OpenCloudOS-Kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c

393 lines
10 KiB
C
Raw Normal View History

/*
* Copyright 2008 Advanced Micro Devices, Inc.
* Copyright 2008 Red Hat Inc.
* Copyright 2009 Jerome Glisse.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
* OTHER DEALINGS IN THE SOFTWARE.
*
* Authors: Dave Airlie
* Alex Deucher
* Jerome Glisse
*/
#include <drm/drmP.h>
#include <drm/amdgpu_drm.h>
#ifdef CONFIG_X86
#include <asm/set_memory.h>
#endif
#include "amdgpu.h"
/*
* GART
* The GART (Graphics Aperture Remapping Table) is an aperture
* in the GPU's address space. System pages can be mapped into
* the aperture and look like contiguous pages from the GPU's
* perspective. A page table maps the pages in the aperture
* to the actual backing pages in system memory.
*
* Radeon GPUs support both an internal GART, as described above,
* and AGP. AGP works similarly, but the GART table is configured
* and maintained by the northbridge rather than the driver.
* Radeon hw has a separate AGP aperture that is programmed to
* point to the AGP aperture provided by the northbridge and the
* requests are passed through to the northbridge aperture.
* Both AGP and internal GART can be used at the same time, however
* that is not currently supported by the driver.
*
* This file handles the common internal GART management.
*/
/*
* Common GART table functions.
*/
/**
* amdgpu_dummy_page_init - init dummy page used by the driver
*
* @adev: amdgpu_device pointer
*
* Allocate the dummy page used by the driver (all asics).
* This dummy page is used by the driver as a filler for gart entries
* when pages are taken out of the GART
* Returns 0 on sucess, -ENOMEM on failure.
*/
static int amdgpu_gart_dummy_page_init(struct amdgpu_device *adev)
{
struct page *dummy_page = adev->mman.bdev.glob->dummy_read_page;
if (adev->dummy_page_addr)
return 0;
adev->dummy_page_addr = pci_map_page(adev->pdev, dummy_page, 0,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
if (pci_dma_mapping_error(adev->pdev, adev->dummy_page_addr)) {
dev_err(&adev->pdev->dev, "Failed to DMA MAP the dummy page\n");
adev->dummy_page_addr = 0;
return -ENOMEM;
}
return 0;
}
/**
* amdgpu_dummy_page_fini - free dummy page used by the driver
*
* @adev: amdgpu_device pointer
*
* Frees the dummy page used by the driver (all asics).
*/
static void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev)
{
if (!adev->dummy_page_addr)
return;
pci_unmap_page(adev->pdev, adev->dummy_page_addr,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
adev->dummy_page_addr = 0;
}
/**
* amdgpu_gart_table_vram_alloc - allocate vram for gart page table
*
* @adev: amdgpu_device pointer
*
* Allocate video memory for GART page table
* (pcie r4xx, r5xx+). These asics require the
* gart table to be in video memory.
* Returns 0 for success, error for failure.
*/
int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
{
int r;
if (adev->gart.bo == NULL) {
struct amdgpu_bo_param bp;
memset(&bp, 0, sizeof(bp));
bp.size = adev->gart.table_size;
bp.byte_align = PAGE_SIZE;
bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
bp.type = ttm_bo_type_kernel;
bp.resv = NULL;
r = amdgpu_bo_create(adev, &bp, &adev->gart.bo);
if (r) {
return r;
}
}
return 0;
}
/**
* amdgpu_gart_table_vram_pin - pin gart page table in vram
*
* @adev: amdgpu_device pointer
*
* Pin the GART page table in vram so it will not be moved
* by the memory manager (pcie r4xx, r5xx+). These asics require the
* gart table to be in video memory.
* Returns 0 for success, error for failure.
*/
int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
{
int r;
r = amdgpu_bo_reserve(adev->gart.bo, false);
if (unlikely(r != 0))
return r;
r = amdgpu_bo_pin(adev->gart.bo, AMDGPU_GEM_DOMAIN_VRAM);
if (r) {
amdgpu_bo_unreserve(adev->gart.bo);
return r;
}
r = amdgpu_bo_kmap(adev->gart.bo, &adev->gart.ptr);
if (r)
amdgpu_bo_unpin(adev->gart.bo);
amdgpu_bo_unreserve(adev->gart.bo);
return r;
}
/**
* amdgpu_gart_table_vram_unpin - unpin gart page table in vram
*
* @adev: amdgpu_device pointer
*
* Unpin the GART page table in vram (pcie r4xx, r5xx+).
* These asics require the gart table to be in video memory.
*/
void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev)
{
int r;
if (adev->gart.bo == NULL) {
return;
}
r = amdgpu_bo_reserve(adev->gart.bo, true);
if (likely(r == 0)) {
amdgpu_bo_kunmap(adev->gart.bo);
amdgpu_bo_unpin(adev->gart.bo);
amdgpu_bo_unreserve(adev->gart.bo);
adev->gart.ptr = NULL;
}
}
/**
* amdgpu_gart_table_vram_free - free gart page table vram
*
* @adev: amdgpu_device pointer
*
* Free the video memory used for the GART page table
* (pcie r4xx, r5xx+). These asics require the gart table to
* be in video memory.
*/
void amdgpu_gart_table_vram_free(struct amdgpu_device *adev)
{
if (adev->gart.bo == NULL) {
return;
}
amdgpu_bo_unref(&adev->gart.bo);
}
/*
* Common gart functions.
*/
/**
* amdgpu_gart_unbind - unbind pages from the gart page table
*
* @adev: amdgpu_device pointer
* @offset: offset into the GPU's gart aperture
* @pages: number of pages to unbind
*
* Unbinds the requested pages from the gart page table and
* replaces them with the dummy page (all asics).
* Returns 0 for success, -EINVAL for failure.
*/
int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
int pages)
{
unsigned t;
unsigned p;
int i, j;
u64 page_base;
/* Starting from VEGA10, system bit must be 0 to mean invalid. */
uint64_t flags = 0;
if (!adev->gart.ready) {
WARN(1, "trying to unbind memory from uninitialized GART !\n");
return -EINVAL;
}
t = offset / AMDGPU_GPU_PAGE_SIZE;
p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
for (i = 0; i < pages; i++, p++) {
#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
adev->gart.pages[p] = NULL;
#endif
page_base = adev->dummy_page_addr;
if (!adev->gart.ptr)
continue;
for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr,
t, page_base, flags);
page_base += AMDGPU_GPU_PAGE_SIZE;
}
}
mb();
amdgpu_asic_flush_hdp(adev, NULL);
amdgpu_gmc_flush_gpu_tlb(adev, 0);
return 0;
}
/**
* amdgpu_gart_map - map dma_addresses into GART entries
*
* @adev: amdgpu_device pointer
* @offset: offset into the GPU's gart aperture
* @pages: number of pages to bind
* @dma_addr: DMA addresses of pages
*
* Map the dma_addresses into GART entries (all asics).
* Returns 0 for success, -EINVAL for failure.
*/
int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
int pages, dma_addr_t *dma_addr, uint64_t flags,
void *dst)
{
uint64_t page_base;
unsigned i, j, t;
if (!adev->gart.ready) {
WARN(1, "trying to bind memory to uninitialized GART !\n");
return -EINVAL;
}
t = offset / AMDGPU_GPU_PAGE_SIZE;
for (i = 0; i < pages; i++) {
page_base = dma_addr[i];
for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
page_base += AMDGPU_GPU_PAGE_SIZE;
}
}
return 0;
}
/**
* amdgpu_gart_bind - bind pages into the gart page table
*
* @adev: amdgpu_device pointer
* @offset: offset into the GPU's gart aperture
* @pages: number of pages to bind
* @pagelist: pages to bind
* @dma_addr: DMA addresses of pages
*
* Binds the requested pages to the gart page table
* (all asics).
* Returns 0 for success, -EINVAL for failure.
*/
int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
int pages, struct page **pagelist, dma_addr_t *dma_addr,
uint64_t flags)
{
#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
unsigned i,t,p;
#endif
int r;
if (!adev->gart.ready) {
WARN(1, "trying to bind memory to uninitialized GART !\n");
return -EINVAL;
}
#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
t = offset / AMDGPU_GPU_PAGE_SIZE;
p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
for (i = 0; i < pages; i++, p++)
adev->gart.pages[p] = pagelist ? pagelist[i] : NULL;
#endif
if (!adev->gart.ptr)
return 0;
r = amdgpu_gart_map(adev, offset, pages, dma_addr, flags,
adev->gart.ptr);
if (r)
return r;
mb();
amdgpu_asic_flush_hdp(adev, NULL);
amdgpu_gmc_flush_gpu_tlb(adev, 0);
return 0;
}
/**
* amdgpu_gart_init - init the driver info for managing the gart
*
* @adev: amdgpu_device pointer
*
* Allocate the dummy page and init the gart driver info (all asics).
* Returns 0 for success, error for failure.
*/
int amdgpu_gart_init(struct amdgpu_device *adev)
{
int r;
if (adev->dummy_page_addr)
return 0;
/* We need PAGE_SIZE >= AMDGPU_GPU_PAGE_SIZE */
if (PAGE_SIZE < AMDGPU_GPU_PAGE_SIZE) {
DRM_ERROR("Page size is smaller than GPU page size!\n");
return -EINVAL;
}
r = amdgpu_gart_dummy_page_init(adev);
if (r)
return r;
/* Compute table size */
adev->gart.num_cpu_pages = adev->gmc.gart_size / PAGE_SIZE;
adev->gart.num_gpu_pages = adev->gmc.gart_size / AMDGPU_GPU_PAGE_SIZE;
DRM_INFO("GART: num cpu pages %u, num gpu pages %u\n",
adev->gart.num_cpu_pages, adev->gart.num_gpu_pages);
#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
/* Allocate pages table */
treewide: Use array_size() in vzalloc() The vzalloc() function has no 2-factor argument form, so multiplication factors need to be wrapped in array_size(). This patch replaces cases of: vzalloc(a * b) with: vzalloc(array_size(a, b)) as well as handling cases of: vzalloc(a * b * c) with: vzalloc(array3_size(a, b, c)) This does, however, attempt to ignore constant size factors like: vzalloc(4 * 1024) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( vzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | vzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( vzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | vzalloc( - sizeof(u8) * COUNT + COUNT , ...) | vzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | vzalloc( - sizeof(char) * COUNT + COUNT , ...) | vzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( vzalloc( - sizeof(TYPE) * (COUNT_ID) + array_size(COUNT_ID, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT_ID + array_size(COUNT_ID, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT_CONST + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | vzalloc( - sizeof(THING) * (COUNT_ID) + array_size(COUNT_ID, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT_ID + array_size(COUNT_ID, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT_CONST + array_size(COUNT_CONST, sizeof(THING)) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ vzalloc( - SIZE * COUNT + array_size(COUNT, SIZE) , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( vzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | vzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | vzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( vzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | vzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | vzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | vzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( vzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | vzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( vzalloc(C1 * C2 * C3, ...) | vzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants. @@ expression E1, E2; constant C1, C2; @@ ( vzalloc(C1 * C2, ...) | vzalloc( - E1 * E2 + array_size(E1, E2) , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:27:37 +08:00
adev->gart.pages = vzalloc(array_size(sizeof(void *),
adev->gart.num_cpu_pages));
if (adev->gart.pages == NULL)
return -ENOMEM;
#endif
return 0;
}
/**
* amdgpu_gart_fini - tear down the driver info for managing the gart
*
* @adev: amdgpu_device pointer
*
* Tear down the gart driver info and free the dummy page (all asics).
*/
void amdgpu_gart_fini(struct amdgpu_device *adev)
{
#ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
vfree(adev->gart.pages);
adev->gart.pages = NULL;
#endif
amdgpu_gart_dummy_page_fini(adev);
}