summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/scheduler/sched-deadline.txt6
-rw-r--r--Documentation/scheduler/sched-rt-group.txt8
-rw-r--r--arch/ia64/include/asm/thread_info.h6
-rw-r--r--arch/ia64/kernel/setup.c2
-rw-r--r--arch/ia64/kernel/time.c66
-rw-r--r--arch/parisc/kernel/setup.c2
-rw-r--r--arch/powerpc/include/asm/accounting.h14
-rw-r--r--arch/powerpc/include/asm/paca.h1
-rw-r--r--arch/powerpc/kernel/asm-offsets.c8
-rw-r--r--arch/powerpc/kernel/time.c138
-rw-r--r--arch/powerpc/xmon/xmon.c8
-rw-r--r--arch/s390/include/asm/lowcore.h65
-rw-r--r--arch/s390/include/asm/processor.h3
-rw-r--r--arch/s390/kernel/vtime.c138
-rw-r--r--arch/x86/kernel/cpu/amd.c6
-rw-r--r--arch/x86/kernel/cpu/centaur.c6
-rw-r--r--arch/x86/kernel/cpu/common.c3
-rw-r--r--arch/x86/kernel/cpu/cyrix.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c6
-rw-r--r--arch/x86/kernel/cpu/transmeta.c3
-rw-r--r--arch/x86/kernel/itmt.c6
-rw-r--r--arch/x86/kernel/kvmclock.c2
-rw-r--r--arch/x86/kernel/tsc.c11
-rw-r--r--fs/jbd2/commit.c2
-rw-r--r--fs/jbd2/journal.c12
-rw-r--r--include/linux/clocksource.h3
-rw-r--r--include/linux/kernel_stat.h5
-rw-r--r--include/linux/mutex.h4
-rw-r--r--include/linux/sched.h14
-rw-r--r--include/linux/vtime.h7
-rw-r--r--init/main.c1
-rw-r--r--kernel/locking/mutex.c24
-rw-r--r--kernel/sched/clock.c158
-rw-r--r--kernel/sched/completion.c10
-rw-r--r--kernel/sched/core.c223
-rw-r--r--kernel/sched/cputime.c16
-rw-r--r--kernel/sched/deadline.c13
-rw-r--r--kernel/sched/debug.c4
-rw-r--r--kernel/sched/fair.c94
-rw-r--r--kernel/sched/idle_task.c2
-rw-r--r--kernel/sched/rt.c9
-rw-r--r--kernel/sched/sched.h105
-rw-r--r--kernel/sched/stop_task.c2
-rw-r--r--kernel/time/clocksource.c4
44 files changed, 827 insertions, 395 deletions
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 8e37b0ba2c9d..cbc1b46cbf70 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -408,6 +408,11 @@ CONTENTS
* the new scheduling related syscalls that manipulate it, i.e.,
sched_setattr() and sched_getattr() are implemented.
+ For debugging purposes, the leftover runtime and absolute deadline of a
+ SCHED_DEADLINE task can be retrieved through /proc/<pid>/sched (entries
+ dl.runtime and dl.deadline, both values in ns). A programmatic way to
+ retrieve these values from production code is under discussion.
+
4.3 Default behavior
---------------------
@@ -476,6 +481,7 @@ CONTENTS
Still missing:
+ - programmatic way to retrieve current runtime and absolute deadline
- refinements to deadline inheritance, especially regarding the possibility
of retaining bandwidth isolation among non-interacting tasks. This is
being studied from both theoretical and practical points of view, and
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index a03f0d944fe6..d8fce3e78457 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -158,11 +158,11 @@ as its prone to starvation without deadline scheduling.
Consider two sibling groups A and B; both have 50% bandwidth, but A's
period is twice the length of B's.
-* group A: period=100000us, runtime=10000us
- - this runs for 0.01s once every 0.1s
+* group A: period=100000us, runtime=50000us
+ - this runs for 0.05s once every 0.1s
-* group B: period= 50000us, runtime=10000us
- - this runs for 0.01s twice every 0.1s (or once every 0.05 sec).
+* group B: period= 50000us, runtime=25000us
+ - this runs for 0.025s twice every 0.1s (or once every 0.05 sec).
This means that currently a while (1) loop in A will run for the full period of
B and can starve B's tasks (assuming they are of lower priority) for a whole
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index c7026429816b..8742d741d19a 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -27,6 +27,12 @@ struct thread_info {
mm_segment_t addr_limit; /* user-level address space limit */
int preempt_count; /* 0=premptable, <0=BUG; will also serve as bh-counter */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ __u64 utime;
+ __u64 stime;
+ __u64 gtime;
+ __u64 hardirq_time;
+ __u64 softirq_time;
+ __u64 idle_time;
__u64 ac_stamp;
__u64 ac_leave;
__u64 ac_stime;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 7ec7acc844c2..c483ece3eb84 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -619,6 +619,8 @@ setup_arch (char **cmdline_p)
check_sal_cache_flush();
#endif
paging_init();
+
+ clear_sched_clock_stable();
}
/*
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 71775b95d6cc..d040f12ea9f9 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -61,16 +61,41 @@ static struct clocksource *itc_clocksource;
extern cputime_t cycle_to_cputime(u64 cyc);
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
{
- cputime_t delta_utime;
struct thread_info *ti = task_thread_info(tsk);
+ cputime_t delta;
- if (ti->ac_utime) {
- delta_utime = cycle_to_cputime(ti->ac_utime);
- account_user_time(tsk, delta_utime);
- ti->ac_utime = 0;
+ if (ti->utime)
+ account_user_time(tsk, cycle_to_cputime(ti->utime));
+
+ if (ti->gtime)
+ account_guest_time(tsk, cycle_to_cputime(ti->gtime));
+
+ if (ti->idle_time)
+ account_idle_time(cycle_to_cputime(ti->idle_time));
+
+ if (ti->stime) {
+ delta = cycle_to_cputime(ti->stime);
+ account_system_index_time(tsk, delta, CPUTIME_SYSTEM);
+ }
+
+ if (ti->hardirq_time) {
+ delta = cycle_to_cputime(ti->hardirq_time);
+ account_system_index_time(tsk, delta, CPUTIME_IRQ);
+ }
+
+ if (ti->softirq_time) {
+ delta = cycle_to_cputime(ti->softirq_time);
+ account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
}
+
+ ti->utime = 0;
+ ti->gtime = 0;
+ ti->idle_time = 0;
+ ti->stime = 0;
+ ti->hardirq_time = 0;
+ ti->softirq_time = 0;
}
/*
@@ -83,7 +108,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
struct thread_info *pi = task_thread_info(prev);
struct thread_info *ni = task_thread_info(current);
- pi->ac_stamp = ni->ac_stamp;
+ ni->ac_stamp = pi->ac_stamp;
ni->ac_stime = ni->ac_utime = 0;
}
@@ -91,18 +116,15 @@ void arch_vtime_task_switch(struct task_struct *prev)
* Account time for a transition between system, hard irq or soft irq state.
* Note that this function is called with interrupts enabled.
*/
-static cputime_t vtime_delta(struct task_struct *tsk)
+static __u64 vtime_delta(struct task_struct *tsk)
{
struct thread_info *ti = task_thread_info(tsk);
- cputime_t delta_stime;
- __u64 now;
+ __u64 now, delta_stime;
WARN_ON_ONCE(!irqs_disabled());
now = ia64_get_itc();
-
- delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
- ti->ac_stime = 0;
+ delta_stime = now - ti->ac_stamp;
ti->ac_stamp = now;
return delta_stime;
@@ -110,15 +132,25 @@ static cputime_t vtime_delta(struct task_struct *tsk)
void vtime_account_system(struct task_struct *tsk)
{
- cputime_t delta = vtime_delta(tsk);
-
- account_system_time(tsk, 0, delta);
+ struct thread_info *ti = task_thread_info(tsk);
+ __u64 stime = vtime_delta(tsk);
+
+ if ((tsk->flags & PF_VCPU) && !irq_count())
+ ti->gtime += stime;
+ else if (hardirq_count())
+ ti->hardirq_time += stime;
+ else if (in_serving_softirq())
+ ti->softirq_time += stime;
+ else
+ ti->stime += stime;
}
EXPORT_SYMBOL_GPL(vtime_account_system);
void vtime_account_idle(struct task_struct *tsk)
{
- account_idle_time(vtime_delta(tsk));
+ struct thread_info *ti = task_thread_info(tsk);
+
+ ti->idle_time += vtime_delta(tsk);
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 2e66a887788e..068ed3607bac 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -36,6 +36,7 @@
#undef PCI_DEBUG
#include <linux/proc_fs.h>
#include <linux/export.h>
+#include <linux/sched.h>
#include <asm/processor.h>
#include <asm/sections.h>
@@ -176,6 +177,7 @@ void __init setup_arch(char **cmdline_p)
conswitchp = &dummy_con; /* we use do_take_over_console() later ! */
#endif
+ clear_sched_clock_stable();
}
/*
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h
index c133246df467..3abcf98ed2e0 100644
--- a/arch/powerpc/include/asm/accounting.h
+++ b/arch/powerpc/include/asm/accounting.h
@@ -12,9 +12,17 @@
/* Stuff for accurate time accounting */
struct cpu_accounting_data {
- unsigned long user_time; /* accumulated usermode TB ticks */
- unsigned long system_time; /* accumulated system TB ticks */
- unsigned long user_time_scaled; /* accumulated usermode SPURR ticks */
+ /* Accumulated cputime values to flush on ticks*/
+ unsigned long utime;
+ unsigned long stime;
+ unsigned long utime_scaled;
+ unsigned long stime_scaled;
+ unsigned long gtime;
+ unsigned long hardirq_time;
+ unsigned long softirq_time;
+ unsigned long steal_time;
+ unsigned long idle_time;
+ /* Internal counters */
unsigned long starttime; /* TB value snapshot */
unsigned long starttime_user; /* TB value on exit to usermode */
unsigned long startspurr; /* SPURR value snapshot */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 6a6792bb39fb..708c3e592eeb 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -187,7 +187,6 @@ struct paca_struct {
/* Stuff for accurate time accounting */
struct cpu_accounting_data accounting;
- u64 stolen_time; /* TB ticks taken by hypervisor */
u64 dtl_ridx; /* read index in dispatch log */
struct dtl_entry *dtl_curr; /* pointer corresponding to dtl_ridx */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0601e6a7297c..e505319574ca 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -252,9 +252,9 @@ int main(void)
DEFINE(ACCOUNT_STARTTIME_USER,
offsetof(struct paca_struct, accounting.starttime_user));
DEFINE(ACCOUNT_USER_TIME,
- offsetof(struct paca_struct, accounting.user_time));
+ offsetof(struct paca_struct, accounting.utime));
DEFINE(ACCOUNT_SYSTEM_TIME,
- offsetof(struct paca_struct, accounting.system_time));
+ offsetof(struct paca_struct, accounting.stime));
DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
@@ -265,9 +265,9 @@ int main(void)
DEFINE(ACCOUNT_STARTTIME_USER,
offsetof(struct thread_info, accounting.starttime_user));
DEFINE(ACCOUNT_USER_TIME,
- offsetof(struct thread_info, accounting.user_time));
+ offsetof(struct thread_info, accounting.utime));
DEFINE(ACCOUNT_SYSTEM_TIME,
- offsetof(struct thread_info, accounting.system_time));
+ offsetof(struct thread_info, accounting.stime));
#endif
#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index bc2e08d415fa..02e97305d22b 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -271,25 +271,19 @@ void accumulate_stolen_time(void)
sst = scan_dispatch_log(acct->starttime_user);
ust = scan_dispatch_log(acct->starttime);
- acct->system_time -= sst;
- acct->user_time -= ust;
- local_paca->stolen_time += ust + sst;
+ acct->stime -= sst;
+ acct->utime -= ust;
+ acct->steal_time += ust + sst;
local_paca->soft_enabled = save_soft_enabled;
}
static inline u64 calculate_stolen_time(u64 stop_tb)
{
- u64 stolen = 0;
-
- if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
- stolen = scan_dispatch_log(stop_tb);
- get_paca()->accounting.system_time -= stolen;
- }
+ if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
+ return scan_dispatch_log(stop_tb);
- stolen += get_paca()->stolen_time;
- get_paca()->stolen_time = 0;
- return stolen;
+ return 0;
}
#else /* CONFIG_PPC_SPLPAR */
@@ -305,28 +299,27 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
* or soft irq state.
*/
static unsigned long vtime_delta(struct task_struct *tsk,
- unsigned long *sys_scaled,
- unsigned long *stolen)
+ unsigned long *stime_scaled,
+ unsigned long *steal_time)
{
unsigned long now, nowscaled, deltascaled;
- unsigned long udelta, delta, user_scaled;
+ unsigned long stime;
+ unsigned long utime, utime_scaled;
struct cpu_accounting_data *acct = get_accounting(tsk);
WARN_ON_ONCE(!irqs_disabled());
now = mftb();
nowscaled = read_spurr(now);
- acct->system_time += now - acct->starttime;
+ stime = now - acct->starttime;
acct->starttime = now;
deltascaled = nowscaled - acct->startspurr;
acct->startspurr = nowscaled;
- *stolen = calculate_stolen_time(now);
+ *steal_time = calculate_stolen_time(now);
- delta = acct->system_time;
- acct->system_time = 0;
- udelta = acct->user_time - acct->utime_sspurr;
- acct->utime_sspurr = acct->user_time;
+ utime = acct->utime - acct->utime_sspurr;
+ acct->utime_sspurr = acct->utime;
/*
* Because we don't read the SPURR on every kernel entry/exit,
@@ -338,62 +331,104 @@ static unsigned long vtime_delta(struct task_struct *tsk,
* the user ticks get saved up in paca->user_time_scaled to be
* used by account_process_tick.
*/
- *sys_scaled = delta;
- user_scaled = udelta;
- if (deltascaled != delta + udelta) {
- if (udelta) {
- *sys_scaled = deltascaled * delta / (delta + udelta);
- user_scaled = deltascaled - *sys_scaled;
+ *stime_scaled = stime;
+ utime_scaled = utime;
+ if (deltascaled != stime + utime) {
+ if (utime) {
+ *stime_scaled = deltascaled * stime / (stime + utime);
+ utime_scaled = deltascaled - *stime_scaled;
} else {
- *sys_scaled = deltascaled;
+ *stime_scaled = deltascaled;
}
}
- acct->user_time_scaled += user_scaled;
+ acct->utime_scaled += utime_scaled;
- return delta;
+ return stime;
}
void vtime_account_system(struct task_struct *tsk)
{
- unsigned long delta, sys_scaled, stolen;
+ unsigned long stime, stime_scaled, steal_time;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
+
+ stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+
+ stime -= min(stime, steal_time);
+ acct->steal_time += steal_time;
- delta = vtime_delta(tsk, &sys_scaled, &stolen);
- account_system_time(tsk, 0, delta);
- tsk->stimescaled += sys_scaled;
- if (stolen)
- account_steal_time(stolen);
+ if ((tsk->flags & PF_VCPU) && !irq_count()) {
+ acct->gtime += stime;
+ acct->utime_scaled += stime_scaled;
+ } else {
+ if (hardirq_count())
+ acct->hardirq_time += stime;
+ else if (in_serving_softirq())
+ acct->softirq_time += stime;
+ else
+ acct->stime += stime;
+
+ acct->stime_scaled += stime_scaled;
+ }
}
EXPORT_SYMBOL_GPL(vtime_account_system);
void vtime_account_idle(struct task_struct *tsk)
{
- unsigned long delta, sys_scaled, stolen;
+ unsigned long stime, stime_scaled, steal_time;
+ struct cpu_accounting_data *acct = get_accounting(tsk);
- delta = vtime_delta(tsk, &sys_scaled, &stolen);
- account_idle_time(delta + stolen);
+ stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+ acct->idle_time += stime + steal_time;
}
/*
- * Transfer the user time accumulated in the paca
- * by the exception entry and exit code to the generic
- * process user time records.
+ * Account the whole cputime accumulated in the paca
* Must be called with interrupts disabled.
* Assumes that vtime_account_system/idle() has been called
* recently (i.e. since the last entry from usermode) so that
* get_paca()->user_time_scaled is up to date.
*/
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
{
- cputime_t utime, utimescaled;
struct cpu_accounting_data *acct = get_accounting(tsk);
- utime = acct->user_time;
- utimescaled = acct->user_time_scaled;
- acct->user_time = 0;
- acct->user_time_scaled = 0;
+ if (acct->utime)
+ account_user_time(tsk, acct->utime);
+
+ if (acct->utime_scaled)
+ tsk->utimescaled += acct->utime_scaled;
+
+ if (acct->gtime)
+ account_guest_time(tsk, acct->gtime);
+
+ if (acct->steal_time)
+ account_steal_time(acct->steal_time);
+
+ if (acct->idle_time)
+ account_idle_time(acct->idle_time);
+
+ if (acct->stime)
+ account_system_index_time(tsk, acct->stime, CPUTIME_SYSTEM);
+
+ if (acct->stime_scaled)
+ tsk->stimescaled += acct->stime_scaled;
+
+ if (acct->hardirq_time)
+ account_system_index_time(tsk, acct->hardirq_time, CPUTIME_IRQ);
+
+ if (acct->softirq_time)
+ account_system_index_time(tsk, acct->softirq_time, CPUTIME_SOFTIRQ);
+
+ acct->utime = 0;
+ acct->utime_scaled = 0;
acct->utime_sspurr = 0;
- account_user_time(tsk, utime);
- tsk->utimescaled += utimescaled;
+ acct->gtime = 0;
+ acct->steal_time = 0;
+ acct->idle_time = 0;
+ acct->stime = 0;
+ acct->stime_scaled = 0;
+ acct->hardirq_time = 0;
+ acct->softirq_time = 0;
}
#ifdef CONFIG_PPC32
@@ -407,8 +442,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
struct cpu_accounting_data *acct = get_accounting(current);
acct->starttime = get_accounting(prev)->starttime;
- acct->system_time = 0;
- acct->user_time = 0;
+ acct->startspurr = get_accounting(prev)->startspurr;
}
#endif /* CONFIG_PPC32 */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 9c0e17cf6886..3f864c36d847 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2287,14 +2287,14 @@ static void dump_one_paca(int cpu)
DUMP(p, subcore_sibling_mask, "x");
#endif
- DUMP(p, accounting.user_time, "llx");
- DUMP(p, accounting.system_time, "llx");
- DUMP(p, accounting.user_time_scaled, "llx");
+ DUMP(p, accounting.utime, "llx");
+ DUMP(p, accounting.stime, "llx");
+ DUMP(p, accounting.utime_scaled, "llx");
DUMP(p, accounting.starttime, "llx");
DUMP(p, accounting.starttime_user, "llx");
DUMP(p, accounting.startspurr, "llx");
DUMP(p, accounting.utime_sspurr, "llx");
- DUMP(p, stolen_time, "llx");
+ DUMP(p, accounting.steal_time, "llx");
#undef DUMP
catch_memory_errors = 0;
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 9bfad2ad6312..61261e0e95c0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -85,53 +85,56 @@ struct lowcore {
__u64 mcck_enter_timer; /* 0x02c0 */
__u64 exit_timer; /* 0x02c8 */
__u64 user_timer; /* 0x02d0 */
- __u64 system_timer; /* 0x02d8 */
- __u64 steal_timer; /* 0x02e0 */
- __u64 last_update_timer; /* 0x02e8 */
- __u64 last_update_clock; /* 0x02f0 */
- __u64 int_clock; /* 0x02f8 */
- __u64 mcck_clock; /* 0x0300 */
- __u64 clock_comparator; /* 0x0308 */
+ __u64 guest_timer; /* 0x02d8 */
+ __u64 system_timer; /* 0x02e0 */
+ __u64 hardirq_timer; /* 0x02e8 */
+ __u64 softirq_timer; /* 0x02f0 */
+ __u64 steal_timer; /* 0x02f8 */
+ __u64 last_update_timer; /* 0x0300 */
+ __u64 last_update_clock; /* 0x0308 */
+ __u64 int_clock; /* 0x0310 */
+ __u64 mcck_clock; /* 0x0318 */
+ __u64 clock_comparator; /* 0x0320 */
/* Current process. */
- __u64 current_task; /* 0x0310 */
- __u8 pad_0x318[0x320-0x318]; /* 0x0318 */
- __u64 kernel_stack; /* 0x0320 */
+ __u64 current_task; /* 0x0328 */
+ __u8 pad_0x318[0x320-0x318]; /* 0x0330 */
+ __u64 kernel_stack; /* 0x0338 */
/* Interrupt, panic and restart stack. */
- __u64 async_stack; /* 0x0328 */
- __u64 panic_stack; /* 0x0330 */
- __u64 restart_stack; /* 0x0338 */
+ __u64 async_stack; /* 0x0340 */
+ __u64 panic_stack; /* 0x0348 */
+ __u64 restart_stack; /* 0x0350 */
/* Restart function and parameter. */
- __u64 restart_fn; /* 0x0340 */
- __u64 restart_data; /* 0x0348 */
- __u64 restart_source; /* 0x0350 */
+ __u64 restart_fn; /* 0x0358 */
+ __u64 restart_data; /* 0x0360 */
+ __u64 restart_source; /* 0x0368 */
/* Address space pointer. */
- __u64 kernel_asce; /* 0x0358 */
- __u64 user_asce; /* 0x0360 */
+ __u64 kernel_asce; /* 0x0370 */
+ __u64 user_asce; /* 0x0378 */
/*
* The lpp and current_pid fields form a
* 64-bit value that is set as program
* parameter with the LPP instruction.
*/
- __u32 lpp; /* 0x0368 */
- __u32 current_pid; /* 0x036c */
+ __u32 lpp; /* 0x0380 */
+ __u32 current_pid; /* 0x0384 */
/* SMP info area */
- __u32 cpu_nr; /* 0x0370 */
- __u32 softirq_pending; /* 0x0374 */
- __u64 percpu_offset; /* 0x0378 */
- __u64 vdso_per_cpu_data; /* 0x0380 */
- __u64 machine_flags; /* 0x0388 */
- __u32 preempt_count; /* 0x0390 */
- __u8 pad_0x0394[0x0398-0x0394]; /* 0x0394 */
- __u64 gmap; /* 0x0398 */
- __u32 spinlock_lockval; /* 0x03a0 */
- __u32 fpu_flags; /* 0x03a4 */
- __u8 pad_0x03a8[0x0400-0x03a8]; /* 0x03a8 */
+ __u32 cpu_nr; /* 0x0388 */
+ __u32 softirq_pending; /* 0x038c */
+ __u64 percpu_offset; /* 0x0390 */
+ __u64 vdso_per_cpu_data; /* 0x0398 */
+ __u64 machine_flags; /* 0x03a0 */
+ __u32 preempt_count; /* 0x03a8 */
+ __u8 pad_0x03ac[0x03b0-0x03ac]; /* 0x03ac */
+ __u64 gmap; /* 0x03b0 */
+ __u32 spinlock_lockval; /* 0x03b8 */
+ __u32 fpu_flags; /* 0x03bc */
+ __u8 pad_0x03c0[0x0400-0x03c0]; /* 0x03c0 */
/* Per cpu primary space access list */
__u32 paste[16]; /* 0x0400 */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6bca916a5ba0..977a5b6501b8 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -111,7 +111,10 @@ struct thread_struct {
unsigned int acrs[NUM_ACRS];
unsigned long ksp; /* kernel stack pointer */
unsigned long user_timer; /* task cputime in user space */
+ unsigned long guest_timer; /* task cputime in kvm guest */
unsigned long system_timer; /* task cputime in kernel space */
+ unsigned long hardirq_timer; /* task cputime in hardirq context */
+ unsigned long softirq_timer; /* task cputime in softirq context */
unsigned long sys_call_table; /* system call table address */
mm_segment_t mm_segment;
unsigned long gmap_addr; /* address of last gmap fault. */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 1b5c5ee9fc1b..0a9e5d67547d 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -90,14 +90,41 @@ static void update_mt_scaling(void)
__this_cpu_write(mt_scaling_jiffies, jiffies_64);
}
+static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new)
+{
+ u64 delta;
+
+ delta = new - *tsk_vtime;
+ *tsk_vtime = new;
+ return delta;
+}
+
+
+static inline u64 scale_vtime(u64 vtime)
+{
+ u64 mult = __this_cpu_read(mt_scaling_mult);
+ u64 div = __this_cpu_read(mt_scaling_div);
+
+ if (smp_cpu_mtid)
+ return vtime * mult / div;
+ return vtime;
+}
+
+static void account_system_index_scaled(struct task_struct *p,
+ cputime_t cputime, cputime_t scaled,
+ enum cpu_usage_stat index)
+{
+ p->stimescaled += scaled;
+ account_system_index_time(p, cputime, index);
+}
+
/*
* Update process times based on virtual cpu times stored by entry.S
* to the lowcore fields user_timer, system_timer & steal_clock.
*/
static int do_account_vtime(struct task_struct *tsk)
{
- u64 timer, clock, user, system, steal;
- u64 user_scaled, system_scaled;
+ u64 timer, clock, user, guest, system, hardirq, softirq, steal;
timer = S390_lowcore.last_update_timer;
clock = S390_lowcore.last_update_clock;
@@ -110,36 +137,53 @@ static int do_account_vtime(struct task_struct *tsk)
#endif
: "=m" (S390_lowcore.last_update_timer),
"=m" (S390_lowcore.last_update_clock));
- S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
- S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
+ clock = S390_lowcore.last_update_clock - clock;
+ timer -= S390_lowcore.last_update_timer;
+
+ if (hardirq_count())
+ S390_lowcore.hardirq_timer += timer;
+ else
+ S390_lowcore.system_timer += timer;
/* Update MT utilization calculation */
if (smp_cpu_mtid &&
time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
update_mt_scaling();
- user = S390_lowcore.user_timer - tsk->thread.user_timer;
- S390_lowcore.steal_timer -= user;
- tsk->thread.user_timer = S390_lowcore.user_timer;
-
- system = S390_lowcore.system_timer - tsk->thread.system_timer;
- S390_lowcore.steal_timer -= system;
- tsk->thread.system_timer = S390_lowcore.system_timer;
-
- user_scaled = user;
- system_scaled = system;
- /* Do MT utilization scaling */
- if (smp_cpu_mtid) {
- u64 mult = __this_cpu_read(mt_scaling_mult);
- u64 div = __this_cpu_read(mt_scaling_div);
+ /* Calculate cputime delta */
+ user = update_tsk_timer(&tsk->thread.user_timer,
+ READ_ONCE(S390_lowcore.user_timer));
+ guest = update_tsk_timer(&tsk->thread.guest_timer,
+ READ_ONCE(S390_lowcore.guest_timer));
+ system = update_tsk_timer(&tsk->thread.system_timer,
+ READ_ONCE(S390_lowcore.system_timer));
+ hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
+ READ_ONCE(S390_lowcore.hardirq_timer));
+ softirq = update_tsk_timer(&tsk->thread.softirq_timer,
+ READ_ONCE(S390_lowcore.softirq_timer));
+ S390_lowcore.steal_timer +=
+ clock - user - guest - system - hardirq - softirq;
+
+ /* Push account value */
+ if (user) {
+ account_user_time(tsk, user);
+ tsk->utimescaled += scale_vtime(user);
+ }
- user_scaled = (user_scaled * mult) / div;
- system_scaled = (system_scaled * mult) / div;
+ if (guest) {
+ account_guest_time(tsk, guest);
+ tsk->utimescaled += scale_vtime(guest);
}
- account_user_time(tsk, user);
- tsk->utimescaled += user_scaled;
- account_system_time(tsk, 0, system);
- tsk->stimescaled += system_scaled;
+
+ if (system)
+ account_system_index_scaled(tsk, system, scale_vtime(system),
+ CPUTIME_SYSTEM);
+ if (hardirq)
+ account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
+ CPUTIME_IRQ);
+ if (softirq)
+ account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
+ CPUTIME_SOFTIRQ);
steal = S390_lowcore.steal_timer;
if ((s64) steal > 0) {
@@ -147,16 +191,22 @@ static int do_account_vtime(struct task_struct *tsk)
account_steal_time(steal);
}
- return virt_timer_forward(user + system);
+ return virt_timer_forward(user + guest + system + hardirq + softirq);
}
void vtime_task_switch(struct task_struct *prev)
{
do_account_vtime(prev);
prev->thread.user_timer = S390_lowcore.user_timer;
+ prev->thread.guest_timer = S390_lowcore.guest_timer;
prev->thread.system_timer = S390_lowcore.system_timer;
+ prev->thread.hardirq_timer = S390_lowcore.hardirq_timer;
+ prev->thread.softirq_timer = S390_lowcore.softirq_timer;
S390_lowcore.user_timer = current->thread.user_timer;
+ S390_lowcore.guest_timer = current->thread.guest_timer;
S390_lowcore.system_timer = current->thread.system_timer;
+ S390_lowcore.hardirq_timer = current->thread.hardirq_timer;
+ S390_lowcore.softirq_timer = current->thread.softirq_timer;
}
/*
@@ -164,7 +214,7 @@ void vtime_task_switch(struct task_struct *prev)
* accounting system time in order to correctly compute
* the stolen time accounting.
*/
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
{
if (do_account_vtime(tsk))
virt_timer_expire();
@@ -176,32 +226,22 @@ void vtime_account_user(struct task_struct *tsk)
*/
void vtime_account_irq_enter(struct task_struct *tsk)
{
- u64 timer, system, system_scaled;
+ u64 timer;
timer = S390_lowcore.last_update_timer;
S390_lowcore.last_update_timer = get_vtimer();
- S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-
- /* Update MT utilization calculation */
- if (smp_cpu_mtid &&
- time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
- update_mt_scaling();
-
- system = S390_lowcore.system_timer - tsk->thread.system_timer;
- S390_lowcore.steal_timer -= system;
- tsk->thread.system_timer = S390_lowcore.system_timer;
- system_scaled = system;
- /* Do MT utilization scaling */
- if (smp_cpu_mtid) {
- u64 mult = __this_cpu_read(mt_scaling_mult);
- u64 div = __this_cpu_read(mt_scaling_div);
-
- system_scaled = (system_scaled * mult) / div;
- }
- account_system_time(tsk, 0, system);
- tsk->stimescaled += system_scaled;
-
- virt_timer_forward(system);
+ timer -= S390_lowcore.last_update_timer;
+
+ if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
+ S390_lowcore.guest_timer += timer;
+ else if (hardirq_count())
+ S390_lowcore.hardirq_timer += timer;
+ else if (in_serving_softirq())
+ S390_lowcore.softirq_timer += timer;
+ else
+ S390_lowcore.system_timer += timer;
+
+ virt_timer_forward(timer);
}
EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..80e657e89eed 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -541,8 +541,10 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (!check_tsc_unstable())
- set_sched_clock_stable();
+ if (check_tsc_unstable())
+ clear_sched_clock_stable();
+ } else {
+ clear_sched_clock_stable();
}
/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 1661d8ec9280..2c234a6d94c4 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,5 +1,5 @@
-#include <linux/bitops.h>
-#include <linux/kernel.h>
+
+#include <linux/sched.h>
#include <asm/cpufeature.h>
#include <asm/e820.h>
@@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#endif
+
+ clear_sched_clock_stable();
}
static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bab7a8a4293..0bdb1ab7d17c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -83,6 +83,7 @@ static void default_init(struct cpuinfo_x86 *c)
strcpy(c->x86_model_id, "386");
}
#endif
+ clear_sched_clock_stable();
}
static const struct cpu_dev default_cpu = {
@@ -1055,6 +1056,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
*/
if (this_cpu->c_init)
this_cpu->c_init(c);
+ else
+ clear_sched_clock_stable();
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index bd9dcd6b712d..47416f959a48 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -9,6 +9,7 @@
#include <asm/pci-direct.h>
#include <asm/tsc.h>
#include <asm/cpufeature.h>
+#include <linux/sched.h>
#include "cpu.h"
@@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
break;
}
+ clear_sched_clock_stable();
}
static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 203f860d2ab3..026c728d6ba7 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -119,8 +119,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (!check_tsc_unstable())
- set_sched_clock_stable();
+ if (check_tsc_unstable())
+ clear_sched_clock_stable();
+ } else {
+ clear_sched_clock_stable();
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 34178564be2a..c1ea5b999839 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,4 +1,5 @@
#include <linux/kernel.h>
+#include <linux/sched.h>
#include <linux/mm.h>
#include <asm/cpufeature.h>
#include <asm/msr.h>
@@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
if (xlvl >= 0x80860001)
c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
}
+
+ clear_sched_clock_stable();
}
static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index cb9c1ed1d391..f73f475d0573 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -132,10 +132,8 @@ int sched_set_itmt_support(void)
sysctl_sched_itmt_enabled = 1;
- if (sysctl_sched_itmt_enabled) {
- x86_topology_update = true;
- rebuild_sched_domains();
- }
+ x86_topology_update = true;
+ rebuild_sched_domains();
mutex_unlock(&itmt_update_mutex);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2a5cafdf8808..542710b99f52 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable)
{
if (!stable) {
pv_time_ops.sched_clock = kvm_clock_read;
+ clear_sched_clock_stable();
return;
}
kvm_sched_clock_offset = kvm_clock_read();
pv_time_ops.sched_clock = kvm_sched_clock_read;
- set_sched_clock_stable();
printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e41af597aed8..cb60bbe093b2 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs)
return (u64)rdtsc_ordered();
}
+static void tsc_cs_mark_unstable(struct clocksource *cs)
+{
+ if (tsc_unstable)
+ return;
+ tsc_unstable = 1;
+ clear_sched_clock_stable();
+ disable_sched_clock_irqtime();
+ pr_info("Marking TSC unstable due to clocksource watchdog\n");
+}
+
/*
* .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
*/
@@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = {
CLOCK_SOURCE_MUST_VERIFY,
.archdata = { .vclock_mode = VCLOCK_TSC },
.resume = tsc_resume,
+ .mark_unstable = tsc_cs_mark_unstable,
};
void mark_tsc_unstable(char *reason)
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8c514367ba5a..b6b194ec1b4f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -393,7 +393,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/* Do we need to erase the effects of a prior jbd2_journal_flush? */
if (journal->j_flags & JBD2_FLUSHED) {
jbd_debug(3, "super block updated\n");
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
/*
* We hold j_checkpoint_mutex so tail cannot change under us.
* We don't need any special data guarantees for writing sb
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a097048ed1a3..d8a5d0a08f07 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -944,7 +944,7 @@ out:
*/
void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
{
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
if (tid_gt(tid, journal->j_tail_sequence))
__jbd2_update_log_tail(journal, tid, block);
mutex_unlock(&journal->j_checkpoint_mutex);
@@ -1304,7 +1304,7 @@ static int journal_reset(journal_t *journal)
journal->j_flags |= JBD2_FLUSHED;
} else {
/* Lock here to make assertions happy... */
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
/*
* Update log tail information. We use REQ_FUA since new
* transaction will start reusing journal space and so we
@@ -1691,7 +1691,7 @@ int jbd2_journal_destroy(journal_t *journal)
spin_lock(&journal->j_list_lock);
while (journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
err = jbd2_log_do_checkpoint(journal);
mutex_unlock(&journal->j_checkpoint_mutex);
/*
@@ -1713,7 +1713,7 @@ int jbd2_journal_destroy(journal_t *journal)
if (journal->j_sb_buffer) {
if (!is_journal_aborted(journal)) {
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
write_lock(&journal->j_state_lock);
journal->j_tail_sequence =
@@ -1955,7 +1955,7 @@ int jbd2_journal_flush(journal_t *journal)
spin_lock(&journal->j_list_lock);
while (!err && journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
err = jbd2_log_do_checkpoint(journal);
mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
@@ -1965,7 +1965,7 @@ int jbd2_journal_flush(journal_t *journal)
if (is_journal_aborted(journal))
return -EIO;
- mutex_lock(&journal->j_checkpoint_mutex);
+ mutex_lock_io(&journal->j_checkpoint_mutex);
if (!err) {
err = jbd2_cleanup_journal_tail(journal);
if (err < 0) {
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index e315d04a2fd9..cfc75848a35d 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -62,6 +62,8 @@ struct module;
* @archdata: arch-specific data
* @suspend: suspend function for the clocksource, if necessary
* @resume: resume function for the clocksource, if necessary
+ * @mark_unstable: Optional function to inform the clocksource driver that
+ * the watchdog marked the clocksource unstable
* @owner: module reference, must be set by clocksource in modules
*
* Note: This struct is not used in hotpathes of the timekeeping code
@@ -93,6 +95,7 @@ struct clocksource {
unsigned long flags;
void (*suspend)(struct clocksource *cs);
void (*resume)(struct clocksource *cs);
+ void (*mark_unstable)(struct clocksource *cs);
/* private: */
#ifdef CONFIG_CLOCKSOURCE_WATCHDOG
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 00f776816aa3..c3e38ded2d73 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -79,14 +79,17 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
}
extern void account_user_time(struct task_struct *, cputime_t);
+extern void account_guest_time(struct task_struct *, cputime_t);
extern void account_system_time(struct task_struct *, int, cputime_t);
+extern void account_system_index_time(struct task_struct *, cputime_t,
+ enum cpu_usage_stat);
extern void account_steal_time(cputime_t);
extern void account_idle_time(cputime_t);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
static inline void account_process_tick(struct task_struct *tsk, int user)
{
- vtime_account_user(tsk);
+ vtime_flush(tsk);
}
#else
extern void account_process_tick(struct task_struct *, int user);
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index b97870f2debd..7fffbfcd5430 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -156,10 +156,12 @@ extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
unsigned int subclass);
extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
unsigned int subclass);
+extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass);
#define mutex_lock(lock) mutex_lock_nested(lock, 0)
#define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
#define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+#define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0)
#define mutex_lock_nest_lock(lock, nest_lock) \
do { \
@@ -171,11 +173,13 @@ do { \
extern void mutex_lock(struct mutex *lock);
extern int __must_check mutex_lock_interruptible(struct mutex *lock);
extern int __must_check mutex_lock_killable(struct mutex *lock);
+extern void mutex_lock_io(struct mutex *lock);
# define mutex_lock_nested(lock, subclass) mutex_lock(lock)
# define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
# define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
#endif
/*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ad3ec9ec61f7..69e6852fede1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -461,12 +461,10 @@ extern signed long schedule_timeout_idle(signed long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
+extern int __must_check io_schedule_prepare(void);
+extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
-
-static inline void io_schedule(void)
-{
- io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
-}
+extern void io_schedule(void);
void __noreturn do_task_dead(void);
@@ -2515,6 +2513,10 @@ extern u64 sched_clock_cpu(int cpu);
extern void sched_clock_init(void);
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_init_late(void)
+{
+}
+
static inline void sched_clock_tick(void)
{
}
@@ -2537,6 +2539,7 @@ static inline u64 local_clock(void)
return sched_clock();
}
#else
+extern void sched_clock_init_late(void);
/*
* Architectures can set this to 1 if they have specified
* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
@@ -2544,7 +2547,6 @@ static inline u64 local_clock(void)
* is reliable after all:
*/
extern int sched_clock_stable(void);
-extern void set_sched_clock_stable(void);
extern void clear_sched_clock_stable(void);
extern void sched_clock_tick(void);
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index aa9bfea8804a..0681fe25abeb 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -58,27 +58,28 @@ static inline void vtime_task_switch(struct task_struct *prev)
extern void vtime_account_system(struct task_struct *tsk);
extern void vtime_account_idle(struct task_struct *tsk);
-extern void vtime_account_user(struct task_struct *tsk);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
static inline void vtime_task_switch(struct task_struct *prev) { }
static inline void vtime_account_system(struct task_struct *tsk) { }
-static inline void vtime_account_user(struct task_struct *tsk) { }
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern void arch_vtime_task_switch(struct task_struct *tsk);
+extern void vtime_account_user(struct task_struct *tsk);
extern void vtime_user_enter(struct task_struct *tsk);
static inline void vtime_user_exit(struct task_struct *tsk)
{
vtime_account_user(tsk);
}
+
extern void vtime_guest_enter(struct task_struct *tsk);
extern void vtime_guest_exit(struct task_struct *tsk);
extern void vtime_init_idle(struct task_struct *tsk, int cpu);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */
+static inline void vtime_account_user(struct task_struct *tsk) { }
static inline void vtime_user_enter(struct task_struct *tsk) { }
static inline void vtime_user_exit(struct task_struct *tsk) { }
static inline void vtime_guest_enter(struct task_struct *tsk) { }
@@ -93,9 +94,11 @@ static inline void vtime_account_irq_exit(struct task_struct *tsk)
/* On hard|softirq exit we always account to hard|softirq cputime */
vtime_account_system(tsk);
}
+extern void vtime_flush(struct task_struct *tsk);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
+static inline void vtime_flush(struct task_struct *tsk) { }
#endif
diff --git a/init/main.c b/init/main.c
index b0c9d6facef9..19228149386c 100644
--- a/init/main.c
+++ b/init/main.c
@@ -625,7 +625,6 @@ asmlinkage __visible void __init start_kernel(void)
numa_policy_init();
if (late_time_init)
late_time_init();
- sched_clock_init();
calibrate_delay();
pidmap_init();
anon_vma_init();
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 9b349619f431..8464a5cbab97 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -783,6 +783,20 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
}
EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
+void __sched
+mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
+{
+ int token;
+
+ might_sleep();
+
+ token = io_schedule_prepare();
+ __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
+ subclass, NULL, _RET_IP_, NULL, 0);
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io_nested);
+
static inline int
ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
{
@@ -950,6 +964,16 @@ int __sched mutex_lock_killable(struct mutex *lock)
}
EXPORT_SYMBOL(mutex_lock_killable);
+void __sched mutex_lock_io(struct mutex *lock)
+{
+ int token;
+
+ token = io_schedule_prepare();
+ mutex_lock(lock);
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io);
+
static noinline void __sched
__mutex_lock_slowpath(struct mutex *lock)
{
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e85a725e5c34..ad64efe41722 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -77,41 +77,88 @@ EXPORT_SYMBOL_GPL(sched_clock);
__read_mostly int sched_clock_running;
+void sched_clock_init(void)
+{
+ sched_clock_running = 1;
+}
+
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
-static int __sched_clock_stable_early;
+/*
+ * We must start with !__sched_clock_stable because the unstable -> stable
+ * transition is accurate, while the stable -> unstable transition is not.
+ *
+ * Similarly we start with __sched_clock_stable_early, thereby assuming we
+ * will become stable, such that there's only a single 1 -> 0 transition.
+ */
+static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
+static int __sched_clock_stable_early = 1;
-int sched_clock_stable(void)
+/*
+ * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ */
+static __read_mostly u64 raw_offset;
+static __read_mostly u64 gtod_offset;
+
+struct sched_clock_data {
+ u64 tick_raw;
+ u64 tick_gtod;
+ u64 clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
{
- return static_key_false(&__sched_clock_stable);
+ return this_cpu_ptr(&sched_clock_data);
}
-static void __set_sched_clock_stable(void)
+static inline struct sched_clock_data *cpu_sdc(int cpu)
{
- if (!sched_clock_stable())
- static_key_slow_inc(&__sched_clock_stable);
+ return &per_cpu(sched_clock_data, cpu);
+}
- tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
+int sched_clock_stable(void)
+{
+ return static_branch_likely(&__sched_clock_stable);
}
-void set_sched_clock_stable(void)
+static void __set_sched_clock_stable(void)
{
- __sched_clock_stable_early = 1;
+ struct sched_clock_data *scd = this_scd();
- smp_mb(); /* matches sched_clock_init() */
+ /*
+ * Attempt to make the (initial) unstable->stable transition continuous.
+ */
+ raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
- if (!sched_clock_running)
- return;
+ printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
+ scd->tick_gtod, gtod_offset,
+ scd->tick_raw, raw_offset);
- __set_sched_clock_stable();
+ static_branch_enable(&__sched_clock_stable);
+ tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
}
static void __clear_sched_clock_stable(struct work_struct *work)
{
- /* XXX worry about clock continuity */
- if (sched_clock_stable())
- static_key_slow_dec(&__sched_clock_stable);
+ struct sched_clock_data *scd = this_scd();
+
+ /*
+ * Attempt to make the stable->unstable transition continuous.
+ *
+ * Trouble is, this is typically called from the TSC watchdog
+ * timer, which is late per definition. This means the tick
+ * values can already be screwy.
+ *
+ * Still do what we can.
+ */
+ gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+
+ printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+ scd->tick_gtod, gtod_offset,
+ scd->tick_raw, raw_offset);
+ static_branch_disable(&__sched_clock_stable);
tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
}
@@ -121,47 +168,15 @@ void clear_sched_clock_stable(void)
{
__sched_clock_stable_early = 0;
- smp_mb(); /* matches sched_clock_init() */
-
- if (!sched_clock_running)
- return;
+ smp_mb(); /* matches sched_clock_init_late() */
- schedule_work(&sched_clock_work);
+ if (sched_clock_running == 2)
+ schedule_work(&sched_clock_work);
}
-struct sched_clock_data {
- u64 tick_raw;
- u64 tick_gtod;
- u64 clock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
-
-static inline struct sched_clock_data *this_scd(void)
+void sched_clock_init_late(void)
{
- return this_cpu_ptr(&sched_clock_data);
-}
-
-static inline struct sched_clock_data *cpu_sdc(int cpu)
-{
- return &per_cpu(sched_clock_data, cpu);
-}
-
-void sched_clock_init(void)
-{
- u64 ktime_now = ktime_to_ns(ktime_get());
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct sched_clock_data *scd = cpu_sdc(cpu);
-
- scd->tick_raw = 0;
- scd->tick_gtod = ktime_now;
- scd->clock = ktime_now;
- }
-
- sched_clock_running = 1;
-
+ sched_clock_running = 2;
/*
* Ensure that it is impossible to not do a static_key update.
*
@@ -173,8 +188,6 @@ void sched_clock_init(void)
if (__sched_clock_stable_early)
__set_sched_clock_stable();
- else
- __clear_sched_clock_stable(NULL);
}
/*
@@ -216,7 +229,7 @@ again:
* scd->tick_gtod + TICK_NSEC);
*/
- clock = scd->tick_gtod + delta;
+ clock = scd->tick_gtod + gtod_offset + delta;
min_clock = wrap_max(scd->tick_gtod, old_clock);
max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
@@ -302,7 +315,7 @@ u64 sched_clock_cpu(int cpu)
u64 clock;
if (sched_clock_stable())
- return sched_clock();
+ return sched_clock() + raw_offset;
if (unlikely(!sched_clock_running))
return 0ull;
@@ -323,23 +336,22 @@ EXPORT_SYMBOL_GPL(sched_clock_cpu);
void sched_clock_tick(void)
{
struct sched_clock_data *scd;
- u64 now, now_gtod;
-
- if (sched_clock_stable())
- return;
-
- if (unlikely(!sched_clock_running))
- return;
WARN_ON_ONCE(!irqs_disabled());
+ /*
+ * Update these values even if sched_clock_stable(), because it can
+ * become unstable at any point in time at which point we need some
+ * values to fall back on.
+ *
+ * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+ */
scd = this_scd();
- now_gtod = ktime_to_ns(ktime_get());
- now = sched_clock();
+ scd->tick_raw = sched_clock();
+ scd->tick_gtod = ktime_get_ns();
- scd->tick_raw = now;
- scd->tick_gtod = now_gtod;
- sched_clock_local(scd);
+ if (!sched_clock_stable() && likely(sched_clock_running))
+ sched_clock_local(scd);
}
/*
@@ -366,11 +378,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-void sched_clock_init(void)
-{
- sched_clock_running = 1;
-}
-
u64 sched_clock_cpu(int cpu)
{
if (unlikely(!sched_clock_running))
@@ -378,6 +385,7 @@ u64 sched_clock_cpu(int cpu)
return sched_clock();
}
+
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
/*
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 8d0f35debf35..f063a25d4449 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -31,7 +31,8 @@ void complete(struct completion *x)
unsigned long flags;
spin_lock_irqsave(&x->wait.lock, flags);
- x->done++;
+ if (x->done != UINT_MAX)
+ x->done++;
__wake_up_locked(&x->wait, TASK_NORMAL, 1);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
@@ -51,7 +52,7 @@ void complete_all(struct completion *x)
unsigned long flags;
spin_lock_irqsave(&x->wait.lock, flags);
- x->done += UINT_MAX/2;
+ x->done = UINT_MAX;
__wake_up_locked(&x->wait, TASK_NORMAL, 0);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
@@ -79,7 +80,8 @@ do_wait_for_common(struct completion *x,
if (!x->done)
return timeout;
}
- x->done--;
+ if (x->done != UINT_MAX)
+ x->done--;
return timeout ?: 1;
}
@@ -280,7 +282,7 @@ bool try_wait_for_completion(struct completion *x)
spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = 0;
- else
+ else if (x->done != UINT_MAX)
x->done--;
spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c56fb57f2991..d01f9d047397 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -102,9 +102,12 @@ void update_rq_clock(struct rq *rq)
lockdep_assert_held(&rq->lock);
- if (rq->clock_skip_update & RQCF_ACT_SKIP)
+ if (rq->clock_update_flags & RQCF_ACT_SKIP)
return;
+#ifdef CONFIG_SCHED_DEBUG
+ rq->clock_update_flags |= RQCF_UPDATED;
+#endif
delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
if (delta < 0)
return;
@@ -185,7 +188,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
rq = task_rq(p);
raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
@@ -225,7 +228,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
* pair with the WMB to ensure we must then also see migrating.
*/
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
- rf->cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
return rq;
}
raw_spin_unlock(&rq->lock);
@@ -1195,9 +1198,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
* OK, since we're going to drop the lock immediately
* afterwards anyway.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
rq = move_queued_task(rq, p, dest_cpu);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
out:
task_rq_unlock(rq, p, &rf);
@@ -1690,7 +1693,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
* Mark the task runnable and perform wakeup-preemption.
*/
static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
- struct pin_cookie cookie)
+ struct rq_flags *rf)
{
check_preempt_curr(rq, p, wake_flags);
p->state = TASK_RUNNING;
@@ -1702,9 +1705,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
* Our task @p is fully woken up and running; so its safe to
* drop the rq->lock, hereafter rq is only used for statistics.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
p->sched_class->task_woken(rq, p);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
}
if (rq->idle_stamp) {
@@ -1723,7 +1726,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
static void
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
- struct pin_cookie cookie)
+ struct rq_flags *rf)
{
int en_flags = ENQUEUE_WAKEUP;
@@ -1738,7 +1741,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
#endif
ttwu_activate(rq, p, en_flags);
- ttwu_do_wakeup(rq, p, wake_flags, cookie);
+ ttwu_do_wakeup(rq, p, wake_flags, rf);
}
/*
@@ -1757,7 +1760,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
if (task_on_rq_queued(p)) {
/* check_preempt_curr() may use rq clock */
update_rq_clock(rq);
- ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
+ ttwu_do_wakeup(rq, p, wake_flags, &rf);
ret = 1;
}
__task_rq_unlock(rq, &rf);
@@ -1770,15 +1773,15 @@ void sched_ttwu_pending(void)
{
struct rq *rq = this_rq();
struct llist_node *llist = llist_del_all(&rq->wake_list);
- struct pin_cookie cookie;
struct task_struct *p;
unsigned long flags;
+ struct rq_flags rf;
if (!llist)
return;
raw_spin_lock_irqsave(&rq->lock, flags);
- cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, &rf);
while (llist) {
int wake_flags = 0;
@@ -1789,10 +1792,10 @@ void sched_ttwu_pending(void)
if (p->sched_remote_wakeup)
wake_flags = WF_MIGRATED;
- ttwu_do_activate(rq, p, wake_flags, cookie);
+ ttwu_do_activate(rq, p, wake_flags, &rf);
}
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -1881,7 +1884,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
- struct pin_cookie cookie;
+ struct rq_flags rf;
#if defined(CONFIG_SMP)
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
@@ -1892,9 +1895,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
#endif
raw_spin_lock(&rq->lock);
- cookie = lockdep_pin_lock(&rq->lock);
- ttwu_do_activate(rq, p, wake_flags, cookie);
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_pin_lock(rq, &rf);
+ ttwu_do_activate(rq, p, wake_flags, &rf);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock(&rq->lock);
}
@@ -2086,11 +2089,24 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
p->sched_contributes_to_load = !!task_contributes_to_load(p);
p->state = TASK_WAKING;
+ if (p->in_iowait) {
+ delayacct_blkio_end();
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
set_task_cpu(p, cpu);
}
+
+#else /* CONFIG_SMP */
+
+ if (p->in_iowait) {
+ delayacct_blkio_end();
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu, wake_flags);
@@ -2111,7 +2127,7 @@ out:
* ensure that this_rq() is locked, @p is bound to this_rq() and not
* the current task.
*/
-static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie)
+static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
{
struct rq *rq = task_rq(p);
@@ -2128,11 +2144,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
* disabled avoiding further scheduler activity on it and we've
* not yet picked a replacement task.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
raw_spin_lock(&p->pi_lock);
raw_spin_lock(&rq->lock);
- lockdep_repin_lock(&rq->lock, cookie);
+ rq_repin_lock(rq, rf);
}
if (!(p->state & TASK_NORMAL))
@@ -2140,10 +2156,15 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
trace_sched_waking(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ if (p->in_iowait) {
+ delayacct_blkio_end();
+ atomic_dec(&rq->nr_iowait);
+ }
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ }
- ttwu_do_wakeup(rq, p, 0, cookie);
+ ttwu_do_wakeup(rq, p, 0, rf);
ttwu_stat(p, smp_processor_id(), 0);
out:
raw_spin_unlock(&p->pi_lock);
@@ -2578,6 +2599,7 @@ void wake_up_new_task(struct task_struct *p)
__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
rq = __task_rq_lock(p, &rf);
+ update_rq_clock(rq);
post_init_entity_util_avg(&p->se);
activate_task(rq, p, 0);
@@ -2590,9 +2612,9 @@ void wake_up_new_task(struct task_struct *p)
* Nothing relies on rq->lock after this, so its fine to
* drop it.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
p->sched_class->task_woken(rq, p);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
#endif
task_rq_unlock(rq, p, &rf);
@@ -2861,7 +2883,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
*/
static __always_inline struct rq *
context_switch(struct rq *rq, struct task_struct *prev,
- struct task_struct *next, struct pin_cookie cookie)
+ struct task_struct *next, struct rq_flags *rf)
{
struct mm_struct *mm, *oldmm;
@@ -2887,13 +2909,16 @@ context_switch(struct rq *rq, struct task_struct *prev,
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
+
+ rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+
/*
* Since the runqueue lock will be released by the next
* task (which is an invalid locking op but in the case
* of the scheduler it's an obvious special-case), so we
* do an early lockdep release here:
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
/* Here we just switch the register state and the stack. */
@@ -2949,6 +2974,36 @@ unsigned long long nr_context_switches(void)
return sum;
}
+/*
+ * IO-wait accounting, and how its mostly bollocks (on SMP).
+ *
+ * The idea behind IO-wait account is to account the idle time that we could
+ * have spend running if it were not for IO. That is, if we were to improve the
+ * storage performance, we'd have a proportional reduction in IO-wait time.
+ *
+ * This all works nicely on UP, where, when a task blocks on IO, we account
+ * idle time as IO-wait, because if the storage were faster, it could've been
+ * running and we'd not be idle.
+ *
+ * This has been extended to SMP, by doing the same for each CPU. This however
+ * is broken.
+ *
+ * Imagine for instance the case where two tasks block on one CPU, only the one
+ * CPU will have IO-wait accounted, while the other has regular idle. Even
+ * though, if the storage were faster, both could've ran at the same time,
+ * utilising both CPUs.
+ *
+ * This means, that when looking globally, the current IO-wait accounting on
+ * SMP is a lower bound, by reason of under accounting.
+ *
+ * Worse, since the numbers are provided per CPU, they are sometimes
+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
+ * associated with any one particular CPU, it can wake to another CPU than it
+ * blocked on. This means the per CPU IO-wait number is meaningless.
+ *
+ * Task CPU affinities can make all that even more 'interesting'.
+ */
+
unsigned long nr_iowait(void)
{
unsigned long i, sum = 0;
@@ -2959,6 +3014,13 @@ unsigned long nr_iowait(void)
return sum;
}
+/*
+ * Consumers of these two interfaces, like for example the cpufreq menu
+ * governor are using nonsensical data. Boosting frequency for a CPU that has
+ * IO-wait which might not even end up running the task when it does become
+ * runnable.
+ */
+
unsigned long nr_iowait_cpu(int cpu)
{
struct rq *this = cpu_rq(cpu);
@@ -3257,31 +3319,30 @@ static inline void schedule_debug(struct task_struct *prev)
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
- const struct sched_class *class = &fair_sched_class;
+ const struct sched_class *class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in
* the fair class we can call that function directly:
*/
- if (likely(prev->sched_class == class &&
- rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq, prev, cookie);
+ if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+ p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto again;
/* assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
- p = idle_sched_class.pick_next_task(rq, prev, cookie);
+ p = idle_sched_class.pick_next_task(rq, prev, rf);
return p;
}
again:
for_each_class(class) {
- p = class->pick_next_task(rq, prev, cookie);
+ p = class->pick_next_task(rq, prev, rf);
if (p) {
if (unlikely(p == RETRY_TASK))
goto again;
@@ -3335,7 +3396,7 @@ static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
- struct pin_cookie cookie;
+ struct rq_flags rf;
struct rq *rq;
int cpu;
@@ -3358,9 +3419,9 @@ static void __sched notrace __schedule(bool preempt)
*/
smp_mb__before_spinlock();
raw_spin_lock(&rq->lock);
- cookie = lockdep_pin_lock(&rq->lock);
+ rq_pin_lock(rq, &rf);
- rq->clock_skip_update <<= 1; /* promote REQ to ACT */
+ rq->clock_update_flags <<= 1; /* promote REQ to ACT */
switch_count = &prev->nivcsw;
if (!preempt && prev->state) {
@@ -3370,6 +3431,11 @@ static void __sched notrace __schedule(bool preempt)
deactivate_task(rq, prev, DEQUEUE_SLEEP);
prev->on_rq = 0;
+ if (prev->in_iowait) {
+ atomic_inc(&rq->nr_iowait);
+ delayacct_blkio_start();
+ }
+
/*
* If a worker went to sleep, notify and ask workqueue
* whether it wants to wake up a task to maintain
@@ -3380,7 +3446,7 @@ static void __sched notrace __schedule(bool preempt)
to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
- try_to_wake_up_local(to_wakeup, cookie);
+ try_to_wake_up_local(to_wakeup, &rf);
}
}
switch_count = &prev->nvcsw;
@@ -3389,10 +3455,9 @@ static void __sched notrace __schedule(bool preempt)
if (task_on_rq_queued(prev))
update_rq_clock(rq);
- next = pick_next_task(rq, prev, cookie);
+ next = pick_next_task(rq, prev, &rf);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
- rq->clock_skip_update = 0;
if (likely(prev != next)) {
rq->nr_switches++;
@@ -3400,9 +3465,10 @@ static void __sched notrace __schedule(bool preempt)
++*switch_count;
trace_sched_switch(preempt, prev, next);
- rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */
+ rq = context_switch(rq, prev, next, &rf); /* unlocks the rq */
} else {
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock_irq(&rq->lock);
}
@@ -3651,6 +3717,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p, &rf);
+ update_rq_clock(rq);
/*
* Idle task boosting is a nono in general. There is one
@@ -3747,6 +3814,8 @@ void set_user_nice(struct task_struct *p, long nice)
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
+
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
@@ -4179,6 +4248,7 @@ recheck:
* runqueue lock must be held.
*/
rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
/*
* Changing the policy of the stop threads its a very bad idea
@@ -5057,31 +5127,48 @@ out_irq:
}
EXPORT_SYMBOL_GPL(yield_to);
+int io_schedule_prepare(void)
+{
+ int old_iowait = current->in_iowait;
+
+ current->in_iowait = 1;
+ blk_schedule_flush_plug(current);
+
+ return old_iowait;
+}
+
+void io_schedule_finish(int token)
+{
+ current->in_iowait = token;
+}
+
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*/
long __sched io_schedule_timeout(long timeout)
{
- int old_iowait = current->in_iowait;
- struct rq *rq;
+ int token;
long ret;
- current->in_iowait = 1;
- blk_schedule_flush_plug(current);
-
- delayacct_blkio_start();
- rq = raw_rq();
- atomic_inc(&rq->nr_iowait);
+ token = io_schedule_prepare();
ret = schedule_timeout(timeout);
- current->in_iowait = old_iowait;
- atomic_dec(&rq->nr_iowait);
- delayacct_blkio_end();
+ io_schedule_finish(token);
return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);
+void io_schedule(void)
+{
+ int token;
+
+ token = io_schedule_prepare();
+ schedule();
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL(io_schedule);
+
/**
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
@@ -5521,7 +5608,7 @@ static void migrate_tasks(struct rq *dead_rq)
{
struct rq *rq = dead_rq;
struct task_struct *next, *stop = rq->stop;
- struct pin_cookie cookie;
+ struct rq_flags rf, old_rf;
int dest_cpu;
/*
@@ -5553,8 +5640,8 @@ static void migrate_tasks(struct rq *dead_rq)
/*
* pick_next_task assumes pinned rq->lock.
*/
- cookie = lockdep_pin_lock(&rq->lock);
- next = pick_next_task(rq, &fake_task, cookie);
+ rq_pin_lock(rq, &rf);
+ next = pick_next_task(rq, &fake_task, &rf);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
@@ -5567,7 +5654,7 @@ static void migrate_tasks(struct rq *dead_rq)
* because !cpu_active at this point, which means load-balance
* will not interfere. Also, stop-machine.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, &rf);
raw_spin_unlock(&rq->lock);
raw_spin_lock(&next->pi_lock);
raw_spin_lock(&rq->lock);
@@ -5582,6 +5669,13 @@ static void migrate_tasks(struct rq *dead_rq)
continue;
}
+ /*
+ * __migrate_task() may return with a different
+ * rq->lock held and a new cookie in 'rf', but we need
+ * to preserve rf::clock_update_flags for 'dead_rq'.
+ */
+ old_rf = rf;
+
/* Find suitable destination for @next, with force if needed. */
dest_cpu = select_fallback_rq(dead_rq->cpu, next);
@@ -5590,6 +5684,7 @@ static void migrate_tasks(struct rq *dead_rq)
raw_spin_unlock(&rq->lock);
rq = dead_rq;
raw_spin_lock(&rq->lock);
+ rf = old_rf;
}
raw_spin_unlock(&next->pi_lock);
}
@@ -5881,12 +5976,14 @@ static int init_rootdomain(struct root_domain *rd)
init_dl_bw(&rd->dl_bw);
if (cpudl_init(&rd->cpudl) != 0)
- goto free_dlo_mask;
+ goto free_rto_mask;
if (cpupri_init(&rd->cpupri) != 0)
- goto free_rto_mask;
+ goto free_cpudl;
return 0;
+free_cpudl:
+ cpudl_cleanup(&rd->cpudl);
free_rto_mask:
free_cpumask_var(rd->rto_mask);
free_dlo_mask:
@@ -7487,6 +7584,7 @@ void __init sched_init_smp(void)
init_sched_dl_class();
sched_init_smt();
+ sched_clock_init_late();
sched_smp_initialized = true;
}
@@ -7502,6 +7600,7 @@ early_initcall(migration_init);
void __init sched_init_smp(void)
{
sched_init_granularity();
+ sched_clock_init_late();
}
#endif /* CONFIG_SMP */
@@ -7545,6 +7644,8 @@ void __init sched_init(void)
int i, j;
unsigned long alloc_size = 0, ptr;
+ sched_clock_init();
+
for (i = 0; i < WAIT_TABLE_SIZE; i++)
init_waitqueue_head(bit_wait_table + i);
@@ -7983,6 +8084,7 @@ void sched_move_task(struct task_struct *tsk)
struct rq *rq;
rq = task_rq_lock(tsk, &rf);
+ update_rq_clock(rq);
running = task_current(rq, tsk);
queued = task_on_rq_queued(tsk);
@@ -8431,6 +8533,7 @@ static void cpu_cgroup_fork(struct task_struct *task)
rq = task_rq_lock(task, &rf);
+ update_rq_clock(rq);
sched_change_group(task, TASK_SET_GROUP);
task_rq_unlock(rq, task, &rf);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7700a9cba335..f7c14cc71d06 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -151,7 +151,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in virtual machine since the last update
*/
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+void account_guest_time(struct task_struct *p, cputime_t cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
@@ -176,8 +176,8 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
* @cputime: the cpu time spent in kernel space since the last update
* @index: pointer to cpustat field that has to be updated
*/
-static inline
-void __account_system_time(struct task_struct *p, cputime_t cputime, int index)
+void account_system_index_time(struct task_struct *p,
+ cputime_t cputime, enum cpu_usage_stat index)
{
/* Add system time to process. */
p->stime += cputime;
@@ -213,7 +213,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
else
index = CPUTIME_SYSTEM;
- __account_system_time(p, cputime, index);
+ account_system_index_time(p, cputime, index);
}
/*
@@ -400,7 +400,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
* So, we have to handle it separately here.
* Also, p->stime needs to be updated for ksoftirqd.
*/
- __account_system_time(p, cputime, CPUTIME_SOFTIRQ);
+ account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
} else if (user_tick) {
account_user_time(p, cputime);
} else if (p == rq->idle) {
@@ -408,7 +408,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
} else if (p->flags & PF_VCPU) { /* System time or guest time */
account_guest_time(p, cputime);
} else {
- __account_system_time(p, cputime, CPUTIME_SYSTEM);
+ account_system_index_time(p, cputime, CPUTIME_SYSTEM);
}
}
@@ -437,9 +437,7 @@ void vtime_common_task_switch(struct task_struct *prev)
else
vtime_account_system(prev);
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
- vtime_account_user(prev);
-#endif
+ vtime_flush(prev);
arch_vtime_task_switch(prev);
}
#endif
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 70ef2b1901e4..27737f34757d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -663,9 +663,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
* Nothing relies on rq->lock after this, so its safe to drop
* rq->lock.
*/
- lockdep_unpin_lock(&rq->lock, rf.cookie);
+ rq_unpin_lock(rq, &rf);
push_dl_task(rq);
- lockdep_repin_lock(&rq->lock, rf.cookie);
+ rq_repin_lock(rq, &rf);
}
#endif
@@ -1118,7 +1118,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
}
struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct sched_dl_entity *dl_se;
struct task_struct *p;
@@ -1133,9 +1133,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie coo
* disabled avoiding further scheduler activity on it and we're
* being very careful to re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
pull_dl_task(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ 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
@@ -1729,12 +1729,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
#ifdef CONFIG_SMP
if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded)
queue_push_tasks(rq);
-#else
+#endif
if (dl_task(rq->curr))
check_preempt_curr_dl(rq, p, 0);
else
resched_curr(rq);
-#endif
}
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fa178b62ea79..109adc0e9cb9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -953,6 +953,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
#endif
P(policy);
P(prio);
+ if (p->policy == SCHED_DEADLINE) {
+ P(dl.runtime);
+ P(dl.deadline);
+ }
#undef PN_SCHEDSTAT
#undef PN
#undef __PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6559d197e08a..274c747a01ce 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2657,6 +2657,18 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
if (tg_weight)
shares /= tg_weight;
+ /*
+ * MIN_SHARES has to be unscaled here to support per-CPU partitioning
+ * of a group with small tg->shares value. It is a floor value which is
+ * assigned as a minimum load.weight to the sched_entity representing
+ * the group on a CPU.
+ *
+ * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024
+ * on an 8-core system with 8 tasks each runnable on one CPU shares has
+ * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In
+ * case no task is runnable on a CPU MIN_SHARES=2 should be returned
+ * instead of 0.
+ */
if (shares < MIN_SHARES)
shares = MIN_SHARES;
if (shares > tg->shares)
@@ -2689,16 +2701,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct sched_entity *se)
{
+ struct cfs_rq *cfs_rq = group_cfs_rq(se);
struct task_group *tg;
- struct sched_entity *se;
long shares;
- tg = cfs_rq->tg;
- se = tg->se[cpu_of(rq_of(cfs_rq))];
- if (!se || throttled_hierarchy(cfs_rq))
+ if (!cfs_rq)
+ return;
+
+ if (throttled_hierarchy(cfs_rq))
return;
+
+ tg = cfs_rq->tg;
+
#ifndef CONFIG_SMP
if (likely(se->load.weight == tg->shares))
return;
@@ -2707,8 +2723,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
reweight_entity(cfs_rq_of(se), se, shares);
}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct sched_entity *se)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -3424,7 +3441,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
return cfs_rq->avg.load_avg;
}
-static int idle_balance(struct rq *this_rq);
+static int idle_balance(struct rq *this_rq, struct rq_flags *rf);
#else /* CONFIG_SMP */
@@ -3453,7 +3470,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
-static inline int idle_balance(struct rq *rq)
+static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
{
return 0;
}
@@ -3582,10 +3599,18 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (renorm && !curr)
se->vruntime += cfs_rq->min_vruntime;
+ /*
+ * When enqueuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Add its load to cfs_rq->runnable_avg
+ * - For group_entity, update its weight to reflect the new share of
+ * its group cfs_rq
+ * - Add its new weight to cfs_rq->load.weight
+ */
update_load_avg(se, UPDATE_TG);
enqueue_entity_load_avg(cfs_rq, se);
+ update_cfs_shares(se);
account_entity_enqueue(cfs_rq, se);
- update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP)
place_entity(cfs_rq, se, 0);
@@ -3657,6 +3682,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+
+ /*
+ * When dequeuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Substract its load from the cfs_rq->runnable_avg.
+ * - Substract its previous weight from cfs_rq->load.weight.
+ * - For group entity, update its weight to reflect the new share
+ * of its group cfs_rq.
+ */
update_load_avg(se, UPDATE_TG);
dequeue_entity_load_avg(cfs_rq, se);
@@ -3681,7 +3715,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
/* return excess runtime on last dequeue */
return_cfs_rq_runtime(cfs_rq);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
/*
* Now advance min_vruntime if @se was the entity holding it back,
@@ -3864,7 +3898,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
* Ensure that runnable average is periodically updated.
*/
update_load_avg(curr, UPDATE_TG);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(curr);
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -4761,7 +4795,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
break;
update_load_avg(se, UPDATE_TG);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
}
if (!se)
@@ -4820,7 +4854,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
break;
update_load_avg(se, UPDATE_TG);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
}
if (!se)
@@ -6213,7 +6247,7 @@ preempt:
}
static struct task_struct *
-pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
@@ -6320,15 +6354,8 @@ simple:
return p;
idle:
- /*
- * 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.
- */
- lockdep_unpin_lock(&rq->lock, cookie);
- new_tasks = idle_balance(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ new_tasks = idle_balance(rq, rf);
+
/*
* Because idle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
@@ -8077,6 +8104,7 @@ redo:
more_balance:
raw_spin_lock_irqsave(&busiest->lock, flags);
+ update_rq_clock(busiest);
/*
* cur_ld_moved - load moved in current iteration
@@ -8297,7 +8325,7 @@ update_next_balance(struct sched_domain *sd, unsigned long *next_balance)
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
-static int idle_balance(struct rq *this_rq)
+static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
{
unsigned long next_balance = jiffies + HZ;
int this_cpu = this_rq->cpu;
@@ -8311,6 +8339,14 @@ static int idle_balance(struct rq *this_rq)
*/
this_rq->idle_stamp = rq_clock(this_rq);
+ /*
+ * 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(this_rq, rf);
+
if (this_rq->avg_idle < sysctl_sched_migration_cost ||
!this_rq->rd->overload) {
rcu_read_lock();
@@ -8388,6 +8424,8 @@ out:
if (pulled_task)
this_rq->idle_stamp = 0;
+ rq_repin_lock(this_rq, rf);
+
return pulled_task;
}
@@ -8443,6 +8481,7 @@ static int active_load_balance_cpu_stop(void *data)
};
schedstat_inc(sd->alb_count);
+ update_rq_clock(busiest_rq);
p = detach_one_task(&env);
if (p) {
@@ -9264,6 +9303,7 @@ void online_fair_sched_group(struct task_group *tg)
se = tg->se[i];
raw_spin_lock_irq(&rq->lock);
+ update_rq_clock(rq);
attach_entity_cfs_rq(se);
sync_throttle(tg, i);
raw_spin_unlock_irq(&rq->lock);
@@ -9356,8 +9396,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
/* Possible calls to update_curr() need rq clock */
update_rq_clock(rq);
- for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se));
+ for_each_sched_entity(se) {
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
+ }
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 5405d3feb112..0c00172db63e 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -24,7 +24,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
}
static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
put_prev_task(rq, prev);
update_idle_core(rq);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2516b8df6dbb..704f2b89abf1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1523,7 +1523,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
}
static struct task_struct *
-pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
@@ -1535,9 +1535,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie coo
* disabled avoiding further scheduler activity on it and we're
* being very careful to re-start the picking loop.
*/
- lockdep_unpin_lock(&rq->lock, cookie);
+ rq_unpin_lock(rq, rf);
pull_rt_task(rq);
- lockdep_repin_lock(&rq->lock, cookie);
+ 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
@@ -2198,10 +2198,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
#ifdef CONFIG_SMP
if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded)
queue_push_tasks(rq);
-#else
+#endif /* CONFIG_SMP */
if (p->prio < rq->curr->prio)
resched_curr(rq);
-#endif /* CONFIG_SMP */
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b34c7826ca5..6eeae7ebd99b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -644,7 +644,7 @@ struct rq {
unsigned long next_balance;
struct mm_struct *prev_mm;
- unsigned int clock_skip_update;
+ unsigned int clock_update_flags;
u64 clock;
u64 clock_task;
@@ -768,28 +768,110 @@ static inline u64 __rq_clock_broken(struct rq *rq)
return READ_ONCE(rq->clock);
}
+/*
+ * rq::clock_update_flags bits
+ *
+ * %RQCF_REQ_SKIP - will request skipping of clock update on the next
+ * call to __schedule(). This is an optimisation to avoid
+ * neighbouring rq clock updates.
+ *
+ * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is
+ * in effect and calls to update_rq_clock() are being ignored.
+ *
+ * %RQCF_UPDATED - is a debug flag that indicates whether a call has been
+ * made to update_rq_clock() since the last time rq::lock was pinned.
+ *
+ * If inside of __schedule(), clock_update_flags will have been
+ * shifted left (a left shift is a cheap operation for the fast path
+ * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use,
+ *
+ * if (rq-clock_update_flags >= RQCF_UPDATED)
+ *
+ * to check if %RQCF_UPADTED is set. It'll never be shifted more than
+ * one position though, because the next rq_unpin_lock() will shift it
+ * back.
+ */
+#define RQCF_REQ_SKIP 0x01
+#define RQCF_ACT_SKIP 0x02
+#define RQCF_UPDATED 0x04
+
+static inline void assert_clock_updated(struct rq *rq)
+{
+ /*
+ * The only reason for not seeing a clock update since the
+ * last rq_pin_lock() is if we're currently skipping updates.
+ */
+ SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP);
+}
+
static inline u64 rq_clock(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
+ assert_clock_updated(rq);
+
return rq->clock;
}
static inline u64 rq_clock_task(struct rq *rq)
{
lockdep_assert_held(&rq->lock);
+ assert_clock_updated(rq);
+
return rq->clock_task;
}
-#define RQCF_REQ_SKIP 0x01
-#define RQCF_ACT_SKIP 0x02
-
static inline void rq_clock_skip_update(struct rq *rq, bool skip)
{
lockdep_assert_held(&rq->lock);
if (skip)
- rq->clock_skip_update |= RQCF_REQ_SKIP;
+ rq->clock_update_flags |= RQCF_REQ_SKIP;
else
- rq->clock_skip_update &= ~RQCF_REQ_SKIP;
+ rq->clock_update_flags &= ~RQCF_REQ_SKIP;
+}
+
+struct rq_flags {
+ unsigned long flags;
+ struct pin_cookie cookie;
+#ifdef CONFIG_SCHED_DEBUG
+ /*
+ * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the
+ * current pin context is stashed here in case it needs to be
+ * restored in rq_repin_lock().
+ */
+ unsigned int clock_update_flags;
+#endif
+};
+
+static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ rf->cookie = lockdep_pin_lock(&rq->lock);
+
+#ifdef CONFIG_SCHED_DEBUG
+ rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+ rf->clock_update_flags = 0;
+#endif
+}
+
+static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ if (rq->clock_update_flags > RQCF_ACT_SKIP)
+ rf->clock_update_flags = RQCF_UPDATED;
+#endif
+
+ lockdep_unpin_lock(&rq->lock, rf->cookie);
+}
+
+static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
+{
+ lockdep_repin_lock(&rq->lock, rf->cookie);
+
+#ifdef CONFIG_SCHED_DEBUG
+ /*
+ * Restore the value we stashed in @rf for this pin context.
+ */
+ rq->clock_update_flags |= rf->clock_update_flags;
+#endif
}
#ifdef CONFIG_NUMA
@@ -1245,7 +1327,7 @@ struct sched_class {
*/
struct task_struct * (*pick_next_task) (struct rq *rq,
struct task_struct *prev,
- struct pin_cookie cookie);
+ struct rq_flags *rf);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
@@ -1501,11 +1583,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
static inline void sched_avg_update(struct rq *rq) { }
#endif
-struct rq_flags {
- unsigned long flags;
- struct pin_cookie cookie;
-};
-
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(rq->lock);
struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -1515,7 +1592,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
__releases(rq->lock)
{
- lockdep_unpin_lock(&rq->lock, rf->cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
}
@@ -1524,7 +1601,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
__releases(rq->lock)
__releases(p->pi_lock)
{
- lockdep_unpin_lock(&rq->lock, rf->cookie);
+ rq_unpin_lock(rq, rf);
raw_spin_unlock(&rq->lock);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 604297a08b3a..9f69fb630853 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -24,7 +24,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
}
static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *stop = rq->stop;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 665985b0a89a..93621ae718d3 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -141,6 +141,10 @@ static void __clocksource_unstable(struct clocksource *cs)
{
cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
cs->flags |= CLOCK_SOURCE_UNSTABLE;
+
+ if (cs->mark_unstable)
+ cs->mark_unstable(cs);
+
if (finished_booting)
schedule_work(&watchdog_work);
}