On 1 March 2016 at 16:39, Catalin Marinas [off-list ref] wrote:

On Mon, Feb 29, 2016 at 03:44:40PM +0100, Ard Biesheuvel wrote:

quoted

@@ -404,6 +404,12 @@ void __init mem_init(void)
      BUILD_BUG_ON(TASK_SIZE_32                       > TASK_SIZE_64);
 #endif

+     /*
+      * Make sure we chose the upper bound of sizeof(struct page)
+      * correctly.
+      */
+     BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));

Since with the vmemmap fix you already assume that PAGE_OFFSET is half
of the VA space, we should add another check on PAGE_OFFSET !=
UL(0xffffffffffffffff) << (VA_BITS - 1), just in case someone thinks
they could map a bit of extra RAM without going for a larger VA.

Indeed. The __pa() check only checks a single bit, so it must be split
exactly in half, unless we want to revisit that in the future (if
__pa() is no longer on a hot path after changes like these).