The function sdm845_slim_snd_hw_params() calls the functuion
snd_soc_dai_set_channel_map() but does not check its return
value. A proper implementation can be found in msm_snd_hw_params().
Add error handling for snd_soc_dai_set_channel_map(). If the
function fails and it is not a unsupported error, return the
error code immediately.
Fixes: 5caf64c633a3 ("ASoC: qcom: sdm845: add support to DB845c and Lenovo Yoga")
Cc: stable(a)vger.kernel.org # v5.6
Signed-off-by: Wentao Liang <vulab(a)iscas.ac.cn>
---
sound/soc/qcom/sdm845.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index a479d7e5b7fb..314ff68506d9 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -91,6 +91,10 @@ static int sdm845_slim_snd_hw_params(struct snd_pcm_substream *substream,
else
ret = snd_soc_dai_set_channel_map(cpu_dai, tx_ch_cnt,
tx_ch, 0, NULL);
+ if (ret != 0 && ret != -ENOTSUPP) {
+ dev_err(rtd->dev, "failed to set cpu chan map, err:%d\n", ret);
+ return ret;
+ }
}
return 0;
--
2.42.0.windows.2
On 5/21/25 11:48, Maud Spierings wrote:
> On 5/21/25 11:29, Christian Heusel wrote:
>> On 25/05/21 10:53AM, Maud Spierings wrote:
>>> I've just experienced an Issue that I think may be a regression.
>>>
>>> I'm enabling a device which incorporates a lis2dw12 accelerometer,
>>> currently
>>> I am running 6.12 lts, so 6.12.29 as of typing this message.
>>
>> Could you check whether the latest mainline release (at the time this is
>> v6.15-rc7) is also affected? If that's not the case the bug might
>> already be fixed ^_^
>
> Unfortunately doesn't seem to be the case, still gets the panic. I also
> tried 6.12(.0), but that also has the panic, so it is definitely older
> than this lts.
>
>> Also as you said that this is a regression, what is the last revision
>> that the accelerometer worked with?
>
> Thats a difficult one to pin down, I'm moving from the nxp vendor kernel
> to mainline, the last working one that I know sure is 5.10.72 of that
> vendor kernel.
I did some more digging and the latest lts it seems to work with is
6.1.139, 6.6.91 also crashes. So it seems to be a very old regression.
>>> This is where my ability to fix thing fizzles out and so here I am
>>> asking
>>> for assistance.
>>>
>>> Kind regards,
>>> Maud
>>
>> Cheers,
>> Chris
>
> From: Parav Pandit <parav(a)nvidia.com>
> Sent: Thursday, May 22, 2025 1:19 PM
> To: Max Gurtovoy <mgurtovoy(a)nvidia.com>; Israel Rukshin
> <israelr(a)nvidia.com>
> Cc: Parav Pandit <parav(a)nvidia.com>; stable(a)vger.kernel.org; NBU-Contact-
> Li Rongqing (EXTERNAL) <lirongqing(a)baidu.com>
> Subject: [PATCH v6] virtio_blk: Fix disk deletion hang on device surprise
> removal
>
> When the PCI device is surprise removed, requests may not complete the
> device as the VQ is marked as broken. Due to this, the disk deletion hangs.
>
> Fix it by aborting the requests when the VQ is broken.
>
> With this fix now fio completes swiftly.
> An alternative of IO timeout has been considered, however when the driver
> knows about unresponsive block device, swiftly clearing them enables users
> and upper layers to react quickly.
>
> Verified with multiple device unplug iterations with pending requests in virtio
> used ring and some pending with the device.
>
> Fixes: 43bb40c5b926 ("virtio_pci: Support surprise removal of virtio pci
> device")
> Cc: stable(a)vger.kernel.org
> Reported-by: Li RongQing <lirongqing(a)baidu.com>
> Closes:
> https://lore.kernel.org/virtualization/c45dd68698cd47238c55fb73ca9b4741
> @baidu.com/
> Signed-off-by: Parav Pandit <parav(a)nvidia.com>
>
This is an internal patch, which got CCed to stable by mistake.
Please ignore this patch for stable kernels.
It is still under internal review.
I am sorry for the noise.
> ---
> v1->v2: (internal v5->v6):
> - Addressed comments from Stephan
> - fixed spelling to 'waiting'
> v1->v2: (internal v4->v5):
> - Addressed comments from MST
> - removed the vq broken check in queue_rq(s)
> ---
> drivers/block/virtio_blk.c | 85
> ++++++++++++++++++++++++++++++++++++++
> 1 file changed, 85 insertions(+)
>
> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index
> 7cffea01d868..04f24ec20405 100644
> --- a/drivers/block/virtio_blk.c
> +++ b/drivers/block/virtio_blk.c
> @@ -1554,6 +1554,89 @@ static int virtblk_probe(struct virtio_device *vdev)
> return err;
> }
>
> +static bool virtblk_request_cancel(struct request *rq, void *data) {
> + struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
> + struct virtio_blk *vblk = data;
> + struct virtio_blk_vq *vq;
> + unsigned long flags;
> +
> + vq = &vblk->vqs[rq->mq_hctx->queue_num];
> +
> + spin_lock_irqsave(&vq->lock, flags);
> +
> + vbr->in_hdr.status = VIRTIO_BLK_S_IOERR;
> + if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq))
> + blk_mq_complete_request(rq);
> +
> + spin_unlock_irqrestore(&vq->lock, flags);
> + return true;
> +}
> +
> +static void virtblk_broken_device_cleanup(struct virtio_blk *vblk) {
> + struct request_queue *q = vblk->disk->queue;
> +
> + return;
> +
> + if (!virtqueue_is_broken(vblk->vqs[0].vq))
> + return;
> +
> + /* Start freezing the queue, so that new requests keeps waiting at the
> + * door of bio_queue_enter(). We cannot fully freeze the queue
> because
> + * freezed queue is an empty queue and there are pending requests,
> so
> + * only start freezing it.
> + */
> + blk_freeze_queue_start(q);
> +
> + /* When quiescing completes, all ongoing dispatches have completed
> + * and no new dispatch will happen towards the driver.
> + * This ensures that later when cancel is attempted, then are not
> + * getting processed by the queue_rq() or queue_rqs() handlers.
> + */
> + blk_mq_quiesce_queue(q);
> +
> + /*
> + * Synchronize with any ongoing VQ callbacks, effectively quiescing
> + * the device and preventing it from completing further requests
> + * to the block layer. Any outstanding, incomplete requests will be
> + * completed by virtblk_request_cancel().
> + */
> + virtio_synchronize_cbs(vblk->vdev);
> +
> + /* At this point, no new requests can enter the queue_rq() and
> + * completion routine will not complete any new requests either for
> the
> + * broken vq. Hence, it is safe to cancel all requests which are
> + * started.
> + */
> + blk_mq_tagset_busy_iter(&vblk->tag_set, virtblk_request_cancel,
> vblk);
> + blk_mq_tagset_wait_completed_request(&vblk->tag_set);
> +
> + /* All pending requests are cleaned up. Time to resume so that disk
> + * deletion can be smooth. Start the HW queues so that when queue is
> + * unquiesced requests can again enter the driver.
> + */
> + blk_mq_start_stopped_hw_queues(q, true);
> +
> + /* Unquiescing will trigger dispatching any pending requests to the
> + * driver which has crossed bio_queue_enter() to the driver.
> + */
> + blk_mq_unquiesce_queue(q);
> +
> + /* Wait for all pending dispatches to terminate which may have been
> + * initiated after unquiescing.
> + */
> + blk_mq_freeze_queue_wait(q);
> +
> + /* Mark the disk dead so that once queue unfreeze, the requests
> + * waiting at the door of bio_queue_enter() can be aborted right away.
> + */
> + blk_mark_disk_dead(vblk->disk);
> +
> + /* Unfreeze the queue so that any waiting requests will be aborted. */
> + blk_mq_unfreeze_queue_nomemrestore(q);
> +}
> +
> static void virtblk_remove(struct virtio_device *vdev) {
> struct virtio_blk *vblk = vdev->priv;
> @@ -1561,6 +1644,8 @@ static void virtblk_remove(struct virtio_device
> *vdev)
> /* Make sure no work handler is accessing the device. */
> flush_work(&vblk->config_work);
>
> + virtblk_broken_device_cleanup(vblk);
> +
> del_gendisk(vblk->disk);
> blk_mq_free_tag_set(&vblk->tag_set);
>
> --
> 2.34.1
Hi,
I'd like to report a regression which seems related to the latest
ITS mitigations in Linux 6.1.x:
The server in question is a Supermicro SYS-120C-TN10R with
a "Intel(R) Xeon(R) Silver 4310 CPU @ 2.10GHz" CPU, running
Debian Bookworm. The full output of /proc/cpuinfo is attached
as cpuinfo.txt
In addition to the kernel changes between 6.1.135 and 6.1.139
there is also some additional invariant, namely the Intel microcode
loaded at early boot:
On Linux 6.1.135 every works fine with both the 20250211 and
20250512 microcode releases (kern.log is attached as
6.1.135-feb-microcode.log and 6.1.135-may-microcode.log)
With 6.1.139 and the February microcode, oopses appear related
to clear_bhb_loop() (which may be related to "x86/its: Align
RETs in BHB clear sequence to avoid thunking"?). This is
captured in 6.1.139-feb-microcode.log.
With 6.1.139 and the May microcode, the system mostly
crashes on bootup (in my tests it crashed in three out of
four attempts). I've captured both the crash
(6.1.139-may-microcode-crash.log) and a working boot
(6.1.139-may-microcode-noncrash.log).
If you need any additional information, please let me know!
Cheers,
Moritz
Generally PASID support requires ACS settings that usually create
single device groups, but there are some niche cases where we can get
multi-device groups and still have working PASID support. The primary
issue is that PCI switches are not required to treat PASID tagged TLPs
specially so appropriate ACS settings are required to route all TLPs to
the host bridge if PASID is going to work properly.
pci_enable_pasid() does check that each device that will use PASID has
the proper ACS settings to achieve this routing.
However, no-PASID devices can be combined with PASID capable devices
within the same topology using non-uniform ACS settings. In this case
the no-PASID devices may not have strict route to host ACS flags and
end up being grouped with the PASID devices.
This configuration fails to allow use of the PASID within the iommu
core code which wrongly checks if the no-PASID device supports PASID.
Fix this by ignoring no-PASID devices during the PASID validation. They
will never issue a PASID TLP anyhow so they can be ignored.
Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()")
Cc: stable(a)vger.kernel.org
Signed-off-by: Tushar Dave <tdave(a)nvidia.com>
---
changes in v4:
- rebase to 6.15-rc7
drivers/iommu/iommu.c | 43 ++++++++++++++++++++++++++++---------------
1 file changed, 28 insertions(+), 15 deletions(-)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 4f91a740c15f..9d728800a862 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3366,10 +3366,12 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain,
int ret;
for_each_group_device(group, device) {
- ret = domain->ops->set_dev_pasid(domain, device->dev,
- pasid, old);
- if (ret)
- goto err_revert;
+ if (device->dev->iommu->max_pasids > 0) {
+ ret = domain->ops->set_dev_pasid(domain, device->dev,
+ pasid, old);
+ if (ret)
+ goto err_revert;
+ }
}
return 0;
@@ -3379,15 +3381,18 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain,
for_each_group_device(group, device) {
if (device == last_gdev)
break;
- /*
- * If no old domain, undo the succeeded devices/pasid.
- * Otherwise, rollback the succeeded devices/pasid to the old
- * domain. And it is a driver bug to fail attaching with a
- * previously good domain.
- */
- if (!old || WARN_ON(old->ops->set_dev_pasid(old, device->dev,
+ if (device->dev->iommu->max_pasids > 0) {
+ /*
+ * If no old domain, undo the succeeded devices/pasid.
+ * Otherwise, rollback the succeeded devices/pasid to
+ * the old domain. And it is a driver bug to fail
+ * attaching with a previously good domain.
+ */
+ if (!old ||
+ WARN_ON(old->ops->set_dev_pasid(old, device->dev,
pasid, domain)))
- iommu_remove_dev_pasid(device->dev, pasid, domain);
+ iommu_remove_dev_pasid(device->dev, pasid, domain);
+ }
}
return ret;
}
@@ -3398,8 +3403,10 @@ static void __iommu_remove_group_pasid(struct iommu_group *group,
{
struct group_device *device;
- for_each_group_device(group, device)
- iommu_remove_dev_pasid(device->dev, pasid, domain);
+ for_each_group_device(group, device) {
+ if (device->dev->iommu->max_pasids > 0)
+ iommu_remove_dev_pasid(device->dev, pasid, domain);
+ }
}
/*
@@ -3440,7 +3447,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
mutex_lock(&group->mutex);
for_each_group_device(group, device) {
- if (pasid >= device->dev->iommu->max_pasids) {
+ /*
+ * Skip PASID validation for devices without PASID support
+ * (max_pasids = 0). These devices cannot issue transactions
+ * with PASID, so they don't affect group's PASID usage.
+ */
+ if ((device->dev->iommu->max_pasids > 0) &&
+ (pasid >= device->dev->iommu->max_pasids)) {
ret = -EINVAL;
goto out_unlock;
}
--
2.34.1