1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
linux/drivers/gpu/drm/mediatek/mtk_gem.c
Linus Torvalds 61307b7be4 The usual shower of singleton fixes and minor series all over MM,
documented (hopefully adequately) in the respective changelogs.  Notable
 series include:
 
 - Lucas Stach has provided some page-mapping
   cleanup/consolidation/maintainability work in the series "mm/treewide:
   Remove pXd_huge() API".
 
 - In the series "Allow migrate on protnone reference with
   MPOL_PREFERRED_MANY policy", Donet Tom has optimized mempolicy's
   MPOL_PREFERRED_MANY mode, yielding almost doubled performance in one
   test.
 
 - In their series "Memory allocation profiling" Kent Overstreet and
   Suren Baghdasaryan have contributed a means of determining (via
   /proc/allocinfo) whereabouts in the kernel memory is being allocated:
   number of calls and amount of memory.
 
 - Matthew Wilcox has provided the series "Various significant MM
   patches" which does a number of rather unrelated things, but in largely
   similar code sites.
 
 - In his series "mm: page_alloc: freelist migratetype hygiene" Johannes
   Weiner has fixed the page allocator's handling of migratetype requests,
   with resulting improvements in compaction efficiency.
 
 - In the series "make the hugetlb migration strategy consistent" Baolin
   Wang has fixed a hugetlb migration issue, which should improve hugetlb
   allocation reliability.
 
 - Liu Shixin has hit an I/O meltdown caused by readahead in a
   memory-tight memcg.  Addressed in the series "Fix I/O high when memory
   almost met memcg limit".
 
 - In the series "mm/filemap: optimize folio adding and splitting" Kairui
   Song has optimized pagecache insertion, yielding ~10% performance
   improvement in one test.
 
 - Baoquan He has cleaned up and consolidated the early zone
   initialization code in the series "mm/mm_init.c: refactor
   free_area_init_core()".
 
 - Baoquan has also redone some MM initializatio code in the series
   "mm/init: minor clean up and improvement".
 
 - MM helper cleanups from Christoph Hellwig in his series "remove
   follow_pfn".
 
 - More cleanups from Matthew Wilcox in the series "Various page->flags
   cleanups".
 
 - Vlastimil Babka has contributed maintainability improvements in the
   series "memcg_kmem hooks refactoring".
 
 - More folio conversions and cleanups in Matthew Wilcox's series
 
 	"Convert huge_zero_page to huge_zero_folio"
 	"khugepaged folio conversions"
 	"Remove page_idle and page_young wrappers"
 	"Use folio APIs in procfs"
 	"Clean up __folio_put()"
 	"Some cleanups for memory-failure"
 	"Remove page_mapping()"
 	"More folio compat code removal"
 
 - David Hildenbrand chipped in with "fs/proc/task_mmu: convert hugetlb
   functions to work on folis".
 
 - Code consolidation and cleanup work related to GUP's handling of
   hugetlbs in Peter Xu's series "mm/gup: Unify hugetlb, part 2".
 
 - Rick Edgecombe has developed some fixes to stack guard gaps in the
   series "Cover a guard gap corner case".
 
 - Jinjiang Tu has fixed KSM's behaviour after a fork+exec in the series
   "mm/ksm: fix ksm exec support for prctl".
 
 - Baolin Wang has implemented NUMA balancing for multi-size THPs.  This
   is a simple first-cut implementation for now.  The series is "support
   multi-size THP numa balancing".
 
 - Cleanups to vma handling helper functions from Matthew Wilcox in the
   series "Unify vma_address and vma_pgoff_address".
 
 - Some selftests maintenance work from Dev Jain in the series
   "selftests/mm: mremap_test: Optimizations and style fixes".
 
 - Improvements to the swapping of multi-size THPs from Ryan Roberts in
   the series "Swap-out mTHP without splitting".
 
 - Kefeng Wang has significantly optimized the handling of arm64's
   permission page faults in the series
 
 	"arch/mm/fault: accelerate pagefault when badaccess"
 	"mm: remove arch's private VM_FAULT_BADMAP/BADACCESS"
 
 - GUP cleanups from David Hildenbrand in "mm/gup: consistently call it
   GUP-fast".
 
 - hugetlb fault code cleanups from Vishal Moola in "Hugetlb fault path to
   use struct vm_fault".
 
 - selftests build fixes from John Hubbard in the series "Fix
   selftests/mm build without requiring "make headers"".
 
 - Memory tiering fixes/improvements from Ho-Ren (Jack) Chuang in the
   series "Improved Memory Tier Creation for CPUless NUMA Nodes".  Fixes
   the initialization code so that migration between different memory types
   works as intended.
 
 - David Hildenbrand has improved follow_pte() and fixed an errant driver
   in the series "mm: follow_pte() improvements and acrn follow_pte()
   fixes".
 
 - David also did some cleanup work on large folio mapcounts in his
   series "mm: mapcount for large folios + page_mapcount() cleanups".
 
 - Folio conversions in KSM in Alex Shi's series "transfer page to folio
   in KSM".
 
 - Barry Song has added some sysfs stats for monitoring multi-size THP's
   in the series "mm: add per-order mTHP alloc and swpout counters".
 
 - Some zswap cleanups from Yosry Ahmed in the series "zswap same-filled
   and limit checking cleanups".
 
 - Matthew Wilcox has been looking at buffer_head code and found the
   documentation to be lacking.  The series is "Improve buffer head
   documentation".
 
 - Multi-size THPs get more work, this time from Lance Yang.  His series
   "mm/madvise: enhance lazyfreeing with mTHP in madvise_free" optimizes
   the freeing of these things.
 
 - Kemeng Shi has added more userspace-visible writeback instrumentation
   in the series "Improve visibility of writeback".
 
 - Kemeng Shi then sent some maintenance work on top in the series "Fix
   and cleanups to page-writeback".
 
 - Matthew Wilcox reduces mmap_lock traffic in the anon vma code in the
   series "Improve anon_vma scalability for anon VMAs".  Intel's test bot
   reported an improbable 3x improvement in one test.
 
 - SeongJae Park adds some DAMON feature work in the series
 
 	"mm/damon: add a DAMOS filter type for page granularity access recheck"
 	"selftests/damon: add DAMOS quota goal test"
 
 - Also some maintenance work in the series
 
 	"mm/damon/paddr: simplify page level access re-check for pageout"
 	"mm/damon: misc fixes and improvements"
 
 - David Hildenbrand has disabled some known-to-fail selftests ni the
   series "selftests: mm: cow: flag vmsplice() hugetlb tests as XFAIL".
 
 - memcg metadata storage optimizations from Shakeel Butt in "memcg:
   reduce memory consumption by memcg stats".
 
 - DAX fixes and maintenance work from Vishal Verma in the series
   "dax/bus.c: Fixups for dax-bus locking".
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZkgQYwAKCRDdBJ7gKXxA
 jrdKAP9WVJdpEcXxpoub/vVE0UWGtffr8foifi9bCwrQrGh5mgEAx7Yf0+d/oBZB
 nvA4E0DcPrUAFy144FNM0NTCb7u9vAw=
 =V3R/
 -----END PGP SIGNATURE-----

Merge tag 'mm-stable-2024-05-17-19-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull mm updates from Andrew Morton:
 "The usual shower of singleton fixes and minor series all over MM,
  documented (hopefully adequately) in the respective changelogs.
  Notable series include:

   - Lucas Stach has provided some page-mapping cleanup/consolidation/
     maintainability work in the series "mm/treewide: Remove pXd_huge()
     API".

   - In the series "Allow migrate on protnone reference with
     MPOL_PREFERRED_MANY policy", Donet Tom has optimized mempolicy's
     MPOL_PREFERRED_MANY mode, yielding almost doubled performance in
     one test.

   - In their series "Memory allocation profiling" Kent Overstreet and
     Suren Baghdasaryan have contributed a means of determining (via
     /proc/allocinfo) whereabouts in the kernel memory is being
     allocated: number of calls and amount of memory.

   - Matthew Wilcox has provided the series "Various significant MM
     patches" which does a number of rather unrelated things, but in
     largely similar code sites.

   - In his series "mm: page_alloc: freelist migratetype hygiene"
     Johannes Weiner has fixed the page allocator's handling of
     migratetype requests, with resulting improvements in compaction
     efficiency.

   - In the series "make the hugetlb migration strategy consistent"
     Baolin Wang has fixed a hugetlb migration issue, which should
     improve hugetlb allocation reliability.

   - Liu Shixin has hit an I/O meltdown caused by readahead in a
     memory-tight memcg. Addressed in the series "Fix I/O high when
     memory almost met memcg limit".

   - In the series "mm/filemap: optimize folio adding and splitting"
     Kairui Song has optimized pagecache insertion, yielding ~10%
     performance improvement in one test.

   - Baoquan He has cleaned up and consolidated the early zone
     initialization code in the series "mm/mm_init.c: refactor
     free_area_init_core()".

   - Baoquan has also redone some MM initializatio code in the series
     "mm/init: minor clean up and improvement".

   - MM helper cleanups from Christoph Hellwig in his series "remove
     follow_pfn".

   - More cleanups from Matthew Wilcox in the series "Various
     page->flags cleanups".

   - Vlastimil Babka has contributed maintainability improvements in the
     series "memcg_kmem hooks refactoring".

   - More folio conversions and cleanups in Matthew Wilcox's series:
	"Convert huge_zero_page to huge_zero_folio"
	"khugepaged folio conversions"
	"Remove page_idle and page_young wrappers"
	"Use folio APIs in procfs"
	"Clean up __folio_put()"
	"Some cleanups for memory-failure"
	"Remove page_mapping()"
	"More folio compat code removal"

   - David Hildenbrand chipped in with "fs/proc/task_mmu: convert
     hugetlb functions to work on folis".

   - Code consolidation and cleanup work related to GUP's handling of
     hugetlbs in Peter Xu's series "mm/gup: Unify hugetlb, part 2".

   - Rick Edgecombe has developed some fixes to stack guard gaps in the
     series "Cover a guard gap corner case".

   - Jinjiang Tu has fixed KSM's behaviour after a fork+exec in the
     series "mm/ksm: fix ksm exec support for prctl".

   - Baolin Wang has implemented NUMA balancing for multi-size THPs.
     This is a simple first-cut implementation for now. The series is
     "support multi-size THP numa balancing".

   - Cleanups to vma handling helper functions from Matthew Wilcox in
     the series "Unify vma_address and vma_pgoff_address".

   - Some selftests maintenance work from Dev Jain in the series
     "selftests/mm: mremap_test: Optimizations and style fixes".

   - Improvements to the swapping of multi-size THPs from Ryan Roberts
     in the series "Swap-out mTHP without splitting".

   - Kefeng Wang has significantly optimized the handling of arm64's
     permission page faults in the series
	"arch/mm/fault: accelerate pagefault when badaccess"
	"mm: remove arch's private VM_FAULT_BADMAP/BADACCESS"

   - GUP cleanups from David Hildenbrand in "mm/gup: consistently call
     it GUP-fast".

   - hugetlb fault code cleanups from Vishal Moola in "Hugetlb fault
     path to use struct vm_fault".

   - selftests build fixes from John Hubbard in the series "Fix
     selftests/mm build without requiring "make headers"".

   - Memory tiering fixes/improvements from Ho-Ren (Jack) Chuang in the
     series "Improved Memory Tier Creation for CPUless NUMA Nodes".
     Fixes the initialization code so that migration between different
     memory types works as intended.

   - David Hildenbrand has improved follow_pte() and fixed an errant
     driver in the series "mm: follow_pte() improvements and acrn
     follow_pte() fixes".

   - David also did some cleanup work on large folio mapcounts in his
     series "mm: mapcount for large folios + page_mapcount() cleanups".

   - Folio conversions in KSM in Alex Shi's series "transfer page to
     folio in KSM".

   - Barry Song has added some sysfs stats for monitoring multi-size
     THP's in the series "mm: add per-order mTHP alloc and swpout
     counters".

   - Some zswap cleanups from Yosry Ahmed in the series "zswap
     same-filled and limit checking cleanups".

   - Matthew Wilcox has been looking at buffer_head code and found the
     documentation to be lacking. The series is "Improve buffer head
     documentation".

   - Multi-size THPs get more work, this time from Lance Yang. His
     series "mm/madvise: enhance lazyfreeing with mTHP in madvise_free"
     optimizes the freeing of these things.

   - Kemeng Shi has added more userspace-visible writeback
     instrumentation in the series "Improve visibility of writeback".

   - Kemeng Shi then sent some maintenance work on top in the series
     "Fix and cleanups to page-writeback".

   - Matthew Wilcox reduces mmap_lock traffic in the anon vma code in
     the series "Improve anon_vma scalability for anon VMAs". Intel's
     test bot reported an improbable 3x improvement in one test.

   - SeongJae Park adds some DAMON feature work in the series
	"mm/damon: add a DAMOS filter type for page granularity access recheck"
	"selftests/damon: add DAMOS quota goal test"

   - Also some maintenance work in the series
	"mm/damon/paddr: simplify page level access re-check for pageout"
	"mm/damon: misc fixes and improvements"

   - David Hildenbrand has disabled some known-to-fail selftests ni the
     series "selftests: mm: cow: flag vmsplice() hugetlb tests as
     XFAIL".

   - memcg metadata storage optimizations from Shakeel Butt in "memcg:
     reduce memory consumption by memcg stats".

   - DAX fixes and maintenance work from Vishal Verma in the series
     "dax/bus.c: Fixups for dax-bus locking""

* tag 'mm-stable-2024-05-17-19-19' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (426 commits)
  memcg, oom: cleanup unused memcg_oom_gfp_mask and memcg_oom_order
  selftests/mm: hugetlb_madv_vs_map: avoid test skipping by querying hugepage size at runtime
  mm/hugetlb: add missing VM_FAULT_SET_HINDEX in hugetlb_wp
  mm/hugetlb: add missing VM_FAULT_SET_HINDEX in hugetlb_fault
  selftests: cgroup: add tests to verify the zswap writeback path
  mm: memcg: make alloc_mem_cgroup_per_node_info() return bool
  mm/damon/core: fix return value from damos_wmark_metric_value
  mm: do not update memcg stats for NR_{FILE/SHMEM}_PMDMAPPED
  selftests: cgroup: remove redundant enabling of memory controller
  Docs/mm/damon/maintainer-profile: allow posting patches based on damon/next tree
  Docs/mm/damon/maintainer-profile: change the maintainer's timezone from PST to PT
  Docs/mm/damon/design: use a list for supported filters
  Docs/admin-guide/mm/damon/usage: fix wrong schemes effective quota update command
  Docs/admin-guide/mm/damon/usage: fix wrong example of DAMOS filter matching sysfs file
  selftests/damon: classify tests for functionalities and regressions
  selftests/damon/_damon_sysfs: use 'is' instead of '==' for 'None'
  selftests/damon/_damon_sysfs: find sysfs mount point from /proc/mounts
  selftests/damon/_damon_sysfs: check errors from nr_schemes file reads
  mm/damon/core: initialize ->esz_bp from damos_quota_init_priv()
  selftests/damon: add a test for DAMOS quota goal
  ...
2024-05-19 09:21:03 -07:00

288 lines
6.8 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2015 MediaTek Inc.
*/
#include <linux/dma-buf.h>
#include <linux/vmalloc.h>
#include <drm/drm.h>
#include <drm/drm_device.h>
#include <drm/drm_gem.h>
#include <drm/drm_gem_dma_helper.h>
#include <drm/drm_prime.h>
#include "mtk_drm_drv.h"
#include "mtk_gem.h"
static int mtk_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
static const struct vm_operations_struct vm_ops = {
.open = drm_gem_vm_open,
.close = drm_gem_vm_close,
};
static const struct drm_gem_object_funcs mtk_gem_object_funcs = {
.free = mtk_gem_free_object,
.get_sg_table = mtk_gem_prime_get_sg_table,
.vmap = mtk_gem_prime_vmap,
.vunmap = mtk_gem_prime_vunmap,
.mmap = mtk_gem_object_mmap,
.vm_ops = &vm_ops,
};
static struct mtk_gem_obj *mtk_gem_init(struct drm_device *dev,
unsigned long size)
{
struct mtk_gem_obj *mtk_gem_obj;
int ret;
size = round_up(size, PAGE_SIZE);
if (size == 0)
return ERR_PTR(-EINVAL);
mtk_gem_obj = kzalloc(sizeof(*mtk_gem_obj), GFP_KERNEL);
if (!mtk_gem_obj)
return ERR_PTR(-ENOMEM);
mtk_gem_obj->base.funcs = &mtk_gem_object_funcs;
ret = drm_gem_object_init(dev, &mtk_gem_obj->base, size);
if (ret < 0) {
DRM_ERROR("failed to initialize gem object\n");
kfree(mtk_gem_obj);
return ERR_PTR(ret);
}
return mtk_gem_obj;
}
struct mtk_gem_obj *mtk_gem_create(struct drm_device *dev,
size_t size, bool alloc_kmap)
{
struct mtk_drm_private *priv = dev->dev_private;
struct mtk_gem_obj *mtk_gem;
struct drm_gem_object *obj;
int ret;
mtk_gem = mtk_gem_init(dev, size);
if (IS_ERR(mtk_gem))
return ERR_CAST(mtk_gem);
obj = &mtk_gem->base;
mtk_gem->dma_attrs = DMA_ATTR_WRITE_COMBINE;
if (!alloc_kmap)
mtk_gem->dma_attrs |= DMA_ATTR_NO_KERNEL_MAPPING;
mtk_gem->cookie = dma_alloc_attrs(priv->dma_dev, obj->size,
&mtk_gem->dma_addr, GFP_KERNEL,
mtk_gem->dma_attrs);
if (!mtk_gem->cookie) {
DRM_ERROR("failed to allocate %zx byte dma buffer", obj->size);
ret = -ENOMEM;
goto err_gem_free;
}
if (alloc_kmap)
mtk_gem->kvaddr = mtk_gem->cookie;
DRM_DEBUG_DRIVER("cookie = %p dma_addr = %pad size = %zu\n",
mtk_gem->cookie, &mtk_gem->dma_addr,
size);
return mtk_gem;
err_gem_free:
drm_gem_object_release(obj);
kfree(mtk_gem);
return ERR_PTR(ret);
}
void mtk_gem_free_object(struct drm_gem_object *obj)
{
struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
struct mtk_drm_private *priv = obj->dev->dev_private;
if (mtk_gem->sg)
drm_prime_gem_destroy(obj, mtk_gem->sg);
else
dma_free_attrs(priv->dma_dev, obj->size, mtk_gem->cookie,
mtk_gem->dma_addr, mtk_gem->dma_attrs);
/* release file pointer to gem object. */
drm_gem_object_release(obj);
kfree(mtk_gem);
}
int mtk_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
struct drm_mode_create_dumb *args)
{
struct mtk_gem_obj *mtk_gem;
int ret;
args->pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
/*
* Multiply 2 variables of different types,
* for example: args->size = args->spacing * args->height;
* may cause coverity issue with unintentional overflow.
*/
args->size = args->pitch;
args->size *= args->height;
mtk_gem = mtk_gem_create(dev, args->size, false);
if (IS_ERR(mtk_gem))
return PTR_ERR(mtk_gem);
/*
* allocate a id of idr table where the obj is registered
* and handle has the id what user can see.
*/
ret = drm_gem_handle_create(file_priv, &mtk_gem->base, &args->handle);
if (ret)
goto err_handle_create;
/* drop reference from allocate - handle holds it now. */
drm_gem_object_put(&mtk_gem->base);
return 0;
err_handle_create:
mtk_gem_free_object(&mtk_gem->base);
return ret;
}
static int mtk_gem_object_mmap(struct drm_gem_object *obj,
struct vm_area_struct *vma)
{
int ret;
struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
struct mtk_drm_private *priv = obj->dev->dev_private;
/*
* Set vm_pgoff (used as a fake buffer offset by DRM) to 0 and map the
* whole buffer from the start.
*/
vma->vm_pgoff = 0;
/*
* dma_alloc_attrs() allocated a struct page table for mtk_gem, so clear
* VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap().
*/
vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP);
vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
ret = dma_mmap_attrs(priv->dma_dev, vma, mtk_gem->cookie,
mtk_gem->dma_addr, obj->size, mtk_gem->dma_attrs);
return ret;
}
/*
* Allocate a sg_table for this GEM object.
* Note: Both the table's contents, and the sg_table itself must be freed by
* the caller.
* Returns a pointer to the newly allocated sg_table, or an ERR_PTR() error.
*/
struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj)
{
struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
struct mtk_drm_private *priv = obj->dev->dev_private;
struct sg_table *sgt;
int ret;
sgt = kzalloc(sizeof(*sgt), GFP_KERNEL);
if (!sgt)
return ERR_PTR(-ENOMEM);
ret = dma_get_sgtable_attrs(priv->dma_dev, sgt, mtk_gem->cookie,
mtk_gem->dma_addr, obj->size,
mtk_gem->dma_attrs);
if (ret) {
DRM_ERROR("failed to allocate sgt, %d\n", ret);
kfree(sgt);
return ERR_PTR(ret);
}
return sgt;
}
struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
struct dma_buf_attachment *attach, struct sg_table *sg)
{
struct mtk_gem_obj *mtk_gem;
/* check if the entries in the sg_table are contiguous */
if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) {
DRM_ERROR("sg_table is not contiguous");
return ERR_PTR(-EINVAL);
}
mtk_gem = mtk_gem_init(dev, attach->dmabuf->size);
if (IS_ERR(mtk_gem))
return ERR_CAST(mtk_gem);
mtk_gem->dma_addr = sg_dma_address(sg->sgl);
mtk_gem->sg = sg;
return &mtk_gem->base;
}
int mtk_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map)
{
struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
struct sg_table *sgt = NULL;
unsigned int npages;
if (mtk_gem->kvaddr)
goto out;
sgt = mtk_gem_prime_get_sg_table(obj);
if (IS_ERR(sgt))
return PTR_ERR(sgt);
npages = obj->size >> PAGE_SHIFT;
mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL);
if (!mtk_gem->pages) {
sg_free_table(sgt);
kfree(sgt);
return -ENOMEM;
}
drm_prime_sg_to_page_array(sgt, mtk_gem->pages, npages);
mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP,
pgprot_writecombine(PAGE_KERNEL));
if (!mtk_gem->kvaddr) {
sg_free_table(sgt);
kfree(sgt);
kfree(mtk_gem->pages);
return -ENOMEM;
}
sg_free_table(sgt);
kfree(sgt);
out:
iosys_map_set_vaddr(map, mtk_gem->kvaddr);
return 0;
}
void mtk_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map)
{
struct mtk_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
void *vaddr = map->vaddr;
if (!mtk_gem->pages)
return;
vunmap(vaddr);
mtk_gem->kvaddr = NULL;
kfree(mtk_gem->pages);
}