search for: dma_attr_weak_ord

Displaying 20 results from an estimated 25 matches for "dma_attr_weak_ord".

2016 Jun 02
0
[RFC v3 01/45] powerpc: dma-mapping: Don't hard-code the value of DMA_ATTR_WEAK_ORDERING
Hard-coded value of DMA_ATTR_WEAK_ORDERING is then compared with the symbol. This will stop matching if the value of symbol is changed (when switching DMA attributes to unsigned long). Signed-off-by: Krzysztof Kozlowski <k.kozlowski at samsung.com> --- arch/powerpc/platforms/cell/iommu.c | 2 +- 1 file changed, 1 insertion(+),...
2016 Jun 02
0
[RFC v3 44/45] dma-mapping: Remove dma_get_attr
...++ b/arch/powerpc/platforms/cell/iommu.c @@ -193,7 +193,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages, base_pte = CBE_IOPTE_PP_W | CBE_IOPTE_PP_R | CBE_IOPTE_M | CBE_IOPTE_SO_RW | (window->ioid & CBE_IOPTE_IOID_Mask); #endif - if (unlikely(dma_get_attr(DMA_ATTR_WEAK_ORDERING, attrs))) + if (unlikely(attrs & DMA_ATTR_WEAK_ORDERING)) base_pte &= ~CBE_IOPTE_SO_RW; io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset); @@ -600,7 +600,7 @@ static dma_addr_t dma_fixed_map_page(struct device *dev, struct page *page, enum dma_dat...
2015 Feb 17
1
[PATCH v3 4/6] instmem/gk20a: use DMA attributes
...t; + init_dma_attrs(&node->attrs); > + /* > + * We will access this memory through PRAMIN and thus do not need a > + * consistent CPU pointer > + */ > + dma_set_attr(DMA_ATTR_NON_CONSISTENT, &node->attrs); > + dma_set_attr(DMA_ATTR_WEAK_ORDERING, &node->attrs); > + dma_set_attr(DMA_ATTR_WRITE_COMBINE, &node->attrs); > + dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &node->attrs); I wonder, is it possible to have a per-priv version of this instead of per-object? The kernel's function prototypes ar...
2016 Jun 10
0
[PATCH v4 14/44] drm/nouveau: dma-mapping: Use unsigned long for dma_attrs
...); return -ENOMEM; @@ -597,10 +597,9 @@ gk20a_instmem_new(struct nvkm_device *device, int index, nvkm_info(&imem->base.subdev, "using IOMMU\n"); } else { - init_dma_attrs(&imem->attrs); - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &imem->attrs); - dma_set_attr(DMA_ATTR_WEAK_ORDERING, &imem->attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &imem->attrs); + imem->attrs = DMA_ATTR_NON_CONSISTENT | + DMA_ATTR_WEAK_ORDERING | + DMA_ATTR_WRITE_COMBINE; nvkm_info(&imem->base.subdev, "using DMA API\n"); } -- 1.9.1
2016 Jun 30
0
[PATCH v5 14/44] drm/nouveau: dma-mapping: Use unsigned long for dma_attrs
...); return -ENOMEM; @@ -597,10 +597,9 @@ gk20a_instmem_new(struct nvkm_device *device, int index, nvkm_info(&imem->base.subdev, "using IOMMU\n"); } else { - init_dma_attrs(&imem->attrs); - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &imem->attrs); - dma_set_attr(DMA_ATTR_WEAK_ORDERING, &imem->attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &imem->attrs); + imem->attrs = DMA_ATTR_NON_CONSISTENT | + DMA_ATTR_WEAK_ORDERING | + DMA_ATTR_WRITE_COMBINE; nvkm_info(&imem->base.subdev, "using DMA API\n"); } -- 1.9.1
2016 Jul 13
0
[PATCH v6 15/46] drm/nouveau: dma-mapping: Use unsigned long for dma_attrs
...); return -ENOMEM; @@ -597,10 +597,9 @@ gk20a_instmem_new(struct nvkm_device *device, int index, nvkm_info(&imem->base.subdev, "using IOMMU\n"); } else { - init_dma_attrs(&imem->attrs); - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &imem->attrs); - dma_set_attr(DMA_ATTR_WEAK_ORDERING, &imem->attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &imem->attrs); + imem->attrs = DMA_ATTR_NON_CONSISTENT | + DMA_ATTR_WEAK_ORDERING | + DMA_ATTR_WRITE_COMBINE; nvkm_info(&imem->base.subdev, "using DMA API\n"); } -- 1.9.1
2015 Jan 23
0
[PATCH 4/6] instmem/gk20a: use DMA attributes
...v, npages << PAGE_SHIFT, - &node->handle, GFP_KERNEL); + init_dma_attrs(&node->attrs); + /* + * We will access this memory through PRAMIN and thus do not need a + * consistent CPU pointer + */ + dma_set_attr(DMA_ATTR_NON_CONSISTENT, &node->attrs); + dma_set_attr(DMA_ATTR_WEAK_ORDERING, &node->attrs); + dma_set_attr(DMA_ATTR_WRITE_COMBINE, &node->attrs); + dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &node->attrs); + + node->cpuaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT, + &node->handle, GFP_KERNEL, + &node->attrs); if...
2015 Feb 17
0
[PATCH v3 4/6] instmem/gk20a: use DMA attributes
...v, npages << PAGE_SHIFT, - &node->handle, GFP_KERNEL); + init_dma_attrs(&node->attrs); + /* + * We will access this memory through PRAMIN and thus do not need a + * consistent CPU pointer + */ + dma_set_attr(DMA_ATTR_NON_CONSISTENT, &node->attrs); + dma_set_attr(DMA_ATTR_WEAK_ORDERING, &node->attrs); + dma_set_attr(DMA_ATTR_WRITE_COMBINE, &node->attrs); + dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &node->attrs); + + node->cpuaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT, + &node->handle, GFP_KERNEL, + &node->attrs); if...
2016 Jun 10
1
[PATCH v4 00/44] dma-mapping: Use unsigned long for dma_attrs
...Rebased on next-20160607. For easier testing the patchset is available here: repo: https://github.com/krzk/linux branch: for-next/dma-attrs-const-v4 Changes since v3 ================ 1. Collect some acks. 2. Drop wrong patch 1/45 ("powerpc: dma-mapping: Don't hard-code the value of DMA_ATTR_WEAK_ORDERING"). 3. Minor fix pointed out by Michael Ellerman. Changes since v2 ================ 1. Follow Christoph Hellwig's comments (don't use BIT add documentation, remove dma_get_attr). Rationale ========= The dma-mapping core and the implementations do not change the DMA attribute...
2016 Jun 03
1
[RFC v3 02/45] dma-mapping: Use unsigned long for dma_attrs
...* > + * List of possible attributes associated with a DMA mapping. The semantics > + * of each attribute should be defined in Documentation/DMA-attributes.txt. > + */ > +#define DMA_ATTR_WRITE_BARRIER (1UL << 1) Any particular reason they start at 2, not 1? > +#define DMA_ATTR_WEAK_ORDERING (1UL << 2) > +#define DMA_ATTR_WRITE_COMBINE (1UL << 3) > +#define DMA_ATTR_NON_CONSISTENT (1UL << 4) > +#define DMA_ATTR_NO_KERNEL_MAPPING (1UL << 5) > +#define DMA_ATTR_SKIP_CPU_SYNC (1UL << 6) > +#define...
2016 Jun 02
52
[RFC v3 00/45] dma-mapping: Use unsigned long for dma_attrs
...on the stack and passing pointer to it to dma_set_attr(), just set the bits. 2. It brings safeness and checking for const correctness because the attributes are passed by value. Best regards, Krzysztof Krzysztof Kozlowski (45): powerpc: dma-mapping: Don't hard-code the value of DMA_ATTR_WEAK_ORDERING dma-mapping: Use unsigned long for dma_attrs alpha: dma-mapping: Use unsigned long for dma_attrs arc: dma-mapping: Use unsigned long for dma_attrs ARM: dma-mapping: Use unsigned long for dma_attrs arm64: dma-mapping: Use unsigned long for dma_attrs avr32: dma-mapping: Use unsigned...
2016 Jun 02
0
[RFC v3 02/45] dma-mapping: Use unsigned long for dma_attrs
...ap.h> -#include <linux/bitops.h> -#include <linux/bug.h> - -/** - * an enum dma_attr represents an attribute associated with a DMA - * mapping. The semantics of each attribute should be defined in - * Documentation/DMA-attributes.txt. - */ -enum dma_attr { - DMA_ATTR_WRITE_BARRIER, - DMA_ATTR_WEAK_ORDERING, - DMA_ATTR_WRITE_COMBINE, - DMA_ATTR_NON_CONSISTENT, - DMA_ATTR_NO_KERNEL_MAPPING, - DMA_ATTR_SKIP_CPU_SYNC, - DMA_ATTR_FORCE_CONTIGUOUS, - DMA_ATTR_ALLOC_SINGLE_PAGES, - DMA_ATTR_MAX, -}; - -#define __DMA_ATTRS_LONGS BITS_TO_LONGS(DMA_ATTR_MAX) - -/** - * struct dma_attrs - an opaque contain...
2015 Feb 20
6
[PATCH v4 0/6] nouveau/gk20a: RAM device removal & IOMMU support
Changes since v3: - Use a single dma_attr for all DMA-API allocations in instmem instead of one per allocation - Use device.info.ram_size instead of pfb->ram to check whether VRAM is present outside of nvkm Changes since v2: - Cleaner changes for ltc - Fixed typos in gk20a instmem IOMMU comments Changes since v1: - Add missing else condition in ltc - Remove extra flags that slipped into
2015 Nov 11
2
[PATCH] instmem/gk20a: use DMA API CPU mapping
...iommu_bit = tdev->func->iommu_bit; nvkm_info(&imem->base.subdev, "using IOMMU\n"); } else { init_dma_attrs(&imem->attrs); - /* We will access the memory through our own mapping */ dma_set_attr(DMA_ATTR_NON_CONSISTENT, &imem->attrs); dma_set_attr(DMA_ATTR_WEAK_ORDERING, &imem->attrs); dma_set_attr(DMA_ATTR_WRITE_COMBINE, &imem->attrs); - dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &imem->attrs); - imem->cpu_map = gk20a_instobj_cpu_map_dma; nvkm_info(&imem->base.subdev, "using DMA API\n"); } diff --git a/lib/i...
2016 Jun 30
2
[PATCH v5 00/44] dma-mapping: Use unsigned long for dma_attrs
...d by Robin Murphy. 3. Applied changes from Bart Van Assche's comment. 4. More tests and builds (using https://www.kernel.org/pub/tools/crosstool/). Changes since v3 ================ 1. Collect some acks. 2. Drop wrong patch 1/45 ("powerpc: dma-mapping: Don't hard-code the value of DMA_ATTR_WEAK_ORDERING"). 3. Minor fix pointed out by Michael Ellerman. Changes since v2 ================ 1. Follow Christoph Hellwig's comments (don't use BIT add documentation, remove dma_get_attr). Rationale ========= The dma-mapping core and the implementations do not change the DMA attribute...
2015 Feb 17
8
[PATCH v3 0/6] nouveau/gk20a: RAM device removal & IOMMU support
Thanks Ilia for the v2 review! Here is the v3 of this IOMMU support for GK20A series. Changes since v2: - Cleaner changes for ltc - Fixed typos in gk20a instmem IOMMU comments Changes since v1: - Add missing else condition in ltc - Remove extra flags that slipped into nouveau_display.c and nv84_fence.c. Original cover letter: Patches 1-3 make the presence of a RAM device optional, and remove
2015 Nov 11
0
[PATCH] instmem/gk20a: use DMA API CPU mapping
..._bit; > > nvkm_info(&imem->base.subdev, "using IOMMU\n"); > } else { > init_dma_attrs(&imem->attrs); > - /* We will access the memory through our own mapping */ > dma_set_attr(DMA_ATTR_NON_CONSISTENT, &imem->attrs); > dma_set_attr(DMA_ATTR_WEAK_ORDERING, &imem->attrs); > dma_set_attr(DMA_ATTR_WRITE_COMBINE, &imem->attrs); > - dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &imem->attrs); > - imem->cpu_map = gk20a_instobj_cpu_map_dma; > > nvkm_info(&imem->base.subdev, "using DMA API\n"...
2016 Jul 12
0
[PATCH v5 00/44] dma-mapping: Use unsigned long for dma_attrs
...om Bart Van Assche's comment. > 4. More tests and builds (using https://www.kernel.org/pub/tools/crosstool/). > > > Changes since v3 > ================ > 1. Collect some acks. > 2. Drop wrong patch 1/45 ("powerpc: dma-mapping: Don't hard-code > the value of DMA_ATTR_WEAK_ORDERING"). > 3. Minor fix pointed out by Michael Ellerman. > > > Changes since v2 > ================ > 1. Follow Christoph Hellwig's comments (don't use BIT add > documentation, remove dma_get_attr). > > > Rationale > ========= > The dma-mapping...
2016 Jul 13
0
[PATCH v6 00/46] dma-mapping: Use unsigned long for dma_attrs
...d by Robin Murphy. 3. Applied changes from Bart Van Assche's comment. 4. More tests and builds (using https://www.kernel.org/pub/tools/crosstool/). Changes since v3 ================ 1. Collect some acks. 2. Drop wrong patch 1/45 ("powerpc: dma-mapping: Don't hard-code the value of DMA_ATTR_WEAK_ORDERING"). 3. Minor fix pointed out by Michael Ellerman. Changes since v2 ================ 1. Follow Christoph Hellwig's comments (don't use BIT add documentation, remove dma_get_attr). Rationale ========= The dma-mapping core and the implementations do not change the DMA attribute...
2015 Feb 11
9
[PATCH v2 0/6] nouveau/gk20a: RAM device removal & IOMMU support
Changes since v1: - Add missing else condition in ltc - Remove extra flags that slipped into nouveau_display.c and nv84_fence.c. Original cover letter: Patches 1-3 make the presence of a RAM device optional, and remove GK20A's dummy RAM driver we were using so far. On chips using shared memory, such a device can confuse the driver into moving objects where there is no need to, and can trick