ioremap buffer according to TTM mem caching setting
If tbo.mem.bus.caching is cached, buffer is intended to be mapped as cached from CPU. Map it with ioremap_cache.
This wasn't necessary before as device memory was never mapped as cached from CPU side. It becomes necessary for aldebaran as device memory is mapped cached from CPU.
Signed-off-by: Oak Zeng Oak.Zeng@amd.com Reviewed-by: Christian Konig Christian.Koenig@amd.com --- drivers/gpu/drm/ttm/ttm_bo_util.c | 8 ++++++++ 1 file changed, 8 insertions(+)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 031e581..8c65a13 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -91,6 +91,8 @@ static int ttm_resource_ioremap(struct ttm_device *bdev,
if (mem->bus.caching == ttm_write_combined) addr = ioremap_wc(mem->bus.offset, bus_size); + else if (mem->bus.caching == ttm_cached) + addr = ioremap_wc(mem->bus.offset, bus_size); else addr = ioremap(mem->bus.offset, bus_size); if (!addr) { @@ -372,6 +374,9 @@ static int ttm_bo_ioremap(struct ttm_buffer_object *bo, if (mem->bus.caching == ttm_write_combined) map->virtual = ioremap_wc(bo->mem.bus.offset + offset, size); + else if (mem->bus.caching == ttm_cached) + map->virtual = ioremap_wc(bo->mem.bus.offset + offset, + size); else map->virtual = ioremap(bo->mem.bus.offset + offset, size); @@ -490,6 +495,9 @@ int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) else if (mem->bus.caching == ttm_write_combined) vaddr_iomem = ioremap_wc(mem->bus.offset, bo->base.size); + else if (mem->bus.caching == ttm_cached) + vaddr_iomem = ioremap_cache(mem->bus.offset, + bo->base.size); else vaddr_iomem = ioremap(mem->bus.offset, bo->base.size);
Hi Oak,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on drm-intel/for-linux-next] [also build test ERROR on drm-tip/drm-tip linus/master v5.12-rc1 next-20210303] [cannot apply to tegra-drm/drm/tegra/for-next drm-exynos/exynos-drm-next drm/drm-next] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Oak-Zeng/drm-ttm-PLEASE-ignore-Just... base: git://anongit.freedesktop.org/drm-intel for-linux-next config: s390-randconfig-r003-20210303 (attached as .config) compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project a7cad6680b4087eff8994f1f99ac40c661a6621f) reproduce (this is a W=1 build): wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross # install s390 cross compiling tool for clang build # apt-get install binutils-s390x-linux-gnu # https://github.com/0day-ci/linux/commit/00ccdcad822515e31482876e46504b6038e9... git remote add linux-review https://github.com/0day-ci/linux git fetch --no-tags linux-review Oak-Zeng/drm-ttm-PLEASE-ignore-Just-test-Intel-build-robot/20210303-091234 git checkout 00ccdcad822515e31482876e46504b6038e904aa # save the attached .config to linux build tree COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=s390
If you fix the issue, kindly add following tag as appropriate Reported-by: kernel test robot lkp@intel.com
All error/warnings (new ones prefixed by >>):
#define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) ^ include/uapi/linux/swab.h:119:21: note: expanded from macro '__swab32' ___constant_swab32(x) : \ ^ include/uapi/linux/swab.h:19:12: note: expanded from macro '___constant_swab32' (((__u32)(x) & (__u32)0x000000ffUL) << 24) | \ ^ In file included from drivers/gpu/drm/ttm/ttm_bo_util.c:35: In file included from include/linux/dma-buf-map.h:9: In file included from include/linux/io.h:13: In file included from arch/s390/include/asm/io.h:80: include/asm-generic/io.h:490:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr)); ~~~~~~~~~~ ^ include/uapi/linux/byteorder/big_endian.h:34:59: note: expanded from macro '__le32_to_cpu' #define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) ^ include/uapi/linux/swab.h:119:21: note: expanded from macro '__swab32' ___constant_swab32(x) : \ ^ include/uapi/linux/swab.h:20:12: note: expanded from macro '___constant_swab32' (((__u32)(x) & (__u32)0x0000ff00UL) << 8) | \ ^ In file included from drivers/gpu/drm/ttm/ttm_bo_util.c:35: In file included from include/linux/dma-buf-map.h:9: In file included from include/linux/io.h:13: In file included from arch/s390/include/asm/io.h:80: include/asm-generic/io.h:490:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr)); ~~~~~~~~~~ ^ include/uapi/linux/byteorder/big_endian.h:34:59: note: expanded from macro '__le32_to_cpu' #define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) ^ include/uapi/linux/swab.h:119:21: note: expanded from macro '__swab32' ___constant_swab32(x) : \ ^ include/uapi/linux/swab.h:21:12: note: expanded from macro '___constant_swab32' (((__u32)(x) & (__u32)0x00ff0000UL) >> 8) | \ ^ In file included from drivers/gpu/drm/ttm/ttm_bo_util.c:35: In file included from include/linux/dma-buf-map.h:9: In file included from include/linux/io.h:13: In file included from arch/s390/include/asm/io.h:80: include/asm-generic/io.h:490:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr)); ~~~~~~~~~~ ^ include/uapi/linux/byteorder/big_endian.h:34:59: note: expanded from macro '__le32_to_cpu' #define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) ^ include/uapi/linux/swab.h:119:21: note: expanded from macro '__swab32' ___constant_swab32(x) : \ ^ include/uapi/linux/swab.h:22:12: note: expanded from macro '___constant_swab32' (((__u32)(x) & (__u32)0xff000000UL) >> 24))) ^ In file included from drivers/gpu/drm/ttm/ttm_bo_util.c:35: In file included from include/linux/dma-buf-map.h:9: In file included from include/linux/io.h:13: In file included from arch/s390/include/asm/io.h:80: include/asm-generic/io.h:490:61: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr)); ~~~~~~~~~~ ^ include/uapi/linux/byteorder/big_endian.h:34:59: note: expanded from macro '__le32_to_cpu' #define __le32_to_cpu(x) __swab32((__force __u32)(__le32)(x)) ^ include/uapi/linux/swab.h:120:12: note: expanded from macro '__swab32' __fswab32(x)) ^ In file included from drivers/gpu/drm/ttm/ttm_bo_util.c:35: In file included from include/linux/dma-buf-map.h:9: In file included from include/linux/io.h:13: In file included from arch/s390/include/asm/io.h:80: include/asm-generic/io.h:501:33: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] __raw_writeb(value, PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:511:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] __raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:521:59: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] __raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr); ~~~~~~~~~~ ^ include/asm-generic/io.h:609:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] readsb(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:617:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] readsw(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:625:20: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] readsl(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:634:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] writesb(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:643:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] writesw(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^ include/asm-generic/io.h:652:21: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] writesl(PCI_IOBASE + addr, buffer, count); ~~~~~~~~~~ ^
drivers/gpu/drm/ttm/ttm_bo_util.c:500:18: error: implicit declaration of function 'ioremap_cache' [-Werror,-Wimplicit-function-declaration]
vaddr_iomem = ioremap_cache(mem->bus.offset, ^
drivers/gpu/drm/ttm/ttm_bo_util.c:500:16: warning: incompatible integer to pointer conversion assigning to 'void *' from 'int' [-Wint-conversion]
vaddr_iomem = ioremap_cache(mem->bus.offset, ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 21 warnings and 1 error generated.
vim +/ioremap_cache +500 drivers/gpu/drm/ttm/ttm_bo_util.c
481 482 int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) 483 { 484 struct ttm_resource *mem = &bo->mem; 485 int ret; 486 487 ret = ttm_mem_io_reserve(bo->bdev, mem); 488 if (ret) 489 return ret; 490 491 if (mem->bus.is_iomem) { 492 void __iomem *vaddr_iomem; 493 494 if (mem->bus.addr) 495 vaddr_iomem = (void __iomem *)mem->bus.addr; 496 else if (mem->bus.caching == ttm_write_combined) 497 vaddr_iomem = ioremap_wc(mem->bus.offset, 498 bo->base.size); 499 else if (mem->bus.caching == ttm_cached)
500 vaddr_iomem = ioremap_cache(mem->bus.offset,
501 bo->base.size); 502 else 503 vaddr_iomem = ioremap(mem->bus.offset, bo->base.size); 504 505 if (!vaddr_iomem) 506 return -ENOMEM; 507 508 dma_buf_map_set_vaddr_iomem(map, vaddr_iomem); 509 510 } else { 511 struct ttm_operation_ctx ctx = { 512 .interruptible = false, 513 .no_wait_gpu = false 514 }; 515 struct ttm_tt *ttm = bo->ttm; 516 pgprot_t prot; 517 void *vaddr; 518 519 ret = ttm_tt_populate(bo->bdev, ttm, &ctx); 520 if (ret) 521 return ret; 522 523 /* 524 * We need to use vmap to get the desired page protection 525 * or to make the buffer object look contiguous. 526 */ 527 prot = ttm_io_prot(bo, mem, PAGE_KERNEL); 528 vaddr = vmap(ttm->pages, ttm->num_pages, 0, prot); 529 if (!vaddr) 530 return -ENOMEM; 531 532 dma_buf_map_set_vaddr(map, vaddr); 533 } 534 535 return 0; 536 } 537 EXPORT_SYMBOL(ttm_bo_vmap); 538
--- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
dri-devel@lists.freedesktop.org
-
kernel test robot -
Oak Zeng