
extension caused ranges to get messed up, and ahcich* to not attach.
There may be more signed longs used in this way, which will be fixed as they're
reported.
Reported by: pho
Summary:
Migrate to using the semi-opaque type rman_res_t to specify rman resources. For
now, this is still compatible with u_long.
This is step one in migrating rman to use uintmax_t for resources instead of
u_long.
Going forward, this could feasibly be used to specify architecture-specific
definitions of resource ranges, rather than baking a specific integer type into
the API.
This change has been broken out to facilitate MFC'ing drivers back to 10 without
breaking ABI.
Reviewed By: jhb
Sponsored by: Alex Perez/Inertial Computing
Differential Revision: https://reviews.freebsd.org/D5075
typically memory mapped bus, for example on the AMD Opteron A1100 the AHCI
device is mapped in the CPUs address space, and not through a PCI
controller.
Further work is needed for this to work with ACPI as this is expected to be
common on ARMv8 servers.
Reviewed by: mav, mmel
Obtained from: mmel, ABT Systems Ltd
Relnotes: yes
Sponsored by: SoftIron Inc
Differential Revision: https://reviews.freebsd.org/D4269
On ARM, we must ensure proper interdevice write ordering.
The AHCI interrupt status register must be updated in HW before
registers in interrupt controller.
Unfortunately, only way how we can do it is readback.
Discussed with: mav
Approved by: kib (mentor)
Differential Revision: https://reviews.freebsd.org/D4240
- Allocate resources for MSI-X table and PBA if necessary
- Add function ahci_free_mem() to free all resources
Reviewed by: jhb, mav
Obtained from: Semihalf
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D3009
The Allwinner SoC has an AHCI device on its internal main bus rather
than the PCI bus. This SoC is somewhat underdocumented, and its SATA
controller is no exception. The methods to support this chip were
harvested from the Linux Allwinner SDK, and then constants invented to
describe what's going on based on low-level constants contained in the
SATA standard and guess work.
This SoC requires a specific AHCI channel setup in order to start the
operations on the channel properly.
Clock setup and AHCI channel setup idea came from NetBSD.
Tested on Cubieboard 2 and Banana pi (and attachment on Cubieboard by
Pratik Singhal).
Differential Revision: https://reviews.freebsd.org/D737
Submitted by: imp
Reviewed by: imp, ganbold, mav, andrew
According to report, some recent unrelated changes in the driver triggered
timeouts when testing for absent port multiplier. Cause of this behavior
channge is unclear, but since these chips are old, rare and buggy, it is
easier to just disable port multiplier support, same as done in Linux.
Reported by: bar
MFC after: 3 days
Overview:
* implemented quirk for forcing SATA interface enable
* restore value to status register - this enables link autonegotiation
Modifications:
* devid:vendorid field
* quirk for forcing PI setting (BIOS is doing that on PC-like systems)
* write to capabilites field to enable phy link initialization
Submitted by: Wojciech Macek <wma@semihalf.com>
Reviewed by: imp, mav
Obtained from: Semihalf
In 10.1-RELEASE the default number of MSI vectors used was changed from one
to as many vectors as the HW supports.
This change resulted in an ahci timeouts regression when running on AMD
SB7x0/SB8x0/SB9x0 hardware, so its now limited to 1 MSI by default using
this new quirk.
MFC after: 2 weeks
Sponsored by: Multiplay
Previously ahci_attach returned a hard coded ENXIO instead of the value
from ahci_setup_interrupt. This is effectively a NOOP change as currently
ahci_setup_interrupt only ever returns 0 or ENXIO, so just there to protect
against any future changes to that.
Differential Revision: D838
MFC after: 2 weeks
Sponsored by: Multiplay
This prevents the possiblity of any overruns on the statically allocated
struct irqs field.
Differential Revision: D838
MFC after: 2 weeks
X-MFC-With: r276012
Sponsored by: Multiplay
Previously, any timeout value for which (timeout * hz) will overflow the
signed integer, will give weird results, since callout(9) routines will
convert negative values of ticks to '1'. For unsigned integer overflow we
will get sufficiently smaller timeout values than expected.
Switch from callout_reset, which requires conversion to int based ticks
to callout_reset_sbt to avoid this.
Also correct isci to correctly resolve ccb timeout.
This was based on the original work done by Eygene Ryabinkin
<rea@freebsd.org> back in 5 Aug 2011 which used a macro to help avoid
the overlow.
Differential Revision: https://reviews.freebsd.org/D1157
Reviewed by: mav, davide
MFC after: 1 month
Sponsored by: Multiplay
It was found that VirtualBox' AHCI does not allow nterrupt to be cleared
before the interrupt status register is read, causing interrupt storm.
AHCI specification allows to skip this register use when multi-vector MSI
is enabled and so interrupting port is known. For single-vector MSI that
is not stated explicitly, but if the port is only one, it is obviously
known too.
Previously it was possible for issues e.g. use after free, to result
from processing the done queue while not holding the channel lock.
While this should never happen in practice, unexpected code flows
which result in two threads processing from the same queue may
be possible.
We now use a local STAILQ to prevent this ever being an issue.
Sponsored by: Multiplay
For controllers with only one port (like PCIe or M.2 SSDs) interrupt can
come from only one source, and skipping read saves few percents of CPU time.
MFC after: 1 month
H/W donated by: I/O Switch
I gave up to update list of Marvell chips that require this quirk.
The final nail was growing number of PCIe/M.2 SSDs where Marvell chips
have PCI IDs of different vendors.
MFC after: 1 week
H/W donated by: I/O Switch
PCI IDs into quirks, which mostly fit (though you'd get no argument
from me that AHCI_Q_SATA1_UNIT0 is oddly specific). Set these quirks
in the PCI attachment. Make some shared functions public so that PCI
and possibly other bus attachments can use them.
The split isn't perfect yet, but it is functional. The split will be
perfected as other bus attachments for AHCI are written.
Sponsored by: Netflix
Reviewed by: kan, mav
Differential Revision: https://reviews.freebsd.org/D699
initializing 16. Initialize all 20 so we don't send garbage in the
Auxiliary register. The SATA standard mandates a 5 dword length for
the Host to Device FIS.
Sponsored by: Netflix
Using unmapped BIOs causes failure inside bus_dmamap_sync, since
this function requires valid MVA address, which is not present
if mapping is not set up.
Submitted by: Wojciech Macek <wma@semihalf.com>
Obtained from: Semihalf
shifts into the sign bit. Instead use (1U << 31) which gets the
expected result.
This fix is not ideal as it assumes a 32 bit int, but does fix the issue
for most cases.
A similar change was made in OpenBSD.
Discussed with: -arch, rdivacky
Reviewed by: cperciva
reduce lock congestion and improve SMP scalability of the SCSI/ATA stack,
preparing the ground for the coming next GEOM direct dispatch support.
Replace big per-SIM locks with bunch of smaller ones:
- per-LUN locks to protect device and peripheral drivers state;
- per-target locks to protect list of LUNs on target;
- per-bus locks to protect reference counting;
- per-send queue locks to protect queue of CCBs to be sent;
- per-done queue locks to protect queue of completed CCBs;
- remaining per-SIM locks now protect only HBA driver internals.
While holding LUN lock it is allowed (while not recommended for performance
reasons) to take SIM lock. The opposite acquisition order is forbidden.
All the other locks are leaf locks, that can be taken anywhere, but should
not be cascaded. Many functions, such as: xpt_action(), xpt_done(),
xpt_async(), xpt_create_path(), etc. are no longer require (but allow) SIM
lock to be held.
To keep compatibility and solve cases where SIM lock can't be dropped, all
xpt_async() calls in addition to xpt_done() calls are queued to completion
threads for async processing in clean environment without SIM lock held.
Instead of single CAM SWI thread, used for commands completion processing
before, use multiple (depending on number of CPUs) threads. Load balanced
between them using "hash" of the device B:T:L address.
HBA drivers that can drop SIM lock during completion processing and have
sufficient number of completion threads to efficiently scale to multiple
CPUs can use new function xpt_done_direct() to avoid extra context switch.
Make ahci(4) driver to use this mechanism depending on hardware setup.
Sponsored by: iXsystems, Inc.
MFC after: 2 months
extra read from PxCI/PxSACT registers. If only NCQ commands are running, we
don't really need PxCI. If only non-NCQ commands are running we don't need
PxSACT. Mixed set may happen only on controllers with FIS-based switching
when port multiplier is attached, and then we have to read both registers.
MFC after: 1 month
every architecture's busdma_machdep.c. It is done by unifying the
bus_dmamap_load_buffer() routines so that they may be called from MI
code. The MD busdma is then given a chance to do any final processing
in the complete() callback.
The cam changes unify the bus_dmamap_load* handling in cam drivers.
The arm and mips implementations are updated to track virtual
addresses for sync(). Previously this was done in a type specific
way. Now it is done in a generic way by recording the list of
virtuals in the map.
Submitted by: jeff (sponsored by EMC/Isilon)
Reviewed by: kan (previous version), scottl,
mjacob (isp(4), no objections for target mode changes)
Discussed with: ian (arm changes)
Tested by: marius (sparc64), mips (jmallet), isci(4) on x86 (jharris),
amd64 (Fabian Keil <freebsd-listen@fabiankeil.de>)
I am not exactly sure about the naming due to lack of specs on AMD site,
but it is better to have some identification then none at all.
MFC after: 1 month
subdevice ahciem. Emulate SEMB SES device from AHCI LED interface to expose
it to users in form of ses(4) CAM device. If we ever see AHCI controllers
supporting SES of SAF-TE over I2C as described by specification, they should
fit well into this new picture.
Sponsored by: iXsystems, Inc.
Return PROTO_ATA protocol in response to XPT_PATH_INQ.
smartmontools uses it to identify ATA devices and I don't know any other
place now where it is important. It could probably use XPT_GDEV_TYPE
instead for more accurate protocol information, but let it live for now.
Reported by: matthew
MFC after: 3 days
until transport will do some probe actions (at least soft reset).
Make ATA/SATA SIMs to not report bogus and confusing PROTO_ATA protocol.
Make ATA/SATA transport to fill that gap by reporting protocol to SIM with
XPT_SET_TRAN_SETTINGS and patching XPT_GET_TRAN_SETTINGS results if needed.
to allow drivers to handle request completion directly without passing
them to the CAM SWI thread removing extra context switch.
Modify all ATA/SATA drivers to use them.
Reviewed by: gibbs, ken
MFC after: 2 weeks
interface supported by mvs(4) are 88SX, while AHCI-like chips are 88SE.
PR: kern/165271
Submitted by: Jia-Shiun Li <jiashiun@gmail.com>
MFC after: 1 week
to known AHCI-capable chips (AMD/NVIDIA), configured for legacy emulation.
Enabled by default to get additional performance and functionality of AHCI
when it can't be enabled by BIOS. Can be disabled to honor BIOS settings if
needed for some reason.
MFC after: 1 month
to kern/subr_bus.c. Simplify this function so that it no longer
depends on malloc() to execute. Identify a few other places where
it makes sense to use device_delete_all_children().
MFC after: 1 week
completely skipping them, create ahcich devices for them to allocate unit
numbers, but mark them as disabled to prevent driver probe and attach.
Last time some BIOSes tend to report unused channels as "not implemented".
This change makes ahcichX devices numbering consistent, independently of
connected disks. It makes per-channel driver hints usable and CAM devices
wiring possible on such systems.
Mac with this chipset does not initialize AHCI mode unless it is started
from EFI loader. However, legacy ATA mode works.
Submitted by: jkim@ (original version)
Approved by: re (kib)
MFC after: 1 week
Slot field of the PxCMD register may point to an empty command slot.
That breaks command timeout detection logic, making impossible to find
what command actually caused timeout, and leading to infinite wait.
Workaround that by checking whether pointed command slot is really used
and can timeout in its time. And if not, fallback to the dumb algorithm
used with FBS -- let all commands to time out and then fail all of them.
Approved by: re (kib)
MFC after: 1 week
without waiting for device readiness (or at least not updating FIS receive
area in time). To workaround that, special quirk was added earlier to wait
for the FIS receive area update. But it was found that under same PCI ID
0x91231b4b and revision 0x11 there are two completely different chip
versions (firmware?): HBA and RAID. The problem is that RAID version in
some cases, such as hot-plug, does not update FIS receive area at all!
To workaround that, differentiate the chip versions by their capabilities,
and, if RAID version found, skip FIS receive area update waiting and read
device signature from the PxSIG register instead. This method doesn't work
for HBA version when PMP attached, so keep using previous workaround there.
(SEMB) is unable to communicate to Storage Enclosure Processor (SEP), in
response to hard and soft resets it should among other things return value
0x7F in Status register. The weird side is that it means DRQ bit set, which
tells that reset request is not completed. It would be fine if SEMB was the
only device on port. But if SEMB connected to PMP or built into it, it may
block access to other devices sharing same SATA port.
Make some tunings/fixes to soft-reset handling to workaround the issue:
- ahci(4): request CLO on the port after soft reset to ignore DRQ bit;
- siis(4): gracefully reinitialize port after soft reset timeout (hardware
doesn't detect reset request completion in this case);
- mvs(4): if PMP is used, send dummy soft-reset to the PMP port to make it
clear DRQ bit for us.
For now this makes quirks in ata_pmp.c, hiding SEMB ports of SiI3726/SiI4726
PMPs, less important. Further, if hardware permit, I hope to implement real
SEMB support.
