From patchwork Tue Jul 7 15:14:48 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Michel Thierry X-Patchwork-Id: 6734141 Return-Path: X-Original-To: patchwork-intel-gfx@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id B04D99F2F0 for ; Tue, 7 Jul 2015 15:15:13 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 83C59206F8 for ; Tue, 7 Jul 2015 15:15:12 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) by mail.kernel.org (Postfix) with ESMTP id 7D0C820732 for ; Tue, 7 Jul 2015 15:15:10 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 10D386EA3E; Tue, 7 Jul 2015 08:15:10 -0700 (PDT) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by gabe.freedesktop.org (Postfix) with ESMTP id 51AD66EA3C for ; Tue, 7 Jul 2015 08:15:08 -0700 (PDT) Received: from orsmga003.jf.intel.com ([10.7.209.27]) by orsmga103.jf.intel.com with ESMTP; 07 Jul 2015 08:15:08 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.15,424,1432623600"; d="scan'208";a="601641124" Received: from michelth-linux2.isw.intel.com ([10.102.226.189]) by orsmga003.jf.intel.com with ESMTP; 07 Jul 2015 08:15:07 -0700 From: Michel Thierry To: intel-gfx@lists.freedesktop.org Date: Tue, 7 Jul 2015 16:14:48 +0100 Message-Id: <1436282103-5854-4-git-send-email-michel.thierry@intel.com> X-Mailer: git-send-email 2.4.5 In-Reply-To: <1436282103-5854-1-git-send-email-michel.thierry@intel.com> References: <1436282103-5854-1-git-send-email-michel.thierry@intel.com> Cc: akash.goel@intel.com Subject: [Intel-gfx] [PATCH v4 03/18] drm/i915/gen8: Add PML4 structure X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.18 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Spam-Status: No, score=-5.0 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_MED, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Introduces the Page Map Level 4 (PML4), ie. the new top level structure of the page tables. To facilitate testing, 48b mode will be available on Broadwell and GEN9+, when i915.enable_ppgtt = 3. Cc: Akash Goel Signed-off-by: Michel Thierry --- drivers/gpu/drm/i915/i915_drv.h | 7 ++++++- drivers/gpu/drm/i915/i915_gem_gtt.c | 40 ++++++++++++++++++++++++------------- drivers/gpu/drm/i915/i915_gem_gtt.h | 35 ++++++++++++++++++++++++-------- 3 files changed, 59 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 464b28d..de3a5d1 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2497,7 +2497,12 @@ struct drm_i915_cmd_table { #define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6) #define HAS_LOGICAL_RING_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 8) #define USES_PPGTT(dev) (i915.enable_ppgtt) -#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt == 2) +#define USES_FULL_PPGTT(dev) (i915.enable_ppgtt >= 2) +#ifdef CONFIG_X86_64 +# define USES_FULL_48BIT_PPGTT(dev) (i915.enable_ppgtt == 3) +#else +# define USES_FULL_48BIT_PPGTT(dev) false +#endif #define HAS_OVERLAY(dev) (INTEL_INFO(dev)->has_overlay) #define OVERLAY_NEEDS_PHYSICAL(dev) (INTEL_INFO(dev)->overlay_needs_physical) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 4e1501a..fa66dfa 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -104,9 +104,13 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt) { bool has_aliasing_ppgtt; bool has_full_ppgtt; + bool has_full_64bit_ppgtt; has_aliasing_ppgtt = INTEL_INFO(dev)->gen >= 6; has_full_ppgtt = INTEL_INFO(dev)->gen >= 7; + has_full_64bit_ppgtt = IS_ENABLED(CONFIG_X86_64) && + (IS_BROADWELL(dev) || + INTEL_INFO(dev)->gen >= 9) && false; /* FIXME: 64b */ if (intel_vgpu_active(dev)) has_full_ppgtt = false; /* emulation is too hard */ @@ -125,6 +129,9 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt) if (enable_ppgtt == 2 && has_full_ppgtt) return 2; + if (enable_ppgtt == 3 && has_full_64bit_ppgtt) + return 3; + #ifdef CONFIG_INTEL_IOMMU /* Disable ppgtt on SNB if VT-d is on. */ if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) { @@ -557,6 +564,8 @@ static void free_pdp(struct drm_device *dev, struct i915_page_directory_pointer *pdp) { __pdp_fini(pdp); + if (USES_FULL_48BIT_PPGTT(dev)) + kfree(pdp); } /* Broadwell Page Directory Pointer Descriptors */ @@ -671,9 +680,6 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, pt_vaddr = NULL; for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) { - if (WARN_ON(pdpe >= GEN8_LEGACY_PDPES)) - break; - if (pt_vaddr == NULL) { struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe]; struct i915_page_table *pt = pd->page_table[pde]; @@ -1066,14 +1072,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) return ret; ppgtt->base.start = 0; - ppgtt->base.total = 1ULL << 32; - if (IS_ENABLED(CONFIG_X86_32)) - /* While we have a proliferation of size_t variables - * we cannot represent the full ppgtt size on 32bit, - * so limit it to the same size as the GGTT (currently - * 2GiB). - */ - ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total; ppgtt->base.cleanup = gen8_ppgtt_cleanup; ppgtt->base.allocate_va_range = gen8_alloc_va_range; ppgtt->base.insert_entries = gen8_ppgtt_insert_entries; @@ -1083,10 +1081,24 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->switch_mm = gen8_mm_switch; - ret = __pdp_init(false, &ppgtt->pdp); + if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) { + ret = __pdp_init(false, &ppgtt->pdp); - if (ret) - goto free_scratch; + if (ret) + goto free_scratch; + + ppgtt->base.total = 1ULL << 32; + if (IS_ENABLED(CONFIG_X86_32)) + /* While we have a proliferation of size_t variables + * we cannot represent the full ppgtt size on 32bit, + * so limit it to the same size as the GGTT (currently + * 2GiB). + */ + ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total; + } else { + ppgtt->base.total = 1ULL << 48; + return -EPERM; /* Not yet implemented */ + } return 0; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index f5928db..6fa824e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -88,9 +88,17 @@ typedef uint64_t gen8_pde_t; * PDPE | PDE | PTE | offset * The difference as compared to normal x86 3 level page table is the PDPEs are * programmed via register. + * + * GEN8 48b legacy style address is defined as a 4 level page table: + * 47:39 | 38:30 | 29:21 | 20:12 | 11:0 + * PML4E | PDPE | PDE | PTE | offset */ +#define GEN8_PML4ES_PER_PML4 512 +#define GEN8_PML4E_SHIFT 39 #define GEN8_PDPE_SHIFT 30 -#define GEN8_PDPE_MASK 0x3 +/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page + * tables */ +#define GEN8_PDPE_MASK 0x1ff #define GEN8_PDE_SHIFT 21 #define GEN8_PDE_MASK 0x1ff #define GEN8_PTE_SHIFT 12 @@ -98,8 +106,8 @@ typedef uint64_t gen8_pde_t; #define GEN8_LEGACY_PDPES 4 #define GEN8_PTES I915_PTES(sizeof(gen8_pte_t)) -/* FIXME: Next patch will use dev */ -#define I915_PDPES_PER_PDP(dev) GEN8_LEGACY_PDPES +#define I915_PDPES_PER_PDP(dev) (USES_FULL_48BIT_PPGTT(dev) ?\ + GEN8_PML4ES_PER_PML4 : GEN8_LEGACY_PDPES) #define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD) #define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */ @@ -250,6 +258,13 @@ struct i915_page_directory_pointer { struct i915_page_directory **page_directory; }; +struct i915_pml4 { + struct i915_page_dma base; + + DECLARE_BITMAP(used_pml4es, GEN8_PML4ES_PER_PML4); + struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4]; +}; + struct i915_address_space { struct drm_mm mm; struct drm_device *dev; @@ -345,8 +360,9 @@ struct i915_hw_ppgtt { struct drm_mm_node node; unsigned long pd_dirty_rings; union { - struct i915_page_directory_pointer pdp; - struct i915_page_directory pd; + struct i915_pml4 pml4; /* GEN8+ & 48b PPGTT */ + struct i915_page_directory_pointer pdp; /* GEN8+ */ + struct i915_page_directory pd; /* GEN6-7 */ }; struct drm_i915_file_private *file_priv; @@ -440,14 +456,17 @@ static inline uint32_t gen6_pde_index(uint32_t addr) temp = min(temp, length), \ start += temp, length -= temp) -#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \ - for (iter = gen8_pdpe_index(start); \ - pd = (pdp)->page_directory[iter], length > 0 && iter < GEN8_LEGACY_PDPES; \ +#define gen8_for_each_pdpe_e(pd, pdp, start, length, temp, iter, b) \ + for (iter = gen8_pdpe_index(start); \ + pd = (pdp)->page_directory[iter], length > 0 && (iter < b); \ iter++, \ temp = ALIGN(start+1, 1 << GEN8_PDPE_SHIFT) - start, \ temp = min(temp, length), \ start += temp, length -= temp) +#define gen8_for_each_pdpe(pd, pdp, start, length, temp, iter) \ + gen8_for_each_pdpe_e(pd, pdp, start, length, temp, iter, I915_PDPES_PER_PDP(dev)) + static inline uint32_t gen8_pte_index(uint64_t address) { return i915_pte_index(address, GEN8_PDE_SHIFT);