All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Auld <matthew.auld@intel.com>
To: "Matthew Brost" <matthew.brost@intel.com>,
	"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Himal Prasad Ghimiray" <himal.prasad.ghimiray@intel.com>,
	"Stuart Summers" <stuart.summers@intel.com>
Cc: intel-xe@lists.freedesktop.org, Matthew Auld <matthew.auld@intel.com>
Subject: [PATCH v2 4/6] drm/xe: Add a userptr repin timeout sysfs attribute
Date: Fri, 20 Nov 2026 13:02:19 +0000	[thread overview]
Message-ID: <20261120-userptr-repin-v2-4-65e1f6e582ef@intel.com> (raw)
In-Reply-To: <20261120-userptr-repin-v2-0-65e1f6e582ef@intel.com>

From: Thomas Hellström <thomas.hellstrom@linux.intel.com>

Add a per-device sysfs attribute, userptr_repin_timeout_ms, to be used
to bound the overall time a userptr repin is retried when the CPU
mappings keep changing during the repin. The default is 10000 ms on
single-node systems and 30000 ms on multi-node NUMA systems, and zero
means retry indefinitely. The value can be changed at any time and is
read each time the timeout is checked.

v2 (Matt):
- Reject values above INT_MAX (or reaching MAX_JIFFY_OFFSET) with
  -EINVAL in userptr_repin_timeout_ms_store() so msecs_to_jiffies() does
  not treat them as an infinite timeout.
- Lower the default from 100000 ms to 10000 ms on single-node systems
  and 30000 ms on multi-node NUMA systems (Himal).

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Co-developed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c       |  5 ++++
 drivers/gpu/drm/xe/xe_device.h       |  3 ++
 drivers/gpu/drm/xe/xe_device_sysfs.c | 57 ++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_device_types.h |  8 +++++
 4 files changed, 73 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index f5a581d39c96..f0c88d3297f9 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -8,6 +8,7 @@
 #include <linux/aperture.h>
 #include <linux/delay.h>
 #include <linux/error-injection.h>
+#include <linux/nodemask.h>
 #include <linux/units.h>
 
 #include <drm/drm_client.h>
@@ -439,6 +440,10 @@ struct xe_device *xe_device_create(struct pci_dev *pdev)
 	if (err)
 		return ERR_PTR(err);
 
+	xe->userptr_repin_timeout_ms = num_online_nodes() > 1 ?
+		XE_USERPTR_REPIN_TIMEOUT_MS_NUMA_DEFAULT :
+		XE_USERPTR_REPIN_TIMEOUT_MS_DEFAULT;
+
 	return xe;
 }
 ALLOW_ERROR_INJECTION(xe_device_create, ERRNO); /* See xe_pci_probe() */
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index 7a7632e2d56b..6b1e48369bdd 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -43,6 +43,9 @@ static inline struct xe_device *ttm_to_xe_device(struct ttm_device *ttm)
 	return container_of(ttm, struct xe_device, ttm);
 }
 
+#define XE_USERPTR_REPIN_TIMEOUT_MS_DEFAULT		10000
+#define XE_USERPTR_REPIN_TIMEOUT_MS_NUMA_DEFAULT	30000
+
 struct xe_device *xe_device_create(struct pci_dev *pdev);
 int xe_device_init_early(struct xe_device *xe);
 int xe_device_probe_early(struct xe_device *xe);
diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
index ff5d25dd867c..f6275e74eb31 100644
--- a/drivers/gpu/drm/xe/xe_device_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
@@ -4,7 +4,9 @@
  */
 
 #include <linux/device.h>
+#include <linux/jiffies.h>
 #include <linux/kobject.h>
+#include <linux/limits.h>
 #include <linux/pci.h>
 #include <linux/sysfs.h>
 
@@ -38,6 +40,16 @@
  * reclaimed by the shrinker. Higher values reduce reclaim pressure on
  * non-purgeable buffer objects. Valid values are 1 to 64. Defaults to
  * CONFIG_DRM_XE_SHRINKER_NON_PURGEABLE_SEEKS.
+ *
+ * userptr_repin_timeout_ms - Report/change the overall time, in
+ * milliseconds, a userptr repin is retried, with all locks dropped between
+ * the attempts, when the CPU mappings keep changing during the repin. The
+ * time is measured from the first repin attempt after an invalidation. When
+ * it expires the repin fails with -EBUSY. Zero means retry indefinitely.
+ * Valid values are 0 to INT_MAX (capped by MAX_JIFFY_OFFSET). The value is
+ * read each time the timeout is checked, so a change takes effect
+ * immediately. Defaults to 10000 on single-node systems and 30000 on
+ * multi-node NUMA systems.
  */
 
 static ssize_t
@@ -340,6 +352,47 @@ static const struct attribute_group shrinker_attr_group = {
 	.attrs = shrinker_attrs,
 };
 
+static ssize_t
+userptr_repin_timeout_ms_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
+
+	return sysfs_emit(buf, "%u\n", READ_ONCE(xe->userptr_repin_timeout_ms));
+}
+
+static ssize_t
+userptr_repin_timeout_ms_store(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
+	u32 val;
+	int ret;
+
+	ret = kstrtou32(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val > INT_MAX || msecs_to_jiffies(val) >= MAX_JIFFY_OFFSET)
+		return -EINVAL;
+
+	WRITE_ONCE(xe->userptr_repin_timeout_ms, val);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(userptr_repin_timeout_ms);
+
+static struct attribute *userptr_attrs[] = {
+	&dev_attr_userptr_repin_timeout_ms.attr,
+	NULL
+};
+
+static const struct attribute_group userptr_attr_group = {
+	.attrs = userptr_attrs,
+};
+
 int xe_device_sysfs_init(struct xe_device *xe)
 {
 	struct device *dev = xe->drm.dev;
@@ -349,6 +402,10 @@ int xe_device_sysfs_init(struct xe_device *xe)
 	if (ret)
 		return ret;
 
+	ret = devm_device_add_group(dev, &userptr_attr_group);
+	if (ret)
+		return ret;
+
 	if (xe->d3cold.capable) {
 		ret = devm_device_add_group(dev, &vram_attr_group);
 		if (ret)
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 8f2a31949073..fc80cd2c766e 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -437,6 +437,14 @@ struct xe_device {
 		u16 idx[__XE_CACHE_LEVEL_COUNT];
 	} pat;
 
+	/**
+	 * @userptr_repin_timeout_ms: Overall time in milliseconds a userptr
+	 * repin is retried before failing with -EBUSY. Zero means retry
+	 * indefinitely. Accessed with READ_ONCE() / WRITE_ONCE() and tunable
+	 * through sysfs.
+	 */
+	u32 userptr_repin_timeout_ms;
+
 	/** @d3cold: Encapsulate d3cold related stuff */
 	struct {
 		/** @d3cold.capable: Indicates if root port is d3cold capable */

-- 
2.56.1


  parent reply	other threads:[~2026-11-20 13:03 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-20 13:02 [PATCH v2 0/6] Non-fatal repin retries and NUMA-local rebind worker Matthew Auld
2026-11-20 13:02 ` [PATCH v2 1/6] drm/xe/vm: restore userptr invalidations on VMA op unwind Matthew Auld
2026-11-20 13:02 ` [PATCH v2 2/6] drm/xe/vf: Free preempt fences on rebind worker retry Matthew Auld
2026-11-20 15:59   ` Himal prasad Ghimiray
2026-11-20 13:02 ` [PATCH v2 3/6] drm/xe: Requeue the rebind worker instead of retrying in-line on -EAGAIN Matthew Auld
2026-11-20 13:02 ` Matthew Auld [this message]
2026-11-20 15:56   ` [PATCH v2 4/6] drm/xe: Add a userptr repin timeout sysfs attribute Himal prasad Ghimiray
2026-11-20 13:02 ` [PATCH v2 5/6] drm/xe/userptr: Make the repin retry loop non-fatal Matthew Auld
2026-11-20 14:03   ` sashiko-bot
2026-11-20 14:52     ` Matthew Auld
2026-11-20 13:02 ` [PATCH v2 6/6] drm/xe: run compute rebind worker on device NUMA node Matthew Auld
2026-11-20 13:12 ` ✓ CI.KUnit: success for Non-fatal repin retries and NUMA-local rebind worker (rev2) Patchwork
2026-11-20 13:47 ` ✓ Xe.CI.BAT: " 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=20261120-userptr-repin-v2-4-65e1f6e582ef@intel.com \
    --to=matthew.auld@intel.com \
    --cc=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=stuart.summers@intel.com \
    --cc=thomas.hellstrom@linux.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.