#include <linux/init.h>
#include <linux/bootmem.h>
+#include <linux/iommu-helper.h>
#define OFFSET(val,align) ((unsigned long) \
( (val) & ( (align) - 1)))
-#define SG_ENT_VIRT_ADDRESS(sg) (page_address((sg)->page) + (sg)->offset)
+#define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg)))
#define SG_ENT_PHYS_ADDRESS(sg) virt_to_bus(SG_ENT_VIRT_ADDRESS(sg))
/*
return -ENOMEM;
}
-static inline int
+static int
address_needs_mapping(struct device *hwdev, dma_addr_t addr)
{
dma_addr_t mask = 0xffffffff;
char *dma_addr;
unsigned int nslots, stride, index, wrap;
int i;
+ unsigned long start_dma_addr;
+ unsigned long mask;
+ unsigned long offset_slots;
+ unsigned long max_slots;
+
+ mask = dma_get_seg_boundary(hwdev);
+ start_dma_addr = virt_to_bus(io_tlb_start) & mask;
+
+ offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ max_slots = mask + 1
+ ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
+ : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
/*
* For mappings greater than a page, we limit the stride (and
* request and allocate a buffer from that IO TLB pool.
*/
spin_lock_irqsave(&io_tlb_lock, flags);
- {
- wrap = index = ALIGN(io_tlb_index, stride);
+ index = ALIGN(io_tlb_index, stride);
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ wrap = index;
+
+ do {
+ while (iommu_is_span_boundary(index, nslots, offset_slots,
+ max_slots)) {
+ index += stride;
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ if (index == wrap)
+ goto not_found;
+ }
- if (index >= io_tlb_nslabs)
- wrap = index = 0;
+ /*
+ * If we find a slot that indicates we have 'nslots' number of
+ * contiguous buffers, we allocate the buffers from that slot
+ * and mark the entries as '0' indicating unavailable.
+ */
+ if (io_tlb_list[index] >= nslots) {
+ int count = 0;
+
+ for (i = index; i < (int) (index + nslots); i++)
+ io_tlb_list[i] = 0;
+ for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+ dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);
- do {
/*
- * If we find a slot that indicates we have 'nslots'
- * number of contiguous buffers, we allocate the
- * buffers from that slot and mark the entries as '0'
- * indicating unavailable.
+ * Update the indices to avoid searching in the next
+ * round.
*/
- if (io_tlb_list[index] >= nslots) {
- int count = 0;
-
- for (i = index; i < (int) (index + nslots); i++)
- io_tlb_list[i] = 0;
- for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
- io_tlb_list[i] = ++count;
- dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);
-
- /*
- * Update the indices to avoid searching in
- * the next round.
- */
- io_tlb_index = ((index + nslots) < io_tlb_nslabs
- ? (index + nslots) : 0);
-
- goto found;
- }
- index += stride;
- if (index >= io_tlb_nslabs)
- index = 0;
- } while (index != wrap);
+ io_tlb_index = ((index + nslots) < io_tlb_nslabs
+ ? (index + nslots) : 0);
- spin_unlock_irqrestore(&io_tlb_lock, flags);
- return NULL;
- }
- found:
+ goto found;
+ }
+ index += stride;
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ } while (index != wrap);
+
+not_found:
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+ return NULL;
+found:
spin_unlock_irqrestore(&io_tlb_lock, flags);
/*
* This is needed when we sync the memory. Then we sync the buffer if
* needed.
*/
- io_tlb_orig_addr[index] = buffer;
+ for (i = 0; i < nslots; i++)
+ io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT);
if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
memcpy(dma_addr, buffer, size);
int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
char *buffer = io_tlb_orig_addr[index];
+ buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
+
switch (target) {
case SYNC_FOR_CPU:
if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
dma_addr_t dma_handle)
{
+ WARN_ON(irqs_disabled());
if (!(vaddr >= (void *)io_tlb_start
&& vaddr < (void *)io_tlb_end))
free_pages((unsigned long) vaddr, get_order(size));
* either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
*/
dma_addr_t
-swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
+swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
+ int dir, struct dma_attrs *attrs)
{
dma_addr_t dev_addr = virt_to_bus(ptr);
void *map;
return dev_addr;
}
+EXPORT_SYMBOL(swiotlb_map_single_attrs);
+
+dma_addr_t
+swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
+{
+ return swiotlb_map_single_attrs(hwdev, ptr, size, dir, NULL);
+}
/*
* Unmap a single streaming mode DMA translation. The dma_addr and size must
* whatever the device wrote there.
*/
void
-swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
- int dir)
+swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, int dir, struct dma_attrs *attrs)
{
char *dma_addr = bus_to_virt(dev_addr);
else if (dir == DMA_FROM_DEVICE)
dma_mark_clean(dma_addr, size);
}
+EXPORT_SYMBOL(swiotlb_unmap_single_attrs);
+void
+swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
+ int dir)
+{
+ return swiotlb_unmap_single_attrs(hwdev, dev_addr, size, dir, NULL);
+}
/*
* Make physical memory consistent for a single streaming mode DMA translation
* after a transfer.
* address back to the card, you must first perform a
* swiotlb_dma_sync_for_device, and then the device again owns the buffer
*/
-static inline void
+static void
swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, int dir, int target)
{
/*
* Same as above, but for a sub-range of the mapping.
*/
-static inline void
+static void
swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
unsigned long offset, size_t size,
int dir, int target)
SYNC_FOR_DEVICE);
}
+void swiotlb_unmap_sg_attrs(struct device *, struct scatterlist *, int, int,
+ struct dma_attrs *);
/*
* Map a set of buffers described by scatterlist in streaming mode for DMA.
* This is the scatter-gather version of the above swiotlb_map_single
* same here.
*/
int
-swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
- int dir)
+swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
+ int dir, struct dma_attrs *attrs)
{
+ struct scatterlist *sg;
void *addr;
dma_addr_t dev_addr;
int i;
BUG_ON(dir == DMA_NONE);
- for (i = 0; i < nelems; i++, sg++) {
+ for_each_sg(sgl, sg, nelems, i) {
addr = SG_ENT_VIRT_ADDRESS(sg);
dev_addr = virt_to_bus(addr);
if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
/* Don't panic here, we expect map_sg users
to do proper error handling. */
swiotlb_full(hwdev, sg->length, dir, 0);
- swiotlb_unmap_sg(hwdev, sg - i, i, dir);
- sg[0].dma_length = 0;
+ swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+ attrs);
+ sgl[0].dma_length = 0;
return 0;
}
sg->dma_address = virt_to_bus(map);
}
return nelems;
}
+EXPORT_SYMBOL(swiotlb_map_sg_attrs);
+
+int
+swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+ int dir)
+{
+ return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
+}
/*
* Unmap a set of streaming mode DMA translations. Again, cpu read rules
* concerning calls here are the same as for swiotlb_unmap_single() above.
*/
void
-swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
- int dir)
+swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+ int nelems, int dir, struct dma_attrs *attrs)
{
+ struct scatterlist *sg;
int i;
BUG_ON(dir == DMA_NONE);
- for (i = 0; i < nelems; i++, sg++)
+ for_each_sg(sgl, sg, nelems, i) {
if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
unmap_single(hwdev, bus_to_virt(sg->dma_address),
sg->dma_length, dir);
else if (dir == DMA_FROM_DEVICE)
dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+ }
+}
+EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
+
+void
+swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
+ int dir)
+{
+ return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
}
/*
* The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
* and usage.
*/
-static inline void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
+static void
+swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
int nelems, int dir, int target)
{
+ struct scatterlist *sg;
int i;
BUG_ON(dir == DMA_NONE);
- for (i = 0; i < nelems; i++, sg++)
+ for_each_sg(sgl, sg, nelems, i) {
if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
sync_single(hwdev, bus_to_virt(sg->dma_address),
sg->dma_length, dir, target);
else if (dir == DMA_FROM_DEVICE)
dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+ }
}
void
return virt_to_bus(io_tlb_end - 1) <= mask;
}
-EXPORT_SYMBOL(swiotlb_init);
EXPORT_SYMBOL(swiotlb_map_single);
EXPORT_SYMBOL(swiotlb_unmap_single);
EXPORT_SYMBOL(swiotlb_map_sg);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff