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 };

We should be able to do this now after checking all the prerequisites.

v2: fix entrie count in the sgt v3: manually construct the sg

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 | 99 ++++++++++++++++++++ 3 files changed, 153 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 bd05bbb4878d..6b22dc41ef13 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..128a667ed8fa 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 +459,104 @@ 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_page(sg, NULL, size, 0); + sg_dma_address(sg) = addr; + sg_dma_len(sg) = size; + } + 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 Mon, Mar 30, 2020 at 03:55:31PM +0200, Christian König wrote:

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

On the series:

Acked-by: Daniel Vetter daniel.vetter@ffwll.ch

---

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 ccc9eda1bc28..570c923023e6 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -690,6 +690,8 @@ 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;

-- 2.17.1

On Mon, Mar 30, 2020 at 03:55:31PM +0200, Christian König wrote:

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 ccc9eda1bc28..570c923023e6 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -690,6 +690,8 @@ 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;
  

So an idea that crossed my mind to validate this, since we need quite some bad amounts of bad luck if someone accidentally introduces and access to struct_page in sg lists in some slowpath.

On map_sg, if ->peer2peer is set, we could mangle the struct_page pointers, e.g. swap high bits for low bits (so that NULL stays NULL). On unmap_sg we obviously need to undo that, in case the exporter needs those pointers for its own book-keeping for some reason. I was also pondering just setting them all to NULL, but that might break some exporters. With the pointer mangling trick (especially if we flip high for low bits on 64 where this should result in invalid addresses in almost all cases) we should be able to catch buggy p2p importers quite quickly.

Thoughts? Maybe add as a follow-up patch for testing? -Daniel

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;

-- 2.17.1