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>,
	"Maarten Lankhorst" <maarten.lankhorst@linux.intel.com>,
	"Matthew Brost" <matthew.brost@intel.com>
Subject: [PATCH v2 2/2] drm/xe: Don't unnecessarily invoke the OOM killer on multiple binds
Date: Thu, 31 Oct 2024 16:37:32 +0100	[thread overview]
Message-ID: <20241031153732.164995-3-thomas.hellstrom@linux.intel.com> (raw)
In-Reply-To: <20241031153732.164995-1-thomas.hellstrom@linux.intel.com>

Multiple single-ioctl binds can be split up into multiple bind
ioctls, reducing the memory required to hold the bind array.

So rather than allowing the OOM killer to be invoked, return
-ENOMEM or -ENOBUFS to user-space to take corrective action.

v2:
- Add __GFP_NOWARN to __GFP_RETRY_MAYFAIL allocations to avoid
  spamming the kernel log if a recoverable allocation fails.

Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2701
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com> #v1
---
 drivers/gpu/drm/xe/xe_vm.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index c99380271de6..624133fae5f5 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -733,7 +733,7 @@ static int xe_vma_ops_alloc(struct xe_vma_ops *vops, bool array_of_binds)
 		vops->pt_update_ops[i].ops =
 			kmalloc_array(vops->pt_update_ops[i].num_ops,
 				      sizeof(*vops->pt_update_ops[i].ops),
-				      GFP_KERNEL);
+				      GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 		if (!vops->pt_update_ops[i].ops)
 			return array_of_binds ? -ENOBUFS : -ENOMEM;
 	}
@@ -2733,7 +2733,8 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe,
 
 		*bind_ops = kvmalloc_array(args->num_binds,
 					   sizeof(struct drm_xe_vm_bind_op),
-					   GFP_KERNEL | __GFP_ACCOUNT);
+					   GFP_KERNEL | __GFP_ACCOUNT |
+					   __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 		if (!*bind_ops)
 			return args->num_binds > 1 ? -ENOBUFS : -ENOMEM;
 
@@ -2973,14 +2974,16 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	if (args->num_binds) {
 		bos = kvcalloc(args->num_binds, sizeof(*bos),
-			       GFP_KERNEL | __GFP_ACCOUNT);
+			       GFP_KERNEL | __GFP_ACCOUNT |
+			       __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 		if (!bos) {
 			err = -ENOMEM;
 			goto release_vm_lock;
 		}
 
 		ops = kvcalloc(args->num_binds, sizeof(*ops),
-			       GFP_KERNEL | __GFP_ACCOUNT);
+			       GFP_KERNEL | __GFP_ACCOUNT |
+			       __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 		if (!ops) {
 			err = -ENOMEM;
 			goto release_vm_lock;
-- 
2.46.2


  parent reply	other threads:[~2024-10-31 15:37 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-31 15:37 [PATCH v2 0/2] drm/xe: Avoid unnecessary OOM kills Thomas Hellström
2024-10-31 15:37 ` [PATCH v2 1/2] drm/xe: Avoid the OOM killer on buffer object memory allocation Thomas Hellström
2024-10-31 15:37 ` Thomas Hellström [this message]
2024-10-31 16:29 ` ✓ CI.Patch_applied: success for drm/xe: Avoid unnecessary OOM kills (rev2) Patchwork
2024-10-31 16:29 ` ✓ CI.checkpatch: " Patchwork
2024-10-31 16:30 ` ✓ CI.KUnit: " Patchwork
2024-10-31 16:42 ` ✓ CI.Build: " Patchwork
2024-10-31 16:44 ` ✓ CI.Hooks: " Patchwork
2024-10-31 16:45 ` ✓ CI.checksparse: " Patchwork
2024-10-31 17:07 ` ✓ CI.BAT: " Patchwork
2024-10-31 20:30 ` ✗ 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=20241031153732.164995-3-thomas.hellstrom@linux.intel.com \
    --to=thomas.hellstrom@linux.intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=matthew.brost@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