mm/hmm: remove the customizable pfn format from hmm_range_fault

Presumably the intent here was that hmm_range_fault() could put the data
into some HW specific format and thus avoid some work. However, nothing
actually does that, and it isn't clear how anything actually could do that
as hmm_range_fault() provides CPU addresses which must be DMA mapped.

Perhaps there is some special HW that does not need DMA mapping, but we
don't have any examples of this, and the theoretical performance win of
avoiding an extra scan over the pfns array doesn't seem worth the
complexity. Plus pfns needs to be scanned anyhow to sort out any
DEVICE_PRIVATE pages.

This version replaces the uint64_t with an usigned long containing a pfn
and fixed flags. On input flags is filled with the HMM_PFN_REQ_* values,
on successful output it is filled with HMM_PFN_* values, describing the
state of the pages.

amdgpu is simple to convert, it doesn't use snapshot and doesn't use
per-page flags.

nouveau uses only 16 hmm_pte entries at most (ie fits in a few cache
lines), and it sweeps over its pfns array a couple of times anyhow. It
also has a nasty call chain before it reaches the dma map and hardware
suggesting performance isn't important:

   nouveau_svm_fault():
     args.i.m.method = NVIF_VMM_V0_PFNMAP
     nouveau_range_fault()
      nvif_object_ioctl()
       client->driver->ioctl()
	  struct nvif_driver nvif_driver_nvkm:
	    .ioctl = nvkm_client_ioctl
	   nvkm_ioctl()
	    nvkm_ioctl_path()
	      nvkm_ioctl_v0[type].func(..)
	      nvkm_ioctl_mthd()
	       nvkm_object_mthd()
		  struct nvkm_object_func nvkm_uvmm:
		    .mthd = nvkm_uvmm_mthd
		   nvkm_uvmm_mthd()
		    nvkm_uvmm_mthd_pfnmap()
		     nvkm_vmm_pfn_map()
		      nvkm_vmm_ptes_get_map()
		       func == gp100_vmm_pgt_pfn
			struct nvkm_vmm_desc_func gp100_vmm_desc_spt:
			  .pfn = gp100_vmm_pgt_pfn
			 nvkm_vmm_iter()
			  REF_PTES == func == gp100_vmm_pgt_pfn()
			    dma_map_page()

Link: https://lore.kernel.org/r/5-v2-b4e84f444c7d+24f57-hmm_no_flags_jgg@mellanox.com
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 10 insertions, 25 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 76b4a4fa39ed..b1c62da527c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -766,17 +766,6 @@ struct amdgpu_ttm_tt {
 };
 
 #ifdef CONFIG_DRM_AMDGPU_USERPTR
-/* flags used by HMM internal, not related to CPU/GPU PTE flags */
-static const uint64_t hmm_range_flags[HMM_PFN_FLAG_MAX] = {
-	(1 << 0), /* HMM_PFN_VALID */
-	(1 << 1), /* HMM_PFN_WRITE */
-};
-
-static const uint64_t hmm_range_values[HMM_PFN_VALUE_MAX] = {
-	0xfffffffffffffffeUL, /* HMM_PFN_ERROR */
-	0, /* HMM_PFN_NONE */
-};
-
 /**
  * amdgpu_ttm_tt_get_user_pages - get device accessible pages that back user
  * memory and start HMM tracking CPU page table update
@@ -815,18 +804,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 		goto out;
 	}
 	range->notifier = &bo->notifier;
-	range->flags = hmm_range_flags;
-	range->values = hmm_range_values;
-	range->pfn_shift = PAGE_SHIFT;
 	range->start = bo->notifier.interval_tree.start;
 	range->end = bo->notifier.interval_tree.last + 1;
-	range->default_flags = hmm_range_flags[HMM_PFN_VALID];
+	range->default_flags = HMM_PFN_REQ_FAULT;
 	if (!amdgpu_ttm_tt_is_readonly(ttm))
-		range->default_flags |= range->flags[HMM_PFN_WRITE];
+		range->default_flags |= HMM_PFN_REQ_WRITE;
 
-	range->pfns = kvmalloc_array(ttm->num_pages, sizeof(*range->pfns),
-				     GFP_KERNEL);
-	if (unlikely(!range->pfns)) {
+	range->hmm_pfns = kvmalloc_array(ttm->num_pages,
+					 sizeof(*range->hmm_pfns), GFP_KERNEL);
+	if (unlikely(!range->hmm_pfns)) {
 		r = -ENOMEM;
 		goto out_free_ranges;
 	}
@@ -867,7 +853,7 @@ retry:
 	 * the notifier_lock, and mmu_interval_read_retry() must be done first.
 	 */
 	for (i = 0; i < ttm->num_pages; i++)
-		pages[i] = hmm_device_entry_to_page(range, range->pfns[i]);
+		pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
 
 	gtt->range = range;
 	mmput(mm);
@@ -877,7 +863,7 @@ retry:
 out_unlock:
 	up_read(&mm->mmap_sem);
 out_free_pfns:
-	kvfree(range->pfns);
+	kvfree(range->hmm_pfns);
 out_free_ranges:
 	kfree(range);
 out:
@@ -902,7 +888,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 	DRM_DEBUG_DRIVER("user_pages_done 0x%llx pages 0x%lx\n",
 		gtt->userptr, ttm->num_pages);
 
-	WARN_ONCE(!gtt->range || !gtt->range->pfns,
+	WARN_ONCE(!gtt->range || !gtt->range->hmm_pfns,
 		"No user pages to check\n");
 
 	if (gtt->range) {
@@ -912,7 +898,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
 		 */
 		r = mmu_interval_read_retry(gtt->range->notifier,
 					 gtt->range->notifier_seq);
-		kvfree(gtt->range->pfns);
+		kvfree(gtt->range->hmm_pfns);
 		kfree(gtt->range);
 		gtt->range = NULL;
 	}
@@ -1003,8 +989,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 
 		for (i = 0; i < ttm->num_pages; i++) {
 			if (ttm->pages[i] !=
-				hmm_device_entry_to_page(gtt->range,
-					      gtt->range->pfns[i]))
+			    hmm_pfn_to_page(gtt->range->hmm_pfns[i]))
 				break;
 		}