drm/ttm, drm/vmwgfx: Support huge TTM pagefaults

Support huge (PMD-size and PUD-size) page-table entries by providing a
huge_fault() callback.
We still support private mappings and write-notify by splitting the huge
page-table entries on write-access.

Note that for huge page-faults to occur, either the kernel needs to be
compiled with trans-huge-pages always enabled, or the kernel needs to be
compiled with trans-huge-pages enabled using madvise, and the user-space
app needs to call madvise() to enable trans-huge pages on a per-mapping
basis.

Furthermore huge page-faults will not succeed unless buffer objects and
user-space addresses are aligned on huge page size boundaries.

Cc: Andrew Morton <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: "Matthew Wilcox (Oracle)" <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Ralph Campbell <[email protected]>
Cc: "Jérôme Glisse" <[email protected]>
Cc: "Christian König" <[email protected]>
Cc: Dan Williams <[email protected]>
Signed-off-by: Thomas Hellstrom (VMware) <[email protected]>
Reviewed-by: Roland Scheidegger <[email protected]>
Reviewed-by: Christian König <[email protected]>

Author: thellstrom-os

drivers/gpu/drm/ttm/ttm_bo_vm.c

@@ -156,13 +156,97 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_vm_reserve);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/**
+ * ttm_bo_vm_insert_huge - Insert a pfn for PUD or PMD faults
+ * @vmf: Fault data
+ * @bo: The buffer object
+ * @page_offset: Page offset from bo start
+ * @fault_page_size: The size of the fault in pages.
+ * @pgprot: The page protections.
+ * Does additional checking whether it's possible to insert a PUD or PMD
+ * pfn and performs the insertion.
+ *
+ * Return: VM_FAULT_NOPAGE on successful insertion, VM_FAULT_FALLBACK if
+ * a huge fault was not possible, or on insertion error.
+ */
+static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
+					struct ttm_buffer_object *bo,
+					pgoff_t page_offset,
+					pgoff_t fault_page_size,
+					pgprot_t pgprot)
+{
+	pgoff_t i;
+	vm_fault_t ret;
+	unsigned long pfn;
+	pfn_t pfnt;
+	struct ttm_tt *ttm = bo->ttm;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	/* Fault should not cross bo boundary. */
+	page_offset &= ~(fault_page_size - 1);
+	if (page_offset + fault_page_size > bo->num_pages)
+		goto out_fallback;
+
+	if (bo->mem.bus.is_iomem)
+		pfn = ttm_bo_io_mem_pfn(bo, page_offset);
+	else
+		pfn = page_to_pfn(ttm->pages[page_offset]);
+
+	/* pfn must be fault_page_size aligned. */
+	if ((pfn & (fault_page_size - 1)) != 0)
+		goto out_fallback;
+
+	/* Check that memory is contiguous. */
+	if (!bo->mem.bus.is_iomem) {
+		for (i = 1; i < fault_page_size; ++i) {
+			if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i)
+				goto out_fallback;
+		}
+	} else if (bo->bdev->driver->io_mem_pfn) {
+		for (i = 1; i < fault_page_size; ++i) {
+			if (ttm_bo_io_mem_pfn(bo, page_offset + i) != pfn + i)
+				goto out_fallback;
+		}
+	}
+
+	pfnt = __pfn_to_pfn_t(pfn, PFN_DEV);
+	if (fault_page_size == (HPAGE_PMD_SIZE >> PAGE_SHIFT))
+		ret = vmf_insert_pfn_pmd_prot(vmf, pfnt, pgprot, write);
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	else if (fault_page_size == (HPAGE_PUD_SIZE >> PAGE_SHIFT))
+		ret = vmf_insert_pfn_pud_prot(vmf, pfnt, pgprot, write);
+#endif
+	else
+		WARN_ON_ONCE(ret = VM_FAULT_FALLBACK);
+
+	if (ret != VM_FAULT_NOPAGE)
+		goto out_fallback;
+
+	return VM_FAULT_NOPAGE;
+out_fallback:
+	count_vm_event(THP_FAULT_FALLBACK);
+	return VM_FAULT_FALLBACK;
+}
+#else
+static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf,
+					struct ttm_buffer_object *bo,
+					pgoff_t page_offset,
+					pgoff_t fault_page_size,
+					pgprot_t pgprot)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif
+
 /**
  * ttm_bo_vm_fault_reserved - TTM fault helper
  * @vmf: The struct vm_fault given as argument to the fault callback
  * @prot: The page protection to be used for this memory area.
  * @num_prefault: Maximum number of prefault pages. The caller may want to
  * specify this based on madvice settings and the size of the GPU object
  * backed by the memory.
+ * @fault_page_size: The size of the fault in pages.
  *
  * This function inserts one or more page table entries pointing to the
  * memory backing the buffer object, and then returns a return code
@@ -176,7 +260,8 @@ EXPORT_SYMBOL(ttm_bo_vm_reserve);
  */
 vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 				    pgprot_t prot,
-				    pgoff_t num_prefault)
+				    pgoff_t num_prefault,
+				    pgoff_t fault_page_size)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
@@ -268,6 +353,13 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		prot = pgprot_decrypted(prot);
 	}
 
+	/* We don't prefault on huge faults. Yet. */
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1) {
+		ret = ttm_bo_vm_insert_huge(vmf, bo, page_offset,
+					    fault_page_size, prot);
+		goto out_io_unlock;
+	}
+
 	/*
 	 * Speculatively prefault a number of pages. Only error on
 	 * first page.
@@ -334,7 +426,7 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		return ret;
 
 	prot = vma->vm_page_prot;
-	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
+	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT, 1);
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
 
@@ -344,6 +436,66 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(ttm_bo_vm_fault);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/**
+ * ttm_pgprot_is_wrprotecting - Is a page protection value write-protecting?
+ * @prot: The page protection value
+ *
+ * Return: true if @prot is write-protecting. false otherwise.
+ */
+static bool ttm_pgprot_is_wrprotecting(pgprot_t prot)
+{
+	/*
+	 * This is meant to say "pgprot_wrprotect(prot) == prot" in a generic
+	 * way. Unfortunately there is no generic pgprot_wrprotect.
+	 */
+	return pte_val(pte_wrprotect(__pte(pgprot_val(prot)))) ==
+		pgprot_val(prot);
+}
+
+static vm_fault_t ttm_bo_vm_huge_fault(struct vm_fault *vmf,
+				       enum page_entry_size pe_size)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	pgprot_t prot;
+	struct ttm_buffer_object *bo = vma->vm_private_data;
+	vm_fault_t ret;
+	pgoff_t fault_page_size = 0;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
+
+	switch (pe_size) {
+	case PE_SIZE_PMD:
+		fault_page_size = HPAGE_PMD_SIZE >> PAGE_SHIFT;
+		break;
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	case PE_SIZE_PUD:
+		fault_page_size = HPAGE_PUD_SIZE >> PAGE_SHIFT;
+		break;
+#endif
+	default:
+		WARN_ON_ONCE(1);
+		return VM_FAULT_FALLBACK;
+	}
+
+	/* Fallback on write dirty-tracking or COW */
+	if (write && ttm_pgprot_is_wrprotecting(vma->vm_page_prot))
+		return VM_FAULT_FALLBACK;
+
+	ret = ttm_bo_vm_reserve(bo, vmf);
+	if (ret)
+		return ret;
+
+	prot = vm_get_page_prot(vma->vm_flags);
+	ret = ttm_bo_vm_fault_reserved(vmf, prot, 1, fault_page_size);
+	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
+		return ret;
+
+	dma_resv_unlock(bo->base.resv);
+
+	return ret;
+}
+#endif
+
 void ttm_bo_vm_open(struct vm_area_struct *vma)
 {
 	struct ttm_buffer_object *bo = vma->vm_private_data;
@@ -445,7 +597,10 @@ static const struct vm_operations_struct ttm_bo_vm_ops = {
 	.fault = ttm_bo_vm_fault,
 	.open = ttm_bo_vm_open,
 	.close = ttm_bo_vm_close,
-	.access = ttm_bo_vm_access
+	.access = ttm_bo_vm_access,
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	.huge_fault = ttm_bo_vm_huge_fault,
+#endif
 };
 
 static struct ttm_buffer_object *ttm_bo_vm_lookup(struct ttm_bo_device *bdev,

drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c

@@ -477,7 +477,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf)
 	else
 		prot = vm_get_page_prot(vma->vm_flags);
 
-	ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault);
+	ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault, 1);
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
 

include/drm/ttm/ttm_bo_api.h

@@ -727,7 +727,8 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 
 vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 				    pgprot_t prot,
-				    pgoff_t num_prefault);
+				    pgoff_t num_prefault,
+				    pgoff_t fault_page_size);
 
 vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf);