From 682e6b4da5cbe8e9a53f979a58c2a9d7dc997175 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 10 Apr 2018 21:49:32 +1000 Subject: rtc: opal: Fix OPAL RTC driver OPAL_BUSY loops The OPAL RTC driver does not sleep in case it gets OPAL_BUSY or OPAL_BUSY_EVENT from firmware, which causes large scheduling latencies, up to 50 seconds have been observed here when RTC stops responding (BMC reboot can do it). Fix this by converting it to the standard form OPAL_BUSY loop that sleeps. Fixes: 628daa8d5abf ("powerpc/powernv: Add RTC and NVRAM support plus RTAS fallbacks") Cc: stable@vger.kernel.org # v3.2+ Signed-off-by: Nicholas Piggin Acked-by: Alexandre Belloni Signed-off-by: Michael Ellerman --- drivers/rtc/rtc-opal.c | 37 +++++++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 14 deletions(-) (limited to 'drivers') diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c index 304e891e35fc..60f2250fd96b 100644 --- a/drivers/rtc/rtc-opal.c +++ b/drivers/rtc/rtc-opal.c @@ -57,7 +57,7 @@ static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms) static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) { - long rc = OPAL_BUSY; + s64 rc = OPAL_BUSY; int retries = 10; u32 y_m_d; u64 h_m_s_ms; @@ -66,13 +66,17 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) + if (rc == OPAL_BUSY_EVENT) { + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); - else if (retries-- && (rc == OPAL_HARDWARE - || rc == OPAL_INTERNAL_ERROR)) - msleep(10); - else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT) - break; + } else if (rc == OPAL_BUSY) { + msleep(OPAL_BUSY_DELAY_MS); + } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) { + if (retries--) { + msleep(10); /* Wait 10ms before retry */ + rc = OPAL_BUSY; /* go around again */ + } + } } if (rc != OPAL_SUCCESS) @@ -87,21 +91,26 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm) { - long rc = OPAL_BUSY; + s64 rc = OPAL_BUSY; int retries = 10; u32 y_m_d = 0; u64 h_m_s_ms = 0; tm_to_opal(tm, &y_m_d, &h_m_s_ms); + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_rtc_write(y_m_d, h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) + if (rc == OPAL_BUSY_EVENT) { + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); - else if (retries-- && (rc == OPAL_HARDWARE - || rc == OPAL_INTERNAL_ERROR)) - msleep(10); - else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT) - break; + } else if (rc == OPAL_BUSY) { + msleep(OPAL_BUSY_DELAY_MS); + } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) { + if (retries--) { + msleep(10); /* Wait 10ms before retry */ + rc = OPAL_BUSY; /* go around again */ + } + } } return rc == OPAL_SUCCESS ? 0 : -EIO; -- cgit v1.2.3 From c0f7f5b6c69107ca92909512533e70258ee19188 Mon Sep 17 00:00:00 2001 From: Shilpasri G Bhat Date: Wed, 25 Apr 2018 16:29:31 +0530 Subject: cpufreq: powernv: Fix hardlockup due to synchronous smp_call in timer interrupt gpstate_timer_handler() uses synchronous smp_call to set the pstate on the requested core. This causes the below hard lockup: smp_call_function_single+0x110/0x180 (unreliable) smp_call_function_any+0x180/0x250 gpstate_timer_handler+0x1e8/0x580 call_timer_fn+0x50/0x1c0 expire_timers+0x138/0x1f0 run_timer_softirq+0x1e8/0x270 __do_softirq+0x158/0x3e4 irq_exit+0xe8/0x120 timer_interrupt+0x9c/0xe0 decrementer_common+0x114/0x120 -- interrupt: 901 at doorbell_global_ipi+0x34/0x50 LR = arch_send_call_function_ipi_mask+0x120/0x130 arch_send_call_function_ipi_mask+0x4c/0x130 smp_call_function_many+0x340/0x450 pmdp_invalidate+0x98/0xe0 change_huge_pmd+0xe0/0x270 change_protection_range+0xb88/0xe40 mprotect_fixup+0x140/0x340 SyS_mprotect+0x1b4/0x350 system_call+0x58/0x6c One way to avoid this is removing the smp-call. We can ensure that the timer always runs on one of the policy-cpus. If the timer gets migrated to a cpu outside the policy then re-queue it back on the policy->cpus. This way we can get rid of the smp-call which was being used to set the pstate on the policy->cpus. Fixes: 7bc54b652f13 ("timers, cpufreq/powernv: Initialize the gpstate timer as pinned") Cc: stable@vger.kernel.org # v4.8+ Reported-by: Nicholas Piggin Reported-by: Pridhiviraj Paidipeddi Signed-off-by: Shilpasri G Bhat Acked-by: Nicholas Piggin Acked-by: Viresh Kumar Acked-by: Vaidyanathan Srinivasan Signed-off-by: Michael Ellerman --- drivers/cpufreq/powernv-cpufreq.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 0591874856d3..54edaec1e608 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -679,6 +679,16 @@ void gpstate_timer_handler(struct timer_list *t) if (!spin_trylock(&gpstates->gpstate_lock)) return; + /* + * If the timer has migrated to the different cpu then bring + * it back to one of the policy->cpus + */ + if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) { + gpstates->timer.expires = jiffies + msecs_to_jiffies(1); + add_timer_on(&gpstates->timer, cpumask_first(policy->cpus)); + spin_unlock(&gpstates->gpstate_lock); + return; + } /* * If PMCR was last updated was using fast_swtich then @@ -718,10 +728,8 @@ void gpstate_timer_handler(struct timer_list *t) if (gpstate_idx != gpstates->last_lpstate_idx) queue_gpstate_timer(gpstates); + set_pstate(&freq_data); spin_unlock(&gpstates->gpstate_lock); - - /* Timer may get migrated to a different cpu on cpu hot unplug */ - smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1); } /* -- cgit v1.2.3