From: Dave Jiang <dave.jiang@intel.com>
To: Vinicius Costa Gomes <vinicius.gomes@intel.com>,
Vinod Koul <vkoul@kernel.org>,
Dan Williams <dan.j.williams@intel.com>,
Fenghua Yu <fenghuay@nvidia.com>
Cc: dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 4/9] dmaengine: idxd: Flush kernel workqueues on Field Level Reset
Date: Wed, 6 Aug 2025 10:12:00 -0700 [thread overview]
Message-ID: <0814df45-15b2-4dc3-98fd-8f30befc800a@intel.com> (raw)
In-Reply-To: <20250804-idxd-fix-flr-on-kernel-queues-v3-v1-4-4e020fbf52c1@intel.com>
On 8/4/25 6:27 PM, Vinicius Costa Gomes wrote:
> When a Field Level Reset (FLR) happens terminate the pending
> descriptors that were issued by in-kernel users and disable the
> interrupts associated with those. They will be re-enabled after FLR
> finishes.
>
> Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
> ---
> drivers/dma/idxd/device.c | 24 ++++++++++++++++++++++++
> drivers/dma/idxd/idxd.h | 1 +
> drivers/dma/idxd/irq.c | 5 +++++
> 3 files changed, 30 insertions(+)
>
> diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
> index c599a902767ee9904d75a0510a911596e35a259b..287cf3bf1f5a2efdc9037968e9a4eed506e489c3 100644
> --- a/drivers/dma/idxd/device.c
> +++ b/drivers/dma/idxd/device.c
> @@ -1315,6 +1315,11 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
>
> free_irq(ie->vector, ie);
> idxd_flush_pending_descs(ie);
> +
> + /* The interrupt might have been already released by FLR */
> + if (ie->int_handle == INVALID_INT_HANDLE)
> + return;
> +
> if (idxd->request_int_handles)
> idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
> idxd_device_clear_perm_entry(idxd, ie);
> @@ -1323,6 +1328,25 @@ void idxd_wq_free_irq(struct idxd_wq *wq)
> ie->pasid = IOMMU_PASID_INVALID;
> }
>
> +void idxd_wqs_flush_descs(struct idxd_device *idxd)
> +{
> + struct idxd_wq *wq;
> + int i;
> +
> + for (i = 0; i < idxd->max_wqs; i++) {
> + wq = idxd->wqs[i];
> + if (wq->state == IDXD_WQ_ENABLED && wq->type == IDXD_WQT_KERNEL) {
> + struct idxd_irq_entry *ie = &wq->ie;
> +
> + idxd_flush_pending_descs(ie);
> + if (idxd->request_int_handles)
> + idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
> + idxd_device_clear_perm_entry(idxd, ie);
> + ie->int_handle = INVALID_INT_HANDLE;
> + }
> + }
> +}
> +
> int idxd_wq_request_irq(struct idxd_wq *wq)
> {
> struct idxd_device *idxd = wq->idxd;
> diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
> index 74e6695881e6f1684512601ca2c2ee241aaf0a78..6ccca3c56556dbffe0a7c983a2f11f6c73ff2bfd 100644
> --- a/drivers/dma/idxd/idxd.h
> +++ b/drivers/dma/idxd/idxd.h
> @@ -737,6 +737,7 @@ static inline void idxd_desc_complete(struct idxd_desc *desc,
> int idxd_register_devices(struct idxd_device *idxd);
> void idxd_unregister_devices(struct idxd_device *idxd);
> void idxd_wqs_quiesce(struct idxd_device *idxd);
> +void idxd_wqs_flush_descs(struct idxd_device *idxd);
> bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc);
> void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count);
> int idxd_load_iaa_device_defaults(struct idxd_device *idxd);
> diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
> index 74059fe43fafeb930f58db21d3824f62b095b968..26547586fcfaa1b9d244b678bf8e209b7b14d35a 100644
> --- a/drivers/dma/idxd/irq.c
> +++ b/drivers/dma/idxd/irq.c
> @@ -417,6 +417,11 @@ static irqreturn_t idxd_halt(struct idxd_device *idxd)
> } else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) {
> idxd->state = IDXD_DEV_HALTED;
> idxd_mask_error_interrupts(idxd);
> + /* Flush all pending descriptors, and disable
> + * interrupts, they will be re-enabled when FLR
> + * concludes.
> + */
> + idxd_wqs_flush_descs(idxd);
> dev_dbg(&idxd->pdev->dev,
> "idxd halted, doing FLR. After FLR, configs are restored\n");
> INIT_WORK(&idxd->work, idxd_device_flr);
>
next prev parent reply other threads:[~2025-08-06 17:12 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-05 1:27 [PATCH 0/9] dmaengine: idxd: Memory leak and FLR fixes Vinicius Costa Gomes
2025-08-05 1:27 ` [PATCH 1/9] dmaengine: idxd: Fix lockdep warnings when calling idxd_device_config() Vinicius Costa Gomes
2025-08-06 17:02 ` Dave Jiang
2025-08-06 20:25 ` Vinicius Costa Gomes
2025-08-05 1:27 ` [PATCH 2/9] dmaengine: idxd: Fix crash when the event log is disabled Vinicius Costa Gomes
2025-08-06 17:07 ` Dave Jiang
2025-08-05 1:27 ` [PATCH 3/9] dmaengine: idxd: Fix possible invalid memory access after FLR Vinicius Costa Gomes
2025-08-06 17:09 ` Dave Jiang
2025-08-15 19:26 ` Nathan Lynch
2025-08-15 22:45 ` Vinicius Costa Gomes
2025-08-05 1:27 ` [PATCH 4/9] dmaengine: idxd: Flush kernel workqueues on Field Level Reset Vinicius Costa Gomes
2025-08-06 17:12 ` Dave Jiang [this message]
2025-08-05 1:27 ` [PATCH 5/9] dmaengine: idxd: Allow DMA clients to empty the pending queue Vinicius Costa Gomes
2025-08-06 17:17 ` Dave Jiang
2025-08-06 20:30 ` Vinicius Costa Gomes
2025-08-05 1:27 ` [PATCH 6/9] dmaengine: idxd: Fix not releasing workqueue on .release() Vinicius Costa Gomes
2025-08-06 17:24 ` Dave Jiang
2025-08-05 1:27 ` [PATCH 7/9] dmaengine: idxd: Fix memory leak when a wq is reset Vinicius Costa Gomes
2025-08-06 17:25 ` Dave Jiang
2025-08-05 1:27 ` [PATCH 8/9] dmaengine: idxd: Fix freeing the allocated ida too late Vinicius Costa Gomes
2025-08-06 17:27 ` Dave Jiang
2025-08-05 1:28 ` [PATCH 9/9] dmaengine: idxd: Fix leaking event log memory Vinicius Costa Gomes
2025-08-06 17:29 ` Dave Jiang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=0814df45-15b2-4dc3-98fd-8f30befc800a@intel.com \
--to=dave.jiang@intel.com \
--cc=dan.j.williams@intel.com \
--cc=dmaengine@vger.kernel.org \
--cc=fenghuay@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=vinicius.gomes@intel.com \
--cc=vkoul@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).