Skip to contentSkip to conversation

OProfile changes for v2.6.34

GIT PULL Ingo Molnar 1 participant 1 message Feb 27, 2010 x86

lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest oprofile-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git oprofile-for-linus

Thanks,

Ingo

------------------>
Naga Chumbalkar (1):
oprofile/x86: add comment to counter-in-use warning

Robert Richter (10):
oprofile: remove tracing build dependency
oprofile: remove EXPERIMENTAL from the config option description oprofile/x86: remove OPROFILE_IBS config option oprofile/x86: remove node check in AMD IBS initialization oprofile/x86: implement IBS cpuid feature detection oprofile/x86: implement randomization for IBS periodic op counter oprofile/x86: warn user if a counter is already active oprofile/x86: fix perfctr nmi reservation for mulitplexing oprofile/x86: use kzalloc() instead of kmalloc() oprofile/x86: fix msr access to reserved counters

Suravee Suthikulpanit (1):
oprofile/x86: implement lsfr pseudo-random number generator for IBS

 arch/Kconfig                      |   18 +---
 arch/x86/oprofile/nmi_int.c       |   17 ++--
 arch/x86/oprofile/op_model_amd.c  |  244 ++++++++++++++++++++++++-------------
 arch/x86/oprofile/op_model_p4.c   |    6 -
 arch/x86/oprofile/op_model_ppro.c |   17 ++-
 arch/x86/oprofile/op_x86_model.h  |   20 +++
 init/Kconfig                      |    2 +-
 7 files changed, 200 insertions(+), 124 deletions(-)
arch/Kconfig +1 -17
index 9d055b4..06a1372 100644
@@ -3,11 +3,9 @@
 #
 
 config OPROFILE
-	tristate "OProfile system profiling (EXPERIMENTAL)"
+	tristate "OProfile system profiling"
 	depends on PROFILING
 	depends on HAVE_OPROFILE
-	depends on TRACING_SUPPORT
-	select TRACING
 	select RING_BUFFER
 	select RING_BUFFER_ALLOW_SWAP
 	help
@@ -17,20 +15,6 @@ config OPROFILE
 
 	  If unsure, say N.
 
-config OPROFILE_IBS
-	bool "OProfile AMD IBS support (EXPERIMENTAL)"
-	default n
-	depends on OPROFILE && SMP && X86
-	help
-          Instruction-Based Sampling (IBS) is a new profiling
-          technique that provides rich, precise program performance
-          information. IBS is introduced by AMD Family10h processors
-          (AMD Opteron Quad-Core processor "Barcelona") to overcome
-          the limitations of conventional performance counter
-          sampling.
-
-	  If unsure, say N.
-
 config OPROFILE_EVENT_MULTIPLEX
 	bool "OProfile multiplexing support (EXPERIMENTAL)"
 	default n
arch/x86/oprofile/nmi_int.c +9 -8
index 3347f69..2c505ee 100644
@@ -159,7 +159,7 @@ static int nmi_setup_mux(void)
 
 	for_each_possible_cpu(i) {
 		per_cpu(cpu_msrs, i).multiplex =
-			kmalloc(multiplex_size, GFP_KERNEL);
+			kzalloc(multiplex_size, GFP_KERNEL);
 		if (!per_cpu(cpu_msrs, i).multiplex)
 			return 0;
 	}
@@ -179,7 +179,6 @@ static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs)
 		if (counter_config[i].enabled) {
 			multiplex[i].saved = -(u64)counter_config[i].count;
 		} else {
-			multiplex[i].addr  = 0;
 			multiplex[i].saved = 0;
 		}
 	}
@@ -189,25 +188,27 @@ static void nmi_cpu_setup_mux(int cpu, struct op_msrs const * const msrs)
 
 static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs)
 {
+	struct op_msr *counters = msrs->counters;
 	struct op_msr *multiplex = msrs->multiplex;
 	int i;
 
 	for (i = 0; i < model->num_counters; ++i) {
 		int virt = op_x86_phys_to_virt(i);
-		if (multiplex[virt].addr)
-			rdmsrl(multiplex[virt].addr, multiplex[virt].saved);
+		if (counters[i].addr)
+			rdmsrl(counters[i].addr, multiplex[virt].saved);
 	}
 }
 
 static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs)
 {
+	struct op_msr *counters = msrs->counters;
 	struct op_msr *multiplex = msrs->multiplex;
 	int i;
 
 	for (i = 0; i < model->num_counters; ++i) {
 		int virt = op_x86_phys_to_virt(i);
-		if (multiplex[virt].addr)
-			wrmsrl(multiplex[virt].addr, multiplex[virt].saved);
+		if (counters[i].addr)
+			wrmsrl(counters[i].addr, multiplex[virt].saved);
 	}
 }
 
@@ -303,11 +304,11 @@ static int allocate_msrs(void)
 
 	int i;
 	for_each_possible_cpu(i) {
-		per_cpu(cpu_msrs, i).counters = kmalloc(counters_size,
+		per_cpu(cpu_msrs, i).counters = kzalloc(counters_size,
 							GFP_KERNEL);
 		if (!per_cpu(cpu_msrs, i).counters)
 			return 0;
-		per_cpu(cpu_msrs, i).controls = kmalloc(controls_size,
+		per_cpu(cpu_msrs, i).controls = kzalloc(controls_size,
 							GFP_KERNEL);
 		if (!per_cpu(cpu_msrs, i).controls)
 			return 0;
arch/x86/oprofile/op_model_amd.c +158 -86

427 lines not on this page · raw message

arch/x86/oprofile/op_model_p4.c +0 -6
index ac6b354..e6a160a 100644
@@ -394,12 +394,6 @@ static void p4_fill_in_addresses(struct op_msrs * const msrs)
 	setup_num_counters();
 	stag = get_stagger();
 
-	/* initialize some registers */
-	for (i = 0; i < num_counters; ++i)
-		msrs->counters[i].addr = 0;
-	for (i = 0; i < num_controls; ++i)
-		msrs->controls[i].addr = 0;
-
 	/* the counter & cccr registers we pay attention to */
 	for (i = 0; i < num_counters; ++i) {
 		addr = p4_counters[VIRT_CTR(stag, i)].counter_address;
arch/x86/oprofile/op_model_ppro.c +11 -6
index 8eb0587..5d1727b 100644
@@ -37,15 +37,11 @@ static void ppro_fill_in_addresses(struct op_msrs * const msrs)
 	for (i = 0; i < num_counters; i++) {
 		if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
 			msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
-		else
-			msrs->counters[i].addr = 0;
 	}
 
 	for (i = 0; i < num_counters; i++) {
 		if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
 			msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
-		else
-			msrs->controls[i].addr = 0;
 	}
 }
 
@@ -57,7 +53,7 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
 	int i;
 
 	if (!reset_value) {
-		reset_value = kmalloc(sizeof(reset_value[0]) * num_counters,
+		reset_value = kzalloc(sizeof(reset_value[0]) * num_counters,
 					GFP_ATOMIC);
 		if (!reset_value)
 			return;
@@ -82,9 +78,18 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
 
 	/* clear all counters */
 	for (i = 0; i < num_counters; ++i) {
-		if (unlikely(!msrs->controls[i].addr))
+		if (unlikely(!msrs->controls[i].addr)) {
+			if (counter_config[i].enabled && !smp_processor_id())
+				/*
+				 * counter is reserved, this is on all
+				 * cpus, so report only for cpu #0
+				 */
+				op_x86_warn_reserved(i);
 			continue;
+		}
 		rdmsrl(msrs->controls[i].addr, val);
+		if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+			op_x86_warn_in_use(i);
 		val &= model->reserved;
 		wrmsrl(msrs->controls[i].addr, val);
 	}
arch/x86/oprofile/op_x86_model.h +20 -0
index 7b8e75d..ff82a75 100644
@@ -57,6 +57,26 @@ struct op_x86_model_spec {
 
 struct op_counter_config;
 
+static inline void op_x86_warn_in_use(int counter)
+{
+	/*
+	 * The warning indicates an already running counter. If
+	 * oprofile doesn't collect data, then try using a different
+	 * performance counter on your platform to monitor the desired
+	 * event. Delete counter #%d from the desired event by editing
+	 * the /usr/share/oprofile/%s/<cpu>/events file. If the event
+	 * cannot be monitored by any other counter, contact your
+	 * hardware or BIOS vendor.
+	 */
+	pr_warning("oprofile: counter #%d on cpu #%d may already be used\n",
+		   counter, smp_processor_id());
+}
+
+static inline void op_x86_warn_reserved(int counter)
+{
+	pr_warning("oprofile: counter #%d is already reserved\n", counter);
+}
+
 extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 			   struct op_counter_config *counter_config);
 extern int op_x86_phys_to_virt(int phys);
init/Kconfig +1 -1
index d95ca7c..b7c5839 100644
@@ -1112,7 +1112,7 @@ config MMAP_ALLOW_UNINITIALIZED
 	  See Documentation/nommu-mmap.txt for more information.
 
 config PROFILING
-	bool "Profiling support (EXPERIMENTAL)"
+	bool "Profiling support"
 	help
 	  Say Y here to enable the extended profiling support mechanisms used
 	  by profilers such as OProfile.