drm/amdgpu: Optimize VM invalidation engine allocation and synchronize GPU TLB flush

- Modify the VM invalidation engine allocation logic to handle SDMA page rings.
  SDMA page rings now share the VM invalidation engine with SDMA gfx rings instead of
  allocating a separate engine. This change ensures efficient resource management and
  avoids the issue of insufficient VM invalidation engines.

- Add synchronization for GPU TLB flush operations in gmc_v9_0.c.
  Use spin_lock and spin_unlock to ensure thread safety and prevent race conditions
  during TLB flush operations. This improves the stability and reliability of the driver,
  especially in multi-threaded environments.

 v2: replace the sdma ring check with a function `amdgpu_sdma_is_page_queue`
 to check if a ring is an SDMA page queue.(Lijo)

 v3: Add GC version check, only enabled on GC9.4.3/9.4.4/9.5.0
 v4: Fix code style and add more detailed description (Christian)
 v5: Remove dependency on vm_inv_eng loop order, explicitly lookup shared inv_eng(Christian/Lijo)
 v6: Added search shared ring function amdgpu_sdma_get_shared_ring (Lijo)

Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

@@ -573,6 +573,7 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] = {0};
 	unsigned i;
 	unsigned vmhub, inv_eng;
+	struct amdgpu_ring *shared_ring;
 
 	/* init the vm inv eng for all vmhubs */
 	for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS) {
@@ -595,6 +596,10 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 		    ring == &adev->cper.ring_buf)
 			continue;
 
+		/* Skip if the ring is a shared ring */
+		if (amdgpu_sdma_is_shared_inv_eng(adev, ring))
+			continue;
+
 		inv_eng = ffs(vm_inv_engs[vmhub]);
 		if (!inv_eng) {
 			dev_err(adev->dev, "no VM inv eng for ring %s\n",
@@ -607,6 +612,21 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 
 		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
 			 ring->name, ring->vm_inv_eng, ring->vm_hub);
+		/* SDMA has a special packet which allows it to use the same
+		 * invalidation engine for all the rings in one instance.
+		 * Therefore, we do not allocate a separate VM invalidation engine
+		 * for SDMA page rings. Instead, they share the VM invalidation
+		 * engine with the SDMA gfx ring. This change ensures efficient
+		 * resource management and avoids the issue of insufficient VM
+		 * invalidation engines.
+		 */
+		shared_ring = amdgpu_sdma_get_shared_ring(adev, ring);
+		if (shared_ring) {
+			shared_ring->vm_inv_eng = ring->vm_inv_eng;
+			dev_info(adev->dev, "ring %s shares VM invalidation engine %u with ring %s on hub %u\n",
+					ring->name, ring->vm_inv_eng, shared_ring->name, ring->vm_hub);
+			continue;
+		}
 	}
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c

@@ -504,6 +504,39 @@ void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
 	}
 }
 
+struct amdgpu_ring *amdgpu_sdma_get_shared_ring(struct amdgpu_device *adev, struct amdgpu_ring *ring)
+{
+	if (adev->sdma.has_page_queue &&
+	    (ring->me < adev->sdma.num_instances) &&
+	    (ring == &adev->sdma.instance[ring->me].ring))
+		return &adev->sdma.instance[ring->me].page;
+	else
+		return NULL;
+}
+
+/**
+* amdgpu_sdma_is_shared_inv_eng - Check if a ring is an SDMA ring that shares a VM invalidation engine
+* @adev: Pointer to the AMDGPU device structure
+* @ring: Pointer to the ring structure to check
+*
+* This function checks if the given ring is an SDMA ring that shares a VM invalidation engine.
+* It returns true if the ring is such an SDMA ring, false otherwise.
+*/
+bool amdgpu_sdma_is_shared_inv_eng(struct amdgpu_device *adev, struct amdgpu_ring *ring)
+{
+	int i = ring->me;
+
+	if (!adev->sdma.has_page_queue || i >= adev->sdma.num_instances)
+		return false;
+
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
+	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+		return (ring == &adev->sdma.instance[i].page);
+	else
+		return false;
+}
+
 /**
  * amdgpu_sdma_register_on_reset_callbacks - Register SDMA reset callbacks
  * @funcs: Pointer to the callback structure containing pre_reset and post_reset functions
@@ -544,7 +577,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 {
 	struct sdma_on_reset_funcs *funcs;
 	int ret = 0;
-	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];;
+	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
 	struct amdgpu_ring *gfx_ring = &sdma_instance->ring;
 	struct amdgpu_ring *page_ring = &sdma_instance->page;
 	bool gfx_sched_stopped = false, page_sched_stopped = false;

drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h

@@ -196,4 +196,7 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev);
 int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev);
 void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev);
+bool amdgpu_sdma_is_shared_inv_eng(struct amdgpu_device *adev, struct amdgpu_ring *ring);
+struct amdgpu_ring *amdgpu_sdma_get_shared_ring(struct amdgpu_device *adev,
+	struct amdgpu_ring *ring);
 #endif