[ARM] 3762/1: Fix ptrace cache coherency bug for ARM1136 VIPT nonaliasing Harvard caches

Patch from George G. Davis

Resolve ARM1136 VIPT non-aliasing cache coherency issues observed when
using ptrace to set breakpoints and cleanup copy_{to,from}_user_page()
while we're here as requested by Russell King because "it's also far
too heavy on non-v6 CPUs".

NOTES:

1. Only access_process_vm() calls copy_{to,from}_user_page().
2. access_process_vm() calls get_user_pages() to pin down the "page".
3. get_user_pages() calls flush_dcache_page(page) which ensures cache
   coherency between kernel and userspace mappings of "page".  However
   flush_dcache_page(page) may not invalidate I-Cache over this range
   for all cases, specifically, I-Cache is not invalidated for the VIPT
   non-aliasing case.  So memory is consistent between kernel and user
   space mappings of "page" but I-Cache may still be hot over this
   range.  IOW, we don't have to worry about flush_cache_page() before
   memcpy().
4. Now, for the copy_to_user_page() case, after memcpy(), we must flush
   the caches so memory is consistent with kernel cache entries and
   invalidate the I-Cache if this mm region is executable.  We don't
   need to do anything after memcpy() for the copy_from_user_page()
   case since kernel cache entries will be invalidated via the same
   process above if we access "page" again.  The flush_ptrace_access()
   function (borrowed from SPARC64 implementation) is added to handle
   cache flushing after memcpy() for the copy_to_user_page() case.

Signed-off-by: George G. Davis <gdavis@mvista.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/include/asm-arm/cacheflush.h b/include/asm-arm/cacheflush.h
index fe0c744..e4a2569 100644
--- a/include/asm-arm/cacheflush.h
+++ b/include/asm-arm/cacheflush.h
@@ -247,14 +247,12 @@
  */
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 	do {							\
-		flush_cache_page(vma, vaddr, page_to_pfn(page));\
 		memcpy(dst, src, len);				\
-		flush_dcache_page(page);			\
+		flush_ptrace_access(vma, page, vaddr, dst, len, 1);\
 	} while (0)
 
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	do {							\
-		flush_cache_page(vma, vaddr, page_to_pfn(page));\
 		memcpy(dst, src, len);				\
 	} while (0)
 
@@ -285,10 +283,24 @@
 		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
 	}
 }
+
+static inline void
+flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
+			 unsigned long uaddr, void *kaddr,
+			 unsigned long len, int write)
+{
+	if (cpu_isset(smp_processor_id(), vma->vm_mm->cpu_vm_mask)) {
+		unsigned long addr = (unsigned long)kaddr;
+		__cpuc_coherent_kern_range(addr, addr + len);
+	}
+}
 #else
 extern void flush_cache_mm(struct mm_struct *mm);
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn);
+extern void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
+				unsigned long uaddr, void *kaddr,
+				unsigned long len, int write);
 #endif
 
 /*