torvalds/linux
torvalds/linux
2
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
Code

drm/msm: Mark VM as unusable on GPU hangs

Browse Source 
If userspace has opted-in to VM_BIND, then GPU hangs and VM_BIND errors
will mark the VM as unusable.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Tested-by: Antonino Maniscalco <antomani103@gmail.com>
Reviewed-by: Antonino Maniscalco <antomani103@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/661499/
This commit is contained in:
Rob Clark 2025-06-29 13:13:06 -07:00 committed by Rob Clark
parent feb8ef4636
commit 6a4d287a1a
3 changed files with 34 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
drivers/gpu/drm/msm/msm_gem.h
View File

@ -76,6 +76,23 @@ struct msm_gem_vm {
/** @managed: is this a kernel managed VM? */ /** @managed: is this a kernel managed VM? */
bool managed; bool managed;
/**
* @unusable: True if the VM has turned unusable because something
* bad happened during an asynchronous request.
*
* We don't try to recover from such failures, because this implies
* informing userspace about the specific operation that failed, and
* hoping the userspace driver can replay things from there. This all
* sounds very complicated for little gain.
*
* Instead, we should just flag the VM as unusable, and fail any
* further request targeting this VM.
*
* As an analogy, this would be mapped to a VK_ERROR_DEVICE_LOST
* situation, where the logical device needs to be re-created.
*/
bool unusable;
}; };
#define to_msm_vm(x) container_of(x, struct msm_gem_vm, base) #define to_msm_vm(x) container_of(x, struct msm_gem_vm, base)

3
drivers/gpu/drm/msm/msm_gem_submit.c
View File

@ -681,6 +681,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
if (args->pad) if (args->pad)
return -EINVAL; return -EINVAL;
if (to_msm_vm(ctx->vm)->unusable)
return UERR(EPIPE, dev, "context is unusable");
/* for now, we just have 3d pipe.. eventually this would need to /* for now, we just have 3d pipe.. eventually this would need to
* be more clever to dispatch to appropriate gpu module: * be more clever to dispatch to appropriate gpu module:
*/ */

16
drivers/gpu/drm/msm/msm_gpu.c
View File

@ -389,8 +389,20 @@ static void recover_worker(struct kthread_work *work)
/* Increment the fault counts */ /* Increment the fault counts */
submit->queue->faults++; submit->queue->faults++;
if (submit->vm) if (submit->vm) {
to_msm_vm(submit->vm)->faults++; struct msm_gem_vm *vm = to_msm_vm(submit->vm);
vm->faults++;
/*
* If userspace has opted-in to VM_BIND (and therefore userspace
* management of the VM), faults mark the VM as unusuable. This
* matches vulkan expectations (vulkan is the main target for
* VM_BIND)
*/
if (!vm->managed)
vm->unusable = true;
}
get_comm_cmdline(submit, &comm, &cmd); get_comm_cmdline(submit, &comm, &cmd);