Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: intel-xe@lists.freedesktop.org
Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"John Falkowski" <john.falkowski@intel.com>,
	"Michal Mrozek" <michal.mrozek@intel.com>,
	"Matthew Brost" <matthew.brost@intel.com>
Subject: [PATCH] drm/xe/uapi: Introduce a flag to disallow vm overcommit in fault mode
Date: Wed,  4 Feb 2026 16:33:20 +0100	[thread overview]
Message-ID: <20260204153320.17989-1-thomas.hellstrom@linux.intel.com> (raw)

Some compute applications may try to allocate device memory to probe
how much device memory is actually available, assuming that the
application will be the only one running on the particular GPU.

That strategy fails in fault mode since it allows VM overcommit.

While this could be resolved in user-space it's further complicated
by cgroups potentially restricting the amount of memory available
to the application.

Introduce a vm create flag, DRM_XE_VM_CREATE_NO_VM_OVERCOMMIT, that
allows fault mode to mimic the behaviour of !fault mode WRT this. It
blocks evicting same vm bos during VM_BIND processing. However,
it does *not* block evicting same-vm bos during pagefault
processing, preferring eviction rather than VM banning in
OOM situations.

Cc: John Falkowski <john.falkowski@intel.com>
Cc: Michal Mrozek <michal.mrozek@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c       | 11 +++++++++--
 drivers/gpu/drm/xe/xe_vm.h       |  7 +++++++
 drivers/gpu/drm/xe/xe_vm_types.h |  1 +
 include/uapi/drm/xe_drm.h        |  6 ++++++
 4 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 8fe54a998385..cf92b6e13a16 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1938,7 +1938,8 @@ find_ufence_get(struct xe_sync_entry *syncs, u32 num_syncs)
 
 #define ALL_DRM_XE_VM_CREATE_FLAGS (DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE | \
 				    DRM_XE_VM_CREATE_FLAG_LR_MODE | \
-				    DRM_XE_VM_CREATE_FLAG_FAULT_MODE)
+				    DRM_XE_VM_CREATE_FLAG_FAULT_MODE | \
+				    DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT)
 
 int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file)
@@ -1977,12 +1978,18 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE))
 		return -EINVAL;
 
+	if (XE_IOCTL_DBG(xe, !(args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE) &&
+			 args->flags & DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT))
+		return -EINVAL;
+
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE)
 		flags |= XE_VM_FLAG_SCRATCH_PAGE;
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_LR_MODE)
 		flags |= XE_VM_FLAG_LR_MODE;
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE)
 		flags |= XE_VM_FLAG_FAULT_MODE;
+	if (args->flags & DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT)
+		flags |= XE_VM_FLAG_NO_VM_OVERCOMMIT;
 
 	vm = xe_vm_create(xe, flags, xef);
 	if (IS_ERR(vm))
@@ -2903,7 +2910,7 @@ static int vma_lock_and_validate(struct drm_exec *exec, struct xe_vma *vma,
 			err = drm_exec_lock_obj(exec, &bo->ttm.base);
 		if (!err && validate)
 			err = xe_bo_validate(bo, vm,
-					     !xe_vm_in_preempt_fence_mode(vm) &&
+					     xe_vm_allow_vm_eviction(vm) &&
 					     res_evict, exec);
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 288115c7844a..f849e369432b 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -220,6 +220,13 @@ static inline bool xe_vm_in_preempt_fence_mode(struct xe_vm *vm)
 	return xe_vm_in_lr_mode(vm) && !xe_vm_in_fault_mode(vm);
 }
 
+static inline bool xe_vm_allow_vm_eviction(struct xe_vm *vm)
+{
+	return !xe_vm_in_lr_mode(vm) ||
+		(xe_vm_in_fault_mode(vm) &&
+		 !(vm->flags & XE_VM_FLAG_NO_VM_OVERCOMMIT));
+}
+
 int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q);
 void xe_vm_remove_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 43203e90ee3e..1f6f7e30e751 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -232,6 +232,7 @@ struct xe_vm {
 #define XE_VM_FLAG_TILE_ID(flags)	FIELD_GET(GENMASK(7, 6), flags)
 #define XE_VM_FLAG_SET_TILE_ID(tile)	FIELD_PREP(GENMASK(7, 6), (tile)->id)
 #define XE_VM_FLAG_GSC			BIT(8)
+#define XE_VM_FLAG_NO_VM_OVERCOMMIT     BIT(9)
 	unsigned long flags;
 
 	/**
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 077e66a682e2..e54f8e12acd9 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -975,6 +975,11 @@ struct drm_xe_gem_mmap_offset {
  *    demand when accessed, and also allows per-VM overcommit of memory.
  *    The xe driver internally uses recoverable pagefaults to implement
  *    this.
+ *  - %DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT - Requires also
+ *    DRM_XE_VM_CREATE_FLAG_FAULT_MODE. This disallows per-VM overcommit
+ *    but only during a &DRM_IOCTL_XE_VM_BIND operation with the
+ *    %DRM_XE_VM_BIND_FLAG_IMMEDIATE flag set. This may be useful for
+ *    user-space naively probing the amount of available memory.
  */
 struct drm_xe_vm_create {
 	/** @extensions: Pointer to the first extension struct, if any */
@@ -983,6 +988,7 @@ struct drm_xe_vm_create {
 #define DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE	(1 << 0)
 #define DRM_XE_VM_CREATE_FLAG_LR_MODE	        (1 << 1)
 #define DRM_XE_VM_CREATE_FLAG_FAULT_MODE	(1 << 2)
+#define DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT  (1 << 3)
 	/** @flags: Flags */
 	__u32 flags;
 
-- 
2.52.0


             reply	other threads:[~2026-02-04 15:33 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-04 15:33 Thomas Hellström [this message]
2026-02-04 18:56 ` [PATCH] drm/xe/uapi: Introduce a flag to disallow vm overcommit in fault mode Matthew Brost
2026-02-05  8:06   ` Thomas Hellström
2026-02-05 17:58     ` Matthew Brost
2026-02-05  0:50 ` ✓ CI.KUnit: success for " Patchwork
2026-02-05  1:23 ` ✓ Xe.CI.BAT: " Patchwork
2026-02-05 16:14 ` ✓ Xe.CI.FULL: " 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=20260204153320.17989-1-thomas.hellstrom@linux.intel.com \
    --to=thomas.hellstrom@linux.intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=john.falkowski@intel.com \
    --cc=matthew.brost@intel.com \
    --cc=michal.mrozek@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