X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=lib%2Fswiotlb.c;h=437eedb5a53ba1feae04f98b5def86798462f920;hp=30c1400e749e8299be6767e32e9f3531ae18a0a4;hb=e071041be037eca208b62b84469a06bdfc692bea;hpb=aa24886e379d2b641c5117e178b15ce1d5d366ba

diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 30c1400..437eedb 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -14,6 +14,7 @@
  * 04/07/.. ak		Better overflow handling. Assorted fixes.
  * 05/09/10 linville	Add support for syncing ranges, support syncing for
  *			DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ * 08/12/11 beckyb	Add highmem support
  */
 
 #include <linux/cache.h>
@@ -22,8 +23,11 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/swiotlb.h>
+#include <linux/pfn.h>
 #include <linux/types.h>
 #include <linux/ctype.h>
+#include <linux/highmem.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
@@ -31,26 +35,11 @@
 
 #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_bus(SG_ENT_VIRT_ADDRESS(sg))
-
-/*
- * Maximum allowable number of contiguous slabs to map,
- * must be a power of 2.  What is the appropriate value ?
- * The complexity of {map,unmap}_single is linearly dependent on this value.
- */
-#define IO_TLB_SEGSIZE	128
-
-/*
- * log of the size of each IO TLB slab.  The number of slabs is command line
- * controllable.
- */
-#define IO_TLB_SHIFT 11
-
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 
 /*
@@ -71,8 +60,8 @@ enum dma_sync_target {
 int swiotlb_force;
 
 /*
- * Used to do a quick range check in swiotlb_unmap_single and
- * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
+ * Used to do a quick range check in unmap_single and
+ * sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
 static char *io_tlb_start, *io_tlb_end;
@@ -101,13 +90,15 @@ static unsigned int io_tlb_index;
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
  */
-static unsigned char **io_tlb_orig_addr;
+static phys_addr_t *io_tlb_orig_addr;
 
 /*
  * Protect the above data structures in the map and unmap calls
  */
 static DEFINE_SPINLOCK(io_tlb_lock);
 
+static int late_alloc;
+
 static int __init
 setup_io_tlb_npages(char *str)
 {
@@ -120,17 +111,40 @@ setup_io_tlb_npages(char *str)
 		++str;
 	if (!strcmp(str, "force"))
 		swiotlb_force = 1;
+
 	return 1;
 }
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
+/* Note that this doesn't work with highmem page */
+static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
+				      volatile void *address)
+{
+	return phys_to_dma(hwdev, virt_to_phys(address));
+}
+
+void swiotlb_print_info(void)
+{
+	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+	phys_addr_t pstart, pend;
+
+	pstart = virt_to_phys(io_tlb_start);
+	pend = virt_to_phys(io_tlb_end);
+
+	printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
+	       bytes >> 20, io_tlb_start, io_tlb_end);
+	printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
+	       (unsigned long long)pstart,
+	       (unsigned long long)pend);
+}
+
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
 void __init
-swiotlb_init_with_default_size(size_t default_size)
+swiotlb_init_with_default_size(size_t default_size, int verbose)
 {
 	unsigned long i, bytes;
 
@@ -158,7 +172,7 @@ swiotlb_init_with_default_size(size_t default_size)
 	for (i = 0; i < io_tlb_nslabs; i++)
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
 	io_tlb_index = 0;
-	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *));
+	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(phys_addr_t));
 
 	/*
 	 * Get the overflow emergency buffer
@@ -166,15 +180,14 @@ swiotlb_init_with_default_size(size_t default_size)
 	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_bus(io_tlb_start), virt_to_bus(io_tlb_end));
+	if (verbose)
+		swiotlb_print_info();
 }
 
 void __init
-swiotlb_init(void)
+swiotlb_init(int verbose)
 {
-	swiotlb_init_with_default_size(64 * (1<<20));	/* default to 64MB */
+	swiotlb_init_with_default_size(64 * (1<<20), verbose);	/* default to 64MB */
 }
 
 /*
@@ -201,8 +214,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
 	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,
-		                                        order);
+		io_tlb_start = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+							order);
 		if (io_tlb_start)
 			break;
 		order--;
@@ -234,12 +247,14 @@ swiotlb_late_init_with_default_size(size_t default_size)
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
 	io_tlb_index = 0;
 
-	io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL,
-	                           get_order(io_tlb_nslabs * sizeof(char *)));
+	io_tlb_orig_addr = (phys_addr_t *)
+		__get_free_pages(GFP_KERNEL,
+				 get_order(io_tlb_nslabs *
+					   sizeof(phys_addr_t)));
 	if (!io_tlb_orig_addr)
 		goto cleanup3;
 
-	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *));
+	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(phys_addr_t));
 
 	/*
 	 * Get the overflow emergency buffer
@@ -249,15 +264,15 @@ swiotlb_late_init_with_default_size(size_t default_size)
 	if (!io_tlb_overflow_buffer)
 		goto cleanup4;
 
-	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));
+	swiotlb_print_info();
+
+	late_alloc = 1;
 
 	return 0;
 
 cleanup4:
-	free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
-	                                                      sizeof(char *)));
+	free_pages((unsigned long)io_tlb_orig_addr,
+		   get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
 	io_tlb_orig_addr = NULL;
 cleanup3:
 	free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
@@ -272,26 +287,105 @@ cleanup1:
 	return -ENOMEM;
 }
 
-static int
-address_needs_mapping(struct device *hwdev, dma_addr_t addr)
+void __init swiotlb_free(void)
 {
-	dma_addr_t mask = 0xffffffff;
-	/* If the device has a mask, use it, otherwise default to 32 bits */
-	if (hwdev && hwdev->dma_mask)
-		mask = *hwdev->dma_mask;
-	return (addr & ~mask) != 0;
+	if (!io_tlb_overflow_buffer)
+		return;
+
+	if (late_alloc) {
+		free_pages((unsigned long)io_tlb_overflow_buffer,
+			   get_order(io_tlb_overflow));
+		free_pages((unsigned long)io_tlb_orig_addr,
+			   get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
+		free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+								 sizeof(int)));
+		free_pages((unsigned long)io_tlb_start,
+			   get_order(io_tlb_nslabs << IO_TLB_SHIFT));
+	} else {
+		free_bootmem_late(__pa(io_tlb_overflow_buffer),
+				  io_tlb_overflow);
+		free_bootmem_late(__pa(io_tlb_orig_addr),
+				  io_tlb_nslabs * sizeof(phys_addr_t));
+		free_bootmem_late(__pa(io_tlb_list),
+				  io_tlb_nslabs * sizeof(int));
+		free_bootmem_late(__pa(io_tlb_start),
+				  io_tlb_nslabs << IO_TLB_SHIFT);
+	}
+}
+
+static int is_swiotlb_buffer(phys_addr_t paddr)
+{
+	return paddr >= virt_to_phys(io_tlb_start) &&
+		paddr < virt_to_phys(io_tlb_end);
+}
+
+/*
+ * Bounce: copy the swiotlb buffer back to the original dma location
+ */
+static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
+			   enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(phys);
+
+	if (PageHighMem(pfn_to_page(pfn))) {
+		/* The buffer does not have a mapping.  Map it in and copy */
+		unsigned int offset = phys & ~PAGE_MASK;
+		char *buffer;
+		unsigned int sz = 0;
+		unsigned long flags;
+
+		while (size) {
+			sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+			local_irq_save(flags);
+			buffer = kmap_atomic(pfn_to_page(pfn),
+					     KM_BOUNCE_READ);
+			if (dir == DMA_TO_DEVICE)
+				memcpy(dma_addr, buffer + offset, sz);
+			else
+				memcpy(buffer + offset, dma_addr, sz);
+			kunmap_atomic(buffer, KM_BOUNCE_READ);
+			local_irq_restore(flags);
+
+			size -= sz;
+			pfn++;
+			dma_addr += sz;
+			offset = 0;
+		}
+	} else {
+		if (dir == DMA_TO_DEVICE)
+			memcpy(dma_addr, phys_to_virt(phys), size);
+		else
+			memcpy(phys_to_virt(phys), dma_addr, size);
+	}
 }
 
 /*
  * Allocates bounce buffer and returns its kernel virtual address.
  */
 static void *
-map_single(struct device *hwdev, char *buffer, size_t size, int dir)
+map_single(struct device *hwdev, phys_addr_t phys, size_t size, int dir)
 {
 	unsigned long flags;
 	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 = swiotlb_virt_to_bus(hwdev, io_tlb_start) & mask;
+
+	offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+
+	/*
+ 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
+ 	 */
+	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
@@ -310,46 +404,53 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	 * 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);
 
 	/*
@@ -358,9 +459,9 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	 * needed.
 	 */
 	for (i = 0; i < nslots; i++)
-		io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT);
+		io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-		memcpy(dma_addr, buffer, size);
+		swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
 
 	return dma_addr;
 }
@@ -369,26 +470,22 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
 static void
-unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 {
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	char *buffer = io_tlb_orig_addr[index];
+	phys_addr_t phys = io_tlb_orig_addr[index];
 
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		/*
-		 * bounce... copy the data back into the original buffer * and
-		 * delete the bounce buffer.
-		 */
-		memcpy(buffer, dma_addr, size);
+	if (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+		swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
-	 * entries to indicate the number of contigous entries available.
+	 * entries to indicate the number of contiguous entries available.
 	 * While returning the entries to the free list, we merge the entries
 	 * with slots below and above the pool being returned.
 	 */
@@ -417,20 +514,20 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 	    int dir, int target)
 {
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	char *buffer = io_tlb_orig_addr[index];
+	phys_addr_t phys = io_tlb_orig_addr[index];
 
-	buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
+	phys += ((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);
+			swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
 		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);
+			swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
 		else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
@@ -446,19 +543,15 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	dma_addr_t dev_addr;
 	void *ret;
 	int order = get_order(size);
+	u64 dma_mask = DMA_BIT_MASK(32);
 
-	/*
-	 * XXX fix me: the DMA API should pass us an explicit DMA mask
-	 * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32
-	 * bit range instead of a 16MB one).
-	 */
-	flags |= GFP_DMA;
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = hwdev->coherent_dma_mask;
 
 	ret = (void *)__get_free_pages(flags, order);
-	if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) {
+	if (ret && swiotlb_virt_to_bus(hwdev, ret) + size - 1 > dma_mask) {
 		/*
 		 * The allocated memory isn't reachable by the device.
-		 * Fall back on swiotlb_map_single().
 		 */
 		free_pages((unsigned long) ret, order);
 		ret = NULL;
@@ -466,45 +559,46 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	if (!ret) {
 		/*
 		 * We are either out of memory or the device can't DMA
-		 * to GFP_DMA memory; fall back on
-		 * swiotlb_map_single(), which will grab memory from
-		 * the lowest available address range.
+		 * to GFP_DMA memory; fall back on map_single(), which
+		 * will grab memory from the lowest available address range.
 		 */
-		dma_addr_t handle;
-		handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE);
-		if (swiotlb_dma_mapping_error(handle))
+		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
+		if (!ret)
 			return NULL;
-
-		ret = bus_to_virt(handle);
 	}
 
 	memset(ret, 0, size);
-	dev_addr = virt_to_bus(ret);
+	dev_addr = swiotlb_virt_to_bus(hwdev, ret);
 
 	/* Confirm address can be DMA'd by device */
-	if (address_needs_mapping(hwdev, dev_addr)) {
+	if (dev_addr + size - 1 > dma_mask) {
 		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
-		       (unsigned long long)*hwdev->dma_mask,
+		       (unsigned long long)dma_mask,
 		       (unsigned long long)dev_addr);
-		panic("swiotlb_alloc_coherent: allocated memory is out of "
-		      "range for device");
+
+		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
+		do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
+		return NULL;
 	}
 	*dma_handle = dev_addr;
 	return ret;
 }
+EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
 void
 swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-		      dma_addr_t dma_handle)
+		      dma_addr_t dev_addr)
 {
+	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
 	WARN_ON(irqs_disabled());
-	if (!(vaddr >= (void *)io_tlb_start
-                    && vaddr < (void *)io_tlb_end))
-		free_pages((unsigned long) vaddr, get_order(size));
+	if (!is_swiotlb_buffer(paddr))
+		free_pages((unsigned long)vaddr, get_order(size));
 	else
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-		swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE);
+		do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_free_coherent);
 
 static void
 swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
@@ -517,14 +611,17 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 	 * the damage, or panic when the transfer is too big.
 	 */
 	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
-	       "device %s\n", size, dev ? dev->bus_id : "?");
+	       "device %s\n", size, dev ? dev_name(dev) : "?");
 
-	if (size > io_tlb_overflow && do_panic) {
-		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
-			panic("DMA: Memory would be corrupted\n");
-		if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-			panic("DMA: Random memory would be DMAed\n");
-	}
+	if (size <= io_tlb_overflow || !do_panic)
+		return;
+
+	if (dir == DMA_BIDIRECTIONAL)
+		panic("DMA: Random memory could be DMA accessed\n");
+	if (dir == DMA_FROM_DEVICE)
+		panic("DMA: Random memory could be DMA written\n");
+	if (dir == DMA_TO_DEVICE)
+		panic("DMA: Random memory could be DMA read\n");
 }
 
 /*
@@ -532,69 +629,92 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
  * physical address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
  */
-dma_addr_t
-swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
+dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
+			    unsigned long offset, size_t size,
+			    enum dma_data_direction dir,
+			    struct dma_attrs *attrs)
 {
-	dma_addr_t dev_addr = virt_to_bus(ptr);
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dev_addr = phys_to_dma(dev, phys);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
 	/*
-	 * If the pointer passed in happens to be in the device's DMA window,
+	 * If the address happens to be in the device's DMA window,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
+	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
 		return dev_addr;
 
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
-	map = map_single(hwdev, ptr, size, dir);
+	map = map_single(dev, phys, size, dir);
 	if (!map) {
-		swiotlb_full(hwdev, size, dir, 1);
+		swiotlb_full(dev, size, dir, 1);
 		map = io_tlb_overflow_buffer;
 	}
 
-	dev_addr = virt_to_bus(map);
+	dev_addr = swiotlb_virt_to_bus(dev, map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (address_needs_mapping(hwdev, dev_addr))
+	if (!dma_capable(dev, dev_addr, size))
 		panic("map_single: bounce buffer is not DMA'ble");
 
 	return dev_addr;
 }
+EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_single call.  All
+ * match what was provided for in a previous swiotlb_map_page call.  All
  * other usages are undefined.
  *
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-void
-swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
-		     int dir)
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+			 size_t size, int dir)
 {
-	char *dma_addr = bus_to_virt(dev_addr);
+	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	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)
-		dma_mark_clean(dma_addr, size);
+
+	if (is_swiotlb_buffer(paddr)) {
+		do_unmap_single(hwdev, phys_to_virt(paddr), size, dir);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	/*
+	 * phys_to_virt doesn't work with hihgmem page but we could
+	 * call dma_mark_clean() with hihgmem page here. However, we
+	 * are fine since dma_mark_clean() is null on POWERPC. We can
+	 * make dma_mark_clean() take a physical address if necessary.
+	 */
+	dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+			size_t size, enum dma_data_direction dir,
+			struct dma_attrs *attrs)
+{
+	unmap_single(hwdev, dev_addr, size, dir);
 }
+EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
 
 /*
  * Make physical memory consistent for a single streaming mode DMA translation
  * after a transfer.
  *
- * If you perform a swiotlb_map_single() but wish to interrogate the buffer
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
  * using the cpu, yet do not wish to teardown the dma mapping, you must
  * call this function before doing so.  At the next point you give the dma
  * address back to the card, you must first perform a
@@ -604,28 +724,36 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 		    size_t size, int dir, int target)
 {
-	char *dma_addr = bus_to_virt(dev_addr);
+	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	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)
-		dma_mark_clean(dma_addr, size);
+
+	if (is_swiotlb_buffer(paddr)) {
+		sync_single(hwdev, phys_to_virt(paddr), size, dir, target);
+		return;
+	}
+
+	if (dir != DMA_FROM_DEVICE)
+		return;
+
+	dma_mark_clean(phys_to_virt(paddr), size);
 }
 
 void
 swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, int dir)
+			    size_t size, enum dma_data_direction dir)
 {
 	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
 
 void
 swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
-			       size_t size, int dir)
+			       size_t size, enum dma_data_direction dir)
 {
 	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_sync_single_for_device);
 
 /*
  * Same as above, but for a sub-range of the mapping.
@@ -635,34 +763,32 @@ 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 = bus_to_virt(dev_addr) + offset;
-
-	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)
-		dma_mark_clean(dma_addr, size);
+	swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target);
 }
 
 void
 swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-				  unsigned long offset, size_t size, int dir)
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction dir)
 {
 	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
 				  SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
 
 void
 swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
-				     unsigned long offset, size_t size, int dir)
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir)
 {
 	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
 				  SYNC_FOR_DEVICE);
 }
+EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 
 /*
  * 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
+ * This is the scatter-gather version of the above swiotlb_map_page
  * interface.  Here the scatter gather list elements are each tagged with the
  * appropriate dma address and length.  They are obtained via
  * sg_dma_{address,length}(SG).
@@ -673,59 +799,78 @@ swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
  *       The routine returns the number of addr/length pairs actually
  *       used, at most nents.
  *
- * Device ownership issues as mentioned above for swiotlb_map_single are the
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
  * 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,
+		     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	void *addr;
-	dma_addr_t dev_addr;
+	struct scatterlist *sg;
 	int i;
 
 	BUG_ON(dir == DMA_NONE);
 
-	for (i = 0; i < nelems; i++, sg++) {
-		addr = SG_ENT_VIRT_ADDRESS(sg);
-		dev_addr = virt_to_bus(addr);
-		if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
-			void *map = map_single(hwdev, addr, sg->length, dir);
+	for_each_sg(sgl, sg, nelems, i) {
+		phys_addr_t paddr = sg_phys(sg);
+		dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
+
+		if (swiotlb_force ||
+		    !dma_capable(hwdev, dev_addr, sg->length)) {
+			void *map = map_single(hwdev, sg_phys(sg),
+					       sg->length, dir);
 			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);
+			sg->dma_address = swiotlb_virt_to_bus(hwdev, 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);
+}
+EXPORT_SYMBOL(swiotlb_map_sg);
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_single() above.
+ * concerning calls here are the same as for swiotlb_unmap_page() 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, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
+	struct scatterlist *sg;
 	int i;
 
 	BUG_ON(dir == DMA_NONE);
 
-	for (i = 0; i < nelems; i++, sg++)
-		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);
+	for_each_sg(sgl, sg, nelems, i)
+		unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
 }
+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);
+}
+EXPORT_SYMBOL(swiotlb_unmap_sg);
 
 /*
  * Make physical memory consistent for a set of streaming mode DMA translations
@@ -735,40 +880,39 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
  * and usage.
  */
 static void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
+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++)
-		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
-			sync_single(hwdev, bus_to_virt(sg->dma_address),
+	for_each_sg(sgl, sg, nelems, i)
+		swiotlb_sync_single(hwdev, 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
 swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			int nelems, int dir)
+			int nelems, enum dma_data_direction dir)
 {
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
 
 void
 swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-			   int nelems, int dir)
+			   int nelems, enum dma_data_direction dir)
 {
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
 
 int
-swiotlb_dma_mapping_error(dma_addr_t dma_addr)
+swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 {
-	return (dma_addr == virt_to_bus(io_tlb_overflow_buffer));
+	return (dma_addr == swiotlb_virt_to_bus(hwdev, io_tlb_overflow_buffer));
 }
+EXPORT_SYMBOL(swiotlb_dma_mapping_error);
 
 /*
  * Return whether the given device DMA address mask can be supported
@@ -779,20 +923,6 @@ swiotlb_dma_mapping_error(dma_addr_t dma_addr)
 int
 swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return virt_to_bus(io_tlb_end - 1) <= mask;
+	return swiotlb_virt_to_bus(hwdev, io_tlb_end - 1) <= mask;
 }
-
-EXPORT_SYMBOL(swiotlb_map_single);
-EXPORT_SYMBOL(swiotlb_unmap_single);
-EXPORT_SYMBOL(swiotlb_map_sg);
-EXPORT_SYMBOL(swiotlb_unmap_sg);
-EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
-EXPORT_SYMBOL(swiotlb_sync_single_for_device);
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
-EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
-EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
-EXPORT_SYMBOL(swiotlb_dma_mapping_error);
-EXPORT_SYMBOL(swiotlb_alloc_coherent);
-EXPORT_SYMBOL(swiotlb_free_coherent);
 EXPORT_SYMBOL(swiotlb_dma_supported);