Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754085AbcCUJ6O (ORCPT ); Mon, 21 Mar 2016 05:58:14 -0400 Received: from [198.137.202.10] ([198.137.202.10]:45774 "EHLO terminus.zytor.com" rhost-flags-FAIL-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752002AbcCUJ57 (ORCPT ); Mon, 21 Mar 2016 05:57:59 -0400 Date: Mon, 21 Mar 2016 02:53:27 -0700 From: tip-bot for Vikas Shivappa Message-ID: Cc: vikas.shivappa@linux.intel.com, matt@codeblueprint.co.uk, namhyung@kernel.org, alexander.shishkin@linux.intel.com, vincent.weaver@maine.edu, peterz@infradead.org, linux-kernel@vger.kernel.org, brgerst@gmail.com, eranian@google.com, bp@alien8.de, dvlasenk@redhat.com, acme@redhat.com, mingo@kernel.org, torvalds@linux-foundation.org, luto@amacapital.net, tglx@linutronix.de, tony.luck@intel.com, jolsa@redhat.com, hpa@zytor.com, dsahern@gmail.com Reply-To: mingo@kernel.org, torvalds@linux-foundation.org, bp@alien8.de, acme@redhat.com, dvlasenk@redhat.com, dsahern@gmail.com, hpa@zytor.com, jolsa@redhat.com, tglx@linutronix.de, luto@amacapital.net, tony.luck@intel.com, vincent.weaver@maine.edu, alexander.shishkin@linux.intel.com, matt@codeblueprint.co.uk, namhyung@kernel.org, peterz@infradead.org, vikas.shivappa@linux.intel.com, eranian@google.com, linux-kernel@vger.kernel.org, brgerst@gmail.com In-Reply-To: <013b756c5006b1c4ca411f3ecf43ed52f19fbf87.1457723885.git.tony.luck@intel.com> References: <013b756c5006b1c4ca411f3ecf43ed52f19fbf87.1457723885.git.tony.luck@intel.com> To: linux-tip-commits@vger.kernel.org Subject: [tip:perf/urgent] perf/x86/mbm: Add support for MBM counter overflow handling Git-Commit-ID: e7ee3e8cb550ce43752ae1d1b190d6b5c4150a43 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8115 Lines: 278 Commit-ID: e7ee3e8cb550ce43752ae1d1b190d6b5c4150a43 Gitweb: http://git.kernel.org/tip/e7ee3e8cb550ce43752ae1d1b190d6b5c4150a43 Author: Vikas Shivappa AuthorDate: Fri, 11 Mar 2016 11:26:17 -0800 Committer: Ingo Molnar CommitDate: Mon, 21 Mar 2016 09:08:21 +0100 perf/x86/mbm: Add support for MBM counter overflow handling This patch adds a per package timer which periodically updates the memory bandwidth counters for the events that are currently active. Current patch has a periodic timer every 1s since the SDM guarantees that the counter will not overflow in 1s but this time can be definitely improved by calibrating on the system. The overflow is really a function of the max memory b/w that the socket can support, max counter value and scaling factor. Signed-off-by: Vikas Shivappa Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Tony Luck Acked-by: Thomas Gleixner Cc: Alexander Shishkin Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Brian Gerst Cc: David Ahern Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Matt Fleming Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Vince Weaver Cc: fenghua.yu@intel.com Cc: h.peter.anvin@intel.com Cc: ravi.v.shankar@intel.com Cc: vikas.shivappa@intel.com Link: http://lkml.kernel.org/r/013b756c5006b1c4ca411f3ecf43ed52f19fbf87.1457723885.git.tony.luck@intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/cqm.c | 139 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 134 insertions(+), 5 deletions(-) diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c index a98f472..380d62d 100644 --- a/arch/x86/events/intel/cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -14,10 +14,15 @@ #define MSR_IA32_QM_EVTSEL 0x0c8d #define MBM_CNTR_WIDTH 24 +/* + * Guaranteed time in ms as per SDM where MBM counters will not overflow. + */ +#define MBM_CTR_OVERFLOW_TIME 1000 static u32 cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ static bool cqm_enabled, mbm_enabled; +unsigned int mbm_socket_max; /** * struct intel_pqr_state - State cache for the PQR MSR @@ -45,6 +50,7 @@ struct intel_pqr_state { * interrupts disabled, which is sufficient for the protection. */ static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); +static struct hrtimer *mbm_timers; /** * struct sample - mbm event's (local or total) data * @total_bytes #bytes since we began monitoring @@ -945,6 +951,10 @@ static u64 update_sample(unsigned int rmid, u32 evt_type, int first) return mbm_current->total_bytes; } + /* + * The h/w guarantees that counters will not overflow + * so long as we poll them at least once per second. + */ shift = 64 - MBM_CNTR_WIDTH; bytes = (val << shift) - (mbm_current->prev_msr << shift); bytes >>= shift; @@ -1088,6 +1098,84 @@ static void __intel_mbm_event_count(void *info) atomic64_add(val, &rr->value); } +static enum hrtimer_restart mbm_hrtimer_handle(struct hrtimer *hrtimer) +{ + struct perf_event *iter, *iter1; + int ret = HRTIMER_RESTART; + struct list_head *head; + unsigned long flags; + u32 grp_rmid; + + /* + * Need to cache_lock as the timer Event Select MSR reads + * can race with the mbm/cqm count() and mbm_init() reads. + */ + raw_spin_lock_irqsave(&cache_lock, flags); + + if (list_empty(&cache_groups)) { + ret = HRTIMER_NORESTART; + goto out; + } + + list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { + grp_rmid = iter->hw.cqm_rmid; + if (!__rmid_valid(grp_rmid)) + continue; + if (is_mbm_event(iter->attr.config)) + update_sample(grp_rmid, iter->attr.config, 0); + + head = &iter->hw.cqm_group_entry; + if (list_empty(head)) + continue; + list_for_each_entry(iter1, head, hw.cqm_group_entry) { + if (!iter1->hw.is_group_event) + break; + if (is_mbm_event(iter1->attr.config)) + update_sample(iter1->hw.cqm_rmid, + iter1->attr.config, 0); + } + } + + hrtimer_forward_now(hrtimer, ms_to_ktime(MBM_CTR_OVERFLOW_TIME)); +out: + raw_spin_unlock_irqrestore(&cache_lock, flags); + + return ret; +} + +static void __mbm_start_timer(void *info) +{ + hrtimer_start(&mbm_timers[pkg_id], ms_to_ktime(MBM_CTR_OVERFLOW_TIME), + HRTIMER_MODE_REL_PINNED); +} + +static void __mbm_stop_timer(void *info) +{ + hrtimer_cancel(&mbm_timers[pkg_id]); +} + +static void mbm_start_timers(void) +{ + on_each_cpu_mask(&cqm_cpumask, __mbm_start_timer, NULL, 1); +} + +static void mbm_stop_timers(void) +{ + on_each_cpu_mask(&cqm_cpumask, __mbm_stop_timer, NULL, 1); +} + +static void mbm_hrtimer_init(void) +{ + struct hrtimer *hr; + int i; + + for (i = 0; i < mbm_socket_max; i++) { + hr = &mbm_timers[i]; + hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hr->function = mbm_hrtimer_handle; + } +} + static u64 intel_cqm_event_count(struct perf_event *event) { unsigned long flags; @@ -1217,8 +1305,14 @@ static int intel_cqm_event_add(struct perf_event *event, int mode) static void intel_cqm_event_destroy(struct perf_event *event) { struct perf_event *group_other = NULL; + unsigned long flags; mutex_lock(&cache_mutex); + /* + * Hold the cache_lock as mbm timer handlers could be + * scanning the list of events. + */ + raw_spin_lock_irqsave(&cache_lock, flags); /* * If there's another event in this group... @@ -1250,6 +1344,14 @@ static void intel_cqm_event_destroy(struct perf_event *event) } } + raw_spin_unlock_irqrestore(&cache_lock, flags); + + /* + * Stop the mbm overflow timers when the last event is destroyed. + */ + if (mbm_enabled && list_empty(&cache_groups)) + mbm_stop_timers(); + mutex_unlock(&cache_mutex); } @@ -1257,6 +1359,7 @@ static int intel_cqm_event_init(struct perf_event *event) { struct perf_event *group = NULL; bool rotate = false; + unsigned long flags; if (event->attr.type != intel_cqm_pmu.type) return -ENOENT; @@ -1282,9 +1385,21 @@ static int intel_cqm_event_init(struct perf_event *event) mutex_lock(&cache_mutex); + /* + * Start the mbm overflow timers when the first event is created. + */ + if (mbm_enabled && list_empty(&cache_groups)) + mbm_start_timers(); + /* Will also set rmid */ intel_cqm_setup_event(event, &group); + /* + * Hold the cache_lock as mbm timer handlers be + * scanning the list of events. + */ + raw_spin_lock_irqsave(&cache_lock, flags); + if (group) { list_add_tail(&event->hw.cqm_group_entry, &group->hw.cqm_group_entry); @@ -1303,6 +1418,7 @@ static int intel_cqm_event_init(struct perf_event *event) rotate = true; } + raw_spin_unlock_irqrestore(&cache_lock, flags); mutex_unlock(&cache_mutex); if (rotate) @@ -1536,20 +1652,33 @@ static const struct x86_cpu_id intel_mbm_total_match[] = { static int intel_mbm_init(void) { - int array_size, maxid = cqm_max_rmid + 1; + int ret = 0, array_size, maxid = cqm_max_rmid + 1; - array_size = sizeof(struct sample) * maxid * topology_max_packages(); + mbm_socket_max = topology_max_packages(); + array_size = sizeof(struct sample) * maxid * mbm_socket_max; mbm_local = kmalloc(array_size, GFP_KERNEL); if (!mbm_local) return -ENOMEM; mbm_total = kmalloc(array_size, GFP_KERNEL); if (!mbm_total) { - mbm_cleanup(); - return -ENOMEM; + ret = -ENOMEM; + goto out; } - return 0; + array_size = sizeof(struct hrtimer) * mbm_socket_max; + mbm_timers = kmalloc(array_size, GFP_KERNEL); + if (!mbm_timers) { + ret = -ENOMEM; + goto out; + } + mbm_hrtimer_init(); + +out: + if (ret) + mbm_cleanup(); + + return ret; } static int __init intel_cqm_init(void)