x86: don't flush the whole cache when changing cachability

Introduce the FLUSH_VA_VALID flag to flush_area_mask() and friends to
say that it is safe to use CLFLUSH (i.e., the virtual address is still
valid).

Use this when changing the cachability of the Xen direct mappings (in
response to the guest changing the cachability of its mappings). This
significantly improves performance by avoiding an expensive WBINVD.

This fixes a performance regression introduced by
c61a6f74f8 (x86: enforce consistent
cachability of MMIO mappings), the fix for XSA-154.

e.g., A set_memory_wc() call in Linux:

before: 4097 us
after:    47 us

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/flushtlb.c

@@ -140,7 +140,8 @@ unsigned int flush_area_local(const void *va, unsigned int flags)
         if ( order < (BITS_PER_LONG - PAGE_SHIFT) )
             sz = 1UL << (order + PAGE_SHIFT);
 
-        if ( !(flags & (FLUSH_TLB|FLUSH_TLB_GLOBAL)) &&
+        if ( (!(flags & (FLUSH_TLB|FLUSH_TLB_GLOBAL)) ||
+              (flags & FLUSH_VA_VALID)) &&
              c->x86_clflush_size && c->x86_cache_size && sz &&
              ((sz >> 10) < c->x86_cache_size) )
         {

xen/arch/x86/mm.c

@@ -5641,7 +5641,12 @@ int map_pages_to_xen(
         flush_flags |= FLUSH_TLB_GLOBAL;       \
     if ( (flags & _PAGE_PRESENT) &&            \
          (((o_) ^ flags) & PAGE_CACHE_ATTRS) ) \
+    {                                          \
         flush_flags |= FLUSH_CACHE;            \
+        if ( virt >= DIRECTMAP_VIRT_START &&   \
+             virt < HYPERVISOR_VIRT_END )      \
+            flush_flags |= FLUSH_VA_VALID;     \
+    }                                          \
 } while (0)
 
     while ( nr_mfns != 0 )

xen/include/asm-x86/flushtlb.h

@@ -85,6 +85,8 @@ void write_cr3(unsigned long cr3);
 #define FLUSH_TLB_GLOBAL 0x200
  /* Flush data caches */
 #define FLUSH_CACHE      0x400
+ /* VA for the flush has a valid mapping */
+#define FLUSH_VA_VALID   0x800
 
 /* Flush local TLBs/caches. */
 unsigned int flush_area_local(const void *va, unsigned int flags);