| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1384275531-10892-5-git-send-email-eranian@google.com>
Date: Tue, 12 Nov 2013 17:58:51 +0100
From: Stephane Eranian <eranian@...gle.com>
To: linux-kernel@...r.kernel.org
Cc: peterz@...radead.org, mingo@...e.hu, ak@...ux.intel.com,
acme@...hat.com, jolsa@...hat.com, zheng.z.yan@...el.com,
bp@...en8.de, maria.n.dimakopoulou@...il.com
Subject: [PATCH v7 4/4] perf,x86: add RAPL hrtimer support
The RAPL PMU counters do not interrupt on overflow.
Therefore, the kernel needs to poll the counters
to avoid missing an overflow. This patch adds
the hrtimer code to do this.
The timer interval is calculated at boot time
based on the power unit used by the HW.
There is one hrtimer per-cpu to handle the case
of multiple simultaneous use across cores on
the same package + hotplug CPU.
Signed-off-by: Stephane Eranian <eranian@...gle.com>
---
arch/x86/kernel/cpu/perf_event_intel_rapl.c | 74 ++++++++++++++++++++++++++-
1 file changed, 72 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index cfcd386..a6f16ca 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -96,6 +96,8 @@ struct rapl_pmu {
int n_active; /* number of active events */
struct list_head active_list;
struct pmu *pmu; /* pointer to rapl_pmu_class */
+ ktime_t timer_interval; /* in ktime_t unit */
+ struct hrtimer hrtimer;
};
static struct pmu rapl_pmu_class;
@@ -158,6 +160,48 @@ static u64 rapl_event_update(struct perf_event *event)
return new_raw_count;
}
+static void rapl_start_hrtimer(struct rapl_pmu *pmu)
+{
+ __hrtimer_start_range_ns(&pmu->hrtimer,
+ pmu->timer_interval, 0,
+ HRTIMER_MODE_REL_PINNED, 0);
+}
+
+static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
+{
+ hrtimer_cancel(&pmu->hrtimer);
+}
+
+static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
+{
+ struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct perf_event *event;
+ unsigned long flags;
+
+ if (!pmu->n_active)
+ return HRTIMER_NORESTART;
+
+ spin_lock_irqsave(&pmu->lock, flags);
+
+ list_for_each_entry(event, &pmu->active_list, active_entry) {
+ rapl_event_update(event);
+ }
+
+ spin_unlock_irqrestore(&pmu->lock, flags);
+
+ hrtimer_forward_now(hrtimer, pmu->timer_interval);
+
+ return HRTIMER_RESTART;
+}
+
+static void rapl_hrtimer_init(struct rapl_pmu *pmu)
+{
+ struct hrtimer *hr = &pmu->hrtimer;
+
+ hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hr->function = rapl_hrtimer_handle;
+}
+
static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
struct perf_event *event)
{
@@ -171,6 +215,8 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
local64_set(&event->hw.prev_count, rapl_read_counter(event));
pmu->n_active++;
+ if (pmu->n_active == 1)
+ rapl_start_hrtimer(pmu);
}
static void rapl_pmu_event_start(struct perf_event *event, int mode)
@@ -195,6 +241,8 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
if (!(hwc->state & PERF_HES_STOPPED)) {
WARN_ON_ONCE(pmu->n_active <= 0);
pmu->n_active--;
+ if (pmu->n_active == 0)
+ rapl_stop_hrtimer(pmu);
list_del(&event->active_entry);
@@ -423,6 +471,9 @@ static void rapl_cpu_exit(int cpu)
*/
if (target >= 0)
perf_pmu_migrate_context(pmu->pmu, cpu, target);
+
+ /* cancel overflow polling timer for CPU */
+ rapl_stop_hrtimer(pmu);
}
static void rapl_cpu_init(int cpu)
@@ -442,6 +493,7 @@ static int rapl_cpu_prepare(int cpu)
{
struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
int phys_id = topology_physical_package_id(cpu);
+ u64 ms;
if (pmu)
return 0;
@@ -466,6 +518,22 @@ static int rapl_cpu_prepare(int cpu)
pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
pmu->pmu = &rapl_pmu_class;
+ /*
+ * use reference of 200W for scaling the timeout
+ * to avoid missing counter overflows.
+ * 200W = 200 Joules/sec
+ * divide interval by 2 to avoid lockstep (2 * 100)
+ * if hw unit is 32, then we use 2 ms 1/200/2
+ */
+ if (pmu->hw_unit < 32)
+ ms = 1000 * (1ULL << (32 - pmu->hw_unit - 1)) / (2 * 100);
+ else
+ ms = 2;
+
+ pmu->timer_interval = ms_to_ktime(ms);
+
+ rapl_hrtimer_init(pmu);
+
/* set RAPL pmu for this cpu for now */
per_cpu(rapl_pmu, cpu) = pmu;
per_cpu(rapl_pmu_to_free, cpu) = NULL;
@@ -580,9 +648,11 @@ static int __init rapl_pmu_init(void)
pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
" API unit is 2^-32 Joules,"
- " %d fixed counters\n",
+ " %d fixed counters"
+ " %llu ms ovfl timer\n",
pmu->hw_unit,
- hweight32(rapl_cntr_mask));
+ hweight32(rapl_cntr_mask),
+ ktime_to_ms(pmu->timer_interval));
put_online_cpus();
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists