#address-cells = <1>;
#size-cells = <0>;
+ idle-states {
+ entry-method = "psci";
+
+ cpu_pd_wait: cpu-pd-wait {
+ compatible = "arm,idle-state";
+ arm,psci-suspend-param = <0x0010033>;
+ local-timer-stop;
+ entry-latency-us = <1000>;
+ exit-latency-us = <700>;
+ min-residency-us = <2700>;
+ };
+ };
+
A53_0: cpu@0 {
device_type = "cpu";
compatible = "arm,cortex-a53";
operating-points-v2 = <&a53_opp_table>;
nvmem-cells = <&cpu_speed_grade>;
nvmem-cell-names = "speed_grade";
+ cpu-idle-states = <&cpu_pd_wait>;
};
A53_1: cpu@1 {
enable-method = "psci";
next-level-cache = <&A53_L2>;
operating-points-v2 = <&a53_opp_table>;
+ cpu-idle-states = <&cpu_pd_wait>;
};
A53_2: cpu@2 {
enable-method = "psci";
next-level-cache = <&A53_L2>;
operating-points-v2 = <&a53_opp_table>;
+ cpu-idle-states = <&cpu_pd_wait>;
};
A53_3: cpu@3 {
enable-method = "psci";
next-level-cache = <&A53_L2>;
operating-points-v2 = <&a53_opp_table>;
+ cpu-idle-states = <&cpu_pd_wait>;
};
A53_L2: l2-cache0 {
opp-microvolt = <850000>;
opp-supported-hw = <0xe>, <0x7>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
opp-1600000000 {
opp-microvolt = <900000>;
opp-supported-hw = <0xc>, <0x7>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
opp-1800000000 {
opp-hz = /bits/ 64 <1800000000>;
opp-microvolt = <1000000>;
- /* Consumer only but rely on speed grading */
- opp-supported-hw = <0x8>, <0x7>;
+ opp-supported-hw = <0x8>, <0x3>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
};
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 10 30>;
};
gpio2: gpio@30210000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 40 21>;
};
gpio3: gpio@30220000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 61 26>;
};
gpio4: gpio@30230000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 87 32>;
};
gpio5: gpio@30240000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 119 30>;
};
wdog1: watchdog@30280000 {
<&clk_ext3>, <&clk_ext4>;
clock-names = "osc_32k", "osc_24m", "clk_ext1", "clk_ext2",
"clk_ext3", "clk_ext4";
+ assigned-clocks = <&clk IMX8MM_CLK_NOC>,
+ <&clk IMX8MM_CLK_AUDIO_AHB>,
+ <&clk IMX8MM_CLK_IPG_AUDIO_ROOT>,
+ <&clk IMX8MM_SYS_PLL3>,
+ <&clk IMX8MM_VIDEO_PLL1>;
+ assigned-clock-parents = <&clk IMX8MM_SYS_PLL3_OUT>,
+ <&clk IMX8MM_SYS_PLL1_800M>;
+ assigned-clock-rates = <0>,
+ <400000000>,
+ <400000000>,
+ <750000000>,
+ <594000000>;
};
src: reset-controller@30390000 {
- compatible = "fsl,imx8mm-src", "syscon";
+ compatible = "fsl,imx8mm-src", "fsl,imx8mq-src", "syscon";
reg = <0x30390000 0x10000>;
interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
#reset-cells = <1>;
#pwm-cells = <2>;
status = "disabled";
};
+
+ system_counter: timer@306a0000 {
+ compatible = "nxp,sysctr-timer";
+ reg = <0x306a0000 0x20000>;
+ interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&osc_24m>;
+ clock-names = "per";
+ };
};
aips3: bus@30800000 {
interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MM_CLK_USB1_CTRL_ROOT>;
clock-names = "usb1_ctrl_root_clk";
- assigned-clocks = <&clk IMX8MM_CLK_USB_BUS>,
- <&clk IMX8MM_CLK_USB_CORE_REF>;
- assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>,
- <&clk IMX8MM_SYS_PLL1_100M>;
+ assigned-clocks = <&clk IMX8MM_CLK_USB_BUS>;
+ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>;
fsl,usbphy = <&usbphynop1>;
fsl,usbmisc = <&usbmisc1 0>;
status = "disabled";
interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MM_CLK_USB1_CTRL_ROOT>;
clock-names = "usb1_ctrl_root_clk";
- assigned-clocks = <&clk IMX8MM_CLK_USB_BUS>,
- <&clk IMX8MM_CLK_USB_CORE_REF>;
- assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>,
- <&clk IMX8MM_SYS_PLL1_100M>;
+ assigned-clocks = <&clk IMX8MM_CLK_USB_BUS>;
+ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>;
fsl,usbphy = <&usbphynop2>;
fsl,usbmisc = <&usbmisc2 0>;
status = "disabled";
interrupt-controller;
interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
};
+
+ ddr-pmu@3d800000 {
+ compatible = "fsl,imx8mm-ddr-pmu", "fsl,imx8m-ddr-pmu";
+ reg = <0x3d800000 0x400000>;
+ interrupt-parent = <&gic>;
+ interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+ };
};
};
/* Industrial only */
opp-supported-hw = <0xf>, <0x4>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
opp-1000000000 {
/* Consumer only */
opp-supported-hw = <0xe>, <0x3>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
opp-1300000000 {
opp-hz = /bits/ 64 <1300000000>;
opp-microvolt = <1000000>;
- opp-supported-hw = <0xc>, <0x7>;
+ opp-supported-hw = <0xc>, <0x4>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
opp-1500000000 {
opp-hz = /bits/ 64 <1500000000>;
opp-microvolt = <1000000>;
- /* Consumer only but rely on speed grading */
- opp-supported-hw = <0x8>, <0x7>;
+ opp-supported-hw = <0x8>, <0x3>;
clock-latency-ns = <150000>;
+ opp-suspend;
};
};
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 10 30>;
};
gpio2: gpio@30210000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 40 21>;
};
gpio3: gpio@30220000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 61 26>;
};
gpio4: gpio@30230000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 87 32>;
};
gpio5: gpio@30240000 {
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
+ gpio-ranges = <&iomuxc 0 119 30>;
};
tmu: tmu@30260000 {
compatible = "fsl,imx8mq-tmu";
reg = <0x30260000 0x10000>;
interrupt = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clk IMX8MQ_CLK_TMU_ROOT>;
little-endian;
fsl,tmu-range = <0xb0000 0xa0026 0x80048 0x70061>;
fsl,tmu-calibration = <0x00000000 0x00000023
};
iomuxc_gpr: syscon@30340000 {
- compatible = "fsl,imx8mq-iomuxc-gpr", "fsl,imx6q-iomuxc-gpr", "syscon";
+ compatible = "fsl,imx8mq-iomuxc-gpr", "fsl,imx6q-iomuxc-gpr",
+ "syscon", "simple-mfd";
reg = <0x30340000 0x10000>;
+
+ mux: mux-controller {
+ compatible = "mmio-mux";
+ #mux-control-cells = <1>;
+ mux-reg-masks = <0x34 0x00000004>; /* MIPI_MUX_SEL */
+ };
};
ocotp: ocotp-ctrl@30350000 {
#pwm-cells = <2>;
status = "disabled";
};
+
+ system_counter: timer@306a0000 {
+ compatible = "nxp,sysctr-timer";
+ reg = <0x306a0000 0x20000>;
+ interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&osc_25m>;
+ clock-names = "per";
+ };
};
bus@30800000 { /* AIPS3 */
sai2: sai@308b0000 {
#sound-dai-cells = <0>;
- compatible = "fsl,imx8mq-sai",
- "fsl,imx6sx-sai";
+ compatible = "fsl,imx8mq-sai";
reg = <0x308b0000 0x10000>;
interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MQ_CLK_SAI2_IPG>,
status = "disabled";
};
+ dphy: dphy@30a00300 {
+ compatible = "fsl,imx8mq-mipi-dphy";
+ reg = <0x30a00300 0x100>;
+ clocks = <&clk IMX8MQ_CLK_DSI_PHY_REF>;
+ clock-names = "phy_ref";
+ assigned-clocks = <&clk IMX8MQ_CLK_DSI_PHY_REF>;
+ assigned-clock-parents = <&clk IMX8MQ_VIDEO_PLL1_OUT>;
+ assigned-clock-rates = <24000000>;
+ #phy-cells = <0>;
+ power-domains = <&pgc_mipi>;
+ status = "disabled";
+ };
+
i2c1: i2c@30a20000 {
compatible = "fsl,imx8mq-i2c", "fsl,imx21-i2c";
reg = <0x30a20000 0x10000>;
usb_dwc3_0: usb@38100000 {
compatible = "fsl,imx8mq-dwc3", "snps,dwc3";
reg = <0x38100000 0x10000>;
- clocks = <&clk IMX8MQ_CLK_USB_BUS>,
+ clocks = <&clk IMX8MQ_CLK_USB1_CTRL_ROOT>,
<&clk IMX8MQ_CLK_USB_CORE_REF>,
- <&clk IMX8MQ_CLK_USB1_CTRL_ROOT>;
+ <&clk IMX8MQ_CLK_32K>;
clock-names = "bus_early", "ref", "suspend";
assigned-clocks = <&clk IMX8MQ_CLK_USB_BUS>,
<&clk IMX8MQ_CLK_USB_CORE_REF>;
usb_dwc3_1: usb@38200000 {
compatible = "fsl,imx8mq-dwc3", "snps,dwc3";
reg = <0x38200000 0x10000>;
- clocks = <&clk IMX8MQ_CLK_USB_BUS>,
+ clocks = <&clk IMX8MQ_CLK_USB2_CTRL_ROOT>,
<&clk IMX8MQ_CLK_USB_CORE_REF>,
- <&clk IMX8MQ_CLK_USB2_CTRL_ROOT>;
+ <&clk IMX8MQ_CLK_32K>;
clock-names = "bus_early", "ref", "suspend";
assigned-clocks = <&clk IMX8MQ_CLK_USB_BUS>,
<&clk IMX8MQ_CLK_USB_CORE_REF>;
interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
};
+
+ ddr-pmu@3d800000 {
+ compatible = "fsl,imx8mq-ddr-pmu", "fsl,imx8m-ddr-pmu";
+ reg = <0x3d800000 0x400000>;
+ interrupt-parent = <&gic>;
+ interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>;
+ };
};
};
u32 hv_max_vp_index;
EXPORT_SYMBOL_GPL(hv_max_vp_index);
+void *hv_alloc_hyperv_page(void)
+{
+ BUILD_BUG_ON(PAGE_SIZE != HV_HYP_PAGE_SIZE);
+
+ return (void *)__get_free_page(GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page);
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+ free_page(addr);
+}
+EXPORT_SYMBOL_GPL(hv_free_hyperv_page);
+
static int hv_cpu_init(unsigned int cpu)
{
u64 msr_vp_index;
x86_init.pci.arch_init = hv_pci_init;
- /* Register Hyper-V specific clocksource */
- hv_init_clocksource();
return;
remove_cpuhp_state:
__attribute__((visibility("hidden")));
#endif
- #ifdef CONFIG_HYPERV_TSCPAGE
+ #ifdef CONFIG_HYPERV_TIMER
extern struct ms_hyperv_tsc_page hvclock_page
__attribute__((visibility("hidden")));
#endif
#else
+#define VDSO_HAS_32BIT_FALLBACK 1
+
static __always_inline
long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
{
return ret;
}
+static __always_inline
+long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_gettime), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
static __always_inline
long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
struct timezone *_tz)
return ret;
}
+static __always_inline
+long clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_getres), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
#endif
#ifdef CONFIG_PARAVIRT_CLOCK
}
#endif
- #ifdef CONFIG_HYPERV_TSCPAGE
+ #ifdef CONFIG_HYPERV_TIMER
static u64 vread_hvclock(void)
{
return hv_read_tsc_page(&hvclock_page);
return vread_pvclock();
}
#endif
- #ifdef CONFIG_HYPERV_TSCPAGE
+ #ifdef CONFIG_HYPERV_TIMER
if (clock_mode == VCLOCK_HVCLOCK) {
barrier();
return vread_hvclock();
if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
new->phys_map[xapic_id] = apic;
+ if (!kvm_apic_sw_enabled(apic))
+ continue;
+
ldr = kvm_lapic_get_reg(apic, APIC_LDR);
if (apic_x2apic_mode(apic)) {
static_key_slow_dec_deferred(&apic_sw_disabled);
else
static_key_slow_inc(&apic_sw_disabled.key);
+
+ recalculate_apic_map(apic->vcpu->kvm);
}
}
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
- struct swait_queue_head *q = &vcpu->wq;
struct kvm_timer *ktimer = &apic->lapic_timer;
if (atomic_read(&apic->lapic_timer.pending))
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
-
- /*
- * For x86, the atomic_inc() is serialized, thus
- * using swait_active() is safe.
- */
- if (swait_active(q))
- swake_up_one(q);
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
likely(ns > apic->lapic_timer.timer_advance_ns)) {
expire = ktime_add_ns(now, ns);
expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
- hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS);
+ hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD);
} else
apic_timer_expired(apic);
apic->vcpu = vcpu;
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_ABS);
+ HRTIMER_MODE_ABS_HARD);
apic->lapic_timer.timer.function = apic_timer_fn;
if (timer_advance_ns == -1) {
apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
timer = &vcpu->arch.apic->lapic_timer.timer;
if (hrtimer_cancel(timer))
- hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_HARD);
}
/*
{
struct request_queue *q = rq->q;
- blk_mq_sched_started_request(rq);
-
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
struct blk_mq_hw_ctx *hctx, *next;
int i;
- cancel_delayed_work_sync(&q->requeue_work);
-
queue_for_each_hw_ctx(q, hctx, i)
WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
kt = nsecs;
mode = HRTIMER_MODE_REL;
- hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode);
+ hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode);
hrtimer_set_expires(&hs.timer, kt);
- hrtimer_init_sleeper(&hs, current);
do {
if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE)
break;
set_current_state(TASK_UNINTERRUPTIBLE);
- hrtimer_start_expires(&hs.timer, mode);
+ hrtimer_sleeper_start_expires(&hs, mode);
if (hs.task)
io_schedule();
hrtimer_cancel(&hs.timer);
#include <linux/resource.h>
#include <linux/latencytop.h>
#include <linux/sched/prio.h>
+ #include <linux/sched/types.h>
#include <linux/signal_types.h>
#include <linux/mm_types_task.h>
#include <linux/task_io_accounting.h>
+ #include <linux/posix-timers.h>
#include <linux/rseq.h>
/* task_struct member predeclarations (sorted alphabetically): */
#endif
};
- /**
- * struct task_cputime - collected CPU time counts
- * @utime: time spent in user mode, in nanoseconds
- * @stime: time spent in kernel mode, in nanoseconds
- * @sum_exec_runtime: total time spent on the CPU, in nanoseconds
- *
- * This structure groups together three kinds of CPU time that are tracked for
- * threads and thread groups. Most things considering CPU time want to group
- * these counts together and treat all three of them in parallel.
- */
- struct task_cputime {
- u64 utime;
- u64 stime;
- unsigned long long sum_exec_runtime;
- };
-
- /* Alternate field names when used on cache expirations: */
- #define virt_exp utime
- #define prof_exp stime
- #define sched_exp sum_exec_runtime
-
enum vtime_state {
/* Task is sleeping or running in a CPU with VTIME inactive: */
VTIME_INACTIVE = 0,
UCLAMP_CNT
};
+#ifdef CONFIG_SMP
+extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+#endif
+
struct sched_info {
#ifdef CONFIG_SCHED_INFO
/* Cumulative counters: */
unsigned long min_flt;
unsigned long maj_flt;
- #ifdef CONFIG_POSIX_TIMERS
- struct task_cputime cputime_expires;
- struct list_head cpu_timers[3];
- #endif
+ /* Empty if CONFIG_POSIX_CPUTIMERS=n */
+ struct posix_cputimers posix_cputimers;
/* Process credentials: */
u64 last_sum_exec_runtime;
struct callback_head numa_work;
- struct numa_group *numa_group;
+ /*
+ * This pointer is only modified for current in syscall and
+ * pagefault context (and for tasks being destroyed), so it can be read
+ * from any of the following contexts:
+ * - RCU read-side critical section
+ * - current->numa_group from everywhere
+ * - task's runqueue locked, task not running
+ */
+ struct numa_group __rcu *numa_group;
/*
* numa_faults is an array split into four regions:
* value indicates whether a reschedule was done in fact.
* cond_resched_lock() will drop the spinlock before scheduling,
*/
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
extern int _cond_resched(void);
#else
static inline int _cond_resched(void) { return 0; }
/*
* Does a critical section need to be broken due to another
- * task waiting?: (technically does not depend on CONFIG_PREEMPT,
+ * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
* but a general need for low latency)
*/
static inline int spin_needbreak(spinlock_t *lock)
{
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
return spin_is_contended(lock);
#else
return 0;
return !list_empty(&wq_head->head);
}
+/**
+ * wq_has_single_sleeper - check if there is only one sleeper
+ * @wq_head: wait queue head
+ *
+ * Returns true of wq_head has only one sleeper on the list.
+ *
+ * Please refer to the comment for waitqueue_active.
+ */
+static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head)
+{
+ return list_is_singular(&wq_head->head);
+}
+
/**
* wq_has_sleeper - check if there are any waiting processes
* @wq_head: wait queue head
int __ret = 0; \
struct hrtimer_sleeper __t; \
\
- hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \
- hrtimer_init_sleeper(&__t, current); \
+ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \
+ HRTIMER_MODE_REL); \
if ((timeout) != KTIME_MAX) \
hrtimer_start_range_ns(&__t.timer, timeout, \
current->timer_slack_ns, \
.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
.cputimer = {
.cputime_atomic = INIT_CPUTIME_ATOMIC,
- .running = false,
- .checking_timer = false,
},
#endif
INIT_CPU_TIMERS(init_signals)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.ret_stack = NULL,
#endif
-#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPT)
+#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
.trace_recursion = 0,
#endif
#ifdef CONFIG_LIVEPATCH
cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
raw_spin_lock_init(&cpuctx->hrtimer_lock);
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
timer->function = perf_mux_hrtimer_handler;
}
if (!cpuctx->hrtimer_active) {
cpuctx->hrtimer_active = 1;
hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
- hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
}
raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
ctx->generation++;
}
+static int
+perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
+{
+ if (!has_aux(aux_event))
+ return 0;
+
+ if (!event->pmu->aux_output_match)
+ return 0;
+
+ return event->pmu->aux_output_match(aux_event);
+}
+
+static void put_event(struct perf_event *event);
+static void event_sched_out(struct perf_event *event,
+ struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx);
+
+static void perf_put_aux_event(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct perf_event *iter;
+
+ /*
+ * If event uses aux_event tear down the link
+ */
+ if (event->aux_event) {
+ iter = event->aux_event;
+ event->aux_event = NULL;
+ put_event(iter);
+ return;
+ }
+
+ /*
+ * If the event is an aux_event, tear down all links to
+ * it from other events.
+ */
+ for_each_sibling_event(iter, event->group_leader) {
+ if (iter->aux_event != event)
+ continue;
+
+ iter->aux_event = NULL;
+ put_event(event);
+
+ /*
+ * If it's ACTIVE, schedule it out and put it into ERROR
+ * state so that we don't try to schedule it again. Note
+ * that perf_event_enable() will clear the ERROR status.
+ */
+ event_sched_out(iter, cpuctx, ctx);
+ perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+ }
+}
+
+static int perf_get_aux_event(struct perf_event *event,
+ struct perf_event *group_leader)
+{
+ /*
+ * Our group leader must be an aux event if we want to be
+ * an aux_output. This way, the aux event will precede its
+ * aux_output events in the group, and therefore will always
+ * schedule first.
+ */
+ if (!group_leader)
+ return 0;
+
+ if (!perf_aux_output_match(event, group_leader))
+ return 0;
+
+ if (!atomic_long_inc_not_zero(&group_leader->refcount))
+ return 0;
+
+ /*
+ * Link aux_outputs to their aux event; this is undone in
+ * perf_group_detach() by perf_put_aux_event(). When the
+ * group in torn down, the aux_output events loose their
+ * link to the aux_event and can't schedule any more.
+ */
+ event->aux_event = group_leader;
+
+ return 1;
+}
+
static void perf_group_detach(struct perf_event *event)
{
struct perf_event *sibling, *tmp;
event->attach_state &= ~PERF_ATTACH_GROUP;
+ perf_put_aux_event(event);
+
/*
* If this is a sibling, remove it from its group.
*/
return NULL;
__perf_event_init_context(ctx);
- if (task) {
- ctx->task = task;
- get_task_struct(task);
- }
+ if (task)
+ ctx->task = get_task_struct(task);
ctx->pmu = pmu;
return ctx;
period = max_t(u64, 10000, hwc->sample_period);
}
hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
- HRTIMER_MODE_REL_PINNED);
+ HRTIMER_MODE_REL_PINNED_HARD);
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
if (!is_sampling_event(event))
return;
- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
hwc->hrtimer.function = perf_swevent_hrtimer;
/*
* and we cannot use the ctx information because we need the
* pmu before we get a ctx.
*/
- get_task_struct(task);
- event->hw.target = task;
+ event->hw.target = get_task_struct(task);
}
event->clock = &local_clock;
goto err_ns;
}
+ if (event->attr.aux_output &&
+ !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+ err = -EOPNOTSUPP;
+ goto err_pmu;
+ }
+
err = exclusive_event_init(event);
if (err)
goto err_pmu;
}
}
+ if (event->attr.aux_output && !perf_get_aux_event(event, group_leader))
+ goto err_locked;
/*
* Must be under the same ctx::mutex as perf_install_in_context(),
goto err_unlock;
}
- perf_install_in_context(ctx, event, cpu);
+ perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
WARN_ON(tsk == current);
cgroup_free(tsk);
- task_numa_free(tsk);
+ task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
int arch_task_struct_size __read_mostly;
#endif
+#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
{
/* Fetch thread_struct whitelist for the architecture. */
else
*offset += offsetof(struct task_struct, thread);
}
+#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */
void __init fork_init(void)
{
}
}
- #ifdef CONFIG_POSIX_TIMERS
/*
* Initialize POSIX timer handling for a thread group.
*/
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
+ struct posix_cputimers *pct = &sig->posix_cputimers;
unsigned long cpu_limit;
cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
- if (cpu_limit != RLIM_INFINITY) {
- sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
- sig->cputimer.running = true;
- }
-
- /* The timer lists. */
- INIT_LIST_HEAD(&sig->cpu_timers[0]);
- INIT_LIST_HEAD(&sig->cpu_timers[1]);
- INIT_LIST_HEAD(&sig->cpu_timers[2]);
+ posix_cputimers_group_init(pct, cpu_limit);
}
- #else
- static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { }
- #endif
static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
#endif
}
- #ifdef CONFIG_POSIX_TIMERS
- /*
- * Initialize POSIX timer handling for a single task.
- */
- static void posix_cpu_timers_init(struct task_struct *tsk)
- {
- tsk->cputime_expires.prof_exp = 0;
- tsk->cputime_expires.virt_exp = 0;
- tsk->cputime_expires.sched_exp = 0;
- INIT_LIST_HEAD(&tsk->cpu_timers[0]);
- INIT_LIST_HEAD(&tsk->cpu_timers[1]);
- INIT_LIST_HEAD(&tsk->cpu_timers[2]);
- }
- #else
- static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
- #endif
-
static inline void init_task_pid_links(struct task_struct *task)
{
enum pid_type type;
#endif /* #ifdef CONFIG_TASKS_RCU */
}
+struct pid *pidfd_pid(const struct file *file)
+{
+ if (file->f_op == &pidfd_fops)
+ return file->private_data;
+
+ return ERR_PTR(-EBADF);
+}
+
static int pidfd_release(struct inode *inode, struct file *file)
{
struct pid *pid = file->private_data;
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
- posix_cpu_timers_init(p);
+ posix_cputimers_init(&p->posix_cputimers);
p->io_context = NULL;
audit_set_context(p, NULL);
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
+ *
+ * args->exit_signal is expected to be checked for sanity by the caller.
*/
long _do_fork(struct kernel_clone_args *args)
{
if (copy_from_user(&args, uargs, size))
return -EFAULT;
+ /*
+ * Verify that higher 32bits of exit_signal are unset and that
+ * it is a valid signal
+ */
+ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) ||
+ !valid_signal(args.exit_signal)))
+ return -EINVAL;
+
*kargs = (struct kernel_clone_args){
.flags = args.flags,
.pidfd = u64_to_user_ptr(args.pidfd),
{
struct hrtimer *timer = &rq->hrtick_timer;
- hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
}
/*
*/
delay = max_t(u64, delay, 10000LL);
hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
- HRTIMER_MODE_REL_PINNED);
+ HRTIMER_MODE_REL_PINNED_HARD);
}
#endif /* CONFIG_SMP */
rq->hrtick_csd.info = rq;
#endif
- hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
rq->hrtick_timer.function = hrtick;
}
#else /* CONFIG_SCHED_HRTICK */
}
#ifdef CONFIG_UCLAMP_TASK
+/*
+ * Serializes updates of utilization clamp values
+ *
+ * The (slow-path) user-space triggers utilization clamp value updates which
+ * can require updates on (fast-path) scheduler's data structures used to
+ * support enqueue/dequeue operations.
+ * While the per-CPU rq lock protects fast-path update operations, user-space
+ * requests are serialized using a mutex to reduce the risk of conflicting
+ * updates or API abuses.
+ */
+static DEFINE_MUTEX(uclamp_mutex);
+
/* Max allowed minimum utilization */
unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
}
-static inline unsigned int uclamp_none(int clamp_id)
+static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id)
{
if (clamp_id == UCLAMP_MIN)
return 0;
}
static inline unsigned int
-uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
+uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
/*
return uclamp_none(UCLAMP_MIN);
}
-static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
+static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
unsigned int clamp_value)
{
/* Reset max-clamp retention only on idle exit */
}
static inline
-unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
- unsigned int clamp_value)
+enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
+ unsigned int clamp_value)
{
struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
int bucket_id = UCLAMP_BUCKETS - 1;
return uclamp_idle_value(rq, clamp_id, clamp_value);
}
+static inline struct uclamp_se
+uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
+{
+ struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ struct uclamp_se uc_max;
+
+ /*
+ * Tasks in autogroups or root task group will be
+ * restricted by system defaults.
+ */
+ if (task_group_is_autogroup(task_group(p)))
+ return uc_req;
+ if (task_group(p) == &root_task_group)
+ return uc_req;
+
+ uc_max = task_group(p)->uclamp[clamp_id];
+ if (uc_req.value > uc_max.value || !uc_req.user_defined)
+ return uc_max;
+#endif
+
+ return uc_req;
+}
+
/*
* The effective clamp bucket index of a task depends on, by increasing
* priority:
* - the task specific clamp value, when explicitly requested from userspace
+ * - the task group effective clamp value, for tasks not either in the root
+ * group or in an autogroup
* - the system default clamp value, defined by the sysadmin
*/
static inline struct uclamp_se
-uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
+uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id)
{
- struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+ struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id);
struct uclamp_se uc_max = uclamp_default[clamp_id];
/* System default restrictions always apply */
return uc_req;
}
-unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
+enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
{
struct uclamp_se uc_eff;
* for each bucket when all its RUNNABLE tasks require the same clamp.
*/
static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
- unsigned int clamp_id)
+ enum uclamp_id clamp_id)
{
struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
struct uclamp_se *uc_se = &p->uclamp[clamp_id];
* enforce the expected state and warn.
*/
static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
- unsigned int clamp_id)
+ enum uclamp_id clamp_id)
{
struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
struct uclamp_se *uc_se = &p->uclamp[clamp_id];
static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
if (unlikely(!p->sched_class->uclamp_enabled))
return;
static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
if (unlikely(!p->sched_class->uclamp_enabled))
return;
uclamp_rq_dec_id(rq, p, clamp_id);
}
+static inline void
+uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+
+ /*
+ * Lock the task and the rq where the task is (or was) queued.
+ *
+ * We might lock the (previous) rq of a !RUNNABLE task, but that's the
+ * price to pay to safely serialize util_{min,max} updates with
+ * enqueues, dequeues and migration operations.
+ * This is the same locking schema used by __set_cpus_allowed_ptr().
+ */
+ rq = task_rq_lock(p, &rf);
+
+ /*
+ * Setting the clamp bucket is serialized by task_rq_lock().
+ * If the task is not yet RUNNABLE and its task_struct is not
+ * affecting a valid clamp bucket, the next time it's enqueued,
+ * it will already see the updated clamp bucket value.
+ */
+ if (!p->uclamp[clamp_id].active) {
+ uclamp_rq_dec_id(rq, p, clamp_id);
+ uclamp_rq_inc_id(rq, p, clamp_id);
+ }
+
+ task_rq_unlock(rq, p, &rf);
+}
+
+static inline void
+uclamp_update_active_tasks(struct cgroup_subsys_state *css,
+ unsigned int clamps)
+{
+ enum uclamp_id clamp_id;
+ struct css_task_iter it;
+ struct task_struct *p;
+
+ css_task_iter_start(css, 0, &it);
+ while ((p = css_task_iter_next(&it))) {
+ for_each_clamp_id(clamp_id) {
+ if ((0x1 << clamp_id) & clamps)
+ uclamp_update_active(p, clamp_id);
+ }
+ }
+ css_task_iter_end(&it);
+}
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css);
+static void uclamp_update_root_tg(void)
+{
+ struct task_group *tg = &root_task_group;
+
+ uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN],
+ sysctl_sched_uclamp_util_min, false);
+ uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
+ sysctl_sched_uclamp_util_max, false);
+
+ rcu_read_lock();
+ cpu_util_update_eff(&root_task_group.css);
+ rcu_read_unlock();
+}
+#else
+static void uclamp_update_root_tg(void) { }
+#endif
+
int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
+ bool update_root_tg = false;
int old_min, old_max;
- static DEFINE_MUTEX(mutex);
int result;
- mutex_lock(&mutex);
+ mutex_lock(&uclamp_mutex);
old_min = sysctl_sched_uclamp_util_min;
old_max = sysctl_sched_uclamp_util_max;
if (old_min != sysctl_sched_uclamp_util_min) {
uclamp_se_set(&uclamp_default[UCLAMP_MIN],
sysctl_sched_uclamp_util_min, false);
+ update_root_tg = true;
}
if (old_max != sysctl_sched_uclamp_util_max) {
uclamp_se_set(&uclamp_default[UCLAMP_MAX],
sysctl_sched_uclamp_util_max, false);
+ update_root_tg = true;
}
+ if (update_root_tg)
+ uclamp_update_root_tg();
+
/*
- * Updating all the RUNNABLE task is expensive, keep it simple and do
- * just a lazy update at each next enqueue time.
+ * We update all RUNNABLE tasks only when task groups are in use.
+ * Otherwise, keep it simple and do just a lazy update at each next
+ * task enqueue time.
*/
+
goto done;
undo:
sysctl_sched_uclamp_util_min = old_min;
sysctl_sched_uclamp_util_max = old_max;
done:
- mutex_unlock(&mutex);
+ mutex_unlock(&uclamp_mutex);
return result;
}
static void __setscheduler_uclamp(struct task_struct *p,
const struct sched_attr *attr)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
/*
* On scheduling class change, reset to default clamps for tasks
static void uclamp_fork(struct task_struct *p)
{
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
for_each_clamp_id(clamp_id)
p->uclamp[clamp_id].active = false;
static void __init init_uclamp(void)
{
struct uclamp_se uc_max = {};
- unsigned int clamp_id;
+ enum uclamp_id clamp_id;
int cpu;
+ mutex_init(&uclamp_mutex);
+
for_each_possible_cpu(cpu) {
memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
cpu_rq(cpu)->uclamp_flags = 0;
/* System defaults allow max clamp values for both indexes */
uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false);
- for_each_clamp_id(clamp_id)
+ for_each_clamp_id(clamp_id) {
uclamp_default[clamp_id] = uc_max;
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ root_task_group.uclamp_req[clamp_id] = uc_max;
+ root_task_group.uclamp[clamp_id] = uc_max;
+#endif
+ }
}
#else /* CONFIG_UCLAMP_TASK */
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
}
/*
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next, struct rq_flags *rf)
{
- struct mm_struct *mm, *oldmm;
-
prepare_task_switch(rq, prev, next);
- mm = next->mm;
- oldmm = prev->active_mm;
/*
* For paravirt, this is coupled with an exit in switch_to to
* combine the page table reload and the switch backend into
arch_start_context_switch(prev);
/*
- * If mm is non-NULL, we pass through switch_mm(). If mm is
- * NULL, we will pass through mmdrop() in finish_task_switch().
- * Both of these contain the full memory barrier required by
- * membarrier after storing to rq->curr, before returning to
- * user-space.
+ * kernel -> kernel lazy + transfer active
+ * user -> kernel lazy + mmgrab() active
+ *
+ * kernel -> user switch + mmdrop() active
+ * user -> user switch
*/
- if (!mm) {
- next->active_mm = oldmm;
- mmgrab(oldmm);
- enter_lazy_tlb(oldmm, next);
- } else
- switch_mm_irqs_off(oldmm, mm, next);
+ if (!next->mm) { // to kernel
+ enter_lazy_tlb(prev->active_mm, next);
+
+ next->active_mm = prev->active_mm;
+ if (prev->mm) // from user
+ mmgrab(prev->active_mm);
+ else
+ prev->active_mm = NULL;
+ } else { // to user
+ /*
+ * sys_membarrier() requires an smp_mb() between setting
+ * rq->curr and returning to userspace.
+ *
+ * The below provides this either through switch_mm(), or in
+ * case 'prev->active_mm == next->mm' through
+ * finish_task_switch()'s mmdrop().
+ */
- if (!prev->mm) {
- prev->active_mm = NULL;
- rq->prev_mm = oldmm;
+ switch_mm_irqs_off(prev->active_mm, next->mm, next);
+
+ if (!prev->mm) { // from kernel
+ /* will mmdrop() in finish_task_switch(). */
+ rq->prev_mm = prev->active_mm;
+ prev->active_mm = NULL;
+ }
}
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
struct tick_work {
int cpu;
+ atomic_t state;
struct delayed_work work;
};
+/* Values for ->state, see diagram below. */
+#define TICK_SCHED_REMOTE_OFFLINE 0
+#define TICK_SCHED_REMOTE_OFFLINING 1
+#define TICK_SCHED_REMOTE_RUNNING 2
+
+/*
+ * State diagram for ->state:
+ *
+ *
+ * TICK_SCHED_REMOTE_OFFLINE
+ * | ^
+ * | |
+ * | | sched_tick_remote()
+ * | |
+ * | |
+ * +--TICK_SCHED_REMOTE_OFFLINING
+ * | ^
+ * | |
+ * sched_tick_start() | | sched_tick_stop()
+ * | |
+ * V |
+ * TICK_SCHED_REMOTE_RUNNING
+ *
+ *
+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
+ * and sched_tick_start() are happy to leave the state in RUNNING.
+ */
static struct tick_work __percpu *tick_work_cpu;
struct task_struct *curr;
struct rq_flags rf;
u64 delta;
+ int os;
/*
* Handle the tick only if it appears the remote CPU is running in full
rq_lock_irq(rq, &rf);
curr = rq->curr;
- if (is_idle_task(curr))
+ if (is_idle_task(curr) || cpu_is_offline(cpu))
goto out_unlock;
update_rq_clock(rq);
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
- * to keep scheduler internal stats reasonably up to date.
+ * to keep scheduler internal stats reasonably up to date. But
+ * first update state to reflect hotplug activity if required.
*/
- queue_delayed_work(system_unbound_wq, dwork, HZ);
+ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
+ if (os == TICK_SCHED_REMOTE_RUNNING)
+ queue_delayed_work(system_unbound_wq, dwork, HZ);
}
static void sched_tick_start(int cpu)
{
+ int os;
struct tick_work *twork;
if (housekeeping_cpu(cpu, HK_FLAG_TICK))
WARN_ON_ONCE(!tick_work_cpu);
twork = per_cpu_ptr(tick_work_cpu, cpu);
- twork->cpu = cpu;
- INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
- queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
+ if (os == TICK_SCHED_REMOTE_OFFLINE) {
+ twork->cpu = cpu;
+ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+ }
}
#ifdef CONFIG_HOTPLUG_CPU
static void sched_tick_stop(int cpu)
{
struct tick_work *twork;
+ int os;
if (housekeeping_cpu(cpu, HK_FLAG_TICK))
return;
WARN_ON_ONCE(!tick_work_cpu);
twork = per_cpu_ptr(tick_work_cpu, cpu);
- cancel_delayed_work_sync(&twork->work);
+ /* There cannot be competing actions, but don't rely on stop-machine. */
+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
+ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
+ /* Don't cancel, as this would mess up the state machine. */
}
#endif /* CONFIG_HOTPLUG_CPU */
{
tick_work_cpu = alloc_percpu(struct tick_work);
BUG_ON(!tick_work_cpu);
-
return 0;
}
static inline void sched_tick_stop(int cpu) { }
#endif
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
defined(CONFIG_TRACE_PREEMPT_TOGGLE))
/*
* If the value passed in is equal to the current preempt count
p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
- goto again;
+ goto restart;
/* Assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
return p;
}
-again:
+restart:
+ /*
+ * Ensure that we put DL/RT tasks before the pick loop, such that they
+ * can PULL higher prio tasks when we lower the RQ 'priority'.
+ */
+ prev->sched_class->put_prev_task(rq, prev, rf);
+ if (!rq->nr_running)
+ newidle_balance(rq, rf);
+
for_each_class(class) {
- p = class->pick_next_task(rq, prev, rf);
- if (p) {
- if (unlikely(p == RETRY_TASK))
- goto again;
+ p = class->pick_next_task(rq, NULL, NULL);
+ if (p)
return p;
- }
}
/* The idle class should always have a runnable task: */
* task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
* called on the nearest possible occasion:
*
- * - If the kernel is preemptible (CONFIG_PREEMPT=y):
+ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
*
* - in syscall or exception context, at the next outmost
* preempt_enable(). (this might be as soon as the wake_up()'s
* - in IRQ context, return from interrupt-handler to
* preemptible context
*
- * - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
+ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
* then at the next:
*
* - cond_resched() call
static inline void sched_submit_work(struct task_struct *tsk)
{
- if (!tsk->state || tsk_is_pi_blocked(tsk))
+ if (!tsk->state)
return;
/*
preempt_enable_no_resched();
}
+ if (tsk_is_pi_blocked(tsk))
+ return;
+
/*
* If we are going to sleep and we have plugged IO queued,
* make sure to submit it to avoid deadlocks.
} while (need_resched());
}
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
/*
* this is the entry point to schedule() from in-kernel preemption
* off of preempt_enable. Kernel preemptions off return from interrupt
}
EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
/*
* this is the entry point to schedule() from kernel preemption
if (queued)
enqueue_task(rq, p, queue_flag);
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
resched_curr(rq);
}
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
out_unlock:
task_rq_unlock(rq, p, &rf);
}
return retval;
}
+ if (pi)
+ cpuset_read_lock();
+
/*
* Make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
* Changing the policy of the stop threads its a very bad idea:
*/
if (p == rq->stop) {
- task_rq_unlock(rq, p, &rf);
- return -EINVAL;
+ retval = -EINVAL;
+ goto unlock;
}
/*
goto change;
p->sched_reset_on_fork = reset_on_fork;
- task_rq_unlock(rq, p, &rf);
- return 0;
+ retval = 0;
+ goto unlock;
}
change:
if (rt_bandwidth_enabled() && rt_policy(policy) &&
task_group(p)->rt_bandwidth.rt_runtime == 0 &&
!task_group_is_autogroup(task_group(p))) {
- task_rq_unlock(rq, p, &rf);
- return -EPERM;
+ retval = -EPERM;
+ goto unlock;
}
#endif
#ifdef CONFIG_SMP
*/
if (!cpumask_subset(span, p->cpus_ptr) ||
rq->rd->dl_bw.bw == 0) {
- task_rq_unlock(rq, p, &rf);
- return -EPERM;
+ retval = -EPERM;
+ goto unlock;
}
}
#endif
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
task_rq_unlock(rq, p, &rf);
+ if (pi)
+ cpuset_read_unlock();
goto recheck;
}
* is available.
*/
if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
- task_rq_unlock(rq, p, &rf);
- return -EBUSY;
+ retval = -EBUSY;
+ goto unlock;
}
p->sched_reset_on_fork = reset_on_fork;
enqueue_task(rq, p, queue_flags);
}
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
preempt_disable();
task_rq_unlock(rq, p, &rf);
- if (pi)
+ if (pi) {
+ cpuset_read_unlock();
rt_mutex_adjust_pi(p);
+ }
/* Run balance callbacks after we've adjusted the PI chain: */
balance_callback(rq);
preempt_enable();
return 0;
+
+unlock:
+ task_rq_unlock(rq, p, &rf);
+ if (pi)
+ cpuset_read_unlock();
+ return retval;
}
static int _sched_setscheduler(struct task_struct *p, int policy,
rcu_read_lock();
retval = -ESRCH;
p = find_process_by_pid(pid);
- if (p != NULL)
- retval = sched_setscheduler(p, policy, &lparam);
+ if (likely(p))
+ get_task_struct(p);
rcu_read_unlock();
+ if (likely(p)) {
+ retval = sched_setscheduler(p, policy, &lparam);
+ put_task_struct(p);
+ }
+
return retval;
}
return retval;
}
-static int sched_read_attr(struct sched_attr __user *uattr,
- struct sched_attr *attr,
- unsigned int usize)
+/*
+ * Copy the kernel size attribute structure (which might be larger
+ * than what user-space knows about) to user-space.
+ *
+ * Note that all cases are valid: user-space buffer can be larger or
+ * smaller than the kernel-space buffer. The usual case is that both
+ * have the same size.
+ */
+static int
+sched_attr_copy_to_user(struct sched_attr __user *uattr,
+ struct sched_attr *kattr,
+ unsigned int usize)
{
- int ret;
+ unsigned int ksize = sizeof(*kattr);
if (!access_ok(uattr, usize))
return -EFAULT;
/*
- * If we're handed a smaller struct than we know of,
- * ensure all the unknown bits are 0 - i.e. old
- * user-space does not get uncomplete information.
+ * sched_getattr() ABI forwards and backwards compatibility:
+ *
+ * If usize == ksize then we just copy everything to user-space and all is good.
+ *
+ * If usize < ksize then we only copy as much as user-space has space for,
+ * this keeps ABI compatibility as well. We skip the rest.
+ *
+ * If usize > ksize then user-space is using a newer version of the ABI,
+ * which part the kernel doesn't know about. Just ignore it - tooling can
+ * detect the kernel's knowledge of attributes from the attr->size value
+ * which is set to ksize in this case.
*/
- if (usize < sizeof(*attr)) {
- unsigned char *addr;
- unsigned char *end;
-
- addr = (void *)attr + usize;
- end = (void *)attr + sizeof(*attr);
-
- for (; addr < end; addr++) {
- if (*addr)
- return -EFBIG;
- }
-
- attr->size = usize;
- }
+ kattr->size = min(usize, ksize);
- ret = copy_to_user(uattr, attr, attr->size);
- if (ret)
+ if (copy_to_user(uattr, kattr, kattr->size))
return -EFAULT;
return 0;
* sys_sched_getattr - similar to sched_getparam, but with sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
- * @size: sizeof(attr) for fwd/bwd comp.
+ * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
* @flags: for future extension.
*/
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
- unsigned int, size, unsigned int, flags)
+ unsigned int, usize, unsigned int, flags)
{
- struct sched_attr attr = {
- .size = sizeof(struct sched_attr),
- };
+ struct sched_attr kattr = { };
struct task_struct *p;
int retval;
- if (!uattr || pid < 0 || size > PAGE_SIZE ||
- size < SCHED_ATTR_SIZE_VER0 || flags)
+ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
+ usize < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
if (retval)
goto out_unlock;
- attr.sched_policy = p->policy;
+ kattr.sched_policy = p->policy;
if (p->sched_reset_on_fork)
- attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
if (task_has_dl_policy(p))
- __getparam_dl(p, &attr);
+ __getparam_dl(p, &kattr);
else if (task_has_rt_policy(p))
- attr.sched_priority = p->rt_priority;
+ kattr.sched_priority = p->rt_priority;
else
- attr.sched_nice = task_nice(p);
+ kattr.sched_nice = task_nice(p);
#ifdef CONFIG_UCLAMP_TASK
- attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
- attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif
rcu_read_unlock();
- retval = sched_read_attr(uattr, &attr, size);
- return retval;
+ return sched_attr_copy_to_user(uattr, &kattr, usize);
out_unlock:
rcu_read_unlock();
return 0;
}
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
int __sched _cond_resched(void)
{
if (should_resched(0)) {
* __cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
- * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
+ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
- set_curr_task(rq, p);
+ set_next_task(rq, p);
task_rq_unlock(rq, p, &rf);
}
#endif /* CONFIG_NUMA_BALANCING */
atomic_long_add(delta, &calc_load_tasks);
}
-static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+static struct task_struct *__pick_migrate_task(struct rq *rq)
{
-}
+ const struct sched_class *class;
+ struct task_struct *next;
-static const struct sched_class fake_sched_class = {
- .put_prev_task = put_prev_task_fake,
-};
+ for_each_class(class) {
+ next = class->pick_next_task(rq, NULL, NULL);
+ if (next) {
+ next->sched_class->put_prev_task(rq, next, NULL);
+ return next;
+ }
+ }
-static struct task_struct fake_task = {
- /*
- * Avoid pull_{rt,dl}_task()
- */
- .prio = MAX_PRIO + 1,
- .sched_class = &fake_sched_class,
-};
+ /* The idle class should always have a runnable task */
+ BUG();
+}
/*
* Migrate all tasks from the rq, sleeping tasks will be migrated by
if (rq->nr_running == 1)
break;
- /*
- * pick_next_task() assumes pinned rq->lock:
- */
- next = pick_next_task(rq, &fake_task, rf);
- BUG_ON(!next);
- put_prev_task(rq, next);
+ next = __pick_migrate_task(rq);
/*
* Rules for changing task_struct::cpus_mask are holding
void __init sched_init(void)
{
- unsigned long alloc_size = 0, ptr;
+ unsigned long ptr = 0;
int i;
wait_bit_init();
#ifdef CONFIG_FAIR_GROUP_SCHED
- alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+ ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
- alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+ ptr += 2 * nr_cpu_ids * sizeof(void **);
#endif
- if (alloc_size) {
- ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
+ if (ptr) {
+ ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.se = (struct sched_entity **)ptr;
#ifdef CONFIG_IA64
/**
- * set_curr_task - set the current task for a given CPU.
+ * ia64_set_curr_task - set the current task for a given CPU.
* @cpu: the processor in question.
* @p: the task pointer to set.
*
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
+static inline void alloc_uclamp_sched_group(struct task_group *tg,
+ struct task_group *parent)
+{
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ enum uclamp_id clamp_id;
+
+ for_each_clamp_id(clamp_id) {
+ uclamp_se_set(&tg->uclamp_req[clamp_id],
+ uclamp_none(clamp_id), false);
+ tg->uclamp[clamp_id] = parent->uclamp[clamp_id];
+ }
+#endif
+}
+
static void sched_free_group(struct task_group *tg)
{
free_fair_sched_group(tg);
if (!alloc_rt_sched_group(tg, parent))
goto err;
+ alloc_uclamp_sched_group(tg, parent);
+
return tg;
err:
if (queued)
enqueue_task(rq, tsk, queue_flags);
if (running)
- set_curr_task(rq, tsk);
+ set_next_task(rq, tsk);
task_rq_unlock(rq, tsk, &rf);
}
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
-#else
- /* We don't support RT-tasks being in separate groups */
- if (task->sched_class != &fair_sched_class)
- return -EINVAL;
#endif
/*
* Serialize against wake_up_new_task() such that if its
sched_move_task(task);
}
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css)
+{
+ struct cgroup_subsys_state *top_css = css;
+ struct uclamp_se *uc_parent = NULL;
+ struct uclamp_se *uc_se = NULL;
+ unsigned int eff[UCLAMP_CNT];
+ enum uclamp_id clamp_id;
+ unsigned int clamps;
+
+ css_for_each_descendant_pre(css, top_css) {
+ uc_parent = css_tg(css)->parent
+ ? css_tg(css)->parent->uclamp : NULL;
+
+ for_each_clamp_id(clamp_id) {
+ /* Assume effective clamps matches requested clamps */
+ eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value;
+ /* Cap effective clamps with parent's effective clamps */
+ if (uc_parent &&
+ eff[clamp_id] > uc_parent[clamp_id].value) {
+ eff[clamp_id] = uc_parent[clamp_id].value;
+ }
+ }
+ /* Ensure protection is always capped by limit */
+ eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]);
+
+ /* Propagate most restrictive effective clamps */
+ clamps = 0x0;
+ uc_se = css_tg(css)->uclamp;
+ for_each_clamp_id(clamp_id) {
+ if (eff[clamp_id] == uc_se[clamp_id].value)
+ continue;
+ uc_se[clamp_id].value = eff[clamp_id];
+ uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
+ clamps |= (0x1 << clamp_id);
+ }
+ if (!clamps) {
+ css = css_rightmost_descendant(css);
+ continue;
+ }
+
+ /* Immediately update descendants RUNNABLE tasks */
+ uclamp_update_active_tasks(css, clamps);
+ }
+}
+
+/*
+ * Integer 10^N with a given N exponent by casting to integer the literal "1eN"
+ * C expression. Since there is no way to convert a macro argument (N) into a
+ * character constant, use two levels of macros.
+ */
+#define _POW10(exp) ((unsigned int)1e##exp)
+#define POW10(exp) _POW10(exp)
+
+struct uclamp_request {
+#define UCLAMP_PERCENT_SHIFT 2
+#define UCLAMP_PERCENT_SCALE (100 * POW10(UCLAMP_PERCENT_SHIFT))
+ s64 percent;
+ u64 util;
+ int ret;
+};
+
+static inline struct uclamp_request
+capacity_from_percent(char *buf)
+{
+ struct uclamp_request req = {
+ .percent = UCLAMP_PERCENT_SCALE,
+ .util = SCHED_CAPACITY_SCALE,
+ .ret = 0,
+ };
+
+ buf = strim(buf);
+ if (strcmp(buf, "max")) {
+ req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT,
+ &req.percent);
+ if (req.ret)
+ return req;
+ if (req.percent > UCLAMP_PERCENT_SCALE) {
+ req.ret = -ERANGE;
+ return req;
+ }
+
+ req.util = req.percent << SCHED_CAPACITY_SHIFT;
+ req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE);
+ }
+
+ return req;
+}
+
+static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
+ size_t nbytes, loff_t off,
+ enum uclamp_id clamp_id)
+{
+ struct uclamp_request req;
+ struct task_group *tg;
+
+ req = capacity_from_percent(buf);
+ if (req.ret)
+ return req.ret;
+
+ mutex_lock(&uclamp_mutex);
+ rcu_read_lock();
+
+ tg = css_tg(of_css(of));
+ if (tg->uclamp_req[clamp_id].value != req.util)
+ uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false);
+
+ /*
+ * Because of not recoverable conversion rounding we keep track of the
+ * exact requested value
+ */
+ tg->uclamp_pct[clamp_id] = req.percent;
+
+ /* Update effective clamps to track the most restrictive value */
+ cpu_util_update_eff(of_css(of));
+
+ rcu_read_unlock();
+ mutex_unlock(&uclamp_mutex);
+
+ return nbytes;
+}
+
+static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN);
+}
+
+static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX);
+}
+
+static inline void cpu_uclamp_print(struct seq_file *sf,
+ enum uclamp_id clamp_id)
+{
+ struct task_group *tg;
+ u64 util_clamp;
+ u64 percent;
+ u32 rem;
+
+ rcu_read_lock();
+ tg = css_tg(seq_css(sf));
+ util_clamp = tg->uclamp_req[clamp_id].value;
+ rcu_read_unlock();
+
+ if (util_clamp == SCHED_CAPACITY_SCALE) {
+ seq_puts(sf, "max\n");
+ return;
+ }
+
+ percent = tg->uclamp_pct[clamp_id];
+ percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem);
+ seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem);
+}
+
+static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
+{
+ cpu_uclamp_print(sf, UCLAMP_MIN);
+ return 0;
+}
+
+static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
+{
+ cpu_uclamp_print(sf, UCLAMP_MAX);
+ return 0;
+}
+#endif /* CONFIG_UCLAMP_TASK_GROUP */
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
.read_u64 = cpu_rt_period_read_uint,
.write_u64 = cpu_rt_period_write_uint,
},
+#endif
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ {
+ .name = "uclamp.min",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_min_show,
+ .write = cpu_uclamp_min_write,
+ },
+ {
+ .name = "uclamp.max",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_max_show,
+ .write = cpu_uclamp_max_write,
+ },
#endif
{ } /* Terminate */
};
.seq_show = cpu_max_show,
.write = cpu_max_write,
},
+#endif
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+ {
+ .name = "uclamp.min",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_min_show,
+ .write = cpu_uclamp_min_write,
+ },
+ {
+ .name = "uclamp.max",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cpu_uclamp_max_show,
+ .write = cpu_uclamp_max_write,
+ },
#endif
{ } /* terminate */
};
dl_se->dl_non_contending = 1;
get_task_struct(p);
- hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+ hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
}
static void task_contending(struct sched_dl_entity *dl_se, int flags)
static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p)
{
struct rq *later_rq = NULL;
+ struct dl_bw *dl_b;
later_rq = find_lock_later_rq(p, rq);
if (!later_rq) {
double_lock_balance(rq, later_rq);
}
+ if (p->dl.dl_non_contending || p->dl.dl_throttled) {
+ /*
+ * Inactive timer is armed (or callback is running, but
+ * waiting for us to release rq locks). In any case, when it
+ * will fire (or continue), it will see running_bw of this
+ * task migrated to later_rq (and correctly handle it).
+ */
+ sub_running_bw(&p->dl, &rq->dl);
+ sub_rq_bw(&p->dl, &rq->dl);
+
+ add_rq_bw(&p->dl, &later_rq->dl);
+ add_running_bw(&p->dl, &later_rq->dl);
+ } else {
+ sub_rq_bw(&p->dl, &rq->dl);
+ add_rq_bw(&p->dl, &later_rq->dl);
+ }
+
+ /*
+ * And we finally need to fixup root_domain(s) bandwidth accounting,
+ * since p is still hanging out in the old (now moved to default) root
+ * domain.
+ */
+ dl_b = &rq->rd->dl_bw;
+ raw_spin_lock(&dl_b->lock);
+ __dl_sub(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
+ raw_spin_unlock(&dl_b->lock);
+
+ dl_b = &later_rq->rd->dl_bw;
+ raw_spin_lock(&dl_b->lock);
+ __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(later_rq->rd->span));
+ raw_spin_unlock(&dl_b->lock);
+
set_task_cpu(p, later_rq->cpu);
double_unlock_balance(later_rq, rq);
*/
if (!hrtimer_is_queued(timer)) {
get_task_struct(p);
- hrtimer_start(timer, act, HRTIMER_MODE_ABS);
+ hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
}
return 1;
{
struct hrtimer *timer = &dl_se->dl_timer;
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
timer->function = dl_task_timer;
}
{
struct hrtimer *timer = &dl_se->inactive_timer;
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
timer->function = inactive_task_timer;
}
}
#endif
-static inline void set_next_task(struct rq *rq, struct task_struct *p)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p)
{
p->se.exec_start = rq_clock_task(rq);
/* You can't push away the running task */
dequeue_pushable_dl_task(rq, p);
+
+ if (hrtick_enabled(rq))
+ start_hrtick_dl(rq, p);
+
+ if (rq->curr->sched_class != &dl_sched_class)
+ update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+ deadline_queue_push_tasks(rq);
}
static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
struct task_struct *p;
struct dl_rq *dl_rq;
- dl_rq = &rq->dl;
-
- if (need_pull_dl_task(rq, prev)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we're
- * being very careful to re-start the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_dl_task(rq);
- rq_repin_lock(rq, rf);
- /*
- * pull_dl_task() can drop (and re-acquire) rq->lock; this
- * means a stop task can slip in, in which case we need to
- * re-start task selection.
- */
- if (rq->stop && task_on_rq_queued(rq->stop))
- return RETRY_TASK;
- }
+ WARN_ON_ONCE(prev || rf);
- /*
- * When prev is DL, we may throttle it in put_prev_task().
- * So, we update time before we check for dl_nr_running.
- */
- if (prev->sched_class == &dl_sched_class)
- update_curr_dl(rq);
+ dl_rq = &rq->dl;
if (unlikely(!dl_rq->dl_nr_running))
return NULL;
- put_prev_task(rq, prev);
-
dl_se = pick_next_dl_entity(rq, dl_rq);
BUG_ON(!dl_se);
p = dl_task_of(dl_se);
- set_next_task(rq, p);
-
- if (hrtick_enabled(rq))
- start_hrtick_dl(rq, p);
-
- deadline_queue_push_tasks(rq);
-
- if (rq->curr->sched_class != &dl_sched_class)
- update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+ set_next_task_dl(rq, p);
return p;
}
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
{
update_curr_dl(rq);
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
+
+ if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_dl_task(rq);
+ rq_repin_lock(rq, rf);
+ }
}
/*
*/
}
-static void set_curr_task_dl(struct rq *rq)
-{
- set_next_task(rq, rq->curr);
-}
-
#ifdef CONFIG_SMP
/* Only try algorithms three times */
}
deactivate_task(rq, next_task, 0);
- sub_running_bw(&next_task->dl, &rq->dl);
- sub_rq_bw(&next_task->dl, &rq->dl);
set_task_cpu(next_task, later_rq->cpu);
- add_rq_bw(&next_task->dl, &later_rq->dl);
/*
* Update the later_rq clock here, because the clock is used
* by the cpufreq_update_util() inside __add_running_bw().
*/
update_rq_clock(later_rq);
- add_running_bw(&next_task->dl, &later_rq->dl);
activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
ret = 1;
resched = true;
deactivate_task(src_rq, p, 0);
- sub_running_bw(&p->dl, &src_rq->dl);
- sub_rq_bw(&p->dl, &src_rq->dl);
set_task_cpu(p, this_cpu);
- add_rq_bw(&p->dl, &this_rq->dl);
- add_running_bw(&p->dl, &this_rq->dl);
activate_task(this_rq, p, 0);
dmin = p->dl.deadline;
GFP_KERNEL, cpu_to_node(i));
}
+void dl_add_task_root_domain(struct task_struct *p)
+{
+ struct rq_flags rf;
+ struct rq *rq;
+ struct dl_bw *dl_b;
+
+ rq = task_rq_lock(p, &rf);
+ if (!dl_task(p))
+ goto unlock;
+
+ dl_b = &rq->rd->dl_bw;
+ raw_spin_lock(&dl_b->lock);
+
+ __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
+
+ raw_spin_unlock(&dl_b->lock);
+
+unlock:
+ task_rq_unlock(rq, p, &rf);
+}
+
+void dl_clear_root_domain(struct root_domain *rd)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
+ rd->dl_bw.total_bw = 0;
+ raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
+}
+
#endif /* CONFIG_SMP */
static void switched_from_dl(struct rq *rq, struct task_struct *p)
.pick_next_task = pick_next_task_dl,
.put_prev_task = put_prev_task_dl,
+ .set_next_task = set_next_task_dl,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_dl,
.task_woken = task_woken_dl,
#endif
- .set_curr_task = set_curr_task_dl,
.task_tick = task_tick_dl,
.task_fork = task_fork_dl,
raw_spin_lock_init(&rt_b->rt_runtime_lock);
- hrtimer_init(&rt_b->rt_period_timer,
- CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL_HARD);
rt_b->rt_period_timer.function = sched_rt_period_timer;
}
* to update the period.
*/
hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0));
- hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED);
+ hrtimer_start_expires(&rt_b->rt_period_timer,
+ HRTIMER_MODE_ABS_PINNED_HARD);
}
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
#endif
}
-static inline void set_next_task(struct rq *rq, struct task_struct *p)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p)
{
p->se.exec_start = rq_clock_task(rq);
/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
+
+ /*
+ * If prev task was rt, put_prev_task() has already updated the
+ * utilization. We only care of the case where we start to schedule a
+ * rt task
+ */
+ if (rq->curr->sched_class != &rt_sched_class)
+ update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+
+ rt_queue_push_tasks(rq);
}
static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
- if (need_pull_rt_task(rq, prev)) {
- /*
- * This is OK, because current is on_cpu, which avoids it being
- * picked for load-balance and preemption/IRQs are still
- * disabled avoiding further scheduler activity on it and we're
- * being very careful to re-start the picking loop.
- */
- rq_unpin_lock(rq, rf);
- pull_rt_task(rq);
- rq_repin_lock(rq, rf);
- /*
- * pull_rt_task() can drop (and re-acquire) rq->lock; this
- * means a dl or stop task can slip in, in which case we need
- * to re-start task selection.
- */
- if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
- rq->dl.dl_nr_running))
- return RETRY_TASK;
- }
-
- /*
- * We may dequeue prev's rt_rq in put_prev_task().
- * So, we update time before rt_queued check.
- */
- if (prev->sched_class == &rt_sched_class)
- update_curr_rt(rq);
+ WARN_ON_ONCE(prev || rf);
if (!rt_rq->rt_queued)
return NULL;
- put_prev_task(rq, prev);
-
p = _pick_next_task_rt(rq);
- set_next_task(rq, p);
-
- rt_queue_push_tasks(rq);
-
- /*
- * If prev task was rt, put_prev_task() has already updated the
- * utilization. We only care of the case where we start to schedule a
- * rt task
- */
- if (rq->curr->sched_class != &rt_sched_class)
- update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);
+ set_next_task_rt(rq, p);
return p;
}
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
{
update_curr_rt(rq);
*/
if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
+
+ if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+ /*
+ * This is OK, because current is on_cpu, which avoids it being
+ * picked for load-balance and preemption/IRQs are still
+ * disabled avoiding further scheduler activity on it and we've
+ * not yet started the picking loop.
+ */
+ rq_unpin_lock(rq, rf);
+ pull_rt_task(rq);
+ rq_repin_lock(rq, rf);
+ }
}
#ifdef CONFIG_SMP
}
next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
- if (p->rt.timeout > next)
- p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
+ if (p->rt.timeout > next) {
+ posix_cputimers_rt_watchdog(&p->posix_cputimers,
+ p->se.sum_exec_runtime);
+ }
}
}
#else
}
}
-static void set_curr_task_rt(struct rq *rq)
-{
- set_next_task(rq, rq->curr);
-}
-
static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
{
/*
.pick_next_task = pick_next_task_rt,
.put_prev_task = put_prev_task_rt,
+ .set_next_task = set_next_task_rt,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_rt,
.switched_from = switched_from_rt,
#endif
- .set_curr_task = set_curr_task_rt,
.task_tick = task_tick_rt,
.get_rr_interval = get_rr_interval_rt,
#ifndef SET_TSC_CTL
# define SET_TSC_CTL(a) (-EINVAL)
#endif
-#ifndef MPX_ENABLE_MANAGEMENT
-# define MPX_ENABLE_MANAGEMENT() (-EINVAL)
-#endif
-#ifndef MPX_DISABLE_MANAGEMENT
-# define MPX_DISABLE_MANAGEMENT() (-EINVAL)
-#endif
#ifndef GET_FP_MODE
# define GET_FP_MODE(a) (-EINVAL)
#endif
#ifndef PAC_RESET_KEYS
# define PAC_RESET_KEYS(a, b) (-EINVAL)
#endif
+#ifndef SET_TAGGED_ADDR_CTRL
+# define SET_TAGGED_ADDR_CTRL(a) (-EINVAL)
+#endif
+#ifndef GET_TAGGED_ADDR_CTRL
+# define GET_TAGGED_ADDR_CTRL() (-EINVAL)
+#endif
/*
* this is where the system-wide overflow UID and GID are defined, for
retval = -EPERM;
if (!retval)
retval = security_task_setrlimit(tsk, resource, new_rlim);
- if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) {
- /*
- * The caller is asking for an immediate RLIMIT_CPU
- * expiry. But we use the zero value to mean "it was
- * never set". So let's cheat and make it one second
- * instead
- */
- new_rlim->rlim_cur = 1;
- }
}
if (!retval) {
if (old_rlim)
task_unlock(tsk->group_leader);
/*
- * RLIMIT_CPU handling. Note that the kernel fails to return an error
- * code if it rejected the user's attempt to set RLIMIT_CPU. This is a
- * very long-standing error, and fixing it now risks breakage of
- * applications, so we live with it
+ * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not
+ * infite. In case of RLIM_INFINITY the posix CPU timer code
+ * ignores the rlimit.
*/
if (!retval && new_rlim && resource == RLIMIT_CPU &&
new_rlim->rlim_cur != RLIM_INFINITY &&
up_write(&me->mm->mmap_sem);
break;
case PR_MPX_ENABLE_MANAGEMENT:
- if (arg2 || arg3 || arg4 || arg5)
- return -EINVAL;
- error = MPX_ENABLE_MANAGEMENT();
- break;
case PR_MPX_DISABLE_MANAGEMENT:
- if (arg2 || arg3 || arg4 || arg5)
- return -EINVAL;
- error = MPX_DISABLE_MANAGEMENT();
- break;
+ /* No longer implemented: */
+ return -EINVAL;
case PR_SET_FP_MODE:
error = SET_FP_MODE(me, arg2);
break;
return -EINVAL;
error = PAC_RESET_KEYS(me, arg2);
break;
+ case PR_SET_TAGGED_ADDR_CTRL:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = SET_TAGGED_ADDR_CTRL(arg2);
+ break;
+ case PR_GET_TAGGED_ADDR_CTRL:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = GET_TAGGED_ADDR_CTRL();
+ break;
default:
error = -EINVAL;
break;
int ret = alarm_try_to_cancel(alarm);
if (ret >= 0)
return ret;
- cpu_relax();
+ hrtimer_cancel_wait_running(&alarm->timer);
}
}
EXPORT_SYMBOL_GPL(alarm_cancel);
return alarm_try_to_cancel(&timr->it.alarm.alarmtimer);
}
+ /**
+ * alarm_timer_wait_running - Posix timer callback to wait for a timer
+ * @timr: Pointer to the posixtimer data struct
+ *
+ * Called from the core code when timer cancel detected that the callback
+ * is running. @timr is unlocked and rcu read lock is held to prevent it
+ * from being freed.
+ */
+ static void alarm_timer_wait_running(struct k_itimer *timr)
+ {
+ hrtimer_cancel_wait_running(&timr->it.alarm.alarmtimer.timer);
+ }
+
/**
* alarm_timer_arm - Posix timer callback to arm a timer
* @timr: Pointer to the posixtimer data struct
enum alarmtimer_type type;
if (!alarmtimer_get_rtcdev())
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (!capable(CAP_WAKE_ALARM))
return -EPERM;
int ret = 0;
if (!alarmtimer_get_rtcdev())
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
if (flags & ~TIMER_ABSTIME)
return -EINVAL;
.timer_forward = alarm_timer_forward,
.timer_remaining = alarm_timer_remaining,
.timer_try_to_cancel = alarm_timer_try_to_cancel,
+ .timer_wait_running = alarm_timer_wait_running,
.nsleep = alarm_timer_nsleep,
};
#endif /* CONFIG_POSIX_TIMERS */
projects / linux.git / commitdiff