2009-06-05 14:42:42 +02:00
/*
* 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
*/
2019-06-08 10:02:40 +02:00
2019-12-03 11:04:02 +01:00
# include <linux/pci.h>
2019-06-08 10:02:40 +02:00
# include <linux/vmalloc.h>
2012-10-02 18:01:07 +01:00
# include <drm/radeon_drm.h>
2017-05-08 15:58:17 -07:00
# ifdef CONFIG_X86
# include <asm/set_memory.h>
# endif
2009-06-05 14:42:42 +02:00
# include "radeon.h"
2012-07-17 14:02:39 -04:00
/*
* 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 .
*/
2009-06-05 14:42:42 +02:00
/*
* Common GART table functions .
*/
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_table_ram_alloc - allocate system ram for gart page table
*
* @ rdev : radeon_device pointer
*
* Allocate system memory for GART page table
* ( r1xx - r3xx , non - pcie r4xx , rs400 ) . These asics require the
* gart table to be in system memory .
* Returns 0 for success , - ENOMEM for failure .
*/
2009-06-05 14:42:42 +02:00
int radeon_gart_table_ram_alloc ( struct radeon_device * rdev )
{
void * ptr ;
drm/radeon: switch from 'pci_' to 'dma_' API
The wrappers in include/linux/pci-dma-compat.h should go away.
The patch has been generated with the coccinelle script below and has been
hand modified to replace GFP_ with a correct flag.
It has been compile tested.
When memory is allocated in 'radeon_gart_table_ram_alloc()' GFP_KERNEL
can be used because its callers already use this flag.
Both 'r100_pci_gart_init()' (r100.c) and 'rs400_gart_init()' (rs400.c)
call 'radeon_gart_init()'.
This function uses 'vmalloc'.
@@
@@
- PCI_DMA_BIDIRECTIONAL
+ DMA_BIDIRECTIONAL
@@
@@
- PCI_DMA_TODEVICE
+ DMA_TO_DEVICE
@@
@@
- PCI_DMA_FROMDEVICE
+ DMA_FROM_DEVICE
@@
@@
- PCI_DMA_NONE
+ DMA_NONE
@@
expression e1, e2, e3;
@@
- pci_alloc_consistent(e1, e2, e3)
+ dma_alloc_coherent(&e1->dev, e2, e3, GFP_)
@@
expression e1, e2, e3;
@@
- pci_zalloc_consistent(e1, e2, e3)
+ dma_alloc_coherent(&e1->dev, e2, e3, GFP_)
@@
expression e1, e2, e3, e4;
@@
- pci_free_consistent(e1, e2, e3, e4)
+ dma_free_coherent(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_map_single(e1, e2, e3, e4)
+ dma_map_single(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_unmap_single(e1, e2, e3, e4)
+ dma_unmap_single(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4, e5;
@@
- pci_map_page(e1, e2, e3, e4, e5)
+ dma_map_page(&e1->dev, e2, e3, e4, e5)
@@
expression e1, e2, e3, e4;
@@
- pci_unmap_page(e1, e2, e3, e4)
+ dma_unmap_page(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_map_sg(e1, e2, e3, e4)
+ dma_map_sg(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_unmap_sg(e1, e2, e3, e4)
+ dma_unmap_sg(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_single_for_cpu(e1, e2, e3, e4)
+ dma_sync_single_for_cpu(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_single_for_device(e1, e2, e3, e4)
+ dma_sync_single_for_device(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_sg_for_cpu(e1, e2, e3, e4)
+ dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_sg_for_device(e1, e2, e3, e4)
+ dma_sync_sg_for_device(&e1->dev, e2, e3, e4)
@@
expression e1, e2;
@@
- pci_dma_mapping_error(e1, e2)
+ dma_mapping_error(&e1->dev, e2)
@@
expression e1, e2;
@@
- pci_set_dma_mask(e1, e2)
+ dma_set_mask(&e1->dev, e2)
@@
expression e1, e2;
@@
- pci_set_consistent_dma_mask(e1, e2)
+ dma_set_coherent_mask(&e1->dev, e2)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-07-27 12:34:21 +02:00
ptr = dma_alloc_coherent ( & rdev - > pdev - > dev , rdev - > gart . table_size ,
& rdev - > gart . table_addr , GFP_KERNEL ) ;
2009-06-05 14:42:42 +02:00
if ( ptr = = NULL ) {
return - ENOMEM ;
}
# ifdef CONFIG_X86
if ( rdev - > family = = CHIP_RS400 | | rdev - > family = = CHIP_RS480 | |
rdev - > family = = CHIP_RS690 | | rdev - > family = = CHIP_RS740 ) {
set_memory_uc ( ( unsigned long ) ptr ,
rdev - > gart . table_size > > PAGE_SHIFT ) ;
}
# endif
2011-11-03 11:16:49 -04:00
rdev - > gart . ptr = ptr ;
2009-06-05 14:42:42 +02:00
return 0 ;
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_table_ram_free - free system ram for gart page table
*
* @ rdev : radeon_device pointer
*
* Free system memory for GART page table
* ( r1xx - r3xx , non - pcie r4xx , rs400 ) . These asics require the
* gart table to be in system memory .
*/
2009-06-05 14:42:42 +02:00
void radeon_gart_table_ram_free ( struct radeon_device * rdev )
{
2011-11-03 11:16:49 -04:00
if ( rdev - > gart . ptr = = NULL ) {
2009-06-05 14:42:42 +02:00
return ;
}
# ifdef CONFIG_X86
if ( rdev - > family = = CHIP_RS400 | | rdev - > family = = CHIP_RS480 | |
rdev - > family = = CHIP_RS690 | | rdev - > family = = CHIP_RS740 ) {
2011-11-03 11:16:49 -04:00
set_memory_wb ( ( unsigned long ) rdev - > gart . ptr ,
2009-06-05 14:42:42 +02:00
rdev - > gart . table_size > > PAGE_SHIFT ) ;
}
# endif
drm/radeon: switch from 'pci_' to 'dma_' API
The wrappers in include/linux/pci-dma-compat.h should go away.
The patch has been generated with the coccinelle script below and has been
hand modified to replace GFP_ with a correct flag.
It has been compile tested.
When memory is allocated in 'radeon_gart_table_ram_alloc()' GFP_KERNEL
can be used because its callers already use this flag.
Both 'r100_pci_gart_init()' (r100.c) and 'rs400_gart_init()' (rs400.c)
call 'radeon_gart_init()'.
This function uses 'vmalloc'.
@@
@@
- PCI_DMA_BIDIRECTIONAL
+ DMA_BIDIRECTIONAL
@@
@@
- PCI_DMA_TODEVICE
+ DMA_TO_DEVICE
@@
@@
- PCI_DMA_FROMDEVICE
+ DMA_FROM_DEVICE
@@
@@
- PCI_DMA_NONE
+ DMA_NONE
@@
expression e1, e2, e3;
@@
- pci_alloc_consistent(e1, e2, e3)
+ dma_alloc_coherent(&e1->dev, e2, e3, GFP_)
@@
expression e1, e2, e3;
@@
- pci_zalloc_consistent(e1, e2, e3)
+ dma_alloc_coherent(&e1->dev, e2, e3, GFP_)
@@
expression e1, e2, e3, e4;
@@
- pci_free_consistent(e1, e2, e3, e4)
+ dma_free_coherent(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_map_single(e1, e2, e3, e4)
+ dma_map_single(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_unmap_single(e1, e2, e3, e4)
+ dma_unmap_single(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4, e5;
@@
- pci_map_page(e1, e2, e3, e4, e5)
+ dma_map_page(&e1->dev, e2, e3, e4, e5)
@@
expression e1, e2, e3, e4;
@@
- pci_unmap_page(e1, e2, e3, e4)
+ dma_unmap_page(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_map_sg(e1, e2, e3, e4)
+ dma_map_sg(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_unmap_sg(e1, e2, e3, e4)
+ dma_unmap_sg(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_single_for_cpu(e1, e2, e3, e4)
+ dma_sync_single_for_cpu(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_single_for_device(e1, e2, e3, e4)
+ dma_sync_single_for_device(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_sg_for_cpu(e1, e2, e3, e4)
+ dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4)
@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_sg_for_device(e1, e2, e3, e4)
+ dma_sync_sg_for_device(&e1->dev, e2, e3, e4)
@@
expression e1, e2;
@@
- pci_dma_mapping_error(e1, e2)
+ dma_mapping_error(&e1->dev, e2)
@@
expression e1, e2;
@@
- pci_set_dma_mask(e1, e2)
+ dma_set_mask(&e1->dev, e2)
@@
expression e1, e2;
@@
- pci_set_consistent_dma_mask(e1, e2)
+ dma_set_coherent_mask(&e1->dev, e2)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2020-07-27 12:34:21 +02:00
dma_free_coherent ( & rdev - > pdev - > dev , rdev - > gart . table_size ,
( void * ) rdev - > gart . ptr , rdev - > gart . table_addr ) ;
2011-11-03 11:16:49 -04:00
rdev - > gart . ptr = NULL ;
2009-06-05 14:42:42 +02:00
rdev - > gart . table_addr = 0 ;
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_table_vram_alloc - allocate vram for gart page table
*
* @ rdev : radeon_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 .
*/
2009-06-05 14:42:42 +02:00
int radeon_gart_table_vram_alloc ( struct radeon_device * rdev )
{
int r ;
2011-11-03 11:16:49 -04:00
if ( rdev - > gart . robj = = NULL ) {
2011-02-18 17:59:16 +01:00
r = radeon_bo_create ( rdev , rdev - > gart . table_size ,
2010-11-17 19:00:26 -05:00
PAGE_SIZE , true , RADEON_GEM_DOMAIN_VRAM ,
2014-09-18 14:11:56 +02:00
0 , NULL , NULL , & rdev - > gart . robj ) ;
2009-06-05 14:42:42 +02:00
if ( r ) {
return r ;
}
}
2009-09-14 18:29:49 +02:00
return 0 ;
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_table_vram_pin - pin gart page table in vram
*
* @ rdev : radeon_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 .
*/
2009-09-14 18:29:49 +02:00
int radeon_gart_table_vram_pin ( struct radeon_device * rdev )
{
uint64_t gpu_addr ;
int r ;
2011-11-03 11:16:49 -04:00
r = radeon_bo_reserve ( rdev - > gart . robj , false ) ;
2009-11-20 14:29:23 +01:00
if ( unlikely ( r ! = 0 ) )
2009-06-05 14:42:42 +02:00
return r ;
2011-11-03 11:16:49 -04:00
r = radeon_bo_pin ( rdev - > gart . robj ,
2009-11-20 14:29:23 +01:00
RADEON_GEM_DOMAIN_VRAM , & gpu_addr ) ;
2009-06-05 14:42:42 +02:00
if ( r ) {
2011-11-03 11:16:49 -04:00
radeon_bo_unreserve ( rdev - > gart . robj ) ;
2009-06-05 14:42:42 +02:00
return r ;
}
2011-11-03 11:16:49 -04:00
r = radeon_bo_kmap ( rdev - > gart . robj , & rdev - > gart . ptr ) ;
2009-11-20 14:29:23 +01:00
if ( r )
2011-11-03 11:16:49 -04:00
radeon_bo_unpin ( rdev - > gart . robj ) ;
radeon_bo_unreserve ( rdev - > gart . robj ) ;
2009-06-05 14:42:42 +02:00
rdev - > gart . table_addr = gpu_addr ;
2015-01-22 18:58:46 +09:00
if ( ! r ) {
int i ;
/* We might have dropped some GART table updates while it wasn't
* mapped , restore all entries
*/
for ( i = 0 ; i < rdev - > gart . num_gpu_pages ; i + + )
radeon_gart_set_page ( rdev , i , rdev - > gart . pages_entry [ i ] ) ;
mb ( ) ;
radeon_gart_tlb_flush ( rdev ) ;
}
2009-11-20 14:29:23 +01:00
return r ;
2009-06-05 14:42:42 +02:00
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_table_vram_unpin - unpin gart page table in vram
*
* @ rdev : radeon_device pointer
*
* Unpin the GART page table in vram ( pcie r4xx , r5xx + ) .
* These asics require the gart table to be in video memory .
*/
2011-11-03 11:16:49 -04:00
void radeon_gart_table_vram_unpin ( struct radeon_device * rdev )
2009-06-05 14:42:42 +02:00
{
2009-11-20 14:29:23 +01:00
int r ;
2011-11-03 11:16:49 -04:00
if ( rdev - > gart . robj = = NULL ) {
2009-06-05 14:42:42 +02:00
return ;
}
2011-11-03 11:16:49 -04:00
r = radeon_bo_reserve ( rdev - > gart . robj , false ) ;
2009-11-20 14:29:23 +01:00
if ( likely ( r = = 0 ) ) {
2011-11-03 11:16:49 -04:00
radeon_bo_kunmap ( rdev - > gart . robj ) ;
radeon_bo_unpin ( rdev - > gart . robj ) ;
radeon_bo_unreserve ( rdev - > gart . robj ) ;
rdev - > gart . ptr = NULL ;
}
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_table_vram_free - free gart page table vram
*
* @ rdev : radeon_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 .
*/
2011-11-03 11:16:49 -04:00
void radeon_gart_table_vram_free ( struct radeon_device * rdev )
{
if ( rdev - > gart . robj = = NULL ) {
return ;
2009-11-20 14:29:23 +01:00
}
2011-11-03 11:16:49 -04:00
radeon_bo_unref ( & rdev - > gart . robj ) ;
2009-06-05 14:42:42 +02:00
}
/*
* Common gart functions .
*/
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_unbind - unbind pages from the gart page table
*
* @ rdev : radeon_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 ) .
*/
2009-06-05 14:42:42 +02:00
void radeon_gart_unbind ( struct radeon_device * rdev , unsigned offset ,
int pages )
{
unsigned t ;
unsigned p ;
int i , j ;
if ( ! rdev - > gart . ready ) {
2011-08-31 21:54:07 +00:00
WARN ( 1 , " trying to unbind memory from uninitialized GART ! \n " ) ;
2009-06-05 14:42:42 +02:00
return ;
}
2009-10-14 00:34:41 -04:00
t = offset / RADEON_GPU_PAGE_SIZE ;
p = t / ( PAGE_SIZE / RADEON_GPU_PAGE_SIZE ) ;
2009-06-05 14:42:42 +02:00
for ( i = 0 ; i < pages ; i + + , p + + ) {
if ( rdev - > gart . pages [ p ] ) {
rdev - > gart . pages [ p ] = NULL ;
2009-10-14 00:34:41 -04:00
for ( j = 0 ; j < ( PAGE_SIZE / RADEON_GPU_PAGE_SIZE ) ; j + + , t + + ) {
2015-01-21 17:36:35 +09:00
rdev - > gart . pages_entry [ t ] = rdev - > dummy_page . entry ;
2011-11-03 11:16:49 -04:00
if ( rdev - > gart . ptr ) {
2015-01-21 17:36:35 +09:00
radeon_gart_set_page ( rdev , t ,
rdev - > dummy_page . entry ) ;
2011-11-03 11:16:49 -04:00
}
2009-06-05 14:42:42 +02:00
}
}
}
2015-07-03 10:02:27 +09:00
if ( rdev - > gart . ptr ) {
mb ( ) ;
radeon_gart_tlb_flush ( rdev ) ;
}
2009-06-05 14:42:42 +02:00
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_bind - bind pages into the gart page table
*
* @ rdev : radeon_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
2014-07-17 19:01:07 +09:00
* @ flags : RADEON_GART_PAGE_ * flags
2012-07-17 14:02:39 -04:00
*
* Binds the requested pages to the gart page table
* ( all asics ) .
* Returns 0 for success , - EINVAL for failure .
*/
2009-06-05 14:42:42 +02:00
int radeon_gart_bind ( struct radeon_device * rdev , unsigned offset ,
2014-07-17 19:01:07 +09:00
int pages , struct page * * pagelist , dma_addr_t * dma_addr ,
uint32_t flags )
2009-06-05 14:42:42 +02:00
{
unsigned t ;
unsigned p ;
2015-01-21 17:36:35 +09:00
uint64_t page_base , page_entry ;
2009-06-05 14:42:42 +02:00
int i , j ;
if ( ! rdev - > gart . ready ) {
2011-08-31 21:54:07 +00:00
WARN ( 1 , " trying to bind memory to uninitialized GART ! \n " ) ;
2009-06-05 14:42:42 +02:00
return - EINVAL ;
}
2009-10-14 00:34:41 -04:00
t = offset / RADEON_GPU_PAGE_SIZE ;
p = t / ( PAGE_SIZE / RADEON_GPU_PAGE_SIZE ) ;
2009-06-05 14:42:42 +02:00
for ( i = 0 ; i < pages ; i + + , p + + ) {
rdev - > gart . pages [ p ] = pagelist [ i ] ;
2015-01-21 17:36:35 +09:00
page_base = dma_addr [ i ] ;
for ( j = 0 ; j < ( PAGE_SIZE / RADEON_GPU_PAGE_SIZE ) ; j + + , t + + ) {
page_entry = radeon_gart_get_page_entry ( page_base , flags ) ;
rdev - > gart . pages_entry [ t ] = page_entry ;
if ( rdev - > gart . ptr ) {
radeon_gart_set_page ( rdev , t , page_entry ) ;
2011-11-03 11:16:49 -04:00
}
2015-01-21 17:36:35 +09:00
page_base + = RADEON_GPU_PAGE_SIZE ;
2009-06-05 14:42:42 +02:00
}
}
2015-07-03 10:02:27 +09:00
if ( rdev - > gart . ptr ) {
mb ( ) ;
radeon_gart_tlb_flush ( rdev ) ;
}
2009-06-05 14:42:42 +02:00
return 0 ;
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_init - init the driver info for managing the gart
*
* @ rdev : radeon_device pointer
*
* Allocate the dummy page and init the gart driver info ( all asics ) .
* Returns 0 for success , error for failure .
*/
2009-06-05 14:42:42 +02:00
int radeon_gart_init ( struct radeon_device * rdev )
{
2010-02-05 16:00:07 +10:00
int r , i ;
2009-06-05 14:42:42 +02:00
if ( rdev - > gart . pages ) {
return 0 ;
}
2009-10-14 00:34:41 -04:00
/* We need PAGE_SIZE >= RADEON_GPU_PAGE_SIZE */
if ( PAGE_SIZE < RADEON_GPU_PAGE_SIZE ) {
2009-06-05 14:42:42 +02:00
DRM_ERROR ( " Page size is smaller than GPU page size! \n " ) ;
return - EINVAL ;
}
2010-02-05 16:00:07 +10:00
r = radeon_dummy_page_init ( rdev ) ;
if ( r )
return r ;
2009-06-05 14:42:42 +02:00
/* Compute table size */
rdev - > gart . num_cpu_pages = rdev - > mc . gtt_size / PAGE_SIZE ;
2009-10-14 00:34:41 -04:00
rdev - > gart . num_gpu_pages = rdev - > mc . gtt_size / RADEON_GPU_PAGE_SIZE ;
2009-06-05 14:42:42 +02:00
DRM_INFO ( " GART: num cpu pages %u, num gpu pages %u \n " ,
rdev - > gart . num_cpu_pages , rdev - > gart . num_gpu_pages ) ;
/* 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>
2018-06-12 14:27:37 -07:00
rdev - > gart . pages = vzalloc ( array_size ( sizeof ( void * ) ,
rdev - > gart . num_cpu_pages ) ) ;
2009-06-05 14:42:42 +02:00
if ( rdev - > gart . pages = = NULL ) {
radeon_gart_fini ( rdev ) ;
return - ENOMEM ;
}
treewide: Use array_size() in vmalloc()
The vmalloc() function has no 2-factor argument form, so multiplication
factors need to be wrapped in array_size(). This patch replaces cases of:
vmalloc(a * b)
with:
vmalloc(array_size(a, b))
as well as handling cases of:
vmalloc(a * b * c)
with:
vmalloc(array3_size(a, b, c))
This does, however, attempt to ignore constant size factors like:
vmalloc(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;
@@
(
vmalloc(
- (sizeof(TYPE)) * E
+ sizeof(TYPE) * E
, ...)
|
vmalloc(
- (sizeof(THING)) * E
+ sizeof(THING) * E
, ...)
)
// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@
(
vmalloc(
- sizeof(u8) * (COUNT)
+ COUNT
, ...)
|
vmalloc(
- sizeof(__u8) * (COUNT)
+ COUNT
, ...)
|
vmalloc(
- sizeof(char) * (COUNT)
+ COUNT
, ...)
|
vmalloc(
- sizeof(unsigned char) * (COUNT)
+ COUNT
, ...)
|
vmalloc(
- sizeof(u8) * COUNT
+ COUNT
, ...)
|
vmalloc(
- sizeof(__u8) * COUNT
+ COUNT
, ...)
|
vmalloc(
- sizeof(char) * COUNT
+ COUNT
, ...)
|
vmalloc(
- 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;
@@
(
vmalloc(
- sizeof(TYPE) * (COUNT_ID)
+ array_size(COUNT_ID, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(TYPE) * COUNT_ID
+ array_size(COUNT_ID, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(TYPE) * (COUNT_CONST)
+ array_size(COUNT_CONST, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(TYPE) * COUNT_CONST
+ array_size(COUNT_CONST, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(THING) * (COUNT_ID)
+ array_size(COUNT_ID, sizeof(THING))
, ...)
|
vmalloc(
- sizeof(THING) * COUNT_ID
+ array_size(COUNT_ID, sizeof(THING))
, ...)
|
vmalloc(
- sizeof(THING) * (COUNT_CONST)
+ array_size(COUNT_CONST, sizeof(THING))
, ...)
|
vmalloc(
- sizeof(THING) * COUNT_CONST
+ array_size(COUNT_CONST, sizeof(THING))
, ...)
)
// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@
vmalloc(
- 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;
@@
(
vmalloc(
- sizeof(TYPE) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(TYPE) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(TYPE) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(TYPE) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
, ...)
|
vmalloc(
- sizeof(THING) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
vmalloc(
- sizeof(THING) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
vmalloc(
- sizeof(THING) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
, ...)
|
vmalloc(
- 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;
@@
(
vmalloc(
- sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
vmalloc(
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
, ...)
|
vmalloc(
- sizeof(THING1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
vmalloc(
- sizeof(THING1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
, ...)
|
vmalloc(
- sizeof(TYPE1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
, ...)
|
vmalloc(
- 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;
@@
(
vmalloc(
- (COUNT) * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- COUNT * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- COUNT * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- (COUNT) * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- COUNT * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- (COUNT) * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- (COUNT) * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
, ...)
|
vmalloc(
- 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;
@@
(
vmalloc(C1 * C2 * C3, ...)
|
vmalloc(
- 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;
@@
(
vmalloc(C1 * C2, ...)
|
vmalloc(
- E1 * E2
+ array_size(E1, E2)
, ...)
)
Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 14:27:11 -07:00
rdev - > gart . pages_entry = vmalloc ( array_size ( sizeof ( uint64_t ) ,
rdev - > gart . num_gpu_pages ) ) ;
2015-01-21 17:36:35 +09:00
if ( rdev - > gart . pages_entry = = NULL ) {
radeon_gart_fini ( rdev ) ;
return - ENOMEM ;
}
2010-02-05 16:00:07 +10:00
/* set GART entry to point to the dummy page by default */
2015-01-21 17:36:35 +09:00
for ( i = 0 ; i < rdev - > gart . num_gpu_pages ; i + + )
rdev - > gart . pages_entry [ i ] = rdev - > dummy_page . entry ;
2009-06-05 14:42:42 +02:00
return 0 ;
}
2012-07-17 14:02:39 -04:00
/**
* radeon_gart_fini - tear down the driver info for managing the gart
*
* @ rdev : radeon_device pointer
*
* Tear down the gart driver info and free the dummy page ( all asics ) .
*/
2009-06-05 14:42:42 +02:00
void radeon_gart_fini ( struct radeon_device * rdev )
{
2015-01-21 17:36:35 +09:00
if ( rdev - > gart . ready ) {
2009-06-05 14:42:42 +02:00
/* unbind pages */
radeon_gart_unbind ( rdev , 0 , rdev - > gart . num_cpu_pages ) ;
}
rdev - > gart . ready = false ;
2012-10-23 15:53:17 +02:00
vfree ( rdev - > gart . pages ) ;
2015-01-21 17:36:35 +09:00
vfree ( rdev - > gart . pages_entry ) ;
2009-06-05 14:42:42 +02:00
rdev - > gart . pages = NULL ;
2015-01-21 17:36:35 +09:00
rdev - > gart . pages_entry = NULL ;
2011-04-12 13:32:13 -04:00
radeon_dummy_page_fini ( rdev ) ;
2009-06-05 14:42:42 +02:00
}