swiotlb: Add support for DMA_ATTR_SKIP_CPU_SYNC
As a first step to making DMA_ATTR_SKIP_CPU_SYNC apply to architectures
beyond just ARM I need to make it so that the swiotlb will respect the
flag. In order to do that I also need to update the swiotlb-xen since it
heavily makes use of the functionality.
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad@kernel.org>
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index bdcc0d8..8e883c7 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -425,7 +425,8 @@
phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
dma_addr_t tbl_dma_addr,
phys_addr_t orig_addr, size_t size,
- enum dma_data_direction dir)
+ enum dma_data_direction dir,
+ unsigned long attrs)
{
unsigned long flags;
phys_addr_t tlb_addr;
@@ -526,7 +527,8 @@
*/
for (i = 0; i < nslots; i++)
io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
- if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
return tlb_addr;
@@ -539,18 +541,20 @@
static phys_addr_t
map_single(struct device *hwdev, phys_addr_t phys, size_t size,
- enum dma_data_direction dir)
+ enum dma_data_direction dir, unsigned long attrs)
{
dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
- return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir);
+ return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
+ dir, attrs);
}
/*
* dma_addr is the kernel virtual address of the bounce buffer to unmap.
*/
void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
- size_t size, enum dma_data_direction dir)
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
{
unsigned long flags;
int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
@@ -561,6 +565,7 @@
* First, sync the memory before unmapping the entry
*/
if (orig_addr != INVALID_PHYS_ADDR &&
+ !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
@@ -654,7 +659,8 @@
* GFP_DMA memory; fall back on map_single(), which
* will grab memory from the lowest available address range.
*/
- phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
+ phys_addr_t paddr = map_single(hwdev, 0, size,
+ DMA_FROM_DEVICE, 0);
if (paddr == SWIOTLB_MAP_ERROR)
goto err_warn;
@@ -667,9 +673,13 @@
(unsigned long long)dma_mask,
(unsigned long long)dev_addr);
- /* DMA_TO_DEVICE to avoid memcpy in unmap_single */
+ /*
+ * DMA_TO_DEVICE to avoid memcpy in unmap_single.
+ * The DMA_ATTR_SKIP_CPU_SYNC is optional.
+ */
swiotlb_tbl_unmap_single(hwdev, paddr,
- size, DMA_TO_DEVICE);
+ size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
goto err_warn;
}
}
@@ -698,8 +708,12 @@
if (!is_swiotlb_buffer(paddr))
free_pages((unsigned long)vaddr, get_order(size));
else
- /* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */
- swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE);
+ /*
+ * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
+ * DMA_ATTR_SKIP_CPU_SYNC is optional.
+ */
+ swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
}
EXPORT_SYMBOL(swiotlb_free_coherent);
@@ -755,7 +769,7 @@
trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
/* Oh well, have to allocate and map a bounce buffer. */
- map = map_single(dev, phys, size, dir);
+ map = map_single(dev, phys, size, dir, attrs);
if (map == SWIOTLB_MAP_ERROR) {
swiotlb_full(dev, size, dir, 1);
return phys_to_dma(dev, io_tlb_overflow_buffer);
@@ -764,12 +778,13 @@
dev_addr = phys_to_dma(dev, map);
/* Ensure that the address returned is DMA'ble */
- if (!dma_capable(dev, dev_addr, size)) {
- swiotlb_tbl_unmap_single(dev, map, size, dir);
- return phys_to_dma(dev, io_tlb_overflow_buffer);
- }
+ if (dma_capable(dev, dev_addr, size))
+ return dev_addr;
- return dev_addr;
+ swiotlb_tbl_unmap_single(dev, map, size, dir,
+ attrs | DMA_ATTR_SKIP_CPU_SYNC);
+
+ return phys_to_dma(dev, io_tlb_overflow_buffer);
}
EXPORT_SYMBOL_GPL(swiotlb_map_page);
@@ -782,14 +797,15 @@
* whatever the device wrote there.
*/
static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir)
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
{
phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
BUG_ON(dir == DMA_NONE);
if (is_swiotlb_buffer(paddr)) {
- swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
+ swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
return;
}
@@ -809,7 +825,7 @@
size_t size, enum dma_data_direction dir,
unsigned long attrs)
{
- unmap_single(hwdev, dev_addr, size, dir);
+ unmap_single(hwdev, dev_addr, size, dir, attrs);
}
EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
@@ -891,7 +907,7 @@
if (swiotlb_force ||
!dma_capable(hwdev, dev_addr, sg->length)) {
phys_addr_t map = map_single(hwdev, sg_phys(sg),
- sg->length, dir);
+ sg->length, dir, attrs);
if (map == SWIOTLB_MAP_ERROR) {
/* Don't panic here, we expect map_sg users
to do proper error handling. */
@@ -925,7 +941,8 @@
BUG_ON(dir == DMA_NONE);
for_each_sg(sgl, sg, nelems, i)
- unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir);
+ unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
+ attrs);
}
EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);