From patchwork Thu Jun 27 20:56:11 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Matthew Auld X-Patchwork-Id: 11020589 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 26B6A14C0 for ; Thu, 27 Jun 2019 20:57:25 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 1E23428703 for ; Thu, 27 Jun 2019 20:57:25 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 0B0CF2870F; Thu, 27 Jun 2019 20:57:25 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.2 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id A45A928703 for ; Thu, 27 Jun 2019 20:57:24 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 4EEBC6E854; Thu, 27 Jun 2019 20:57:18 +0000 (UTC) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id B4B066E843 for ; Thu, 27 Jun 2019 20:56:53 +0000 (UTC) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga007.fm.intel.com ([10.253.24.52]) by orsmga104.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 27 Jun 2019 13:56:53 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.63,425,1557212400"; d="scan'208";a="164455663" Received: from unknown (HELO mwahaha-bdw.ger.corp.intel.com) ([10.252.4.227]) by fmsmga007.fm.intel.com with ESMTP; 27 Jun 2019 13:56:52 -0700 From: Matthew Auld To: intel-gfx@lists.freedesktop.org Date: Thu, 27 Jun 2019 21:56:11 +0100 Message-Id: <20190627205633.1143-16-matthew.auld@intel.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190627205633.1143-1-matthew.auld@intel.com> References: <20190627205633.1143-1-matthew.auld@intel.com> MIME-Version: 1.0 Subject: [Intel-gfx] [PATCH v2 15/37] drm/i915/lmem: support CPU relocations X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP Add LMEM support for the CPU reloc path. When doing relocations we have both a GPU and CPU reloc path, as well as some debugging options to force a particular path. The GPU reloc path is preferred when the object is not currently idle, otherwise we use the CPU reloc path. Since we can't kmap the object, and the mappable aperture might not be available, add support for mapping it through LMEMBAR. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Abdiel Janulgue Cc: Rodrigo Vivi --- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 69 ++++++++++++++++--- 1 file changed, 58 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 1c5dfbfad71b..b724143e88d2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -251,6 +251,7 @@ struct i915_execbuffer { bool has_llc : 1; bool has_fence : 1; bool needs_unfenced : 1; + bool is_lmem : 1; struct i915_request *rq; u32 *rq_cmd; @@ -963,6 +964,7 @@ static void reloc_cache_init(struct reloc_cache *cache, cache->use_64bit_reloc = HAS_64BIT_RELOC(i915); cache->has_fence = cache->gen < 4; cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment; + cache->is_lmem = false; cache->node.allocated = false; cache->rq = NULL; cache->rq_size = 0; @@ -1020,16 +1022,23 @@ static void reloc_cache_reset(struct reloc_cache *cache) i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm); } else { wmb(); - io_mapping_unmap_atomic((void __iomem *)vaddr); - if (cache->node.allocated) { - struct i915_ggtt *ggtt = cache_to_ggtt(cache); - - ggtt->vm.clear_range(&ggtt->vm, - cache->node.start, - cache->node.size); - drm_mm_remove_node(&cache->node); + + if (cache->is_lmem) { + io_mapping_unmap_atomic((void __iomem *)vaddr); + i915_gem_object_unpin_pages((struct drm_i915_gem_object *)cache->node.mm); + cache->is_lmem = false; } else { - i915_vma_unpin((struct i915_vma *)cache->node.mm); + io_mapping_unmap_atomic((void __iomem *)vaddr); + if (cache->node.allocated) { + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + + ggtt->vm.clear_range(&ggtt->vm, + cache->node.start, + cache->node.size); + drm_mm_remove_node(&cache->node); + } else { + i915_vma_unpin((struct i915_vma *)cache->node.mm); + } } } @@ -1069,6 +1078,40 @@ static void *reloc_kmap(struct drm_i915_gem_object *obj, return vaddr; } +static void *reloc_lmem(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + int err; + + GEM_BUG_ON(use_cpu_reloc(cache, obj)); + + if (cache->vaddr) { + io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr)); + } else { + i915_gem_object_lock(obj); + err = i915_gem_object_set_to_wc_domain(obj, true); + i915_gem_object_unlock(obj); + if (err) + return ERR_PTR(err); + + err = i915_gem_object_pin_pages(obj); + if (err) + return ERR_PTR(err); + + cache->node.mm = (void *)obj; + cache->is_lmem = true; + } + + vaddr = i915_gem_object_lmem_io_map_page(obj, page); + + cache->vaddr = (unsigned long)vaddr; + cache->page = page; + + return vaddr; +} + static void *reloc_iomap(struct drm_i915_gem_object *obj, struct reloc_cache *cache, unsigned long page) @@ -1145,8 +1188,12 @@ static void *reloc_vaddr(struct drm_i915_gem_object *obj, vaddr = unmask_page(cache->vaddr); } else { vaddr = NULL; - if ((cache->vaddr & KMAP) == 0) - vaddr = reloc_iomap(obj, cache, page); + if ((cache->vaddr & KMAP) == 0) { + if (i915_gem_object_is_lmem(obj)) + vaddr = reloc_lmem(obj, cache, page); + else + vaddr = reloc_iomap(obj, cache, page); + } if (!vaddr) vaddr = reloc_kmap(obj, cache, page); }