From: Thomas Hellström <[email protected]> Drivers that use the GPU SVM core to DMA-map system memory for GPU access may want to keep track of how many pages they have mapped, for example to expose statistics or to detect leaks. Doing this accounting in the driver around drm_gpusvm_get_pages() / drm_gpusvm_unmap_pages() is error prone: the number, order and kind of the dma_addr[] entries can change between map and unmap (migration, partial unmaps, the iova vs non-iova paths), which makes symmetric accounting hard to get right.
Add an optional @dma_map_account callback to struct drm_gpusvm_ops and invoke it once per &drm_pagemap_addr entry at the exact points where the entry is DMA-mapped (sign == +1) in drm_gpusvm_get_pages() and unmapped (sign == -1) in __drm_gpusvm_unmap_pages(). Since the map error path and every unmap/free path funnel through __drm_gpusvm_unmap_pages() for the entries that were actually mapped, the accounting is symmetric by construction. The callback receives the full &drm_pagemap_addr so the driver can use the order and the proto field to distinguish system memory mappings from device interconnect mappings. The callback must also be usable by the core drm_gpusvm_pages-only API (mm == NULL), as used e.g. for userptr-style mappings. Relax drm_gpusvm_init() to allow such users to pass a restricted @ops that only implements the page-level hooks; the full-SVM hooks (@invalidate) and the chunk configuration must still be unset in that mode. Assisted-by: LLM Signed-off-by: Thomas Hellström <[email protected]> Signed-off-by: Matthew Brost <[email protected]> Reviewed-by: Niranjana Vishwanathapura <[email protected]> --- drivers/gpu/drm/drm_gpusvm.c | 40 ++++++++++++++++++++++++++++-------- include/drm/drm_gpusvm.h | 19 +++++++++++++++++ 2 files changed, 50 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 03dbe304e4b8..5ef9d7233491 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -503,8 +503,15 @@ int drm_gpusvm_init(struct drm_gpusvm *gpusvm, return -EINVAL; mmgrab(mm); } else { - /* No full SVM mode, only core drm_gpusvm_pages API. */ - if (ops || num_chunks || mm_range || notifier_size) + /* + * No full SVM mode, only core drm_gpusvm_pages API. A + * restricted @ops that only implements the page-level hooks + * (e.g. @dma_map_account) is allowed; the full-SVM hooks must + * not be set. + */ + if (num_chunks || mm_range || notifier_size) + return -EINVAL; + if (ops && ops->invalidate) return -EINVAL; } @@ -1240,9 +1247,12 @@ static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, struct drm_gpusvm_pages_flags flags = { .__flags = svm_pages->flags.__flags, }; + bool contiguous; const struct drm_pagemap_addr *addrs = - drm_gpusvm_pages_first_dma(svm_pages, NULL); + drm_gpusvm_pages_first_dma(svm_pages, &contiguous); bool use_iova = dma_use_iova(&svm_pages->state); + bool needs_account = gpusvm->ops && + gpusvm->ops->dma_map_account; /* * IOVA is reserved for the whole range but only the linked @@ -1260,14 +1270,18 @@ static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, /* * With IOVA and no device page the unlink above tore every - * entry down, and that is also when the range may be folded - * to one entry, which must not be walked per entry. dpagemap - * is set before the first device_map(), so it is also right - * on the error path, where the flags are not published yet. + * entry down, but the per-entry walk is still needed when the + * driver accounts the mappings. A folded (inline) mapping has + * a single entry describing the whole range, so it must be + * re-read for every iteration instead of indexed by @j. + * dpagemap is set before the first device_map(), so it is also + * right on the error path, where the flags are not published + * yet. */ for (i = 0, j = 0; - (!use_iova || dpagemap) && i < npages; j++) { - const struct drm_pagemap_addr *addr = &addrs[j]; + (!use_iova || dpagemap || needs_account) && i < npages; j++) { + const struct drm_pagemap_addr *addr = + contiguous ? &addrs[0] : &addrs[j]; if (addr->proto == DRM_INTERCONNECT_SYSTEM) { /* @@ -1283,6 +1297,10 @@ static void __drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm, } else if (dpagemap && dpagemap->ops->device_unmap) dpagemap->ops->device_unmap(dpagemap, dev, addr); + + if (needs_account) + gpusvm->ops->dma_map_account(gpusvm, addr, -1); + i += 1 << addr->order; } @@ -1705,6 +1723,10 @@ static int drm_gpusvm_dma_map_pages(struct drm_gpusvm *gpusvm, (addr, DRM_INTERCONNECT_SYSTEM, order, dma_dir); } + if (gpusvm->ops && gpusvm->ops->dma_map_account) + gpusvm->ops->dma_map_account(gpusvm, + &svm_pages->dma_addr[j], + 1); i += 1 << order; num_dma_mapped = i; flags.has_dma_mapping = true; diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h index 4d31c6bba745..637c19f7169f 100644 --- a/include/drm/drm_gpusvm.h +++ b/include/drm/drm_gpusvm.h @@ -75,6 +75,25 @@ struct drm_gpusvm_ops { void (*invalidate)(struct drm_gpusvm *gpusvm, struct drm_gpusvm_notifier *notifier, const struct mmu_notifier_range *mmu_range); + + /** + * @dma_map_account: Account a DMA-mapping change (optional) + * @gpusvm: Pointer to the GPU SVM + * @addr: The address descriptor of the chunk being (un)mapped + * @sign: +1 when @addr has just been DMA-mapped, -1 when it is being + * unmapped + * + * Called once per &drm_pagemap_addr entry, when the entry is + * DMA-mapped by drm_gpusvm_get_pages() (@sign == +1) and when it is + * unmapped (@sign == -1), so the driver can keep symmetric accounting + * of the pages it has mapped for GPU access. The @addr->proto field + * can be used to distinguish system-memory mappings from device + * interconnect mappings. May be provided in both full SVM mode and the + * core drm_gpusvm_pages-only mode. + */ + void (*dma_map_account)(struct drm_gpusvm *gpusvm, + const struct drm_pagemap_addr *addr, + int sign); }; /** -- 2.34.1
