linux_dsm_epyc7002/arch/sh/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

162 lines
3.8 KiB
C

/*
* arch/sh/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/mm.h>
#include <asm/io.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
static inline void remap_area_pte(pte_t * pte, unsigned long address,
unsigned long size, unsigned long phys_addr, unsigned long flags)
{
unsigned long end;
unsigned long pfn;
pgprot_t pgprot = __pgprot(_PAGE_PRESENT | _PAGE_RW |
_PAGE_DIRTY | _PAGE_ACCESSED |
_PAGE_HW_SHARED | _PAGE_FLAGS_HARD | flags);
address &= ~PMD_MASK;
end = address + size;
if (end > PMD_SIZE)
end = PMD_SIZE;
if (address >= end)
BUG();
pfn = phys_addr >> PAGE_SHIFT;
do {
if (!pte_none(*pte)) {
printk("remap_area_pte: page already exists\n");
BUG();
}
set_pte(pte, pfn_pte(pfn, pgprot));
address += PAGE_SIZE;
pfn++;
pte++;
} while (address && (address < end));
}
static inline int remap_area_pmd(pmd_t * pmd, unsigned long address,
unsigned long size, unsigned long phys_addr, unsigned long flags)
{
unsigned long end;
address &= ~PGDIR_MASK;
end = address + size;
if (end > PGDIR_SIZE)
end = PGDIR_SIZE;
phys_addr -= address;
if (address >= end)
BUG();
do {
pte_t * pte = pte_alloc_kernel(pmd, address);
if (!pte)
return -ENOMEM;
remap_area_pte(pte, address, end - address, address + phys_addr, flags);
address = (address + PMD_SIZE) & PMD_MASK;
pmd++;
} while (address && (address < end));
return 0;
}
int remap_area_pages(unsigned long address, unsigned long phys_addr,
unsigned long size, unsigned long flags)
{
int error;
pgd_t * dir;
unsigned long end = address + size;
phys_addr -= address;
dir = pgd_offset_k(address);
flush_cache_all();
if (address >= end)
BUG();
do {
pmd_t *pmd;
pmd = pmd_alloc(&init_mm, dir, address);
error = -ENOMEM;
if (!pmd)
break;
if (remap_area_pmd(pmd, address, end - address,
phys_addr + address, flags))
break;
error = 0;
address = (address + PGDIR_SIZE) & PGDIR_MASK;
dir++;
} while (address && (address < end));
flush_tlb_all();
return error;
}
/*
* 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 * p3_ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags)
{
void * 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 >= 0xA0000 && last_addr < 0x100000)
return 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))
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);
if (!area)
return NULL;
area->phys_addr = phys_addr;
addr = area->addr;
if (remap_area_pages((unsigned long) addr, phys_addr, size, flags)) {
vunmap(addr);
return NULL;
}
return (void *) (offset + (char *)addr);
}
void p3_iounmap(void *addr)
{
if (addr > high_memory)
vfree((void *)(PAGE_MASK & (unsigned long)addr));
}