The dma-map IOVA alloc, link, and sync APIs perform significantly better than dma-map / dma-unmap, as they avoid costly IOMMU synchronizations. This difference is especially noticeable when mapping a 2MB region in 4KB pages.
Use the IOVA alloc, link, and sync APIs for GPU SVM, which create DMA mappings between the CPU and GPU. Signed-off-by: Matthew Brost <[email protected]> --- drivers/gpu/drm/drm_gpusvm.c | 63 +++++++++++++++++++++++++----------- include/drm/drm_gpusvm.h | 3 ++ 2 files changed, 47 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 585d913d3d19..eff764445108 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1139,19 +1139,26 @@ static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, struct drm_gpusvm_pages_flags flags = { .__flags = svm_pages->flags.__flags, }; + struct dma_iova_state __state = {}; - for (i = 0, j = 0; i < npages; j++) { - struct drm_pagemap_addr *addr = &svm_pages->dma_addr[j]; - - if (addr->proto == DRM_INTERCONNECT_SYSTEM) - dma_unmap_page(dev, - addr->addr, - PAGE_SIZE << addr->order, - addr->dir); - else if (dpagemap && dpagemap->ops->device_unmap) - dpagemap->ops->device_unmap(dpagemap, - dev, *addr); - i += 1 << addr->order; + if (dma_use_iova(&svm_pages->state)) { + dma_iova_destroy(dev, &svm_pages->state, + npages * PAGE_SIZE, + svm_pages->dma_addr[0].dir, 0); + } else { + for (i = 0, j = 0; i < npages; j++) { + struct drm_pagemap_addr *addr = &svm_pages->dma_addr[j]; + + if (addr->proto == DRM_INTERCONNECT_SYSTEM) + dma_unmap_page(dev, + addr->addr, + PAGE_SIZE << addr->order, + addr->dir); + else if (dpagemap && dpagemap->ops->device_unmap) + dpagemap->ops->device_unmap(dpagemap, + dev, *addr); + i += 1 << addr->order; + } } /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ @@ -1161,6 +1168,7 @@ static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, drm_pagemap_put(svm_pages->dpagemap); svm_pages->dpagemap = NULL; + svm_pages->state = __state; } } @@ -1408,6 +1416,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, struct drm_gpusvm_pages_flags flags; enum dma_data_direction dma_dir = ctx->read_only ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL; + struct dma_iova_state *state = &svm_pages->state; retry: if (time_after(jiffies, timeout)) @@ -1539,13 +1548,29 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, goto err_unmap; } - addr = dma_map_page(gpusvm->drm->dev, - page, 0, - PAGE_SIZE << order, - dma_dir); - if (dma_mapping_error(gpusvm->drm->dev, addr)) { - err = -EFAULT; - goto err_unmap; + if (!i) + dma_iova_try_alloc(gpusvm->drm->dev, state, 0, + npages * PAGE_SIZE); + + if (dma_use_iova(state)) { + err = dma_iova_link(gpusvm->drm->dev, state, + page_to_phys(page), + i * PAGE_SIZE, + PAGE_SIZE << order, + dma_dir, 0); + if (err) + goto err_unmap; + + addr = state->addr + i * PAGE_SIZE; + } else { + addr = dma_map_page(gpusvm->drm->dev, + page, 0, + PAGE_SIZE << order, + dma_dir); + if (dma_mapping_error(gpusvm->drm->dev, addr)) { + err = -EFAULT; + goto err_unmap; + } } svm_pages->dma_addr[j] = drm_pagemap_addr_encode diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h index 2578ac92a8d4..6772d8a92788 100644 --- a/include/drm/drm_gpusvm.h +++ b/include/drm/drm_gpusvm.h @@ -6,6 +6,7 @@ #ifndef __DRM_GPUSVM_H__ #define __DRM_GPUSVM_H__ +#include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/interval_tree.h> #include <linux/mmu_notifier.h> @@ -136,6 +137,7 @@ struct drm_gpusvm_pages_flags { * @dma_addr: Device address array * @dpagemap: The struct drm_pagemap of the device pages we're dma-mapping. * Note this is assuming only one drm_pagemap per range is allowed. + * @state: DMA IOVA state for mapping. * @notifier_seq: Notifier sequence number of the range's pages * @flags: Flags for range * @flags.migrate_devmem: Flag indicating whether the range can be migrated to device memory @@ -147,6 +149,7 @@ struct drm_gpusvm_pages_flags { struct drm_gpusvm_pages { struct drm_pagemap_addr *dma_addr; struct drm_pagemap *dpagemap; + struct dma_iova_state state; unsigned long notifier_seq; struct drm_gpusvm_pages_flags flags; }; -- 2.34.1
