mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH 6/11] x86, UV: correct BAU software acknowledge
@ 2010-06-02 21:22 Cliff Wickman
  2010-06-08 20:57 ` [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


Correct the acknowledgment and the reset of a BAU software-acknowledged
message.

A retry message should be testing only for timed-out resources (mask << 8).
(And we delete a log message that might cause unnecessary concern)
The acknowledge MMR is  |--timed-out--|---pending--|,  each is 8 bits.

The IPI-driven reset of software acknowledge resources frees both timed out
and pending resources.

Diffed against 2.6.34 -tip

Signed-off-by: Cliff Wickman <cpw@sgi.com>
---
 arch/x86/kernel/tlb_uv.c |   17 ++++++++---------
 1 file changed, 8 insertions(+), 9 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
@@ -161,15 +161,14 @@ static inline void uv_bau_process_retry_
 			slot2 = msg2 - mdp->va_queue_first;
 			mmr = uv_read_local_mmr
 				(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
-			msg_res = ((msg2->sw_ack_vector << 8) |
-				   msg2->sw_ack_vector);
+			msg_res = msg2->sw_ack_vector;
 			/*
 			 * This is a message retry; clear the resources held
 			 * by the previous message only if they timed out.
 			 * If it has not timed out we have an unexpected
 			 * situation to report.
 			 */
-			if (mmr & (msg_res << 8)) {
+			if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
 				/*
 				 * is the resource timed out?
 				 * make everyone ignore the cancelled message.
@@ -179,9 +178,9 @@ static inline void uv_bau_process_retry_
 				cancel_count++;
 				uv_write_local_mmr(
 				    UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS,
-					(msg_res << 8) | msg_res);
-			} else
-				printk(KERN_INFO "note bau retry: no effect\n");
+					(msg_res << UV_SW_ACK_NPENDING) |
+					 msg_res);
+			}
 		}
 	}
 	if (!cancel_count)
@@ -317,13 +316,13 @@ uv_do_reset(void *ptr)
 			 */
 			mmr = uv_read_local_mmr
 					(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
-			msg_res = ((msg->sw_ack_vector << 8) |
-						   msg->sw_ack_vector);
+			msg_res = msg->sw_ack_vector;
 			if (mmr & msg_res) {
 				stat->d_rcanceled++;
 				uv_write_local_mmr(
 				    UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS,
-							msg_res);
+					(msg_res << UV_SW_ACK_NPENDING) |
+					 msg_res);
 			}
 		}
 	}

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

end of thread, other threads:[~2010-06-08 20:58 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 6/11] x86, UV: correct BAU software acknowledge Cliff Wickman
2010-06-08 20:57 ` [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®