drm/xe: Hold a PM ref when GT TLB invalidations are inflight

Avoid GT TLB invalidation timeouts by holding a PM ref when
invalidations are inflight.

v2:
 - Drop PM ref before signaling fence (CI)
v3:
 - Move invalidation_fence_signal helper in tlb timeout to previous
   patch (Matthew Auld)

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-4-matthew.brost@intel.com

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index c3419d4412ce85340b6deb15abd5425c00a81873..481d83d07367d23df42d7fd97fbae65617bee94e 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -13,6 +13,7 @@
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_mmio.h"
+#include "xe_pm.h"
 #include "xe_sriov.h"
 #include "xe_trace.h"
 #include "regs/xe_guc_regs.h"
@@ -41,6 +42,7 @@ __invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_
        bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
 
        trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
+       xe_gt_tlb_invalidation_fence_fini(fence);
        dma_fence_signal(&fence->base);
        if (!stack)
                dma_fence_put(&fence->base);
@@ -263,8 +265,10 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 
                xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
                ret = xe_gt_tlb_invalidation_guc(gt, &fence);
-               if (ret < 0)
+               if (ret < 0) {
+                       xe_gt_tlb_invalidation_fence_fini(&fence);
                        return ret;
+               }
 
                xe_gt_tlb_invalidation_fence_wait(&fence);
        } else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
@@ -489,12 +493,15 @@ static const struct dma_fence_ops invalidation_fence_ops = {
  * @fence: TLB invalidation fence to initialize
  * @stack: fence is stack variable
  *
- * Initialize TLB invalidation fence for use
+ * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
+ * must be called if fence is not signaled.
  */
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
                                       struct xe_gt_tlb_invalidation_fence *fence,
                                       bool stack)
 {
+       xe_pm_runtime_get_noresume(gt_to_xe(gt));
+
        spin_lock_irq(&gt->tlb_invalidation.lock);
        dma_fence_init(&fence->base, &invalidation_fence_ops,
                       &gt->tlb_invalidation.lock,
@@ -505,4 +512,16 @@ void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
                set_bit(FENCE_STACK_BIT, &fence->base.flags);
        else
                dma_fence_get(&fence->base);
+       fence->gt = gt;
+}
+
+/**
+ * xe_gt_tlb_invalidation_fence_fini - Finalize TLB invalidation fence
+ * @fence: TLB invalidation fence to finalize
+ *
+ * Drop PM ref which fence took durinig init.
+ */
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+{
+       xe_pm_runtime_put(gt_to_xe(fence->gt));
 }

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index f430d5797af701cd500f8b890169ffbeef9403fd..a84065fa324c766ad5c81889333bb738c409684b 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -28,6 +28,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
                                       struct xe_gt_tlb_invalidation_fence *fence,
                                       bool stack);
+void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence);
 
 static inline void
 xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
index 934c828efe31cb728d7e751555e9525233f30ae6..de6e825e0851e5097443b0ebec0cbddaa75cb3d6 100644 (file)
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
@@ -8,6 +8,8 @@
 
 #include <linux/dma-fence.h>
 
+struct xe_gt;
+
 /**
  * struct xe_gt_tlb_invalidation_fence - XE GT TLB invalidation fence
  *
@@ -17,6 +19,8 @@
 struct xe_gt_tlb_invalidation_fence {
        /** @base: dma fence base */
        struct dma_fence base;
+       /** @gt: GT which fence belong to */
+       struct xe_gt *gt;
        /** @link: link into list of pending tlb fences */
        struct list_head link;
        /** @seqno: seqno of TLB invalidation to signal fence one */

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 86e9e2f877e51f175bd6f8bbced6cc4643da6b54..d8e099347df09b3c1caee3eca9b197c119c06d07 100644 (file)
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3218,8 +3218,10 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
                         */
                        ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
                                                         &fence[id], vma);
-                       if (ret < 0)
+                       if (ret < 0) {
+                               xe_gt_tlb_invalidation_fence_fini(&fence[id]);
                                goto wait;
+                       }
 
                        tile_needs_invalidate |= BIT(id);
                }