From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-12.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 61D7FC4727E for ; Thu, 24 Sep 2020 14:00:05 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 1B71E20B1F for ; Thu, 24 Sep 2020 14:00:05 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=infradead.org header.i=@infradead.org header.b="eVcrp51t" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728273AbgIXOAD (ORCPT ); Thu, 24 Sep 2020 10:00:03 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:53306 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728149AbgIXN7W (ORCPT ); Thu, 24 Sep 2020 09:59:22 -0400 Received: from casper.infradead.org (casper.infradead.org [IPv6:2001:8b0:10b:1236::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CD6C8C0613CE for ; Thu, 24 Sep 2020 06:59:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Transfer-Encoding:MIME-Version: References:In-Reply-To:Message-Id:Date:Subject:Cc:To:From:Sender:Reply-To: Content-Type:Content-ID:Content-Description; bh=IV+5G3JY9ITNxQsZ2scDnXefMHEiNcoILBZrmnx9LqY=; b=eVcrp51tU/1VUllGrBsmEMDRJF Oa8azxOrxIve8eOcqGMESUBdvV21tVe29JUePa2/QKfrksNjNoY0FfxtHipVka+VDzXV3Uw/t65vM d6xc6edaYPqHIJ55twKgv9IlDVwlthwgOUk/RFi81tsUINjkVakHbycDUpuEwygIrEIo7pDe0ccii BtcNrj1WyblQ9O8jDl6upG+Yc/NdkQyp0nmN2rlNDc9IlalpWpA6HJRZVAhwEeWGnW7nMJJC7ORS1 UWlN5Gsoq/7E9Zc8bBSM2fMLcHu+0tEWg9MeP0JNDBhoQEO4RFxzpykzkdwG3Qw4FpKuo95UeSOH2 6Xb1GYog==; Received: from p4fdb0c34.dip0.t-ipconnect.de ([79.219.12.52] helo=localhost) by casper.infradead.org with esmtpsa (Exim 4.92.3 #3 (Red Hat Linux)) id 1kLRm4-0003wW-K4; Thu, 24 Sep 2020 13:59:04 +0000 From: Christoph Hellwig To: Andrew Morton Cc: Peter Zijlstra , Boris Ostrovsky , Juergen Gross , Stefano Stabellini , Jani Nikula , Joonas Lahtinen , Tvrtko Ursulin , Chris Wilson , Matthew Auld , Rodrigo Vivi , Minchan Kim , Matthew Wilcox , Nitin Gupta , x86@kernel.org, xen-devel@lists.xenproject.org, linux-kernel@vger.kernel.org, intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org, linux-mm@kvack.org Subject: [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map Date: Thu, 24 Sep 2020 15:58:50 +0200 Message-Id: <20200924135853.875294-9-hch@lst.de> X-Mailer: git-send-email 2.28.0 In-Reply-To: <20200924135853.875294-1-hch@lst.de> References: <20200924135853.875294-1-hch@lst.de> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org i915_gem_object_map implements fairly low-level vmap functionality in a driver. Split it into two helpers, one for remapping kernel memory which can use vmap, and one for I/O memory that uses vmap_pfn. The only practical difference is that alloc_vm_area prefeaults the vmalloc area PTEs, which doesn't seem to be required here for the kernel memory case (and could be added to vmap using a flag if actually required). Signed-off-by: Christoph Hellwig --- drivers/gpu/drm/i915/Kconfig | 1 + drivers/gpu/drm/i915/gem/i915_gem_pages.c | 126 ++++++++++------------ 2 files changed, 59 insertions(+), 68 deletions(-) diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 9afa5c4a6bf006..1e1cb245fca778 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -25,6 +25,7 @@ config DRM_I915 select CRC32 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER + select VMAP_PFN help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 6550c0bc824ea2..b519417667eb4b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -232,34 +232,21 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj) return err; } -static inline pte_t iomap_pte(resource_size_t base, - dma_addr_t offset, - pgprot_t prot) -{ - return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot)); -} - /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(struct drm_i915_gem_object *obj, - enum i915_map_type type) +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj, + enum i915_map_type type) { - unsigned long n_pte = obj->base.size >> PAGE_SHIFT; - struct sg_table *sgt = obj->mm.pages; - pte_t *stack[32], **mem; - struct vm_struct *area; + unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i; + struct page *stack[32], **pages = stack, *page; + struct sgt_iter iter; pgprot_t pgprot; + void *vaddr; - if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC) - return NULL; - - if (GEM_WARN_ON(type == I915_MAP_WC && - !static_cpu_has(X86_FEATURE_PAT))) - return NULL; - - /* A single page can always be kmapped */ - if (n_pte == 1 && type == I915_MAP_WB) { - struct page *page = sg_page(sgt->sgl); - + switch (type) { + default: + MISSING_CASE(type); + fallthrough; /* to use PAGE_KERNEL anyway */ + case I915_MAP_WB: /* * On 32b, highmem using a finite set of indirect PTE (i.e. * vmap) to provide virtual mappings of the high pages. @@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, * So if the page is beyond the 32b boundary, make an explicit * vmap. */ - if (!PageHighMem(page)) - return page_address(page); - } - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - /* Too big for stack -- allocate temporary array instead */ - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } - - area = alloc_vm_area(obj->base.size, mem); - if (!area) { - if (mem != stack) - kvfree(mem); - return NULL; - } - - switch (type) { - default: - MISSING_CASE(type); - fallthrough; /* to use PAGE_KERNEL anyway */ - case I915_MAP_WB: + if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl))) + return page_address(sg_page(obj->mm.pages->sgl)); pgprot = PAGE_KERNEL; break; case I915_MAP_WC: @@ -308,30 +273,49 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, break; } - if (i915_gem_object_has_struct_page(obj)) { - struct sgt_iter iter; - struct page *page; - pte_t **ptes = mem; + if (n_pages > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return NULL; + } - for_each_sgt_page(page, iter, sgt) - **ptes++ = mk_pte(page, pgprot); - } else { - resource_size_t iomap; - struct sgt_iter iter; - pte_t **ptes = mem; - dma_addr_t addr; + i = 0; + for_each_sgt_page(page, iter, obj->mm.pages) + pages[i++] = page; + vaddr = vmap(pages, n_pages, 0, pgprot); + if (pages != stack) + kvfree(pages); + return vaddr; +} - iomap = obj->mm.region->iomap.base; - iomap -= obj->mm.region->region.start; +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj, + enum i915_map_type type) +{ + resource_size_t iomap = obj->mm.region->iomap.base - + obj->mm.region->region.start; + unsigned long n_pfn = obj->base.size >> PAGE_SHIFT; + unsigned long stack[32], *pfns = stack, i; + struct sgt_iter iter; + dma_addr_t addr; + void *vaddr; + + if (type != I915_MAP_WC) + return NULL; - for_each_sgt_daddr(addr, iter, sgt) - **ptes++ = iomap_pte(iomap, addr, pgprot); + if (n_pfn > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return NULL; } - if (mem != stack) - kvfree(mem); - - return area->addr; + for_each_sgt_daddr(addr, iter, obj->mm.pages) + pfns[i++] = (iomap + addr) >> PAGE_SHIFT; + vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO)); + if (pfns != stack) + kvfree(pfns); + return vaddr; } /* get, pin, and map the pages of the object into kernel space */ @@ -383,7 +367,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } if (!ptr) { - ptr = i915_gem_object_map(obj, type); + if (GEM_WARN_ON(type == I915_MAP_WC && + !static_cpu_has(X86_FEATURE_PAT))) + ptr = NULL; + else if (i915_gem_object_has_struct_page(obj)) + ptr = i915_gem_object_map_page(obj, type); + else + ptr = i915_gem_object_map_pfn(obj, type); if (!ptr) { err = -ENOMEM; goto err_unpin; -- 2.28.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-12.6 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 63523C47423 for ; Thu, 24 Sep 2020 13:59:26 +0000 (UTC) Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 0DDF720B1F for ; Thu, 24 Sep 2020 13:59:25 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=infradead.org header.i=@infradead.org header.b="eVcrp51t" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 0DDF720B1F Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=lst.de Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=intel-gfx-bounces@lists.freedesktop.org Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 3C8C86EB0B; Thu, 24 Sep 2020 13:59:24 +0000 (UTC) Received: from casper.infradead.org (casper.infradead.org [IPv6:2001:8b0:10b:1236::1]) by gabe.freedesktop.org (Postfix) with ESMTPS id F170F6E428; Thu, 24 Sep 2020 13:59:20 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Transfer-Encoding:MIME-Version: References:In-Reply-To:Message-Id:Date:Subject:Cc:To:From:Sender:Reply-To: Content-Type:Content-ID:Content-Description; bh=IV+5G3JY9ITNxQsZ2scDnXefMHEiNcoILBZrmnx9LqY=; b=eVcrp51tU/1VUllGrBsmEMDRJF Oa8azxOrxIve8eOcqGMESUBdvV21tVe29JUePa2/QKfrksNjNoY0FfxtHipVka+VDzXV3Uw/t65vM d6xc6edaYPqHIJ55twKgv9IlDVwlthwgOUk/RFi81tsUINjkVakHbycDUpuEwygIrEIo7pDe0ccii BtcNrj1WyblQ9O8jDl6upG+Yc/NdkQyp0nmN2rlNDc9IlalpWpA6HJRZVAhwEeWGnW7nMJJC7ORS1 UWlN5Gsoq/7E9Zc8bBSM2fMLcHu+0tEWg9MeP0JNDBhoQEO4RFxzpykzkdwG3Qw4FpKuo95UeSOH2 6Xb1GYog==; Received: from p4fdb0c34.dip0.t-ipconnect.de ([79.219.12.52] helo=localhost) by casper.infradead.org with esmtpsa (Exim 4.92.3 #3 (Red Hat Linux)) id 1kLRm4-0003wW-K4; Thu, 24 Sep 2020 13:59:04 +0000 From: Christoph Hellwig To: Andrew Morton Date: Thu, 24 Sep 2020 15:58:50 +0200 Message-Id: <20200924135853.875294-9-hch@lst.de> X-Mailer: git-send-email 2.28.0 In-Reply-To: <20200924135853.875294-1-hch@lst.de> References: <20200924135853.875294-1-hch@lst.de> MIME-Version: 1.0 X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html Subject: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Juergen Gross , Stefano Stabellini , Matthew Wilcox , dri-devel@lists.freedesktop.org, linux-mm@kvack.org, Peter Zijlstra , linux-kernel@vger.kernel.org, intel-gfx@lists.freedesktop.org, x86@kernel.org, Chris Wilson , Minchan Kim , Matthew Auld , xen-devel@lists.xenproject.org, Boris Ostrovsky , Nitin Gupta Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" i915_gem_object_map implements fairly low-level vmap functionality in a driver. Split it into two helpers, one for remapping kernel memory which can use vmap, and one for I/O memory that uses vmap_pfn. The only practical difference is that alloc_vm_area prefeaults the vmalloc area PTEs, which doesn't seem to be required here for the kernel memory case (and could be added to vmap using a flag if actually required). Signed-off-by: Christoph Hellwig --- drivers/gpu/drm/i915/Kconfig | 1 + drivers/gpu/drm/i915/gem/i915_gem_pages.c | 126 ++++++++++------------ 2 files changed, 59 insertions(+), 68 deletions(-) diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 9afa5c4a6bf006..1e1cb245fca778 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -25,6 +25,7 @@ config DRM_I915 select CRC32 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER + select VMAP_PFN help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 6550c0bc824ea2..b519417667eb4b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -232,34 +232,21 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj) return err; } -static inline pte_t iomap_pte(resource_size_t base, - dma_addr_t offset, - pgprot_t prot) -{ - return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot)); -} - /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(struct drm_i915_gem_object *obj, - enum i915_map_type type) +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj, + enum i915_map_type type) { - unsigned long n_pte = obj->base.size >> PAGE_SHIFT; - struct sg_table *sgt = obj->mm.pages; - pte_t *stack[32], **mem; - struct vm_struct *area; + unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i; + struct page *stack[32], **pages = stack, *page; + struct sgt_iter iter; pgprot_t pgprot; + void *vaddr; - if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC) - return NULL; - - if (GEM_WARN_ON(type == I915_MAP_WC && - !static_cpu_has(X86_FEATURE_PAT))) - return NULL; - - /* A single page can always be kmapped */ - if (n_pte == 1 && type == I915_MAP_WB) { - struct page *page = sg_page(sgt->sgl); - + switch (type) { + default: + MISSING_CASE(type); + fallthrough; /* to use PAGE_KERNEL anyway */ + case I915_MAP_WB: /* * On 32b, highmem using a finite set of indirect PTE (i.e. * vmap) to provide virtual mappings of the high pages. @@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, * So if the page is beyond the 32b boundary, make an explicit * vmap. */ - if (!PageHighMem(page)) - return page_address(page); - } - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - /* Too big for stack -- allocate temporary array instead */ - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } - - area = alloc_vm_area(obj->base.size, mem); - if (!area) { - if (mem != stack) - kvfree(mem); - return NULL; - } - - switch (type) { - default: - MISSING_CASE(type); - fallthrough; /* to use PAGE_KERNEL anyway */ - case I915_MAP_WB: + if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl))) + return page_address(sg_page(obj->mm.pages->sgl)); pgprot = PAGE_KERNEL; break; case I915_MAP_WC: @@ -308,30 +273,49 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, break; } - if (i915_gem_object_has_struct_page(obj)) { - struct sgt_iter iter; - struct page *page; - pte_t **ptes = mem; + if (n_pages > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return NULL; + } - for_each_sgt_page(page, iter, sgt) - **ptes++ = mk_pte(page, pgprot); - } else { - resource_size_t iomap; - struct sgt_iter iter; - pte_t **ptes = mem; - dma_addr_t addr; + i = 0; + for_each_sgt_page(page, iter, obj->mm.pages) + pages[i++] = page; + vaddr = vmap(pages, n_pages, 0, pgprot); + if (pages != stack) + kvfree(pages); + return vaddr; +} - iomap = obj->mm.region->iomap.base; - iomap -= obj->mm.region->region.start; +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj, + enum i915_map_type type) +{ + resource_size_t iomap = obj->mm.region->iomap.base - + obj->mm.region->region.start; + unsigned long n_pfn = obj->base.size >> PAGE_SHIFT; + unsigned long stack[32], *pfns = stack, i; + struct sgt_iter iter; + dma_addr_t addr; + void *vaddr; + + if (type != I915_MAP_WC) + return NULL; - for_each_sgt_daddr(addr, iter, sgt) - **ptes++ = iomap_pte(iomap, addr, pgprot); + if (n_pfn > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return NULL; } - if (mem != stack) - kvfree(mem); - - return area->addr; + for_each_sgt_daddr(addr, iter, obj->mm.pages) + pfns[i++] = (iomap + addr) >> PAGE_SHIFT; + vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO)); + if (pfns != stack) + kvfree(pfns); + return vaddr; } /* get, pin, and map the pages of the object into kernel space */ @@ -383,7 +367,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } if (!ptr) { - ptr = i915_gem_object_map(obj, type); + if (GEM_WARN_ON(type == I915_MAP_WC && + !static_cpu_has(X86_FEATURE_PAT))) + ptr = NULL; + else if (i915_gem_object_has_struct_page(obj)) + ptr = i915_gem_object_map_page(obj, type); + else + ptr = i915_gem_object_map_pfn(obj, type); if (!ptr) { err = -ENOMEM; goto err_unpin; -- 2.28.0 _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx