Attempt a PMD sized PFN insertion into the VMA if the faulty address
of the fault handler is part of a huge page.

On builds with CONFIG_TRANSPARENT_HUGEPAGE enabled, if the mmap() user
address is PMD size aligned, if the GEM object is backed by shmem
buffers on mountpoints setting the 'huge=' option and if the shmem
backing store manages to allocate a huge folio, CPU mapping would then
benefit from significantly increased memcpy() performance. When these
conditions are met on a system with 2 MiB huge pages, an aligned copy
of 2 MiB would raise a single page fault instead of 4096.

v4:
- implement map_pages instead of huge_fault

v6:
- get rid of map_pages handler for now (keep it for another series
  along with arm64 contpte support)

Signed-off-by: Loïc Molinari <loic.molinari@collabora.com>
---
 drivers/gpu/drm/drm_gem_shmem_helper.c | 55 +++++++++++++++++++++-----
 1 file changed, 46 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index be89be1c804c..81f4ac7cb8f6 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -567,31 +567,68 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev,
 }
 EXPORT_SYMBOL_GPL(drm_gem_shmem_dumb_create);
 
+static bool drm_gem_shmem_fault_is_valid(struct drm_gem_object *obj,
+					 pgoff_t pgoff)
+{
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
+
+	if (drm_WARN_ON_ONCE(obj->dev, !shmem->pages) ||
+	    pgoff >= (obj->size >> PAGE_SHIFT) ||
+	    shmem->madv < 0)
+		return false;
+
+	return true;
+}
+
+static bool drm_gem_shmem_map_pmd(struct vm_fault *vmf, unsigned long addr,
+				  struct page *page)
+{
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long paddr = pfn << PAGE_SHIFT;
+	bool aligned = (addr & ~PMD_MASK) == (paddr & ~PMD_MASK);
+
+	if (aligned &&
+	    pmd_none(*vmf->pmd) &&
+	    folio_test_pmd_mappable(page_folio(page))) {
+		pfn &= PMD_MASK >> PAGE_SHIFT;
+		if (vmf_insert_pfn_pmd(vmf, pfn, false) == VM_FAULT_NOPAGE)
+			return true;
+	}
+#endif
+
+	return false;
+}
+
 static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-	loff_t num_pages = obj->size >> PAGE_SHIFT;
-	vm_fault_t ret;
-	struct page *page;
+	struct page **pages = shmem->pages;
 	pgoff_t page_offset;
+	unsigned long pfn;
+	vm_fault_t ret;
 
 	/* Offset to faulty address in the VMA (without the fake offset). */
 	page_offset = vmf->pgoff - vma->vm_pgoff;
 
 	dma_resv_lock(shmem->base.resv, NULL);
 
-	if (page_offset >= num_pages ||
-	    drm_WARN_ON_ONCE(obj->dev, !shmem->pages) ||
-	    shmem->madv < 0) {
+	if (unlikely(!drm_gem_shmem_fault_is_valid(obj, page_offset))) {
 		ret = VM_FAULT_SIGBUS;
-	} else {
-		page = shmem->pages[page_offset];
+		goto out;
+	}
 
-		ret = vmf_insert_pfn(vma, vmf->address, page_to_pfn(page));
+	if (drm_gem_shmem_map_pmd(vmf, vmf->address, pages[page_offset])) {
+		ret = VM_FAULT_NOPAGE;
+		goto out;
 	}
 
+	pfn = page_to_pfn(pages[page_offset]);
+	ret = vmf_insert_pfn(vma, vmf->address, pfn);
+
+ out:
 	dma_resv_unlock(shmem->base.resv);
 
 	return ret;
-- 
2.47.3