diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt index 62328d76b55b..b0e911e0e8f5 100644 --- a/Documentation/power/pci.txt +++ b/Documentation/power/pci.txt @@ -979,20 +979,45 @@ every time right after the runtime_resume() callback has returned (alternatively, the runtime_suspend() callback will have to check if the device should really be suspended and return -EAGAIN if that is not the case). -The runtime PM of PCI devices is disabled by default. It is also blocked by -pci_pm_init() that runs the pm_runtime_forbid() helper function. If a PCI -driver implements the runtime PM callbacks and intends to use the runtime PM -framework provided by the PM core and the PCI subsystem, it should enable this -feature by executing the pm_runtime_enable() helper function. However, the -driver should not call the pm_runtime_allow() helper function unblocking -the runtime PM of the device. Instead, it should allow user space or some -platform-specific code to do that (user space can do it via sysfs), although -once it has called pm_runtime_enable(), it must be prepared to handle the +The runtime PM of PCI devices is enabled by default by the PCI core. PCI +device drivers do not need to enable it and should not attempt to do so. +However, it is blocked by pci_pm_init() that runs the pm_runtime_forbid() +helper function. In addition to that, the runtime PM usage counter of +each PCI device is incremented by local_pci_probe() before executing the +probe callback provided by the device's driver. + +If a PCI driver implements the runtime PM callbacks and intends to use the +runtime PM framework provided by the PM core and the PCI subsystem, it needs +to decrement the device's runtime PM usage counter in its probe callback +function. If it doesn't do that, the counter will always be different from +zero for the device and it will never be runtime-suspended. The simplest +way to do that is by calling pm_runtime_put_noidle(), but if the driver +wants to schedule an autosuspend right away, for example, it may call +pm_runtime_put_autosuspend() instead for this purpose. Generally, it +just needs to call a function that decrements the devices usage counter +from its probe routine to make runtime PM work for the device. + +It is important to remember that the driver's runtime_suspend() callback +may be executed right after the usage counter has been decremented, because +user space may already have cuased the pm_runtime_allow() helper function +unblocking the runtime PM of the device to run via sysfs, so the driver must +be prepared to cope with that. + +The driver itself should not call pm_runtime_allow(), though. Instead, it +should let user space or some platform-specific code do that (user space can +do it via sysfs as stated above), but it must be prepared to handle the runtime PM of the device correctly as soon as pm_runtime_allow() is called -(which may happen at any time). [It also is possible that user space causes -pm_runtime_allow() to be called via sysfs before the driver is loaded, so in -fact the driver has to be prepared to handle the runtime PM of the device as -soon as it calls pm_runtime_enable().] +(which may happen at any time, even before the driver is loaded). + +When the driver's remove callback runs, it has to balance the decrementation +of the device's runtime PM usage counter at the probe time. For this reason, +if it has decremented the counter in its probe callback, it must run +pm_runtime_get_noresume() in its remove callback. [Since the core carries +out a runtime resume of the device and bumps up the device's usage counter +before running the driver's remove callback, the runtime PM of the device +is effectively disabled for the duration of the remove execution and all +runtime PM helper functions incrementing the device's usage counter are +then effectively equivalent to pm_runtime_get_noresume().] The runtime PM framework works by processing requests to suspend or resume devices, or to check if they are idle (in which cases it is reasonable to diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 2614a839c60d..42c66b64c12c 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1044,8 +1044,10 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data) goto err_exit; mutex_lock(&ec->mutex); + result = -ENODATA; list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { + result = 0; q->handler = acpi_ec_get_query_handler(handler); ec_dbg_evt("Query(0x%02x) scheduled", q->handler->query_bit); diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 6da0f9beab19..c9336751e5e3 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -372,6 +372,7 @@ static int acpi_isa_register_gsi(struct pci_dev *dev) /* Interrupt Line values above 0xF are forbidden */ if (dev->irq > 0 && (dev->irq <= 0xF) && + acpi_isa_irq_available(dev->irq) && (acpi_isa_irq_to_gsi(dev->irq, &dev_gsi) == 0)) { dev_warn(&dev->dev, "PCI INT %c: no GSI - using ISA IRQ %d\n", pin_name(dev->pin), dev->irq); diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 3b4ea98e3ea0..7c8408b946ca 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -498,8 +498,7 @@ int __init acpi_irq_penalty_init(void) PIRQ_PENALTY_PCI_POSSIBLE; } } - /* Add a penalty for the SCI */ - acpi_irq_penalty[acpi_gbl_FADT.sci_interrupt] += PIRQ_PENALTY_PCI_USING; + return 0; } @@ -553,6 +552,13 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) irq = link->irq.possible[i]; } } + if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) { + printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. " + "Try pci=noacpi or acpi=off\n", + acpi_device_name(link->device), + acpi_device_bid(link->device)); + return -ENODEV; + } /* Attempt to enable the link device at this IRQ. */ if (acpi_pci_link_set(link, irq)) { @@ -821,6 +827,12 @@ void acpi_penalize_isa_irq(int irq, int active) } } +bool acpi_isa_irq_available(int irq) +{ + return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) || + acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS); +} + /* * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with * PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index 28cd75c535b0..7ae7cd990fbf 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -892,10 +892,17 @@ static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev) u32 microvolt[3] = {0}; int count, ret; - count = of_property_count_u32_elems(opp->np, "opp-microvolt"); - if (!count) + /* Missing property isn't a problem, but an invalid entry is */ + if (!of_find_property(opp->np, "opp-microvolt", NULL)) return 0; + count = of_property_count_u32_elems(opp->np, "opp-microvolt"); + if (count < 0) { + dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n", + __func__, count); + return count; + } + /* There can be one or three elements here */ if (count != 1 && count != 3) { dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n", @@ -1063,7 +1070,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add); * share a common logic which is isolated here. * * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the - * copy operation, returns 0 if no modifcation was done OR modification was + * copy operation, returns 0 if no modification was done OR modification was * successful. * * Locking: The internal device_opp and opp structures are RCU protected. @@ -1151,7 +1158,7 @@ unlock: * mutex locking or synchronize_rcu() blocking calls cannot be used. * * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the - * copy operation, returns 0 if no modifcation was done OR modification was + * copy operation, returns 0 if no modification was done OR modification was * successful. */ int dev_pm_opp_enable(struct device *dev, unsigned long freq) @@ -1177,7 +1184,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable); * mutex locking or synchronize_rcu() blocking calls cannot be used. * * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the - * copy operation, returns 0 if no modifcation was done OR modification was + * copy operation, returns 0 if no modification was done OR modification was * successful. */ int dev_pm_opp_disable(struct device *dev, unsigned long freq) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 3a3738fe016b..cd4510a63375 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -620,7 +620,7 @@ static struct cpuidle_state skl_cstates[] = { .name = "C6-SKL", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, - .exit_latency = 75, + .exit_latency = 85, .target_residency = 200, .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, @@ -636,10 +636,18 @@ static struct cpuidle_state skl_cstates[] = { .name = "C8-SKL", .desc = "MWAIT 0x40", .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, - .exit_latency = 174, + .exit_latency = 200, .target_residency = 800, .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, + { + .name = "C9-SKL", + .desc = "MWAIT 0x50", + .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 480, + .target_residency = 5000, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, { .name = "C10-SKL", .desc = "MWAIT 0x60", diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index dd652f2ae03d..108a3118ace7 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -299,9 +299,10 @@ static long local_pci_probe(void *_ddi) * Unbound PCI devices are always put in D0, regardless of * runtime PM status. During probe, the device is set to * active and the usage count is incremented. If the driver - * supports runtime PM, it should call pm_runtime_put_noidle() - * in its probe routine and pm_runtime_get_noresume() in its - * remove routine. + * supports runtime PM, it should call pm_runtime_put_noidle(), + * or any other runtime PM helper function decrementing the usage + * count, in its probe routine and pm_runtime_get_noresume() in + * its remove routine. */ pm_runtime_get_sync(dev); pci_dev->driver = pci_drv; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7235c4851460..43856d19cf4d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -217,6 +217,7 @@ struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); +bool acpi_isa_irq_available(int irq); void acpi_penalize_sci_irq(int irq, int trigger, int polarity); void acpi_pci_irq_disable (struct pci_dev *dev); diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9655cb49c7cb..bde0ef1a63df 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -71,8 +71,11 @@ unsigned int extra_msr_offset32; unsigned int extra_msr_offset64; unsigned int extra_delta_offset32; unsigned int extra_delta_offset64; +unsigned int aperf_mperf_multiplier = 1; int do_smi; double bclk; +double base_hz; +double tsc_tweak = 1.0; unsigned int show_pkg; unsigned int show_core; unsigned int show_cpu; @@ -502,7 +505,7 @@ int format_counters(struct thread_data *t, struct core_data *c, /* %Busy */ if (has_aperf) { if (!skip_c0) - outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc); + outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak); else outp += sprintf(outp, "********"); } @@ -510,7 +513,7 @@ int format_counters(struct thread_data *t, struct core_data *c, /* Bzy_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", - 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); + 1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float); /* TSC_MHz */ outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float); @@ -984,6 +987,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -3; if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) return -4; + t->aperf = t->aperf * aperf_mperf_multiplier; + t->mperf = t->mperf * aperf_mperf_multiplier; } if (do_smi) { @@ -1149,6 +1154,19 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; + +static void +calculate_tsc_tweak() +{ + unsigned long long msr; + unsigned int base_ratio; + + get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); + base_ratio = (msr >> 8) & 0xFF; + base_hz = base_ratio * bclk * 1000000; + tsc_tweak = base_hz / tsc_hz; +} + static void dump_nhm_platform_info(void) { @@ -1926,8 +1944,6 @@ int has_config_tdp(unsigned int family, unsigned int model) switch (model) { case 0x3A: /* IVB */ - case 0x3E: /* IVB Xeon */ - case 0x3C: /* HSW */ case 0x3F: /* HSX */ case 0x45: /* HSW */ @@ -2543,6 +2559,13 @@ int is_knl(unsigned int family, unsigned int model) return 0; } +unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model) +{ + if (is_knl(family, model)) + return 1024; + return 1; +} + #define SLM_BCLK_FREQS 5 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0}; @@ -2744,6 +2767,9 @@ void process_cpuid() } } + if (has_aperf) + aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model); + do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model); do_snb_cstates = has_snb_msrs(family, model); do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2); @@ -2762,6 +2788,9 @@ void process_cpuid() if (debug) dump_cstate_pstate_config_info(); + if (has_skl_msrs(family, model)) + calculate_tsc_tweak(); + return; } @@ -3090,7 +3119,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(stderr, "turbostat version 4.7 17-June, 2015" + fprintf(stderr, "turbostat version 4.8 26-Sep, 2015" " - Len Brown \n"); }