Friedrich Weber reported a kernel crash problem and bisected to commit
81ada09cc2 ("blk-flush: reuse rq queuelist in flush state machine").
The root cause is that we use "list_move_tail(&rq->queuelist, pending)"
in the PREFLUSH/POSTFLUSH sequences. But rq->queuelist.next == xxx since
it's popped out from plug->cached_rq in __blk_mq_alloc_requests_batch().
We don't initialize its queuelist just for this first request, although
the queuelist of all later popped requests will be initialized.
Fix it by changing to use "list_add_tail(&rq->queuelist, pending)" so
rq->queuelist doesn't need to be initialized. It should be ok since rq
can't be on any list when PREFLUSH or POSTFLUSH, has no move actually.
Please note the commit 81ada09cc2 ("blk-flush: reuse rq queuelist in
flush state machine") also has another requirement that no drivers would
touch rq->queuelist after blk_mq_end_request() since we will reuse it to
add rq to the post-flush pending list in POSTFLUSH. If this is not true,
we will have to revert that commit IMHO.
This updated version adds "list_del_init(&rq->queuelist)" in flush rq
callback since the dm layer may submit request of a weird invalid format
(REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH), which causes double list_add
if without this "list_del_init(&rq->queuelist)". The weird invalid format
problem should be fixed in dm layer.
Reported-by: Friedrich Weber <f.weber@proxmox.com>
Closes: https://lore.kernel.org/lkml/14b89dfb-505c-49f7-aebb-01c54451db40@proxmox.com/
Closes: https://lore.kernel.org/lkml/c9d03ff7-27c5-4ebd-b3f6-5a90d96f35ba@proxmox.com/
Fixes: 81ada09cc2 ("blk-flush: reuse rq queuelist in flush state machine")
Cc: Christoph Hellwig <hch@lst.de>
Cc: ming.lei@redhat.com
Cc: bvanassche@acm.org
Tested-by: Friedrich Weber <f.weber@proxmox.com>
Signed-off-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240608143115.972486-1-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For zoned block devices using zone write plugging, an rcu_barrier() call
is needed in disk_free_zone_resources() to synchronize freeing of zone
write plugs and the destrution of the mempool used to allocate the
plugs. The barrier call does slow down a little teardown of zoned block
devices but should not affect teardown of regular block devices or zoned
block devices that do not use zone write plugging (e.g. zoned DM devices
that do not require zone append emulation).
Modify disk_free_zone_resources() to return early if we do not have a
mempool to start with, that is, if the device does not use zone write
plugging. This avoids the costly rcu_barrier() and speeds up disk
teardown.
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: dd291d77cc ("block: Introduce zone write plugging")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20240607002126.104227-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Clang static checker (scan-build) warning:
block/sed-opal.c:line 317, column 3
Value stored to 'ret' is never read.
Fix this problem by returning the error code when keyring_search() failed.
Otherwise, 'key' will have a wrong value when 'kerf' stores the error code.
Fixes: 3bfeb61256 ("block: sed-opal: keyring support for SED keys")
Signed-off-by: Su Hui <suhui@nfschina.com>
Link: https://lore.kernel.org/r/20240611073659.429582-1-suhui@nfschina.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is a couple of outdated addresses that are still visible
in the Git history, add them to .mailmap.
While at it, replace one in the comment.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When an I2C adapter acts only as a slave, it should not claim to
support I2C master capabilities.
Fixes: 5b6d721b26 ("i2c: designware: enable SLAVE in platform module")
Signed-off-by: Jean Delvare <jdelvare@suse.de>
Cc: Luis Oliveira <lolivei@synopsys.com>
Cc: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Jan Dabros <jsd@semihalf.com>
Cc: Andi Shyti <andi.shyti@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Tested-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
After recent changes in intel_pstate, global.turbo_disabled is only set
at the initialization time and never changed. However, it turns out
that on some systems the "turbo disabled" bit in MSR_IA32_MISC_ENABLE,
the initial state of which is reflected by global.turbo_disabled, can be
flipped later and there should be a way to take that into account (other
than checking that MSR every time the driver runs which is costly and
useless overhead on the vast majority of systems).
For this purpose, notice that before the changes in question,
store_no_turbo() contained a turbo_is_disabled() check that was used
for updating global.turbo_disabled if the "turbo disabled" bit in
MSR_IA32_MISC_ENABLE had been flipped and that functionality can be
restored. Then, users will be able to reset global.turbo_disabled
by writing 0 to no_turbo which used to work before on systems with
flipping "turbo disabled" bit.
This guarantees the driver state to remain in sync, but READ_ONCE()
annotations need to be added in two places where global.turbo_disabled
is accessed locklessly, so modify the driver to make that happen.
Fixes: 0940f1a801 ("cpufreq: intel_pstate: Do not update global.turbo_disabled after initialization")
Closes: https://lore.kernel.org/linux-pm/bf3ebf1571a4788e97daf861eb493c12d42639a3.camel@xry111.site
Suggested-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Reported-by: Xi Ruoyao <xry111@xry111.site>
Tested-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Based on grepping through the source code this driver appears to be
missing a call to drm_atomic_helper_shutdown() at system shutdown
time. Among other things, this means that if a panel is in use that it
won't be cleanly powered off at system shutdown time.
The fact that we should call drm_atomic_helper_shutdown() in the case
of OS shutdown/restart comes straight out of the kernel doc "driver
instance overview" in drm_drv.c.
This driver users the component model and shutdown happens in the base
driver. The "drvdata" for this driver will always be valid if
shutdown() is called and as of commit 2a07396828
("drm/atomic-helper: drm_atomic_helper_shutdown(NULL) should be a
noop") we don't need to confirm that "drm" is non-NULL.
Suggested-by: Maxime Ripard <mripard@kernel.org>
Reviewed-by: Maxime Ripard <mripard@kernel.org>
Reviewed-by: Fei Shao <fshao@chromium.org>
Tested-by: Fei Shao <fshao@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240611102744.v2.1.I2b014f90afc4729b6ecc7b5ddd1f6dedcea4625b@changeid
Based on grepping through the source code, this driver appears to be
missing a call to drm_atomic_helper_shutdown() at system shutdown time.
This is important because drm_atomic_helper_shutdown() will cause
panels to get disabled cleanly which may be important for their power
sequencing. Future changes will remove any custom powering off in
individual panel drivers so the DRM drivers need to start getting this
right.
The fact that we should call drm_atomic_helper_shutdown() in the case of
OS shutdown comes straight out of the kernel doc "driver instance
overview" in drm_drv.c.
[geert: shmob_drm_remove() already calls drm_atomic_helper_shutdown]
Suggested-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20230901164111.RFT.15.Iaf638a1d4c8b3c307a6192efabb4cbb06b195f15@changeid
[geert: s/drm_helper_force_disable_all/drm_atomic_helper_shutdown/]
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Sui Jingfeng <sui.jingfeng@linux.dev>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/17c6a5a668e5975f871b77fb1fca6711a0799d9e.1718176895.git.geert+renesas@glider.be
When multiple streams are in use, multiple TDs might be in flight when
an endpoint is stopped. We need to issue a Set TR Dequeue Pointer for
each, to ensure everything is reset properly and the caches cleared.
Change the logic so that any N>1 TDs found active for different streams
are deferred until after the first one is processed, calling
xhci_invalidate_cancelled_tds() again from xhci_handle_cmd_set_deq() to
queue another command until we are done with all of them. Also change
the error/"should never happen" paths to ensure we at least clear any
affected TDs, even if we can't issue a command to clear the hardware
cache, and complain loudly with an xhci_warn() if this ever happens.
This problem case dates back to commit e9df17eb14 ("USB: xhci: Correct
assumptions about number of rings per endpoint.") early on in the XHCI
driver's life, when stream support was first added.
It was then identified but not fixed nor made into a warning in commit
674f8438c1 ("xhci: split handling halted endpoints into two steps"),
which added a FIXME comment for the problem case (without materially
changing the behavior as far as I can tell, though the new logic made
the problem more obvious).
Then later, in commit 94f339147f ("xhci: Fix failure to give back some
cached cancelled URBs."), it was acknowledged again.
[Mathias: commit 94f339147f ("xhci: Fix failure to give back some cached
cancelled URBs.") was a targeted regression fix to the previously mentioned
patch. Users reported issues with usb stuck after unmounting/disconnecting
UAS devices. This rolled back the TD clearing of multiple streams to its
original state.]
Apparently the commit author was aware of the problem (yet still chose
to submit it): It was still mentioned as a FIXME, an xhci_dbg() was
added to log the problem condition, and the remaining issue was mentioned
in the commit description. The choice of making the log type xhci_dbg()
for what is, at this point, a completely unhandled and known broken
condition is puzzling and unfortunate, as it guarantees that no actual
users would see the log in production, thereby making it nigh
undebuggable (indeed, even if you turn on DEBUG, the message doesn't
really hint at there being a problem at all).
It took me *months* of random xHC crashes to finally find a reliable
repro and be able to do a deep dive debug session, which could all have
been avoided had this unhandled, broken condition been actually reported
with a warning, as it should have been as a bug intentionally left in
unfixed (never mind that it shouldn't have been left in at all).
> Another fix to solve clearing the caches of all stream rings with
> cancelled TDs is needed, but not as urgent.
3 years after that statement and 14 years after the original bug was
introduced, I think it's finally time to fix it. And maybe next time
let's not leave bugs unfixed (that are actually worse than the original
bug), and let's actually get people to review kernel commits please.
Fixes xHC crashes and IOMMU faults with UAS devices when handling
errors/faults. Easiest repro is to use `hdparm` to mark an early sector
(e.g. 1024) on a disk as bad, then `cat /dev/sdX > /dev/null` in a loop.
At least in the case of JMicron controllers, the read errors end up
having to cancel two TDs (for two queued requests to different streams)
and the one that didn't get cleared properly ends up faulting the xHC
entirely when it tries to access DMA pages that have since been unmapped,
referred to by the stale TDs. This normally happens quickly (after two
or three loops). After this fix, I left the `cat` in a loop running
overnight and experienced no xHC failures, with all read errors
recovered properly. Repro'd and tested on an Apple M1 Mac Mini
(dwc3 host).
On systems without an IOMMU, this bug would instead silently corrupt
freed memory, making this a security bug (even on systems with IOMMUs
this could silently corrupt memory belonging to other USB devices on the
same controller, so it's still a security bug). Given that the kernel
autoprobes partition tables, I'm pretty sure a malicious USB device
pretending to be a UAS device and reporting an error with the right
timing could deliberately trigger a UAF and write to freed memory, with
no user action.
[Mathias: Commit message and code comment edit, original at:]
https://lore.kernel.org/linux-usb/20240524-xhci-streams-v1-1-6b1f13819bea@marcan.st/
Fixes: e9df17eb14 ("USB: xhci: Correct assumptions about number of rings per endpoint.")
Fixes: 94f339147f ("xhci: Fix failure to give back some cached cancelled URBs.")
Fixes: 674f8438c1 ("xhci: split handling halted endpoints into two steps")
Cc: stable@vger.kernel.org
Cc: security@kernel.org
Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20240611120610.3264502-5-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
As described in commit 8f873c1ff4 ("xhci: Blacklist using streams on the
Etron EJ168 controller"), EJ188 have the same issue as EJ168, where Streams
do not work reliable on EJ188. So apply XHCI_BROKEN_STREAMS quirk to EJ188
as well.
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/20240611120610.3264502-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
As described in commit c877b3b2ad ("xhci: Add reset on resume quirk for
asrock p67 host"), EJ188 have the same issue as EJ168, where completely
dies on resume. So apply XHCI_RESET_ON_RESUME quirk to EJ188 as well.
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/20240611120610.3264502-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The transferred length is set incorrectly for cancelled bulk
transfer TDs in case the bulk transfer ring stops on the last transfer
block with a 'Stop - Length Invalid' completion code.
length essentially ends up being set to the requested length:
urb->actual_length = urb->transfer_buffer_length
Length for 'Stop - Length Invalid' cases should be the sum of all
TRB transfer block lengths up to the one the ring stopped on,
_excluding_ the one stopped on.
Fix this by always summing up TRB lengths for 'Stop - Length Invalid'
bulk cases.
This issue was discovered by Alan Stern while debugging
https://bugzilla.kernel.org/show_bug.cgi?id=218890, but does not
solve that bug. Issue is older than 4.10 kernel but fix won't apply
to those due to major reworks in that area.
Tested-by: Pierre Tomon <pierretom+12@ik.me>
Cc: stable@vger.kernel.org # v4.10+
Cc: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20240611120610.3264502-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix an issue where get_write is not used in smb2_set_ea().
Fixes: 6fc0a265e1 ("ksmbd: fix potential circular locking issue in smb2_set_ea()")
Cc: stable@vger.kernel.org
Reported-by: Wang Zhaolong <wangzhaolong1@huawei.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
If the directory name in the root of the share starts with
character like 镜(0x955c) or Ṝ(0x1e5c), it (and anything inside)
cannot be accessed. The leading slash check must be checked after
converting unicode to nls string.
Cc: stable@vger.kernel.org
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
The current cbs parameter depends on speed after uplinking,
which is not needed and will report a configuration error
if the port is not initially connected. The UAPI exposed by
tc-cbs requires userspace to recalculate the send slope anyway,
because the formula depends on port_transmit_rate (see man tc-cbs),
which is not an invariant from tc's perspective. Therefore, we
use offload->sendslope and offload->idleslope to derive the
original port_transmit_rate from the CBS formula.
Fixes: 1f705bc61a ("net: stmmac: Add support for CBS QDISC")
Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/20240608143524.2065736-1-xiaolei.wang@windriver.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TSO currently fails when the skb's gso_type field has more than one bit
set.
TSO packets can be passed from userspace using PF_PACKET, TUNTAP and a
few others, using virtio_net_hdr (e.g., PACKET_VNET_HDR). This includes
virtualization, such as QEMU, a real use-case.
The gso_type and gso_size fields as passed from userspace in
virtio_net_hdr are not trusted blindly by the kernel. It adds gso_type
|= SKB_GSO_DODGY to force the packet to enter the software GSO stack
for verification.
This issue might similarly come up when the CWR bit is set in the TCP
header for congestion control, causing the SKB_GSO_TCP_ECN gso_type bit
to be set.
Fixes: a57e5de476 ("gve: DQO: Add TX path")
Signed-off-by: Joshua Washington <joshwash@google.com>
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Acked-by: Andrei Vagin <avagin@gmail.com>
v2 - Remove unnecessary comments, remove line break between fixes tag
and signoffs.
v3 - Add back unrelated empty line removal.
Link: https://lore.kernel.org/r/20240610225729.2985343-1-joshwash@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP as reported by
checkpatch script.
Fixes: 18ff0bcda6 ("ethtool: add interface to interact with Ethernet Power Equipment")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://lore.kernel.org/r/20240610083426.740660-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The function mpi3mr_qcmd() of the mpi3mr driver is able to indicate to
the HBA if a read or write command directed at an ATA device should be
translated to an NCQ read/write command with the high prioiryt bit set
when the request uses the RT priority class and the user has enabled NCQ
priority through sysfs.
However, unlike the mpt3sas driver, the mpi3mr driver does not define
the sas_ncq_prio_supported and sas_ncq_prio_enable sysfs attributes, so
the ncq_prio_enable field of struct mpi3mr_sdev_priv_data is never
actually set and NCQ Priority cannot ever be used.
Fix this by defining these missing atributes to allow a user to check if
an ATA device supports NCQ priority and to enable/disable the use of NCQ
priority. To do this, lift the function scsih_ncq_prio_supp() out of the
mpt3sas driver and make it the generic SCSI SAS transport function
sas_ata_ncq_prio_supported(). Nothing in that function is hardware
specific, so this function can be used in both the mpt3sas driver and
the mpi3mr driver.
Reported-by: Scott McCoy <scott.mccoy@wdc.com>
Fixes: 023ab2a9b4 ("scsi: mpi3mr: Add support for queue command processing")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240611083435.92961-1-dlemoal@kernel.org
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
In ufshcd_clock_scaling_prepare(), after SCSI layer is blocked,
ufshcd_pending_cmds() is called to check whether there are pending
transactions or not. And only if there are no pending transactions can we
proceed to kickstart the clock scaling sequence.
ufshcd_pending_cmds() traverses over all SCSI devices and calls
sbitmap_weight() on their budget_map. sbitmap_weight() can be broken down
to three steps:
1. Calculate the nr outstanding bits set in the 'word' bitmap.
2. Calculate the nr outstanding bits set in the 'cleared' bitmap.
3. Subtract the result from step 1 by the result from step 2.
This can lead to a race condition as outlined below:
Assume there is one pending transaction in the request queue of one SCSI
device, say sda, and the budget token of this request is 0, the 'word' is
0x1 and the 'cleared' is 0x0.
1. When step 1 executes, it gets the result as 1.
2. Before step 2 executes, block layer tries to dispatch a new request to
sda. Since the SCSI layer is blocked, the request cannot pass through
SCSI but the block layer would do budget_get() and budget_put() to
sda's budget map regardless, so the 'word' has become 0x3 and 'cleared'
has become 0x2 (assume the new request got budget token 1).
3. When step 2 executes, it gets the result as 1.
4. When step 3 executes, it gets the result as 0, meaning there is no
pending transactions, which is wrong.
Thread A Thread B
ufshcd_pending_cmds() __blk_mq_sched_dispatch_requests()
| |
sbitmap_weight(word) |
| scsi_mq_get_budget()
| |
| scsi_mq_put_budget()
| |
sbitmap_weight(cleared)
...
When this race condition happens, the clock scaling sequence is started
with transactions still in flight, leading to subsequent hibernate enter
failure, broken link, task abort and back to back error recovery.
Fix this race condition by quiescing the request queues before calling
ufshcd_pending_cmds() so that block layer won't touch the budget map when
ufshcd_pending_cmds() is working on it. In addition, remove the SCSI layer
blocking/unblocking to reduce redundancies and latencies.
Fixes: 8d077ede48 ("scsi: ufs: Optimize the command queueing code")
Co-developed-by: Can Guo <quic_cang@quicinc.com>
Signed-off-by: Can Guo <quic_cang@quicinc.com>
Signed-off-by: Ziqi Chen <quic_ziqichen@quicinc.com>
Link: https://lore.kernel.org/r/1717754818-39863-1-git-send-email-quic_ziqichen@quicinc.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
For SCSI devices supporting the Command Duration Limits feature set, the
user can enable/disable this feature use through the sysfs device attribute
"cdl_enable". This attribute modification triggers a call to
scsi_cdl_enable() to enable and disable the feature for ATA devices and set
the scsi device cdl_enable field to the user provided bool value. For SCSI
devices supporting CDL, the feature set is always enabled and
scsi_cdl_enable() is reduced to setting the cdl_enable field.
However, for ATA devices, a drive may spin-up with the CDL feature enabled
by default. But the SCSI device cdl_enable field is always initialized to
false (CDL disabled), regardless of the actual device CDL feature
state. For ATA devices managed by libata (or libsas), libata-core always
disables the CDL feature set when the device is attached, thus syncing the
state of the CDL feature on the device and of the SCSI device cdl_enable
field. However, for ATA devices connected to a SAS HBA, the CDL feature is
not disabled on scan for ATA devices that have this feature enabled by
default, leading to an inconsistent state of the feature on the device with
the SCSI device cdl_enable field.
Avoid this inconsistency by adding a call to scsi_cdl_enable() in
scsi_cdl_check() to make sure that the device-side state of the CDL feature
set always matches the scsi device cdl_enable field state. This implies
that CDL will always be disabled for ATA devices connected to SAS HBAs,
which is consistent with libata/libsas initialization of the device.
Reported-by: Scott McCoy <scott.mccoy@wdc.com>
Fixes: 1b22cfb141 ("scsi: core: Allow enabling and disabling command duration limits")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240607012507.111488-1-dlemoal@kernel.org
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Igor Pylypiv <ipylypiv@google.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
PA-RISC systems with PA8800 and PA8900 processors have had problems
with random segmentation faults for many years. Systems with earlier
processors are much more stable.
Systems with PA8800 and PA8900 processors have a large L2 cache which
needs per page flushing for decent performance when a large range is
flushed. The combined cache in these systems is also more sensitive to
non-equivalent aliases than the caches in earlier systems.
The majority of random segmentation faults that I have looked at
appear to be memory corruption in memory allocated using mmap and
malloc.
My first attempt at fixing the random faults didn't work. On
reviewing the cache code, I realized that there were two issues
which the existing code didn't handle correctly. Both relate
to cache move-in. Another issue is that the present bit in PTEs
is racy.
1) PA-RISC caches have a mind of their own and they can speculatively
load data and instructions for a page as long as there is a entry in
the TLB for the page which allows move-in. TLBs are local to each
CPU. Thus, the TLB entry for a page must be purged before flushing
the page. This is particularly important on SMP systems.
In some of the flush routines, the flush routine would be called
and then the TLB entry would be purged. This was because the flush
routine needed the TLB entry to do the flush.
2) My initial approach to trying the fix the random faults was to
try and use flush_cache_page_if_present for all flush operations.
This actually made things worse and led to a couple of hardware
lockups. It finally dawned on me that some lines weren't being
flushed because the pte check code was racy. This resulted in
random inequivalent mappings to physical pages.
The __flush_cache_page tmpalias flush sets up its own TLB entry
and it doesn't need the existing TLB entry. As long as we can find
the pte pointer for the vm page, we can get the pfn and physical
address of the page. We can also purge the TLB entry for the page
before doing the flush. Further, __flush_cache_page uses a special
TLB entry that inhibits cache move-in.
When switching page mappings, we need to ensure that lines are
removed from the cache. It is not sufficient to just flush the
lines to memory as they may come back.
This made it clear that we needed to implement all the required
flush operations using tmpalias routines. This includes flushes
for user and kernel pages.
After modifying the code to use tmpalias flushes, it became clear
that the random segmentation faults were not fully resolved. The
frequency of faults was worse on systems with a 64 MB L2 (PA8900)
and systems with more CPUs (rp4440).
The warning that I added to flush_cache_page_if_present to detect
pages that couldn't be flushed triggered frequently on some systems.
Helge and I looked at the pages that couldn't be flushed and found
that the PTE was either cleared or for a swap page. Ignoring pages
that were swapped out seemed okay but pages with cleared PTEs seemed
problematic.
I looked at routines related to pte_clear and noticed ptep_clear_flush.
The default implementation just flushes the TLB entry. However, it was
obvious that on parisc we need to flush the cache page as well. If
we don't flush the cache page, stale lines will be left in the cache
and cause random corruption. Once a PTE is cleared, there is no way
to find the physical address associated with the PTE and flush the
associated page at a later time.
I implemented an updated change with a parisc specific version of
ptep_clear_flush. It fixed the random data corruption on Helge's rp4440
and rp3440, as well as on my c8000.
At this point, I realized that I could restore the code where we only
flush in flush_cache_page_if_present if the page has been accessed.
However, for this, we also need to flush the cache when the accessed
bit is cleared in ptep_clear_flush_young to keep things synchronized.
The default implementation only flushes the TLB entry.
Other changes in this version are:
1) Implement parisc specific version of ptep_get. It's identical to
default but needed in arch/parisc/include/asm/pgtable.h.
2) Revise parisc implementation of ptep_test_and_clear_young to use
ptep_get (READ_ONCE).
3) Drop parisc implementation of ptep_get_and_clear. We can use default.
4) Revise flush_kernel_vmap_range and invalidate_kernel_vmap_range to
use full data cache flush.
5) Move flush_cache_vmap and flush_cache_vunmap to cache.c. Handle
VM_IOREMAP case in flush_cache_vmap.
At this time, I don't know whether it is better to always flush when
the PTE present bit is set or when both the accessed and present bits
are set. The later saves flushing pages that haven't been accessed,
but we need to flush in ptep_clear_flush_young. It also needs a page
table lookup to find the PTE pointer. The lpa instruction only needs
a page table lookup when the PTE entry isn't in the TLB.
We don't atomically handle setting and clearing the _PAGE_ACCESSED bit.
If we miss an update, we may miss a flush and the cache may get corrupted.
Whether the current code is effectively atomic depends on process control.
When CONFIG_FLUSH_PAGE_ACCESSED is set to zero, the page will eventually
be flushed when the PTE is cleared or in flush_cache_page_if_present. The
_PAGE_ACCESSED bit is not used, so the problem is avoided.
The flush method can be selected using the CONFIG_FLUSH_PAGE_ACCESSED
define in cache.c. The default is 0. I didn't see a large difference
in performance.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: <stable@vger.kernel.org> # v6.6+
Signed-off-by: Helge Deller <deller@gmx.de>
When reworking the range checking for get_user(), the get_user_8() case
on 32-bit wasn't zeroing the high register. (The jump to bad_get_user_8
was accidentally dropped.) Restore the correct error handling
destination (and rename the jump to using the expected ".L" prefix).
While here, switch to using a named argument ("size") for the call
template ("%c4" to "%c[size]") as already used in the other call
templates in this file.
Found after moving the usercopy selftests to KUnit:
# usercopy_test_invalid: EXPECTATION FAILED at
lib/usercopy_kunit.c:278
Expected val_u64 == 0, but
val_u64 == -60129542144 (0xfffffff200000000)
Closes: https://lore.kernel.org/all/CABVgOSn=tb=Lj9SxHuT4_9MTjjKVxsq-ikdXC4kGHO4CfKVmGQ@mail.gmail.com
Fixes: b19b74bc99 ("x86/mm: Rework address range check in get_user() and put_user()")
Reported-by: David Gow <davidgow@google.com>
Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Tested-by: David Gow <davidgow@google.com>
Link: https://lore.kernel.org/all/20240610210213.work.143-kees%40kernel.org
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZmb/TwAKCRCRxhvAZXjc
om/QAQCaXBrLRBLS0lvpmGfyFhBC+N+hNLEw5bzA0Dkm39nCUQEAwaMCWYzzSLMK
SfRAqKYkfQKSSHIGOq63ThZWkuFIMgQ=
=Z5xj
-----END PGP SIGNATURE-----
Merge tag 'vfs-6.10-rc4.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs fixes from Christian Brauner:
"Misc:
- Restore debugfs behavior of ignoring unknown mount options
- Fix kernel doc for netfs_wait_for_oustanding_io()
- Fix struct statx comment after new addition for this cycle
- Fix a check in find_next_fd()
iomap:
- Fix data zeroing behavior when an extent spans the block that
contains i_size
- Restore i_size increasing in iomap_write_end() for now to avoid
stale data exposure on xfs with a realtime device
Cachefiles:
- Remove unneeded fdtable.h include
- Improve trace output for cachefiles_obj_{get,put}_ondemand_fd()
- Remove requests from the request list to prevent accessing already
freed requests
- Fix UAF when issuing restore command while the daemon is still
alive by adding an additional reference count to requests
- Fix UAF by grabbing a reference during xarray lookup with xa_lock()
held
- Simplify error handling in cachefiles_ondemand_daemon_read()
- Add consistency checks read and open requests to avoid crashes
- Add a spinlock to protect ondemand_id variable which is used to
determine whether an anonymous cachefiles fd has already been
closed
- Make on-demand reads killable allowing to handle broken cachefiles
daemon better
- Flush all requests after the kernel has been marked dead via
CACHEFILES_DEAD to avoid hung-tasks
- Ensure that closed requests are marked as such to avoid reusing
them with a reopen request
- Defer fd_install() until after copy_to_user() succeeded and thereby
get rid of having to use close_fd()
- Ensure that anonymous cachefiles on-demand fds are reused while
they are valid to avoid pinning already freed cookies"
* tag 'vfs-6.10-rc4.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
iomap: Fix iomap_adjust_read_range for plen calculation
iomap: keep on increasing i_size in iomap_write_end()
cachefiles: remove unneeded include of <linux/fdtable.h>
fs/file: fix the check in find_next_fd()
cachefiles: make on-demand read killable
cachefiles: flush all requests after setting CACHEFILES_DEAD
cachefiles: Set object to close if ondemand_id < 0 in copen
cachefiles: defer exposing anon_fd until after copy_to_user() succeeds
cachefiles: never get a new anonymous fd if ondemand_id is valid
cachefiles: add spin_lock for cachefiles_ondemand_info
cachefiles: add consistency check for copen/cread
cachefiles: remove err_put_fd label in cachefiles_ondemand_daemon_read()
cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read()
cachefiles: fix slab-use-after-free in cachefiles_ondemand_get_fd()
cachefiles: remove requests from xarray during flushing requests
cachefiles: add output string to cachefiles_obj_[get|put]_ondemand_fd
statx: Update offset commentary for struct statx
netfs: fix kernel doc for nets_wait_for_outstanding_io()
debugfs: continue to ignore unknown mount options
Consider a thermal zone with one passive trip point, a cooling device
with 3 states (0, 1, 2) bound to it, passive polling enabled (nonzero
passive_delay_jiffies) and no regular polling (polling_delay_jiffies
equal to 0) that is managed by the Step-Wise governor. Suppose that
the initial state of the cooling device is 0 and the zone temperature
is below the trip point to start with.
When the trip point is crossed, tz->passive is incremented by the
thermal core and the governor's .manage() callback is invoked. It
sets 'throttle' to 'true' for the trip in question and
get_target_state() returns 1 for the instance corresponding to the
cooling device (say that 'upper' and 'lower' are set to 2 and 0 for
it, respectively), so its state changes to 1.
Passive polling is still active for the zone, so next time the
temperature is updated, the governor's .manage() callback will be
invoked again. If the temperature is still rising, it will change
the state of the cooling device to 2.
Now suppose that next time the zone temperature is updated, it falls
below the trip point, so tz->passive is decremented for the zone (say
it becomes 0 then) and the governor's .manage() callbacks runs.
It finds that the temperature trend for the zone is 'falling' and
'throttle' will be set to 'false' for the trip in question, so the
cooling device's state will be changed to 1. However, because
tz->polling is 0 for the zone, the governor's .manage() callback
may not be invoked again for a long time and the cooling device's
state will not be reset back to 0.
This can happen because commit 042a3d80f1 ("thermal: core: Move
passive polling management to the core") removed passive polling
management from the Step-Wise governor.
Before that change, thermal_zone_trip_update() would bump up
tz->passive when changing the target state for a thermal instance
from "no target" to a specific value and it would drop tz->passive
when changing it back to "no target" which would cause passive
polling to be active for the zone until the governor has reset the
states of all cooling devices. In particular, in the example above
tz->passive would be incremented when changing the state of the
cooling device from 0 to 1 and then it would be still nonzero when
the state of the cooling device was changed from 2 to 1.
To prevent this problem from occurring, restore the passive polling
management in the Step-Wise governor by partially reverting the
commit in question and update the comment in the restored code
to explain its role more clearly.
Fixes: 042a3d80f1 ("thermal: core: Move passive polling management to the core")
Closes: https://lore.kernel.org/linux-pm/ZmVfcEOxmjUHZTSX@hovoldconsulting.com
Reported-by: Johan Hovold <johan+linaro@kernel.org>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
'ip6 dscp set $v' in an nftables outpute route chain has no effect.
While nftables does detect the dscp change and calls the reroute hook.
But ip6_route_me_harder never sets the dscp/flowlabel:
flowlabel/dsfield routing rules are ignored and no reroute takes place.
Thanks to Yi Chen for an excellent reproducer script that I used
to validate this change.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: Yi Chen <yiche@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Lion Ackermann reported that there is a race condition between namespace cleanup
in ipset and the garbage collection of the list:set type. The namespace
cleanup can destroy the list:set type of sets while the gc of the set type is
waiting to run in rcu cleanup. The latter uses data from the destroyed set which
thus leads use after free. The patch contains the following parts:
- When destroying all sets, first remove the garbage collectors, then wait
if needed and then destroy the sets.
- Fix the badly ordered "wait then remove gc" for the destroy a single set
case.
- Fix the missing rcu locking in the list:set type in the userspace test
case.
- Use proper RCU list handlings in the list:set type.
The patch depends on c1193d9bbb (netfilter: ipset: Add list flush to cancel_gc).
Fixes: 97f7cf1cd8 (netfilter: ipset: fix performance regression in swap operation)
Reported-by: Lion Ackermann <nnamrec@gmail.com>
Tested-by: Lion Ackermann <nnamrec@gmail.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Check for mandatory netlink attributes in payload and meta expression
when used embedded from the inner expression, otherwise NULL pointer
dereference is possible from userspace.
Fixes: a150d122b6 ("netfilter: nft_meta: add inner match support")
Fixes: 3a07327d10 ("netfilter: nft_inner: support for inner tunnel header matching")
Signed-off-by: Davide Ornaghi <d.ornaghi97@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Since physical and virtual kernel address spaces are uncoupled
the kernel image is not mapped using large segment pages anymore,
which is a regression.
Put the kernel image at the same large segment page offset in
physical memory as in virtual memory. Such approach preserves
the existing number of bits of entropy used for randomization
of the kernel location in virtual memory when KASLR is on.
As result, the kernel is mapped using large segment pages.
Fixes: c98d2ecae0 ("s390/mm: Uncouple physical vs virtual address spaces")
Reported-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Do not allow creation of large pages against physical addresses,
which itself are not aligned on the correct boundary. Failure to
do so might lead to referencing wrong memory as result of the way
DAT works.
Fixes: c98d2ecae0 ("s390/mm: Uncouple physical vs virtual address spaces")
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
If the card doesn't have display hardware, hpd_work and hpd_lock are
left uninitialized which causes BUG when attempting to schedule hpd_work
on runtime PM resume.
Fix it by adding headless flag to DRM and skip any hpd if it's set.
Fixes: ae1aadb1eb ("nouveau: don't fail driver load if no display hw present.")
Link: https://gitlab.freedesktop.org/drm/nouveau/-/issues/337
Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com>
Reviewed-by: Ben Skeggs <bskeggs@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240607221032.25918-1-anarsoul@gmail.com
Due to timer wheel implementation, a timer will usually fire
after its schedule.
For instance, for HZ=1000, a timeout between 512ms and 4s
has a granularity of 64ms.
For this range of values, the extra delay could be up to 63ms.
For TCP, this means that tp->rcv_tstamp may be after
inet_csk(sk)->icsk_timeout whenever the timer interrupt
finally triggers, if one packet came during the extra delay.
We need to make sure tcp_rtx_probe0_timed_out() handles this case.
Fixes: e89688e3e9 ("net: tcp: fix unexcepted socket die when snd_wnd is 0")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Menglong Dong <imagedong@tencent.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20240607125652.1472540-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Matthieu Baerts says:
====================
mptcp: various fixes
The different patches here are some unrelated fixes for MPTCP:
- Patch 1 ensures 'snd_una' is initialised on connect in case of MPTCP
fallback to TCP followed by retransmissions before the processing of
any other incoming packets. A fix for v5.9+.
- Patch 2 makes sure the RmAddr MIB counter is incremented, and only
once per ID, upon the reception of a RM_ADDR. A fix for v5.10+.
- Patch 3 doesn't update 'add addr' related counters if the connect()
was not possible. A fix for v5.7+.
- Patch 4 updates the mailmap file to add Geliang's new email address.
====================
Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-0-1ab9ddfa3d00@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Just like my other email addresses, map my new one to kernel.org
account too.
My new email address uses "last name, first name" format, which is
different from my other email addresses. This mailmap is also used
to indicate that it is actually the same person.
Suggested-by: Mat Martineau <martineau@kernel.org>
Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-4-1ab9ddfa3d00@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The creation of new subflows can fail for different reasons. If no
subflow have been created using the received ADD_ADDR, the related
counters should not be updated, otherwise they will never be decremented
for events related to this ID later on.
For the moment, the number of accepted ADD_ADDR is only decremented upon
the reception of a related RM_ADDR, and only if the remote address ID is
currently being used by at least one subflow. In other words, if no
subflow can be created with the received address, the counter will not
be decremented. In this case, it is then important not to increment
pm.add_addr_accepted counter, and not to modify pm.accept_addr bit.
Note that this patch does not modify the behaviour in case of failures
later on, e.g. if the MP Join is dropped or rejected.
The "remove invalid addresses" MP Join subtest has been modified to
validate this case. The broadcast IP address is added before the "valid"
address that will be used to successfully create a subflow, and the
limit is decreased by one: without this patch, it was not possible to
create the last subflow, because:
- the broadcast address would have been accepted even if it was not
usable: the creation of a subflow to this address results in an error,
- the limit of 2 accepted ADD_ADDR would have then been reached.
Fixes: 01cacb00b3 ("mptcp: add netlink-based PM")
Cc: stable@vger.kernel.org
Co-developed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: YonglongLi <liyonglong@chinatelecom.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-3-1ab9ddfa3d00@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The RmAddr MIB counter is supposed to be incremented once when a valid
RM_ADDR has been received. Before this patch, it could have been
incremented as many times as the number of subflows connected to the
linked address ID, so it could have been 0, 1 or more than 1.
The "RmSubflow" is incremented after a local operation. In this case,
it is normal to tied it with the number of subflows that have been
actually removed.
The "remove invalid addresses" MP Join subtest has been modified to
validate this case. A broadcast IP address is now used instead: the
client will not be able to create a subflow to this address. The
consequence is that when receiving the RM_ADDR with the ID attached to
this broadcast IP address, no subflow linked to this ID will be found.
Fixes: 7a7e52e38a ("mptcp: add RM_ADDR related mibs")
Cc: stable@vger.kernel.org
Co-developed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: YonglongLi <liyonglong@chinatelecom.cn>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-2-1ab9ddfa3d00@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This is strictly related to commit fb7a0d3348 ("mptcp: ensure snd_nxt
is properly initialized on connect"). It turns out that syzkaller can
trigger the retransmit after fallback and before processing any other
incoming packet - so that snd_una is still left uninitialized.
Address the issue explicitly initializing snd_una together with snd_nxt
and write_seq.
Suggested-by: Mat Martineau <martineau@kernel.org>
Fixes: 8fd738049a ("mptcp: fallback in case of simultaneous connect")
Cc: stable@vger.kernel.org
Reported-by: Christoph Paasch <cpaasch@apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/485
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://lore.kernel.org/r/20240607-upstream-net-20240607-misc-fixes-v1-1-1ab9ddfa3d00@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When the noop_qdisc owner isn't initialized, then it will be 0,
so packets will erroneously be regarded as having been subject
to recursion as long as only CPU 0 queues them. For non-SMP,
that's all packets, of course. This causes a change in what's
reported to userspace, normally noop_qdisc would drop packets
silently, but with this change the syscall returns -ENOBUFS if
RECVERR is also set on the socket.
Fix this by initializing the owner field to -1, just like it
would be for dynamically allocated qdiscs by qdisc_alloc().
Fixes: 0f022d32c3 ("net/sched: Fix mirred deadlock on device recursion")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240607175340.786bfb938803.I493bf8422e36be4454c08880a8d3703cea8e421a@changeid
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
After the recent commit 5097cbcb38 ("sched/isolation: Prevent boot crash
when the boot CPU is nohz_full") the kernel no longer crashes, but there is
another problem.
In this case tick_setup_device() calls tick_take_do_timer_from_boot() to
update tick_do_timer_cpu and this triggers the WARN_ON_ONCE(irqs_disabled)
in smp_call_function_single().
Kill tick_take_do_timer_from_boot() and just use WRITE_ONCE(), the new
comment explains why this is safe (thanks Thomas!).
Fixes: 08ae95f4fd ("nohz_full: Allow the boot CPU to be nohz_full")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20240528122019.GA28794@redhat.com
Link: https://lore.kernel.org/all/20240522151742.GA10400@redhat.com
This happens when the amdgpu_bo_release_notify running
before amdgpu_ttm_set_buffer_funcs_status set the buffer
funcs to enabled.
check the buffer funcs enablement before calling the fill
buffer memory.
v2:(Christian)
- Apply it only for GEM buffers and since GEM buffers are only
allocated/freed while the driver is loaded we never run into
the issue to clear with buffer funcs disabled.
v3:(Mario)
- drop the stable tag as this will presumably go into a
-fixes PR for 6.10
Log snip:
*ERROR* Trying to clear memory with ring turned off.
RIP: 0010:amdgpu_bo_release_notify+0x201/0x220 [amdgpu]
Fixes: a68c7eaa7a ("drm/amdgpu: Enable clear page functionality")
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Tested-by: Richard Gong <richard.gong@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240610180401.9540-1-Arunpravin.PaneerSelvam@amd.com
The bucket_gens array and gc_buckets array known their own size; we
should be using those members, and returning an error.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
fsck_err() does a goto fsck_err on error; factor out check_fix_ptr() so
that our error label can drop our device ref.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
