summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/relocation.c
diff options
context:
space:
mode:
authorJosef Bacik <josef@redhat.com>2011-08-30 12:34:28 -0400
committerJosef Bacik <josef@redhat.com>2011-10-19 15:12:44 -0400
commit4a92b1b8d2810db4ea0c34616b94c0b3810fa027 (patch)
treedd01cff1987b8178be84f8b750951497b7f525a7 /fs/btrfs/relocation.c
parentd02c9955ded7fc56dd1edc987558b084ccb03eb4 (diff)
Btrfs: stop passing a trans handle all around the reservation code
The only thing that we need to have a trans handle for is in reserve_metadata_bytes and thats to know how much flushing we can do. So instead of passing it around, just check current->journal_info for a trans_handle so we know if we can commit a transaction to try and free up space or not. Thanks, Signed-off-by: Josef Bacik <josef@redhat.com>
Diffstat (limited to 'fs/btrfs/relocation.c')
-rw-r--r--fs/btrfs/relocation.c15
1 files changed, 7 insertions, 8 deletions
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index fd9ac66434b0..3ab67409f90f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2041,8 +2041,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
2041 BUG_ON(IS_ERR(trans)); 2041 BUG_ON(IS_ERR(trans));
2042 trans->block_rsv = rc->block_rsv; 2042 trans->block_rsv = rc->block_rsv;
2043 2043
2044 ret = btrfs_block_rsv_check(trans, root, rc->block_rsv, 2044 ret = btrfs_block_rsv_check(root, rc->block_rsv, min_reserved,
2045 min_reserved, 0, 0); 2045 0, 0);
2046 if (ret) { 2046 if (ret) {
2047 BUG_ON(ret != -EAGAIN); 2047 BUG_ON(ret != -EAGAIN);
2048 ret = btrfs_commit_transaction(trans, root); 2048 ret = btrfs_commit_transaction(trans, root);
@@ -2152,8 +2152,7 @@ int prepare_to_merge(struct reloc_control *rc, int err)
2152again: 2152again:
2153 if (!err) { 2153 if (!err) {
2154 num_bytes = rc->merging_rsv_size; 2154 num_bytes = rc->merging_rsv_size;
2155 ret = btrfs_block_rsv_add(NULL, root, rc->block_rsv, 2155 ret = btrfs_block_rsv_add(root, rc->block_rsv, num_bytes);
2156 num_bytes);
2157 if (ret) 2156 if (ret)
2158 err = ret; 2157 err = ret;
2159 } 2158 }
@@ -2427,7 +2426,7 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
2427 num_bytes = calcu_metadata_size(rc, node, 1) * 2; 2426 num_bytes = calcu_metadata_size(rc, node, 1) * 2;
2428 2427
2429 trans->block_rsv = rc->block_rsv; 2428 trans->block_rsv = rc->block_rsv;
2430 ret = btrfs_block_rsv_add(trans, root, rc->block_rsv, num_bytes); 2429 ret = btrfs_block_rsv_add(root, rc->block_rsv, num_bytes);
2431 if (ret) { 2430 if (ret) {
2432 if (ret == -EAGAIN) 2431 if (ret == -EAGAIN)
2433 rc->commit_transaction = 1; 2432 rc->commit_transaction = 1;
@@ -3645,7 +3644,7 @@ int prepare_to_relocate(struct reloc_control *rc)
3645 * btrfs_init_reloc_root will use them when there 3644 * btrfs_init_reloc_root will use them when there
3646 * is no reservation in transaction handle. 3645 * is no reservation in transaction handle.
3647 */ 3646 */
3648 ret = btrfs_block_rsv_add(NULL, rc->extent_root, rc->block_rsv, 3647 ret = btrfs_block_rsv_add(rc->extent_root, rc->block_rsv,
3649 rc->extent_root->nodesize * 256); 3648 rc->extent_root->nodesize * 256);
3650 if (ret) 3649 if (ret)
3651 return ret; 3650 return ret;
@@ -3774,8 +3773,8 @@ restart:
3774 } 3773 }
3775 } 3774 }
3776 3775
3777 ret = btrfs_block_rsv_check(trans, rc->extent_root, 3776 ret = btrfs_block_rsv_check(rc->extent_root, rc->block_rsv, 0,
3778 rc->block_rsv, 0, 5, 0); 3777 5, 0);
3779 if (ret < 0) { 3778 if (ret < 0) {
3780 if (ret != -EAGAIN) { 3779 if (ret != -EAGAIN) {
3781 err = ret; 3780 err = ret;
'n728' href='#n728'>728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925
/*
 * Dynamic DMA mapping 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>
 * Copyright (C) 2000, 2003 Hewlett-Packard Co
 *	David Mosberger-Tang <davidm@hpl.hp.com>
 *
 * 03/05/07 davidm	Switch from PCI-DMA to generic device DMA API.
 * 00/12/13 davidm	Rename to swiotlb.c and add mark_clean() to avoid
 *			unnecessary i-cache flushing.
 * 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>
#include <linux/dma-mapping.h>
#include <linux/mm.h>
#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>
#include <asm/scatterlist.h>

#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/iommu-helper.h>

#define OFFSET(val,align) ((unsigned long)	\
	                   ( (val) & ( (align) - 1)))

#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))

/*
 * Minimum IO TLB size to bother booting with.  Systems with mainly
 * 64bit capable cards will only lightly use the swiotlb.  If we can't
 * allocate a contiguous 1MB, we're probably in trouble anyway.
 */
#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)

/*
 * Enumeration for sync targets
 */
enum dma_sync_target {
	SYNC_FOR_CPU = 0,
	SYNC_FOR_DEVICE = 1,
};

int swiotlb_force;

/*
 * 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;

/*
 * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and
 * io_tlb_end.  This is command line adjustable via setup_io_tlb_npages.
 */
static unsigned long io_tlb_nslabs;

/*
 * When the IOMMU overflows we return a fallback buffer. This sets the size.
 */
static unsigned long io_tlb_overflow = 32*1024;

void *io_tlb_overflow_buffer;

/*
 * This is a free list describing the number of free entries available from
 * each index
 */
static unsigned int *io_tlb_list;
static unsigned int io_tlb_index;

/*
 * We need to save away the original address corresponding to a mapped entry
 * for the sync operations.
 */
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 __init
setup_io_tlb_npages(char *str)
{
	if (isdigit(*str)) {
		io_tlb_nslabs = simple_strtoul(str, &str, 0);
		/* avoid tail segment of size < IO_TLB_SEGSIZE */
		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
	}
	if (*str == ',')
		++str;
	if (!strcmp(str, "force"))
		swiotlb_force = 1;
	return 1;
}
__setup("swiotlb=", setup_io_tlb_npages);
/* make io_tlb_overflow tunable too? */

void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
{
	return alloc_bootmem_low_pages(size);
}

void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
{
	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
}

dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
{
	return paddr;
}

phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
{
	return baddr;
}

static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
				      volatile void *address)
{
	return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
}

static void *swiotlb_bus_to_virt(dma_addr_t address)
{
	return phys_to_virt(swiotlb_bus_to_phys(address));
}

int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
{
	return 0;
}

static void swiotlb_print_info(unsigned long bytes)
{
	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)
{
	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 = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
	if (!io_tlb_start)
		panic("Cannot allocate SWIOTLB buffer");
	io_tlb_end = io_tlb_start + bytes;

	/*
	 * Allocate and initialize the free list array.  This array is used
	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
	 * between io_tlb_start and io_tlb_end.
	 */
	io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
	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(phys_addr_t));

	/*
	 * 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");

	swiotlb_print_info(bytes);
}

void __init
swiotlb_init(void)
{
	swiotlb_init_with_default_size(64 * (1<<20));	/* default to 64MB */
}

/*
 * Systems with larger DMA zones (those that don't support ISA) can
 * initialize the swiotlb later using the slab allocator if needed.
 * This should be just like above, but with some error catching.
 */
int
swiotlb_late_init_with_default_size(size_t default_size)
{
	unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
	unsigned int order;

	if (!io_tlb_nslabs) {
		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
	}

	/*
	 * Get IO TLB memory from the low pages
	 */
	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 = swiotlb_alloc(order, io_tlb_nslabs);
		if (io_tlb_start)
			break;
		order--;
	}

	if (!io_tlb_start)
		goto cleanup1;

	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 + bytes;
	memset(io_tlb_start, 0, bytes);

	/*
	 * Allocate and initialize the free list array.  This array is used
	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
	 * between io_tlb_start and io_tlb_end.
	 */
	io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
	                              get_order(io_tlb_nslabs * sizeof(int)));
	if (!io_tlb_list)
		goto cleanup2;

	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 = (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(phys_addr_t));

	/*
	 * Get the overflow emergency buffer
	 */
	io_tlb_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
	                                          get_order(io_tlb_overflow));
	if (!io_tlb_overflow_buffer)
		goto cleanup4;

	swiotlb_print_info(bytes);

	return 0;

cleanup4:
	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 *
	                                                 sizeof(int)));
	io_tlb_list = NULL;
cleanup2:
	io_tlb_end = NULL;
	free_pages((unsigned long)io_tlb_start, order);
	io_tlb_start = NULL;
cleanup1:
	io_tlb_nslabs = req_nslabs;
	return -ENOMEM;
}

static int
address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
{
	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
}

static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
{
	return swiotlb_force || swiotlb_arch_range_needs_mapping(paddr, size);
}

static int is_swiotlb_buffer(char *addr)
{
	return addr >= io_tlb_start && addr < 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(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, 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
	 * hence alignment) to a page size.
	 */
	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
	if (size > PAGE_SIZE)
		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
	else
		stride = 1;

	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);
	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 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);

			/*
			 * 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);

not_found:
	spin_unlock_irqrestore(&io_tlb_lock, flags);
	return NULL;
found:
	spin_unlock_irqrestore(&io_tlb_lock, flags);

	/*
	 * Save away the mapping from the original address to the DMA address.
	 * This is needed when we sync the memory.  Then we sync the buffer if
	 * needed.
	 */
	for (i = 0; i < nslots; i++)
		io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT);
	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
		swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);

	return dma_addr;
}

/*
 * 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)
{
	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;
	phys_addr_t phys = io_tlb_orig_addr[index];

	/*
	 * First, sync the memory before unmapping the entry
	 */
	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.
	 * While returning the entries to the free list, we merge the entries
	 * with slots below and above the pool being returned.
	 */
	spin_lock_irqsave(&io_tlb_lock, flags);
	{
		count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
			 io_tlb_list[index + nslots] : 0);
		/*
		 * Step 1: return the slots to the free list, merging the
		 * slots with superceeding slots
		 */
		for (i = index + nslots - 1; i >= index; i--)
			io_tlb_list[i] = ++count;
		/*
		 * Step 2: merge the returned slots with the preceding slots,
		 * if available (non zero)
		 */
		for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
			io_tlb_list[i] = ++count;
	}
	spin_unlock_irqrestore(&io_tlb_lock, flags);
}

static void
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;
	phys_addr_t phys = io_tlb_orig_addr[index];

	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))
			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))
			swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
		else
			BUG_ON(dir != DMA_FROM_DEVICE);
		break;
	default:
		BUG();
	}
}

void *
swiotlb_alloc_coherent(struct device *hwdev, size_t size,
		       dma_addr_t *dma_handle, gfp_t flags)
{
	dma_addr_t dev_addr;
	void *ret;
	int order = get_order(size);
	u64 dma_mask = DMA_BIT_MASK(32);

	if (hwdev && hwdev->coherent_dma_mask)
		dma_mask = hwdev->coherent_dma_mask;

	ret = (void *)__get_free_pages(flags, order);
	if (ret &&
	    !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(hwdev, ret),
				   size)) {
		/*
		 * The allocated memory isn't reachable by the device.
		 */
		free_pages((unsigned long) ret, order);
		ret = NULL;
	}
	if (!ret) {
		/*
		 * We are either out of memory or the device can't DMA
		 * to GFP_DMA memory; fall back on map_single(), which
		 * will grab memory from the lowest available address range.
		 */
		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
		if (!ret)
			return NULL;
	}

	memset(ret, 0, size);
	dev_addr = swiotlb_virt_to_bus(hwdev, ret);

	/* Confirm address can be DMA'd by device */
	if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
		       (unsigned long long)dma_mask,
		       (unsigned long long)dev_addr);

		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
		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)
{
	WARN_ON(irqs_disabled());
	if (!is_swiotlb_buffer(vaddr))
		free_pages((unsigned long) vaddr, get_order(size));
	else
		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
		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)
{
	/*
	 * Ran out of IOMMU space for this operation. This is very bad.
	 * Unfortunately the drivers cannot handle this operation properly.
	 * unless they check for dma_mapping_error (most don't)
	 * 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 %zu bytes at "
	       "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");
	}
}

/*
 * Map a single buffer of the indicated size for DMA in streaming mode.  The
 * physical address to use is returned.
 *
 * Once the device is given the dma address, the device owns this memory until
 * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
 */
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)
{
	phys_addr_t phys = page_to_phys(page) + offset;
	void *ptr = page_address(page) + offset;
	dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
	void *map;

	BUG_ON(dir == DMA_NONE);
	/*
	 * 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(dev, dev_addr, size) &&
	    !range_needs_mapping(virt_to_phys(ptr), size))
		return dev_addr;

	/*
	 * Oh well, have to allocate and map a bounce buffer.
	 */
	map = map_single(dev, phys, size, dir);
	if (!map) {
		swiotlb_full(dev, size, dir, 1);
		map = io_tlb_overflow_buffer;
	}

	dev_addr = swiotlb_virt_to_bus(dev, map);

	/*
	 * Ensure that the address returned is DMA'ble
	 */
	if (address_needs_mapping(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_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_page(struct device *hwdev, dma_addr_t dev_addr,
			size_t size, enum dma_data_direction dir,
			struct dma_attrs *attrs)
{
	char *dma_addr = swiotlb_bus_to_virt(dev_addr);

	BUG_ON(dir == DMA_NONE);
	if (is_swiotlb_buffer(dma_addr))
		unmap_single(hwdev, dma_addr, size, dir);
	else if (dir == DMA_FROM_DEVICE)
		dma_mark_clean(dma_addr, size);
}
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_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
 * swiotlb_dma_sync_for_device, and then the device again owns the buffer
 */
static void
swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
		    size_t size, int dir, int target)
{
	char *dma_addr = swiotlb_bus_to_virt(dev_addr);

	BUG_ON(dir == DMA_NONE);
	if (is_swiotlb_buffer(dma_addr))
		sync_single(hwdev, dma_addr, size, dir, target);
	else if (dir == DMA_FROM_DEVICE)
		dma_mark_clean(dma_addr, size);
}

void
swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
			    size_t size, enum dma_data_direction dir)
{