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>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
"Rafael J. Wysocki" <rafael@kernel.org>,
Magnus Karlsson <magnus.karlsson@intel.com>,
Maciej Fijalkowski <maciej.fijalkowski@intel.com>,
Alexander Duyck <alexanderduyck@fb.com>,
bpf@vger.kernel.org, netdev@vger.kernel.org,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org
Subject: [PATCH net-next v2 1/7] dma: compile-out DMA sync op calls when not used
Date: Mon, 5 Feb 2024 12:04:20 +0100 [thread overview]
Message-ID: <20240205110426.764393-2-aleksander.lobakin@intel.com> (raw)
In-Reply-To: <20240205110426.764393-1-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
enabled. Set dma_need_sync() and dma_skip_sync() depending on this
symbol state and don't call sync ops when dma_skip_sync() is true.
The change allows for future optimizations of DMA sync calls depending
on compile-time or runtime conditions.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
kernel/dma/Kconfig | 4 ++
include/linux/dma-mapping.h | 118 ++++++++++++++++++++++++++++--------
kernel/dma/mapping.c | 28 ++++-----
3 files changed, 110 insertions(+), 40 deletions(-)
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index d62f5957f36b..1c9ff05b1ecb 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -107,6 +107,10 @@ 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_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..569a4da68f56 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -117,14 +117,14 @@ 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_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 +147,7 @@ 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);
+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);
@@ -195,20 +195,24 @@ 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_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_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_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 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)
@@ -277,7 +281,7 @@ 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)
+static inline bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr)
{
return false;
}
@@ -348,18 +352,80 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
return dma_unmap_page_attrs(dev, addr, size, dir, attrs);
}
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
- dma_addr_t addr, unsigned long offset, size_t size,
- enum dma_data_direction dir)
+static inline void
+__dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t addr,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir)
+{
+ __dma_sync_single_for_cpu(dev, addr + offset, size, dir);
+}
+
+static inline void
+__dma_sync_single_range_for_device(struct device *dev, dma_addr_t addr,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir)
+{
+ __dma_sync_single_for_device(dev, addr + offset, size, dir);
+}
+
+static inline bool dma_skip_sync(const struct device *dev)
+{
+ return !IS_ENABLED(CONFIG_DMA_NEED_SYNC);
+}
+
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+ return !dma_skip_sync(dev) ? __dma_need_sync(dev, dma_addr) : false;
+}
+
+static inline void dma_sync_single_for_cpu(struct device *dev,
+ dma_addr_t addr, size_t size,
+ enum dma_data_direction dir)
+{
+ if (!dma_skip_sync(dev))
+ __dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size,
+ enum dma_data_direction dir)
+{
+ if (!dma_skip_sync(dev))
+ __dma_sync_single_for_device(dev, addr, size, dir);
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sg, int nelems,
+ enum dma_data_direction dir)
+{
+ if (!dma_skip_sync(dev))
+ __dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+
+static inline void dma_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sg, int nelems,
+ enum dma_data_direction dir)
+{
+ if (!dma_skip_sync(dev))
+ __dma_sync_sg_for_device(dev, sg, nelems, dir);
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t addr,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir)
{
- return dma_sync_single_for_cpu(dev, addr + offset, size, dir);
+ if (!dma_skip_sync(dev))
+ __dma_sync_single_for_cpu(dev, addr + offset, size, dir);
}
-static inline void dma_sync_single_range_for_device(struct device *dev,
- dma_addr_t addr, unsigned long offset, size_t size,
- enum dma_data_direction dir)
+static inline void
+dma_sync_single_range_for_device(struct device *dev, dma_addr_t addr,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir)
{
- return dma_sync_single_for_device(dev, addr + offset, size, dir);
+ if (!dma_skip_sync(dev))
+ __dma_sync_single_for_device(dev, addr + offset, size, dir);
}
/**
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 58db8fd70471..8716e5e8281c 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -329,8 +329,8 @@ void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
}
EXPORT_SYMBOL(dma_unmap_resource);
-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_cpu(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -341,10 +341,10 @@ void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
ops->sync_single_for_cpu(dev, addr, size, dir);
debug_dma_sync_single_for_cpu(dev, addr, size, dir);
}
-EXPORT_SYMBOL(dma_sync_single_for_cpu);
+EXPORT_SYMBOL(__dma_sync_single_for_cpu);
-void dma_sync_single_for_device(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)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -355,10 +355,10 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
ops->sync_single_for_device(dev, addr, size, dir);
debug_dma_sync_single_for_device(dev, addr, size, dir);
}
-EXPORT_SYMBOL(dma_sync_single_for_device);
+EXPORT_SYMBOL(__dma_sync_single_for_device);
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
- int nelems, enum dma_data_direction dir)
+void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -369,10 +369,10 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
ops->sync_sg_for_cpu(dev, sg, nelems, dir);
debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
}
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
+EXPORT_SYMBOL(__dma_sync_sg_for_cpu);
-void dma_sync_sg_for_device(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)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -383,7 +383,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
ops->sync_sg_for_device(dev, sg, nelems, dir);
debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
}
-EXPORT_SYMBOL(dma_sync_sg_for_device);
+EXPORT_SYMBOL(__dma_sync_sg_for_device);
/*
* The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
@@ -841,7 +841,7 @@ 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)
+bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
@@ -849,7 +849,7 @@ bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
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);
+EXPORT_SYMBOL_GPL(__dma_need_sync);
unsigned long dma_get_merge_boundary(struct device *dev)
{
--
2.43.0
next prev parent reply other threads:[~2024-02-05 11:05 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-05 11:04 [PATCH net-next v2 0/7] dma: skip calling no-op sync ops when possible Alexander Lobakin
2024-02-05 11:04 ` Alexander Lobakin [this message]
2024-02-13 5:57 ` [PATCH net-next v2 1/7] dma: compile-out DMA sync op calls when not used Christoph Hellwig
2024-02-13 10:14 ` Alexander Lobakin
2024-02-05 11:04 ` [PATCH net-next v2 2/7] dma: avoid redundant calls for sync operations Alexander Lobakin
2024-02-13 6:11 ` Christoph Hellwig
2024-02-13 10:19 ` Alexander Lobakin
2024-02-05 11:04 ` [PATCH net-next v2 3/7] iommu/dma: avoid expensive indirect " Alexander Lobakin
2024-02-05 11:04 ` [PATCH net-next v2 4/7] page_pool: make sure frag API fields don't span between cachelines Alexander Lobakin
2024-02-05 11:04 ` [PATCH net-next v2 5/7] page_pool: don't use driver-set flags field directly Alexander Lobakin
2024-02-05 11:04 ` [PATCH net-next v2 6/7] page_pool: check for DMA sync shortcut earlier Alexander Lobakin
2024-02-05 11:04 ` [PATCH net-next v2 7/7] xsk: use generic DMA sync shortcut instead of a custom one 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=20240205110426.764393-2-aleksander.lobakin@intel.com \
--to=aleksander.lobakin@intel.com \
--cc=alexanderduyck@fb.com \
--cc=bpf@vger.kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=gregkh@linuxfoundation.org \
--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=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--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