All of lore.kernel.org
 help / color / mirror / Atom feed
From: Catalin Marinas <catalin.marinas@arm.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Arnd Bergmann <arnd@arndb.de>, Christoph Hellwig <hch@lst.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Ard Biesheuvel <ardb@kernel.org>,
	Isaac Manjarres <isaacmanjarres@google.com>,
	Saravana Kannan <saravanak@google.com>,
	Alasdair Kergon <agk@redhat.com>, Daniel Vetter <daniel@ffwll.ch>,
	Joerg Roedel <joro@8bytes.org>, Mark Brown <broonie@kernel.org>,
	Mike Snitzer <snitzer@kernel.org>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	linux-mm@kvack.org, iommu@lists.linux.dev,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 02/13] dma-mapping: Force bouncing if the kmalloc() size is not cacheline-aligned
Date: Sun,  6 Nov 2022 22:01:32 +0000	[thread overview]
Message-ID: <20221106220143.2129263-3-catalin.marinas@arm.com> (raw)
In-Reply-To: <20221106220143.2129263-1-catalin.marinas@arm.com>

For direct DMA, if the size is small enough to have originated from a
kmalloc() cache below ARCH_DMA_MINALIGN, check its alignment against
cache_line_size() and bounce if necessary. For larger sizes, it is the
responsibility of the DMA API caller to ensure proper alignment.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Robin Murphy <robin.murphy@arm.com>
---
 include/linux/dma-map-ops.h | 27 +++++++++++++++++++++++++++
 kernel/dma/direct.h         |  3 ++-
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index d678afeb8a13..785f7aa90f57 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,6 +8,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pgtable.h>
+#include <linux/slab.h>
 
 struct cma;
 
@@ -275,6 +276,32 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
+/*
+ * Check whether the given size, assuming it is for a kmalloc()'ed object, is
+ * safe for non-coherent DMA or needs bouncing.
+ */
+static inline bool dma_kmalloc_needs_bounce(struct device *dev, size_t size,
+					    enum dma_data_direction dir)
+{
+	/*
+	 * No need for bouncing if coherent DMA or the direction is
+	 * DMA_TO_DEVICE.
+	 */
+	if (!IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) ||
+	    dir == DMA_TO_DEVICE || dev_is_dma_coherent(dev))
+		return false;
+
+	/*
+	 * Larger kmalloc() sizes are guaranteed to be aligned to
+	 * ARCH_DMA_MINALIGN.
+	 */
+	if (size >= 2 * ARCH_DMA_MINALIGN ||
+	    IS_ALIGNED(kmalloc_size_roundup(size), dma_get_cache_alignment()))
+		return false;
+
+	return true;
+}
+
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e38ffc5e6bdd..97ec892ea0b5 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -94,7 +94,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
 
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+	if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+	    dma_kmalloc_needs_bounce(dev, size, dir)) {
 		if (is_pci_p2pdma_page(page))
 			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))


WARNING: multiple messages have this Message-ID (diff)
From: Catalin Marinas <catalin.marinas@arm.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Arnd Bergmann <arnd@arndb.de>, Christoph Hellwig <hch@lst.de>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Will Deacon <will@kernel.org>, Marc Zyngier <maz@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Ard Biesheuvel <ardb@kernel.org>,
	Isaac Manjarres <isaacmanjarres@google.com>,
	Saravana Kannan <saravanak@google.com>,
	Alasdair Kergon <agk@redhat.com>, Daniel Vetter <daniel@ffwll.ch>,
	Joerg Roedel <joro@8bytes.org>, Mark Brown <broonie@kernel.org>,
	Mike Snitzer <snitzer@kernel.org>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	linux-mm@kvack.org, iommu@lists.linux.dev,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v3 02/13] dma-mapping: Force bouncing if the kmalloc() size is not cacheline-aligned
Date: Sun,  6 Nov 2022 22:01:32 +0000	[thread overview]
Message-ID: <20221106220143.2129263-3-catalin.marinas@arm.com> (raw)
In-Reply-To: <20221106220143.2129263-1-catalin.marinas@arm.com>

For direct DMA, if the size is small enough to have originated from a
kmalloc() cache below ARCH_DMA_MINALIGN, check its alignment against
cache_line_size() and bounce if necessary. For larger sizes, it is the
responsibility of the DMA API caller to ensure proper alignment.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Robin Murphy <robin.murphy@arm.com>
---
 include/linux/dma-map-ops.h | 27 +++++++++++++++++++++++++++
 kernel/dma/direct.h         |  3 ++-
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index d678afeb8a13..785f7aa90f57 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,6 +8,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pgtable.h>
+#include <linux/slab.h>
 
 struct cma;
 
@@ -275,6 +276,32 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
+/*
+ * Check whether the given size, assuming it is for a kmalloc()'ed object, is
+ * safe for non-coherent DMA or needs bouncing.
+ */
+static inline bool dma_kmalloc_needs_bounce(struct device *dev, size_t size,
+					    enum dma_data_direction dir)
+{
+	/*
+	 * No need for bouncing if coherent DMA or the direction is
+	 * DMA_TO_DEVICE.
+	 */
+	if (!IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) ||
+	    dir == DMA_TO_DEVICE || dev_is_dma_coherent(dev))
+		return false;
+
+	/*
+	 * Larger kmalloc() sizes are guaranteed to be aligned to
+	 * ARCH_DMA_MINALIGN.
+	 */
+	if (size >= 2 * ARCH_DMA_MINALIGN ||
+	    IS_ALIGNED(kmalloc_size_roundup(size), dma_get_cache_alignment()))
+		return false;
+
+	return true;
+}
+
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index e38ffc5e6bdd..97ec892ea0b5 100644
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -94,7 +94,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 		return swiotlb_map(dev, phys, size, dir, attrs);
 	}
 
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+	if (unlikely(!dma_capable(dev, dma_addr, size, true)) ||
+	    dma_kmalloc_needs_bounce(dev, size, dir)) {
 		if (is_pci_p2pdma_page(page))
 			return DMA_MAPPING_ERROR;
 		if (is_swiotlb_active(dev))

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2022-11-06 22:02 UTC|newest]

Thread overview: 90+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-06 22:01 [PATCH v3 00/13] mm, dma, arm64: Reduce ARCH_KMALLOC_MINALIGN to 8 Catalin Marinas
2022-11-06 22:01 ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 01/13] mm/slab: Decouple ARCH_KMALLOC_MINALIGN from ARCH_DMA_MINALIGN Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` Catalin Marinas [this message]
2022-11-06 22:01   ` [PATCH v3 02/13] dma-mapping: Force bouncing if the kmalloc() size is not cacheline-aligned Catalin Marinas
2022-11-07  9:43   ` Christoph Hellwig
2022-11-07  9:43     ` Christoph Hellwig
2022-11-06 22:01 ` [PATCH v3 03/13] iommu/dma: Force bouncing of the " Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-07  9:46   ` Christoph Hellwig
2022-11-07  9:46     ` Christoph Hellwig
2022-11-07 10:54     ` Catalin Marinas
2022-11-07 10:54       ` Catalin Marinas
2022-11-07 13:26       ` Robin Murphy
2022-11-07 13:26         ` Robin Murphy
2022-11-08 10:51         ` Catalin Marinas
2022-11-08 10:51           ` Catalin Marinas
2022-11-08 11:40           ` Robin Murphy
2022-11-08 11:40             ` Robin Murphy
2022-11-08  7:50       ` Christoph Hellwig
2022-11-08  7:50         ` Christoph Hellwig
2022-11-14 23:23   ` Isaac Manjarres
2022-11-14 23:23     ` Isaac Manjarres
2022-11-15 11:48     ` Catalin Marinas
2022-11-15 11:48       ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 04/13] mm/slab: Allow kmalloc() minimum alignment fallback to dma_get_cache_alignment() Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-07  0:50   ` kernel test robot
2022-11-07  9:22     ` Catalin Marinas
2022-11-07  9:22       ` Catalin Marinas
2022-11-07  1:51   ` kernel test robot
2022-11-06 22:01 ` [PATCH v3 05/13] mm/slab: Simplify create_kmalloc_cache() args and make it static Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 06/13] dma: Allow the smaller cache_line_size() returned by dma_get_cache_alignment() Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 07/13] drivers/base: Use ARCH_DMA_MINALIGN instead of ARCH_KMALLOC_MINALIGN Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 08/13] drivers/gpu: " Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 09/13] drivers/usb: " Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 10/13] drivers/spi: " Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-07 12:58   ` Mark Brown
2022-11-07 12:58     ` Mark Brown
2022-11-06 22:01 ` [PATCH v3 11/13] crypto: " Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-07  2:22   ` Herbert Xu
2022-11-07  2:22     ` Herbert Xu
2022-11-07  9:05     ` Catalin Marinas
2022-11-07  9:05       ` Catalin Marinas
2022-11-07  9:12       ` Herbert Xu
2022-11-07  9:12         ` Herbert Xu
2022-11-07  9:38         ` Catalin Marinas
2022-11-07  9:38           ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 12/13] drivers/md: " Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-06 22:01 ` [PATCH v3 13/13] dma: arm64: Add CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC and enable it for arm64 Catalin Marinas
2022-11-06 22:01   ` Catalin Marinas
2022-11-07 13:03   ` Robin Murphy
2022-11-07 13:03     ` Robin Murphy
2022-11-07 14:38     ` Christoph Hellwig
2022-11-07 14:38       ` Christoph Hellwig
2022-11-07 15:24       ` Robin Murphy
2022-11-07 15:24         ` Robin Murphy
2022-11-08  9:52     ` Catalin Marinas
2022-11-08  9:52       ` Catalin Marinas
2022-11-08 10:03       ` Christoph Hellwig
2022-11-08 10:03         ` Christoph Hellwig
2022-11-30 18:48         ` Isaac Manjarres
2022-11-30 18:48           ` Isaac Manjarres
2022-11-30 23:32           ` Alexander Graf
2022-11-30 23:32             ` Alexander Graf
2023-04-20 11:51             ` Petr Tesařík
2023-04-20 11:51               ` Petr Tesařík
2023-03-16 18:38 ` [PATCH v3 00/13] mm, dma, arm64: Reduce ARCH_KMALLOC_MINALIGN to 8 Isaac Manjarres
2023-03-16 18:38   ` Isaac Manjarres
2023-04-19 16:06   ` Catalin Marinas
2023-04-19 16:06     ` Catalin Marinas
2023-04-20  9:52     ` Petr Tesarik
2023-04-20  9:52       ` Petr Tesarik
2023-04-20 17:43       ` Catalin Marinas
2023-04-20 17:43         ` Catalin Marinas
2023-05-15 19:09     ` Isaac Manjarres
2023-05-15 19:09       ` Isaac Manjarres
2023-05-16 17:19       ` Catalin Marinas
2023-05-16 17:19         ` Catalin Marinas
2023-05-16 18:19         ` Isaac Manjarres
2023-05-16 18:19           ` Isaac Manjarres

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221106220143.2129263-3-catalin.marinas@arm.com \
    --to=catalin.marinas@arm.com \
    --cc=agk@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=arnd@arndb.de \
    --cc=broonie@kernel.org \
    --cc=daniel@ffwll.ch \
    --cc=gregkh@linuxfoundation.org \
    --cc=hch@lst.de \
    --cc=herbert@gondor.apana.org.au \
    --cc=iommu@lists.linux.dev \
    --cc=isaacmanjarres@google.com \
    --cc=joro@8bytes.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=maz@kernel.org \
    --cc=rafael@kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=saravanak@google.com \
    --cc=snitzer@kernel.org \
    --cc=torvalds@linux-foundation.org \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.