diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index fd5a1f365c95..3cce71413d0b 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -96,11 +96,15 @@ #define MSR_IA32_MC0_ADDR 0x00000402 #define MSR_IA32_MC0_MISC 0x00000403 +#define MSR_AMD64_MC0_MASK 0xc0010044 + #define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) #define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x)) #define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x)) #define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x)) +#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x)) + /* These are consecutive and not in the normal 4er MCE bank block */ #define MSR_IA32_MC0_CTL2 0x00000280 #define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3ecece0217ef..3532d3bf8105 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* As a rule processors have APIC timer running in deep C states */ if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400)) set_cpu_cap(c, X86_FEATURE_ARAT); + + /* + * Disable GART TLB Walk Errors on Fam10h. We do this here + * because this is always needed when GART is enabled, even in a + * kernel which has no MCE support built in. + */ + if (c->x86 == 0x10) { + /* + * BIOS should disable GartTlbWlk Errors themself. If + * it doesn't do it here as suggested by the BKDG. + * + * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 + */ + u64 mask; + + rdmsrl(MSR_AMD64_MCx_MASK(4), mask); + mask |= (1 << 10); + wrmsrl(MSR_AMD64_MCx_MASK(4), mask); + } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2871d3c71b6..8ed8908cc9f7 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -312,6 +312,26 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } +static void __cpuinit check_cpu_siblings_on_same_node(int cpu1, int cpu2) +{ + int node1 = early_cpu_to_node(cpu1); + int node2 = early_cpu_to_node(cpu2); + + /* + * Our CPU scheduler assumes all logical cpus in the same physical cpu + * share the same node. But, buggy ACPI or NUMA emulation might assign + * them to different node. Fix it. + */ + if (node1 != node2) { + pr_warning("CPU %d in node %d and CPU %d in node %d are in the same physical CPU. forcing same node %d\n", + cpu1, node1, cpu2, node2, node2); + + numa_remove_cpu(cpu1); + numa_set_node(cpu1, node2); + numa_add_cpu(cpu1); + } +} + static void __cpuinit link_thread_siblings(int cpu1, int cpu2) { cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); @@ -320,6 +340,7 @@ static void __cpuinit link_thread_siblings(int cpu1, int cpu2) cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); + check_cpu_siblings_on_same_node(cpu1, cpu2); } @@ -361,10 +382,12 @@ void __cpuinit set_cpu_sibling_map(int cpu) per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); /* * Does this new cpu bringup a new core? */ diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts index dc701ea58546..2d6d226f2b10 100644 --- a/arch/x86/platform/ce4100/falconfalls.dts +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -74,6 +74,7 @@ pci@1,0 { compatible = "intel,ce4100-pci", "pci"; device_type = "pci"; bus-range = <1 1>; + reg = <0x0800 0x0 0x0 0x0 0x0>; ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>; interrupt-parent = <&ioapic2>; @@ -412,6 +413,7 @@ isa@1f,0 { #address-cells = <2>; #size-cells = <1>; compatible = "isa"; + reg = <0xf800 0x0 0x0 0x0 0x0>; ranges = <1 0 0 0 0 0x100>; rtc@70 { diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 5c0207bf959b..275dbc19e2cf 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -97,11 +97,11 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table) pentry->freq_hz, pentry->irq); if (!pentry->irq) continue; - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; /* triggering mode edge bit 2-3, active high polarity bit 0-1 */ mp_irq.irqflag = 5; - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -168,10 +168,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) { pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->irq); - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; mp_irq.irqflag = 0xf; /* level trigger and active low */ - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -282,7 +282,7 @@ void __init x86_mrst_early_setup(void) /* Avoid searching for BIOS MP tables */ x86_init.mpparse.find_smp_config = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; - + set_bit(MP_BUS_ISA, mp_bus_not_pci); } /* diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 09b4437b3e61..39013867cbd6 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -171,7 +171,7 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, err = __rtc_read_alarm(rtc, &alrm); if (!err && !rtc_valid_tm(&alrm.time)) - rtc_set_alarm(rtc, &alrm); + rtc_initialize_alarm(rtc, &alrm); strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE); dev_set_name(&rtc->dev, "rtc%d", id); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 23719f0acbf6..ef6316acec43 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -375,6 +375,32 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) } EXPORT_SYMBOL_GPL(rtc_set_alarm); +/* Called once per device from rtc_device_register */ +int rtc_initialize_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) +{ + int err; + + err = rtc_valid_tm(&alarm->time); + if (err != 0) + return err; + + err = mutex_lock_interruptible(&rtc->ops_lock); + if (err) + return err; + + rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time); + rtc->aie_timer.period = ktime_set(0, 0); + if (alarm->enabled) { + rtc->aie_timer.enabled = 1; + timerqueue_add(&rtc->timerqueue, &rtc->aie_timer.node); + } + mutex_unlock(&rtc->ops_lock); + return err; +} +EXPORT_SYMBOL_GPL(rtc_initialize_alarm); + + + int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled) { int err = mutex_lock_interruptible(&rtc->ops_lock); diff --git a/drivers/rtc/rtc-bfin.c b/drivers/rtc/rtc-bfin.c index a0fc4cf42abf..90d866272c8e 100644 --- a/drivers/rtc/rtc-bfin.c +++ b/drivers/rtc/rtc-bfin.c @@ -250,6 +250,8 @@ static int bfin_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) bfin_rtc_int_set_alarm(rtc); else bfin_rtc_int_clear(~(RTC_ISTAT_ALARM | RTC_ISTAT_ALARM_DAY)); + + return 0; } static int bfin_rtc_read_time(struct device *dev, struct rtc_time *tm) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 714964913e5e..b3466c491cd3 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -336,7 +336,6 @@ static void s3c_rtc_release(struct device *dev) /* do not clear AIE here, it may be needed for wake */ - s3c_rtc_setpie(dev, 0); free_irq(s3c_rtc_alarmno, rtc_dev); free_irq(s3c_rtc_tickno, rtc_dev); } @@ -408,7 +407,6 @@ static int __devexit s3c_rtc_remove(struct platform_device *dev) platform_set_drvdata(dev, NULL); rtc_device_unregister(rtc); - s3c_rtc_setpie(&dev->dev, 0); s3c_rtc_setaie(&dev->dev, 0); clk_disable(rtc_clk); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 2ca7e8a78060..877ece45426f 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -228,6 +228,8 @@ extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); +extern int rtc_initialize_alarm(struct rtc_device *rtc, + struct rtc_wkalrm *alrm); extern void rtc_update_irq(struct rtc_device *rtc, unsigned long num, unsigned long events); diff --git a/kernel/futex.c b/kernel/futex.c index dfb924ffe65b..fe28dc282eae 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1886,7 +1886,7 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, restart->futex.val = val; restart->futex.time = abs_time->tv64; restart->futex.bitset = bitset; - restart->futex.flags = flags; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; ret = -ERESTART_RESTARTBLOCK; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 27960f114efd..8e81a9860a0d 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode) } if (mode & PERF_CGROUP_SWIN) { + WARN_ON_ONCE(cpuctx->cgrp); /* set cgrp before ctxsw in to * allow event_filter_match() to not * have to pass task around @@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) if (!ctx || !ctx->nr_events) goto out; + /* + * We must ctxsw out cgroup events to avoid conflict + * when invoking perf_task_event_sched_in() later on + * in this function. Otherwise we end up trying to + * ctxswin cgroup events which are already scheduled + * in. + */ + perf_cgroup_sched_out(current); task_ctx_sched_out(ctx, EVENT_ALL); raw_spin_lock(&ctx->lock); @@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) raw_spin_unlock(&ctx->lock); + /* + * Also calls ctxswin for cgroup events, if any: + */ perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 7f00772e57c9..6fa833ab2cb8 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2104,21 +2104,20 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, struct cfs_rq *busiest_cfs_rq) { - int loops = 0, pulled = 0, pinned = 0; + int loops = 0, pulled = 0; long rem_load_move = max_load_move; struct task_struct *p, *n; if (max_load_move == 0) goto out; - pinned = 1; - list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) { if (loops++ > sysctl_sched_nr_migrate) break; if ((p->se.load.weight >> 1) > rem_load_move || - !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) + !can_migrate_task(p, busiest, this_cpu, sd, idle, + all_pinned)) continue; pull_task(busiest, p, this_rq, this_cpu); @@ -2153,9 +2152,6 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, */ schedstat_add(sd, lb_gained[idle], pulled); - if (all_pinned) - *all_pinned = pinned; - return max_load_move - rem_load_move; } @@ -3127,6 +3123,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; + sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + /* * If the busiest group is imbalanced the below checks don't * work because they assumes all things are equal, which typically @@ -3151,7 +3149,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * Don't pull any tasks if this group is already above the domain * average load. */ - sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; if (sds.this_load >= sds.avg_load) goto out_balanced; @@ -3340,6 +3337,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, * still unbalanced. ld_moved simply stays zero, so it is * correctly treated as an imbalance. */ + all_pinned = 1; local_irq_save(flags); double_rq_lock(this_rq, busiest); ld_moved = move_tasks(this_rq, this_cpu, busiest, diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 9fea75535221..96bee5c46008 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -13,7 +13,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) { FILE *fp; char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1]; - char *token, *saved_ptr; + char *token, *saved_ptr = NULL; int found = 0; fp = fopen("/proc/mounts", "r");