linux_dsm_epyc7002/arch/mips/mm/highmem.c
Peter Zijlstra 20273941f2 mm: fix race in kunmap_atomic()
Christoph reported a nice splat which illustrated a race in the new stack
based kmap_atomic implementation.

The problem is that we pop our stack slot before we're completely done
resetting its state -- in particular clearing the PTE (sometimes that's
CONFIG_DEBUG_HIGHMEM).  If an interrupt happens before we actually clear
the PTE used for the last slot, that interrupt can reuse the slot in a
dirty state, which triggers a BUG in kmap_atomic().

Fix this by introducing kmap_atomic_idx() which reports the current slot
index without actually releasing it and use that to find the PTE and delay
the _pop() until after we're completely done.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reported-by: Christoph Hellwig <hch@infradead.org>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 18:03:05 -07:00

138 lines
2.9 KiB
C

#include <linux/module.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <asm/fixmap.h>
#include <asm/tlbflush.h>
static pte_t *kmap_pte;
unsigned long highstart_pfn, highend_pfn;
void *kmap(struct page *page)
{
void *addr;
might_sleep();
if (!PageHighMem(page))
return page_address(page);
addr = kmap_high(page);
flush_tlb_one((unsigned long)addr);
return addr;
}
EXPORT_SYMBOL(kmap);
void kunmap(struct page *page)
{
BUG_ON(in_interrupt());
if (!PageHighMem(page))
return;
kunmap_high(page);
}
EXPORT_SYMBOL(kunmap);
/*
* kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because
* no global lock is needed and because the kmap code must perform a global TLB
* invalidation when the kmap pool wraps.
*
* However when holding an atomic kmap is is not legal to sleep, so atomic
* kmaps are appropriate for short, tight code paths only.
*/
void *__kmap_atomic(struct page *page)
{
unsigned long vaddr;
int idx, type;
/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
pagefault_disable();
if (!PageHighMem(page))
return page_address(page);
type = kmap_atomic_idx_push();
idx = type + KM_TYPE_NR*smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
#ifdef CONFIG_DEBUG_HIGHMEM
BUG_ON(!pte_none(*(kmap_pte - idx)));
#endif
set_pte(kmap_pte-idx, mk_pte(page, PAGE_KERNEL));
local_flush_tlb_one((unsigned long)vaddr);
return (void*) vaddr;
}
EXPORT_SYMBOL(__kmap_atomic);
void __kunmap_atomic(void *kvaddr)
{
unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
int type;
if (vaddr < FIXADDR_START) { // FIXME
pagefault_enable();
return;
}
type = kmap_atomic_idx();
#ifdef CONFIG_DEBUG_HIGHMEM
{
int idx = type + KM_TYPE_NR * smp_processor_id();
BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
/*
* force other mappings to Oops if they'll try to access
* this pte without first remap it
*/
pte_clear(&init_mm, vaddr, kmap_pte-idx);
local_flush_tlb_one(vaddr);
}
#endif
kmap_atomic_idx_pop();
pagefault_enable();
}
EXPORT_SYMBOL(__kunmap_atomic);
/*
* This is the same as kmap_atomic() but can map memory that doesn't
* have a struct page associated with it.
*/
void *kmap_atomic_pfn(unsigned long pfn)
{
unsigned long vaddr;
int idx, type;
pagefault_disable();
type = kmap_atomic_idx_push();
idx = type + KM_TYPE_NR*smp_processor_id();
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
set_pte(kmap_pte-idx, pfn_pte(pfn, PAGE_KERNEL));
flush_tlb_one(vaddr);
return (void*) vaddr;
}
struct page *kmap_atomic_to_page(void *ptr)
{
unsigned long idx, vaddr = (unsigned long)ptr;
pte_t *pte;
if (vaddr < FIXADDR_START)
return virt_to_page(ptr);
idx = virt_to_fix(vaddr);
pte = kmap_pte - (idx - FIX_KMAP_BEGIN);
return pte_page(*pte);
}
void __init kmap_init(void)
{
unsigned long kmap_vstart;
/* cache the first kmap pte */
kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
}