From 134fdc1a704f0042465ea993c33540aaec7e1d2e Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Sat, 3 Oct 2015 17:34:25 +1000 Subject: [PATCH] drm/nouveau/core/mm: replace region list with next pointer We never have any need for a double-linked list here, and as there's generally a large number of these objects, replace it with a single- linked list in order to save some memory. Signed-off-by: Ben Skeggs --- .../gpu/drm/nouveau/include/nvkm/core/mm.h | 8 ++++++- .../gpu/drm/nouveau/include/nvkm/subdev/fb.h | 2 +- drivers/gpu/drm/nouveau/nouveau_bo.c | 2 +- drivers/gpu/drm/nouveau/nvkm/core/mm.c | 2 ++ .../gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c | 10 ++++---- .../gpu/drm/nouveau/nvkm/subdev/fb/ramnv50.c | 23 ++++++++----------- .../drm/nouveau/nvkm/subdev/instmem/gk20a.c | 17 ++++---------- .../gpu/drm/nouveau/nvkm/subdev/mmu/base.c | 7 +++--- 8 files changed, 34 insertions(+), 37 deletions(-) diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/mm.h b/drivers/gpu/drm/nouveau/include/nvkm/core/mm.h index d92fd41e4056..7bd4897a8a2a 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/mm.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/mm.h @@ -5,7 +5,7 @@ struct nvkm_mm_node { struct list_head nl_entry; struct list_head fl_entry; - struct list_head rl_entry; + struct nvkm_mm_node *next; #define NVKM_MM_HEAP_ANY 0x00 u8 heap; @@ -38,4 +38,10 @@ int nvkm_mm_tail(struct nvkm_mm *, u8 heap, u8 type, u32 size_max, u32 size_min, u32 align, struct nvkm_mm_node **); void nvkm_mm_free(struct nvkm_mm *, struct nvkm_mm_node **); void nvkm_mm_dump(struct nvkm_mm *, const char *); + +static inline bool +nvkm_mm_contiguous(struct nvkm_mm_node *node) +{ + return !node->next; +} #endif diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h index 794e432578b2..0b26a4c860ec 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h @@ -29,7 +29,7 @@ struct nvkm_mem { u8 page_shift; struct nvkm_mm_node *tag; - struct list_head regions; + struct nvkm_mm_node *mem; dma_addr_t *pages; u32 memtype; u64 offset; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 8a528ebe30f3..ef8a649eac65 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -321,7 +321,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t memtype, bool contig) if (nvbo->tile_flags & NOUVEAU_GEM_TILE_NONCONTIG) { if (bo->mem.mem_type == TTM_PL_VRAM) { struct nvkm_mem *mem = bo->mem.mm_node; - if (!list_is_singular(&mem->regions)) + if (!nvkm_mm_contiguous(mem->mem)) evict = true; } nvbo->tile_flags &= ~NOUVEAU_GEM_TILE_NONCONTIG; diff --git a/drivers/gpu/drm/nouveau/nvkm/core/mm.c b/drivers/gpu/drm/nouveau/nvkm/core/mm.c index 09a1eee8fd33..fd19d652a7ab 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/mm.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/mm.c @@ -147,6 +147,7 @@ nvkm_mm_head(struct nvkm_mm *mm, u8 heap, u8 type, u32 size_max, u32 size_min, if (!this) return -ENOMEM; + this->next = NULL; this->type = type; list_del(&this->fl_entry); *pnode = this; @@ -225,6 +226,7 @@ nvkm_mm_tail(struct nvkm_mm *mm, u8 heap, u8 type, u32 size_max, u32 size_min, if (!this) return -ENOMEM; + this->next = NULL; this->type = type; list_del(&this->fl_entry); *pnode = this; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c index 093223d1df4f..6758da93a3a1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c @@ -445,7 +445,7 @@ gf100_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, { struct nvkm_ltc *ltc = ram->fb->subdev.device->ltc; struct nvkm_mm *mm = &ram->vram; - struct nvkm_mm_node *r; + struct nvkm_mm_node **node, *r; struct nvkm_mem *mem; int type = (memtype & 0x0ff); int back = (memtype & 0x800); @@ -462,7 +462,6 @@ gf100_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, if (!mem) return -ENOMEM; - INIT_LIST_HEAD(&mem->regions); mem->size = size; mutex_lock(&ram->fb->subdev.mutex); @@ -478,6 +477,7 @@ gf100_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, } mem->memtype = type; + node = &mem->mem; do { if (back) ret = nvkm_mm_tail(mm, 0, 1, size, ncmin, align, &r); @@ -489,13 +489,13 @@ gf100_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, return ret; } - list_add_tail(&r->rl_entry, &mem->regions); + *node = r; + node = &r->next; size -= r->length; } while (size); mutex_unlock(&ram->fb->subdev.mutex); - r = list_first_entry(&mem->regions, struct nvkm_mm_node, rl_entry); - mem->offset = (u64)r->offset << NVKM_RAM_MM_SHIFT; + mem->offset = (u64)mem->mem->offset << NVKM_RAM_MM_SHIFT; *pmem = mem; return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv50.c index 87bde8ff2d6b..6549b0588309 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv50.c @@ -496,15 +496,12 @@ nv50_ram_tidy(struct nvkm_ram *base) void __nv50_ram_put(struct nvkm_ram *ram, struct nvkm_mem *mem) { - struct nvkm_mm_node *this; - - while (!list_empty(&mem->regions)) { - this = list_first_entry(&mem->regions, typeof(*this), rl_entry); - - list_del(&this->rl_entry); - nvkm_mm_free(&ram->vram, &this); + struct nvkm_mm_node *next = mem->mem; + struct nvkm_mm_node *node; + while ((node = next)) { + next = node->next; + nvkm_mm_free(&ram->vram, &node); } - nvkm_mm_free(&ram->tags, &mem->tag); } @@ -530,7 +527,7 @@ nv50_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, { struct nvkm_mm *heap = &ram->vram; struct nvkm_mm *tags = &ram->tags; - struct nvkm_mm_node *r; + struct nvkm_mm_node **node, *r; struct nvkm_mem *mem; int comp = (memtype & 0x300) >> 8; int type = (memtype & 0x07f); @@ -559,11 +556,11 @@ nv50_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, comp = 0; } - INIT_LIST_HEAD(&mem->regions); mem->memtype = (comp << 7) | type; mem->size = max; type = nv50_fb_memtype[type]; + node = &mem->mem; do { if (back) ret = nvkm_mm_tail(heap, 0, type, max, min, align, &r); @@ -575,13 +572,13 @@ nv50_ram_get(struct nvkm_ram *ram, u64 size, u32 align, u32 ncmin, return ret; } - list_add_tail(&r->rl_entry, &mem->regions); + *node = r; + node = &r->next; max -= r->length; } while (max); mutex_unlock(&ram->fb->subdev.mutex); - r = list_first_entry(&mem->regions, struct nvkm_mm_node, rl_entry); - mem->offset = (u64)r->offset << NVKM_RAM_MM_SHIFT; + mem->offset = (u64)mem->mem->offset << NVKM_RAM_MM_SHIFT; *pmem = mem; return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c index a6a7fa0d7679..a94238374a39 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/gk20a.c @@ -305,11 +305,11 @@ gk20a_instobj_dtor_iommu(struct nvkm_memory *memory) struct gk20a_instobj_iommu *node = gk20a_instobj_iommu(memory); struct gk20a_instmem *imem = node->base.imem; struct device *dev = imem->base.subdev.device->dev; - struct nvkm_mm_node *r; + struct nvkm_mm_node *r = node->base.mem.mem; unsigned long flags; int i; - if (unlikely(list_empty(&node->base.mem.regions))) + if (unlikely(!r)) goto out; spin_lock_irqsave(&imem->lock, flags); @@ -320,9 +320,6 @@ gk20a_instobj_dtor_iommu(struct nvkm_memory *memory) spin_unlock_irqrestore(&imem->lock, flags); - r = list_first_entry(&node->base.mem.regions, struct nvkm_mm_node, - rl_entry); - /* clear IOMMU bit to unmap pages */ r->offset &= ~BIT(imem->iommu_bit - imem->iommu_pgshift); @@ -404,10 +401,7 @@ gk20a_instobj_ctor_dma(struct gk20a_instmem *imem, u32 npages, u32 align, node->r.length = (npages << PAGE_SHIFT) >> 12; node->base.mem.offset = node->handle; - - INIT_LIST_HEAD(&node->base.mem.regions); - list_add_tail(&node->r.rl_entry, &node->base.mem.regions); - + node->base.mem.mem = &node->r; return 0; } @@ -484,10 +478,7 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, r->offset |= BIT(imem->iommu_bit - imem->iommu_pgshift); node->base.mem.offset = ((u64)r->offset) << imem->iommu_pgshift; - - INIT_LIST_HEAD(&node->base.mem.regions); - list_add_tail(&r->rl_entry, &node->base.mem.regions); - + node->base.mem.mem = r; return 0; release_area: diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c index 5df9669ea39c..d06ad2c372bf 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c @@ -31,7 +31,7 @@ nvkm_vm_map_at(struct nvkm_vma *vma, u64 delta, struct nvkm_mem *node) { struct nvkm_vm *vm = vma->vm; struct nvkm_mmu *mmu = vm->mmu; - struct nvkm_mm_node *r; + struct nvkm_mm_node *r = node->mem; int big = vma->node->type != mmu->func->spg_shift; u32 offset = vma->node->offset + (delta >> 12); u32 bits = vma->node->type - 12; @@ -41,7 +41,7 @@ nvkm_vm_map_at(struct nvkm_vma *vma, u64 delta, struct nvkm_mem *node) u32 end, len; delta = 0; - list_for_each_entry(r, &node->regions, rl_entry) { + while (r) { u64 phys = (u64)r->offset << 12; u32 num = r->length >> bits; @@ -65,7 +65,8 @@ nvkm_vm_map_at(struct nvkm_vma *vma, u64 delta, struct nvkm_mem *node) delta += (u64)len << vma->node->type; } - } + r = r->next; + }; mmu->func->flush(vm); }