linux/arch/arm/mm/dma-mapping.c
Sumit Bhattacharya ea2e7057c0 ARM: 7172/1: dma: Drop GFP_COMP for DMA memory allocations
dma_alloc_coherent wants to split pages after allocation in order to
reduce the memory footprint. This does not work well with GFP_COMP
pages, so drop this flag before allocation.

This patch is ported from arch/avr32
(commit 3611553ef9).

[swarren: s/HUGETLB_PAGE/HUGETLBFS/ in comment, minor comment cleanup]

Signed-off-by: Sumit Bhattacharya <sumitb@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2011-11-26 21:58:53 +00:00

730 lines
18 KiB
C

/*
* linux/arch/arm/mm/dma-mapping.c
*
* Copyright (C) 2000-2004 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* DMA uncached mapping support.
*/
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <asm/memory.h>
#include <asm/highmem.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/sizes.h>
#include <asm/mach/arch.h>
#include "mm.h"
static u64 get_coherent_dma_mask(struct device *dev)
{
u64 mask = (u64)arm_dma_limit;
if (dev) {
mask = dev->coherent_dma_mask;
/*
* Sanity check the DMA mask - it must be non-zero, and
* must be able to be satisfied by a DMA allocation.
*/
if (mask == 0) {
dev_warn(dev, "coherent DMA mask is unset\n");
return 0;
}
if ((~mask) & (u64)arm_dma_limit) {
dev_warn(dev, "coherent DMA mask %#llx is smaller "
"than system GFP_DMA mask %#llx\n",
mask, (u64)arm_dma_limit);
return 0;
}
}
return mask;
}
/*
* Allocate a DMA buffer for 'dev' of size 'size' using the
* specified gfp mask. Note that 'size' must be page aligned.
*/
static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
{
unsigned long order = get_order(size);
struct page *page, *p, *e;
void *ptr;
u64 mask = get_coherent_dma_mask(dev);
#ifdef CONFIG_DMA_API_DEBUG
u64 limit = (mask + 1) & ~mask;
if (limit && size >= limit) {
dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
size, mask);
return NULL;
}
#endif
if (!mask)
return NULL;
if (mask < 0xffffffffULL)
gfp |= GFP_DMA;
page = alloc_pages(gfp, order);
if (!page)
return NULL;
/*
* Now split the huge page and free the excess pages
*/
split_page(page, order);
for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
__free_page(p);
/*
* Ensure that the allocated pages are zeroed, and that any data
* lurking in the kernel direct-mapped region is invalidated.
*/
ptr = page_address(page);
memset(ptr, 0, size);
dmac_flush_range(ptr, ptr + size);
outer_flush_range(__pa(ptr), __pa(ptr) + size);
return page;
}
/*
* Free a DMA buffer. 'size' must be page aligned.
*/
static void __dma_free_buffer(struct page *page, size_t size)
{
struct page *e = page + (size >> PAGE_SHIFT);
while (page < e) {
__free_page(page);
page++;
}
}
#ifdef CONFIG_MMU
#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - consistent_base) >> PAGE_SHIFT)
#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT)
/*
* These are the page tables (2MB each) covering uncached, DMA consistent allocations
*/
static pte_t **consistent_pte;
#define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M
unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
void __init init_consistent_dma_size(unsigned long size)
{
unsigned long base = CONSISTENT_END - ALIGN(size, SZ_2M);
BUG_ON(consistent_pte); /* Check we're called before DMA region init */
BUG_ON(base < VMALLOC_END);
/* Grow region to accommodate specified size */
if (base < consistent_base)
consistent_base = base;
}
#include "vmregion.h"
static struct arm_vmregion_head consistent_head = {
.vm_lock = __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock),
.vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
.vm_end = CONSISTENT_END,
};
#ifdef CONFIG_HUGETLB_PAGE
#error ARM Coherent DMA allocator does not (yet) support huge TLB
#endif
/*
* Initialise the consistent memory allocation.
*/
static int __init consistent_init(void)
{
int ret = 0;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
int i = 0;
unsigned long base = consistent_base;
unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
if (!consistent_pte) {
pr_err("%s: no memory\n", __func__);
return -ENOMEM;
}
pr_debug("DMA memory: 0x%08lx - 0x%08lx:\n", base, CONSISTENT_END);
consistent_head.vm_start = base;
do {
pgd = pgd_offset(&init_mm, base);
pud = pud_alloc(&init_mm, pgd, base);
if (!pud) {
printk(KERN_ERR "%s: no pud tables\n", __func__);
ret = -ENOMEM;
break;
}
pmd = pmd_alloc(&init_mm, pud, base);
if (!pmd) {
printk(KERN_ERR "%s: no pmd tables\n", __func__);
ret = -ENOMEM;
break;
}
WARN_ON(!pmd_none(*pmd));
pte = pte_alloc_kernel(pmd, base);
if (!pte) {
printk(KERN_ERR "%s: no pte tables\n", __func__);
ret = -ENOMEM;
break;
}
consistent_pte[i++] = pte;
base += PMD_SIZE;
} while (base < CONSISTENT_END);
return ret;
}
core_initcall(consistent_init);
static void *
__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
{
struct arm_vmregion *c;
size_t align;
int bit;
if (!consistent_pte) {
printk(KERN_ERR "%s: not initialised\n", __func__);
dump_stack();
return NULL;
}
/*
* Align the virtual region allocation - maximum alignment is
* a section size, minimum is a page size. This helps reduce
* fragmentation of the DMA space, and also prevents allocations
* smaller than a section from crossing a section boundary.
*/
bit = fls(size - 1);
if (bit > SECTION_SHIFT)
bit = SECTION_SHIFT;
align = 1 << bit;
/*
* Allocate a virtual address in the consistent mapping region.
*/
c = arm_vmregion_alloc(&consistent_head, align, size,
gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
if (c) {
pte_t *pte;
int idx = CONSISTENT_PTE_INDEX(c->vm_start);
u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
pte = consistent_pte[idx] + off;
c->vm_pages = page;
do {
BUG_ON(!pte_none(*pte));
set_pte_ext(pte, mk_pte(page, prot), 0);
page++;
pte++;
off++;
if (off >= PTRS_PER_PTE) {
off = 0;
pte = consistent_pte[++idx];
}
} while (size -= PAGE_SIZE);
dsb();
return (void *)c->vm_start;
}
return NULL;
}
static void __dma_free_remap(void *cpu_addr, size_t size)
{
struct arm_vmregion *c;
unsigned long addr;
pte_t *ptep;
int idx;
u32 off;
c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr);
if (!c) {
printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
__func__, cpu_addr);
dump_stack();
return;
}
if ((c->vm_end - c->vm_start) != size) {
printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
__func__, c->vm_end - c->vm_start, size);
dump_stack();
size = c->vm_end - c->vm_start;
}
idx = CONSISTENT_PTE_INDEX(c->vm_start);
off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
ptep = consistent_pte[idx] + off;
addr = c->vm_start;
do {
pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
ptep++;
addr += PAGE_SIZE;
off++;
if (off >= PTRS_PER_PTE) {
off = 0;
ptep = consistent_pte[++idx];
}
if (pte_none(pte) || !pte_present(pte))
printk(KERN_CRIT "%s: bad page in kernel page table\n",
__func__);
} while (size -= PAGE_SIZE);
flush_tlb_kernel_range(c->vm_start, c->vm_end);
arm_vmregion_free(&consistent_head, c);
}
#else /* !CONFIG_MMU */
#define __dma_alloc_remap(page, size, gfp, prot) page_address(page)
#define __dma_free_remap(addr, size) do { } while (0)
#endif /* CONFIG_MMU */
static void *
__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
pgprot_t prot)
{
struct page *page;
void *addr;
/*
* Following is a work-around (a.k.a. hack) to prevent pages
* with __GFP_COMP being passed to split_page() which cannot
* handle them. The real problem is that this flag probably
* should be 0 on ARM as it is not supported on this
* platform; see CONFIG_HUGETLBFS.
*/
gfp &= ~(__GFP_COMP);
*handle = ~0;
size = PAGE_ALIGN(size);
page = __dma_alloc_buffer(dev, size, gfp);
if (!page)
return NULL;
if (!arch_is_coherent())
addr = __dma_alloc_remap(page, size, gfp, prot);
else
addr = page_address(page);
if (addr)
*handle = pfn_to_dma(dev, page_to_pfn(page));
else
__dma_free_buffer(page, size);
return addr;
}
/*
* Allocate DMA-coherent memory space and return both the kernel remapped
* virtual and bus address for that space.
*/
void *
dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
{
void *memory;
if (dma_alloc_from_coherent(dev, size, handle, &memory))
return memory;
return __dma_alloc(dev, size, handle, gfp,
pgprot_dmacoherent(pgprot_kernel));
}
EXPORT_SYMBOL(dma_alloc_coherent);
/*
* Allocate a writecombining region, in much the same way as
* dma_alloc_coherent above.
*/
void *
dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
{
return __dma_alloc(dev, size, handle, gfp,
pgprot_writecombine(pgprot_kernel));
}
EXPORT_SYMBOL(dma_alloc_writecombine);
static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
int ret = -ENXIO;
#ifdef CONFIG_MMU
unsigned long user_size, kern_size;
struct arm_vmregion *c;
user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
if (c) {
unsigned long off = vma->vm_pgoff;
kern_size = (c->vm_end - c->vm_start) >> PAGE_SHIFT;
if (off < kern_size &&
user_size <= (kern_size - off)) {
ret = remap_pfn_range(vma, vma->vm_start,
page_to_pfn(c->vm_pages) + off,
user_size << PAGE_SHIFT,
vma->vm_page_prot);
}
}
#endif /* CONFIG_MMU */
return ret;
}
int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
vma->vm_page_prot = pgprot_dmacoherent(vma->vm_page_prot);
return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
}
EXPORT_SYMBOL(dma_mmap_coherent);
int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
}
EXPORT_SYMBOL(dma_mmap_writecombine);
/*
* free a page as defined by the above mapping.
* Must not be called with IRQs disabled.
*/
void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
{
WARN_ON(irqs_disabled());
if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
return;
size = PAGE_ALIGN(size);
if (!arch_is_coherent())
__dma_free_remap(cpu_addr, size);
__dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
}
EXPORT_SYMBOL(dma_free_coherent);
/*
* Make an area consistent for devices.
* Note: Drivers should NOT use this function directly, as it will break
* platforms with CONFIG_DMABOUNCE.
* Use the driver DMA support - see dma-mapping.h (dma_sync_*)
*/
void ___dma_single_cpu_to_dev(const void *kaddr, size_t size,
enum dma_data_direction dir)
{
unsigned long paddr;
BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1));
dmac_map_area(kaddr, size, dir);
paddr = __pa(kaddr);
if (dir == DMA_FROM_DEVICE) {
outer_inv_range(paddr, paddr + size);
} else {
outer_clean_range(paddr, paddr + size);
}
/* FIXME: non-speculating: flush on bidirectional mappings? */
}
EXPORT_SYMBOL(___dma_single_cpu_to_dev);
void ___dma_single_dev_to_cpu(const void *kaddr, size_t size,
enum dma_data_direction dir)
{
BUG_ON(!virt_addr_valid(kaddr) || !virt_addr_valid(kaddr + size - 1));
/* FIXME: non-speculating: not required */
/* don't bother invalidating if DMA to device */
if (dir != DMA_TO_DEVICE) {
unsigned long paddr = __pa(kaddr);
outer_inv_range(paddr, paddr + size);
}
dmac_unmap_area(kaddr, size, dir);
}
EXPORT_SYMBOL(___dma_single_dev_to_cpu);
static void dma_cache_maint_page(struct page *page, unsigned long offset,
size_t size, enum dma_data_direction dir,
void (*op)(const void *, size_t, int))
{
/*
* A single sg entry may refer to multiple physically contiguous
* pages. But we still need to process highmem pages individually.
* If highmem is not configured then the bulk of this loop gets
* optimized out.
*/
size_t left = size;
do {
size_t len = left;
void *vaddr;
if (PageHighMem(page)) {
if (len + offset > PAGE_SIZE) {
if (offset >= PAGE_SIZE) {
page += offset / PAGE_SIZE;
offset %= PAGE_SIZE;
}
len = PAGE_SIZE - offset;
}
vaddr = kmap_high_get(page);
if (vaddr) {
vaddr += offset;
op(vaddr, len, dir);
kunmap_high(page);
} else if (cache_is_vipt()) {
/* unmapped pages might still be cached */
vaddr = kmap_atomic(page);
op(vaddr + offset, len, dir);
kunmap_atomic(vaddr);
}
} else {
vaddr = page_address(page) + offset;
op(vaddr, len, dir);
}
offset = 0;
page++;
left -= len;
} while (left);
}
void ___dma_page_cpu_to_dev(struct page *page, unsigned long off,
size_t size, enum dma_data_direction dir)
{
unsigned long paddr;
dma_cache_maint_page(page, off, size, dir, dmac_map_area);
paddr = page_to_phys(page) + off;
if (dir == DMA_FROM_DEVICE) {
outer_inv_range(paddr, paddr + size);
} else {
outer_clean_range(paddr, paddr + size);
}
/* FIXME: non-speculating: flush on bidirectional mappings? */
}
EXPORT_SYMBOL(___dma_page_cpu_to_dev);
void ___dma_page_dev_to_cpu(struct page *page, unsigned long off,
size_t size, enum dma_data_direction dir)
{
unsigned long paddr = page_to_phys(page) + off;
/* FIXME: non-speculating: not required */
/* don't bother invalidating if DMA to device */
if (dir != DMA_TO_DEVICE)
outer_inv_range(paddr, paddr + size);
dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
/*
* Mark the D-cache clean for this page to avoid extra flushing.
*/
if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
set_bit(PG_dcache_clean, &page->flags);
}
EXPORT_SYMBOL(___dma_page_dev_to_cpu);
/**
* dma_map_sg - map a set of SG buffers for streaming mode DMA
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to map
* @dir: DMA transfer direction
*
* Map a set of buffers described by scatterlist in streaming mode for DMA.
* This is the scatter-gather version of the dma_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}.
*
* Device ownership issues as mentioned for dma_map_single are the same
* here.
*/
int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
enum dma_data_direction dir)
{
struct scatterlist *s;
int i, j;
BUG_ON(!valid_dma_direction(dir));
for_each_sg(sg, s, nents, i) {
s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
s->length, dir);
if (dma_mapping_error(dev, s->dma_address))
goto bad_mapping;
}
debug_dma_map_sg(dev, sg, nents, nents, dir);
return nents;
bad_mapping:
for_each_sg(sg, s, i, j)
__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
return 0;
}
EXPORT_SYMBOL(dma_map_sg);
/**
* dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to unmap (same as was passed to dma_map_sg)
* @dir: DMA transfer direction (same as was passed to dma_map_sg)
*
* Unmap a set of streaming mode DMA translations. Again, CPU access
* rules concerning calls here are the same as for dma_unmap_single().
*/
void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
enum dma_data_direction dir)
{
struct scatterlist *s;
int i;
debug_dma_unmap_sg(dev, sg, nents, dir);
for_each_sg(sg, s, nents, i)
__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
}
EXPORT_SYMBOL(dma_unmap_sg);
/**
* dma_sync_sg_for_cpu
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to map (returned from dma_map_sg)
* @dir: DMA transfer direction (same as was passed to dma_map_sg)
*/
void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction dir)
{
struct scatterlist *s;
int i;
for_each_sg(sg, s, nents, i) {
if (!dmabounce_sync_for_cpu(dev, sg_dma_address(s), 0,
sg_dma_len(s), dir))
continue;
__dma_page_dev_to_cpu(sg_page(s), s->offset,
s->length, dir);
}
debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
}
EXPORT_SYMBOL(dma_sync_sg_for_cpu);
/**
* dma_sync_sg_for_device
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
* @sg: list of buffers
* @nents: number of buffers to map (returned from dma_map_sg)
* @dir: DMA transfer direction (same as was passed to dma_map_sg)
*/
void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction dir)
{
struct scatterlist *s;
int i;
for_each_sg(sg, s, nents, i) {
if (!dmabounce_sync_for_device(dev, sg_dma_address(s), 0,
sg_dma_len(s), dir))
continue;
__dma_page_cpu_to_dev(sg_page(s), s->offset,
s->length, dir);
}
debug_dma_sync_sg_for_device(dev, sg, nents, dir);
}
EXPORT_SYMBOL(dma_sync_sg_for_device);
/*
* Return whether the given device DMA address mask can be supported
* properly. For example, if your device can only drive the low 24-bits
* during bus mastering, then you would pass 0x00ffffff as the mask
* to this function.
*/
int dma_supported(struct device *dev, u64 mask)
{
if (mask < (u64)arm_dma_limit)
return 0;
return 1;
}
EXPORT_SYMBOL(dma_supported);
int dma_set_mask(struct device *dev, u64 dma_mask)
{
if (!dev->dma_mask || !dma_supported(dev, dma_mask))
return -EIO;
#ifndef CONFIG_DMABOUNCE
*dev->dma_mask = dma_mask;
#endif
return 0;
}
EXPORT_SYMBOL(dma_set_mask);
#define PREALLOC_DMA_DEBUG_ENTRIES 4096
static int __init dma_debug_do_init(void)
{
dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
return 0;
}
fs_initcall(dma_debug_do_init);