mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH 9/11] x86, UV: correct BAU regular message type
@ 2010-06-02 21:22 Cliff Wickman
  2010-06-08 20:58 ` [tip:x86/uv] x86, UV: Correct " tip-bot for Cliff Wickman
  0 siblings, 1 reply; 2+ messages in thread
From: Cliff Wickman @ 2010-06-02 21:22 UTC (permalink / raw)
  To: linux-kernel; +Cc: mingo, hpa, gregkh


The Broadcast Assist Unit messages have a regular or retry message type.
The regular type was not being set, but needs to be, because the lack
of a message type is sometimes used to identify an unused entry in the
message queue.
Also removing some excess comments.

Diffed against 2.6.34 -tip

Signed-off-by: Cliff Wickman <cpw@sgi.com>
---
 arch/x86/kernel/tlb_uv.c |   15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

Index: 100531.linux-tip/arch/x86/kernel/tlb_uv.c
===================================================================
--- 100531.linux-tip.orig/arch/x86/kernel/tlb_uv.c
+++ 100531.linux-tip/arch/x86/kernel/tlb_uv.c
@@ -580,23 +580,10 @@ const struct cpumask *uv_flush_send_and_
 	}
 	time1 = get_cycles();
 	do {
-		/*
-		 * Every message from any given cpu gets a unique message
-		 * sequence number. But retries use that same number.
-		 * Our message may have timed out at the destination because
-		 * all sw-ack resources are in use and there is a timeout
-		 * pending there.  In that case, our last send never got
-		 * placed into the queue and we need to persist until it
-		 * does.
-		 *
-		 * Make any retry a type MSG_RETRY so that the destination will
-		 * free any resource held by a previous message from this cpu.
-		 */
 		if (try == 0) {
-			/* use message type set by the caller the first time */
+			bau_desc->header.msg_type = MSG_REGULAR;
 			seq_number = bcp->message_number++;
 		} else {
-			/* use RETRY type on all the rest; same sequence */
 			bau_desc->header.msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}

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

* [tip:x86/uv] x86, UV: Correct BAU regular message type
  2010-06-02 21:22 [PATCH 9/11] x86, UV: correct BAU regular message type Cliff Wickman
@ 2010-06-08 20:58 ` tip-bot for Cliff Wickman
  0 siblings, 0 replies; 2+ messages in thread
From: tip-bot for Cliff Wickman @ 2010-06-08 20:58 UTC (permalink / raw)
  To: linux-tip-commits; +Cc: linux-kernel, hpa, mingo, cpw, tglx, mingo

Commit-ID:  7fba1bcd4844a4a8619a03bf51cabc92aea365a8
Gitweb:     http://git.kernel.org/tip/7fba1bcd4844a4a8619a03bf51cabc92aea365a8
Author:     Cliff Wickman <cpw@sgi.com>
AuthorDate: Wed, 2 Jun 2010 16:22:02 -0500
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Tue, 8 Jun 2010 21:13:47 +0200

x86, UV: Correct BAU regular message type

The Broadcast Assist Unit messages have a regular or retry
message type. The regular type was not being set, but needs to
be, because the lack of a message type is sometimes used to
identify an unused entry in the message queue.
Also removing some excess comments.

Signed-off-by: Cliff Wickman <cpw@sgi.com>
Cc: gregkh@suse.de
LKML-Reference: <E1OJvNy-0004ak-Dy@eag09.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/tlb_uv.c |   15 +--------------
 1 files changed, 1 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index dc962b5..4cb14db 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -580,23 +580,10 @@ const struct cpumask *uv_flush_send_and_wait(struct bau_desc *bau_desc,
 	}
 	time1 = get_cycles();
 	do {
-		/*
-		 * Every message from any given cpu gets a unique message
-		 * sequence number. But retries use that same number.
-		 * Our message may have timed out at the destination because
-		 * all sw-ack resources are in use and there is a timeout
-		 * pending there.  In that case, our last send never got
-		 * placed into the queue and we need to persist until it
-		 * does.
-		 *
-		 * Make any retry a type MSG_RETRY so that the destination will
-		 * free any resource held by a previous message from this cpu.
-		 */
 		if (try == 0) {
-			/* use message type set by the caller the first time */
+			bau_desc->header.msg_type = MSG_REGULAR;
 			seq_number = bcp->message_number++;
 		} else {
-			/* use RETRY type on all the rest; same sequence */
 			bau_desc->header.msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}

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

end of thread, other threads:[~2010-06-08 20:59 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-06-02 21:22 [PATCH 9/11] x86, UV: correct BAU regular message type Cliff Wickman
2010-06-08 20:58 ` [tip:x86/uv] x86, UV: Correct " tip-bot for Cliff Wickman

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

all inboxes | Powered by JetHome®