/*
* Dynamic DMA mapping support.
*
- * This implementation is for IA-64 and EM64T platforms that do not support
+ * This implementation is a fallback for platforms that do not support
* I/O TLBs (aka DMA address translation hardware).
* Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
* Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
#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_PHYS_ADDRESS(SG) virt_to_phys(SG_ENT_VIRT_ADDRESS(SG))
+#define SG_ENT_VIRT_ADDRESS(sg) (sg_virt((sg)))
+#define SG_ENT_PHYS_ADDRESS(sg) virt_to_bus(SG_ENT_VIRT_ADDRESS(sg))
/*
* Maximum allowable number of contiguous slabs to map,
* Statically reserve bounce buffer space and initialize bounce buffer data
* structures for the software IO TLB used to implement the DMA API.
*/
-void
-swiotlb_init_with_default_size (size_t default_size)
+void __init
+swiotlb_init_with_default_size(size_t default_size)
{
- unsigned long i;
+ unsigned long i, bytes;
if (!io_tlb_nslabs) {
io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
}
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
/*
* Get IO TLB memory from the low pages
*/
- io_tlb_start = alloc_bootmem_low_pages(io_tlb_nslabs * (1 << IO_TLB_SHIFT));
+ io_tlb_start = alloc_bootmem_low_pages(bytes);
if (!io_tlb_start)
panic("Cannot allocate SWIOTLB buffer");
- io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);
+ io_tlb_end = io_tlb_start + bytes;
/*
* Allocate and initialize the free list array. This array is used
* Get the overflow emergency buffer
*/
io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
+ if (!io_tlb_overflow_buffer)
+ panic("Cannot allocate SWIOTLB overflow buffer!\n");
+
printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n",
- virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
+ virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end));
}
-void
-swiotlb_init (void)
+void __init
+swiotlb_init(void)
{
swiotlb_init_with_default_size(64 * (1<<20)); /* default to 64MB */
}
* This should be just like above, but with some error catching.
*/
int
-swiotlb_late_init_with_default_size (size_t default_size)
+swiotlb_late_init_with_default_size(size_t default_size)
{
- unsigned long i, req_nslabs = io_tlb_nslabs;
+ unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
unsigned int order;
if (!io_tlb_nslabs) {
/*
* Get IO TLB memory from the low pages
*/
- order = get_order(io_tlb_nslabs * (1 << IO_TLB_SHIFT));
+ order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
io_tlb_nslabs = SLABS_PER_PAGE << order;
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
if (!io_tlb_start)
goto cleanup1;
- if (order != get_order(io_tlb_nslabs * (1 << IO_TLB_SHIFT))) {
+ if (order != get_order(bytes)) {
printk(KERN_WARNING "Warning: only able to allocate %ld MB "
"for software IO TLB\n", (PAGE_SIZE << order) >> 20);
io_tlb_nslabs = SLABS_PER_PAGE << order;
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
}
- io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);
- memset(io_tlb_start, 0, io_tlb_nslabs * (1 << IO_TLB_SHIFT));
+ io_tlb_end = io_tlb_start + bytes;
+ memset(io_tlb_start, 0, bytes);
/*
* Allocate and initialize the free list array. This array is used
if (!io_tlb_overflow_buffer)
goto cleanup4;
- printk(KERN_INFO "Placing %ldMB software IO TLB between 0x%lx - "
- "0x%lx\n", (io_tlb_nslabs * (1 << IO_TLB_SHIFT)) >> 20,
- virt_to_phys(io_tlb_start), virt_to_phys(io_tlb_end));
+ printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - "
+ "0x%lx\n", bytes >> 20,
+ virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end));
return 0;
free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
sizeof(int)));
io_tlb_list = NULL;
- io_tlb_end = NULL;
cleanup2:
+ io_tlb_end = NULL;
free_pages((unsigned long)io_tlb_start, order);
io_tlb_start = NULL;
cleanup1:
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
else
stride = 1;
- if (!nslots)
- BUG();
+ BUG_ON(!nslots);
/*
* Find suitable number of IO TLB entries size that will fit this
* 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))
memcpy(buffer, dma_addr, size);
- else if (dir != DMA_TO_DEVICE)
- BUG();
+ else
+ BUG_ON(dir != DMA_TO_DEVICE);
break;
case SYNC_FOR_DEVICE:
if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
memcpy(dma_addr, buffer, size);
- else if (dir != DMA_FROM_DEVICE)
- BUG();
+ else
+ BUG_ON(dir != DMA_FROM_DEVICE);
break;
default:
BUG();
swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags)
{
- unsigned long dev_addr;
+ dma_addr_t dev_addr;
void *ret;
int order = get_order(size);
flags |= GFP_DMA;
ret = (void *)__get_free_pages(flags, order);
- if (ret && address_needs_mapping(hwdev, virt_to_phys(ret))) {
+ if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) {
/*
* The allocated memory isn't reachable by the device.
* Fall back on swiotlb_map_single().
*/
dma_addr_t handle;
handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE);
- if (dma_mapping_error(handle))
+ if (swiotlb_dma_mapping_error(handle))
return NULL;
- ret = phys_to_virt(handle);
+ ret = bus_to_virt(handle);
}
memset(ret, 0, size);
- dev_addr = virt_to_phys(ret);
+ dev_addr = virt_to_bus(ret);
/* Confirm address can be DMA'd by device */
if (address_needs_mapping(hwdev, dev_addr)) {
- printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016lx\n",
- (unsigned long long)*hwdev->dma_mask, dev_addr);
+ printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+ (unsigned long long)*hwdev->dma_mask,
+ (unsigned long long)dev_addr);
panic("swiotlb_alloc_coherent: allocated memory is out of "
"range for device");
}
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));
* When the mapping is small enough return a static buffer to limit
* the damage, or panic when the transfer is too big.
*/
- printk(KERN_ERR "DMA: Out of SW-IOMMU space for %lu bytes at "
+ printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
"device %s\n", size, dev ? dev->bus_id : "?");
if (size > io_tlb_overflow && do_panic) {
* 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)
{
- unsigned long dev_addr = virt_to_phys(ptr);
+ dma_addr_t dev_addr = virt_to_bus(ptr);
void *map;
- if (dir == DMA_NONE)
- BUG();
+ BUG_ON(dir == DMA_NONE);
/*
* If the pointer passed in happens to be in the device's DMA window,
* we can safely return the device addr and not worry about bounce
map = io_tlb_overflow_buffer;
}
- dev_addr = virt_to_phys(map);
+ dev_addr = virt_to_bus(map);
/*
* Ensure that the address returned is DMA'ble
return dev_addr;
}
+EXPORT_SYMBOL(swiotlb_map_single_attrs);
-/*
- * Since DMA is i-cache coherent, any (complete) pages that were written via
- * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
- * flush them when they get mapped into an executable vm-area.
- */
-static void
-mark_clean(void *addr, size_t size)
+dma_addr_t
+swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
{
- unsigned long pg_addr, end;
-
- pg_addr = PAGE_ALIGN((unsigned long) addr);
- end = (unsigned long) addr + size;
- while (pg_addr + PAGE_SIZE <= end) {
- struct page *page = virt_to_page(pg_addr);
- set_bit(PG_arch_1, &page->flags);
- pg_addr += PAGE_SIZE;
- }
+ return swiotlb_map_single_attrs(hwdev, ptr, size, dir, NULL);
}
/*
* 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 = phys_to_virt(dev_addr);
+ char *dma_addr = bus_to_virt(dev_addr);
- if (dir == DMA_NONE)
- BUG();
+ BUG_ON(dir == DMA_NONE);
if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
unmap_single(hwdev, dma_addr, size, dir);
else if (dir == DMA_FROM_DEVICE)
- mark_clean(dma_addr, size);
+ 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)
{
- char *dma_addr = phys_to_virt(dev_addr);
+ char *dma_addr = bus_to_virt(dev_addr);
- if (dir == DMA_NONE)
- BUG();
+ BUG_ON(dir == DMA_NONE);
if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
sync_single(hwdev, dma_addr, size, dir, target);
else if (dir == DMA_FROM_DEVICE)
- mark_clean(dma_addr, size);
+ dma_mark_clean(dma_addr, size);
}
void
/*
* 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)
{
- char *dma_addr = phys_to_virt(dev_addr) + offset;
+ char *dma_addr = bus_to_virt(dev_addr) + offset;
- if (dir == DMA_NONE)
- BUG();
+ BUG_ON(dir == DMA_NONE);
if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
sync_single(hwdev, dma_addr, size, dir, target);
else if (dir == DMA_FROM_DEVICE)
- mark_clean(dma_addr, size);
+ dma_mark_clean(dma_addr, size);
}
void
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;
- unsigned long dev_addr;
+ dma_addr_t dev_addr;
int i;
- if (dir == DMA_NONE)
- BUG();
+ 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_phys(addr);
+ dev_addr = virt_to_bus(addr);
if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
void *map = map_single(hwdev, addr, sg->length, dir);
- sg->dma_address = virt_to_bus(map);
if (!map) {
/* 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);
} else
sg->dma_address = dev_addr;
sg->dma_length = sg->length;
}
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;
- if (dir == DMA_NONE)
- BUG();
+ 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, (void *) phys_to_virt(sg->dma_address), sg->dma_length, dir);
+ unmap_single(hwdev, bus_to_virt(sg->dma_address),
+ sg->dma_length, dir);
else if (dir == DMA_FROM_DEVICE)
- mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+ 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;
- if (dir == DMA_NONE)
- BUG();
+ 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, (void *) sg->dma_address,
+ 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
int
swiotlb_dma_mapping_error(dma_addr_t dma_addr)
{
- return (dma_addr == virt_to_phys(io_tlb_overflow_buffer));
+ return (dma_addr == virt_to_bus(io_tlb_overflow_buffer));
}
/*
* this function.
*/
int
-swiotlb_dma_supported (struct device *hwdev, u64 mask)
+swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
- return (virt_to_phys (io_tlb_end) - 1) <= mask;
+ 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);