Kirill A. Shutemov with the commit 96bacfe542 introduced
vm_ops->map_pages() for mapping easy accessible pages around
fault address in hope to reduce number of minor page faults.
Based on his workload runs, suggested FAULT_AROUND_ORDER
(knob to control the numbers of pages to map) is 4.
This patch moves the FAULT_AROUND_ORDER macro to arch/ for
architecture maintainers to decide on suitable FAULT_AROUND_ORDER
value based on performance data for that architecture.
Signed-off-by: Madhavan Srinivasan <ma...@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgtable.h | 6 ++++++
arch/x86/include/asm/pgtable.h | 5 +++++
include/asm-generic/pgtable.h | 10 ++++++++++
mm/memory.c | 2 --
4 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/pgtable.h
b/arch/powerpc/include/asm/pgtable.h
index 3ebb188..9fcbd48 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -19,6 +19,12 @@ struct mm_struct;
#endif
/*
+ * With a few real world workloads that were run,
+ * the performance data showed that a value of 3 is more advantageous.
+ */
+#define FAULT_AROUND_ORDER 3
+
+/*
* We save the slot number & secondary bit in the second half of the
* PTE page. We use the 8 bytes per each pte entry.
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 938ef1d..8387a65 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -7,6 +7,11 @@
#include <asm/pgtable_types.h>
/*
+ * Based on Kirill's test results, fault around order is set to 4
+ */
+#define FAULT_AROUND_ORDER 4
+
+/*
* Macro to mark a page protection value as UC-
*/
#define pgprot_noncached(prot) \
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 1ec08c1..62f7f07 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -7,6 +7,16 @@
#include <linux/mm_types.h>
#include <linux/bug.h>
+
+/*
+ * Fault around order is a control knob to decide the fault around pages.
+ * Default value is set to 0UL (disabled), but the arch can override it as
+ * desired.
+ */
+#ifndef FAULT_AROUND_ORDER
+#define FAULT_AROUND_ORDER 0UL
+#endif
+
/*
* On almost all architectures and configurations, 0 can be used as the
* upper ceiling to free_pgtables(): on many architectures it has the same
diff --git a/mm/memory.c b/mm/memory.c
index b02c584..fd79ffc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3358,8 +3358,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long
address,
update_mmu_cache(vma, address, pte);
}
-#define FAULT_AROUND_ORDER 4
-
#ifdef CONFIG_DEBUG_FS
static unsigned int fault_around_order = FAULT_AROUND_ORDER;
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
