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>

arch/arm/mm/highmem.c

@@ -89,7 +89,7 @@ void __kunmap_atomic(void *kvaddr)
 	int idx, type;
 
 	if (kvaddr >= (void *)FIXADDR_START) {
-		type = kmap_atomic_idx_pop();
+		type = kmap_atomic_idx();
 		idx = type + KM_TYPE_NR * smp_processor_id();
 
 		if (cache_is_vivt())
@@ -101,6 +101,7 @@ void __kunmap_atomic(void *kvaddr)
 #else
 		(void) idx;  /* to kill a warning */
 #endif
+		kmap_atomic_idx_pop();
 	} else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
 		/* this address was obtained through kmap_high_get() */
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));

arch/frv/mm/highmem.c

@@ -68,7 +68,7 @@ EXPORT_SYMBOL(__kmap_atomic);
 
 void __kunmap_atomic(void *kvaddr)
 {
-	int type = kmap_atomic_idx_pop();
+	int type = kmap_atomic_idx();
 	switch (type) {
 	case 0:		__kunmap_atomic_primary(4, 6);	break;
 	case 1:		__kunmap_atomic_primary(5, 7);	break;
@@ -83,6 +83,7 @@ void __kunmap_atomic(void *kvaddr)
 	default:
 		BUG();
 	}
+	kmap_atomic_idx_pop();
 	pagefault_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);

arch/mips/mm/highmem.c

@@ -74,7 +74,7 @@ void __kunmap_atomic(void *kvaddr)
 		return;
 	}
 
-	type = kmap_atomic_idx_pop();
+	type = kmap_atomic_idx();
 #ifdef CONFIG_DEBUG_HIGHMEM
 	{
 		int idx = type + KM_TYPE_NR * smp_processor_id();
@@ -89,6 +89,7 @@ void __kunmap_atomic(void *kvaddr)
 		local_flush_tlb_one(vaddr);
 	}
 #endif
+	kmap_atomic_idx_pop();
 	pagefault_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);

arch/mn10300/include/asm/highmem.h

@@ -101,7 +101,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
 		return;
 	}
 
-	type = kmap_atomic_idx_pop();
+	type = kmap_atomic_idx();
 
 #if HIGHMEM_DEBUG
 	{
@@ -119,6 +119,8 @@ static inline void __kunmap_atomic(unsigned long vaddr)
 		__flush_tlb_one(vaddr);
 	}
 #endif
+
+	kmap_atomic_idx_pop();
 	pagefault_enable();
 }
 #endif /* __KERNEL__ */

arch/powerpc/mm/highmem.c

@@ -62,7 +62,7 @@ void __kunmap_atomic(void *kvaddr)
 		return;
 	}
 
-	type = kmap_atomic_idx_pop();
+	type = kmap_atomic_idx();
 
 #ifdef CONFIG_DEBUG_HIGHMEM
 	{
@@ -79,6 +79,8 @@ void __kunmap_atomic(void *kvaddr)
 		local_flush_tlb_page(NULL, vaddr);
 	}
 #endif
+
+	kmap_atomic_idx_pop();
 	pagefault_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);

arch/sparc/mm/highmem.c

@@ -75,7 +75,7 @@ void __kunmap_atomic(void *kvaddr)
 		return;
 	}
 
-	type = kmap_atomic_idx_pop();
+	type = kmap_atomic_idx();
 
 #ifdef CONFIG_DEBUG_HIGHMEM
 	{
@@ -104,6 +104,8 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 	}
 #endif
+
+	kmap_atomic_idx_pop();
 	pagefault_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);

arch/tile/mm/highmem.c

@@ -241,7 +241,7 @@ void __kunmap_atomic(void *kvaddr)
 		pte_t pteval = *pte;
 		int idx, type;
 
-		type = kmap_atomic_idx_pop();
+		type = kmap_atomic_idx();
 		idx = type + KM_TYPE_NR*smp_processor_id();
 
 		/*
@@ -252,6 +252,7 @@ void __kunmap_atomic(void *kvaddr)
 		BUG_ON(!pte_present(pteval) && !pte_migrating(pteval));
 		kmap_atomic_unregister(pte_page(pteval), vaddr);
 		kpte_clear_flush(pte, vaddr);
+		kmap_atomic_idx_pop();
 	} else {
 		/* Must be a lowmem page */
 		BUG_ON(vaddr < PAGE_OFFSET);

arch/x86/mm/highmem_32.c

@@ -74,7 +74,7 @@ void __kunmap_atomic(void *kvaddr)
 	    vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) {
 		int idx, type;
 
-		type = kmap_atomic_idx_pop();
+		type = kmap_atomic_idx();
 		idx = type + KM_TYPE_NR * smp_processor_id();
 
 #ifdef CONFIG_DEBUG_HIGHMEM
@@ -87,6 +87,7 @@ void __kunmap_atomic(void *kvaddr)
 		 * attributes or becomes a protected page in a hypervisor.
 		 */
 		kpte_clear_flush(kmap_pte-idx, vaddr);
+		kmap_atomic_idx_pop();
 	}
 #ifdef CONFIG_DEBUG_HIGHMEM
 	else {

arch/x86/mm/iomap_32.c

@@ -98,7 +98,7 @@ iounmap_atomic(void __iomem *kvaddr)
 	    vaddr <= __fix_to_virt(FIX_KMAP_BEGIN)) {
 		int idx, type;
 
-		type = kmap_atomic_idx_pop();
+		type = kmap_atomic_idx();
 		idx = type + KM_TYPE_NR * smp_processor_id();
 
 #ifdef CONFIG_DEBUG_HIGHMEM
@@ -111,6 +111,7 @@ iounmap_atomic(void __iomem *kvaddr)
 		 * attributes or becomes a protected page in a hypervisor.
 		 */
 		kpte_clear_flush(kmap_pte-idx, vaddr);
+		kmap_atomic_idx_pop();
 	}
 
 	pagefault_enable();

include/linux/highmem.h

@@ -88,6 +88,11 @@ static inline int kmap_atomic_idx_push(void)
 	return idx;
 }
 
+static inline int kmap_atomic_idx(void)
+{
+	return __get_cpu_var(__kmap_atomic_idx) - 1;
+}
+
 static inline int kmap_atomic_idx_pop(void)
 {
 	int idx = --__get_cpu_var(__kmap_atomic_idx);