Commit b4174173 authored by Christoph Hellwig's avatar Christoph Hellwig

dma-mapping: inline the fast path dma-direct calls

Inline the single page map/unmap/sync dma-direct calls into the now
out of line generic wrappers.  This restores the behavior of a single
function call that we had before moving the generic calls out of line.
Besides the dma-mapping callers there are just a few callers in IOMMU
drivers that have a bypass mode, and more of those are going to be
switched to the generic bypass soon.
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
Tested-by: default avatarAlexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: default avatarAlexey Kardashevskiy <aik@ozlabs.ru>
parent d3fa60d7
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Internals of the DMA direct mapping implementation. Only for use by the
* DMA mapping code and IOMMU drivers.
*/
#ifndef _LINUX_DMA_DIRECT_H
#define _LINUX_DMA_DIRECT_H 1
#include <linux/dma-mapping.h>
#include <linux/dma-noncoherent.h>
#include <linux/memblock.h> /* for min_low_pfn */
#include <linux/mem_encrypt.h>
#include <linux/swiotlb.h>
extern unsigned int zone_dma_bits;
......@@ -87,25 +93,17 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long attrs);
int dma_direct_supported(struct device *dev, u64 mask);
bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size, enum dma_data_direction dir,
unsigned long attrs);
int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
enum dma_data_direction dir, unsigned long attrs);
dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
size_t size, enum dma_data_direction dir, unsigned long attrs);
size_t dma_direct_max_mapping_size(struct device *dev);
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
defined(CONFIG_SWIOTLB)
void dma_direct_sync_single_for_device(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir);
void dma_direct_sync_sg_for_device(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir);
void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
int nents, enum dma_data_direction dir);
#else
static inline void dma_direct_sync_single_for_device(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
}
static inline void dma_direct_sync_sg_for_device(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
{
......@@ -115,34 +113,82 @@ static inline void dma_direct_sync_sg_for_device(struct device *dev,
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
defined(CONFIG_SWIOTLB)
void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
size_t size, enum dma_data_direction dir, unsigned long attrs);
void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
int nents, enum dma_data_direction dir, unsigned long attrs);
void dma_direct_sync_single_for_cpu(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir);
void dma_direct_sync_sg_for_cpu(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir);
#else
static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
}
static inline void dma_direct_unmap_sg(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir,
unsigned long attrs)
{
}
static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
{
}
#endif
static inline void dma_direct_sync_single_for_device(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
phys_addr_t paddr = dma_to_phys(dev, addr);
if (unlikely(is_swiotlb_buffer(paddr)))
swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
if (!dev_is_dma_coherent(dev))
arch_sync_dma_for_device(paddr, size, dir);
}
static inline void dma_direct_sync_single_for_cpu(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
phys_addr_t paddr = dma_to_phys(dev, addr);
if (!dev_is_dma_coherent(dev)) {
arch_sync_dma_for_cpu(paddr, size, dir);
arch_sync_dma_for_cpu_all();
}
if (unlikely(is_swiotlb_buffer(paddr)))
swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
}
static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
static inline dma_addr_t dma_direct_map_page(struct device *dev,
struct page *page, unsigned long offset, size_t size,
enum dma_data_direction dir, unsigned long attrs)
{
phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dma_addr = phys_to_dma(dev, phys);
if (unlikely(swiotlb_force == SWIOTLB_FORCE))
return swiotlb_map(dev, phys, size, dir, attrs);
if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
if (swiotlb_force != SWIOTLB_NO_FORCE)
return swiotlb_map(dev, phys, size, dir, attrs);
dev_WARN_ONCE(dev, 1,
"DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
return DMA_MAPPING_ERROR;
}
if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
arch_sync_dma_for_device(phys, size, dir);
return dma_addr;
}
#endif
size_t dma_direct_max_mapping_size(struct device *dev);
static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
phys_addr_t phys = dma_to_phys(dev, addr);
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
dma_direct_sync_single_for_cpu(dev, addr, size, dir);
if (unlikely(is_swiotlb_buffer(phys)))
swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
}
#endif /* _LINUX_DMA_DIRECT_H */
......@@ -10,11 +10,9 @@
#include <linux/dma-direct.h>
#include <linux/scatterlist.h>
#include <linux/dma-contiguous.h>
#include <linux/dma-noncoherent.h>
#include <linux/pfn.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
#include <linux/swiotlb.h>
/*
* Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
......@@ -304,18 +302,6 @@ void dma_direct_free(struct device *dev, size_t size,
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
defined(CONFIG_SWIOTLB)
void dma_direct_sync_single_for_device(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
phys_addr_t paddr = dma_to_phys(dev, addr);
if (unlikely(is_swiotlb_buffer(paddr)))
swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
if (!dev_is_dma_coherent(dev))
arch_sync_dma_for_device(paddr, size, dir);
}
void dma_direct_sync_sg_for_device(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
{
......@@ -339,20 +325,6 @@ void dma_direct_sync_sg_for_device(struct device *dev,
#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
defined(CONFIG_SWIOTLB)
void dma_direct_sync_single_for_cpu(struct device *dev,
dma_addr_t addr, size_t size, enum dma_data_direction dir)
{
phys_addr_t paddr = dma_to_phys(dev, addr);
if (!dev_is_dma_coherent(dev)) {
arch_sync_dma_for_cpu(paddr, size, dir);
arch_sync_dma_for_cpu_all();
}
if (unlikely(is_swiotlb_buffer(paddr)))
swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
}
void dma_direct_sync_sg_for_cpu(struct device *dev,
struct scatterlist *sgl, int nents, enum dma_data_direction dir)
{
......@@ -374,18 +346,6 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
arch_sync_dma_for_cpu_all();
}
void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
phys_addr_t phys = dma_to_phys(dev, addr);
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
dma_direct_sync_single_for_cpu(dev, addr, size, dir);
if (unlikely(is_swiotlb_buffer(phys)))
swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
}
void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
int nents, enum dma_data_direction dir, unsigned long attrs)
{
......@@ -398,31 +358,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
}
#endif
dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
phys_addr_t phys = page_to_phys(page) + offset;
dma_addr_t dma_addr = phys_to_dma(dev, phys);
if (unlikely(swiotlb_force == SWIOTLB_FORCE))
return swiotlb_map(dev, phys, size, dir, attrs);
if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
if (swiotlb_force != SWIOTLB_NO_FORCE)
return swiotlb_map(dev, phys, size, dir, attrs);
dev_WARN_ONCE(dev, 1,
"DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
return DMA_MAPPING_ERROR;
}
if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
arch_sync_dma_for_device(phys, size, dir);
return dma_addr;
}
int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
enum dma_data_direction dir, unsigned long attrs)
{
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment