This is the third and final part of my series to start supporting P2P with DMA-buf.
The implementation is straight forward, apart from a helper to aid constructing scatterlists without having struct pages we only add a new flag indicating that an DMA-buf importer can handle peer2peer.
The exporter can then check if P2P is general possible using the pci_p2pdma_distance_many() function and if necessary can also clear the flag.
The rest is an example how to implementing the necessary functionality into the amdgpu driver to setup scatterlists pointing to device memory.
Please review and comment, Christian.
This can be used by drivers to setup P2P DMA between device memory which is not backed by struct pages.
The drivers of the involved devices are responsible for setting up and tearing down DMA addresses as necessary using dma_map_resource().
The page pointer is set to NULL and only the DMA address, length and offset values are valid.
Signed-off-by: Christian König christian.koenig@amd.com --- include/linux/scatterlist.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+)
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 6eec50fb36c8..28a477bf0bdf 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -145,6 +145,29 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf, sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf)); }
+/** + * sg_set_dma_addr - Set sg entry to point at specified dma address + * @sg: SG entry + * @address: DMA address to set + * @len: Length of data + * @offset: Offset into page + * + * Description: + * Use this function to set an sg entry to point to device resources mapped + * using dma_map_resource(). The page pointer is set to NULL and only the DMA + * address, length and offset values are valid. + * + **/ +static inline void sg_set_dma_addr(struct scatterlist *sg, dma_addr_t address, + unsigned int len, unsigned int offset) +{ + sg_set_page(sg, NULL, len, offset); + sg->dma_address = address; +#ifdef CONFIG_NEED_SG_DMA_LENGTH + sg->dma_length = len; +#endif +} + /* * Loop over each sg element, following the pointer to a new list if necessary */
Add a peer2peer flag noting that the importer can deal with device resources which are not backed by pages.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-buf.c | 2 ++ include/linux/dma-buf.h | 10 ++++++++++ 2 files changed, 12 insertions(+)
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index f4ace9af2191..f9220928ec90 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -689,6 +689,8 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
attach->dev = dev; attach->dmabuf = dmabuf; + if (importer_ops) + attach->peer2peer = importer_ops->allow_peer2peer; attach->importer_ops = importer_ops; attach->importer_priv = importer_priv;
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 1ade486fc2bb..82e0a4a64601 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -334,6 +334,14 @@ struct dma_buf { * Attachment operations implemented by the importer. */ struct dma_buf_attach_ops { + /** + * @allow_peer2peer: + * + * If this is set to true the importer must be able to handle peer + * resources without struct pages. + */ + bool allow_peer2peer; + /** * @move_notify * @@ -362,6 +370,7 @@ struct dma_buf_attach_ops { * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf. * @sgt: cached mapping. * @dir: direction of cached mapping. + * @peer2peer: true if the importer can handle peer resources without pages. * @priv: exporter specific attachment data. * @importer_ops: importer operations for this attachment, if provided * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. @@ -382,6 +391,7 @@ struct dma_buf_attachment { struct list_head node; struct sg_table *sgt; enum dma_data_direction dir; + bool peer2peer; const struct dma_buf_attach_ops *importer_ops; void *importer_priv; void *priv;
Importing should work out of the box.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index ffeb20f11c07..aef12ee2f1e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -514,6 +514,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) }
static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { + .allow_peer2peer = true, .move_notify = amdgpu_dma_buf_move_notify };
Check if we can do peer2peer on the PCIe bus.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index aef12ee2f1e3..bbf67800c8a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -38,6 +38,7 @@ #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> +#include <linux/pci-p2pdma.h>
/** * amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation @@ -179,6 +180,9 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r;
+ if (pci_p2pdma_distance_many(adev->pdev, &attach->dev, 1, true) < 0) + attach->peer2peer = false; + if (attach->dev->driver == adev->dev->driver) return 0;
On Wed, Mar 11, 2020 at 02:51:56PM +0100, Christian König wrote:
Check if we can do peer2peer on the PCIe bus.
Signed-off-by: Christian König christian.koenig@amd.com drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index aef12ee2f1e3..bbf67800c8a6 100644 +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -38,6 +38,7 @@ #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> +#include <linux/pci-p2pdma.h>
/**
- amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
@@ -179,6 +180,9 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r;
- if (pci_p2pdma_distance_many(adev->pdev, &attach->dev, 1, true) < 0)
attach->peer2peer = false;
Are there other related patches than this series?
p2p dma mapping needs to be done in common code, in p2pdma.c - ie this open coding is missing the bus_offset stuff, at least.
I really do not want to see drivers open code this stuff.
We already have a p2pdma API for handling the struct page case, so I suggest adding some new p2pdma API to handle this for non-struct page cases.
ie some thing like:
int 'p2pdma map bar'( struct pci_device *source, unsigned int source_bar_number, struct pci_device *dest, physaddr&len *array_of_offsets & length pairs into source bar, struct scatterlist *output_sgl)
Jason
Am 11.03.20 um 15:04 schrieb Jason Gunthorpe:
On Wed, Mar 11, 2020 at 02:51:56PM +0100, Christian König wrote:
Check if we can do peer2peer on the PCIe bus.
Signed-off-by: Christian König christian.koenig@amd.com drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index aef12ee2f1e3..bbf67800c8a6 100644 +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -38,6 +38,7 @@ #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> +#include <linux/pci-p2pdma.h>
/**
- amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
@@ -179,6 +180,9 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r;
- if (pci_p2pdma_distance_many(adev->pdev, &attach->dev, 1, true) < 0)
attach->peer2peer = false;Are there other related patches than this series?
p2p dma mapping needs to be done in common code, in p2pdma.c - ie this open coding is missing the bus_offset stuff, at least.
Yeah, I'm aware of this. But I couldn't find a better way for now.
I really do not want to see drivers open code this stuff.
We already have a p2pdma API for handling the struct page case, so I suggest adding some new p2pdma API to handle this for non-struct page cases.
ie some thing like:
int 'p2pdma map bar'( struct pci_device *source, unsigned int source_bar_number, struct pci_device *dest, physaddr&len *array_of_offsets & length pairs into source bar, struct scatterlist *output_sgl)
Well that's exactly what I have to avoid since I don't have the array of offsets around and want to avoid constructing it.
Similar problem for dma_map_resource(). My example does this on demand, but essentially we also have use cases where this is done only once.
Ideally we would have some function to create an sgl based on some arbitrary collection of offsets and length inside a BAR.
Regards, Christian.
Jason
On Wed, Mar 11, 2020 at 03:33:01PM +0100, Christian König wrote:
Am 11.03.20 um 15:04 schrieb Jason Gunthorpe:
On Wed, Mar 11, 2020 at 02:51:56PM +0100, Christian König wrote:
Check if we can do peer2peer on the PCIe bus.
Signed-off-by: Christian König christian.koenig@amd.com drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index aef12ee2f1e3..bbf67800c8a6 100644 +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -38,6 +38,7 @@ #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> +#include <linux/pci-p2pdma.h> /**
- amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
@@ -179,6 +180,9 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r;
- if (pci_p2pdma_distance_many(adev->pdev, &attach->dev, 1, true) < 0)
attach->peer2peer = false;Are there other related patches than this series?
p2p dma mapping needs to be done in common code, in p2pdma.c - ie this open coding is missing the bus_offset stuff, at least.
Yeah, I'm aware of this. But I couldn't find a better way for now.
Well, it isn't optional :)
I really do not want to see drivers open code this stuff.
We already have a p2pdma API for handling the struct page case, so I suggest adding some new p2pdma API to handle this for non-struct page cases.
ie some thing like:
int 'p2pdma map bar'( struct pci_device *source, unsigned int source_bar_number, struct pci_device *dest, physaddr&len *array_of_offsets & length pairs into source bar, struct scatterlist *output_sgl)
Well that's exactly what I have to avoid since I don't have the array of offsets around and want to avoid constructing it.
Maybe it doesn't need an array of offsets - just a single offset and callers can iterate the API?
Similar problem for dma_map_resource(). My example does this on demand, but essentially we also have use cases where this is done only once.
I'm not sure if this is portable. Does any IOMMU HW need to know P2P is happening to setup successfully? We currently support such a narrow scope of HW for P2P..
Ideally we would have some function to create an sgl based on some arbitrary collection of offsets and length inside a BAR.
Isn't that what I just proposed above ?
Jason
Am 11.03.20 um 15:38 schrieb Jason Gunthorpe:
On Wed, Mar 11, 2020 at 03:33:01PM +0100, Christian König wrote:
Am 11.03.20 um 15:04 schrieb Jason Gunthorpe:
On Wed, Mar 11, 2020 at 02:51:56PM +0100, Christian König wrote:
Check if we can do peer2peer on the PCIe bus.
Signed-off-by: Christian König christian.koenig@amd.com drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index aef12ee2f1e3..bbf67800c8a6 100644 +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -38,6 +38,7 @@ #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> +#include <linux/pci-p2pdma.h> /** * amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation @@ -179,6 +180,9 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); int r;
- if (pci_p2pdma_distance_many(adev->pdev, &attach->dev, 1, true) < 0)
attach->peer2peer = false;Are there other related patches than this series?
p2p dma mapping needs to be done in common code, in p2pdma.c - ie this open coding is missing the bus_offset stuff, at least.
Yeah, I'm aware of this. But I couldn't find a better way for now.
Well, it isn't optional :)
I really do not want to see drivers open code this stuff.
We already have a p2pdma API for handling the struct page case, so I suggest adding some new p2pdma API to handle this for non-struct page cases.
ie some thing like:
int 'p2pdma map bar'( struct pci_device *source, unsigned int source_bar_number, struct pci_device *dest, physaddr&len *array_of_offsets & length pairs into source bar, struct scatterlist *output_sgl)
Well that's exactly what I have to avoid since I don't have the array of offsets around and want to avoid constructing it.
Maybe it doesn't need an array of offsets - just a single offset and callers can iterate the API?
Yes, that would of course work as well.
But I was assuming that p2pdma_map_bar() needs some state between those calls.
Similar problem for dma_map_resource(). My example does this on demand, but essentially we also have use cases where this is done only once.
I'm not sure if this is portable. Does any IOMMU HW need to know P2P is happening to setup successfully? We currently support such a narrow scope of HW for P2P..
On the AMD hardware I'm testing this calling dma_map_resource() already seems to work with IOMMU enabled. (Well at least it seemed so 6month ago when I last tested this).
Ideally we would have some function to create an sgl based on some arbitrary collection of offsets and length inside a BAR.
Isn't that what I just proposed above ?
Yes, just didn't thought that this would easily possible. I will double check the p2pdma code again.
Thanks, Christian.
Jason
On Wed, Mar 11, 2020 at 03:43:03PM +0100, Christian König wrote:
int 'p2pdma map bar'( struct pci_device *source, unsigned int source_bar_number, struct pci_device *dest, physaddr&len *array_of_offsets & length pairs into source bar, struct scatterlist *output_sgl)
Well that's exactly what I have to avoid since I don't have the array of offsets around and want to avoid constructing it.
Maybe it doesn't need an array of offsets - just a single offset and callers can iterate the API?
Yes, that would of course work as well.
But I was assuming that p2pdma_map_bar() needs some state between those calls.
It might be able to run faster if some state is held. We've had APIs before where the caller can provide a cache for expensive state for APIs. Maybe that would be an appropriate pattern here?
IIRC the distance calculation is the expensive bit, that would be easy enough to cache.
Jason
We should be able to do this now after checking all the prerequisites.
v2: fix entrie count in the sgt
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 56 ++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 12 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 97 ++++++++++++++++++++ 3 files changed, 151 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index bbf67800c8a6..43d8ed7dbd00 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -276,14 +276,21 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, struct dma_buf *dma_buf = attach->dmabuf; struct drm_gem_object *obj = dma_buf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct sg_table *sgt; long r;
if (!bo->pin_count) { - /* move buffer into GTT */ + /* move buffer into GTT or VRAM */ struct ttm_operation_ctx ctx = { false, false }; + unsigned domains = AMDGPU_GEM_DOMAIN_GTT;
- amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT); + if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM && + attach->peer2peer) { + bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + domains |= AMDGPU_GEM_DOMAIN_VRAM; + } + amdgpu_bo_placement_from_domain(bo, domains); r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); if (r) return ERR_PTR(r); @@ -293,20 +300,34 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, return ERR_PTR(-EBUSY); }
- sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages); - if (IS_ERR(sgt)) - return sgt; - - if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC)) - goto error_free; + switch (bo->tbo.mem.mem_type) { + case TTM_PL_TT: + sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, + bo->tbo.num_pages); + if (IS_ERR(sgt)) + return sgt; + + if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir, + DMA_ATTR_SKIP_CPU_SYNC)) + goto error_free; + break; + + case TTM_PL_VRAM: + r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, attach->dev, + dir, &sgt); + if (r) + return ERR_PTR(r); + break; + default: + return ERR_PTR(-EINVAL); + }
return sgt;
error_free: sg_free_table(sgt); kfree(sgt); - return ERR_PTR(-ENOMEM); + return ERR_PTR(-EBUSY); }
/** @@ -322,9 +343,18 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach, struct sg_table *sgt, enum dma_data_direction dir) { - dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); - sg_free_table(sgt); - kfree(sgt); + struct dma_buf *dma_buf = attach->dmabuf; + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + + if (sgt->sgl->page_link) { + dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); + sg_free_table(sgt); + kfree(sgt); + } else { + amdgpu_vram_mgr_free_sgt(adev, attach->dev, dir, sgt); + } }
/** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 7551f3729445..a99d813b23a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -24,8 +24,9 @@ #ifndef __AMDGPU_TTM_H__ #define __AMDGPU_TTM_H__
-#include "amdgpu.h" +#include <linux/dma-direction.h> #include <drm/gpu_scheduler.h> +#include "amdgpu.h"
#define AMDGPU_PL_GDS (TTM_PL_PRIV + 0) #define AMDGPU_PL_GWS (TTM_PL_PRIV + 1) @@ -74,6 +75,15 @@ uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man); int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo); +int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, + struct ttm_mem_reg *mem, + struct device *dev, + enum dma_data_direction dir, + struct sg_table **sgt); +void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev, + struct device *dev, + enum dma_data_direction dir, + struct sg_table *sgt); uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man); uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 82a3299e53c0..c6e7f00c5b21 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -22,6 +22,7 @@ * Authors: Christian König */
+#include <linux/dma-mapping.h> #include "amdgpu.h" #include "amdgpu_vm.h" #include "amdgpu_atomfirmware.h" @@ -458,6 +459,102 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man, mem->mm_node = NULL; }
+/** + * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table + * + * @adev: amdgpu device pointer + * @mem: TTM memory object + * @dev: the other device + * @dir: dma direction + * @sgt: resulting sg table + * + * Allocate and fill a sg table from a VRAM allocation. + */ +int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, + struct ttm_mem_reg *mem, + struct device *dev, + enum dma_data_direction dir, + struct sg_table **sgt) +{ + struct drm_mm_node *node; + struct scatterlist *sg; + int num_entries = 0; + unsigned int pages; + int i, r; + + *sgt = kmalloc(sizeof(*sg), GFP_KERNEL); + if (!*sgt) + return -ENOMEM; + + for (pages = mem->num_pages, node = mem->mm_node; + pages; pages -= node->size, ++node) + ++num_entries; + + r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL); + if (r) + goto error_free; + + for_each_sg((*sgt)->sgl, sg, num_entries, i) + sg->length = 0; + + node = mem->mm_node; + for_each_sg((*sgt)->sgl, sg, num_entries, i) { + phys_addr_t phys = (node->start << PAGE_SHIFT) + + adev->gmc.aper_base; + size_t size = node->size << PAGE_SHIFT; + dma_addr_t addr; + + ++node; + addr = dma_map_resource(dev, phys, size, dir, + DMA_ATTR_SKIP_CPU_SYNC); + r = dma_mapping_error(dev, addr); + if (r) + goto error_unmap; + + sg_set_dma_addr(sg, addr, size, 0); + } + return 0; + +error_unmap: + for_each_sg((*sgt)->sgl, sg, num_entries, i) { + if (!sg->length) + continue; + + dma_unmap_resource(dev, sg->dma_address, + sg->length, dir, + DMA_ATTR_SKIP_CPU_SYNC); + } + sg_free_table(*sgt); + +error_free: + kfree(*sgt); + return r; +} + +/** + * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table + * + * @adev: amdgpu device pointer + * @sgt: sg table to free + * + * Free a previously allocate sg table. + */ +void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev, + struct device *dev, + enum dma_data_direction dir, + struct sg_table *sgt) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgt->sgl, sg, sgt->nents, i) + dma_unmap_resource(dev, sg->dma_address, + sg->length, dir, + DMA_ATTR_SKIP_CPU_SYNC); + sg_free_table(sgt); + kfree(sgt); +} + /** * amdgpu_vram_mgr_usage - how many bytes are used in this domain *
On Wed, Mar 11, 2020 at 02:51:57PM +0100, Christian König wrote:
+/**
- amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
- @adev: amdgpu device pointer
- @mem: TTM memory object
- @dev: the other device
- @dir: dma direction
- @sgt: resulting sg table
- Allocate and fill a sg table from a VRAM allocation.
- */
+int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
struct ttm_mem_reg *mem,struct device *dev,enum dma_data_direction dir,struct sg_table **sgt)
single ** pointer with an int return is odd, use ERR_PTR?
+{
- struct drm_mm_node *node;
- struct scatterlist *sg;
- int num_entries = 0;
- unsigned int pages;
- int i, r;
- *sgt = kmalloc(sizeof(*sg), GFP_KERNEL);
- if (!*sgt)
return -ENOMEM;- for (pages = mem->num_pages, node = mem->mm_node;
pages; pages -= node->size, ++node)++num_entries;- r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL);
- if (r)
goto error_free;- for_each_sg((*sgt)->sgl, sg, num_entries, i)
sg->length = 0;- node = mem->mm_node;
- for_each_sg((*sgt)->sgl, sg, num_entries, i) {
phys_addr_t phys = (node->start << PAGE_SHIFT) +adev->gmc.aper_base;size_t size = node->size << PAGE_SHIFT;dma_addr_t addr;++node;addr = dma_map_resource(dev, phys, size, dir,DMA_ATTR_SKIP_CPU_SYNC);r = dma_mapping_error(dev, addr);if (r)goto error_unmap;sg_set_dma_addr(sg, addr, size, 0);
Is it possible that phys will need to have contiguous pages joined here, or has 'node' already ensured contiguous pages?
Jason
On Wed, Mar 11, 2020 at 02:51:57PM +0100, Christian König wrote:
+/**
- amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
- @adev: amdgpu device pointer
- @sgt: sg table to free
Wrong kdoc in many ways
- Free a previously allocate sg table.
- */
+void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
struct device *dev,enum dma_data_direction dir,struct sg_table *sgt)+{
Jason
On Wed, Mar 11, 2020 at 9:52 AM Christian König ckoenig.leichtzumerken@gmail.com wrote:
We should be able to do this now after checking all the prerequisites.
v2: fix entrie count in the sgt
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 56 ++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 12 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 97 ++++++++++++++++++++ 3 files changed, 151 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index bbf67800c8a6..43d8ed7dbd00 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -276,14 +276,21 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, struct dma_buf *dma_buf = attach->dmabuf; struct drm_gem_object *obj = dma_buf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct sg_table *sgt; long r; if (!bo->pin_count) {
/* move buffer into GTT */
/* move buffer into GTT or VRAM */ struct ttm_operation_ctx ctx = { false, false };unsigned domains = AMDGPU_GEM_DOMAIN_GTT;
amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&attach->peer2peer) {bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;domains |= AMDGPU_GEM_DOMAIN_VRAM;}amdgpu_bo_placement_from_domain(bo, domains); r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); if (r) return ERR_PTR(r);@@ -293,20 +300,34 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, return ERR_PTR(-EBUSY); }
sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages);if (IS_ERR(sgt))return sgt;if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,DMA_ATTR_SKIP_CPU_SYNC))goto error_free;
switch (bo->tbo.mem.mem_type) {case TTM_PL_TT:sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages,bo->tbo.num_pages);if (IS_ERR(sgt))return sgt;if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,DMA_ATTR_SKIP_CPU_SYNC))goto error_free;break;case TTM_PL_VRAM:r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, attach->dev,dir, &sgt);if (r)return ERR_PTR(r);break;default:return ERR_PTR(-EINVAL);} return sgt;error_free: sg_free_table(sgt); kfree(sgt);
return ERR_PTR(-ENOMEM);
return ERR_PTR(-EBUSY);}
/** @@ -322,9 +343,18 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach, struct sg_table *sgt, enum dma_data_direction dir) {
dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);sg_free_table(sgt);kfree(sgt);
struct dma_buf *dma_buf = attach->dmabuf;struct drm_gem_object *obj = dma_buf->priv;struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);if (sgt->sgl->page_link) {dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);sg_free_table(sgt);kfree(sgt);} else {amdgpu_vram_mgr_free_sgt(adev, attach->dev, dir, sgt);}}
/** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 7551f3729445..a99d813b23a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -24,8 +24,9 @@ #ifndef __AMDGPU_TTM_H__ #define __AMDGPU_TTM_H__
-#include "amdgpu.h" +#include <linux/dma-direction.h> #include <drm/gpu_scheduler.h> +#include "amdgpu.h"
#define AMDGPU_PL_GDS (TTM_PL_PRIV + 0) #define AMDGPU_PL_GWS (TTM_PL_PRIV + 1) @@ -74,6 +75,15 @@ uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man); int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo); +int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
struct ttm_mem_reg *mem,struct device *dev,enum dma_data_direction dir,struct sg_table **sgt);+void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
struct device *dev,enum dma_data_direction dir,struct sg_table *sgt);uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man); uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 82a3299e53c0..c6e7f00c5b21 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -22,6 +22,7 @@
- Authors: Christian König
*/
+#include <linux/dma-mapping.h> #include "amdgpu.h" #include "amdgpu_vm.h" #include "amdgpu_atomfirmware.h" @@ -458,6 +459,102 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man, mem->mm_node = NULL; }
+/**
- amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
- @adev: amdgpu device pointer
- @mem: TTM memory object
- @dev: the other device
- @dir: dma direction
- @sgt: resulting sg table
- Allocate and fill a sg table from a VRAM allocation.
- */
+int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
struct ttm_mem_reg *mem,struct device *dev,enum dma_data_direction dir,struct sg_table **sgt)+{
struct drm_mm_node *node;struct scatterlist *sg;int num_entries = 0;unsigned int pages;int i, r;*sgt = kmalloc(sizeof(*sg), GFP_KERNEL);if (!*sgt)return -ENOMEM;for (pages = mem->num_pages, node = mem->mm_node;pages; pages -= node->size, ++node)++num_entries;r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL);if (r)goto error_free;for_each_sg((*sgt)->sgl, sg, num_entries, i)sg->length = 0;node = mem->mm_node;for_each_sg((*sgt)->sgl, sg, num_entries, i) {phys_addr_t phys = (node->start << PAGE_SHIFT) +adev->gmc.aper_base;size_t size = node->size << PAGE_SHIFT;dma_addr_t addr;++node;addr = dma_map_resource(dev, phys, size, dir,DMA_ATTR_SKIP_CPU_SYNC);r = dma_mapping_error(dev, addr);if (r)goto error_unmap;sg_set_dma_addr(sg, addr, size, 0);}return 0;+error_unmap:
for_each_sg((*sgt)->sgl, sg, num_entries, i) {if (!sg->length)continue;dma_unmap_resource(dev, sg->dma_address,sg->length, dir,DMA_ATTR_SKIP_CPU_SYNC);}sg_free_table(*sgt);+error_free:
kfree(*sgt);return r;+}
+/**
- amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
This should be: amdgpu_vram_mgr_free_sgt - unmap and free an sg table
- @adev: amdgpu device pointer
- @sgt: sg table to free
- Free a previously allocate sg table.
- */
+void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
struct device *dev,enum dma_data_direction dir,struct sg_table *sgt)+{
struct scatterlist *sg;int i;for_each_sg(sgt->sgl, sg, sgt->nents, i)dma_unmap_resource(dev, sg->dma_address,sg->length, dir,DMA_ATTR_SKIP_CPU_SYNC);sg_free_table(sgt);kfree(sgt);+}
/**
- amdgpu_vram_mgr_usage - how many bytes are used in this domain
-- 2.17.1
dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Note if a buffer was imported using peer2peer.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 4277125a79ee..e42608115c99 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/pagemap.h> #include <linux/pci.h> +#include <linux/dma-buf.h>
#include <drm/amdgpu_drm.h> #include <drm/drm_debugfs.h> @@ -854,7 +855,8 @@ static int amdgpu_debugfs_gem_bo_info(int id, void *ptr, void *data) attachment = READ_ONCE(bo->tbo.base.import_attach);
if (attachment) - seq_printf(m, " imported from %p", dma_buf); + seq_printf(m, " imported from %p%s", dma_buf, + attachment->peer2peer ? " P2P" : ""); else if (dma_buf) seq_printf(m, " exported as %p", dma_buf);
dri-devel@lists.freedesktop.org
-
Alex Deucher -
Christian König -
Christian König -
Jason Gunthorpe