perf, x86: Add hw_watchdog_set_attr() in a sake of nmi-watchdog on P4

Due to restriction and specifics of Netburst PMU we need a separated
event for NMI watchdog. In particular every Netburst event
consumes not just a counter and a config register, but also an
additional ESCR register.

Since ESCR registers are grouped upon counters (i.e. if ESCR is occupied
for some event there is no room for another event to enter until its
released) we need to pick up the "least" used ESCR (or the most available
one) for nmi-watchdog purposes -- so MSR_P4_CRU_ESCR2/3 was chosen.

With this patch nmi-watchdog and perf top should be able to run simultaneously.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: Lin Ming <ming.m.lin@intel.com>
CC: Arnaldo Carvalho de Melo <acme@redhat.com>
CC: Frederic Weisbecker <fweisbec@gmail.com>
Tested-and-reviewed-by: Don Zickus <dzickus@redhat.com>
Tested-and-reviewed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110623124918.GC13050@sun
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 38 insertions, 1 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3a0338b4b179..8a57f9aa8e36 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -233,6 +233,7 @@ struct x86_pmu {
         void            (*enable_all)(int added);
         void            (*enable)(struct perf_event *);
         void            (*disable)(struct perf_event *);
+        void            (*hw_watchdog_set_attr)(struct perf_event_attr *attr);
         int             (*hw_config)(struct perf_event *event);
         int             (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
         unsigned        eventsel;
@@ -315,6 +316,12 @@ static u64 __read_mostly hw_cache_extra_regs
                                 [PERF_COUNT_HW_CACHE_OP_MAX]
                                 [PERF_COUNT_HW_CACHE_RESULT_MAX];
 
+void hw_nmi_watchdog_set_attr(struct perf_event_attr *wd_attr)
+{
+        if (x86_pmu.hw_watchdog_set_attr)
+                x86_pmu.hw_watchdog_set_attr(wd_attr);
+}
+
 /*
  * Propagate event elapsed time into the generic event.
  * Can only be executed on the CPU where the event is active.
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ead584fb6a7d..f76fddf63381 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -705,6 +705,31 @@ static int p4_validate_raw_event(struct perf_event *event)
         return 0;
 }
 
+static void p4_hw_watchdog_set_attr(struct perf_event_attr *wd_attr)
+{
+        /*
+         * Watchdog ticks are special on Netburst, we use
+         * that named "non-sleeping" ticks as recommended
+         * by Intel SDM Vol3b.
+         */
+        WARN_ON_ONCE(wd_attr->type      != PERF_TYPE_HARDWARE ||
+                     wd_attr->config    != PERF_COUNT_HW_CPU_CYCLES);
+
+        wd_attr->type   = PERF_TYPE_RAW;
+        wd_attr->config =
+                p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_EXECUTION_EVENT)             |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0)            |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1)            |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2)            |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3)            |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0)             |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1)             |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2)             |
+                        P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3))            |
+                p4_config_pack_cccr(P4_CCCR_THRESHOLD(15) | P4_CCCR_COMPLEMENT          |
+                        P4_CCCR_COMPARE);
+}
+
 static int p4_hw_config(struct perf_event *event)
 {
         int cpu = get_cpu();
@@ -1179,6 +1204,7 @@ static __initconst const struct x86_pmu p4_pmu = {
         .cntval_bits            = ARCH_P4_CNTRVAL_BITS,
         .cntval_mask            = ARCH_P4_CNTRVAL_MASK,
         .max_period             = (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
+        .hw_watchdog_set_attr   = p4_hw_watchdog_set_attr,
         .hw_config              = p4_hw_config,
         .schedule_events        = p4_pmu_schedule_events,
         /*
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 3d0c56ad4792..752b75ba662b 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -200,6 +200,8 @@ static int is_softlockup(unsigned long touch_ts)
 }
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+void __weak hw_nmi_watchdog_set_attr(struct perf_event_attr *wd_attr) { }
+
 static struct perf_event_attr wd_hw_attr = {
         .type           = PERF_TYPE_HARDWARE,
         .config         = PERF_COUNT_HW_CPU_CYCLES,
@@ -368,9 +370,11 @@ static int watchdog_nmi_enable(int cpu)
         if (event != NULL)
                 goto out_enable;
 
-        /* Try to register using hardware perf events */
         wd_attr = &wd_hw_attr;
         wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
+        hw_nmi_watchdog_set_attr(wd_attr);
+
+        /* Try to register using hardware perf events */
         event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback);
         if (!IS_ERR(event)) {
                 printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n");