From patchwork Sat Sep 19 07:49:04 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: John Stultz X-Patchwork-Id: 11786693 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 664526CB for ; Sat, 19 Sep 2020 07:49:25 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 3CA432311D for ; Sat, 19 Sep 2020 07:49:25 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b="BC0RhrRG" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726151AbgISHtY (ORCPT ); Sat, 19 Sep 2020 03:49:24 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47156 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726041AbgISHtY (ORCPT ); Sat, 19 Sep 2020 03:49:24 -0400 Received: from mail-pf1-x442.google.com (mail-pf1-x442.google.com [IPv6:2607:f8b0:4864:20::442]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 16C94C0613CE for ; Sat, 19 Sep 2020 00:49:24 -0700 (PDT) Received: by mail-pf1-x442.google.com with SMTP id o20so4938242pfp.11 for ; Sat, 19 Sep 2020 00:49:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id; bh=euqT8lAbNK8yda4fe5ZlU/VWsoGMJIaK1lu2B8reCtQ=; b=BC0RhrRGJPXpvemnBxslClbKPymkQ96oYf+Ai2v1b9MBEc/maqL371OqqQNo2CodWJ mm0oLv6j/1w3gIGZhSaiCsDSmRG3HLyEYkWnAjoKBVCaOsVuKUccSOhB2ZSCJcoH0mpH 5OsqBadth/QUJ+Dbun88ZdJdIqF71ZRO3hXeUItJponIoDnbJggTBJWHlH2Klu8/gRKY zwspEdA+z589VELkXJrvK39rwLhaJ9dJ6uHrHGwmcZZn8auZeDR5My5bTHUzcCCQpEUf G0Mo514LawqFo8uCYoOWMDWbYwphOV3MHTsTkhw2wCFgq8mYa4RudKbxURJQbUPkqzRl BmtA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id; bh=euqT8lAbNK8yda4fe5ZlU/VWsoGMJIaK1lu2B8reCtQ=; b=riP65FX/mYH3P7lEFEAnRC06c3yhS1oYN0ppy5iIfR+HvTocOlRkypbwKIz41HfzIv n+dpImHcO4/8ixW6Co48tWzOfd8EcZ4FVA7F8LLB+Bc41gvuXe0F7LA3878xYqSgHr0u f8IQ0euMMwjN+dnaSnjf4yX5O5oWbPtz/np/oMxwx00gVW0MDh+dGCRMr9jWGEcW+VG7 i35LGvw/k9SSz/9dnpVdHoL2vr0UFB0qrZPsHOgaKwT5OLKDV4Tm62ktQ1wo8Um3LX1f WRwhjG/saWw4+kXKL7kjSIXSLlHFcHoPe4krYaL2pj4qlImhiaK7luV2n6dIXrJf1rnv vkzA== X-Gm-Message-State: AOAM531elX4DrhLmg7TQJ5l5KfN61JD4fqzqCn/tKaOhj2W/qTD++yfY uWDU1pl5NaSD4HwlYJJkoc8KBw== X-Google-Smtp-Source: ABdhPJxpKPIvszjM3OQE3v39tCZq8Ro9FvcwzLrJYNhAyKJA0YoP0JQIOlLxT75zeuGDZwscO0GLHw== X-Received: by 2002:a62:1c96:0:b029:142:4bf7:15f3 with SMTP id c144-20020a621c960000b02901424bf715f3mr14299830pfc.75.1600501763512; Sat, 19 Sep 2020 00:49:23 -0700 (PDT) Received: from localhost.localdomain ([2601:1c2:680:1319:692:26ff:feda:3a81]) by smtp.gmail.com with ESMTPSA id m13sm5688151pfk.103.2020.09.19.00.49.21 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 19 Sep 2020 00:49:22 -0700 (PDT) From: John Stultz To: lkml Cc: John Stultz , Sumit Semwal , "Andrew F . Davis" , Benjamin Gaignard , Liam Mark , Laura Abbott , Brian Starkey , Hridya Valsaraju , Robin Murphy , Ezequiel Garcia , Simon Ser , James Jones , linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org Subject: [PATCH v3 1/2] dma-heap: Keep track of the heap device struct Date: Sat, 19 Sep 2020 07:49:04 +0000 Message-Id: <20200919074905.82036-1-john.stultz@linaro.org> X-Mailer: git-send-email 2.17.1 Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org Keep track of the heap device struct. This will be useful for special DMA allocations and actions. Cc: Sumit Semwal Cc: Andrew F. Davis Cc: Benjamin Gaignard Cc: Liam Mark Cc: Laura Abbott Cc: Brian Starkey Cc: Hridya Valsaraju Cc: Robin Murphy Cc: Ezequiel Garcia Cc: Simon Ser Cc: James Jones Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: John Stultz --- drivers/dma-buf/dma-heap.c | 33 +++++++++++++++++++++++++-------- include/linux/dma-heap.h | 9 +++++++++ 2 files changed, 34 insertions(+), 8 deletions(-) diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index afd22c9dbdcf..72c746755d89 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -30,6 +30,7 @@ * @heap_devt heap device node * @list list head connecting to list of heaps * @heap_cdev heap char device + * @heap_dev heap device struct * * Represents a heap of memory from which buffers can be made. */ @@ -40,6 +41,7 @@ struct dma_heap { dev_t heap_devt; struct list_head list; struct cdev heap_cdev; + struct device *heap_dev; }; static LIST_HEAD(heap_list); @@ -190,10 +192,21 @@ void *dma_heap_get_drvdata(struct dma_heap *heap) return heap->priv; } +/** + * dma_heap_get_dev() - get device struct for the heap + * @heap: DMA-Heap to retrieve device struct from + * + * Returns: + * The device struct for the heap. + */ +struct device *dma_heap_get_dev(struct dma_heap *heap) +{ + return heap->heap_dev; +} + struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { struct dma_heap *heap, *h, *err_ret; - struct device *dev_ret; unsigned int minor; int ret; @@ -247,16 +260,20 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) goto err1; } - dev_ret = device_create(dma_heap_class, - NULL, - heap->heap_devt, - NULL, - heap->name); - if (IS_ERR(dev_ret)) { + heap->heap_dev = device_create(dma_heap_class, + NULL, + heap->heap_devt, + NULL, + heap->name); + if (IS_ERR(heap->heap_dev)) { pr_err("dma_heap: Unable to create device\n"); - err_ret = ERR_CAST(dev_ret); + err_ret = ERR_CAST(heap->heap_dev); goto err2; } + + /* Make sure it doesn't disappear on us */ + heap->heap_dev = get_device(heap->heap_dev); + /* Add heap to the list */ mutex_lock(&heap_list_lock); list_add(&heap->list, &heap_list); diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 454e354d1ffb..82857e096910 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -50,6 +50,15 @@ struct dma_heap_export_info { */ void *dma_heap_get_drvdata(struct dma_heap *heap); +/** + * dma_heap_get_dev() - get device struct for the heap + * @heap: DMA-Heap to retrieve device struct from + * + * Returns: + * The device struct for the heap. + */ +struct device *dma_heap_get_dev(struct dma_heap *heap); + /** * dma_heap_add - adds a heap to dmabuf heaps * @exp_info: information needed to register this heap From patchwork Sat Sep 19 07:49:05 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: John Stultz X-Patchwork-Id: 11786695 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0C40B6CB for ; Sat, 19 Sep 2020 07:49:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id D9C9D23447 for ; Sat, 19 Sep 2020 07:49:29 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=linaro.org header.i=@linaro.org header.b="VMlNfIw2" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726222AbgISHt3 (ORCPT ); Sat, 19 Sep 2020 03:49:29 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47166 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726054AbgISHtZ (ORCPT ); Sat, 19 Sep 2020 03:49:25 -0400 Received: from mail-pl1-x644.google.com (mail-pl1-x644.google.com [IPv6:2607:f8b0:4864:20::644]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 83222C0613CE for ; Sat, 19 Sep 2020 00:49:25 -0700 (PDT) Received: by mail-pl1-x644.google.com with SMTP id y6so4185666plt.9 for ; Sat, 19 Sep 2020 00:49:25 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=Mo9wAvGILKCqYotrN+tF0XCxTgM5i35wrY/cuVjP5Ps=; b=VMlNfIw2pyfJl6rUyI7rAR56tGSa+aICh4WBFHY+FIFO75ETGjU9BpSfSuvERReo5P iBm2ls1HWbP1Ta9DHf2/gvdVpOqoqvT1MrKw5egGT3xxIAY4wTAsR7IDrzvnhRIpZDyL WJchOoG349il5bAa+xSY3/amWvNYAcvSKTiWjEevs9OhKDNYHiyF29Rtgo11ILK13puX 72Z2I98soY3kveDkcHzui0pbkc207x80/dySWD4Feuu8xEYaCkPXhJYXzuDOXiJDXy0d I/+9rNx5f7pZ+GBw2ienUNvMPB7ev9+FcUqE7bTVxUuDTiSD5JqKOjKPuN60cQ2Lymqn rchQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=Mo9wAvGILKCqYotrN+tF0XCxTgM5i35wrY/cuVjP5Ps=; b=nhMWAwzkqg7WAA5HtiwauS8WQg/halPPvk27L60/Ig1Weue6lafRqVpRnCGw2PfzJx pyMRmYK8ibMJdbvBEVdkutKDKW2GXciHY7r/6xgmGu5Jadl3x/TRJpJRQXogBVH16CXW E2YnctQIsS/9JOC+8RMJaZJDFUMIT9ifZU++M2ZTksJRUIc42PR6p/QA3rQraUvkXTG2 YdOYAJv+NUQjIfDL7vvG0Khl6ZMU0+ENWM6eoEJajLcd6n76wVASl5QunJiY2vcK4vVx hui4Yknz3j7+V7TaMfVOYrSZE/KUi0MjmlZ4mGltBEjxoyEENX1vbt3UDNEHZawRiU5z Gghw== X-Gm-Message-State: AOAM5319UOQ412HC/jPXr80WsUvM0ZZ5CkKHHI9G0bopk4i0Kt0GeM30 WZPJ8V0ZbnnvgXyJy1usJIWCaA== X-Google-Smtp-Source: ABdhPJzxtKNJExQxGphWrBSpCp6nPiEtR1WXPnghOp2j+lZr49oGD8LfOwdiVGslVYrJXFathVlwnA== X-Received: by 2002:a17:90a:ca17:: with SMTP id x23mr15392828pjt.96.1600501765011; Sat, 19 Sep 2020 00:49:25 -0700 (PDT) Received: from localhost.localdomain ([2601:1c2:680:1319:692:26ff:feda:3a81]) by smtp.gmail.com with ESMTPSA id m13sm5688151pfk.103.2020.09.19.00.49.23 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 19 Sep 2020 00:49:24 -0700 (PDT) From: John Stultz To: lkml Cc: John Stultz , Sumit Semwal , "Andrew F . Davis" , Benjamin Gaignard , Liam Mark , Laura Abbott , Brian Starkey , Hridya Valsaraju , Robin Murphy , Ezequiel Garcia , Simon Ser , James Jones , linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org Subject: [PATCH v3 2/2] dma-heap: Add a system-uncached heap Date: Sat, 19 Sep 2020 07:49:05 +0000 Message-Id: <20200919074905.82036-2-john.stultz@linaro.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20200919074905.82036-1-john.stultz@linaro.org> References: <20200919074905.82036-1-john.stultz@linaro.org> Precedence: bulk List-ID: X-Mailing-List: linux-media@vger.kernel.org This adds a heap that allocates non-contiguous buffers that are marked as writecombined, so they are not cached by the CPU. This is useful, as most graphics buffers are usually not touched by the CPU or only written into once by the CPU. So when mapping the buffer over and over between devices, we can skip the CPU syncing, which saves a lot of cache management overhead, greatly improving performance. For folk using ION, there was a ION_FLAG_CACHED flag, which signaled if the returned buffer should be CPU cacheable or not. With DMA-BUF heaps, we do not yet have such a flag, and by default the current heaps (system and cma) produce CPU cachable buffers. So for folks transitioning from ION to DMA-BUF Heaps, this fills in some of that missing functionality. There has been a suggestion to make this functionality a flag (DMAHEAP_FLAG_UNCACHED?) on the system heap, similar to how ION used the ION_FLAG_CACHED. But I want to make sure an _UNCACHED flag would truely be a generic attribute across all heaps. So far that has been unclear, so having it as a separate heap seemes better for now. (But I'm open to discussion on this point!) Feedback would be very welcome! Many thanks to Liam Mark for his help to get this working. Pending opensource users of this code include: * AOSP HiKey960 gralloc: - https://android-review.googlesource.com/c/device/linaro/hikey/+/1399519 - Visibly improves performance over the system heap * AOSP Codec2 (possibly, needs more review): - https://android-review.googlesource.com/c/platform/frameworks/av/+/1360640/17/media/codec2/vndk/C2DmaBufAllocator.cpp#325 Cc: Sumit Semwal Cc: Andrew F. Davis Cc: Benjamin Gaignard Cc: Liam Mark Cc: Laura Abbott Cc: Brian Starkey Cc: Hridya Valsaraju Cc: Robin Murphy Cc: Ezequiel Garcia Cc: Simon Ser Cc: James Jones Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: John Stultz --- v2: * Fix build issue on sh reported-by: kernel test robot * Rework to use for_each_sgtable_sg(), dma_map_sgtable(), and for_each_sg_page() along with numerous other cleanups suggested by Robin Murphy v3: * Clarified commit message to address questions from last submission --- drivers/dma-buf/heaps/Kconfig | 10 + drivers/dma-buf/heaps/Makefile | 1 + drivers/dma-buf/heaps/system_uncached_heap.c | 371 +++++++++++++++++++ 3 files changed, 382 insertions(+) create mode 100644 drivers/dma-buf/heaps/system_uncached_heap.c diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig index a5eef06c4226..420b0ed0a512 100644 --- a/drivers/dma-buf/heaps/Kconfig +++ b/drivers/dma-buf/heaps/Kconfig @@ -5,6 +5,16 @@ config DMABUF_HEAPS_SYSTEM Choose this option to enable the system dmabuf heap. The system heap is backed by pages from the buddy allocator. If in doubt, say Y. +config DMABUF_HEAPS_SYSTEM_UNCACHED + bool "DMA-BUF Uncached System Heap" + depends on DMABUF_HEAPS + help + Choose this option to enable the uncached system dmabuf heap. This + heap is backed by pages from the buddy allocator, but pages are setup + for write combining. This avoids cache management overhead, and can + be faster if pages are mostly untouched by the cpu. If in doubt, + say Y. + config DMABUF_HEAPS_CMA bool "DMA-BUF CMA Heap" depends on DMABUF_HEAPS && DMA_CMA diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile index 6e54cdec3da0..085685ec478f 100644 --- a/drivers/dma-buf/heaps/Makefile +++ b/drivers/dma-buf/heaps/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += heap-helpers.o obj-$(CONFIG_DMABUF_HEAPS_SYSTEM) += system_heap.o +obj-$(CONFIG_DMABUF_HEAPS_SYSTEM_UNCACHED) += system_uncached_heap.o obj-$(CONFIG_DMABUF_HEAPS_CMA) += cma_heap.o diff --git a/drivers/dma-buf/heaps/system_uncached_heap.c b/drivers/dma-buf/heaps/system_uncached_heap.c new file mode 100644 index 000000000000..3b8e699bcae7 --- /dev/null +++ b/drivers/dma-buf/heaps/system_uncached_heap.c @@ -0,0 +1,371 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Uncached System DMA-Heap exporter + * + * Copyright (C) 2020 Linaro Ltd. + * + * Based off of Andrew Davis' SRAM heap: + * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct uncached_heap { + struct dma_heap *heap; +}; + +struct uncached_heap_buffer { + struct dma_heap *heap; + struct list_head attachments; + struct mutex lock; + unsigned long len; + struct sg_table sg_table; + int vmap_cnt; + void *vaddr; +}; + +struct dma_heap_attachment { + struct device *dev; + struct sg_table *table; + struct list_head list; +}; + +static struct sg_table *dup_sg_table(struct sg_table *table) +{ + struct sg_table *new_table; + int ret, i; + struct scatterlist *sg, *new_sg; + + new_table = kzalloc(sizeof(*new_table), GFP_KERNEL); + if (!new_table) + return ERR_PTR(-ENOMEM); + + ret = sg_alloc_table(new_table, table->nents, GFP_KERNEL); + if (ret) { + kfree(new_table); + return ERR_PTR(-ENOMEM); + } + + new_sg = new_table->sgl; + for_each_sgtable_sg(table, sg, i) { + sg_set_page(new_sg, sg_page(sg), sg->length, sg->offset); + new_sg = sg_next(new_sg); + } + + return new_table; +} + +static int dma_heap_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct uncached_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a; + struct sg_table *table; + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + table = dup_sg_table(&buffer->sg_table); + if (IS_ERR(table)) { + kfree(a); + return -ENOMEM; + } + + a->table = table; + a->dev = attachment->dev; + INIT_LIST_HEAD(&a->list); + + attachment->priv = a; + + mutex_lock(&buffer->lock); + list_add(&a->list, &buffer->attachments); + mutex_unlock(&buffer->lock); + + return 0; +} + +static void dma_heap_detatch(struct dma_buf *dmabuf, + struct dma_buf_attachment *attachment) +{ + struct uncached_heap_buffer *buffer = dmabuf->priv; + struct dma_heap_attachment *a = attachment->priv; + + mutex_lock(&buffer->lock); + list_del(&a->list); + mutex_unlock(&buffer->lock); + + sg_free_table(a->table); + kfree(a->table); + kfree(a); +} + +static struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment, + enum dma_data_direction direction) +{ + struct dma_heap_attachment *a = attachment->priv; + struct sg_table *table = a->table; + + if (dma_map_sgtable(attachment->dev, table, direction, DMA_ATTR_SKIP_CPU_SYNC)) + return ERR_PTR(-ENOMEM); + + return table; +} + +static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment, + struct sg_table *table, + enum dma_data_direction direction) +{ + dma_unmap_sgtable(attachment->dev, table, direction, DMA_ATTR_SKIP_CPU_SYNC); +} + +static int dma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) +{ + struct uncached_heap_buffer *buffer = dmabuf->priv; + struct sg_table *table = &buffer->sg_table; + unsigned long addr = vma->vm_start; + struct sg_page_iter piter; + int ret; + + vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); + + for_each_sgtable_page(table, &piter, vma->vm_pgoff) { + struct page *page = sg_page_iter_page(&piter); + + ret = remap_pfn_range(vma, addr, page_to_pfn(page), PAGE_SIZE, + vma->vm_page_prot); + if (ret) + return ret; + addr += PAGE_SIZE; + if (addr >= vma->vm_end) + return 0; + } + return 0; +} + +static void *dma_heap_do_vmap(struct uncached_heap_buffer *buffer) +{ + struct sg_table *table = &buffer->sg_table; + int npages = PAGE_ALIGN(buffer->len) / PAGE_SIZE; + struct page **pages = vmalloc(sizeof(struct page *) * npages); + struct page **tmp = pages; + struct sg_page_iter piter; + pgprot_t pgprot; + void *vaddr; + + if (!pages) + return ERR_PTR(-ENOMEM); + + pgprot = pgprot_writecombine(PAGE_KERNEL); + + for_each_sgtable_page(table, &piter, 0) { + WARN_ON(tmp - pages >= npages); + *tmp++ = sg_page_iter_page(&piter); + } + + vaddr = vmap(pages, npages, VM_MAP, pgprot); + vfree(pages); + + if (!vaddr) + return ERR_PTR(-ENOMEM); + + return vaddr; +} + +static void *dma_heap_buffer_vmap_get(struct uncached_heap_buffer *buffer) +{ + void *vaddr; + + if (buffer->vmap_cnt) { + buffer->vmap_cnt++; + return buffer->vaddr; + } + + vaddr = dma_heap_do_vmap(buffer); + if (IS_ERR(vaddr)) + return vaddr; + + buffer->vaddr = vaddr; + buffer->vmap_cnt++; + return vaddr; +} + +static void dma_heap_buffer_vmap_put(struct uncached_heap_buffer *buffer) +{ + if (!--buffer->vmap_cnt) { + vunmap(buffer->vaddr); + buffer->vaddr = NULL; + } +} + +static void *dma_heap_vmap(struct dma_buf *dmabuf) +{ + struct uncached_heap_buffer *buffer = dmabuf->priv; + void *vaddr; + + mutex_lock(&buffer->lock); + vaddr = dma_heap_buffer_vmap_get(buffer); + mutex_unlock(&buffer->lock); + + return vaddr; +} + +static void dma_heap_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ + struct uncached_heap_buffer *buffer = dmabuf->priv; + + mutex_lock(&buffer->lock); + dma_heap_buffer_vmap_put(buffer); + mutex_unlock(&buffer->lock); +} + +static void dma_heap_dma_buf_release(struct dma_buf *dmabuf) +{ + struct uncached_heap_buffer *buffer = dmabuf->priv; + struct sg_table *table; + struct scatterlist *sg; + int i; + + table = &buffer->sg_table; + dma_unmap_sgtable(dma_heap_get_dev(buffer->heap), table, DMA_BIDIRECTIONAL, 0); + + for_each_sgtable_sg(table, sg, i) + __free_page(sg_page(sg)); + sg_free_table(table); + kfree(buffer); +} + +const struct dma_buf_ops uncached_heap_buf_ops = { + .attach = dma_heap_attach, + .detach = dma_heap_detatch, + .map_dma_buf = dma_heap_map_dma_buf, + .unmap_dma_buf = dma_heap_unmap_dma_buf, + .mmap = dma_heap_mmap, + .vmap = dma_heap_vmap, + .vunmap = dma_heap_vunmap, + .release = dma_heap_dma_buf_release, +}; + +static int uncached_heap_allocate(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags) +{ + struct uncached_heap_buffer *buffer; + DEFINE_DMA_BUF_EXPORT_INFO(exp_info); + struct dma_buf *dmabuf; + struct sg_table *table; + struct scatterlist *sg; + pgoff_t pagecount; + pgoff_t pg; + int i, ret = -ENOMEM; + + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); + if (!buffer) + return -ENOMEM; + + INIT_LIST_HEAD(&buffer->attachments); + mutex_init(&buffer->lock); + buffer->heap = heap; + buffer->len = len; + + table = &buffer->sg_table; + pagecount = len / PAGE_SIZE; + if (sg_alloc_table(table, pagecount, GFP_KERNEL)) + goto free_buffer; + + sg = table->sgl; + for (pg = 0; pg < pagecount; pg++) { + struct page *page; + /* + * Avoid trying to allocate memory if the process + * has been killed by SIGKILL + */ + if (fatal_signal_pending(current)) + goto free_pages; + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto free_pages; + sg_set_page(sg, page, page_size(page), 0); + sg = sg_next(sg); + } + + /* create the dmabuf */ + exp_info.ops = &uncached_heap_buf_ops; + exp_info.size = buffer->len; + exp_info.flags = fd_flags; + exp_info.priv = buffer; + dmabuf = dma_buf_export(&exp_info); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); + goto free_pages; + } + + ret = dma_buf_fd(dmabuf, fd_flags); + if (ret < 0) { + dma_buf_put(dmabuf); + /* just return, as put will call release and that will free */ + return ret; + } + + /* + * XXX This is hackish. While the buffer will be uncached, we need + * to initially flush cpu cache, since the __GFP_ZERO on the + * allocation means the zeroing was done by the cpu and thus it is + * likely cached. Map (and implicitly flush) it out now so we don't + * get corruption later on. + * + * Ideally we could do this without using the heap device as a dummy dev. + */ + dma_map_sgtable(dma_heap_get_dev(heap), table, DMA_BIDIRECTIONAL, 0); + + return ret; + +free_pages: + for_each_sgtable_sg(table, sg, i) + __free_page(sg_page(sg)); + sg_free_table(table); +free_buffer: + kfree(buffer); + + return ret; +} + +static struct dma_heap_ops uncached_heap_ops = { + .allocate = uncached_heap_allocate, +}; + +static int uncached_heap_create(void) +{ + struct uncached_heap *heap; + struct dma_heap_export_info exp_info; + + heap = kzalloc(sizeof(*heap), GFP_KERNEL); + if (!heap) + return -ENOMEM; + + exp_info.name = "system-uncached"; + exp_info.ops = &uncached_heap_ops; + exp_info.priv = heap; + heap->heap = dma_heap_add(&exp_info); + if (IS_ERR(heap->heap)) { + int ret = PTR_ERR(heap->heap); + + kfree(heap); + return ret; + } + dma_coerce_mask_and_coherent(dma_heap_get_dev(heap->heap), DMA_BIT_MASK(64)); + + return 0; +} +device_initcall(uncached_heap_create);