From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Widawsky Subject: [PATCH 25/62] drm/i915/bdw: Implement PPGTT clear range Date: Sat, 2 Nov 2013 21:07:23 -0700 Message-ID: <1383451680-11173-26-git-send-email-benjamin.widawsky@intel.com> References: <1383451680-11173-1-git-send-email-benjamin.widawsky@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by gabe.freedesktop.org (Postfix) with ESMTP id EB05CEDFBE for ; Sat, 2 Nov 2013 21:08:15 -0700 (PDT) In-Reply-To: <1383451680-11173-1-git-send-email-benjamin.widawsky@intel.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces@lists.freedesktop.org Errors-To: intel-gfx-bounces@lists.freedesktop.org To: Intel GFX Cc: Daniel Vetter , Ben Widawsky , Ben Widawsky List-Id: intel-gfx@lists.freedesktop.org GEN8 PPGTT range clearing is very similar to GEN6 if we assume that our PDEs are all valid, which they should be. v2: Rebase on top of the address space refactoring. v3: Rebase on top of the bool use_scratch addition to the clear_range interface. Reviewed-by: Imre Deak Signed-off-by: Ben Widawsky (v1) Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_gtt.c | 42 ++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index bae71b4..7097d4d 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -59,6 +59,7 @@ typedef gen8_gtt_pte_t gen8_ppgtt_pde_t; #define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb) #define HSW_WT_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x6) +#define GEN8_PTES_PER_PAGE (PAGE_SIZE / sizeof(gen8_gtt_pte_t)) #define GEN8_PDES_PER_PAGE (PAGE_SIZE / sizeof(gen8_ppgtt_pde_t)) #define GEN8_LEGACY_PDPS 4 @@ -194,6 +195,41 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr, return pte; } +static void gen8_ppgtt_clear_range(struct i915_address_space *vm, + unsigned first_entry, + unsigned num_entries, + bool use_scratch) +{ + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + gen8_gtt_pte_t *pt_vaddr, scratch_pte; + unsigned act_pt = first_entry / GEN8_PTES_PER_PAGE; + unsigned first_pte = first_entry % GEN8_PTES_PER_PAGE; + unsigned last_pte, i; + + scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr, + I915_CACHE_LLC, use_scratch); + + while (num_entries) { + struct page *page_table = &ppgtt->gen8_pt_pages[act_pt]; + + last_pte = first_pte + num_entries; + if (last_pte > GEN8_PTES_PER_PAGE) + last_pte = GEN8_PTES_PER_PAGE; + + pt_vaddr = kmap_atomic(page_table); + + for (i = first_pte; i < last_pte; i++) + pt_vaddr[i] = scratch_pte; + + kunmap_atomic(pt_vaddr); + + num_entries -= last_pte - first_pte; + first_pte = 0; + act_pt++; + } +} + static void gen8_ppgtt_cleanup(struct i915_address_space *vm) { struct i915_hw_ppgtt *ppgtt = @@ -259,7 +295,7 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT); ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT); ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE; - ppgtt->base.clear_range = NULL; + ppgtt->base.clear_range = gen8_ppgtt_clear_range; ppgtt->base.insert_entries = NULL; ppgtt->base.cleanup = gen8_ppgtt_cleanup; @@ -312,6 +348,10 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) kunmap_atomic(pd_vaddr); } + ppgtt->base.clear_range(&ppgtt->base, 0, + ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE, + true); + DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n", ppgtt->num_pd_pages, ppgtt->num_pd_pages - max_pdp); DRM_DEBUG_DRIVER("Allocated %d pages for page tables (%lld wasted)\n", -- 1.8.4.2