[PATCH] ppc64: silence perfmon exception warnings

Anton Blanchard anton at samba.org
Thu Jul 7 05:09:57 EST 2005


We dont need to use the PERFMON exception on POWER5, in fact the
firmware returns an error. Due to this just remove the warning.

Also now that we have proper runlatch support we can remove the bootup
hack.

Signed-off-by: Anton Blanchard <anton at samba.org>

Index: foobar2/arch/ppc64/kernel/sysfs.c
===================================================================
--- foobar2.orig/arch/ppc64/kernel/sysfs.c	2005-07-06 09:37:32.435185908 +1000
+++ foobar2/arch/ppc64/kernel/sysfs.c	2005-07-06 14:39:14.198111618 +1000
@@ -112,7 +112,6 @@
 	unsigned long hid0;
 #ifdef CONFIG_PPC_PSERIES
 	unsigned long set, reset;
-	int ret;
 #endif /* CONFIG_PPC_PSERIES */
 
 	/* Only need to enable them once */
@@ -145,11 +144,7 @@
 	case PLATFORM_PSERIES_LPAR:
 		set = 1UL << 63;
 		reset = 0;
-		ret = plpar_hcall_norets(H_PERFMON, set, reset);
-		if (ret)
-			printk(KERN_ERR "H_PERFMON call on cpu %u "
-			       "returned %d\n",
-			       smp_processor_id(), ret);
+		plpar_hcall_norets(H_PERFMON, set, reset);
 		break;
 #endif /* CONFIG_PPC_PSERIES */
 
@@ -161,13 +156,6 @@
 	/* instruct hypervisor to maintain PMCs */
 	if (cur_cpu_spec->firmware_features & FW_FEATURE_SPLPAR)
 		get_paca()->lppaca.pmcregs_in_use = 1;
-
-	/*
-	 * On SMT machines we have to set the run latch in the ctrl register
-	 * in order to make PMC6 spin.
-	 */
-	if (cpu_has_feature(CPU_FTR_SMT))
-		ppc64_runlatch_on();
 #endif /* CONFIG_PPC_PSERIES */
 }
 



More information about the Linuxppc64-dev mailing list