From patchwork Thu Nov 7 17:40:34 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christoph Hellwig X-Patchwork-Id: 11233431 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 67C4E139A for ; Thu, 7 Nov 2019 17:40:51 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (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 35C2B2077C for ; Thu, 7 Nov 2019 17:40:51 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=lists.infradead.org header.i=@lists.infradead.org header.b="ac7X+IGy" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 35C2B2077C Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=lst.de Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20170209; h=Sender: Content-Transfer-Encoding:Content-Type:Cc:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-Id:Date:Subject:To:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=6TMRyTDK7bsvv41hUOVufzyCjejqwtPMgVSPBQx+0W0=; b=ac7X+IGyIEzSms sX3AHbRjc1YjAcGaCD4+x/HVnmR4SIKCM/RY/Y/VCy9OKGzkIyFCWYsVQWsAVrwe8kU0fTEcNvfEC 8fMjvh3QWdHXyCluwELdir5yzxYhppnTLNSiTYiMJqYUY+2WDYVaYdBii8zeaPRDvFlExbcpSCS0q qzg+CcelMUXfuzSJdzTH98kY8L5lkGfyee0lyVI9Dt3tNF550v0aSER+Ucyy/KCNm9wnjEm4+7dwU SIpP6j7dMvlPnvyepyNNxp2BiYWY95dZiLgwT/loHwMggvv7nSsKxuTkTWajM+gxm9K321WLXRkES nmRitNwG+4GIPISmv3ig==; Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.92.3 #3 (Red Hat Linux)) id 1iSlm6-0002Vt-JR; Thu, 07 Nov 2019 17:40:50 +0000 Received: from [2001:4bb8:184:e48:c70:4a89:bc61:2] (helo=localhost) by bombadil.infradead.org with esmtpsa (Exim 4.92.3 #3 (Red Hat Linux)) id 1iSllw-0002O1-MK; Thu, 07 Nov 2019 17:40:41 +0000 From: Christoph Hellwig To: Jonas Bonn , Stefan Kristiansson , Stafford Horne Subject: [PATCH 1/2] dma-mapping: support setting memory uncached in place Date: Thu, 7 Nov 2019 18:40:34 +0100 Message-Id: <20191107174035.13783-2-hch@lst.de> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20191107174035.13783-1-hch@lst.de> References: <20191107174035.13783-1-hch@lst.de> MIME-Version: 1.0 X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Mark Rutland , linux-arch@vger.kernel.org, Robin Murphy , linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, openrisc@lists.librecores.org, Will Deacon , linux-arm-kernel@lists.infradead.org, Marek Szyprowski Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org We currently only support remapping memory as uncached through vmap or a magic uncached segment provided by some architectures. But there is a simpler and much better way available on some architectures where we can just remap the memory in place. The advantages are: 1) no aliasing is possible, which prevents speculating into the cached alias 2) there is no need to allocate new ptes and thus no need for a special pre-allocated pool of memory that can be used with GFP_ATOMIC DMA allocations The downside is that architectures must provide a way to set arbitrary pages uncached in the kernel mapping, which might not be possible on architecture that have a special implicit kernel mapping, and requires splitting of huge page kernel mappings where they exist. Signed-off-by: Christoph Hellwig --- include/linux/dma-noncoherent.h | 3 +++ kernel/dma/Kconfig | 8 ++++++++ kernel/dma/direct.c | 28 ++++++++++++++++++---------- 3 files changed, 29 insertions(+), 10 deletions(-) diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index e30fca1f1b12..c4be9697279a 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -111,4 +111,7 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size) void *uncached_kernel_address(void *addr); void *cached_kernel_address(void *addr); +int arch_dma_set_uncached(void *cpu_addr, size_t size); +void arch_dma_clear_uncached(void *cpu_addr, size_t size); + #endif /* _LINUX_DMA_NONCOHERENT_H */ diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 4c103a24e380..7bc0b77f1243 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -83,6 +83,14 @@ config DMA_DIRECT_REMAP bool select DMA_REMAP +# +# Should be selected if the architecture can remap memory from the page +# allocator and CMA as uncached and provides the arch_dma_set_uncached and +# arch_dma_clear_uncached helpers +# +config ARCH_HAS_DMA_SET_UNCACHED + bool + config DMA_CMA bool "DMA Contiguous Memory Allocator" depends on HAVE_DMA_CONTIGUOUS && CMA diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index e37e7ab6e2ee..e2b46001c1b3 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -171,11 +171,8 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size), dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); - if (!ret) { - dma_free_contiguous(dev, page, size); - return ret; - } - + if (!ret) + goto out_free_pages; memset(ret, 0, size); goto done; } @@ -188,8 +185,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, * so log an error and fail. */ dev_info(dev, "Rejecting highmem page from CMA.\n"); - dma_free_contiguous(dev, page, size); - return NULL; + goto out_free_pages; } ret = page_address(page); @@ -198,10 +194,15 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, memset(ret, 0, size); - if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && - dma_alloc_need_uncached(dev, attrs)) { + if (dma_alloc_need_uncached(dev, attrs)) { arch_dma_prep_coherent(page, size); - ret = uncached_kernel_address(ret); + + if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED)) { + if (!arch_dma_set_uncached(ret, size)) + goto out_free_pages; + } else if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT)) { + ret = uncached_kernel_address(ret); + } } done: if (force_dma_unencrypted(dev)) @@ -209,6 +210,9 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, else *dma_handle = phys_to_dma(dev, page_to_phys(page)); return ret; +out_free_pages: + dma_free_contiguous(dev, page, size); + return NULL; } void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, @@ -232,6 +236,8 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) vunmap(cpu_addr); + else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED)) + arch_dma_clear_uncached(cpu_addr, size); dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size); } @@ -240,6 +246,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && + !IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && dma_alloc_need_uncached(dev, attrs)) return arch_dma_alloc(dev, size, dma_handle, gfp, attrs); @@ -250,6 +257,7 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && + !IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && dma_alloc_need_uncached(dev, attrs)) arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); From patchwork Thu Nov 7 17:40:35 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christoph Hellwig X-Patchwork-Id: 11233433 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 A328D1747 for ; Thu, 7 Nov 2019 17:41:09 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (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 7C930218AE for ; Thu, 7 Nov 2019 17:41:09 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=lists.infradead.org header.i=@lists.infradead.org header.b="u6KZvbZB" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 7C930218AE Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=lst.de Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20170209; h=Sender: Content-Transfer-Encoding:Content-Type:Cc:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-Id:Date:Subject:To:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=nSo4xKHUDUWD+v81uMXBrkSPnyUFmBx3FHlNApZw+JI=; b=u6KZvbZBdgkvFf 7HRbshu0TUuJMdqwb104qXaTXZJbsEgamsq6fkPYCtNTK02xNRgHPk7vKGcr4c7bk8bBBaTDQokUU ScQ6xJI83CQsXi/Q1tdSZTK/A+PZMGQIzXqMrhiCy/jvjjpfejuJHOsL+7ZVu9IjY3tGccvzBvrfC AWpQAbHQTG11az/j7yYe98iGBCn/jjnxXI3CiuWtFqUaSKn3iJsMh0aT1PG9nBQm4DKbnn63s207f MvX12P1IbWojD9uGwn8FRS5dgSOgBEr0scUvfhaNSQdHGsEItYCOg+Crcj4jftV/I/wGjn4xKl7mZ hnu3C6A/to1VHZeZ3s1w==; Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.92.3 #3 (Red Hat Linux)) id 1iSlmM-0002r7-Mj; Thu, 07 Nov 2019 17:41:06 +0000 Received: from [2001:4bb8:184:e48:c70:4a89:bc61:2] (helo=localhost) by bombadil.infradead.org with esmtpsa (Exim 4.92.3 #3 (Red Hat Linux)) id 1iSllz-0002ON-Cw; Thu, 07 Nov 2019 17:40:43 +0000 From: Christoph Hellwig To: Jonas Bonn , Stefan Kristiansson , Stafford Horne Subject: [PATCH 2/2] openrisc: use the generic in-place uncached DMA allocator Date: Thu, 7 Nov 2019 18:40:35 +0100 Message-Id: <20191107174035.13783-3-hch@lst.de> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20191107174035.13783-1-hch@lst.de> References: <20191107174035.13783-1-hch@lst.de> MIME-Version: 1.0 X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Mark Rutland , linux-arch@vger.kernel.org, Robin Murphy , linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org, openrisc@lists.librecores.org, Will Deacon , linux-arm-kernel@lists.infradead.org, Marek Szyprowski Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+patchwork-linux-arm=patchwork.kernel.org@lists.infradead.org Switch openrisc to use the dma-direct allocator and just provide the hooks for setting memory uncached or cached. Signed-off-by: Christoph Hellwig --- arch/openrisc/Kconfig | 1 + arch/openrisc/kernel/dma.c | 51 +++++--------------------------------- 2 files changed, 7 insertions(+), 45 deletions(-) diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index bf326f0edd2f..72469d2d2866 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -7,6 +7,7 @@ config OPENRISC def_bool y select ARCH_32BIT_OFF_T + select ARCH_HAS_DMA_SET_UNCACHED select ARCH_HAS_SYNC_DMA_FOR_DEVICE select OF select OF_EARLY_FLATTREE diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 4d5b8bd1d795..9a5b10164b08 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -11,8 +11,6 @@ * Copyright (C) 2010-2011 Jonas Bonn * * DMA mapping callbacks... - * As alloc_coherent is the only DMA callback being used currently, that's - * the only thing implemented properly. The rest need looking into... */ #include @@ -67,62 +65,25 @@ static const struct mm_walk_ops clear_nocache_walk_ops = { .pte_entry = page_clear_nocache, }; -/* - * Alloc "coherent" memory, which for OpenRISC means simply uncached. - * - * This function effectively just calls __get_free_pages, sets the - * cache-inhibit bit on those pages, and makes sure that the pages are - * flushed out of the cache before they are used. - * - * If the NON_CONSISTENT attribute is set, then this function just - * returns "normal", cachable memory. - * - * There are additional flags WEAK_ORDERING and WRITE_COMBINE to take - * into consideration here, too. All current known implementations of - * the OR1K support only strongly ordered memory accesses, so that flag - * is being ignored for now; uncached but write-combined memory is a - * missing feature of the OR1K. - */ -void * -arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) +int arch_dma_set_uncached(void *cpu_addr, size_t size) { - unsigned long va; - void *page; - - page = alloc_pages_exact(size, gfp | __GFP_ZERO); - if (!page) - return NULL; - - /* This gives us the real physical address of the first page. */ - *dma_handle = __pa(page); - - va = (unsigned long)page; + unsigned long va = (unsigned long)cpu_addr; /* * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ - if (walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, - NULL)) { - free_pages_exact(page, size); - return NULL; - } - - return (void *)va; + return walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, + NULL); } -void -arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) +void arch_dma_clear_uncached(void *cpu_addr, size_t size) { - unsigned long va = (unsigned long)vaddr; + unsigned long va = (unsigned long)cpu_addr; /* walk_page_range shouldn't be able to fail here */ WARN_ON(walk_page_range(&init_mm, va, va + size, &clear_nocache_walk_ops, NULL)); - - free_pages_exact(vaddr, size); } void arch_sync_dma_for_device(struct device *dev, phys_addr_t addr, size_t size,