From: Alexander Lobakin <aleksander.lobakin@intel.com>
To: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: Alexander Lobakin <aleksander.lobakin@intel.com>,
Christoph Hellwig <hch@lst.de>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Robin Murphy <robin.murphy@arm.com>,
Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
"Rafael J. Wysocki" <rafael@kernel.org>,
Magnus Karlsson <magnus.karlsson@intel.com>,
nex.sw.ncis.osdt.itp.upstreaming@intel.com, bpf@vger.kernel.org,
netdev@vger.kernel.org, iommu@lists.linux.dev,
linux-kernel@vger.kernel.org
Subject: [PATCH net-next v5 1/7] dma: compile-out DMA sync op calls when not used
Date: Mon, 6 May 2024 11:48:49 +0200 [thread overview]
Message-ID: <20240506094855.12944-2-aleksander.lobakin@intel.com> (raw)
In-Reply-To: <20240506094855.12944-1-aleksander.lobakin@intel.com>
Some platforms do have DMA, but DMA there is always direct and coherent.
Currently, even on such platforms DMA sync operations are compiled and
called.
Add a new hidden Kconfig symbol, DMA_NEED_SYNC, and set it only when
either sync operations are needed or there is DMA ops or swiotlb
or DMA debug is enabled. Compile global dma_sync_*() and dma_need_sync()
only when it's set, otherwise provide empty inline stubs.
The change allows for future optimizations of DMA sync calls depending
on runtime conditions.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
kernel/dma/Kconfig | 5 +++
include/linux/dma-mapping.h | 62 ++++++++++++++++++++-----------------
kernel/dma/mapping.c | 22 +++++++------
3 files changed, 50 insertions(+), 39 deletions(-)
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index d62f5957f36b..c06e56be0ca1 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -107,6 +107,11 @@ config DMA_BOUNCE_UNALIGNED_KMALLOC
bool
depends on SWIOTLB
+config DMA_NEED_SYNC
+ def_bool ARCH_HAS_SYNC_DMA_FOR_DEVICE || ARCH_HAS_SYNC_DMA_FOR_CPU || \
+ ARCH_HAS_SYNC_DMA_FOR_CPU_ALL || DMA_API_DEBUG || DMA_OPS || \
+ SWIOTLB
+
config DMA_RESTRICTED_POOL
bool "DMA Restricted Pool"
depends on OF && OF_RESERVED_MEM && SWIOTLB
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4a658de44ee9..a569b56b25e2 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -117,14 +117,6 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
size_t size, enum dma_data_direction dir, unsigned long attrs);
void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
enum dma_data_direction dir, unsigned long attrs);
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
- enum dma_data_direction dir);
-void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir);
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir);
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir);
void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t flag, unsigned long attrs);
void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
@@ -147,7 +139,6 @@ u64 dma_get_required_mask(struct device *dev);
bool dma_addressing_limited(struct device *dev);
size_t dma_max_mapping_size(struct device *dev);
size_t dma_opt_mapping_size(struct device *dev);
-bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
unsigned long dma_get_merge_boundary(struct device *dev);
struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
@@ -195,22 +186,6 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
}
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
- size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_sync_single_for_device(struct device *dev,
- dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sg, int nelems, enum dma_data_direction dir)
-{
-}
-static inline void dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sg, int nelems, enum dma_data_direction dir)
-{
-}
static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
return -ENOMEM;
@@ -277,10 +252,6 @@ static inline size_t dma_opt_mapping_size(struct device *dev)
{
return 0;
}
-static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
-{
- return false;
-}
static inline unsigned long dma_get_merge_boundary(struct device *dev)
{
return 0;
@@ -310,6 +281,39 @@ static inline int dma_mmap_noncontiguous(struct device *dev,
}
#endif /* CONFIG_HAS_DMA */
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+ enum dma_data_direction dir);
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir);
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir);
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir);
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
+#else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
+static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir)
+{
+}
+static inline void dma_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+}
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sg, int nelems, enum dma_data_direction dir)
+{
+}
+static inline void dma_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sg, int nelems, enum dma_data_direction dir)
+{
+}
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+ return false;
+}
+#endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
+
struct page *dma_alloc_pages(struct device *dev, size_t size,
dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
void dma_free_pages(struct device *dev, size_t size, struct page *page,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 58db8fd70471..c78b78e95a26 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -329,6 +329,7 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
}
EXPORT_SYMBOL(dma_unmap_resource);
+#ifdef CONFIG_DMA_NEED_SYNC
void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
enum dma_data_direction dir)
{
@@ -385,6 +386,17 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
}
EXPORT_SYMBOL(dma_sync_sg_for_device);
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+ const struct dma_map_ops *ops = get_dma_ops(dev);
+
+ if (dma_map_direct(dev, ops))
+ return dma_direct_need_sync(dev, dma_addr);
+ return ops->sync_single_for_cpu || ops->sync_single_for_device;
+}
+EXPORT_SYMBOL_GPL(dma_need_sync);
+#endif /* CONFIG_DMA_NEED_SYNC */
+
/*
* The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
* that the intention is to allow exporting memory allocated via the
@@ -841,16 +853,6 @@ size_t dma_opt_mapping_size(struct device *dev)
}
EXPORT_SYMBOL_GPL(dma_opt_mapping_size);
-bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
-{
- const struct dma_map_ops *ops = get_dma_ops(dev);
-
- if (dma_map_direct(dev, ops))
- return dma_direct_need_sync(dev, dma_addr);
- return ops->sync_single_for_cpu || ops->sync_single_for_device;
-}
-EXPORT_SYMBOL_GPL(dma_need_sync);
-
unsigned long dma_get_merge_boundary(struct device *dev)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
--
2.45.0
next prev parent reply other threads:[~2024-05-06 9:49 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-06 9:48 [PATCH net-next v5 0/7] dma: skip calling no-op sync ops when possible Alexander Lobakin
2024-05-06 9:48 ` Alexander Lobakin [this message]
2024-05-06 9:48 ` [PATCH net-next v5 2/7] dma: avoid redundant calls for sync operations Alexander Lobakin
2024-05-06 9:48 ` [PATCH net-next v5 3/7] iommu/dma: avoid expensive indirect " Alexander Lobakin
2024-05-06 9:48 ` [PATCH net-next v5 4/7] page_pool: make sure frag API fields don't span between cachelines Alexander Lobakin
2024-05-06 9:48 ` [PATCH net-next v5 5/7] page_pool: don't use driver-set flags field directly Alexander Lobakin
2024-05-06 9:48 ` [PATCH net-next v5 6/7] page_pool: check for DMA sync shortcut earlier Alexander Lobakin
2024-05-06 11:50 ` Christoph Hellwig
2024-05-07 9:51 ` Alexander Lobakin
2024-05-07 10:41 ` Christoph Hellwig
2024-05-06 9:48 ` [PATCH net-next v5 7/7] xsk: use generic DMA sync shortcut instead of a custom one Alexander Lobakin
2024-05-06 18:29 ` Jakub Kicinski
2024-05-07 10:06 ` Alexander Lobakin
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=20240506094855.12944-2-aleksander.lobakin@intel.com \
--to=aleksander.lobakin@intel.com \
--cc=bpf@vger.kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hch@lst.de \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=m.szyprowski@samsung.com \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--cc=nex.sw.ncis.osdt.itp.upstreaming@intel.com \
--cc=pabeni@redhat.com \
--cc=rafael@kernel.org \
--cc=robin.murphy@arm.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).