From d31d7cb1460c2942e23bfd0c0f4c8066b60353dc Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 12 Aug 2016 12:39:58 +0100 Subject: [PATCH] drm/i915: Support for creating write combined type vmaps vmaps has a provision for controlling the page protection bits, with which we can use to control the mapping type, e.g. WB, WC, UC or even WT. To allow the caller to choose their mapping type, we add a parameter to i915_gem_object_pin_map - but we still only allow one vmap to be cached per object. If the object is currently not pinned, then we recreate the previous vmap with the new access type, but if it was pinned we report an error. This effectively limits the access via i915_gem_object_pin_map to a single mapping type for the lifetime of the object. Not usually a problem, but something to be aware of when setting up the object's vmap. We will want to vary the access type to enable WC mappings of ringbuffer and context objects on !llc platforms, as well as other objects where we need coherent access to the GPU's pages without going through the GTT v2: Remove the redundant braces around pin count check and fix the marker in documentation (Chris) v3: - Add a new enum for the vmalloc mapping type & pass that as an argument to i915_object_pin_map. (Tvrtko) - Use PAGE_MASK to extract or filter the mapping type info and remove a superfluous BUG_ON.(Tvrtko) v4: - Rename the enums and clean up the pin_map function. (Chris) v5: Drop the VM_NO_GUARD, minor cosmetics. Signed-off-by: Chris Wilson Signed-off-by: Akash Goel Reviewed-by: Tvrtko Ursulin Link: http://patchwork.freedesktop.org/patch/msgid/1471001999-17787-1-git-send-email-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/i915_drv.h | 21 ++++++++- drivers/gpu/drm/i915/i915_gem.c | 58 ++++++++++++++++++++----- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 2 +- drivers/gpu/drm/i915/intel_lrc.c | 8 ++-- drivers/gpu/drm/i915/intel_ringbuffer.c | 2 +- 5 files changed, 73 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7971c76852df..654aabe76efc 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3144,13 +3144,20 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) obj->pages_pin_count--; } +enum i915_map_type { + I915_MAP_WB = 0, + I915_MAP_WC, +}; + /** * i915_gem_object_pin_map - return a contiguous mapping of the entire object * @obj - the object to map into kernel address space + * @type - the type of mapping, used to select pgprot_t * * Calls i915_gem_object_pin_pages() to prevent reaping of the object's * pages and then returns a contiguous mapping of the backing storage into - * the kernel address space. + * the kernel address space. Based on the @type of mapping, the PTE will be + * set to either WriteBack or WriteCombine (via pgprot_t). * * The caller must hold the struct_mutex, and is responsible for calling * i915_gem_object_unpin_map() when the mapping is no longer required. @@ -3158,7 +3165,8 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) * Returns the pointer through which to access the mapped object, or an * ERR_PTR() on error. */ -void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj); +void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj, + enum i915_map_type type); /** * i915_gem_object_unpin_map - releases an earlier mapping @@ -3899,4 +3907,13 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req) return false; } +#define ptr_unpack_bits(ptr, bits) ({ \ + unsigned long __v = (unsigned long)(ptr); \ + (bits) = __v & ~PAGE_MASK; \ + (typeof(ptr))(__v & PAGE_MASK); \ +}) + +#define ptr_pack_bits(ptr, bits) \ + ((typeof(ptr))((unsigned long)(ptr) | (bits))) + #endif diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index e68b4c62be88..75a57e2da86e 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2077,6 +2077,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj) list_del(&obj->global_list); if (obj->mapping) { + /* low bits are ignored by is_vmalloc_addr and kmap_to_page */ if (is_vmalloc_addr(obj->mapping)) vunmap(obj->mapping); else @@ -2253,7 +2254,8 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj) } /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(const struct drm_i915_gem_object *obj) +static void *i915_gem_object_map(const struct drm_i915_gem_object *obj, + enum i915_map_type type) { unsigned long n_pages = obj->base.size >> PAGE_SHIFT; struct sg_table *sgt = obj->pages; @@ -2262,10 +2264,11 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj) struct page *stack_pages[32]; struct page **pages = stack_pages; unsigned long i = 0; + pgprot_t pgprot; void *addr; /* A single page can always be kmapped */ - if (n_pages == 1) + if (n_pages == 1 && type == I915_MAP_WB) return kmap(sg_page(sgt->sgl)); if (n_pages > ARRAY_SIZE(stack_pages)) { @@ -2281,7 +2284,15 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj) /* Check that we have the expected number of pages */ GEM_BUG_ON(i != n_pages); - addr = vmap(pages, n_pages, 0, PAGE_KERNEL); + switch (type) { + case I915_MAP_WB: + pgprot = PAGE_KERNEL; + break; + case I915_MAP_WC: + pgprot = pgprot_writecombine(PAGE_KERNEL_IO); + break; + } + addr = vmap(pages, n_pages, 0, pgprot); if (pages != stack_pages) drm_free_large(pages); @@ -2290,27 +2301,54 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj) } /* get, pin, and map the pages of the object into kernel space */ -void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj) +void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, + enum i915_map_type type) { + enum i915_map_type has_type; + bool pinned; + void *ptr; int ret; lockdep_assert_held(&obj->base.dev->struct_mutex); + GEM_BUG_ON(!i915_gem_object_has_struct_page(obj)); ret = i915_gem_object_get_pages(obj); if (ret) return ERR_PTR(ret); i915_gem_object_pin_pages(obj); + pinned = obj->pages_pin_count > 1; - if (!obj->mapping) { - obj->mapping = i915_gem_object_map(obj); - if (!obj->mapping) { - i915_gem_object_unpin_pages(obj); - return ERR_PTR(-ENOMEM); + ptr = ptr_unpack_bits(obj->mapping, has_type); + if (ptr && has_type != type) { + if (pinned) { + ret = -EBUSY; + goto err; } + + if (is_vmalloc_addr(ptr)) + vunmap(ptr); + else + kunmap(kmap_to_page(ptr)); + + ptr = obj->mapping = NULL; } - return obj->mapping; + if (!ptr) { + ptr = i915_gem_object_map(obj, type); + if (!ptr) { + ret = -ENOMEM; + goto err; + } + + obj->mapping = ptr_pack_bits(ptr, type); + } + + return ptr; + +err: + i915_gem_object_unpin_pages(obj); + return ERR_PTR(ret); } static void diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index c60a8d5bbad0..10265bb35604 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -119,7 +119,7 @@ static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf) if (ret) return ERR_PTR(ret); - addr = i915_gem_object_pin_map(obj); + addr = i915_gem_object_pin_map(obj, I915_MAP_WB); mutex_unlock(&dev->struct_mutex); return addr; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index c7f4b64b16f6..c24ac39d51f6 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -780,7 +780,7 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx, if (ret) goto err; - vaddr = i915_gem_object_pin_map(ce->state); + vaddr = i915_gem_object_pin_map(ce->state, I915_MAP_WB); if (IS_ERR(vaddr)) { ret = PTR_ERR(vaddr); goto unpin_ctx_obj; @@ -1755,7 +1755,7 @@ lrc_setup_hws(struct intel_engine_cs *engine, /* The HWSP is part of the default context object in LRC mode. */ engine->status_page.gfx_addr = i915_gem_obj_ggtt_offset(dctx_obj) + LRC_PPHWSP_PN * PAGE_SIZE; - hws = i915_gem_object_pin_map(dctx_obj); + hws = i915_gem_object_pin_map(dctx_obj, I915_MAP_WB); if (IS_ERR(hws)) return PTR_ERR(hws); engine->status_page.page_addr = hws + LRC_PPHWSP_PN * PAGE_SIZE; @@ -1968,7 +1968,7 @@ populate_lr_context(struct i915_gem_context *ctx, return ret; } - vaddr = i915_gem_object_pin_map(ctx_obj); + vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB); if (IS_ERR(vaddr)) { ret = PTR_ERR(vaddr); DRM_DEBUG_DRIVER("Could not map object pages! (%d)\n", ret); @@ -2189,7 +2189,7 @@ void intel_lr_context_reset(struct drm_i915_private *dev_priv, if (!ctx_obj) continue; - vaddr = i915_gem_object_pin_map(ctx_obj); + vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB); if (WARN_ON(IS_ERR(vaddr))) continue; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index ed19868df9c6..75a9f635c3dc 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1951,7 +1951,7 @@ int intel_ring_pin(struct intel_ring *ring) if (ret) goto err_unpin; - addr = i915_gem_object_pin_map(obj); + addr = i915_gem_object_pin_map(obj, I915_MAP_WB); if (IS_ERR(addr)) { ret = PTR_ERR(addr); goto err_unpin; -- 2.20.1