drm/amdgpu: Move VM PTE MTYPE override to per-PTE granularity

Refactor the NUMA-aware MTYPE override for VM page table entries:

Move the override_vm_pte_flags call from the centralized
amdgpu_vm_pte_update_flags() into the individual CPU and SDMA update
backends, enabling per-PTE MTYPE override including for scattered
pages (pages_addr path).

Move APU, IP version, and direct-mapped eligibility checks from
runtime (gmc_v9_0_override_vm_pte_flags) to init time
(gmc_v9_0_set_gmc_funcs), to avoid repeated runtime checks on
every PTE update.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

7 files changed, 41 insertions, 35 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 6ab4c1e297fc..c6d7a9e54eb3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -365,6 +365,8 @@ struct amdgpu_gmc {
 	bool flush_tlb_needs_extra_type_0;
 	bool flush_tlb_needs_extra_type_2;
 	bool flush_pasid_uses_kiq;
+
+	bool override_pte;
 };
 
 #define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 9ba9de16a27a..2f2ac3c4c2f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1163,7 +1163,7 @@ int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	params.pages_addr = pages_addr;
 	params.unlocked = unlocked;
 	params.needs_flush = flush_tlb;
-	params.allow_override = allow_override;
+	params.override_pte = allow_override && adev->gmc.override_pte;
 	INIT_LIST_HEAD(&params.tlb_flush_waitlist);
 
 	amdgpu_vm_eviction_lock(vm);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index d083d7aab75c..f4b0e9da3fa2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -296,10 +296,10 @@ struct amdgpu_vm_update_params {
 	bool needs_flush;
 
 	/**
-	 * @allow_override: true for memory that is not uncached: allows MTYPE
-	 * to be overridden for NUMA local memory.
+	 * @override_pte: true for memory that is not uncached and gmc override function is
+	 * implemented to allow MTYPE to be overridden for NUMA local memory.
 	 */
-	bool allow_override;
+	bool override_pte;
 
 	/**
 	 * @tlb_flush_waitlist: temporary storage for BOs until tlb_flush
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
index f078db3fef79..b31ff6f56f0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
@@ -88,12 +88,21 @@ static int amdgpu_vm_cpu_update(struct amdgpu_vm_update_params *p,
 
 	trace_amdgpu_vm_set_ptes(pe, addr, count, incr, flags, p->immediate);
 
+	if (!p->pages_addr && p->override_pte)
+		amdgpu_gmc_override_vm_pte_flags(p->adev, p->vm, addr, &flags);
+
 	for (i = 0; i < count; i++) {
+		u64 oflags = flags;
+
 		value = p->pages_addr ?
 			amdgpu_vm_map_gart(p->pages_addr, addr) :
 			addr;
+
+		if (p->pages_addr && p->override_pte)
+			amdgpu_gmc_override_vm_pte_flags(p->adev, p->vm, value, &oflags);
+
 		amdgpu_gmc_set_pte_pde(p->adev, (void *)(uintptr_t)pe,
-				       i, value, flags);
+				       i, value, oflags);
 		addr += incr;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index a930f1522f96..b2494381b98a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -710,15 +710,6 @@ static void amdgpu_vm_pte_update_flags(struct amdgpu_vm_update_params *params,
 	if (level == AMDGPU_VM_PTB)
 		amdgpu_vm_pte_update_noretry_flags(adev, &flags);
 
-	/* APUs mapping system memory may need different MTYPEs on different
-	 * NUMA nodes. Only do this for contiguous ranges that can be assumed
-	 * to be on the same NUMA node.
-	 */
-	if ((flags & AMDGPU_PTE_SYSTEM) && (adev->flags & AMD_IS_APU) &&
-	    adev->gmc.gmc_funcs->override_vm_pte_flags &&
-	    num_possible_nodes() > 1 && !params->pages_addr && params->allow_override)
-		amdgpu_gmc_override_vm_pte_flags(adev, params->vm, addr, &flags);
-
 	params->vm->update_funcs->update(params, pt, pe, addr, count, incr,
 					 flags);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 36805dcfa159..2eb64df6daa9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -257,6 +257,9 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p,
 		}
 
 		if (!p->pages_addr) {
+			if (p->override_pte)
+				amdgpu_gmc_override_vm_pte_flags(p->adev, p->vm, addr, &flags);
+
 			/* set page commands needed */
 			amdgpu_vm_sdma_set_ptes(p, bo, pe, addr, count,
 						incr, flags);
@@ -275,8 +278,14 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p,
 		p->num_dw_left -= nptes * 2;
 		pte = (uint64_t *)&(p->job->ibs->ptr[p->num_dw_left]);
 		for (i = 0; i < nptes; ++i, addr += incr) {
+			u64 oflags = flags;
+
 			pte[i] = amdgpu_vm_map_gart(p->pages_addr, addr);
-			pte[i] |= flags;
+
+			if (p->override_pte)
+				amdgpu_gmc_override_vm_pte_flags(p->adev, p->vm, pte[i], &oflags);
+
+			pte[i] |= oflags;
 		}
 
 		amdgpu_vm_sdma_copy_ptes(p, bo, pe, nptes);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index e7b78027002b..aca7841173f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1204,21 +1204,6 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
 {
 	int local_node, nid;
 
-	/* Only GFX 9.4.3 APUs associate GPUs with NUMA nodes. Local system
-	 * memory can use more efficient MTYPEs.
-	 */
-	if (!(adev->flags & AMD_IS_APU) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(9, 4, 3))
-		return;
-
-	/* Only direct-mapped memory allows us to determine the NUMA node from
-	 * the DMA address.
-	 */
-	if (!adev->ram_is_direct_mapped) {
-		dev_dbg_ratelimited(adev->dev, "RAM is not direct mapped\n");
-		return;
-	}
-
 	/* MTYPE_NC is the same default and can be overridden.
 	 * MTYPE_UC will be present if the memory is extended-coherent
 	 * and can also be overridden.
@@ -1231,11 +1216,7 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
 		return;
 	}
 
-	/* FIXME: Only supported on native mode for now. For carve-out, the
-	 * NUMA affinity of the GPU/VM needs to come from the PCI info because
-	 * memory partitions are not associated with different NUMA nodes.
-	 */
-	if (adev->gmc.is_app_apu && vm->mem_id >= 0) {
+	if (vm->mem_id >= 0) {
 		local_node = adev->gmc.mem_partitions[vm->mem_id].numa.node;
 	} else {
 		dev_dbg_ratelimited(adev->dev, "Only native mode APU is supported.\n");
@@ -1344,6 +1325,20 @@ static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 static void gmc_v9_0_set_gmc_funcs(struct amdgpu_device *adev)
 {
 	adev->gmc.gmc_funcs = &gmc_v9_0_gmc_funcs;
+
+	/* Only GFX 9.4.3 APUs associate GPUs with NUMA nodes, local system
+	 * memory can use more efficient MTYPEs.
+	 *
+	 * APUs mapping system memory may need different MTYPEs on different
+	 * NUMA nodes.
+	 *
+	 * Only direct-mapped memory allows us to determine the NUMA node from
+	 * the DMA address.
+	 */
+	adev->gmc.override_pte = adev->gmc.is_app_apu &&
+				 num_possible_nodes() > 1 &&
+				 amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) &&
+				 adev->ram_is_direct_mapped;
 }
 
 static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)