[PATCH] paravirt: kpte flush

Create a new PTE function which combines clearing a kernel PTE with the
subsequent flush.  This allows the two to be easily combined into a single
hypercall or paravirt-op.  More subtly, reverse the order of the flush for
kmap_atomic.  Instead of flushing on establishing a mapping, flush on clearing
a mapping.  This eliminates the possibility of leaving stale kmap entries
which may still have valid TLB mappings.  This is required for direct mode
hypervisors, which need to reprotect all mappings of a given page when
changing the page type from a normal page to a protected page (such as a page
table or descriptor table page).  But it also provides some nicer semantics
for real hardware, by providing extra debug-proofing against using stale
mappings, as well as ensuring that no stale mappings exist when changing the
cacheability attributes of a page, which could lead to cache conflicts when
two different types of mappings exist for the same page.

Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/mm/highmem.c

@@ -38,22 +38,19 @@ void *kmap_atomic(struct page *page, enum km_type type)
 
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
 	if (!pte_none(*(kmap_pte-idx)))
 		BUG();
-#endif
 	set_pte(kmap_pte-idx, mk_pte(page, kmap_prot));
-	__flush_tlb_one(vaddr);
 
 	return (void*) vaddr;
 }
 
 void kunmap_atomic(void *kvaddr, enum km_type type)
 {
-#ifdef CONFIG_DEBUG_HIGHMEM
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
 
+#ifdef CONFIG_DEBUG_HIGHMEM
 	if (vaddr >= PAGE_OFFSET && vaddr < (unsigned long)high_memory) {
 		dec_preempt_count();
 		preempt_check_resched();
@@ -62,14 +59,14 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 
 	if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx))
 		BUG();
-
+#endif
 	/*
-	 * force other mappings to Oops if they'll try to access
-	 * this pte without first remap it
+	 * Force other mappings to Oops if they'll try to access this pte
+	 * without first remap it.  Keeping stale mappings around is a bad idea
+	 * also, in case the page changes cacheability attributes or becomes
+	 * a protected page in a hypervisor.
 	 */
-	pte_clear(&init_mm, vaddr, kmap_pte-idx);
-	__flush_tlb_one(vaddr);
-#endif
+	kpte_clear_flush(kmap_pte-idx, vaddr);
 
 	dec_preempt_count();
 	preempt_check_resched();
@@ -88,7 +85,6 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	set_pte(kmap_pte-idx, pfn_pte(pfn, kmap_prot));
-	__flush_tlb_one(vaddr);
 
 	return (void*) vaddr;
 }

include/asm-i386/pgtable.h

@@ -441,6 +441,13 @@ extern pte_t *lookup_address(unsigned long address);
 #define pte_unmap_nested(pte) do { } while (0)
 #endif
 
+/* Clear a kernel PTE and flush it from the TLB */
+#define kpte_clear_flush(ptep, vaddr)					\
+do {									\
+	pte_clear(&init_mm, vaddr, ptep);				\
+	__flush_tlb_one(vaddr);						\
+} while (0)
+
 /*
  * The i386 doesn't have any external MMU info: the kernel page
  * tables contain all the necessary information.