[v5 09/15] sparc64: optimized struct page zeroing

From: Pavel Tatashin
Date: Thu Aug 03 2017 - 17:26:40 EST


Add an optimized mm_zero_struct_page(), so struct page's are zeroed without
calling memset(). We do eight regular stores, thus avoid cost of membar.

Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Reviewed-by: Steven Sistare <steven.sistare@xxxxxxxxxx>
Reviewed-by: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Reviewed-by: Bob Picco <bob.picco@xxxxxxxxxx>
---
arch/sparc/include/asm/pgtable_64.h | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)

diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 6fbd931f0570..be47537e84c5 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -230,6 +230,38 @@ extern unsigned long _PAGE_ALL_SZ_BITS;
extern struct page *mem_map_zero;
#define ZERO_PAGE(vaddr) (mem_map_zero)

+/* This macro must be updated when the size of struct page grows above 80
+ * or reduces below 64.
+ * The idea that compiler optimizes out switch() statement, and only
+ * leaves clrx instructions or memset() call.
+ */
+#define mm_zero_struct_page(pp) do { \
+ unsigned long *_pp = (void *)(pp); \
+ \
+ /* Check that struct page is 8-byte aligned */ \
+ BUILD_BUG_ON(sizeof(struct page) & 7); \
+ \
+ switch (sizeof(struct page)) { \
+ case 80: \
+ _pp[9] = 0; /* fallthrough */ \
+ case 72: \
+ _pp[8] = 0; /* fallthrough */ \
+ case 64: \
+ _pp[7] = 0; \
+ _pp[6] = 0; \
+ _pp[5] = 0; \
+ _pp[4] = 0; \
+ _pp[3] = 0; \
+ _pp[2] = 0; \
+ _pp[1] = 0; \
+ _pp[0] = 0; \
+ break; /* no fallthrough */ \
+ default: \
+ pr_warn_once("suboptimal mm_zero_struct_page"); \
+ memset(_pp, 0, sizeof(struct page)); \
+ } \
+} while (0)
+
/* PFNs are real physical page numbers. However, mem_map only begins to record
* per-page information starting at pfn_base. This is to handle systems where
* the first physical page in the machine is at some huge physical address,
--
2.13.4