[patch 34/40] drm/i915: use vmap in i915_gem_object_map

[Andrew Morton <akpm@linux-foundation.org>]

From: Christoph Hellwig <hch@lst.de>
Subject: drm/i915: use vmap in i915_gem_object_map

i915_gem_object_map implements fairly low-level vmap functionality in a
driver.  Split it into two helpers, one for remapping kernel memory which
can use vmap, and one for I/O memory that uses vmap_pfn.

The only practical difference is that alloc_vm_area prefeaults the vmalloc
area PTEs, which doesn't seem to be required here for the kernel memory
case (and could be added to vmap using a flag if actually required).

Link: https://lkml.kernel.org/r/20201002122204.1534411-9-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 drivers/gpu/drm/i915/Kconfig              |    1 
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |  129 +++++++++-----------
 2 files changed, 61 insertions(+), 69 deletions(-)

--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c~drm-i915-use-vmap-in-i915_gem_object_map
+++ a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -232,34 +232,21 @@ unlock:
 	return err;
 }
 
-static inline pte_t iomap_pte(resource_size_t base,
-			      dma_addr_t offset,
-			      pgprot_t prot)
-{
-	return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
-}
-
 /* The 'mapping' part of i915_gem_object_pin_map() below */
-static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
-				 enum i915_map_type type)
+static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
+		enum i915_map_type type)
 {
-	unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
-	struct sg_table *sgt = obj->mm.pages;
-	pte_t *stack[32], **mem;
-	struct vm_struct *area;
+	unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
+	struct page *stack[32], **pages = stack, *page;
+	struct sgt_iter iter;
 	pgprot_t pgprot;
+	void *vaddr;
 
-	if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
-		return NULL;
-
-	if (GEM_WARN_ON(type == I915_MAP_WC &&
-			!static_cpu_has(X86_FEATURE_PAT)))
-		return NULL;
-
-	/* A single page can always be kmapped */
-	if (n_pte == 1 && type == I915_MAP_WB) {
-		struct page *page = sg_page(sgt->sgl);
-
+	switch (type) {
+	default:
+		MISSING_CASE(type);
+		fallthrough;	/* to use PAGE_KERNEL anyway */
+	case I915_MAP_WB:
 		/*
 		 * On 32b, highmem using a finite set of indirect PTE (i.e.
 		 * vmap) to provide virtual mappings of the high pages.
@@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct
 		 * So if the page is beyond the 32b boundary, make an explicit
 		 * vmap.
 		 */
-		if (!PageHighMem(page))
-			return page_address(page);
-	}
-
-	mem = stack;
-	if (n_pte > ARRAY_SIZE(stack)) {
-		/* Too big for stack -- allocate temporary array instead */
-		mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
-		if (!mem)
-			return NULL;
-	}
-
-	area = alloc_vm_area(obj->base.size, mem);
-	if (!area) {
-		if (mem != stack)
-			kvfree(mem);
-		return NULL;
-	}
-
-	switch (type) {
-	default:
-		MISSING_CASE(type);
-		fallthrough;	/* to use PAGE_KERNEL anyway */
-	case I915_MAP_WB:
+		if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl)))
+			return page_address(sg_page(obj->mm.pages->sgl));
 		pgprot = PAGE_KERNEL;
 		break;
 	case I915_MAP_WC:
@@ -308,30 +273,50 @@ static void *i915_gem_object_map(struct
 		break;
 	}
 
-	if (i915_gem_object_has_struct_page(obj)) {
-		struct sgt_iter iter;
-		struct page *page;
-		pte_t **ptes = mem;
-
-		for_each_sgt_page(page, iter, sgt)
-			**ptes++ = mk_pte(page, pgprot);
-	} else {
-		resource_size_t iomap;
-		struct sgt_iter iter;
-		pte_t **ptes = mem;
-		dma_addr_t addr;
+	if (n_pages > ARRAY_SIZE(stack)) {
+		/* Too big for stack -- allocate temporary array instead */
+		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
+		if (!pages)
+			return NULL;
+	}
 
-		iomap = obj->mm.region->iomap.base;
-		iomap -= obj->mm.region->region.start;
+	i = 0;
+	for_each_sgt_page(page, iter, obj->mm.pages)
+		pages[i++] = page;
+	vaddr = vmap(pages, n_pages, 0, pgprot);
+	if (pages != stack)
+		kvfree(pages);
+	return vaddr;
+}
 
-		for_each_sgt_daddr(addr, iter, sgt)
-			**ptes++ = iomap_pte(iomap, addr, pgprot);
-	}
+static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
+		enum i915_map_type type)
+{
+	resource_size_t iomap = obj->mm.region->iomap.base -
+		obj->mm.region->region.start;
+	unsigned long n_pfn = obj->base.size >> PAGE_SHIFT;
+	unsigned long stack[32], *pfns = stack, i;
+	struct sgt_iter iter;
+	dma_addr_t addr;
+	void *vaddr;
 
-	if (mem != stack)
-		kvfree(mem);
+	if (type != I915_MAP_WC)
+		return NULL;
+
+	if (n_pfn > ARRAY_SIZE(stack)) {
+		/* Too big for stack -- allocate temporary array instead */
+		pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL);
+		if (!pfns)
+			return NULL;
+	}
 
-	return area->addr;
+	i = 0;
+	for_each_sgt_daddr(addr, iter, obj->mm.pages)
+		pfns[i++] = (iomap + addr) >> PAGE_SHIFT;
+	vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO));
+	if (pfns != stack)
+		kvfree(pfns);
+	return vaddr;
 }
 
 /* get, pin, and map the pages of the object into kernel space */
@@ -383,7 +368,13 @@ void *i915_gem_object_pin_map(struct drm
 	}
 
 	if (!ptr) {
-		ptr = i915_gem_object_map(obj, type);
+		if (GEM_WARN_ON(type == I915_MAP_WC &&
+				!static_cpu_has(X86_FEATURE_PAT)))
+			ptr = NULL;
+		else if (i915_gem_object_has_struct_page(obj))
+			ptr = i915_gem_object_map_page(obj, type);
+		else
+			ptr = i915_gem_object_map_pfn(obj, type);
 		if (!ptr) {
 			err = -ENOMEM;
 			goto err_unpin;
--- a/drivers/gpu/drm/i915/Kconfig~drm-i915-use-vmap-in-i915_gem_object_map
+++ a/drivers/gpu/drm/i915/Kconfig
@@ -25,6 +25,7 @@ config DRM_I915
 	select CRC32
 	select SND_HDA_I915 if SND_HDA_CORE
 	select CEC_CORE if CEC_NOTIFIER
+	select VMAP_PFN
 	help
 	  Choose this option if you have a system that has "Intel Graphics
 	  Media Accelerator" or "HD Graphics" integrated graphics,
_