Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: daniele.ceraolospurio@intel.com, carlos.santa@intel.com
Subject: [PATCH v2 02/22] drm/xe: Add EXEC_QUEUE_FLAG_CAP_SYS_NICE
Date: Sun,  4 Jan 2026 20:02:17 -0800	[thread overview]
Message-ID: <20260105040237.1307873-3-matthew.brost@intel.com> (raw)
In-Reply-To: <20260105040237.1307873-1-matthew.brost@intel.com>

Store whether CAP_SYS_NICE is set on the user process that creates an
exec queue. This will indicate if the exec queue is eligible for higher
priority levels under deadline pressure.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c       | 3 +++
 drivers/gpu/drm/xe/xe_exec_queue_types.h | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 0b9e074b022f..a9b981591773 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -1158,6 +1158,9 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
 	if (args->flags & DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT)
 		flags |= EXEC_QUEUE_FLAG_LOW_LATENCY;
 
+	if (capable(CAP_SYS_NICE))
+		flags |= EXEC_QUEUE_FLAG_CAP_SYS_NICE;
+
 	if (eci[0].engine_class == DRM_XE_ENGINE_CLASS_VM_BIND) {
 		if (XE_IOCTL_DBG(xe, args->width != 1) ||
 		    XE_IOCTL_DBG(xe, args->num_placements != 1) ||
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 67ea5eebf70b..cd7a6571f5c6 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -128,6 +128,8 @@ struct xe_exec_queue {
 #define EXEC_QUEUE_FLAG_LOW_LATENCY		BIT(5)
 /* for migration (kernel copy, clear, bind) jobs */
 #define EXEC_QUEUE_FLAG_MIGRATE			BIT(6)
+/* for user queues, created in CAP_SYS_NICE context */
+#define EXEC_QUEUE_FLAG_CAP_SYS_NICE		BIT(7)
 
 	/**
 	 * @flags: flags for this exec queue, should statically setup aside from ban
-- 
2.34.1


  parent reply	other threads:[~2026-01-05  4:02 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-05  4:02 [PATCH v2 00/22] Fence deadlines in Xe Matthew Brost
2026-01-05  4:02 ` [PATCH v2 01/22] drm/xe: Add dedicated message lock Matthew Brost
2026-01-05  4:02 ` Matthew Brost [this message]
2026-02-05 16:00   ` [PATCH v2 02/22] drm/xe: Add EXEC_QUEUE_FLAG_CAP_SYS_NICE Rodrigo Vivi
2026-01-05  4:02 ` [PATCH v2 03/22] drm/xe: Store exec queue in hardware fence Matthew Brost
2026-02-05 16:02   ` Rodrigo Vivi
2026-01-05  4:02 ` [PATCH v2 04/22] drm/xe: Add deadline exec queue vfuncs Matthew Brost
2026-02-05 16:03   ` Rodrigo Vivi
2026-01-05  4:02 ` [PATCH v2 05/22] drm/xe: Export to_xe_hw_fence Matthew Brost
2026-01-05  4:02 ` [PATCH v2 06/22] drm/xe: Export xe_hw_fence_signaled Matthew Brost
2026-01-05  4:02 ` [PATCH v2 07/22] drm/xe: Implement deadline manager Matthew Brost
2026-01-05  4:02 ` [PATCH v2 08/22] drm/xe: Initialize deadline manager on exec queues Matthew Brost
2026-01-05  4:02 ` [PATCH v2 09/22] drm/xe: Stub out execlists deadline vfuncs as NOPs Matthew Brost
2026-01-05  4:02 ` [PATCH v2 10/22] drm/xe: Make scheduler message lock IRQ-safe Matthew Brost
2026-01-05  4:02 ` [PATCH v2 11/22] drm/xe: Support unstable opcodes for static scheduler messages Matthew Brost
2026-01-05  4:02 ` [PATCH v2 12/22] drm/xe: Implement GuC submission backend ops for deadlines Matthew Brost
2026-01-10 10:48   ` kernel test robot
2026-01-05  4:02 ` [PATCH v2 13/22] drm/xe: Enable deadlines on hardware fences Matthew Brost
2026-01-05  4:02 ` [PATCH v2 14/22] drm/xe: Fix Kconfig.profile newlines Matthew Brost
2026-02-05 16:06   ` Rodrigo Vivi
2026-01-05  4:02 ` [PATCH v2 15/22] drm/xe: Add deadline Kconfig options Matthew Brost
2026-01-05  4:02 ` [PATCH v2 16/22] drm/xe: Add exec queue deadline trace points Matthew Brost
2026-01-05  4:02 ` [PATCH v2 17/22] drm/xe: Add hw fence " Matthew Brost
2026-01-05  4:02 ` [PATCH v2 18/22] drm/xe: Add timestamp_ms to LRC snapshot Matthew Brost
2026-01-05  4:02 ` [PATCH v2 19/22] drm/xe: Enforce GuC static message defines Matthew Brost
2026-01-05  4:02 ` [PATCH v2 20/22] drm/xe: Document the deadline manager Matthew Brost
2026-01-05  4:02 ` [PATCH v2 21/22] drm/atomic: Export fence deadline helper for atomic commits Matthew Brost
2026-01-05  4:02 ` [PATCH v2 22/22] drm/i915/display: Use atomic helper to set plane fence deadlines Matthew Brost
2026-01-05  4:09 ` ✗ CI.checkpatch: warning for Fence deadlines in Xe (rev2) Patchwork
2026-01-05  4:10 ` ✓ CI.KUnit: success " Patchwork
2026-01-05  4:26 ` ✗ CI.checksparse: warning " Patchwork
2026-01-05  5:07 ` ✓ Xe.CI.BAT: success " Patchwork
2026-01-05  6:51 ` ✗ Xe.CI.Full: 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=20260105040237.1307873-3-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=carlos.santa@intel.com \
    --cc=daniele.ceraolospurio@intel.com \
    --cc=intel-xe@lists.freedesktop.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