Skip to contentSkip to conversation

x86: perf: fix incorrect use of do_div() in nmi warning

PATCH In review Dave Hansen 3 participants 4 messages Jul 8, 2013 – Jul 12, 2013 x86

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 x86: perf: fix incorrect use of do_div() in nmi warning

From: Dave Hansen <[email protected]>

This fixes a bug present in 3.10 and introduced here:

commit 2ab00456ea8a0d79acb1390659b98416111880b2

Author: Dave Hansen <[email protected]>
Date:   Fri Jun 21 08:51:35 2013 -0700

x86: Warn when NMI handlers take large amounts of time

I completely botched understanding the calling conventions of do_div(). I assumed that do_div() returned the result instead of realizing that it modifies its argument and returns a remainder. The side-effect from this would be bogus numbers for the "msecs" value in the warning messages:

INFO: NMI handler (perf_event_nmi_handler) took too long to run: 0.114 msecs

Note, there was a second fix posted by Stephane Eranian for a separate patch which I also botched:

	http://lkml.kernel.org/r/20130704223010.GA30625@quad

Both of these fixes need to get pulled in to Linus's tree and the 3.10 stable tree.

---

 linux.git-davehans/arch/x86/kernel/nmi.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
arch/x86/kernel/nmi.c renamed from arch/x86/kernel/nmi.c~dave-is-stupid-do_div +4 -3
diff -puN arch/x86/kernel/nmi.c~dave-is-stupid-do_div arch/x86/kernel/nmi.c
@@ -111,7 +111,7 @@ static int __kprobes nmi_handle(unsigned
 	 */
 	list_for_each_entry_rcu(a, &desc->head, list) {
 		u64 before, delta, whole_msecs;
-		int decimal_msecs, thishandled;
+		int remainder_ns, decimal_msecs, thishandled;
 
 		before = local_clock();
 		thishandled = a->handler(type, regs);
@@ -123,8 +123,9 @@ static int __kprobes nmi_handle(unsigned
 			continue;
 
 		nmi_longest_ns = delta;
-		whole_msecs = do_div(delta, (1000 * 1000));
-		decimal_msecs = do_div(delta, 1000) % 1000;
+		whole_msecs = delta;
+		remainder_ns = do_div(whole_msecs, (1000 * 1000));
+		decimal_msecs = remainder_ns / 1000;
 		printk_ratelimited(KERN_INFO
 			"INFO: NMI handler (%ps) took too long to run: "
 			"%lld.%03d msecs\n", a->handler, whole_msecs,

_

#1 lore raw
Quoted 19 lines · Dave Hansen

From: Dave Hansen <[email protected]>

This fixes a bug present in 3.10 and introduced here:

commit 2ab00456ea8a0d79acb1390659b98416111880b2

Author: Dave Hansen <[email protected]>
Date:   Fri Jun 21 08:51:35 2013 -0700

x86: Warn when NMI handlers take large amounts of time

I completely botched understanding the calling conventions of do_div(). I assumed that do_div() returned the result instead of realizing that it modifies its argument and returns a remainder. The side-effect from this would be bogus numbers for the "msecs" value in the warning messages:

INFO: NMI handler (perf_event_nmi_handler) took too long to run: 0.114 msecs

Quoted 7 lines

Note, there was a second fix posted by Stephane Eranian for a separate patch which I also botched:

	http://lkml.kernel.org/r/20130704223010.GA30625@quad

Both of these fixes need to get pulled in to Linus's tree and the 3.10 stable tree.

This is a brand new v3.11 commit.

It should not be included in any -stable tree, is it?

Thanks,

Ingo

#2 lore raw
Quoted 10 lines · Ingo Molnar
Quoted 7 lines
Quoted 7 lines

Note, there was a second fix posted by Stephane Eranian for a separate patch which I also botched:

	http://lkml.kernel.org/r/20130704223010.GA30625@quad

Both of these fixes need to get pulled in to Linus's tree and the 3.10 stable tree.

This is a brand new v3.11 commit.

It should not be included in any -stable tree, is it?

Ingo, you are correct. The commit only appeared in Linus's tree post-3.10. It does not need to be in any stable trees.

#3 lore raw

[tip:perf/urgent] perf/x86: Fix incorrect use of do_div() in NMI warning

In reply to Dave Hansen
perf/x86: Fix incorrect use of do_div() in NMI warning
Commit-ID:  baf64b85445546a38b44052d71782dfe7531e350
Gitweb:     http://git.kernel.org/tip/baf64b85445546a38b44052d71782dfe7531e350
Author:     Dave Hansen <[email protected]>
AuthorDate: Mon, 8 Jul 2013 14:44:04 -0700
Committer:  Ingo Molnar <[email protected]>
CommitDate: Fri, 12 Jul 2013 14:13:04 +0200

perf/x86: Fix incorrect use of do_div() in NMI warning

I completely botched understanding the calling conventions of do_div(). I assumed that do_div() returned the result instead of realizing that it modifies its argument and returns a remainder. The side-effect from this would be bogus numbers for the "msecs" value in the warning messages:

INFO: NMI handler (perf_event_nmi_handler) took too long to run: 0.114 msecs

Note, there was a second fix posted by Stephane Eranian for a separate patch which I also botched:

	http://lkml.kernel.org/r/20130704223010.GA30625@quad
---
 arch/x86/kernel/nmi.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
arch/x86/kernel/nmi.c +4 -3
index 0920212..ba77ebc 100644
@@ -111,7 +111,7 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 	 */
 	list_for_each_entry_rcu(a, &desc->head, list) {
 		u64 before, delta, whole_msecs;
-		int decimal_msecs, thishandled;
+		int remainder_ns, decimal_msecs, thishandled;
 
 		before = local_clock();
 		thishandled = a->handler(type, regs);
@@ -123,8 +123,9 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 			continue;
 
 		nmi_longest_ns = delta;
-		whole_msecs = do_div(delta, (1000 * 1000));
-		decimal_msecs = do_div(delta, 1000) % 1000;
+		whole_msecs = delta;
+		remainder_ns = do_div(whole_msecs, (1000 * 1000));
+		decimal_msecs = remainder_ns / 1000;
 		printk_ratelimited(KERN_INFO
 			"INFO: NMI handler (%ps) took too long to run: "
 			"%lld.%03d msecs\n", a->handler, whole_msecs,