From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: intel-xe@lists.freedesktop.org, shekhar.chauhan@intel.com,
harish.chegondi@intel.com
Cc: matthew.brost@intel.com
Subject: [PATCH v9 5/7] drm/xe/oa: Fence OA ioctls and mmap against device unplug and wedging
Date: Fri, 20 Nov 2026 18:01:51 -0800 [thread overview]
Message-ID: <20261121020145.147384-14-umesh.nerlige.ramappa@intel.com> (raw)
In-Reply-To: <20261121020145.147384-9-umesh.nerlige.ramappa@intel.com>
drm_ioctl() only checks for unplug on entry, so an OA ioctl that
started before drm_dev_unplug() can still open a stream, or access
oa->xe and the metrics idr, while the device is removed. The ioctls and
the mmap of the OA stream fd don't go through drm_ioctl() at all, and
neither through the wedged check of xe_drm_ioctl().
Run the OA ioctls of the drm fd and the ioctls and mmap of the OA stream
fd in a drm_dev_enter() section, so that they fail with -ENODEV once the
device is unplugged, and drm_dev_unplug() waits for the ones in flight.
Fail the stream fd ioctls with -ECANCELED on a wedged device, like
xe_drm_ioctl() does.
A config without output syncs waits synchronously for its batch, while
holding stream_lock or gt_lock and now in a drm_dev_enter() section. If
the batch waits on an input fence that never signals, or never completes
on a wedged device, that would block drm_dev_unplug() or the stream
teardown. Stop waiting once the device is unplugged or wedged, and fail
the config.
A stream fd can still outlive the device, the following patch handles
that.
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Shekhar Chauhan <shekhar.chauhan@intel.com>
---
v8: Split out of "drm/xe/oa: Quiesce OA streams on driver unbind and PCI
reset", which carried these changes since v4
---
drivers/gpu/drm/xe/xe_oa.c | 75 +++++++++++++++++++++++------
drivers/gpu/drm/xe/xe_observation.c | 20 +++++++-
2 files changed, 78 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 7241cf18b325..3f51dca91c51 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -43,6 +43,7 @@
#include "xe_sriov.h"
#include "xe_sync.h"
#include "xe_wa.h"
+#include "xe_wedge.h"
#define DEFAULT_POLL_FREQUENCY_HZ 200
#define DEFAULT_POLL_PERIOD_NS (NSEC_PER_SEC / DEFAULT_POLL_FREQUENCY_HZ)
@@ -1082,6 +1083,7 @@ static int xe_oa_emit_oa_config(struct xe_oa_stream *stream, struct xe_oa_config
struct xe_oa_fence *ofence;
int i, err, num_signal = 0;
struct dma_fence *fence;
+ int ret = 0;
ofence = kzalloc_obj(*ofence);
if (!ofence) {
@@ -1125,12 +1127,28 @@ static int xe_oa_emit_oa_config(struct xe_oa_stream *stream, struct xe_oa_config
if (err == -ENOENT)
xe_oa_config_cb(fence, &ofence->cb);
- /* If nothing needs to be signaled we wait synchronously */
+ /*
+ * If nothing needs to be signaled we wait synchronously unless the device
+ * is unplugged/wedged.
+ */
if (!num_signal) {
- dma_fence_wait(&ofence->base, false);
+ while (!dma_fence_wait_timeout(&ofence->base, false, HZ / 10)) {
+ if (drm_dev_is_unplugged(>_to_xe(stream->gt)->drm)) {
+ ret = -ENODEV;
+ break;
+ }
+ if (xe_wedged(gt_to_xe(stream->gt))) {
+ ret = -ECANCELED;
+ break;
+ }
+ }
dma_fence_put(&ofence->base);
}
+ /* The callers clean up the syncs on error */
+ if (ret)
+ return ret;
+
/* Done with syncs */
for (i = 0; i < stream->num_syncs; i++)
xe_sync_entry_cleanup(&stream->syncs[i]);
@@ -1722,11 +1740,20 @@ static long xe_oa_ioctl(struct file *file,
unsigned long arg)
{
struct xe_oa_stream *stream = file->private_data;
- long ret;
+ struct xe_device *xe = gt_to_xe(stream->gt);
+ long ret = -ECANCELED;
+ int idx;
- mutex_lock(&stream->stream_lock);
- ret = xe_oa_ioctl_locked(stream, cmd, arg);
- mutex_unlock(&stream->stream_lock);
+ if (!drm_dev_enter(&xe->drm, &idx))
+ return -ENODEV;
+
+ if (!xe_wedged(xe)) {
+ mutex_lock(&stream->stream_lock);
+ ret = xe_oa_ioctl_locked(stream, cmd, arg);
+ mutex_unlock(&stream->stream_lock);
+ }
+
+ drm_dev_exit(idx);
return ret;
}
@@ -1765,27 +1792,41 @@ static int xe_oa_release(struct inode *inode, struct file *file)
static int xe_oa_mmap(struct file *file, struct vm_area_struct *vma)
{
struct xe_oa_stream *stream = file->private_data;
+ struct xe_device *xe = gt_to_xe(stream->gt);
int ret = xe_observation_paranoid_check();
- struct xe_bo *bo = stream->oa_buffer.bo;
+ struct xe_bo *bo;
+ int idx;
if (ret) {
- drm_dbg(&stream->oa->xe->drm, "Insufficient privilege to map OA buffer\n");
+ drm_dbg(&xe->drm, "Insufficient privilege to map OA buffer\n");
return ret;
}
+ /*
+ * drm_dev_unplug() zaps the OA buffer mmaps and waits for this section to finish, so
+ * no mmap of the OA buffer can be set up after that. Can't use stream_lock here, it is
+ * held across user copies which fault on mmap_lock, held by the caller.
+ */
+ if (!drm_dev_enter(&xe->drm, &idx))
+ return -ENODEV;
+
/*
* Userspace always maps the OA buffer at offset 0, the mapping is moved to the OA
* buffer's own range in the drm device's address_space below
*/
if (vma->vm_pgoff) {
- drm_dbg(&stream->oa->xe->drm, "Wrong mmap offset, must be 0\n");
- return -EINVAL;
+ drm_dbg(&xe->drm, "Wrong mmap offset, must be 0\n");
+ ret = -EINVAL;
+ goto exit;
}
+ bo = stream->oa_buffer.bo;
+
/* Can mmap the entire OA buffer or nothing (no partial OA buffer mmaps) */
if (vma->vm_end - vma->vm_start != xe_bo_size(bo)) {
- drm_dbg(&stream->oa->xe->drm, "Wrong mmap size, must be OA buffer size\n");
- return -EINVAL;
+ drm_dbg(&xe->drm, "Wrong mmap size, must be OA buffer size\n");
+ ret = -EINVAL;
+ goto exit;
}
/*
@@ -1793,15 +1834,19 @@ static int xe_oa_mmap(struct file *file, struct vm_area_struct *vma)
* VM_MAYSHARE, don't copy the vma on fork
*/
if (vma->vm_flags & (VM_WRITE | VM_EXEC | VM_SHARED | VM_MAYSHARE)) {
- drm_dbg(&stream->oa->xe->drm, "mmap must be read only\n");
- return -EINVAL;
+ drm_dbg(&xe->drm, "mmap must be read only\n");
+ ret = -EINVAL;
+ goto exit;
}
vm_flags_mod(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_DONTCOPY,
VM_MAYWRITE | VM_MAYEXEC);
vma->vm_pgoff = drm_vma_node_start(&bo->ttm.base.vma_node);
- return drm_gem_mmap_obj(&bo->ttm.base, xe_bo_size(bo), vma);
+ ret = drm_gem_mmap_obj(&bo->ttm.base, xe_bo_size(bo), vma);
+exit:
+ drm_dev_exit(idx);
+ return ret;
}
static const struct file_operations xe_oa_fops = {
diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c
index 39e05b9131a7..9e23ade51dc1 100644
--- a/drivers/gpu/drm/xe/xe_observation.c
+++ b/drivers/gpu/drm/xe/xe_observation.c
@@ -7,6 +7,7 @@
#include <linux/perf_event.h>
#include <linux/sysctl.h>
+#include <drm/drm_drv.h>
#include <uapi/drm/xe_drm.h>
#include "xe_eu_stall.h"
@@ -35,8 +36,8 @@ int xe_observation_paranoid_check(void)
return perf_allow_cpu();
}
-static int xe_oa_ioctl(struct drm_device *dev, struct drm_xe_observation_param *arg,
- struct drm_file *file)
+static int __xe_oa_ioctl(struct drm_device *dev, struct drm_xe_observation_param *arg,
+ struct drm_file *file)
{
switch (arg->observation_op) {
case DRM_XE_OBSERVATION_OP_STREAM_OPEN:
@@ -50,6 +51,21 @@ static int xe_oa_ioctl(struct drm_device *dev, struct drm_xe_observation_param *
}
}
+static int xe_oa_ioctl(struct drm_device *dev, struct drm_xe_observation_param *arg,
+ struct drm_file *file)
+{
+ int idx, ret;
+
+ /* Hold off drm_dev_unplug() while the OA ioctls run */
+ if (!drm_dev_enter(dev, &idx))
+ return -ENODEV;
+
+ ret = __xe_oa_ioctl(dev, arg, file);
+
+ drm_dev_exit(idx);
+ return ret;
+}
+
static int xe_eu_stall_ioctl(struct drm_device *dev, struct drm_xe_observation_param *arg,
struct drm_file *file)
{
--
2.55.0
next prev parent reply other threads:[~2026-11-21 2:02 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-21 2:01 [PATCH v9 0/7] Cleanup OA stream on PCI unbind/remove Umesh Nerlige Ramappa
2026-11-21 2:01 ` [PATCH v9 1/7] drm/xe/oa: Ignore a HW tail pointer outside the OA buffer Umesh Nerlige Ramappa
2026-11-21 2:01 ` [PATCH v9 2/7] drm/xe/oa: Use the drm device address_space for the OA stream fd Umesh Nerlige Ramappa
2026-11-21 2:01 ` [PATCH v9 3/7] drm/xe: Reject vm_ops->access on BO mappings of an unplugged device Umesh Nerlige Ramappa
2026-11-21 2:01 ` [PATCH v9 4/7] drm/xe/oa: Wait for in-flight OA batches before stream HW teardown Umesh Nerlige Ramappa
2026-11-21 2:11 ` sashiko-bot
2026-11-21 2:01 ` Umesh Nerlige Ramappa [this message]
2026-11-21 2:01 ` [PATCH v9 6/7] drm/xe/oa: Free the OA buffer and the stream after the stream destroy Umesh Nerlige Ramappa
2026-11-21 2:01 ` [PATCH v9 7/7] drm/xe/oa: Quiesce OA streams on driver unbind and PCI reset Umesh Nerlige Ramappa
2026-11-21 2:37 ` sashiko-bot
2026-11-21 2:09 ` ✗ CI.checkpatch: warning for Cleanup OA stream on PCI unbind/remove (rev9) Patchwork
2026-11-21 2:11 ` ✓ CI.KUnit: success " Patchwork
2026-11-21 2:48 ` ✗ Xe.CI.BAT: failure " Patchwork
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=20261121020145.147384-14-umesh.nerlige.ramappa@intel.com \
--to=umesh.nerlige.ramappa@intel.com \
--cc=harish.chegondi@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.brost@intel.com \
--cc=shekhar.chauhan@intel.com \
/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