/*
* linux/arch/arm/mm/consistent.c
*
- * Copyright (C) 2000-2002 Russell King
+ * 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
#include <linux/device.h>
#include <linux/dma-mapping.h>
+#include <asm/memory.h>
#include <asm/cacheflush.h>
-#include <asm/io.h>
#include <asm/tlbflush.h>
+#include <asm/sizes.h>
+
+/* Sanity check size */
+#if (CONSISTENT_DMA_SIZE % SZ_2M)
+#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
+#endif
-#define CONSISTENT_BASE (0xffc00000)
#define CONSISTENT_END (0xffe00000)
+#define CONSISTENT_BASE (CONSISTENT_END - CONSISTENT_DMA_SIZE)
+
#define CONSISTENT_OFFSET(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
+#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+
/*
- * This is the page table (2MB) covering uncached, DMA consistent allocations
+ * These are the page tables (2MB each) covering uncached, DMA consistent allocations
*/
-static pte_t *consistent_pte;
-static spinlock_t consistent_lock = SPIN_LOCK_UNLOCKED;
+static pte_t *consistent_pte[NUM_CONSISTENT_PTES];
+static DEFINE_SPINLOCK(consistent_lock);
/*
* VM region handling support.
struct list_head vm_list;
unsigned long vm_start;
unsigned long vm_end;
+ struct page *vm_pages;
+ int vm_active;
};
static struct vm_region consistent_head = {
};
static struct vm_region *
-vm_region_alloc(struct vm_region *head, size_t size, int gfp)
+vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
{
unsigned long addr = head->vm_start, end = head->vm_end - size;
unsigned long flags;
list_add_tail(&new->vm_list, &c->vm_list);
new->vm_start = addr;
new->vm_end = addr + size;
+ new->vm_active = 1;
spin_unlock_irqrestore(&consistent_lock, flags);
return new;
struct vm_region *c;
list_for_each_entry(c, &head->vm_list, vm_list) {
- if (c->vm_start == addr)
+ if (c->vm_active && c->vm_start == addr)
goto out;
}
c = NULL;
#endif
static void *
-__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, int gfp,
+__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
pgprot_t prot)
{
struct page *page;
struct vm_region *c;
unsigned long order;
- u64 mask = 0x00ffffff, limit; /* ISA default */
+ u64 mask = ISA_DMA_THRESHOLD, limit;
- if (!consistent_pte) {
+ if (!consistent_pte[0]) {
printk(KERN_ERR "%s: not initialised\n", __func__);
dump_stack();
return NULL;
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 NULL;
+ goto no_page;
+ }
+
+ if ((~mask) & ISA_DMA_THRESHOLD) {
+ dev_warn(dev, "coherent DMA mask %#llx is smaller "
+ "than system GFP_DMA mask %#llx\n",
+ mask, (unsigned long long)ISA_DMA_THRESHOLD);
+ goto no_page;
}
}
+ /*
+ * Sanity check the allocation size.
+ */
size = PAGE_ALIGN(size);
limit = (mask + 1) & ~mask;
- if ((limit && size >= limit) || size >= (CONSISTENT_END - CONSISTENT_BASE)) {
- printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
- size, mask);
- *handle = ~0;
- return NULL;
+ if ((limit && size >= limit) ||
+ size >= (CONSISTENT_END - CONSISTENT_BASE)) {
+ printk(KERN_WARNING "coherent allocation too big "
+ "(requested %#x mask %#llx)\n", size, mask);
+ goto no_page;
}
order = get_order(size);
c = vm_region_alloc(&consistent_head, size,
gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
if (c) {
- pte_t *pte = consistent_pte + CONSISTENT_OFFSET(c->vm_start);
+ pte_t *pte;
struct page *end = page + (1 << order);
+ 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;
+
+ split_page(page, order);
/*
* Set the "dma handle"
do {
BUG_ON(!pte_none(*pte));
- set_page_count(page, 1);
+ /*
+ * x86 does not mark the pages reserved...
+ */
SetPageReserved(page);
- set_pte(pte, mk_pte(page, prot));
+ 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);
/*
* Free the otherwise unused pages.
*/
while (page < end) {
- set_page_count(page, 1);
__free_page(page);
page++;
}
if (page)
__free_pages(page, order);
no_page:
+ *handle = ~0;
return NULL;
}
* virtual and bus address for that space.
*/
void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, int gfp)
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
{
+ if (arch_is_coherent()) {
+ void *virt;
+
+ virt = kmalloc(size, gfp);
+ if (!virt)
+ return NULL;
+ *handle = virt_to_dma(dev, virt);
+
+ return virt;
+ }
+
return __dma_alloc(dev, size, handle, gfp,
pgprot_noncached(pgprot_kernel));
}
* dma_alloc_coherent above.
*/
void *
-dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, int gfp)
+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)
+{
+ unsigned long flags, user_size, kern_size;
+ struct vm_region *c;
+ int ret = -ENXIO;
+
+ user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+ spin_lock_irqsave(&consistent_lock, flags);
+ c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
+ spin_unlock_irqrestore(&consistent_lock, flags);
+
+ 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)) {
+ vma->vm_flags |= VM_RESERVED;
+ ret = remap_pfn_range(vma, vma->vm_start,
+ page_to_pfn(c->vm_pages) + off,
+ user_size << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+ }
+
+ 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_noncached(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)
{
struct vm_region *c;
- unsigned long flags;
+ unsigned long flags, addr;
pte_t *ptep;
+ int idx;
+ u32 off;
+
+ WARN_ON(irqs_disabled());
+
+ if (arch_is_coherent()) {
+ kfree(cpu_addr);
+ return;
+ }
size = PAGE_ALIGN(size);
spin_lock_irqsave(&consistent_lock, flags);
-
c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
if (!c)
goto no_area;
+ c->vm_active = 0;
+ spin_unlock_irqrestore(&consistent_lock, flags);
+
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);
size = c->vm_end - c->vm_start;
}
- ptep = consistent_pte + CONSISTENT_OFFSET(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(ptep);
+ pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
unsigned long pfn;
ptep++;
+ addr += PAGE_SIZE;
+ off++;
+ if (off >= PTRS_PER_PTE) {
+ off = 0;
+ ptep = consistent_pte[++idx];
+ }
if (!pte_none(pte) && pte_present(pte)) {
pfn = pte_pfn(pte);
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
+
+ /*
+ * x86 does not mark the pages reserved...
+ */
ClearPageReserved(page);
__free_page(page);
flush_tlb_kernel_range(c->vm_start, c->vm_end);
+ spin_lock_irqsave(&consistent_lock, flags);
list_del(&c->vm_list);
-
spin_unlock_irqrestore(&consistent_lock, flags);
kfree(c);
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte;
- int ret = 0;
-
- spin_lock(&init_mm.page_table_lock);
+ int ret = 0, i = 0;
+ u32 base = CONSISTENT_BASE;
do {
- pgd = pgd_offset(&init_mm, CONSISTENT_BASE);
- pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE);
+ pgd = pgd_offset(&init_mm, base);
+ pmd = pmd_alloc(&init_mm, pgd, base);
if (!pmd) {
printk(KERN_ERR "%s: no pmd tables\n", __func__);
ret = -ENOMEM;
}
WARN_ON(!pmd_none(*pmd));
- pte = pte_alloc_kernel(&init_mm, pmd, CONSISTENT_BASE);
+ pte = pte_alloc_kernel(pmd, base);
if (!pte) {
printk(KERN_ERR "%s: no pte tables\n", __func__);
ret = -ENOMEM;
break;
}
- consistent_pte = pte;
- } while (0);
-
- spin_unlock(&init_mm.page_table_lock);
+ consistent_pte[i++] = pte;
+ base += (1 << PGDIR_SHIFT);
+ } while (base < CONSISTENT_END);
return ret;
}
/*
* 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 consistent_sync(void *vaddr, size_t size, int direction)
{
git://git.onelab.eu / linux-2.6.git / blobdiff