[patch 11/17] LTTng instrumentation - memory page faults

[Mathieu Desnoyers]

Instrument the page fault entry and exit. Useful to detect delays caused by page
faults and bad memory usage patterns.

Those tracepoints are used by LTTng.

About the performance impact of tracepoints (which is comparable to markers),
even without immediate values optimizations, tests done by Hideo Aoki on ia64
show no regression. His test case was using hackbench on a kernel where
scheduler instrumentation (about 5 events in code scheduler code) was added.
See the "Tracepoints" patch header for performance result detail.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxx>
CC: Andi Kleen <andi-suse@xxxxxxxxxxxxxx>
CC: linux-mm@xxxxxxxxx
CC: Dave Hansen <haveblue@xxxxxxxxxx>
CC: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
CC: 'Peter Zijlstra' <peterz@xxxxxxxxxxxxx>
CC: "Frank Ch. Eigler" <fche@xxxxxxxxxx>
CC: 'Ingo Molnar' <mingo@xxxxxxx>
CC: 'Hideo AOKI' <haoki@xxxxxxxxxx>
CC: Takashi Nishiie <t-nishiie@xxxxxxxxxxxxxxxxxx>
CC: 'Steven Rostedt' <rostedt@xxxxxxxxxxx>
CC: Eduard - Gabriel Munteanu <eduard.munteanu@xxxxxxxxxxx>
---
 include/trace/memory.h |   14 ++++++++++++++
 mm/memory.c            |   33 ++++++++++++++++++++++++---------
 2 files changed, 38 insertions(+), 9 deletions(-)

Index: linux-2.6-lttng/mm/memory.c
===================================================================
--- linux-2.6-lttng.orig/mm/memory.c	2008-07-15 14:02:54.000000000 -0400
+++ linux-2.6-lttng/mm/memory.c	2008-07-15 14:03:47.000000000 -0400
@@ -61,6 +61,7 @@
 
 #include <linux/swapops.h>
 #include <linux/elf.h>
+#include <trace/memory.h>
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
@@ -2664,30 +2665,44 @@ unlock:
 int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, int write_access)
 {
+	int res;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
+	trace_memory_handle_fault_entry(mm, vma, address, write_access);
+
 	__set_current_state(TASK_RUNNING);
 
 	count_vm_event(PGFAULT);
 
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		return hugetlb_fault(mm, vma, address, write_access);
+	if (unlikely(is_vm_hugetlb_page(vma))) {
+		res = hugetlb_fault(mm, vma, address, write_access);
+		goto end;
+	}
 
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
-	if (!pud)
-		return VM_FAULT_OOM;
+	if (!pud) {
+		res = VM_FAULT_OOM;
+		goto end;
+	}
 	pmd = pmd_alloc(mm, pud, address);
-	if (!pmd)
-		return VM_FAULT_OOM;
+	if (!pmd) {
+		res = VM_FAULT_OOM;
+		goto end;
+	}
 	pte = pte_alloc_map(mm, pmd, address);
-	if (!pte)
-		return VM_FAULT_OOM;
+	if (!pte) {
+		res = VM_FAULT_OOM;
+		goto end;
+	}
 
-	return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+	res = handle_pte_fault(mm, vma, address, pte, pmd, write_access);
+end:
+	trace_memory_handle_fault_exit(res);
+	return res;
 }
 
 #ifndef __PAGETABLE_PUD_FOLDED
Index: linux-2.6-lttng/include/trace/memory.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6-lttng/include/trace/memory.h	2008-07-15 14:03:47.000000000 -0400
@@ -0,0 +1,14 @@
+#ifndef _TRACE_MEMORY_H
+#define _TRACE_MEMORY_H
+
+#include <linux/tracepoint.h>
+
+DEFINE_TRACE(memory_handle_fault_entry,
+	TPPROTO(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, int write_access),
+	TPARGS(mm, vma, address, write_access));
+DEFINE_TRACE(memory_handle_fault_exit,
+	TPPROTO(int res),
+	TPARGS(res));
+
+#endif

-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/