mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH 1/1] x86/platform: Remove warning message for duplicate NMI handlers
       [not found] <20170307210841.541407747@asylum.americas.sgi.com>
@ 2017-03-07 21:08 ` Mike Travis
  2017-03-13 19:48   ` [tip:x86/urgent] " tip-bot for Mike Travis
  0 siblings, 1 reply; 2+ messages in thread
From: Mike Travis @ 2017-03-07 21:08 UTC (permalink / raw)
  To: Ingo Molnar, Thomas Gleixner, H. Peter Anvin, Don Zickus, Peter Zijlstra
  Cc: Dimitri Sivanich, Frank Ramsay, Russ Anderson, Tony Ernst, x86,
	linux-kernel

[-- Attachment #1: x86_remove_nmi_warning --]
[-- Type: text/plain, Size: 1342 bytes --]

Remove the WARNING message associated with multiple NMI handlers as
there are at least two that are legitimate.  These are the KGDB and the
UV handlers and both want to be called if the NMI has not been claimed
by any other NMI handler.

Use of the UNKNOWN NMI call chain dramatically lowers the NMI call rate
when high frequency NMI tools are in use, notably the perf tools.  It is
required on systems that cannot sustain a high NMI call rate without
adversely affecting the system operation.

Signed-off-by: Mike Travis <mike.travis@hpe.com>
Reviewed-by: Dimitri Sivanich <dimitri.sivanich@hpe.com>
---
 arch/x86/kernel/nmi.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

--- linux.orig/arch/x86/kernel/nmi.c
+++ linux/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/*
-	 * most handlers of type NMI_UNKNOWN never return because
-	 * they just assume the NMI is theirs.  Just a sanity check
-	 * to manage expectations
+	 * Indicate if there are multiple registrations on the
+	 * internal NMI handler call chains (SERR and IO_CHECK).
 	 */
-	WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
 

-- 

^ permalink raw reply	[flat|nested] 2+ messages in thread

* [tip:x86/urgent] x86/platform: Remove warning message for duplicate NMI handlers
  2017-03-07 21:08 ` [PATCH 1/1] x86/platform: Remove warning message for duplicate NMI handlers Mike Travis
@ 2017-03-13 19:48   ` tip-bot for Mike Travis
  0 siblings, 0 replies; 2+ messages in thread
From: tip-bot for Mike Travis @ 2017-03-13 19:48 UTC (permalink / raw)
  To: linux-tip-commits
  Cc: mingo, a.p.zijlstra, dimitri.sivanich, tony.ernst, frank.ramsay,
	linux-kernel, russ.anderson, hpa, mike.travis, tglx, dzickus

Commit-ID:  0d443b70cc92d741cbc1dcbf1079897b3d8bc3cc
Gitweb:     http://git.kernel.org/tip/0d443b70cc92d741cbc1dcbf1079897b3d8bc3cc
Author:     Mike Travis <mike.travis@hpe.com>
AuthorDate: Tue, 7 Mar 2017 15:08:42 -0600
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Mon, 13 Mar 2017 20:45:18 +0100

x86/platform: Remove warning message for duplicate NMI handlers

Remove the WARNING message associated with multiple NMI handlers as
there are at least two that are legitimate.  These are the KGDB and the
UV handlers and both want to be called if the NMI has not been claimed
by any other NMI handler.

Use of the UNKNOWN NMI call chain dramatically lowers the NMI call rate
when high frequency NMI tools are in use, notably the perf tools.  It is
required on systems that cannot sustain a high NMI call rate without
adversely affecting the system operation.

Signed-off-by: Mike Travis <mike.travis@hpe.com>
Reviewed-by: Dimitri Sivanich <dimitri.sivanich@hpe.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Russ Anderson <russ.anderson@hpe.com>
Cc: Frank Ramsay <frank.ramsay@hpe.com>
Cc: Tony Ernst <tony.ernst@hpe.com>
Link: http://lkml.kernel.org/r/20170307210841.730959611@asylum.americas.sgi.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
 arch/x86/kernel/nmi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f088ea4..a723ae94 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 	spin_lock_irqsave(&desc->lock, flags);
 
 	/*
-	 * most handlers of type NMI_UNKNOWN never return because
-	 * they just assume the NMI is theirs.  Just a sanity check
-	 * to manage expectations
+	 * Indicate if there are multiple registrations on the
+	 * internal NMI handler call chains (SERR and IO_CHECK).
 	 */
-	WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
 	WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
 

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2017-03-13 19:49 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
     [not found] <20170307210841.541407747@asylum.americas.sgi.com>
2017-03-07 21:08 ` [PATCH 1/1] x86/platform: Remove warning message for duplicate NMI handlers Mike Travis
2017-03-13 19:48   ` [tip:x86/urgent] " tip-bot for Mike Travis

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome