From patchwork Mon May 9 09:33:32 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Dave Gordon X-Patchwork-Id: 9044091 Return-Path: X-Original-To: patchwork-intel-gfx@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork2.web.kernel.org (Postfix) with ESMTP id EA24BBF29F for ; Mon, 9 May 2016 09:33:52 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 04D2220145 for ; Mon, 9 May 2016 09:33:51 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) by mail.kernel.org (Postfix) with ESMTP id 0E2F020142 for ; Mon, 9 May 2016 09:33:50 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 350FE6E09E; Mon, 9 May 2016 09:33:49 +0000 (UTC) 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 E8E5F6E09E for ; Mon, 9 May 2016 09:33:45 +0000 (UTC) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by orsmga103.jf.intel.com with ESMTP; 09 May 2016 02:33:46 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.24,600,1455004800"; d="scan'208";a="975611803" Received: from dsgordon-linux2.isw.intel.com ([10.102.226.88]) by fmsmga002.fm.intel.com with ESMTP; 09 May 2016 02:33:44 -0700 From: Dave Gordon To: intel-gfx@lists.freedesktop.org Date: Mon, 9 May 2016 10:33:32 +0100 Message-Id: <1462786413-3899-2-git-send-email-david.s.gordon@intel.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1462786413-3899-1-git-send-email-david.s.gordon@intel.com> References: <1462786413-3899-1-git-send-email-david.s.gordon@intel.com> Organization: Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJ Subject: [Intel-gfx] [PATCH 2/3] drm/i915: refactor i915_gem_object_pin_map() 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=-6.3 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 The recently-added i915_gem_object_pin_map() can be further optimised for "small" objects. To facilitate this, and simplify the error paths before adding the new code, this patch pulls out the "mapping" part of the operation (involving local allocations which must be undone before return) into its own subfunction. The next patch will then insert the new optimisation into the middle of the now-separated subfunction. This reorganisation will probably not affect the generated code, as the compiler will most likely inline it anyway, but it makes the logical structure a bit clearer and easier to modify. v2: Restructure loop-over-pages & error check (Chris Wilson) v3: Use new nicer SGL page-range iterator (Dave Gordon) Add page count to debug messages (Chris Wilson) Convert WARN_ON() to GEM_BUG_ON() Signed-off-by: Dave Gordon Cc: Tvrtko Ursulin Cc: Chris Wilson --- drivers/gpu/drm/i915/i915_gem.c | 59 ++++++++++++++++++++++++++--------------- 1 file changed, 38 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 03b2ed3..f459702 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2393,6 +2393,43 @@ static void i915_gem_object_free_mmap_offset(struct drm_i915_gem_object *obj) return 0; } +/* The 'mapping' part of i915_gem_object_pin_map() below */ +static void *i915_gem_object_map(const struct drm_i915_gem_object *obj) +{ + unsigned long n_pages = obj->base.size >> PAGE_SHIFT; + struct sg_table *sgt = obj->pages; + struct sg_page_iter sg_iter; + struct page **pages; + unsigned long i = 0; + void *addr = NULL; + + /* A single page can always be kmapped */ + if (n_pages == 1) + return kmap(sg_page(sgt->sgl)); + + pages = drm_malloc_gfp(n_pages, sizeof(*pages), GFP_TEMPORARY); + if (pages == NULL) { + DRM_DEBUG_DRIVER("Failed to get space for %lu pointers\n", + n_pages); + return NULL; + } + + for_each_sgt_page_range(&sg_iter, sgt, 0, n_pages) + pages[i++] = sg_page_iter_page(&sg_iter); + + /* Check that we have the expected number of pages */ + GEM_BUG_ON(i != n_pages); + + addr = vmap(pages, n_pages, 0, PAGE_KERNEL); + if (addr == NULL) + DRM_DEBUG_DRIVER("Failed to vmap %lu pages\n", n_pages); + + drm_free_large(pages); + + return addr; +} + +/* get, pin, and map the pages of the object into kernel space */ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj) { int ret; @@ -2406,27 +2443,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj) i915_gem_object_pin_pages(obj); if (obj->mapping == NULL) { - struct page **pages; - - pages = NULL; - if (obj->base.size == PAGE_SIZE) - obj->mapping = kmap(sg_page(obj->pages->sgl)); - else - pages = drm_malloc_gfp(obj->base.size >> PAGE_SHIFT, - sizeof(*pages), - GFP_TEMPORARY); - if (pages != NULL) { - struct sg_page_iter sg_iter; - int n; - - n = 0; - for_each_sg_page(obj->pages->sgl, &sg_iter, - obj->pages->nents, 0) - pages[n++] = sg_page_iter_page(&sg_iter); - - obj->mapping = vmap(pages, n, 0, PAGE_KERNEL); - drm_free_large(pages); - } + obj->mapping = i915_gem_object_map(obj); if (obj->mapping == NULL) { i915_gem_object_unpin_pages(obj); return ERR_PTR(-ENOMEM);