Some host controllers fail to atomically transition an endpoint to the
Running state on a doorbell ring and enter a hidden "Restarting" state,
which looks very much like Stopped, with the important difference that
it will spontaneously transition to Running anytime soon.
A Stop Endpoint command queued in the Restarting state typically fails
with Context State Error and the completion handler sees the Endpoint
Context State as either still Stopped or already Running. Even a case
of Halted was observed, when an error occurred right after the restart.
The Halted state is already recovered from by resetting the endpoint.
The Running state is handled by retrying Stop Endpoint.
The Stopped state was recognized as a problem on NEC controllers and
worked around also by retrying, because the endpoint soon restarts and
then stops for good. But there is a risk: the command may fail if the
endpoint is "stopped for good" already, and retries will fail forever.
The possibility of this was not realized at the time, but a number of
cases were discovered later and reproduced. Some proved difficult to
deal with, and it is outright impossible to predict if an endpoint may
fail to ever start at all due to a hardware bug. One such bug (albeit
on ASM3142, not on NEC) was found to be reliably triggered simply by
toggling an AX88179 NIC up/down in a tight loop for a few seconds.
An endless retries storm is quite nasty. Besides putting needless load
on the xHC and CPU, it causes URBs never to be given back, paralyzing
the device and connection/disconnection logic for the whole bus if the
device is unplugged. User processes waiting for URBs become unkillable,
drivers and kworker threads lock up and xhci_hcd cannot be reloaded.
For peace of mind, impose a timeout on Stop Endpoint retries in this
case. If they don't succeed in 100ms, consider the endpoint stopped
permanently for some reason and just give back the unlinked URBs. This
failure case is rare already and work is under way to make it rarer.
Start this work today by also handling one simple case of race with
Reset Endpoint, because it costs just two lines to implement.
Fixes: fd9d55d190 ("xhci: retry Stop Endpoint on buggy NEC controllers")
CC: stable@vger.kernel.org
Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-32-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The function is modified to return 'void' instead of an integer since it
invariably returns '0'. Additionally, multiple functions which only
return xhci_td_cleanup() are also refactored to return void.
This change eliminates the need for callers to handle a return value that
does not convey meaningful information and improve code readability, as it
becomes immediately clear that the function does not produce a significant
output.
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-29-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Old names:
* start_seg - last_trb_seg
* first_trb - last_trb
New names:
* start_seg - end_seg
* start_trb - end_trb
A Transfer Descriptor (TD) in the xhci driver is a data structure that
represents a single transaction to be performed by the USB host controller.
This transaction is defined by TRBs from 'start_trb' in 'start_seg' to
'end_trb' in 'end_seg'.
The terms "start" and "end" were chosen over "first" and "last" for ease
of searching within the codebase. The ring structure uses 'first_seg' and
'last_seg', while the TD structure uses 'start_seg' and 'end_seg'.
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-24-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Since commit f8f80be501 ("xhci: Use soft retry to recover faster from
transaction errors"), unplugging USB device while enumeration results in
errors like this:
[ 364.855321] xhci_hcd 0000:0b:00.0: ERROR Transfer event for disabled endpoint slot 5 ep 2
[ 364.864622] xhci_hcd 0000:0b:00.0: @0000002167656d70 67f03000 00000021 0c000000 05038001
[ 374.934793] xhci_hcd 0000:0b:00.0: Abort failed to stop command ring: -110
[ 374.958793] xhci_hcd 0000:0b:00.0: xHCI host controller not responding, assume dead
[ 374.967590] xhci_hcd 0000:0b:00.0: HC died; cleaning up
[ 374.973984] xhci_hcd 0000:0b:00.0: Timeout while waiting for configure endpoint command
Seems that Etorn xHCI host can not perform Soft Retry correctly, apply
XHCI_NO_SOFT_RETRY quirk to disable Soft Retry and then issue is gone.
This patch depends on commit a4a251f8c2 ("usb: xhci: do not perform
Soft Retry for some xHCI hosts").
Fixes: f8f80be501 ("xhci: Use soft retry to recover faster from transaction errors")
Cc: stable@vger.kernel.org
Signed-off-by: Kuangyi Chiang <ki.chiang65@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-21-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Performing a stability stress test on a USB3.0 2.5G ethernet adapter
results in errors like this:
[ 91.441469] r8152 2-3:1.0 eth3: get_registers -71
[ 91.458659] r8152 2-3:1.0 eth3: get_registers -71
[ 91.475911] r8152 2-3:1.0 eth3: get_registers -71
[ 91.493203] r8152 2-3:1.0 eth3: get_registers -71
[ 91.510421] r8152 2-3:1.0 eth3: get_registers -71
The r8152 driver will periodically issue lots of control-IN requests
to access the status of ethernet adapter hardware registers during
the test.
This happens when the xHCI driver enqueue a control TD (which cross
over the Link TRB between two ring segments, as shown) in the endpoint
zero's transfer ring. Seems the Etron xHCI host can not perform this
TD correctly, causing the USB transfer error occurred, maybe the upper
driver retry that control-IN request can solve problem, but not all
drivers do this.
| |
-------
| TRB | Setup Stage
-------
| TRB | Link
-------
-------
| TRB | Data Stage
-------
| TRB | Status Stage
-------
| |
To work around this, the xHCI driver should enqueue a No Op TRB if
next available TRB is the Link TRB in the ring segment, this can
prevent the Setup and Data Stage TRB to be breaked by the Link TRB.
Check if the XHCI_ETRON_HOST quirk flag is set before invoking the
workaround in xhci_queue_ctrl_tx().
Fixes: d0e96f5a71 ("USB: xhci: Control transfer support.")
Cc: stable@vger.kernel.org
Signed-off-by: Kuangyi Chiang <ki.chiang65@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-20-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Sometimes the hub driver does not recognize the USB device connected
to the external USB2.0 hub when the system resumes from S4.
After the SetPortFeature(PORT_RESET) request is completed, the hub
driver calls the HCD reset_device callback, which will issue a Reset
Device command and free all structures associated with endpoints
that were disabled.
This happens when the xHCI driver issue a Reset Device command to
inform the Etron xHCI host that the USB device associated with a
device slot has been reset. Seems that the Etron xHCI host can not
perform this command correctly, affecting the USB device.
To work around this, the xHCI driver should obtain a new device slot
with reference to commit 651aaf36a7 ("usb: xhci: Handle USB transaction
error on address command"), which is another way to inform the Etron
xHCI host that the USB device has been reset.
Add a new XHCI_ETRON_HOST quirk flag to invoke the workaround in
xhci_discover_or_reset_device().
Fixes: 2a8f82c4ce ("USB: xhci: Notify the xHC when a device is reset.")
Cc: stable@vger.kernel.org
Signed-off-by: Kuangyi Chiang <ki.chiang65@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-19-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
A ring consists of a list of segments, each containing a specific number of
TRBs. The xhci driver allocates and initializes ring segments and TRBs in
the same functions. This combined allocation and initialization process
leads to an issue where, after hibernation (S4 state), the xhci driver
frees all its memory and re-creates the rings, segments, and TRBs from
scratch.
Move all default ring segment initialization into function
xhci_initialize_ring_segments(). This function can be called to
reinitialize a ring without freeing and reallocating it.
Since xhci_alloc_segments_for_ring() no longer initializes segment TRBs,
xhci_initialize_ring_segments() is added to xhci_ring_expansion(). This
results in the last segment of the source ring having the 'LINK_TOGGLE'
bit set. Therefore, if the last source ring segment is not the last in
the destination ring, the 'LINK_TOGGLE' bit must be cleared.
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-17-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Prepare for splitting ring segments allocation and initialization by
reworking the xhci_link_segments() function. Segment linking and ring type
checks are moved out of xhci_link_segments(), and the function is renamed
to "xhci_set_link_trb()".
The goal is to keep ring linking within xhci_alloc_segments_for_ring() and
move initialization into a separate function.
Additionally, reorder and simplify xhci_set_link_trb() for better
readability.
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-16-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The segment list is only relevant within the context of the ring.
Thus, it is more logical to pass the ring itself when freeing all segments
from a ring, rather than passing the ring list.
Rename the function to "xhci_ring_segments_free" to align with the naming
convention of xhci_segment_free().
To make the freeing process more intuitive, free segments sequentially
from start to end (i.e., 0, 1, 2, 3, ...) instead of freeing the first
segment last (i.e., 1, 2, 3, ... 0).
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-14-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The TRB cycle bit indicates TRB ownership by the Host Controller (HC) or
Host Controller Driver (HCD). New rings are initialized with 'cycle_state'
equal to one, and all its TRBs' cycle bits are set to zero. When handling
ring expansion, set the source ring cycle bits to the same value as the
destination ring.
Move the cycle bit setting from xhci_segment_alloc() to xhci_link_rings(),
and remove the 'cycle_state' argument from xhci_initialize_ring_info().
The xhci_segment_alloc() function uses kzalloc_node() to allocate segments,
ensuring that all TRB cycle bits are initialized to zero.
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-12-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don't trace ring pointers every time driver increases enqueue pointer
after queuing a TRB, or dequeue pointer after handling an event.
These xhci_inc_deq: and xhci_inc_enq: trace entries fill up the trace and
provides little useful info now that the TRB DMA address is printed with
the TRB itself.
Only trace ring during xhci_inc_enq() and xhci_inc_deq() in case we move
to a new ring segment.
Also don't show both segment and TRB addess in trace.
Segment is just TRB with 0xfff masked off.
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-7-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The DMA address of a queued TRB is essential when looking at traces as
both transfer events and command completion events refer to the command
or transfer based on its DMA address.
Previously the TRB address was figured out from xhci_inc_enq and
xhci_inc_deq trace entries seen after queuing or handlong a TRB.
Now that DMA address is shown in TRB tracing we can get rid of most of the
xhci_inc_enq and xhci_inc_deq traces thus decreasing trace size.
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-6-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This function is supposed to sum the lengths of all transfer TRBs in
a TD up to a point, but it starts summing at the current dequeue since
it only ever gets called on the first pending TD.
This won't work when there are cancelled TDs at the beginning of the
ring. The function tries to exclude No-Ops from the count, but not all
cancelled TDs are No-Op'ed - not those the HW stopped on.
The absolutely obvious fix is to start counting at the TD's first TRB.
And remove the now-useless 'ring' parameter, and 'xhci' too.
Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20241106101459.775897-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Some PCIe-to-USB controllers such as TI's TUSB73x0 3.0 xHCI host
controller supports controlling the PWRONx polarity via the USB control
register (E0h). Add support for device tree property
ti,pwron-active-high which indicates PWRONx to be active high and
configure the E0h register accordingly. This enables the software
control for the TUSB73x0's PWRONx outputs with an inverted polarity from
the default configuration which could be used as USB EN signals for the
other hubs or devices.
Signed-off-by: Parth Pancholi <parth.pancholi@toradex.com>
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://lore.kernel.org/r/20241029072444.8827-3-francesco@dolcini.it
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Pull misc fixes from Andrew Morton:
"17 hotfixes. 9 are cc:stable. 13 are MM and 4 are non-MM.
The usual collection of singletons - please see the changelogs"
* tag 'mm-hotfixes-stable-2024-11-03-10-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify()
mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats
mm, mmap: limit THP alignment of anonymous mappings to PMD-aligned sizes
mm: shrinker: avoid memleak in alloc_shrinker_info
.mailmap: update e-mail address for Eugen Hristev
vmscan,migrate: fix page count imbalance on node stats when demoting pages
mailmap: update Jarkko's email addresses
mm: allow set/clear page_type again
nilfs2: fix potential deadlock with newly created symlinks
Squashfs: fix variable overflow in squashfs_readpage_block
kasan: remove vmalloc_percpu test
tools/mm: -Werror fixes in page-types/slabinfo
mm, swap: avoid over reclaim of full clusters
mm: fix PSWPIN counter for large folios swap-in
mm: avoid VM_BUG_ON when try to map an anon large folio to zero page.
mm/codetag: fix null pointer check logic for ref and tag
mm/gup: stop leaking pinned pages in low memory conditions
Pull dmaengine fixes from Vinod Koul:
- TI driver fix to set EOP for cyclic BCDMA transfers
- sh rz-dmac driver fix for handling config with zero address
* tag 'dmaengine-fix-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine:
dmaengine: ti: k3-udma: Set EOP for all TRs in cyclic BCDMA transfer
dmaengine: sh: rz-dmac: handle configs where one address is zero
Pull driver core revert from Greg KH:
"Here is a single driver core revert for 6.12-rc6. It reverts a change
that came in -rc1 that was supposed to resolve a reported problem, but
caused another one, so revert it for now so that we can get this all
worked out properly in 6.13.
The revert has been in linux-next all week with no reported issues"
* tag 'driver-core-6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
Revert "driver core: Fix uevent_show() vs driver detach race"
Pull USB / Thunderbolt fixes from Greg KH:
"Here are some small USB and Thunderbolt driver fixes for 6.12-rc6 that
have been sitting in my tree this week. Included in here are the
following:
- thunderbolt driver fixes for reported issues
- USB typec driver fixes
- xhci driver fixes for reported problems
- dwc2 driver revert for a broken change
- usb phy driver fix
- usbip tool fix
All of these have been in linux-next this week with no reported
issues"
* tag 'usb-6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
usb: typec: tcpm: restrict SNK_WAIT_CAPABILITIES_TIMEOUT transitions to non self-powered devices
usb: phy: Fix API devm_usb_put_phy() can not release the phy
usb: typec: use cleanup facility for 'altmodes_node'
usb: typec: fix unreleased fwnode_handle in typec_port_register_altmodes()
usb: typec: qcom-pmic-typec: fix missing fwnode removal in error path
usb: typec: qcom-pmic-typec: use fwnode_handle_put() to release fwnodes
usb: acpi: fix boot hang due to early incorrect 'tunneled' USB3 device links
Revert "usb: dwc2: Skip clock gating on Broadcom SoCs"
xhci: Fix Link TRB DMA in command ring stopped completion event
xhci: Use pm_runtime_get to prevent RPM on unsupported systems
usbip: tools: Fix detach_port() invalid port error path
thunderbolt: Honor TMU requirements in the domain when setting TMU mode
thunderbolt: Fix KASAN reported stack out-of-bounds read in tb_retimer_scan()
Patch series "mm: multi-gen LRU: Have secondary MMUs participate in
MM_WALK".
Today, the MM_WALK capability causes MGLRU to clear the young bit from
PMDs and PTEs during the page table walk before eviction, but MGLRU does
not call the clear_young() MMU notifier in this case. By not calling this
notifier, the MM walk takes less time/CPU, but it causes pages that are
accessed mostly through KVM / secondary MMUs to appear younger than they
should be.
We do call the clear_young() notifier today, but only when attempting to
evict the page, so we end up clearing young/accessed information less
frequently for secondary MMUs than for mm PTEs, and therefore they appear
younger and are less likely to be evicted. Therefore, memory that is
*not* being accessed mostly by KVM will be evicted *more* frequently,
worsening performance.
ChromeOS observed a tab-open latency regression when enabling MGLRU with a
setup that involved running a VM:
Tab-open latency histogram (ms)
Version p50 mean p95 p99 max
base 1315 1198 2347 3454 10319
mglru 2559 1311 7399 12060 43758
fix 1119 926 2470 4211 6947
This series replaces the final non-selftest patchs from this series[1],
which introduced a similar change (and a new MMU notifier) with KVM
optimizations. I'll send a separate series (to Sean and Paolo) for the
KVM optimizations.
This series also makes proactive reclaim with MGLRU possible for KVM
memory. I have verified that this functions correctly with the selftest
from [1], but given that that test is a KVM selftest, I'll send it with
the rest of the KVM optimizations later. Andrew, let me know if you'd
like to take the test now anyway.
[1]: https://lore.kernel.org/linux-mm/20240926013506.860253-18-jthoughton@google.com/
This patch (of 2):
The removed stats, MM_LEAF_OLD and MM_NONLEAF_TOTAL, are not very helpful
and become more complicated to properly compute when adding
test/clear_young() notifiers in MGLRU's mm walk.
Link: https://lkml.kernel.org/r/20241019012940.3656292-1-jthoughton@google.com
Link: https://lkml.kernel.org/r/20241019012940.3656292-2-jthoughton@google.com
Fixes: bd74fdaea1 ("mm: multi-gen LRU: support page table walks")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: James Houghton <jthoughton@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: David Stevens <stevensd@google.com>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Pull misc driver fixes from Greg KH:
"Here are some small char/misc/iio fixes for 6.12-rc6 that resolve
some reported issues. Included in here are the following:
- small IIO driver fixes for many reported issues
- mei driver fix for a suddenly much reported issue for an "old"
issue.
- MAINTAINERS update for a developer who has moved companies and
forgot to update their old entry.
All of these have been in linux-next this week with no reported
issues"
* tag 'char-misc-6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
mei: use kvmalloc for read buffer
MAINTAINERS: add netup_unidvb maintainer
iio: dac: Kconfig: Fix build error for ltc2664
iio: adc: ad7124: fix division by zero in ad7124_set_channel_odr()
staging: iio: frequency: ad9832: fix division by zero in ad9832_calc_freqreg()
docs: iio: ad7380: fix supply for ad7380-4
iio: adc: ad7380: fix supplies for ad7380-4
iio: adc: ad7380: add missing supplies
iio: adc: ad7380: use devm_regulator_get_enable_read_voltage()
dt-bindings: iio: adc: ad7380: fix ad7380-4 reference supply
iio: light: veml6030: fix microlux value calculation
iio: gts-helper: Fix memory leaks for the error path of iio_gts_build_avail_scale_table()
iio: gts-helper: Fix memory leaks in iio_gts_build_avail_scale_table()
