Commit a8a9a590 authored by Loïc Molinari's avatar Loïc Molinari Committed by Boris Brezillon
Browse files

drm/i915: Use huge tmpfs mountpoint helpers 



Make use of the new drm_gem_huge_mnt_create() and
drm_gem_get_huge_mnt() helpers to avoid code duplication. Now that
it's just a few lines long, the single function in i915_gemfs.c is
moved into i915_gem_shmem.c.

v3:
- use huge tmpfs mountpoint in drm_device
- move i915_gemfs.c into i915_gem_shmem.c

v4:
- clean up mountpoint creation error handling

v5:
- use drm_gem_has_huge_mnt() helper

v7:
- include <drm/drm_print.h> in i915_gem_shmem.c

v8:
- keep logging notice message with CONFIG_TRANSPARENT_HUGEPAGE=n
- don't access huge_mnt field with CONFIG_TRANSPARENT_HUGEPAGE=n

v9:
- replace drm_gem_has_huge_mnt() by drm_gem_get_huge_mnt()
- remove useless ternary op test in selftests/huge_pages.c

v12:
- fix layering violation in selftests (Tvrtko)
- fix incorrect filename in commit message

v13:
- add Tvrtko A-b

Signed-off-by: default avatarLoïc Molinari <loic.molinari@collabora.com>
Acked-by: default avatarTvrtko Ursulin <tursulin@ursulin.net>
Link: https://patch.msgid.link/20251205182231.194072-6-loic.molinari@collabora.com


Signed-off-by: default avatarBoris Brezillon <boris.brezillon@collabora.com>
parent 6e0b1b82

drivers/gpu/drm/i915/Makefile

+1 −2
Original line number Diff line number Diff line
@@ -169,8 +169,7 @@ gem-y += \ 
	gem/i915_gem_ttm_move.o \

	gem/i915_gem_ttm_pm.o \

	gem/i915_gem_userptr.o \

	gem/i915_gem_wait.o \

	gem/i915_gemfs.o

	gem/i915_gem_wait.o

i915-y += \

	$(gem-y) \

	i915_active.o \

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

+5 −4
Original line number Diff line number Diff line
@@ -348,12 +348,13 @@ struct drm_i915_gem_object { 
 */

#define I915_BO_ALLOC_GPU_ONLY	  BIT(6)

#define I915_BO_ALLOC_CCS_AUX	  BIT(7)

#define I915_BO_ALLOC_NOTHP	  BIT(8)

/*

 * Object is allowed to retain its initial data and will not be cleared on first

 * access if used along with I915_BO_ALLOC_USER. This is mainly to keep

 * preallocated framebuffer data intact while transitioning it to i915drmfb.

 */

#define I915_BO_PREALLOC	  BIT(8)

#define I915_BO_PREALLOC	  BIT(9)

#define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \

			     I915_BO_ALLOC_VOLATILE | \

			     I915_BO_ALLOC_CPU_CLEAR | \
@@ -363,9 +364,9 @@ struct drm_i915_gem_object { 
			     I915_BO_ALLOC_GPU_ONLY | \

			     I915_BO_ALLOC_CCS_AUX | \

			     I915_BO_PREALLOC)

#define I915_BO_READONLY          BIT(9)

#define I915_TILING_QUIRK_BIT     10 /* unknown swizzling; do not release! */

#define I915_BO_PROTECTED         BIT(11)

#define I915_BO_READONLY          BIT(10)

#define I915_TILING_QUIRK_BIT     11 /* unknown swizzling; do not release! */

#define I915_BO_PROTECTED         BIT(12)

	/**

	 * @mem_flags - Mutable placement-related flags

	 *

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

+41 −17
Original line number Diff line number Diff line
@@ -9,14 +9,16 @@ 
#include <linux/uio.h>



#include <drm/drm_cache.h>

#include <drm/drm_gem.h>

#include <drm/drm_print.h>



#include "gem/i915_gem_region.h"

#include "i915_drv.h"

#include "i915_gem_object.h"

#include "i915_gem_tiling.h"

#include "i915_gemfs.h"

#include "i915_scatterlist.h"

#include "i915_trace.h"

#include "i915_utils.h"



/*

 * Move folios to appropriate lru and release the batch, decrementing the
@@ -494,9 +496,11 @@ const struct drm_i915_gem_object_ops i915_gem_shmem_ops = { 


static int __create_shmem(struct drm_i915_private *i915,

			  struct drm_gem_object *obj,

			  resource_size_t size)

			  resource_size_t size,

			  unsigned int flags)

{

	unsigned long flags = VM_NORESERVE;

	unsigned long shmem_flags = VM_NORESERVE;

	struct vfsmount *huge_mnt;

	struct file *filp;



	drm_gem_private_object_init(&i915->drm, obj, size);
@@ -515,11 +519,12 @@ static int __create_shmem(struct drm_i915_private *i915, 
	if (BITS_PER_LONG == 64 && size > MAX_LFS_FILESIZE)

		return -E2BIG;



	if (i915->mm.gemfs)

		filp = shmem_file_setup_with_mnt(i915->mm.gemfs, "i915", size,

						 flags);

	huge_mnt = drm_gem_get_huge_mnt(&i915->drm);

	if (!(flags & I915_BO_ALLOC_NOTHP) && huge_mnt)

		filp = shmem_file_setup_with_mnt(huge_mnt, "i915", size,

						 shmem_flags);

	else

		filp = shmem_file_setup("i915", size, flags);

		filp = shmem_file_setup("i915", size, shmem_flags);

	if (IS_ERR(filp))

		return PTR_ERR(filp);
@@ -548,7 +553,7 @@ static int shmem_object_init(struct intel_memory_region *mem, 
	gfp_t mask;

	int ret;



	ret = __create_shmem(i915, &obj->base, size);

	ret = __create_shmem(i915, &obj->base, size, flags);

	if (ret)

		return ret;
@@ -644,21 +649,40 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, 


static int init_shmem(struct intel_memory_region *mem)

{

	i915_gemfs_init(mem->i915);

	intel_memory_region_set_name(mem, "system");

	struct drm_i915_private *i915 = mem->i915;



	return 0; /* We have fallback to the kernel mnt if gemfs init failed. */

}

	/*

	 * By creating our own shmemfs mountpoint, we can pass in

	 * mount flags that better match our usecase.

	 *

	 * One example, although it is probably better with a per-file

	 * control, is selecting huge page allocations ("huge=within_size").

	 * However, we only do so on platforms which benefit from it, or to

	 * offset the overhead of iommu lookups, where with latter it is a net

	 * win even on platforms which would otherwise see some performance

	 * regressions such a slow reads issue on Broadwell and Skylake.

	 */



static int release_shmem(struct intel_memory_region *mem)

{

	i915_gemfs_fini(mem->i915);

	return 0;

	if (GRAPHICS_VER(i915) < 11 && !i915_vtd_active(i915))

		goto no_thp;



	drm_gem_huge_mnt_create(&i915->drm, "within_size");

	if (drm_gem_get_huge_mnt(&i915->drm))

		drm_info(&i915->drm, "Using Transparent Hugepages\n");

	else

		drm_notice(&i915->drm,

			   "Transparent Hugepage support is recommended for optimal performance%s\n",

			   GRAPHICS_VER(i915) >= 11 ? " on this platform!" :

						      " when IOMMU is enabled!");



 no_thp:

	intel_memory_region_set_name(mem, "system");



	return 0; /* We have fallback to the kernel mnt if huge mnt failed. */

}



static const struct intel_memory_region_ops shmem_region_ops = {

	.init = init_shmem,

	.release = release_shmem,

	.init_object = shmem_object_init,

};

drivers/gpu/drm/i915/gem/i915_gemfs.c

deleted100644 → 0
+0 −71
Original line number Diff line number Diff line 
// SPDX-License-Identifier: MIT

/*

 * Copyright © 2017 Intel Corporation

 */



#include <linux/fs.h>

#include <linux/mount.h>

#include <linux/fs_context.h>



#include <drm/drm_print.h>



#include "i915_drv.h"

#include "i915_gemfs.h"

#include "i915_utils.h"



void i915_gemfs_init(struct drm_i915_private *i915)

{

	struct file_system_type *type;

	struct fs_context *fc;

	struct vfsmount *gemfs;

	int ret;



	/*

	 * By creating our own shmemfs mountpoint, we can pass in

	 * mount flags that better match our usecase.

	 *

	 * One example, although it is probably better with a per-file

	 * control, is selecting huge page allocations ("huge=within_size").

	 * However, we only do so on platforms which benefit from it, or to

	 * offset the overhead of iommu lookups, where with latter it is a net

	 * win even on platforms which would otherwise see some performance

	 * regressions such a slow reads issue on Broadwell and Skylake.

	 */



	if (GRAPHICS_VER(i915) < 11 && !i915_vtd_active(i915))

		return;



	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))

		goto err;



	type = get_fs_type("tmpfs");

	if (!type)

		goto err;



	fc = fs_context_for_mount(type, SB_KERNMOUNT);

	if (IS_ERR(fc))

		goto err;

	ret = vfs_parse_fs_string(fc, "source", "tmpfs");

	if (!ret)

		ret = vfs_parse_fs_string(fc, "huge", "within_size");

	if (!ret)

		gemfs = fc_mount_longterm(fc);

	put_fs_context(fc);

	if (ret)

		goto err;



	i915->mm.gemfs = gemfs;

	drm_info(&i915->drm, "Using Transparent Hugepages\n");

	return;



err:

	drm_notice(&i915->drm,

		   "Transparent Hugepage support is recommended for optimal performance%s\n",

		   GRAPHICS_VER(i915) >= 11 ? " on this platform!" :

					      " when IOMMU is enabled!");

}



void i915_gemfs_fini(struct drm_i915_private *i915)

{

	kern_unmount(i915->mm.gemfs);

}

drivers/gpu/drm/i915/gem/i915_gemfs.h

deleted100644 → 0
+0 −14
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: MIT */

/*

 * Copyright © 2017 Intel Corporation

 */



#ifndef __I915_GEMFS_H__

#define __I915_GEMFS_H__



struct drm_i915_private;



void i915_gemfs_init(struct drm_i915_private *i915);

void i915_gemfs_fini(struct drm_i915_private *i915);



#endif