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>
		
			
				
	
	
		
			129 lines
		
	
	
	
		
			3.1 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			129 lines
		
	
	
	
		
			3.1 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
/*
 | 
						|
 *  highmem.c: virtual kernel memory mappings for high memory
 | 
						|
 *
 | 
						|
 *  Provides kernel-static versions of atomic kmap functions originally
 | 
						|
 *  found as inlines in include/asm-sparc/highmem.h.  These became
 | 
						|
 *  needed as kmap_atomic() and kunmap_atomic() started getting
 | 
						|
 *  called from within modules.
 | 
						|
 *  -- Tomas Szepe <szepe@pinerecords.com>, September 2002
 | 
						|
 *
 | 
						|
 *  But kmap_atomic() and kunmap_atomic() cannot be inlined in
 | 
						|
 *  modules because they are loaded with btfixup-ped functions.
 | 
						|
 */
 | 
						|
 | 
						|
/*
 | 
						|
 * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
 | 
						|
 * gives a more generic (and caching) interface. But kmap_atomic can
 | 
						|
 * be used in IRQ contexts, so in some (very limited) cases we need it.
 | 
						|
 *
 | 
						|
 * XXX This is an old text. Actually, it's good to use atomic kmaps,
 | 
						|
 * provided you remember that they are atomic and not try to sleep
 | 
						|
 * with a kmap taken, much like a spinlock. Non-atomic kmaps are
 | 
						|
 * shared by CPUs, and so precious, and establishing them requires IPI.
 | 
						|
 * Atomic kmaps are lightweight and we may have NCPUS more of them.
 | 
						|
 */
 | 
						|
#include <linux/mm.h>
 | 
						|
#include <linux/highmem.h>
 | 
						|
#include <asm/pgalloc.h>
 | 
						|
#include <asm/cacheflush.h>
 | 
						|
#include <asm/tlbflush.h>
 | 
						|
#include <asm/fixmap.h>
 | 
						|
 | 
						|
void *__kmap_atomic(struct page *page)
 | 
						|
{
 | 
						|
	unsigned long vaddr;
 | 
						|
	long 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);
 | 
						|
 | 
						|
/* XXX Fix - Anton */
 | 
						|
#if 0
 | 
						|
	__flush_cache_one(vaddr);
 | 
						|
#else
 | 
						|
	flush_cache_all();
 | 
						|
#endif
 | 
						|
 | 
						|
#ifdef CONFIG_DEBUG_HIGHMEM
 | 
						|
	BUG_ON(!pte_none(*(kmap_pte-idx)));
 | 
						|
#endif
 | 
						|
	set_pte(kmap_pte-idx, mk_pte(page, kmap_prot));
 | 
						|
/* XXX Fix - Anton */
 | 
						|
#if 0
 | 
						|
	__flush_tlb_one(vaddr);
 | 
						|
#else
 | 
						|
	flush_tlb_all();
 | 
						|
#endif
 | 
						|
 | 
						|
	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
 | 
						|
	{
 | 
						|
		unsigned long idx;
 | 
						|
 | 
						|
		idx = type + KM_TYPE_NR * smp_processor_id();
 | 
						|
		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx));
 | 
						|
 | 
						|
		/* XXX Fix - Anton */
 | 
						|
#if 0
 | 
						|
		__flush_cache_one(vaddr);
 | 
						|
#else
 | 
						|
		flush_cache_all();
 | 
						|
#endif
 | 
						|
 | 
						|
		/*
 | 
						|
		 * 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);
 | 
						|
		/* XXX Fix - Anton */
 | 
						|
#if 0
 | 
						|
		__flush_tlb_one(vaddr);
 | 
						|
#else
 | 
						|
		flush_tlb_all();
 | 
						|
#endif
 | 
						|
	}
 | 
						|
#endif
 | 
						|
 | 
						|
	kmap_atomic_idx_pop();
 | 
						|
	pagefault_enable();
 | 
						|
}
 | 
						|
EXPORT_SYMBOL(__kunmap_atomic);
 | 
						|
 | 
						|
/* We may be fed a pagetable here by ptep_to_xxx and others. */
 | 
						|
struct page *kmap_atomic_to_page(void *ptr)
 | 
						|
{
 | 
						|
	unsigned long idx, vaddr = (unsigned long)ptr;
 | 
						|
	pte_t *pte;
 | 
						|
 | 
						|
	if (vaddr < SRMMU_NOCACHE_VADDR)
 | 
						|
		return virt_to_page(ptr);
 | 
						|
	if (vaddr < PKMAP_BASE)
 | 
						|
		return pfn_to_page(__nocache_pa(vaddr) >> PAGE_SHIFT);
 | 
						|
	BUG_ON(vaddr < FIXADDR_START);
 | 
						|
	BUG_ON(vaddr > FIXADDR_TOP);
 | 
						|
 | 
						|
	idx = virt_to_fix(vaddr);
 | 
						|
	pte = kmap_pte - (idx - FIX_KMAP_BEGIN);
 | 
						|
	return pte_page(*pte);
 | 
						|
}
 |