2005-04-17 06:20:36 +08:00
|
|
|
/* dma-alloc.c: consistent DMA memory allocation
|
|
|
|
*
|
|
|
|
* Derived from arch/ppc/mm/cachemap.c
|
|
|
|
*
|
|
|
|
* PowerPC version derived from arch/arm/mm/consistent.c
|
|
|
|
* Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
|
|
|
|
*
|
|
|
|
* linux/arch/arm/mm/consistent.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 2000 Russell King
|
|
|
|
*
|
|
|
|
* Consistent memory allocators. Used for DMA devices that want to
|
|
|
|
* share uncached memory with the processor core. The function return
|
|
|
|
* is the virtual address and 'dma_handle' is the physical address.
|
|
|
|
* Mostly stolen from the ARM port, with some changes for PowerPC.
|
|
|
|
* -- Dan
|
|
|
|
* Modified for 36-bit support. -Matt
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/signal.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/string.h>
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/ptrace.h>
|
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/pci.h>
|
2009-02-10 00:47:36 +08:00
|
|
|
#include <linux/hardirq.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/io.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/mmu.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include <asm/smp.h>
|
|
|
|
|
|
|
|
static int map_page(unsigned long va, unsigned long pa, pgprot_t prot)
|
|
|
|
{
|
|
|
|
pgd_t *pge;
|
|
|
|
pud_t *pue;
|
|
|
|
pmd_t *pme;
|
|
|
|
pte_t *pte;
|
|
|
|
int err = -ENOMEM;
|
|
|
|
|
|
|
|
/* Use upper 10 bits of VA to index the first level map */
|
|
|
|
pge = pgd_offset_k(va);
|
|
|
|
pue = pud_offset(pge, va);
|
|
|
|
pme = pmd_offset(pue, va);
|
|
|
|
|
|
|
|
/* Use middle 10 bits of VA to index the second-level map */
|
[PATCH] mm: init_mm without ptlock
First step in pushing down the page_table_lock. init_mm.page_table_lock has
been used throughout the architectures (usually for ioremap): not to serialize
kernel address space allocation (that's usually vmlist_lock), but because
pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it.
Reverse that: don't lock or unlock init_mm.page_table_lock in any of the
architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take
and drop it when allocating a new one, to check lest a racing task already
did. Similarly no page_table_lock in vmalloc's map_vm_area.
Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle
user mms, which are converted only by a later patch, for now they have to lock
differently according to whether or not it's init_mm.
If sources get muddled, there's a danger that an arch source taking
init_mm.page_table_lock will be mixed with common source also taking it (or
neither take it). So break the rules and make another change, which should
break the build for such a mismatch: remove the redundant mm arg from
pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13).
Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64
used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to
pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64
map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free
took page_table_lock for no good reason.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 09:16:21 +08:00
|
|
|
pte = pte_alloc_kernel(pme, va);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (pte != 0) {
|
|
|
|
err = 0;
|
|
|
|
set_pte(pte, mk_pte_phys(pa & PAGE_MASK, prot));
|
|
|
|
}
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function will allocate the requested contiguous pages and
|
|
|
|
* map them into the kernel's vmalloc() space. This is done so we
|
|
|
|
* get unique mapping for these pages, outside of the kernel's 1:1
|
|
|
|
* virtual:physical mapping. This is necessary so we can cover large
|
|
|
|
* portions of the kernel with single large page TLB entries, and
|
|
|
|
* still get unique uncached pages for consistent DMA.
|
|
|
|
*/
|
2005-10-21 15:21:18 +08:00
|
|
|
void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct vm_struct *area;
|
|
|
|
unsigned long page, va, pa;
|
|
|
|
void *ret;
|
|
|
|
int order, err, i;
|
|
|
|
|
|
|
|
if (in_interrupt())
|
|
|
|
BUG();
|
|
|
|
|
|
|
|
/* only allocate page size areas */
|
|
|
|
size = PAGE_ALIGN(size);
|
|
|
|
order = get_order(size);
|
|
|
|
|
|
|
|
page = __get_free_pages(gfp, order);
|
|
|
|
if (!page) {
|
|
|
|
BUG();
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* allocate some common virtual space to map the new pages */
|
|
|
|
area = get_vm_area(size, VM_ALLOC);
|
|
|
|
if (area == 0) {
|
|
|
|
free_pages(page, order);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
va = VMALLOC_VMADDR(area->addr);
|
|
|
|
ret = (void *) va;
|
|
|
|
|
|
|
|
/* this gives us the real physical address of the first page */
|
|
|
|
*dma_handle = pa = virt_to_bus((void *) page);
|
|
|
|
|
|
|
|
/* set refcount=1 on all pages in an order>0 allocation so that vfree() will actually free
|
|
|
|
* all pages that were allocated.
|
|
|
|
*/
|
|
|
|
if (order > 0) {
|
|
|
|
struct page *rpage = virt_to_page(page);
|
2006-03-22 16:08:05 +08:00
|
|
|
split_page(rpage, order);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
for (i = 0; i < size && err == 0; i += PAGE_SIZE)
|
|
|
|
err = map_page(va + i, pa + i, PAGE_KERNEL_NOCACHE);
|
|
|
|
|
|
|
|
if (err) {
|
|
|
|
vfree((void *) va);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* we need to ensure that there are no cachelines in use, or worse dirty in this area
|
|
|
|
* - can't do until after virtual address mappings are created
|
|
|
|
*/
|
|
|
|
frv_cache_invalidate(va, va + size);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* free page(s) as defined by the above mapping.
|
|
|
|
*/
|
|
|
|
void consistent_free(void *vaddr)
|
|
|
|
{
|
|
|
|
if (in_interrupt())
|
|
|
|
BUG();
|
|
|
|
vfree(vaddr);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* make an area consistent.
|
|
|
|
*/
|
|
|
|
void consistent_sync(void *vaddr, size_t size, int direction)
|
|
|
|
{
|
|
|
|
unsigned long start = (unsigned long) vaddr;
|
|
|
|
unsigned long end = start + size;
|
|
|
|
|
|
|
|
switch (direction) {
|
|
|
|
case PCI_DMA_NONE:
|
|
|
|
BUG();
|
|
|
|
case PCI_DMA_FROMDEVICE: /* invalidate only */
|
|
|
|
frv_cache_invalidate(start, end);
|
|
|
|
break;
|
|
|
|
case PCI_DMA_TODEVICE: /* writeback only */
|
|
|
|
frv_dcache_writeback(start, end);
|
|
|
|
break;
|
|
|
|
case PCI_DMA_BIDIRECTIONAL: /* writeback and invalidate */
|
|
|
|
frv_dcache_writeback(start, end);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* consistent_sync_page make a page are consistent. identical
|
|
|
|
* to consistent_sync, but takes a struct page instead of a virtual address
|
|
|
|
*/
|
|
|
|
|
|
|
|
void consistent_sync_page(struct page *page, unsigned long offset,
|
|
|
|
size_t size, int direction)
|
|
|
|
{
|
|
|
|
void *start;
|
|
|
|
|
|
|
|
start = page_address(page) + offset;
|
|
|
|
consistent_sync(start, size, direction);
|
|
|
|
}
|