drm/xe: Timeslice GPU on atomic SVM fault

Ensure GPU can make forward progress on an atomic SVM GPU fault by
giving the GPU a timeslice of 5ms

v2:
 - Reduce timeslice to 5ms
 - Double timeslice on retry
 - Split out GPU SVM changes into independent patch
v5:
 - Double timeslice in a few more places

Fixes: 2f118c949160 ("drm/xe: Add SVM VRAM migration")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://lore.kernel.org/r/20250512135500.1405019-5-matthew.brost@intel.com

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index d8e15259a8dfc5b653bb0d1b13f658fb2da94d4d..d934df622276a690b0aa41fe77ca06d2b713de35 100644 (file)
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -797,6 +797,8 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
                        IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0,
                .devmem_only = atomic && IS_DGFX(vm->xe) &&
                        IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
+               .timeslice_ms = atomic && IS_DGFX(vm->xe) &&
+                       IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? 5 : 0,
        };
        struct xe_svm_range *range;
        struct drm_gpusvm_range *r;
@@ -836,6 +838,7 @@ retry:
        if (--migrate_try_count >= 0 &&
            xe_svm_range_needs_migrate_to_vram(range, vma)) {
                err = xe_svm_alloc_vram(vm, tile, range, &ctx);
+               ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */
                if (err) {
                        if (migrate_try_count || !ctx.devmem_only) {
                                drm_dbg(&vm->xe->drm,
@@ -855,6 +858,7 @@ retry:
        err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx);
        /* Corner where CPU mappings have changed */
        if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) {
+               ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */
                if (migrate_try_count > 0 || !ctx.devmem_only) {
                        if (err == -EOPNOTSUPP) {
                                range_debug(range, "PAGE FAULT - EVICT PAGES");
@@ -894,6 +898,7 @@ retry_bind:
                        drm_exec_fini(&exec);
                        err = PTR_ERR(fence);
                        if (err == -EAGAIN) {
+                               ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */
                                range_debug(range, "PAGE FAULT - RETRY BIND");
                                goto retry;
                        }