linux_dsm_epyc7002/arch/i386/mm/ioremap.c
Hugh Dickins 872fec16d9 [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>
2005-10-29 21:40:40 -07:00

326 lines
8.1 KiB
C

/*
* arch/i386/mm/ioremap.c
*
* Re-map IO memory to kernel address space so that we can access it.
* This is needed for high PCI addresses that aren't mapped in the
* 640k-1MB IO memory area on PC's
*
* (C) Copyright 1995 1996 Linus Torvalds
*/
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <asm/io.h>
#include <asm/fixmap.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#define ISA_START_ADDRESS 0xa0000
#define ISA_END_ADDRESS 0x100000
static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, unsigned long phys_addr, unsigned long flags)
{
pte_t *pte;
unsigned long pfn;
pfn = phys_addr >> PAGE_SHIFT;
pte = pte_alloc_kernel(pmd, addr);
if (!pte)
return -ENOMEM;
do {
BUG_ON(!pte_none(*pte));
set_pte(pte, pfn_pte(pfn, __pgprot(_PAGE_PRESENT | _PAGE_RW |
_PAGE_DIRTY | _PAGE_ACCESSED | flags)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
return 0;
}
static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, unsigned long phys_addr, unsigned long flags)
{
pmd_t *pmd;
unsigned long next;
phys_addr -= addr;
pmd = pmd_alloc(&init_mm, pud, addr);
if (!pmd)
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, flags))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
unsigned long end, unsigned long phys_addr, unsigned long flags)
{
pud_t *pud;
unsigned long next;
phys_addr -= addr;
pud = pud_alloc(&init_mm, pgd, addr);
if (!pud)
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, flags))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
static int ioremap_page_range(unsigned long addr,
unsigned long end, unsigned long phys_addr, unsigned long flags)
{
pgd_t *pgd;
unsigned long next;
int err;
BUG_ON(addr >= end);
flush_cache_all();
phys_addr -= addr;
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, flags);
if (err)
break;
} while (pgd++, addr = next, addr != end);
flush_tlb_all();
return err;
}
/*
* Generic mapping function (not visible outside):
*/
/*
* Remap an arbitrary physical address space into the kernel virtual
* address space. Needed when the kernel wants to access high addresses
* directly.
*
* NOTE! We need to allow non-page-aligned mappings too: we will obviously
* have to convert them into an offset in a page-aligned mapping, but the
* caller shouldn't need to know that small detail.
*/
void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags)
{
void __iomem * addr;
struct vm_struct * area;
unsigned long offset, last_addr;
/* Don't allow wraparound or zero size */
last_addr = phys_addr + size - 1;
if (!size || last_addr < phys_addr)
return NULL;
/*
* Don't remap the low PCI/ISA area, it's always mapped..
*/
if (phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS)
return (void __iomem *) phys_to_virt(phys_addr);
/*
* Don't allow anybody to remap normal RAM that we're using..
*/
if (phys_addr <= virt_to_phys(high_memory - 1)) {
char *t_addr, *t_end;
struct page *page;
t_addr = __va(phys_addr);
t_end = t_addr + (size - 1);
for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++)
if(!PageReserved(page))
return NULL;
}
/*
* Mappings have to be page-aligned
*/
offset = phys_addr & ~PAGE_MASK;
phys_addr &= PAGE_MASK;
size = PAGE_ALIGN(last_addr+1) - phys_addr;
/*
* Ok, go for it..
*/
area = get_vm_area(size, VM_IOREMAP | (flags << 20));
if (!area)
return NULL;
area->phys_addr = phys_addr;
addr = (void __iomem *) area->addr;
if (ioremap_page_range((unsigned long) addr,
(unsigned long) addr + size, phys_addr, flags)) {
vunmap((void __force *) addr);
return NULL;
}
return (void __iomem *) (offset + (char __iomem *)addr);
}
EXPORT_SYMBOL(__ioremap);
/**
* ioremap_nocache - map bus memory into CPU space
* @offset: bus address of the memory
* @size: size of the resource to map
*
* ioremap_nocache performs a platform specific sequence of operations to
* make bus memory CPU accessible via the readb/readw/readl/writeb/
* writew/writel functions and the other mmio helpers. The returned
* address is not guaranteed to be usable directly as a virtual
* address.
*
* This version of ioremap ensures that the memory is marked uncachable
* on the CPU as well as honouring existing caching rules from things like
* the PCI bus. Note that there are other caches and buffers on many
* busses. In particular driver authors should read up on PCI writes
*
* It's useful if some control registers are in such an area and
* write combining or read caching is not desirable:
*
* Must be freed with iounmap.
*/
void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
{
unsigned long last_addr;
void __iomem *p = __ioremap(phys_addr, size, _PAGE_PCD);
if (!p)
return p;
/* Guaranteed to be > phys_addr, as per __ioremap() */
last_addr = phys_addr + size - 1;
if (last_addr < virt_to_phys(high_memory) - 1) {
struct page *ppage = virt_to_page(__va(phys_addr));
unsigned long npages;
phys_addr &= PAGE_MASK;
/* This might overflow and become zero.. */
last_addr = PAGE_ALIGN(last_addr);
/* .. but that's ok, because modulo-2**n arithmetic will make
* the page-aligned "last - first" come out right.
*/
npages = (last_addr - phys_addr) >> PAGE_SHIFT;
if (change_page_attr(ppage, npages, PAGE_KERNEL_NOCACHE) < 0) {
iounmap(p);
p = NULL;
}
global_flush_tlb();
}
return p;
}
EXPORT_SYMBOL(ioremap_nocache);
void iounmap(volatile void __iomem *addr)
{
struct vm_struct *p;
if ((void __force *)addr <= high_memory)
return;
/*
* __ioremap special-cases the PCI/ISA range by not instantiating a
* vm_area and by simply returning an address into the kernel mapping
* of ISA space. So handle that here.
*/
if (addr >= phys_to_virt(ISA_START_ADDRESS) &&
addr < phys_to_virt(ISA_END_ADDRESS))
return;
write_lock(&vmlist_lock);
p = __remove_vm_area((void *)(PAGE_MASK & (unsigned long __force)addr));
if (!p) {
printk(KERN_WARNING "iounmap: bad address %p\n", addr);
dump_stack();
goto out_unlock;
}
if ((p->flags >> 20) && p->phys_addr < virt_to_phys(high_memory) - 1) {
change_page_attr(virt_to_page(__va(p->phys_addr)),
p->size >> PAGE_SHIFT,
PAGE_KERNEL);
global_flush_tlb();
}
out_unlock:
write_unlock(&vmlist_lock);
kfree(p);
}
EXPORT_SYMBOL(iounmap);
void __init *bt_ioremap(unsigned long phys_addr, unsigned long size)
{
unsigned long offset, last_addr;
unsigned int nrpages;
enum fixed_addresses idx;
/* Don't allow wraparound or zero size */
last_addr = phys_addr + size - 1;
if (!size || last_addr < phys_addr)
return NULL;
/*
* Don't remap the low PCI/ISA area, it's always mapped..
*/
if (phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS)
return phys_to_virt(phys_addr);
/*
* Mappings have to be page-aligned
*/
offset = phys_addr & ~PAGE_MASK;
phys_addr &= PAGE_MASK;
size = PAGE_ALIGN(last_addr) - phys_addr;
/*
* Mappings have to fit in the FIX_BTMAP area.
*/
nrpages = size >> PAGE_SHIFT;
if (nrpages > NR_FIX_BTMAPS)
return NULL;
/*
* Ok, go for it..
*/
idx = FIX_BTMAP_BEGIN;
while (nrpages > 0) {
set_fixmap(idx, phys_addr);
phys_addr += PAGE_SIZE;
--idx;
--nrpages;
}
return (void*) (offset + fix_to_virt(FIX_BTMAP_BEGIN));
}
void __init bt_iounmap(void *addr, unsigned long size)
{
unsigned long virt_addr;
unsigned long offset;
unsigned int nrpages;
enum fixed_addresses idx;
virt_addr = (unsigned long)addr;
if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN))
return;
offset = virt_addr & ~PAGE_MASK;
nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT;
idx = FIX_BTMAP_BEGIN;
while (nrpages > 0) {
clear_fixmap(idx);
--idx;
--nrpages;
}
}