[PATCH v2 4/4] drm/gpusvm: make the DMA mapping step in get_pages() optional

[Honglei Huang <honghuan@amd.com>]

Some drivers (e.g. AMDXDNA) only need the CPU pages faulted in and tracked
by the notifier, no need DMA mapping.

Add a drm_gpusvm_ctx::no_dma_map flag. When set, get_pages() does the
shared HMM fault and records notifier_seq, but skips svm_pages->drm
validation, the dma_addr allocation and drm_gpusvm_dma_map_pages().
With no mapping state to check, the fault is redone on every call. The
default (no_dma_map == 0) is unchanged.

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Honglei Huang <honghuan@amd.com>
---
 drivers/gpu/drm/drm_gpusvm.c | 44 ++++++++++++++++++++++++++----------
 include/drm/drm_gpusvm.h     |  9 ++++++++
 2 files changed, 41 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index 810f801a9f7..0156ee82d7c 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -1663,6 +1663,12 @@ static int drm_gpusvm_dma_map_pages(struct drm_gpusvm *gpusvm,
  * On error the instances mapped before the failing one stay mapped, so the
  * caller must unmap and free every instance regardless of the return value.
  *
+ * With &drm_gpusvm_ctx.no_dma_map no mapping state is recorded, so
+ * drm_gpusvm_pages_valid() never returns true and success is only a snapshot:
+ * the caller must recheck mmu_interval_read_retry() against the recorded
+ * &drm_gpusvm_pages.notifier_seq under the notifier lock, and hold it until
+ * its work is visible to invalidation.
+ *
  * Return: 0 on success, negative error code on failure.
  */
 int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
@@ -1689,11 +1695,18 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 	int err = 0;
 	enum dma_data_direction dma_dir = ctx->read_only ? DMA_TO_DEVICE :
 							   DMA_BIDIRECTIONAL;
+	const bool map_dma = !ctx->no_dma_map;
 	unsigned int p;
 
-	for (p = 0; p < num_pages; ++p)
-		if (!svm_pages[p].drm)
-			return -EINVAL;
+	if (ctx->no_dma_map && ctx->devmem_only)
+		return -EINVAL;
+
+	if (map_dma) {
+		for (p = 0; p < num_pages; ++p) {
+			if (!svm_pages[p].drm)
+				return -EINVAL;
+		}
+	}
 
 retry:
 	remaining = timeout - jiffies;
@@ -1703,7 +1716,8 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 
 	hmm_range.notifier_seq = mmu_interval_read_begin(notifier);
 
-	if (drm_gpusvm_pages_valid_unlocked(gpusvm, svm_pages, num_pages))
+	if (map_dma &&
+	    drm_gpusvm_pages_valid_unlocked(gpusvm, svm_pages, num_pages))
 		goto set_seqno;
 
 	pfns = kvmalloc_array(npages, sizeof(*pfns), GFP_KERNEL);
@@ -1721,14 +1735,16 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 	if (err)
 		goto err_free;
 
-	for (p = 0; p < num_pages; ++p) {
-		if (svm_pages[p].dma_addr)
-			continue;
-		svm_pages[p].dma_addr =
-			kvzalloc_objs(*svm_pages[p].dma_addr, npages);
-		if (!svm_pages[p].dma_addr) {
-			err = -ENOMEM;
-			goto err_free;
+	if (map_dma) {
+		for (p = 0; p < num_pages; ++p) {
+			if (svm_pages[p].dma_addr)
+				continue;
+			svm_pages[p].dma_addr =
+				kvzalloc_objs(*svm_pages[p].dma_addr, npages);
+			if (!svm_pages[p].dma_addr) {
+				err = -ENOMEM;
+				goto err_free;
+			}
 		}
 	}
 
@@ -1753,6 +1769,9 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 		goto retry;
 	}
 
+	if (!map_dma)
+		goto done_mapping;
+
 	for (p = 0; p < num_pages; ++p) {
 		if (drm_gpusvm_pages_valid(gpusvm, &svm_pages[p]))
 			continue;
@@ -1771,6 +1790,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 		}
 	}
 
+done_mapping:
 	drm_gpusvm_notifier_unlock(gpusvm);
 	kvfree(pfns);
 set_seqno:
diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index d2b6f3d2b84..ec7b81957b1 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -254,6 +254,14 @@ struct drm_gpusvm {
  * @allow_mixed: Allow mixed mappings in get pages. Mixing between system and
  *               single dpagemap is supported, mixing between multiple dpagemap
  *               is unsupported.
+ * @no_dma_map: Only fault the CPU pages for the range; skip the device DMA
+ *              mapping step. Used by drivers that consume the faulted pages
+ *              without needing a DMA mapping. In this mode @drm on the
+ *              drm_gpusvm_pages is not required, no mapping state is recorded
+ *              and drm_gpusvm_pages_valid() therefore never reports these
+ *              pages as valid; the caller revalidates the snapshot itself, see
+ *              drm_gpusvm_get_pages(). @devmem_only is rejected and no page
+ *              type check is performed, so @allow_mixed has no effect.
  *
  * Context that is DRM GPUSVM is operating in (i.e. user arguments).
  */
@@ -266,6 +274,7 @@ struct drm_gpusvm_ctx {
 	unsigned int devmem_possible :1;
 	unsigned int devmem_only :1;
 	unsigned int allow_mixed :1;
+	unsigned int no_dma_map :1;
 };
 
 int drm_gpusvm_init(struct drm_gpusvm *gpusvm,
-- 
2.34.1