From e3193f0fbd6d83510ff6879ac248f42a7c0fefe7 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 2 May 2024 18:51:55 +0200 Subject: drm/panthor: Make sure the tiler initial/max chunks are consistent It doesn't make sense to have a maximum number of chunks smaller than the initial number of chunks attached to the context. Fix the uAPI header to reflect the new constraint, and mention the undocumented "initial_chunk_count > 0" constraint while at it. v3: - Add R-b v2: - Fix the check Fixes: 9cca48fa4f89 ("drm/panthor: Add the heap logical block") Signed-off-by: Boris Brezillon Reviewed-by: Liviu Dudau Reviewed-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20240502165158.1458959-3-boris.brezillon@collabora.com --- include/uapi/drm/panthor_drm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index dadb05ab1235..5db80a0682d5 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -895,13 +895,17 @@ struct drm_panthor_tiler_heap_create { /** @vm_id: VM ID the tiler heap should be mapped to */ __u32 vm_id; - /** @initial_chunk_count: Initial number of chunks to allocate. */ + /** @initial_chunk_count: Initial number of chunks to allocate. Must be at least one. */ __u32 initial_chunk_count; /** @chunk_size: Chunk size. Must be a power of two at least 256KB large. */ __u32 chunk_size; - /** @max_chunks: Maximum number of chunks that can be allocated. */ + /** + * @max_chunks: Maximum number of chunks that can be allocated. + * + * Must be at least @initial_chunk_count. + */ __u32 max_chunks; /** -- cgit v1.3 From 69a429905ceccad547e4a532b08f9d32c7f3422a Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 2 May 2024 18:51:56 +0200 Subject: drm/panthor: Relax the constraints on the tiler chunk size The field used to store the chunk size if 12 bits wide, and the encoding is chunk_size = chunk_header.chunk_size << 12, which gives us a theoretical [4k:8M] range. This range is further limited by implementation constraints, and all known implementations seem to impose a [128k:8M] range, so do the same here. We also relax the power-of-two constraint, which doesn't seem to exist on v10. This will allow userspace to fine-tune initial/max tiler memory on memory-constrained devices. v4: - Actually fix the range in the kerneldoc v3: - Add R-bs - Fix valid range in the kerneldoc v2: - Turn the power-of-two constraint into a page-aligned constraint to allow fine-tune of the initial/max heap memory size - Fix the panthor_heap_create() kerneldoc Fixes: 9cca48fa4f89 ("drm/panthor: Add the heap logical block") Signed-off-by: Boris Brezillon Reviewed-by: Liviu Dudau Reviewed-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20240502165158.1458959-4-boris.brezillon@collabora.com --- drivers/gpu/drm/panthor/panthor_heap.c | 8 ++++---- include/uapi/drm/panthor_drm.h | 6 +++++- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/panthor/panthor_heap.c b/drivers/gpu/drm/panthor/panthor_heap.c index 3be86ec383d6..b0fc5b9ee847 100644 --- a/drivers/gpu/drm/panthor/panthor_heap.c +++ b/drivers/gpu/drm/panthor/panthor_heap.c @@ -253,8 +253,8 @@ int panthor_heap_destroy(struct panthor_heap_pool *pool, u32 handle) * @pool: Pool to instantiate the heap context from. * @initial_chunk_count: Number of chunk allocated at initialization time. * Must be at least 1. - * @chunk_size: The size of each chunk. Must be a power of two between 256k - * and 2M. + * @chunk_size: The size of each chunk. Must be page-aligned and lie in the + * [128k:8M] range. * @max_chunks: Maximum number of chunks that can be allocated. * @target_in_flight: Maximum number of in-flight render passes. * @heap_ctx_gpu_va: Pointer holding the GPU address of the allocated heap @@ -284,8 +284,8 @@ int panthor_heap_create(struct panthor_heap_pool *pool, if (initial_chunk_count > max_chunks) return -EINVAL; - if (hweight32(chunk_size) != 1 || - chunk_size < SZ_256K || chunk_size > SZ_2M) + if (!IS_ALIGNED(chunk_size, PAGE_SIZE) || + chunk_size < SZ_128K || chunk_size > SZ_8M) return -EINVAL; down_read(&pool->lock); diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index 5db80a0682d5..b8220d2e698f 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -898,7 +898,11 @@ struct drm_panthor_tiler_heap_create { /** @initial_chunk_count: Initial number of chunks to allocate. Must be at least one. */ __u32 initial_chunk_count; - /** @chunk_size: Chunk size. Must be a power of two at least 256KB large. */ + /** + * @chunk_size: Chunk size. + * + * Must be page-aligned and lie in the [128k:8M] range. + */ __u32 chunk_size; /** -- cgit v1.3 From 591eafcd46e09a2468ecf5cdceea676ac72d84bc Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Thu, 2 May 2024 18:51:58 +0200 Subject: drm/panthor: Document drm_panthor_tiler_heap_destroy::handle validity constraints Make sure the user is aware that drm_panthor_tiler_heap_destroy::handle must be a handle previously returned by DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE. v4: - Add Steve's R-b v3: - New patch Signed-off-by: Boris Brezillon Reviewed-by: Steven Price Reviewed-by: Liviu Dudau Link: https://patchwork.freedesktop.org/patch/msgid/20240502165158.1458959-6-boris.brezillon@collabora.com --- include/uapi/drm/panthor_drm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index b8220d2e698f..aaed8e12ad0b 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -939,7 +939,11 @@ struct drm_panthor_tiler_heap_create { * struct drm_panthor_tiler_heap_destroy - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY */ struct drm_panthor_tiler_heap_destroy { - /** @handle: Handle of the tiler heap to destroy */ + /** + * @handle: Handle of the tiler heap to destroy. + * + * Must be a valid heap handle returned by DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE. + */ __u32 handle; /** @pad: Padding field, MBZ. */ -- cgit v1.3 From 959314c438caf1b62d787f02d54a193efda38880 Mon Sep 17 00:00:00 2001 From: Mohamed Ahmed Date: Thu, 9 May 2024 23:43:52 +0300 Subject: drm/nouveau: use tile_mode and pte_kind for VM_BIND bo allocations Allow PTE kind and tile mode on BO create with VM_BIND, and add a GETPARAM to indicate this change. This is needed to support modifiers in NVK and ensure correctness when dealing with the nouveau GL driver. The userspace modifiers implementation this is for can be found here: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795 Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI") Signed-off-by: Mohamed Ahmed Reviewed-by: Faith Ekstrand Signed-off-by: Danilo Krummrich Link: https://patchwork.freedesktop.org/patch/msgid/20240509204352.7597-1-mohamedahmedegypt2001@gmail.com --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 3 +++ drivers/gpu/drm/nouveau/nouveau_bo.c | 44 ++++++++++++++------------------- include/uapi/drm/nouveau_drm.h | 7 ++++++ 3 files changed, 29 insertions(+), 25 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index f465fe93b1f7..d56909071de6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -272,6 +272,9 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) getparam->value = (u64)ttm_resource_manager_usage(vram_mgr); break; } + case NOUVEAU_GETPARAM_HAS_VMA_TILEMODE: + getparam->value = 1; + break; default: NV_PRINTK(dbg, cli, "unknown parameter %lld\n", getparam->param); return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 1e2d28fd10dc..70fb003a6666 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -241,28 +241,28 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG); - if (!nouveau_cli_uvmm(cli) || internal) { - /* for BO noVM allocs, don't assign kinds */ - if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { - nvbo->kind = (tile_flags & 0x0000ff00) >> 8; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; - } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { - nvbo->kind = (tile_flags & 0x00007f00) >> 8; - nvbo->comp = (tile_flags & 0x00030000) >> 16; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } - } else { - nvbo->zeta = (tile_flags & 0x00000007); + if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { + nvbo->kind = (tile_flags & 0x0000ff00) >> 8; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + + nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; + } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + nvbo->kind = (tile_flags & 0x00007f00) >> 8; + nvbo->comp = (tile_flags & 0x00030000) >> 16; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); } - nvbo->mode = tile_mode; + } else { + nvbo->zeta = (tile_flags & 0x00000007); + } + nvbo->mode = tile_mode; + if (!nouveau_cli_uvmm(cli) || internal) { /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail @@ -304,12 +304,6 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, } nvbo->page = vmm->page[pi].shift; } else { - /* reject other tile flags when in VM mode. */ - if (tile_mode) - return ERR_PTR(-EINVAL); - if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG) - return ERR_PTR(-EINVAL); - /* Determine the desirable target GPU page size for the buffer. */ for (i = 0; i < vmm->page_nr; i++) { /* Because we cannot currently allow VMM maps to fail diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 8ad8d1cd1566..dd87f8f30793 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -68,6 +68,13 @@ extern "C" { */ #define NOUVEAU_GETPARAM_VRAM_USED 19 +/* + * NOUVEAU_GETPARAM_HAS_VMA_TILEMODE + * + * Query whether tile mode and PTE kind are accepted with VM allocs or not. + */ +#define NOUVEAU_GETPARAM_HAS_VMA_TILEMODE 20 + struct drm_nouveau_getparam { __u64 param; __u64 value; -- cgit v1.3