swiotlb.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 593 行 · 第 1/2 页

/*
 * Dynamic DMA mapping support.
 *
 * This implementation is for IA-64 platforms that do not support
 * I/O TLBs (aka DMA address translation hardware).
 * Copyright (C) 2000 Asit Mallick <[e-mail]>
 * Copyright (C) 2000 Goutham Rao <[e-mail]>
 * Copyright (C) 2000, 2003 Hewlett-Packard Co
 *	David Mosberger-Tang <[e-mail]>
 *
 * 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.
 */

#include <linux/cache.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ctype.h>

#include <asm/io.h>
#include <asm/pci.h>
#include <asm/dma.h>

#include <linux/init.h>
#include <linux/bootmem.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))

/*
 * 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

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 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.
 * Default to 64MB.
 */
static unsigned long io_tlb_nslabs = 32768;

/* 
 * 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 unsigned char **io_tlb_orig_addr;

/*
 * Protect the above data structures in the map and unmap calls
 */
static spinlock_t io_tlb_lock = SPIN_LOCK_UNLOCKED;

static int __init
setup_io_tlb_npages (char *str)
{
	if (isdigit(*str)) { 
		io_tlb_nslabs = simple_strtoul(str, &str, 0) << (PAGE_SHIFT - IO_TLB_SHIFT);
		/* 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? */

/*
 * Statically reserve bounce buffer space and initialize bounce buffer data structures for
 * the software IO TLB used to implement the PCI DMA API.
 */
void
swiotlb_init (void)
{
	unsigned long i;

	/*
	 * Get IO TLB memory from the low pages
	 */
	io_tlb_start = alloc_bootmem_low_pages(io_tlb_nslabs * (1 << IO_TLB_SHIFT));
	if (!io_tlb_start)
		panic("Cannot allocate SWIOTLB buffer");
	io_tlb_end = io_tlb_start + io_tlb_nslabs * (1 << IO_TLB_SHIFT);

	/*
	 * 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(char *));
	
	/* 
	 * Get the overflow emergency buffer 
	 */
	io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow); 
	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));
}

static inline int address_needs_mapping(struct device *hwdev, dma_addr_t addr)
{ 
	dma_addr_t mask = 0xffffffff; 
	if (hwdev && hwdev->dma_mask) 
		mask = *hwdev->dma_mask; 
	return (addr & ~mask) != 0; 		
} 

/*
 * Allocates bounce buffer and returns its kernel virtual address.
 */
static void *
map_single (struct device *hwdev, char *buffer, size_t size, int dir)
{
	unsigned long flags;
	char *dma_addr;
	unsigned int nslots, stride, index, wrap;
	int i;

	/*
	 * For mappings greater than a page size, we limit the stride (and hence alignment)
	 * to a page size.
	 */
	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
	if (size > (1 << PAGE_SHIFT))
		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
	else
		stride = 1;

	if (!nslots)
		BUG();

	/*
	 * 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);

		if (index >= io_tlb_nslabs)
			wrap = index = 0;

		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.
			 */
			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);

		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.
	 */
	io_tlb_orig_addr[index] = buffer;
	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
		memcpy(dma_addr, buffer, size);

	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, 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];

	/*
	 * First, sync the memory before unmapping the entry
	 */
	if ((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);

	/*
	 * 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);
	{
		int 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 index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
	char *buffer = io_tlb_orig_addr[index];

	/*
	 * bounce... copy the data back into/from the original buffer
	 * XXX How do you handle DMA_BIDIRECTIONAL here ?
	 */
	if (dir == DMA_FROM_DEVICE)
		memcpy(buffer, dma_addr, size);
	else if (dir == DMA_TO_DEVICE)
		memcpy(dma_addr, buffer, size);
	else
		BUG();
}