[RFC PATCH v2 4/5] drm/amd: Fix MQD and control stack alignment for non-4K

[Donet Tom <donettom@linux.ibm.com>]

For gfxV9, due to a hardware bug ("based on the comments in the code
here [1]"), the control stack of a user-mode compute queue must be
allocated immediately after the page boundary of its regular MQD buffer.
To handle this, we allocate an enlarged MQD buffer where the first page
is used as the MQD and the remaining pages store the control stack.
Although these regions share the same BO, they require different memory
types: the MQD must be UC (uncached), while the control stack must be
NC (non-coherent), matching the behavior when the control stack is
allocated in user space.

This logic works correctly on systems where the CPU page size matches
the GPU page size (4K). However, the current implementation aligns both
the MQD and the control stack to the CPU PAGE_SIZE. On systems with a
larger CPU page size, the entire first CPU page is marked UC—even though
that page may contain multiple GPU pages. The GPU treats the second 4K
GPU page inside that CPU page as part of the control stack, but it is
incorrectly mapped as UC.

This patch fixes the issue by aligning both the MQD and control stack
sizes to the GPU page size (4K). The first 4K page is correctly marked
as UC for the MQD, and the remaining GPU pages are marked NC for the
control stack. This ensures proper memory type assignment on systems
with larger CPU page sizes.

[1]: https://elixir.bootlin.com/linux/v6.18/source/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c#L118

Signed-off-by: Donet Tom <donettom@linux.ibm.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c      | 44 +++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h      |  2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       | 16 ++-----
 .../gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c   | 23 ++++++----
 4 files changed, 64 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 1485f4789440..31fa0d9c4dd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -403,6 +403,50 @@ void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
 	drm_dev_exit(idx);
 }
 
+/**
+ * amdgpu_gart_map_gfx9_mqd - map mqd and ctrl_stack dma_addresses into GART entries
+ *
+ * @adev: amdgpu_device pointer
+ * @offset: offset into the GPU's gart aperture
+ * @pages: number of pages to bind
+ * @dma_addr: DMA addresses of pages
+ * @flags: page table entry flags
+ *
+ * Map the MQD and control stack addresses into GART entries with the correct
+ * memory types on gfxv9. The MQD occupies the first 4KB and is followed by
+ * the control stack. The MQD uses UC (uncached) memory, while the control stack
+ * uses NC (non-coherent) memory.
+ */
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags)
+{
+	uint64_t page_base;
+	unsigned int i, j, t;
+	int idx;
+	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
+	void *dst;
+
+	if (!adev->gart.ptr)
+		return;
+
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return;
+
+	t = offset / AMDGPU_GPU_PAGE_SIZE;
+	dst = adev->gart.ptr;
+	for (i = 0; i < pages; i++) {
+		page_base = dma_addr[i];
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
+			if ((i == 0) && (j == 0))
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
+			else
+				amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, ctrl_flags);
+			page_base += AMDGPU_GPU_PAGE_SIZE;
+		}
+	}
+	drm_dev_exit(idx);
+}
+
 /**
  * amdgpu_gart_bind - bind pages into the gart page table
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index d3118275ddae..6ebd2da32ea6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -62,6 +62,8 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 void amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 		     int pages, dma_addr_t *dma_addr, uint64_t flags,
 		     void *dst);
+void amdgpu_gart_map_gfx9_mqd(struct amdgpu_device *adev, uint64_t offset,
+			int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 		      int pages, dma_addr_t *dma_addr, uint64_t flags);
 void amdgpu_gart_map_vram_range(struct amdgpu_device *adev, uint64_t pa,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e4a11944a1fe..bae53779f8ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -841,25 +841,15 @@ static void amdgpu_ttm_gart_bind_gfx9_mqd(struct amdgpu_device *adev,
 	int num_xcc = max(1U, adev->gfx.num_xcc_per_xcp);
 	uint64_t page_idx, pages_per_xcc;
 	int i;
-	uint64_t ctrl_flags = AMDGPU_PTE_MTYPE_VG10(flags, AMDGPU_MTYPE_NC);
 
 	pages_per_xcc = total_pages;
 	do_div(pages_per_xcc, num_xcc);
 
 	for (i = 0, page_idx = 0; i < num_xcc; i++, page_idx += pages_per_xcc) {
-		/* MQD page: use default flags */
-		amdgpu_gart_bind(adev,
+		amdgpu_gart_map_gfx9_mqd(adev,
 				gtt->offset + (page_idx << PAGE_SHIFT),
-				1, &gtt->ttm.dma_address[page_idx], flags);
-		/*
-		 * Ctrl pages - modify the memory type to NC (ctrl_flags) from
-		 * the second page of the BO onward.
-		 */
-		amdgpu_gart_bind(adev,
-				gtt->offset + ((page_idx + 1) << PAGE_SHIFT),
-				pages_per_xcc - 1,
-				&gtt->ttm.dma_address[page_idx + 1],
-				ctrl_flags);
+				pages_per_xcc, &gtt->ttm.dma_address[page_idx],
+				flags);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index f2dee320fada..2b0654572e7a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -42,9 +42,16 @@ static uint64_t mqd_stride_v9(struct mqd_manager *mm,
 				struct queue_properties *q)
 {
 	if (mm->dev->kfd->cwsr_enabled &&
-	    q->type == KFD_QUEUE_TYPE_COMPUTE)
-		return ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-			ALIGN(sizeof(struct v9_mqd), PAGE_SIZE);
+	    q->type == KFD_QUEUE_TYPE_COMPUTE) {
+
+		/* On gfxv9, the MQD resides in the first 4K page,
+		 * followed by the control stack. Align both to
+		 * AMDGPU_GPU_PAGE_SIZE to maintain the required 4K boundary.
+		 */
+
+		return ALIGN(ALIGN(q->ctl_stack_size, AMDGPU_GPU_PAGE_SIZE) +
+			ALIGN(sizeof(struct v9_mqd), AMDGPU_GPU_PAGE_SIZE), PAGE_SIZE);
+	}
 
 	return mm->mqd_size;
 }
@@ -136,8 +143,8 @@ static struct kfd_mem_obj *allocate_mqd(struct kfd_node *node,
 		if (!mqd_mem_obj)
 			return NULL;
 		retval = amdgpu_amdkfd_alloc_gtt_mem(node->adev,
-			(ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-			ALIGN(sizeof(struct v9_mqd), PAGE_SIZE)) *
+			(ALIGN(ALIGN(q->ctl_stack_size, AMDGPU_GPU_PAGE_SIZE) +
+			ALIGN(sizeof(struct v9_mqd), AMDGPU_GPU_PAGE_SIZE), PAGE_SIZE)) *
 			NUM_XCC(node->xcc_mask),
 			&(mqd_mem_obj->gtt_mem),
 			&(mqd_mem_obj->gpu_addr),
@@ -343,7 +350,7 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	struct kfd_context_save_area_header header;
 
 	/* Control stack is located one page after MQD. */
-	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + AMDGPU_GPU_PAGE_SIZE);
 
 	m = get_mqd(mqd);
 
@@ -380,7 +387,7 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, voi
 {
 	struct v9_mqd *m;
 	/* Control stack is located one page after MQD. */
-	void *ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
+	void *ctl_stack = (void *)((uintptr_t)mqd + AMDGPU_GPU_PAGE_SIZE);
 
 	m = get_mqd(mqd);
 
@@ -426,7 +433,7 @@ static void restore_mqd(struct mqd_manager *mm, void **mqd,
 		*gart_addr = addr;
 
 	/* Control stack is located one page after MQD. */
-	ctl_stack = (void *)((uintptr_t)*mqd + PAGE_SIZE);
+	ctl_stack = (void *)((uintptr_t)*mqd + AMDGPU_GPU_PAGE_SIZE);
 	memcpy(ctl_stack, ctl_stack_src, ctl_stack_size);
 
 	m->cp_hqd_pq_doorbell_control =
-- 
2.52.0