github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-27 09:36:22 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/pagemap: Use dma-map IOVA alloc, link, and sync API for DRM pagemap

Browse Source 
The dma-map IOVA alloc, link, and sync APIs perform significantly better
than dma-map / dma-unmap, as they avoid costly IOMMU synchronizations.
This difference is especially noticeable when mapping a 2MB region in
4KB pages.

Use the IOVA alloc, link, and sync APIs for DRM pagemap, which create DMA
mappings between the CPU and GPU for copying data.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Link: https://patch.msgid.link/20260410205929.3914474-5-matthew.brost@intel.com
This commit is contained in:
Matthew Brost 2026-04-10 13:59:28 -07:00
parent 07f123f33d
commit 2e0cd372b8
1 changed files with 70 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

85
drivers/gpu/drm/drm_pagemap.c
View File

@ -291,6 +291,19 @@ drm_pagemap_migrate_map_device_private_pages(struct device *dev,
return 0;
}
/**
* struct drm_pagemap_iova_state - DRM pagemap IOVA state
* @dma_state: DMA IOVA state.
* @offset: Current offset in IOVA.
*
* This structure acts as an iterator for packing all IOVA addresses within a
* contiguous range.
*/
struct drm_pagemap_iova_state {
struct dma_iova_state dma_state;
unsigned long offset;
};
/**
* drm_pagemap_migrate_map_system_pages() - Map system or device coherent
* migration pages for GPU SVM migration
@ -299,22 +312,25 @@ drm_pagemap_migrate_map_device_private_pages(struct device *dev,
* @migrate_pfn: Array of page frame numbers of system pages or peer pages to map.
* @npages: Number of system or device coherent pages to map.
* @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
* @state: DMA IOVA state for mapping.
*
* This function maps pages of memory for migration usage in GPU SVM. It
* iterates over each page frame number provided in @migrate_pfn, maps the
* corresponding page, and stores the DMA address in the provided @dma_addr
* array.
*
* Returns: 0 on success, -EFAULT if an error occurs during mapping.
* Returns: 0 on success, negative error code on failure.
*/
static int
drm_pagemap_migrate_map_system_pages(struct device *dev,
struct drm_pagemap_addr *pagemap_addr,
unsigned long *migrate_pfn,
unsigned long npages,
enum dma_data_direction dir)
enum dma_data_direction dir,
struct drm_pagemap_iova_state *state)
{
unsigned long i;
bool try_alloc = false;
for (i = 0; i < npages;) {
struct page *page = migrate_pfn_to_page(migrate_pfn[i]);
@ -329,9 +345,31 @@ drm_pagemap_migrate_map_system_pages(struct device *dev,
folio = page_folio(page);
order = folio_order(folio);
dma_addr = dma_map_page(dev, page, 0, page_size(page), dir);
if (dma_mapping_error(dev, dma_addr))
return -EFAULT;
if (!try_alloc) {
dma_iova_try_alloc(dev, &state->dma_state,
(npages - i) * PAGE_SIZE >=
HPAGE_PMD_SIZE ?
HPAGE_PMD_SIZE : 0,
npages * PAGE_SIZE);
try_alloc = true;
}
if (dma_use_iova(&state->dma_state)) {
int err = dma_iova_link(dev, &state->dma_state,
page_to_phys(page),
state->offset, page_size(page),
dir, 0);
if (err)
return err;
dma_addr = state->dma_state.addr + state->offset;
state->offset += page_size(page);
} else {
dma_addr = dma_map_page(dev, page, 0, page_size(page),
dir);
if (dma_mapping_error(dev, dma_addr))
return -EFAULT;
}
pagemap_addr[i] =
drm_pagemap_addr_encode(dma_addr,
@ -342,6 +380,9 @@ drm_pagemap_migrate_map_system_pages(struct device *dev,
i += NR_PAGES(order);
}
if (dma_use_iova(&state->dma_state))
return dma_iova_sync(dev, &state->dma_state, 0, state->offset);
return 0;
}
@ -353,6 +394,7 @@ drm_pagemap_migrate_map_system_pages(struct device *dev,
* @pagemap_addr: Array of DMA information corresponding to mapped pages
* @npages: Number of pages to unmap
* @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
* @state: DMA IOVA state for mapping.
*
* This function unmaps previously mapped pages of memory for GPU Shared Virtual
* Memory (SVM). It iterates over each DMA address provided in @dma_addr, checks
@ -362,10 +404,16 @@ static void drm_pagemap_migrate_unmap_pages(struct device *dev,
struct drm_pagemap_addr *pagemap_addr,
unsigned long *migrate_pfn,
unsigned long npages,
enum dma_data_direction dir)
enum dma_data_direction dir,
struct drm_pagemap_iova_state *state)
{
unsigned long i;
if (state && dma_use_iova(&state->dma_state)) {
dma_iova_destroy(dev, &state->dma_state, state->offset, dir, 0);
return;
}
for (i = 0; i < npages;) {
struct page *page = migrate_pfn_to_page(migrate_pfn[i]);
@ -420,7 +468,7 @@ drm_pagemap_migrate_remote_to_local(struct drm_pagemap_devmem *devmem,
devmem->pre_migrate_fence);
out:
drm_pagemap_migrate_unmap_pages(remote_device, pagemap_addr, local_pfns,
npages, DMA_FROM_DEVICE);
npages, DMA_FROM_DEVICE, NULL);
return err;
}
@ -430,11 +478,13 @@ drm_pagemap_migrate_sys_to_dev(struct drm_pagemap_devmem *devmem,
struct page *local_pages[],
struct drm_pagemap_addr pagemap_addr[],
unsigned long npages,
const struct drm_pagemap_devmem_ops *ops)
const struct drm_pagemap_devmem_ops *ops,
struct drm_pagemap_iova_state *state)
{
int err = drm_pagemap_migrate_map_system_pages(devmem->dev,
pagemap_addr, sys_pfns,
npages, DMA_TO_DEVICE);
npages, DMA_TO_DEVICE,
state);
if (err)
goto out;
@ -443,7 +493,7 @@ drm_pagemap_migrate_sys_to_dev(struct drm_pagemap_devmem *devmem,
devmem->pre_migrate_fence);
out:
drm_pagemap_migrate_unmap_pages(devmem->dev, pagemap_addr, sys_pfns, npages,
DMA_TO_DEVICE);
DMA_TO_DEVICE, state);
return err;
}
@ -471,6 +521,7 @@ static int drm_pagemap_migrate_range(struct drm_pagemap_devmem *devmem,
const struct migrate_range_loc *cur,
const struct drm_pagemap_migrate_details *mdetails)
{
struct drm_pagemap_iova_state state = {};
int ret = 0;
if (cur->start == 0)
@ -498,7 +549,7 @@ static int drm_pagemap_migrate_range(struct drm_pagemap_devmem *devmem,
&pages[last->start],
&pagemap_addr[last->start],
cur->start - last->start,
last->ops);
last->ops, &state);
out:
*last = *cur;
@ -1060,6 +1111,7 @@ EXPORT_SYMBOL(drm_pagemap_put);
int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
{
const struct drm_pagemap_devmem_ops *ops = devmem_allocation->ops;
struct drm_pagemap_iova_state state = {};
unsigned long npages, mpages = 0;
struct page **pages;
unsigned long *src, *dst;
@ -1101,7 +1153,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
err = drm_pagemap_migrate_map_system_pages(devmem_allocation->dev,
pagemap_addr,
dst, npages,
DMA_FROM_DEVICE);
DMA_FROM_DEVICE, &state);
if (err)
goto err_finalize;
@ -1125,7 +1177,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
migrate_device_pages(src, dst, npages);
migrate_device_finalize(src, dst, npages);
drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, dst, npages,
DMA_FROM_DEVICE);
DMA_FROM_DEVICE, &state);
err_free:
kvfree(buf);
@ -1137,6 +1189,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
if (retry_count--) {
cond_resched();
state = (struct drm_pagemap_iova_state){};
goto retry;
}
@ -1170,6 +1223,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
MIGRATE_VMA_SELECT_COMPOUND,
.fault_page = page,
};
struct drm_pagemap_iova_state state = {};
struct drm_pagemap_zdd *zdd;
const struct drm_pagemap_devmem_ops *ops;
struct device *dev = NULL;
@ -1229,7 +1283,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
err = drm_pagemap_migrate_map_system_pages(dev, pagemap_addr,
migrate.dst, npages,
DMA_FROM_DEVICE);
DMA_FROM_DEVICE, &state);
if (err)
goto err_finalize;
@ -1254,7 +1308,8 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
migrate_vma_finalize(&migrate);
if (dev)
drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, migrate.dst,
npages, DMA_FROM_DEVICE);
npages, DMA_FROM_DEVICE,
&state);
err_free:
kvfree(buf);
err_out: