From patchwork Sun Nov 3 04:07:21 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ben Widawsky X-Patchwork-Id: 3132191 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 [198.145.19.201]) by patchwork1.web.kernel.org (Postfix) with ESMTP id B41449F3C4 for ; Sun, 3 Nov 2013 04:10:22 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id B00BF20343 for ; Sun, 3 Nov 2013 04:10:21 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) by mail.kernel.org (Postfix) with ESMTP id 9F4CA202E5 for ; Sun, 3 Nov 2013 04:10:20 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id C2F2AEE727; Sat, 2 Nov 2013 21:08:37 -0700 (PDT) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by gabe.freedesktop.org (Postfix) with ESMTP id 78B26EDE75 for ; Sat, 2 Nov 2013 21:08:14 -0700 (PDT) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga101.jf.intel.com with ESMTP; 02 Nov 2013 21:08:14 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.93,535,1378882800"; d="scan'208";a="402748254" Received: from unknown (HELO lundgren.intel.com) ([10.255.15.29]) by orsmga001.jf.intel.com with ESMTP; 02 Nov 2013 21:08:13 -0700 From: Ben Widawsky To: Intel GFX Date: Sat, 2 Nov 2013 21:07:21 -0700 Message-Id: <1383451680-11173-24-git-send-email-benjamin.widawsky@intel.com> X-Mailer: git-send-email 1.8.4.2 In-Reply-To: <1383451680-11173-1-git-send-email-benjamin.widawsky@intel.com> References: <1383451680-11173-1-git-send-email-benjamin.widawsky@intel.com> Cc: Daniel Vetter , Ben Widawsky , Ben Widawsky Subject: [Intel-gfx] [PATCH 23/62] drm/i915/bdw: PPGTT init & cleanup X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.13 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Sender: intel-gfx-bounces@lists.freedesktop.org Errors-To: intel-gfx-bounces@lists.freedesktop.org X-Spam-Status: No, score=-4.7 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 Aside from the potential size increase of the PPGTT, the primary difference from previous hardware is the Page Directories are no longer carved out of the Global GTT. Note that the PDE allocation is done as a 8MB contiguous allocation, this needs to be eventually fixed (since driver reloading will be a pain otherwise). Also, this will be a no-go for real PPGTT support. v2: Move vtable initialization v3: Resolve conflicts due to patch series reordering. v4: Rebase on top of the address space refactoring of the PPGTT support. Drop Imre's r-b tag for v2, too outdated by now. Signed-off-by: Ben Widawsky (v2) Signed-off-by: Daniel Vetter Reviewed-by: Imre Deak --- drivers/gpu/drm/i915/i915_drv.h | 19 ++++-- drivers/gpu/drm/i915/i915_gem_gtt.c | 123 +++++++++++++++++++++++++++++++++++- 2 files changed, 137 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 83d016c..97b0905 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -572,10 +572,21 @@ struct i915_gtt { struct i915_hw_ppgtt { struct i915_address_space base; unsigned num_pd_entries; - struct page **pt_pages; - uint32_t pd_offset; - dma_addr_t *pt_dma_addr; - + union { + struct page **pt_pages; + struct page *gen8_pt_pages; + }; + struct page *pd_pages; + int num_pd_pages; + int num_pt_pages; + union { + uint32_t pd_offset; + dma_addr_t pd_dma_addr[4]; + }; + union { + dma_addr_t *pt_dma_addr; + dma_addr_t *gen8_pt_dma_addr[4]; + }; int (*enable)(struct drm_device *dev); }; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 02de12d..4a11f51 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -31,6 +31,7 @@ #define GEN6_PPGTT_PD_ENTRIES 512 #define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t)) typedef uint64_t gen8_gtt_pte_t; +typedef gen8_gtt_pte_t gen8_ppgtt_pde_t; /* PPGTT stuff */ #define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) @@ -58,6 +59,9 @@ typedef uint64_t gen8_gtt_pte_t; #define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb) #define HSW_WT_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x6) +#define GEN8_PDES_PER_PAGE (PAGE_SIZE / sizeof(gen8_ppgtt_pde_t)) +#define GEN8_LEGACY_PDPS 4 + #define PPAT_UNCACHED_INDEX (_PAGE_PWT | _PAGE_PCD) #define PPAT_CACHED_PDE_INDEX 0 /* WB LLC */ #define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */ @@ -177,6 +181,123 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr, return pte; } +static void gen8_ppgtt_cleanup(struct i915_address_space *vm) +{ + struct i915_hw_ppgtt *ppgtt = + container_of(vm, struct i915_hw_ppgtt, base); + int i, j; + + for (i = 0; i < ppgtt->num_pd_pages ; i++) { + if (ppgtt->pd_dma_addr[i]) { + pci_unmap_page(ppgtt->base.dev->pdev, + ppgtt->pd_dma_addr[i], + PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); + + for (j = 0; j < GEN8_PDES_PER_PAGE; j++) { + dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j]; + if (addr) + pci_unmap_page(ppgtt->base.dev->pdev, + addr, + PAGE_SIZE, + PCI_DMA_BIDIRECTIONAL); + + } + } + kfree(ppgtt->gen8_pt_dma_addr[i]); + } + + __free_pages(ppgtt->gen8_pt_pages, get_order(ppgtt->num_pt_pages)); + __free_pages(ppgtt->pd_pages, get_order(ppgtt->num_pd_pages)); +} + +/** + * GEN8 legacy ppgtt programming is accomplished through 4 PDP registers with a + * net effect resembling a 2-level page table in normal x86 terms. Each PDP + * represents 1GB of memory + * 4 * 512 * 512 * 4096 = 4GB legacy 32b address space. + * + * TODO: Do something with the size parameter + **/ +static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) +{ + struct page *pt_pages; + int i, j, ret = -ENOMEM; + const int max_pdp = DIV_ROUND_UP(size, 1 << 30); + const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp; + + if (size % (1<<30)) + DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size); + + /* FIXME: split allocation into smaller pieces. For now we only ever do + * this once, but with full PPGTT, the multiple contiguous allocations + * will be bad. + */ + ppgtt->pd_pages = alloc_pages(GFP_KERNEL, get_order(max_pdp << PAGE_SHIFT)); + if (!ppgtt->pd_pages) + return -ENOMEM; + + pt_pages = alloc_pages(GFP_KERNEL, get_order(num_pt_pages << PAGE_SHIFT)); + if (!pt_pages) { + __free_pages(ppgtt->pd_pages, get_order(max_pdp << PAGE_SHIFT)); + return -ENOMEM; + } + + ppgtt->gen8_pt_pages = pt_pages; + 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.insert_entries = NULL; + ppgtt->base.cleanup = gen8_ppgtt_cleanup; + + BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS); + + /* + * - Create a mapping for the page directories. + * - For each page directory: + * allocate space for page table mappings. + * map each page table + */ + for (i = 0; i < max_pdp; i++) { + dma_addr_t temp; + temp = pci_map_page(ppgtt->base.dev->pdev, + &ppgtt->pd_pages[i], 0, + PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); + if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp)) + goto err_out; + + ppgtt->pd_dma_addr[i] = temp; + + ppgtt->gen8_pt_dma_addr[i] = kmalloc(sizeof(dma_addr_t) * GEN8_PDES_PER_PAGE, GFP_KERNEL); + if (!ppgtt->gen8_pt_dma_addr[i]) + goto err_out; + + for (j = 0; j < GEN8_PDES_PER_PAGE; j++) { + struct page *p = &pt_pages[i * GEN8_PDES_PER_PAGE + j]; + temp = pci_map_page(ppgtt->base.dev->pdev, + p, 0, PAGE_SIZE, + PCI_DMA_BIDIRECTIONAL); + + if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp)) + goto err_out; + + ppgtt->gen8_pt_dma_addr[i][j] = temp; + } + } + + 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", + ppgtt->num_pt_pages, + (ppgtt->num_pt_pages - num_pt_pages) + + size % (1<<30)); + return -ENOSYS; /* Not ready yet */ + +err_out: + ppgtt->base.cleanup(&ppgtt->base); + return ret; +} + static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt) { struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private; @@ -430,7 +551,7 @@ static int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) if (INTEL_INFO(dev)->gen < 8) ret = gen6_ppgtt_init(ppgtt); else if (IS_GEN8(dev)) - ret = -ENXIO; + ret = gen8_ppgtt_init(ppgtt, dev_priv->gtt.base.total); else BUG();