swiotlb.c

h内核

	ret = (void *)__get_free_pages(flags, order);
	if (ret && address_needs_mapping(hwdev, virt_to_phys(ret))) {
		/*
		 * The allocated memory isn't reachable by the device.
		 * Fall back on swiotlb_map_single().
		 */
		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
		 * swiotlb_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 (dma_mapping_error(handle))
			return NULL;

		ret = phys_to_virt(handle);
	}

	memset(ret, 0, size);
	dev_addr = virt_to_phys(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);
		panic("swiotlb_alloc_coherent: allocated memory is out of "
		      "range for device");
	}
	*dma_handle = dev_addr;
	return ret;
}

void
swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
		      dma_addr_t dma_handle)
{
	if (!(vaddr >= (void *)io_tlb_start
                    && vaddr < (void *)io_tlb_end))
		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);
}

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 pci_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 "PCI-DMA: Out of SW-IOMMU space for %lu bytes at "
	       "device %s\n", size, dev ? dev->bus_id : "?");

	if (size > io_tlb_overflow && do_panic) {
		if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
			panic("PCI-DMA: Memory would be corrupted\n");
		if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
			panic("PCI-DMA: Random memory would be DMAed\n");
	}
}

/*
 * Map a single buffer of the indicated size for DMA in streaming mode.  The
 * PCI 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.
 */
dma_addr_t
swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
{
	unsigned long dev_addr = virt_to_phys(ptr);
	void *map;

	if (dir == DMA_NONE)
		BUG();
	/*
	 * 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
	 * buffering it.
	 */
	if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
		return dev_addr;

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

	dev_addr = virt_to_phys(map);

	/*
	 * Ensure that the address returned is DMA'ble
	 */
	if (address_needs_mapping(hwdev, dev_addr))
		panic("map_single: bounce buffer is not DMA'ble");

	return dev_addr;
}

/*
 * Since DMA is i-cache coherent, any (complete) pages that were written via
 * DMA can be marked as "clean" so that update_mmu_cache() doesn't have to
 * flush them when they get mapped into an executable vm-area.
 */
static void
mark_clean(void *addr, size_t size)
{
	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;
	}
}

/*
 * 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
 * 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)
{
	char *dma_addr = phys_to_virt(dev_addr);

	if (dir == DMA_NONE)
		BUG();
	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);
}

/*
 * 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
 * using the cpu, yet do not wish to teardown the PCI dma mapping, you must
 * call this function before doing so.  At the next point you give the PCI dma
 * address back to the card, you must first perform a
 * swiotlb_dma_sync_for_device, and then the device again owns the buffer
 */
void
swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
			    size_t size, int dir)
{
	char *dma_addr = phys_to_virt(dev_addr);

	if (dir == DMA_NONE)
		BUG();
	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
		sync_single(hwdev, dma_addr, size, dir);
	else if (dir == DMA_FROM_DEVICE)
		mark_clean(dma_addr, size);
}

void
swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
			       size_t size, int dir)
{
	char *dma_addr = phys_to_virt(dev_addr);

	if (dir == DMA_NONE)
		BUG();
	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
		sync_single(hwdev, dma_addr, size, dir);
	else if (dir == DMA_FROM_DEVICE)
		mark_clean(dma_addr, size);
}

/*
 * 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
 * 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).
 *
 * NOTE: An implementation may be able to use a smaller number of
 *       DMA address/length pairs than there are SG table elements.
 *       (for example via virtual mapping capabilities)
 *       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
 * same here.
 */
int
swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
	       int dir)
{
	void *addr;
	unsigned long dev_addr;
	int i;

	if (dir == DMA_NONE)
		BUG();

	for (i = 0; i < nelems; i++, sg++) {
		addr = SG_ENT_VIRT_ADDRESS(sg);
		dev_addr = virt_to_phys(addr);
		if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
			sg->dma_address = (dma_addr_t) virt_to_phys(map_single(hwdev, addr, sg->length, dir));
			if (!sg->dma_address) {
				/* 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;
				return 0;
			}
		} else
			sg->dma_address = dev_addr;
		sg->dma_length = sg->length;
	}
	return nelems;
}

/*
 * 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)
{
	int i;

	if (dir == DMA_NONE)
		BUG();

	for (i = 0; i < nelems; i++, sg++)
		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
			unmap_single(hwdev, (void *) phys_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);
}

/*
 * Make physical memory consistent for a set of streaming mode DMA translations
 * after a transfer.
 *
 * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
 * and usage.
 */
void
swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
			int nelems, int dir)
{
	int i;

	if (dir == DMA_NONE)
		BUG();

	for (i = 0; i < nelems; i++, sg++)
		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
			sync_single(hwdev, (void *) sg->dma_address,
				    sg->dma_length, dir);
}

void
swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
			   int nelems, int dir)
{
	int i;

	if (dir == DMA_NONE)
		BUG();

	for (i = 0; i < nelems; i++, sg++)
		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
			sync_single(hwdev, (void *) sg->dma_address,
				    sg->dma_length, dir);
}

int
swiotlb_dma_mapping_error(dma_addr_t dma_addr)
{
	return (dma_addr == virt_to_phys(io_tlb_overflow_buffer));
}

/*
 * Return whether the given PCI device DMA address mask can be supported
 * properly.  For example, if your device can only drive the low 24-bits
 * during PCI bus mastering, then you would pass 0x00ffffff as the mask to
 * this function.
 */
int
swiotlb_dma_supported (struct device *hwdev, u64 mask)
{
	return (virt_to_phys (io_tlb_end) - 1) <= mask;
}

EXPORT_SYMBOL(swiotlb_init);
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(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);