Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1287901 > unrolled thread

[RFC V5] Add gup trace points support

Back to article view | Back to linux.kernel

Contents

  [RFC V5] Add gup trace points support Yang Shi <yang.shi@linaro.org> - 2015-12-09 22:50 +0100
    [PATCH v5 2/7] mm/gup: add gup trace points Yang Shi <yang.shi@linaro.org> - 2015-12-09 22:50 +0100
    [PATCH v5 5/7] s390: mm/gup: add gup trace points Yang Shi <yang.shi@linaro.org> - 2015-12-09 22:50 +0100

#1287901 — [RFC V5] Add gup trace points support

v5:
* Fixed a typo introduced by v4 rebase
* Removed redundant "#define CREATE_TRACE_POINTS" from architecture specifc
  gup.c

v4:
* Adopted Steven's suggestion to use "unsigned int" for nr_pages to save
  space in ring buffer since it is unlikely to have more than 0xffffffff
  pages are touched by gup in one invoke
* Remove unnecessray type cast

v3:
* Adopted suggestion from Dave Hansen to move the gup header include to the last
* Adopted comments from Steven:
  - Use DECLARE_EVENT_CLASS and DEFINE_EVENT
  - Just keep necessary TP_ARGS
* Moved archtichture specific fall-backable fast version trace point after the
  do while loop since it may jump to the slow version.
* Not implement recording return value since Steven plans to have it in generic
  tracing code
 
v2:
* Adopted commetns from Steven
  - remove all reference to tsk->comm since it is unnecessary for non-sched
    trace points
  - reduce arguments for __get_user_pages trace point and update mm/gup.c
    accordingly
* Added Ralf's acked-by for patch 4/7.


Some background about why I think this might be useful.

When I was profiling some hugetlb related program, I got page-faults event
doubled when hugetlb is enabled. When I looked into the code, I found page-faults
come from two places, do_page_fault and gup. So, I tried to figure out which
play a role (or both) in my use case. But I can't find existing finer tracing
event for sub page-faults in current mainline kernel.

So, I added the gup trace points support to have finer tracing events for
page-faults. The below events are added:

__get_user_pages
__get_user_pages_fast
fixup_user_fault

Both __get_user_pages and fixup_user_fault call handle_mm_fault.

Just added trace points to raw version __get_user_pages since all variants
will call it finally to do real work.

Although __get_user_pages_fast doesn't call handle_mm_fault, it might be useful
to have it to distinguish between slow and fast version.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1287903 — [PATCH v5 2/7] mm/gup: add gup trace points

For slow version, just add trace point for raw __get_user_pages since all
slow variants call it to do the real work finally.

Signed-off-by: Yang Shi <yang.shi@linaro.org>
---
 mm/gup.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/mm/gup.c b/mm/gup.c
index deafa2c..00a3cff 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -18,6 +18,9 @@
 
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/gup.h>
+
 static struct page *no_page_table(struct vm_area_struct *vma,
 		unsigned int flags)
 {
@@ -462,6 +465,8 @@ long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (!nr_pages)
 		return 0;
 
+	trace_gup_get_user_pages(start, nr_pages);
+
 	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
 
 	/*
@@ -599,6 +604,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	if (!(vm_flags & vma->vm_flags))
 		return -EFAULT;
 
+	trace_gup_fixup_user_fault(address);
 	ret = handle_mm_fault(mm, vma, address, fault_flags);
 	if (ret & VM_FAULT_ERROR) {
 		if (ret & VM_FAULT_OOM)
@@ -1340,6 +1346,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 					start, len)))
 		return 0;
 
+	trace_gup_get_user_pages_fast(start, nr_pages);
+
 	/*
 	 * Disable interrupts.  We use the nested form as we can already have
 	 * interrupts disabled by get_futex_key.
-- 
2.0.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1287907 — [PATCH v5 5/7] s390: mm/gup: add gup trace points

Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux-s390@vger.kernel.org
Signed-off-by: Yang Shi <yang.shi@linaro.org>
---
 arch/s390/mm/gup.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 12bbf0e..a1d5db7 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -12,6 +12,8 @@
 #include <linux/rwsem.h>
 #include <asm/pgtable.h>
 
+#include <trace/events/gup.h>
+
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -188,6 +190,9 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	end = start + len;
 	if ((end <= start) || (end > TASK_SIZE))
 		return 0;
+
+	trace_gup_get_user_pages_fast(start, nr_pages);
+
 	/*
 	 * local_irq_save() doesn't prevent pagetable teardown, but does
 	 * prevent the pagetables from being freed on s390.
-- 
2.0.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web