Merge branches 'bigrt.2012.09.20b', 'doctorture.2012.09.18a', 'fixes.2012.09.20a', 'hotplug.2012.09.17a' and 'idle.2012.09.18b' into HEAD
bigrt.2012.09.17c contains additional commits to reduce scheduling
latency from RCU on huge systems (many hundrends or thousands
of CPUs).
doctorture.2012.09.18a contains documentation changes and rcutorture fixes.
fixes.2012.09.17a contains miscellaneous fixes.
hotplug.2012.09.17a contains CPU-hotplug-related changes.
idle.2012.09.18b contains additional RCU changes in support of Frederic's
adaptive dynticks and also fixes architectures for which RCU no
longer considered the idle loop to be a quiescent state due to
earlier adaptive-dynticks changes. Affected architectures are
alpha, cris, frv, h8300, m32r, m68k, mn10300, parisc, score,
xtensa, and ia64.
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index fc103d7..cdb20d4 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -310,6 +310,12 @@
code under the influence of preempt_disable(), you instead
need to use synchronize_irq() or synchronize_sched().
+ This same limitation also applies to synchronize_rcu_bh()
+ and synchronize_srcu(), as well as to the asynchronous and
+ expedited forms of the three primitives, namely call_rcu(),
+ call_rcu_bh(), call_srcu(), synchronize_rcu_expedited(),
+ synchronize_rcu_bh_expedited(), and synchronize_srcu_expedited().
+
12. Any lock acquired by an RCU callback must be acquired elsewhere
with softirq disabled, e.g., via spin_lock_irqsave(),
spin_lock_bh(), etc. Failing to disable irq on a given
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 69ee188..bf0f6de 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -873,7 +873,7 @@
and code segments with preemption disabled (whether
via preempt_disable(), local_irq_save(), local_bh_disable(),
or some other mechanism) as if they were explicit RCU readers?
- If so, you need RCU-sched.
+ If so, RCU-sched is the only choice that will work for you.
e. Do you need RCU grace periods to complete even in the face
of softirq monopolization of one or more of the CPUs? For
@@ -884,7 +884,12 @@
RCU, but inappropriate for other synchronization mechanisms?
If so, consider SLAB_DESTROY_BY_RCU. But please be careful!
-g. Otherwise, use RCU.
+g. Do you need read-side critical sections that are respected
+ even though they are in the middle of the idle loop, during
+ user-mode execution, or on an offlined CPU? If so, SRCU is the
+ only choice that will work for you.
+
+h. Otherwise, use RCU.
Of course, this all assumes that you have determined that RCU is in fact
the right tool for your job.
diff --git a/arch/Kconfig b/arch/Kconfig
index 72f2fa1..1401a75 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -281,4 +281,14 @@
See Documentation/prctl/seccomp_filter.txt for details.
+config HAVE_RCU_USER_QS
+ bool
+ help
+ Provide kernel entry/exit hooks necessary for userspace
+ RCU extended quiescent state. Syscalls need to be wrapped inside
+ rcu_user_exit()-rcu_user_enter() through the slow path using
+ TIF_NOHZ flag. Exceptions handlers must be wrapped as well. Irqs
+ are already protected inside rcu_irq_enter/rcu_irq_exit() but
+ preemption or signal handling on irq exit still need to be protected.
+
source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index d6fde98..83638aa 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -28,6 +28,7 @@
#include <linux/tty.h>
#include <linux/console.h>
#include <linux/slab.h>
+#include <linux/rcupdate.h>
#include <asm/reg.h>
#include <asm/uaccess.h>
@@ -54,9 +55,12 @@
/* FIXME -- EV6 and LCA45 know how to power down
the CPU. */
+ rcu_idle_enter();
while (!need_resched())
cpu_relax();
- schedule();
+
+ rcu_idle_exit();
+ schedule_preempt_disabled();
}
}
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 35ddc02..a41ad90 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -166,6 +166,7 @@
DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
cpuid, current, current->active_mm));
+ preempt_disable();
/* Do nothing. */
cpu_idle();
}
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index 66fd017..7f65be6 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -25,6 +25,7 @@
#include <linux/elfcore.h>
#include <linux/mqueue.h>
#include <linux/reboot.h>
+#include <linux/rcupdate.h>
//#define DEBUG
@@ -74,6 +75,7 @@
{
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched()) {
void (*idle)(void);
/*
@@ -86,6 +88,7 @@
idle = default_idle;
idle();
}
+ rcu_idle_exit();
schedule_preempt_disabled();
}
}
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index ff95f50..2eb7fa5 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -25,6 +25,7 @@
#include <linux/reboot.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
+#include <linux/rcupdate.h>
#include <asm/asm-offsets.h>
#include <asm/uaccess.h>
@@ -69,12 +70,14 @@
{
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched()) {
check_pgt_cache();
if (!frv_dma_inprogress && idle)
idle();
}
+ rcu_idle_exit();
schedule_preempt_disabled();
}
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 0e9c315..f153ed1 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -36,6 +36,7 @@
#include <linux/reboot.h>
#include <linux/fs.h>
#include <linux/slab.h>
+#include <linux/rcupdate.h>
#include <asm/uaccess.h>
#include <asm/traps.h>
@@ -78,8 +79,10 @@
void cpu_idle(void)
{
while (1) {
+ rcu_idle_enter();
while (!need_resched())
idle();
+ rcu_idle_exit();
schedule_preempt_disabled();
}
}
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index dd6fc14..3e316ec 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -29,6 +29,7 @@
#include <linux/kdebug.h>
#include <linux/utsname.h>
#include <linux/tracehook.h>
+#include <linux/rcupdate.h>
#include <asm/cpu.h>
#include <asm/delay.h>
@@ -279,6 +280,7 @@
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
if (can_do_pal_halt) {
current_thread_info()->status &= ~TS_POLLING;
/*
@@ -309,6 +311,7 @@
normal_xtp();
#endif
}
+ rcu_idle_exit();
schedule_preempt_disabled();
check_pgt_cache();
if (cpu_is_offline(cpu))
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 3a4a32b..384e63f 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -26,6 +26,7 @@
#include <linux/ptrace.h>
#include <linux/unistd.h>
#include <linux/hardirq.h>
+#include <linux/rcupdate.h>
#include <asm/io.h>
#include <asm/uaccess.h>
@@ -82,6 +83,7 @@
{
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched()) {
void (*idle)(void) = pm_idle;
@@ -90,6 +92,7 @@
idle();
}
+ rcu_idle_exit();
schedule_preempt_disabled();
}
}
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index c488e3c..ac2892e 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -25,6 +25,7 @@
#include <linux/reboot.h>
#include <linux/init_task.h>
#include <linux/mqueue.h>
+#include <linux/rcupdate.h>
#include <asm/uaccess.h>
#include <asm/traps.h>
@@ -75,8 +76,10 @@
{
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched())
idle();
+ rcu_idle_exit();
schedule_preempt_disabled();
}
}
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 7dab0cd..e9cceba 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -25,6 +25,7 @@
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/slab.h>
+#include <linux/rcupdate.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/io.h>
@@ -107,6 +108,7 @@
{
/* endless idle loop with no priority at all */
for (;;) {
+ rcu_idle_enter();
while (!need_resched()) {
void (*idle)(void);
@@ -121,6 +123,7 @@
}
idle();
}
+ rcu_idle_exit();
schedule_preempt_disabled();
}
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 2c05a929..8c6b6b6 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -48,6 +48,7 @@
#include <linux/unistd.h>
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
+#include <linux/rcupdate.h>
#include <asm/io.h>
#include <asm/asm-offsets.h>
@@ -69,8 +70,10 @@
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched())
barrier();
+ rcu_idle_exit();
schedule_preempt_disabled();
check_pgt_cache();
}
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index 2707023..637970c 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -27,6 +27,7 @@
#include <linux/reboot.h>
#include <linux/elfcore.h>
#include <linux/pm.h>
+#include <linux/rcupdate.h>
void (*pm_power_off)(void);
EXPORT_SYMBOL(pm_power_off);
@@ -50,9 +51,10 @@
{
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched())
barrier();
-
+ rcu_idle_exit();
schedule_preempt_disabled();
}
}
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 664a60e..c17de0d 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -705,6 +705,7 @@
struct task_struct *from = current, *to = arg;
to->thread.saved_task = from;
+ rcu_switch(from, to);
switch_to(from, to, from);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ec3a1a..ed97b1b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -97,6 +97,7 @@
select KTIME_SCALAR if X86_32
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
+ select HAVE_RCU_USER_QS if X86_64
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS || UPROBES)
diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h
new file mode 100644
index 0000000..d1ac07a
--- /dev/null
+++ b/arch/x86/include/asm/rcu.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_RCU_H
+#define _ASM_X86_RCU_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/rcupdate.h>
+#include <asm/ptrace.h>
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+ rcu_user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+#ifdef CONFIG_RCU_USER_QS
+ if (user_mode(regs))
+ rcu_user_enter();
+#endif
+}
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_RCU_USER_QS
+# define SCHEDULE_USER call schedule_user
+#else
+# define SCHEDULE_USER call schedule
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89f794f..c535d847 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -89,6 +89,7 @@
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
#define TIF_IA32 17 /* IA32 compatibility process */
#define TIF_FORK 18 /* ret_from_fork */
+#define TIF_NOHZ 19 /* in adaptive nohz mode */
#define TIF_MEMDIE 20 /* is terminating due to OOM killer */
#define TIF_DEBUG 21 /* uses debug registers */
#define TIF_IO_BITMAP 22 /* uses I/O bitmap */
@@ -114,6 +115,7 @@
#define _TIF_NOTSC (1 << TIF_NOTSC)
#define _TIF_IA32 (1 << TIF_IA32)
#define _TIF_FORK (1 << TIF_FORK)
+#define _TIF_NOHZ (1 << TIF_NOHZ)
#define _TIF_DEBUG (1 << TIF_DEBUG)
#define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP)
#define _TIF_FORCED_TF (1 << TIF_FORCED_TF)
@@ -126,12 +128,13 @@
/* work to do in syscall_trace_enter() */
#define _TIF_WORK_SYSCALL_ENTRY \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \
- _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
+ _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \
+ _TIF_NOHZ)
/* work to do in syscall_trace_leave() */
#define _TIF_WORK_SYSCALL_EXIT \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \
- _TIF_SYSCALL_TRACEPOINT)
+ _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
/* work to do on interrupt/exception return */
#define _TIF_WORK_MASK \
@@ -141,7 +144,8 @@
/* work to do on any return to user space */
#define _TIF_ALLWORK_MASK \
- ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT)
+ ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \
+ _TIF_NOHZ)
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 39472dd..60c7891 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -199,12 +199,14 @@
goto out_chrdev;
}
cpuid_class->devnode = cpuid_devnode;
+ get_online_cpus();
for_each_online_cpu(i) {
err = cpuid_device_create(i);
if (err != 0)
goto out_class;
}
register_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ put_online_cpus();
err = 0;
goto out;
@@ -214,6 +216,7 @@
for_each_online_cpu(i) {
cpuid_device_destroy(i);
}
+ put_online_cpus();
class_destroy(cpuid_class);
out_chrdev:
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
@@ -225,11 +228,13 @@
{
int cpu = 0;
+ get_online_cpus();
for_each_online_cpu(cpu)
cpuid_device_destroy(cpu);
class_destroy(cpuid_class);
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ put_online_cpus();
}
module_init(cpuid_init);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 69babd8..1a8f3cb 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,6 +56,7 @@
#include <asm/ftrace.h>
#include <asm/percpu.h>
#include <asm/asm.h>
+#include <asm/rcu.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -565,7 +566,7 @@
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
jmp sysret_check
@@ -678,7 +679,7 @@
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -974,7 +975,7 @@
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
GET_THREAD_INFO(%rcx)
DISABLE_INTERRUPTS(CLBR_NONE)
@@ -1449,7 +1450,7 @@
paranoid_schedule:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
- call schedule
+ SCHEDULE_USER
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
jmp paranoid_userspace
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index eb11369..a7c5661 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -257,12 +257,14 @@
goto out_chrdev;
}
msr_class->devnode = msr_devnode;
+ get_online_cpus();
for_each_online_cpu(i) {
err = msr_device_create(i);
if (err != 0)
goto out_class;
}
register_hotcpu_notifier(&msr_class_cpu_notifier);
+ put_online_cpus();
err = 0;
goto out;
@@ -271,6 +273,7 @@
i = 0;
for_each_online_cpu(i)
msr_device_destroy(i);
+ put_online_cpus();
class_destroy(msr_class);
out_chrdev:
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
@@ -281,11 +284,13 @@
static void __exit msr_exit(void)
{
int cpu = 0;
+ get_online_cpus();
for_each_online_cpu(cpu)
msr_device_destroy(cpu);
class_destroy(msr_class);
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
unregister_hotcpu_notifier(&msr_class_cpu_notifier);
+ put_online_cpus();
}
module_init(msr_init);
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c..9f94f8e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
#include <linux/signal.h>
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
+#include <linux/rcupdate.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -1463,6 +1464,8 @@
{
long ret = 0;
+ rcu_user_exit();
+
/*
* If we stepped into a sysenter/syscall insn, it trapped in
* kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
@@ -1526,4 +1529,6 @@
!test_thread_flag(TIF_SYSCALL_EMU);
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
+
+ rcu_user_enter();
}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b280908..bca0ab9 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -779,6 +779,8 @@
void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
+ rcu_user_exit();
+
#ifdef CONFIG_X86_MCE
/* notify userspace of pending MCEs */
if (thread_info_flags & _TIF_MCE_NOTIFY)
@@ -804,6 +806,8 @@
#ifdef CONFIG_X86_32
clear_thread_flag(TIF_IRET);
#endif /* CONFIG_X86_32 */
+
+ rcu_user_enter();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b481341c..ab82cbd 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,6 +55,7 @@
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/mce.h>
+#include <asm/rcu.h>
#include <asm/mach_traps.h>
@@ -180,11 +181,15 @@
#define DO_ERROR(trapnr, signr, str, name) \
dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
{ \
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
- == NOTIFY_STOP) \
+ exception_enter(regs); \
+ if (notify_die(DIE_TRAP, str, regs, error_code, \
+ trapnr, signr) == NOTIFY_STOP) { \
+ exception_exit(regs); \
return; \
+ } \
conditional_sti(regs); \
do_trap(trapnr, signr, str, regs, error_code, NULL); \
+ exception_exit(regs); \
}
#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
@@ -195,11 +200,15 @@
info.si_errno = 0; \
info.si_code = sicode; \
info.si_addr = (void __user *)siaddr; \
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
- == NOTIFY_STOP) \
+ exception_enter(regs); \
+ if (notify_die(DIE_TRAP, str, regs, error_code, \
+ trapnr, signr) == NOTIFY_STOP) { \
+ exception_exit(regs); \
return; \
+ } \
conditional_sti(regs); \
do_trap(trapnr, signr, str, regs, error_code, &info); \
+ exception_exit(regs); \
}
DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -312,6 +321,7 @@
ftrace_int3_handler(regs))
return;
#endif
+ exception_enter(regs);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
@@ -331,6 +341,7 @@
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
+ exception_exit(regs);
}
#ifdef CONFIG_X86_64
@@ -391,6 +402,8 @@
unsigned long dr6;
int si_code;
+ exception_enter(regs);
+
get_debugreg(dr6, 6);
/* Filter out all the reserved bits which are preset to 1 */
@@ -406,7 +419,7 @@
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
- return;
+ goto exit;
/* DR6 may or may not be cleared by the CPU */
set_debugreg(0, 6);
@@ -421,7 +434,7 @@
if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
/*
* Let others (NMI) know that the debug stack is in use
@@ -437,7 +450,7 @@
X86_TRAP_DB);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
- return;
+ goto exit;
}
/*
@@ -458,7 +471,8 @@
preempt_conditional_cli(regs);
debug_stack_usage_dec();
- return;
+exit:
+ exception_exit(regs);
}
/*
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 76dcd9d..7dde46d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,6 +18,7 @@
#include <asm/pgalloc.h> /* pgd_*(), ... */
#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
#include <asm/fixmap.h> /* VSYSCALL_START */
+#include <asm/rcu.h> /* exception_enter(), ... */
/*
* Page fault error code bits:
@@ -1000,8 +1001,8 @@
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
-dotraplinkage void __kprobes
-do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes
+__do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
@@ -1209,3 +1210,11 @@
up_read(&mm->mmap_sem);
}
+
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+ exception_enter(regs);
+ __do_page_fault(regs, error_code);
+ exception_exit(regs);
+}
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 2c8d6a3..bc44311 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -31,6 +31,7 @@
#include <linux/mqueue.h>
#include <linux/fs.h>
#include <linux/slab.h>
+#include <linux/rcupdate.h>
#include <asm/pgtable.h>
#include <asm/uaccess.h>
@@ -110,8 +111,10 @@
/* endless idle loop with no priority at all */
while (1) {
+ rcu_idle_enter();
while (!need_resched())
platform_idle();
+ rcu_idle_exit();
schedule_preempt_disabled();
}
}
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c5f856a..5e4e617 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -430,6 +430,8 @@
NR_SOFTIRQS
};
+#define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ))
+
/* map softirq index to softirq name. update 'softirq_to_name' in
* kernel/softirq.c when adding a new softirq.
*/
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 115ead2..7c968e4f 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -191,6 +191,21 @@
extern void rcu_idle_exit(void);
extern void rcu_irq_enter(void);
extern void rcu_irq_exit(void);
+
+#ifdef CONFIG_RCU_USER_QS
+extern void rcu_user_enter(void);
+extern void rcu_user_exit(void);
+extern void rcu_user_enter_after_irq(void);
+extern void rcu_user_exit_after_irq(void);
+extern void rcu_user_hooks_switch(struct task_struct *prev,
+ struct task_struct *next);
+#else
+static inline void rcu_user_enter(void) { }
+static inline void rcu_user_exit(void) { }
+static inline void rcu_user_enter_after_irq(void) { }
+static inline void rcu_user_exit_after_irq(void) { }
+#endif /* CONFIG_RCU_USER_QS */
+
extern void exit_rcu(void);
/**
@@ -210,14 +225,12 @@
* to nest RCU_NONIDLE() wrappers, but the nesting level is currently
* quite limited. If deeper nesting is required, it will be necessary
* to adjust DYNTICK_TASK_NESTING_VALUE accordingly.
- *
- * This macro may be used from process-level code only.
*/
#define RCU_NONIDLE(a) \
do { \
- rcu_idle_exit(); \
+ rcu_irq_enter(); \
do { a; } while (0); \
- rcu_idle_enter(); \
+ rcu_irq_exit(); \
} while (0)
/*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b8c8664..cdaeeff 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1886,6 +1886,14 @@
#endif
+static inline void rcu_switch(struct task_struct *prev,
+ struct task_struct *next)
+{
+#ifdef CONFIG_RCU_USER_QS
+ rcu_user_hooks_switch(prev, next);
+#endif
+}
+
static inline void tsk_restore_flags(struct task_struct *task,
unsigned long orig_flags, unsigned long flags)
{
diff --git a/init/Kconfig b/init/Kconfig
index af6c7f8..c26b8a1d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -441,6 +441,24 @@
This option enables preemptible-RCU code that is common between
the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
+config RCU_USER_QS
+ bool "Consider userspace as in RCU extended quiescent state"
+ depends on HAVE_RCU_USER_QS && SMP
+ help
+ This option sets hooks on kernel / userspace boundaries and
+ puts RCU in extended quiescent state when the CPU runs in
+ userspace. It means that when a CPU runs in userspace, it is
+ excluded from the global RCU state machine and thus doesn't
+ to keep the timer tick on for RCU.
+
+config RCU_USER_QS_FORCE
+ bool "Force userspace extended QS by default"
+ depends on RCU_USER_QS
+ help
+ Set the hooks in user/kernel boundaries by default in order to
+ test this feature that treats userspace as an extended quiescent
+ state until we have a real user like a full adaptive nohz option.
+
config RCU_FANOUT
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 4e6a61b..29ca1c6d 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -45,6 +45,7 @@
#include <linux/mutex.h>
#include <linux/export.h>
#include <linux/hardirq.h>
+#include <linux/delay.h>
#define CREATE_TRACE_POINTS
#include <trace/events/rcu.h>
@@ -81,6 +82,9 @@
} else {
barrier(); /* critical section before exit code. */
t->rcu_read_lock_nesting = INT_MIN;
+#ifdef CONFIG_PROVE_RCU_DELAY
+ udelay(10); /* Make preemption more probable. */
+#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
barrier(); /* assign before ->rcu_read_unlock_special load */
if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
rcu_read_unlock_special(t);
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 547b1fe..e4c6a59 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -56,25 +56,28 @@
static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */
-static void rcu_idle_enter_common(long long oldval)
+static void rcu_idle_enter_common(long long newval)
{
- if (rcu_dynticks_nesting) {
+ if (newval) {
RCU_TRACE(trace_rcu_dyntick("--=",
- oldval, rcu_dynticks_nesting));
+ rcu_dynticks_nesting, newval));
+ rcu_dynticks_nesting = newval;
return;
}
- RCU_TRACE(trace_rcu_dyntick("Start", oldval, rcu_dynticks_nesting));
+ RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval));
if (!is_idle_task(current)) {
struct task_struct *idle = idle_task(smp_processor_id());
RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
- oldval, rcu_dynticks_nesting));
+ rcu_dynticks_nesting, newval));
ftrace_dump(DUMP_ALL);
WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
current->pid, current->comm,
idle->pid, idle->comm); /* must be idle task! */
}
rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */
+ barrier();
+ rcu_dynticks_nesting = newval;
}
/*
@@ -84,17 +87,16 @@
void rcu_idle_enter(void)
{
unsigned long flags;
- long long oldval;
+ long long newval;
local_irq_save(flags);
- oldval = rcu_dynticks_nesting;
WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) ==
DYNTICK_TASK_NEST_VALUE)
- rcu_dynticks_nesting = 0;
+ newval = 0;
else
- rcu_dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- rcu_idle_enter_common(oldval);
+ newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE;
+ rcu_idle_enter_common(newval);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -105,15 +107,15 @@
void rcu_irq_exit(void)
{
unsigned long flags;
- long long oldval;
+ long long newval;
local_irq_save(flags);
- oldval = rcu_dynticks_nesting;
- rcu_dynticks_nesting--;
- WARN_ON_ONCE(rcu_dynticks_nesting < 0);
- rcu_idle_enter_common(oldval);
+ newval = rcu_dynticks_nesting - 1;
+ WARN_ON_ONCE(newval < 0);
+ rcu_idle_enter_common(newval);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_irq_exit);
/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */
static void rcu_idle_exit_common(long long oldval)
@@ -171,6 +173,7 @@
rcu_idle_exit_common(oldval);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_irq_enter);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 918fd1e..3d01902 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -278,7 +278,7 @@
rcu_preempt_ctrlblk.exp_tasks == NULL)
return 0; /* Nothing to boost. */
- raw_local_irq_save(flags);
+ local_irq_save(flags);
/*
* Recheck with irqs disabled: all tasks in need of boosting
@@ -287,7 +287,7 @@
*/
if (rcu_preempt_ctrlblk.boost_tasks == NULL &&
rcu_preempt_ctrlblk.exp_tasks == NULL) {
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
return 0;
}
@@ -317,7 +317,7 @@
t = container_of(tb, struct task_struct, rcu_node_entry);
rt_mutex_init_proxy_locked(&mtx, t);
t->rcu_boost_mutex = &mtx;
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
rt_mutex_lock(&mtx);
rt_mutex_unlock(&mtx); /* Keep lockdep happy. */
@@ -991,9 +991,9 @@
{
unsigned long flags;
- raw_local_irq_save(flags);
+ local_irq_save(flags);
rcp->qlen -= n;
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
}
/*
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 25b1503..aaa7b9f 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -53,10 +53,11 @@
static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */
static int nfakewriters = 4; /* # fake writer threads */
-static int stat_interval; /* Interval between stats, in seconds. */
- /* Defaults to "only at end of test". */
+static int stat_interval = 60; /* Interval between stats, in seconds. */
+ /* Zero means "only at end of test". */
static bool verbose; /* Print more debug info. */
-static bool test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */
+static bool test_no_idle_hz = true;
+ /* Test RCU support for tickless idle CPUs. */
static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
static int stutter = 5; /* Start/stop testing interval (in sec) */
static int irqreader = 1; /* RCU readers from irq (timers). */
@@ -119,11 +120,11 @@
#define TORTURE_FLAG "-torture:"
#define PRINTK_STRING(s) \
- do { printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0)
+ do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
#define VERBOSE_PRINTK_STRING(s) \
- do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0)
+ do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0)
#define VERBOSE_PRINTK_ERRSTRING(s) \
- do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
+ do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
static char printk_buf[4096];
@@ -176,8 +177,14 @@
static long n_rcu_torture_timers;
static long n_offline_attempts;
static long n_offline_successes;
+static unsigned long sum_offline;
+static int min_offline = -1;
+static int max_offline;
static long n_online_attempts;
static long n_online_successes;
+static unsigned long sum_online;
+static int min_online = -1;
+static int max_online;
static long n_barrier_attempts;
static long n_barrier_successes;
static struct list_head rcu_torture_removed;
@@ -235,7 +242,7 @@
if (fullstop == FULLSTOP_DONTSTOP)
fullstop = FULLSTOP_SHUTDOWN;
else
- printk(KERN_WARNING /* but going down anyway, so... */
+ pr_warn(/* but going down anyway, so... */
"Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
mutex_unlock(&fullstop_mutex);
return NOTIFY_DONE;
@@ -248,7 +255,7 @@
static void rcutorture_shutdown_absorb(char *title)
{
if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
- printk(KERN_NOTICE
+ pr_notice(
"rcutorture thread %s parking due to system shutdown\n",
title);
schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
@@ -1214,11 +1221,13 @@
n_rcu_torture_boost_failure,
n_rcu_torture_boosts,
n_rcu_torture_timers);
- cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ",
- n_online_successes,
- n_online_attempts,
- n_offline_successes,
- n_offline_attempts);
+ cnt += sprintf(&page[cnt],
+ "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
+ n_online_successes, n_online_attempts,
+ n_offline_successes, n_offline_attempts,
+ min_online, max_online,
+ min_offline, max_offline,
+ sum_online, sum_offline, HZ);
cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
n_barrier_successes,
n_barrier_attempts,
@@ -1267,7 +1276,7 @@
int cnt;
cnt = rcu_torture_printk(printk_buf);
- printk(KERN_ALERT "%s", printk_buf);
+ pr_alert("%s", printk_buf);
}
/*
@@ -1380,20 +1389,20 @@
static inline void
rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
{
- printk(KERN_ALERT "%s" TORTURE_FLAG
- "--- %s: nreaders=%d nfakewriters=%d "
- "stat_interval=%d verbose=%d test_no_idle_hz=%d "
- "shuffle_interval=%d stutter=%d irqreader=%d "
- "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
- "test_boost=%d/%d test_boost_interval=%d "
- "test_boost_duration=%d shutdown_secs=%d "
- "onoff_interval=%d onoff_holdoff=%d\n",
- torture_type, tag, nrealreaders, nfakewriters,
- stat_interval, verbose, test_no_idle_hz, shuffle_interval,
- stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
- test_boost, cur_ops->can_boost,
- test_boost_interval, test_boost_duration, shutdown_secs,
- onoff_interval, onoff_holdoff);
+ pr_alert("%s" TORTURE_FLAG
+ "--- %s: nreaders=%d nfakewriters=%d "
+ "stat_interval=%d verbose=%d test_no_idle_hz=%d "
+ "shuffle_interval=%d stutter=%d irqreader=%d "
+ "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
+ "test_boost=%d/%d test_boost_interval=%d "
+ "test_boost_duration=%d shutdown_secs=%d "
+ "onoff_interval=%d onoff_holdoff=%d\n",
+ torture_type, tag, nrealreaders, nfakewriters,
+ stat_interval, verbose, test_no_idle_hz, shuffle_interval,
+ stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
+ test_boost, cur_ops->can_boost,
+ test_boost_interval, test_boost_duration, shutdown_secs,
+ onoff_interval, onoff_holdoff);
}
static struct notifier_block rcutorture_shutdown_nb = {
@@ -1460,9 +1469,9 @@
!kthread_should_stop()) {
delta = shutdown_time - jiffies_snap;
if (verbose)
- printk(KERN_ALERT "%s" TORTURE_FLAG
- "rcu_torture_shutdown task: %lu jiffies remaining\n",
- torture_type, delta);
+ pr_alert("%s" TORTURE_FLAG
+ "rcu_torture_shutdown task: %lu jiffies remaining\n",
+ torture_type, delta);
schedule_timeout_interruptible(delta);
jiffies_snap = ACCESS_ONCE(jiffies);
}
@@ -1490,8 +1499,10 @@
rcu_torture_onoff(void *arg)
{
int cpu;
+ unsigned long delta;
int maxcpu = -1;
DEFINE_RCU_RANDOM(rand);
+ unsigned long starttime;
VERBOSE_PRINTK_STRING("rcu_torture_onoff task started");
for_each_online_cpu(cpu)
@@ -1506,29 +1517,51 @@
cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1);
if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) {
if (verbose)
- printk(KERN_ALERT "%s" TORTURE_FLAG
- "rcu_torture_onoff task: offlining %d\n",
- torture_type, cpu);
+ pr_alert("%s" TORTURE_FLAG
+ "rcu_torture_onoff task: offlining %d\n",
+ torture_type, cpu);
+ starttime = jiffies;
n_offline_attempts++;
if (cpu_down(cpu) == 0) {
if (verbose)
- printk(KERN_ALERT "%s" TORTURE_FLAG
- "rcu_torture_onoff task: offlined %d\n",
- torture_type, cpu);
+ pr_alert("%s" TORTURE_FLAG
+ "rcu_torture_onoff task: offlined %d\n",
+ torture_type, cpu);
n_offline_successes++;
+ delta = jiffies - starttime;
+ sum_offline += delta;
+ if (min_offline < 0) {
+ min_offline = delta;
+ max_offline = delta;
+ }
+ if (min_offline > delta)
+ min_offline = delta;
+ if (max_offline < delta)
+ max_offline = delta;
}
} else if (cpu_is_hotpluggable(cpu)) {
if (verbose)
- printk(KERN_ALERT "%s" TORTURE_FLAG
- "rcu_torture_onoff task: onlining %d\n",
- torture_type, cpu);
+ pr_alert("%s" TORTURE_FLAG
+ "rcu_torture_onoff task: onlining %d\n",
+ torture_type, cpu);
+ starttime = jiffies;
n_online_attempts++;
if (cpu_up(cpu) == 0) {
if (verbose)
- printk(KERN_ALERT "%s" TORTURE_FLAG
- "rcu_torture_onoff task: onlined %d\n",
- torture_type, cpu);
+ pr_alert("%s" TORTURE_FLAG
+ "rcu_torture_onoff task: onlined %d\n",
+ torture_type, cpu);
n_online_successes++;
+ delta = jiffies - starttime;
+ sum_online += delta;
+ if (min_online < 0) {
+ min_online = delta;
+ max_online = delta;
+ }
+ if (min_online > delta)
+ min_online = delta;
+ if (max_online < delta)
+ max_online = delta;
}
}
schedule_timeout_interruptible(onoff_interval * HZ);
@@ -1593,14 +1626,14 @@
if (!kthread_should_stop()) {
stop_at = get_seconds() + stall_cpu;
/* RCU CPU stall is expected behavior in following code. */
- printk(KERN_ALERT "rcu_torture_stall start.\n");
+ pr_alert("rcu_torture_stall start.\n");
rcu_read_lock();
preempt_disable();
while (ULONG_CMP_LT(get_seconds(), stop_at))
continue; /* Induce RCU CPU stall warning. */
preempt_enable();
rcu_read_unlock();
- printk(KERN_ALERT "rcu_torture_stall end.\n");
+ pr_alert("rcu_torture_stall end.\n");
}
rcutorture_shutdown_absorb("rcu_torture_stall");
while (!kthread_should_stop())
@@ -1716,12 +1749,12 @@
if (n_barrier_cbs == 0)
return 0;
if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
- printk(KERN_ALERT "%s" TORTURE_FLAG
- " Call or barrier ops missing for %s,\n",
- torture_type, cur_ops->name);
- printk(KERN_ALERT "%s" TORTURE_FLAG
- " RCU barrier testing omitted from run.\n",
- torture_type);
+ pr_alert("%s" TORTURE_FLAG
+ " Call or barrier ops missing for %s,\n",
+ torture_type, cur_ops->name);
+ pr_alert("%s" TORTURE_FLAG
+ " RCU barrier testing omitted from run.\n",
+ torture_type);
return 0;
}
atomic_set(&barrier_cbs_count, 0);
@@ -1814,7 +1847,7 @@
mutex_lock(&fullstop_mutex);
rcutorture_record_test_transition();
if (fullstop == FULLSTOP_SHUTDOWN) {
- printk(KERN_WARNING /* but going down anyway, so... */
+ pr_warn(/* but going down anyway, so... */
"Concurrent 'rmmod rcutorture' and shutdown illegal!\n");
mutex_unlock(&fullstop_mutex);
schedule_timeout_uninterruptible(10);
@@ -1938,17 +1971,17 @@
break;
}
if (i == ARRAY_SIZE(torture_ops)) {
- printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n",
- torture_type);
- printk(KERN_ALERT "rcu-torture types:");
+ pr_alert("rcu-torture: invalid torture type: \"%s\"\n",
+ torture_type);
+ pr_alert("rcu-torture types:");
for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
- printk(KERN_ALERT " %s", torture_ops[i]->name);
- printk(KERN_ALERT "\n");
+ pr_alert(" %s", torture_ops[i]->name);
+ pr_alert("\n");
mutex_unlock(&fullstop_mutex);
return -EINVAL;
}
if (cur_ops->fqs == NULL && fqs_duration != 0) {
- printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
+ pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n");
fqs_duration = 0;
}
if (cur_ops->init)
@@ -1996,14 +2029,15 @@
/* Start up the kthreads. */
VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task");
- writer_task = kthread_run(rcu_torture_writer, NULL,
- "rcu_torture_writer");
+ writer_task = kthread_create(rcu_torture_writer, NULL,
+ "rcu_torture_writer");
if (IS_ERR(writer_task)) {
firsterr = PTR_ERR(writer_task);
VERBOSE_PRINTK_ERRSTRING("Failed to create writer");
writer_task = NULL;
goto unwind;
}
+ wake_up_process(writer_task);
fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
GFP_KERNEL);
if (fakewriter_tasks == NULL) {
@@ -2118,14 +2152,15 @@
}
if (shutdown_secs > 0) {
shutdown_time = jiffies + shutdown_secs * HZ;
- shutdown_task = kthread_run(rcu_torture_shutdown, NULL,
- "rcu_torture_shutdown");
+ shutdown_task = kthread_create(rcu_torture_shutdown, NULL,
+ "rcu_torture_shutdown");
if (IS_ERR(shutdown_task)) {
firsterr = PTR_ERR(shutdown_task);
VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown");
shutdown_task = NULL;
goto unwind;
}
+ wake_up_process(shutdown_task);
}
i = rcu_torture_onoff_init();
if (i != 0) {
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 52b24c0..6c94351 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -207,6 +207,9 @@
DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
.dynticks = ATOMIC_INIT(1),
+#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE)
+ .ignore_user_qs = true,
+#endif
};
static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */
@@ -321,45 +324,17 @@
}
/*
- * If the specified CPU is offline, tell the caller that it is in
- * a quiescent state. Otherwise, whack it with a reschedule IPI.
- * Grace periods can end up waiting on an offline CPU when that
- * CPU is in the process of coming online -- it will be added to the
- * rcu_node bitmasks before it actually makes it online. The same thing
- * can happen while a CPU is in the process of coming online. Because this
- * race is quite rare, we check for it after detecting that the grace
- * period has been delayed rather than checking each and every CPU
- * each and every time we start a new grace period.
- */
-static int rcu_implicit_offline_qs(struct rcu_data *rdp)
-{
- /*
- * If the CPU is offline for more than a jiffy, it is in a quiescent
- * state. We can trust its state not to change because interrupts
- * are disabled. The reason for the jiffy's worth of slack is to
- * handle CPUs initializing on the way up and finding their way
- * to the idle loop on the way down.
- */
- if (cpu_is_offline(rdp->cpu) &&
- ULONG_CMP_LT(rdp->rsp->gp_start + 2, jiffies)) {
- trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl");
- rdp->offline_fqs++;
- return 1;
- }
- return 0;
-}
-
-/*
- * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle
+ * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state
*
* If the new value of the ->dynticks_nesting counter now is zero,
* we really have entered idle, and must do the appropriate accounting.
* The caller must have disabled interrupts.
*/
-static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval)
+static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
+ bool user)
{
trace_rcu_dyntick("Start", oldval, 0);
- if (!is_idle_task(current)) {
+ if (!user && !is_idle_task(current)) {
struct task_struct *idle = idle_task(smp_processor_id());
trace_rcu_dyntick("Error on entry: not idle task", oldval, 0);
@@ -376,7 +351,7 @@
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
/*
- * The idle task is not permitted to enter the idle loop while
+ * It is illegal to enter an extended quiescent state while
* in an RCU read-side critical section.
*/
rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
@@ -387,6 +362,25 @@
"Illegal idle entry in RCU-sched read-side critical section.");
}
+/*
+ * Enter an RCU extended quiescent state, which can be either the
+ * idle loop or adaptive-tickless usermode execution.
+ */
+static void rcu_eqs_enter(bool user)
+{
+ long long oldval;
+ struct rcu_dynticks *rdtp;
+
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ oldval = rdtp->dynticks_nesting;
+ WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
+ if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+ rdtp->dynticks_nesting = 0;
+ else
+ rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
+ rcu_eqs_enter_common(rdtp, oldval, user);
+}
+
/**
* rcu_idle_enter - inform RCU that current CPU is entering idle
*
@@ -402,21 +396,59 @@
void rcu_idle_enter(void)
{
unsigned long flags;
- long long oldval;
+
+ local_irq_save(flags);
+ rcu_eqs_enter(false);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
+
+#ifdef CONFIG_RCU_USER_QS
+/**
+ * rcu_user_enter - inform RCU that we are resuming userspace.
+ *
+ * Enter RCU idle mode right before resuming userspace. No use of RCU
+ * is permitted between this call and rcu_user_exit(). This way the
+ * CPU doesn't need to maintain the tick for RCU maintenance purposes
+ * when the CPU runs in userspace.
+ */
+void rcu_user_enter(void)
+{
+ unsigned long flags;
+ struct rcu_dynticks *rdtp;
+
+ WARN_ON_ONCE(!current->mm);
+
+ local_irq_save(flags);
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ if (!rdtp->ignore_user_qs && !rdtp->in_user) {
+ rdtp->in_user = true;
+ rcu_eqs_enter(true);
+ }
+ local_irq_restore(flags);
+}
+
+/**
+ * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace
+ * after the current irq returns.
+ *
+ * This is similar to rcu_user_enter() but in the context of a non-nesting
+ * irq. After this call, RCU enters into idle mode when the interrupt
+ * returns.
+ */
+void rcu_user_enter_after_irq(void)
+{
+ unsigned long flags;
struct rcu_dynticks *rdtp;
local_irq_save(flags);
rdtp = &__get_cpu_var(rcu_dynticks);
- oldval = rdtp->dynticks_nesting;
- WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
- if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
- rdtp->dynticks_nesting = 0;
- else
- rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
- rcu_idle_enter_common(rdtp, oldval);
+ /* Ensure this irq is interrupting a non-idle RCU state. */
+ WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK));
+ rdtp->dynticks_nesting = 1;
local_irq_restore(flags);
}
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
+#endif /* CONFIG_RCU_USER_QS */
/**
* rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
@@ -448,18 +480,20 @@
if (rdtp->dynticks_nesting)
trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting);
else
- rcu_idle_enter_common(rdtp, oldval);
+ rcu_eqs_enter_common(rdtp, oldval, true);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_irq_exit);
/*
- * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle
+ * rcu_eqs_exit_common - current CPU moving away from extended quiescent state
*
* If the new value of the ->dynticks_nesting counter was previously zero,
* we really have exited idle, and must do the appropriate accounting.
* The caller must have disabled interrupts.
*/
-static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval)
+static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
+ int user)
{
smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */
atomic_inc(&rdtp->dynticks);
@@ -468,7 +502,7 @@
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
rcu_cleanup_after_idle(smp_processor_id());
trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting);
- if (!is_idle_task(current)) {
+ if (!user && !is_idle_task(current)) {
struct task_struct *idle = idle_task(smp_processor_id());
trace_rcu_dyntick("Error on exit: not idle task",
@@ -480,6 +514,25 @@
}
}
+/*
+ * Exit an RCU extended quiescent state, which can be either the
+ * idle loop or adaptive-tickless usermode execution.
+ */
+static void rcu_eqs_exit(bool user)
+{
+ struct rcu_dynticks *rdtp;
+ long long oldval;
+
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ oldval = rdtp->dynticks_nesting;
+ WARN_ON_ONCE(oldval < 0);
+ if (oldval & DYNTICK_TASK_NEST_MASK)
+ rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
+ else
+ rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
+ rcu_eqs_exit_common(rdtp, oldval, user);
+}
+
/**
* rcu_idle_exit - inform RCU that current CPU is leaving idle
*
@@ -494,22 +547,57 @@
void rcu_idle_exit(void)
{
unsigned long flags;
- struct rcu_dynticks *rdtp;
- long long oldval;
local_irq_save(flags);
- rdtp = &__get_cpu_var(rcu_dynticks);
- oldval = rdtp->dynticks_nesting;
- WARN_ON_ONCE(oldval < 0);
- if (oldval & DYNTICK_TASK_NEST_MASK)
- rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
- else
- rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
- rcu_idle_exit_common(rdtp, oldval);
+ rcu_eqs_exit(false);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(rcu_idle_exit);
+#ifdef CONFIG_RCU_USER_QS
+/**
+ * rcu_user_exit - inform RCU that we are exiting userspace.
+ *
+ * Exit RCU idle mode while entering the kernel because it can
+ * run a RCU read side critical section anytime.
+ */
+void rcu_user_exit(void)
+{
+ unsigned long flags;
+ struct rcu_dynticks *rdtp;
+
+ local_irq_save(flags);
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ if (rdtp->in_user) {
+ rdtp->in_user = false;
+ rcu_eqs_exit(true);
+ }
+ local_irq_restore(flags);
+}
+
+/**
+ * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace
+ * idle mode after the current non-nesting irq returns.
+ *
+ * This is similar to rcu_user_exit() but in the context of an irq.
+ * This is called when the irq has interrupted a userspace RCU idle mode
+ * context. When the current non-nesting interrupt returns after this call,
+ * the CPU won't restore the RCU idle mode.
+ */
+void rcu_user_exit_after_irq(void)
+{
+ unsigned long flags;
+ struct rcu_dynticks *rdtp;
+
+ local_irq_save(flags);
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ /* Ensure we are interrupting an RCU idle mode. */
+ WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK);
+ rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE;
+ local_irq_restore(flags);
+}
+#endif /* CONFIG_RCU_USER_QS */
+
/**
* rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
*
@@ -543,9 +631,10 @@
if (oldval)
trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting);
else
- rcu_idle_exit_common(rdtp, oldval);
+ rcu_eqs_exit_common(rdtp, oldval, true);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_irq_enter);
/**
* rcu_nmi_enter - inform RCU of entry to NMI context
@@ -607,6 +696,21 @@
}
EXPORT_SYMBOL(rcu_is_cpu_idle);
+#ifdef CONFIG_RCU_USER_QS
+void rcu_user_hooks_switch(struct task_struct *prev,
+ struct task_struct *next)
+{
+ struct rcu_dynticks *rdtp;
+
+ /* Interrupts are disabled in context switch */
+ rdtp = &__get_cpu_var(rcu_dynticks);
+ if (!rdtp->ignore_user_qs) {
+ clear_tsk_thread_flag(prev, TIF_NOHZ);
+ set_tsk_thread_flag(next, TIF_NOHZ);
+ }
+}
+#endif /* #ifdef CONFIG_RCU_USER_QS */
+
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
@@ -677,7 +781,7 @@
* Return true if the specified CPU has passed through a quiescent
* state by virtue of being in or having passed through an dynticks
* idle state since the last call to dyntick_save_progress_counter()
- * for this same CPU.
+ * for this same CPU, or by virtue of having been offline.
*/
static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
{
@@ -701,8 +805,26 @@
return 1;
}
- /* Go check for the CPU being offline. */
- return rcu_implicit_offline_qs(rdp);
+ /*
+ * Check for the CPU being offline, but only if the grace period
+ * is old enough. We don't need to worry about the CPU changing
+ * state: If we see it offline even once, it has been through a
+ * quiescent state.
+ *
+ * The reason for insisting that the grace period be at least
+ * one jiffy old is that CPUs that are not quite online and that
+ * have just gone offline can still execute RCU read-side critical
+ * sections.
+ */
+ if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
+ return 0; /* Grace period is not old enough. */
+ barrier();
+ if (cpu_is_offline(rdp->cpu)) {
+ trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl");
+ rdp->offline_fqs++;
+ return 1;
+ }
+ return 0;
}
static int jiffies_till_stall_check(void)
@@ -759,14 +881,15 @@
rcu_for_each_leaf_node(rsp, rnp) {
raw_spin_lock_irqsave(&rnp->lock, flags);
ndetected += rcu_print_task_stall(rnp);
+ if (rnp->qsmask != 0) {
+ for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
+ if (rnp->qsmask & (1UL << cpu)) {
+ print_cpu_stall_info(rsp,
+ rnp->grplo + cpu);
+ ndetected++;
+ }
+ }
raw_spin_unlock_irqrestore(&rnp->lock, flags);
- if (rnp->qsmask == 0)
- continue;
- for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
- if (rnp->qsmask & (1UL << cpu)) {
- print_cpu_stall_info(rsp, rnp->grplo + cpu);
- ndetected++;
- }
}
/*
@@ -831,7 +954,8 @@
j = ACCESS_ONCE(jiffies);
js = ACCESS_ONCE(rsp->jiffies_stall);
rnp = rdp->mynode;
- if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
+ if (rcu_gp_in_progress(rsp) &&
+ (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
/* We haven't checked in, so go dump stack. */
print_cpu_stall(rsp);
@@ -1484,17 +1608,6 @@
int i;
struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
- /*
- * If there is an rcu_barrier() operation in progress, then
- * only the task doing that operation is permitted to adopt
- * callbacks. To do otherwise breaks rcu_barrier() and friends
- * by causing them to fail to wait for the callbacks in the
- * orphanage.
- */
- if (rsp->rcu_barrier_in_progress &&
- rsp->rcu_barrier_in_progress != current)
- return;
-
/* Do the accounting first. */
rdp->qlen_lazy += rsp->qlen_lazy;
rdp->qlen += rsp->qlen;
@@ -1549,9 +1662,8 @@
* The CPU has been completely removed, and some other CPU is reporting
* this fact from process context. Do the remainder of the cleanup,
* including orphaning the outgoing CPU's RCU callbacks, and also
- * adopting them, if there is no _rcu_barrier() instance running.
- * There can only be one CPU hotplug operation at a time, so no other
- * CPU can be attempting to update rcu_cpu_kthread_task.
+ * adopting them. There can only be one CPU hotplug operation at a time,
+ * so no other CPU can be attempting to update rcu_cpu_kthread_task.
*/
static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
{
@@ -1609,14 +1721,13 @@
WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
"rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
cpu, rdp->qlen, rdp->nxtlist);
+ init_callback_list(rdp);
+ /* Disallow further callbacks on this CPU. */
+ rdp->nxttail[RCU_NEXT_TAIL] = NULL;
}
#else /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
-{
-}
-
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
}
@@ -1985,8 +2096,6 @@
head->func = func;
head->next = NULL;
- smp_mb(); /* Ensure RCU update seen before callback registry. */
-
/*
* Opportunistically note grace-period endings and beginnings.
* Note that we might see a beginning right after we see an
@@ -1997,6 +2106,12 @@
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
+ if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL)) {
+ /* _call_rcu() is illegal on offline CPU; leak the callback. */
+ WARN_ON_ONCE(1);
+ local_irq_restore(flags);
+ return;
+ }
ACCESS_ONCE(rdp->qlen)++;
if (lazy)
rdp->qlen_lazy++;
@@ -2365,13 +2480,10 @@
static void _rcu_barrier(struct rcu_state *rsp)
{
int cpu;
- unsigned long flags;
struct rcu_data *rdp;
- struct rcu_data rd;
unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done);
unsigned long snap_done;
- init_rcu_head_on_stack(&rd.barrier_head);
_rcu_barrier_trace(rsp, "Begin", -1, snap);
/* Take mutex to serialize concurrent rcu_barrier() requests. */
@@ -2411,70 +2523,30 @@
/*
* Initialize the count to one rather than to zero in order to
* avoid a too-soon return to zero in case of a short grace period
- * (or preemption of this task). Also flag this task as doing
- * an rcu_barrier(). This will prevent anyone else from adopting
- * orphaned callbacks, which could cause otherwise failure if a
- * CPU went offline and quickly came back online. To see this,
- * consider the following sequence of events:
- *
- * 1. We cause CPU 0 to post an rcu_barrier_callback() callback.
- * 2. CPU 1 goes offline, orphaning its callbacks.
- * 3. CPU 0 adopts CPU 1's orphaned callbacks.
- * 4. CPU 1 comes back online.
- * 5. We cause CPU 1 to post an rcu_barrier_callback() callback.
- * 6. Both rcu_barrier_callback() callbacks are invoked, awakening
- * us -- but before CPU 1's orphaned callbacks are invoked!!!
+ * (or preemption of this task). Exclude CPU-hotplug operations
+ * to ensure that no offline CPU has callbacks queued.
*/
init_completion(&rsp->barrier_completion);
atomic_set(&rsp->barrier_cpu_count, 1);
- raw_spin_lock_irqsave(&rsp->onofflock, flags);
- rsp->rcu_barrier_in_progress = current;
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
+ get_online_cpus();
/*
- * Force every CPU with callbacks to register a new callback
- * that will tell us when all the preceding callbacks have
- * been invoked. If an offline CPU has callbacks, wait for
- * it to either come back online or to finish orphaning those
- * callbacks.
+ * Force each CPU with callbacks to register a new callback.
+ * When that callback is invoked, we will know that all of the
+ * corresponding CPU's preceding callbacks have been invoked.
*/
- for_each_possible_cpu(cpu) {
- preempt_disable();
+ for_each_online_cpu(cpu) {
rdp = per_cpu_ptr(rsp->rda, cpu);
- if (cpu_is_offline(cpu)) {
- _rcu_barrier_trace(rsp, "Offline", cpu,
- rsp->n_barrier_done);
- preempt_enable();
- while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen))
- schedule_timeout_interruptible(1);
- } else if (ACCESS_ONCE(rdp->qlen)) {
+ if (ACCESS_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->n_barrier_done);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
- preempt_enable();
} else {
_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
rsp->n_barrier_done);
- preempt_enable();
}
}
-
- /*
- * Now that all online CPUs have rcu_barrier_callback() callbacks
- * posted, we can adopt all of the orphaned callbacks and place
- * an rcu_barrier_callback() callback after them. When that is done,
- * we are guaranteed to have an rcu_barrier_callback() callback
- * following every callback that could possibly have been
- * registered before _rcu_barrier() was called.
- */
- raw_spin_lock_irqsave(&rsp->onofflock, flags);
- rcu_adopt_orphan_cbs(rsp);
- rsp->rcu_barrier_in_progress = NULL;
- raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
- atomic_inc(&rsp->barrier_cpu_count);
- smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */
- rd.rsp = rsp;
- rsp->call(&rd.barrier_head, rcu_barrier_callback);
+ put_online_cpus();
/*
* Now that we have an rcu_barrier_callback() callback on each
@@ -2495,8 +2567,6 @@
/* Other rcu_barrier() invocations can now safely proceed. */
mutex_unlock(&rsp->barrier_mutex);
-
- destroy_rcu_head_on_stack(&rd.barrier_head);
}
/**
@@ -2536,6 +2606,9 @@
rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
+#ifdef CONFIG_RCU_USER_QS
+ WARN_ON_ONCE(rdp->dynticks->in_user);
+#endif
rdp->cpu = cpu;
rdp->rsp = rsp;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -2562,6 +2635,7 @@
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
+ init_callback_list(rdp); /* Re-enable callbacks on this CPU. */
rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
atomic_set(&rdp->dynticks->dynticks,
(atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 935dd4c..499d661 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -102,6 +102,10 @@
/* idle-period nonlazy_posted snapshot. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+#ifdef CONFIG_RCU_USER_QS
+ bool ignore_user_qs; /* Treat userspace as extended QS or not */
+ bool in_user; /* Is the CPU in userland from RCU POV? */
+#endif
};
/* RCU's kthread states for tracing. */
@@ -396,9 +400,6 @@
struct rcu_head **orphan_donetail; /* Tail of above. */
long qlen_lazy; /* Number of lazy callbacks. */
long qlen; /* Total number of callbacks. */
- struct task_struct *rcu_barrier_in_progress;
- /* Task doing rcu_barrier(), */
- /* or NULL if no barrier. */
struct mutex barrier_mutex; /* Guards barrier fields. */
atomic_t barrier_cpu_count; /* # CPUs waiting on. */
struct completion barrier_completion; /* Wake at barrier end. */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 4734afbe..3b1a11e 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -421,9 +421,11 @@
unsigned long flags;
struct task_struct *t;
- if (!rcu_preempt_blocked_readers_cgp(rnp))
- return;
raw_spin_lock_irqsave(&rnp->lock, flags);
+ if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+ raw_spin_unlock_irqrestore(&rnp->lock, flags);
+ return;
+ }
t = list_entry(rnp->gp_tasks,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
@@ -583,17 +585,23 @@
raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
}
+ rnp->gp_tasks = NULL;
+ rnp->exp_tasks = NULL;
#ifdef CONFIG_RCU_BOOST
- /* In case root is being boosted and leaf is not. */
+ rnp->boost_tasks = NULL;
+ /*
+ * In case root is being boosted and leaf was not. Make sure
+ * that we boost the tasks blocking the current grace period
+ * in this case.
+ */
raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
if (rnp_root->boost_tasks != NULL &&
- rnp_root->boost_tasks != rnp_root->gp_tasks)
+ rnp_root->boost_tasks != rnp_root->gp_tasks &&
+ rnp_root->boost_tasks != rnp_root->exp_tasks)
rnp_root->boost_tasks = rnp_root->gp_tasks;
raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */
#endif /* #ifdef CONFIG_RCU_BOOST */
- rnp->gp_tasks = NULL;
- rnp->exp_tasks = NULL;
return retval;
}
@@ -1204,9 +1212,9 @@
* kthread to start boosting them. If there is an expedited grace
* period in progress, it is always time to boost.
*
- * The caller must hold rnp->lock, which this function releases,
- * but irqs remain disabled. The ->boost_kthread_task is immortal,
- * so we don't need to worry about it going away.
+ * The caller must hold rnp->lock, which this function releases.
+ * The ->boost_kthread_task is immortal, so we don't need to worry
+ * about it going away.
*/
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
{
@@ -2010,6 +2018,26 @@
if (!tne)
return;
+ /* Adaptive-tick mode, where usermode execution is idle to RCU. */
+ if (!is_idle_task(current)) {
+ rdtp->dyntick_holdoff = jiffies - 1;
+ if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
+ trace_rcu_prep_idle("User dyntick with callbacks");
+ rdtp->idle_gp_timer_expires =
+ round_up(jiffies + RCU_IDLE_GP_DELAY,
+ RCU_IDLE_GP_DELAY);
+ } else if (rcu_cpu_has_callbacks(cpu)) {
+ rdtp->idle_gp_timer_expires =
+ round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY);
+ trace_rcu_prep_idle("User dyntick with lazy callbacks");
+ } else {
+ return;
+ }
+ tp = &rdtp->idle_gp_timer;
+ mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
+ return;
+ }
+
/*
* If this is an idle re-entry, for example, due to use of
* RCU_NONIDLE() or the new idle-loop tracing API within the idle
@@ -2289,11 +2317,10 @@
/* Increment ->ticks_this_gp for all flavors of RCU. */
static void increment_cpu_stall_ticks(void)
{
- __get_cpu_var(rcu_sched_data).ticks_this_gp++;
- __get_cpu_var(rcu_bh_data).ticks_this_gp++;
-#ifdef CONFIG_TREE_PREEMPT_RCU
- __get_cpu_var(rcu_preempt_data).ticks_this_gp++;
-#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
+ struct rcu_state *rsp;
+
+ for_each_rcu_flavor(rsp)
+ __this_cpu_ptr(rsp->rda)->ticks_this_gp++;
}
#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index bd4df13..7340efd 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -51,8 +51,8 @@
struct rcu_state *rsp;
for_each_rcu_flavor(rsp)
- seq_printf(m, "%s: %c bcc: %d nbd: %lu\n",
- rsp->name, rsp->rcu_barrier_in_progress ? 'B' : '.',
+ seq_printf(m, "%s: bcc: %d nbd: %lu\n",
+ rsp->name,
atomic_read(&rsp->barrier_cpu_count),
rsp->n_barrier_done);
return 0;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fbf1fd0..ce685da 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2081,6 +2081,7 @@
#endif
/* Here we just switch the register state and the stack. */
+ rcu_switch(prev, next);
switch_to(prev, next, prev);
barrier();
@@ -3468,6 +3469,21 @@
}
EXPORT_SYMBOL(schedule);
+#ifdef CONFIG_RCU_USER_QS
+asmlinkage void __sched schedule_user(void)
+{
+ /*
+ * If we come here after a random call to set_need_resched(),
+ * or we have been woken up remotely but the IPI has not yet arrived,
+ * we haven't yet exited the RCU idle mode. Do it here manually until
+ * we find a better solution.
+ */
+ rcu_user_exit();
+ schedule();
+ rcu_user_enter();
+}
+#endif
+
/**
* schedule_preempt_disabled - called with preemption disabled
*
@@ -3569,6 +3585,7 @@
/* Catch callers which need to be fixed */
BUG_ON(ti->preempt_count || !irqs_disabled());
+ rcu_user_exit();
do {
add_preempt_count(PREEMPT_ACTIVE);
local_irq_enable();
@@ -5304,27 +5321,17 @@
}
/*
- * While a dead CPU has no uninterruptible tasks queued at this point,
- * it might still have a nonzero ->nr_uninterruptible counter, because
- * for performance reasons the counter is not stricly tracking tasks to
- * their home CPUs. So we just add the counter to another CPU's counter,
- * to keep the global sum constant after CPU-down:
+ * Since this CPU is going 'away' for a while, fold any nr_active delta
+ * we might have. Assumes we're called after migrate_tasks() so that the
+ * nr_active count is stable.
+ *
+ * Also see the comment "Global load-average calculations".
*/
-static void migrate_nr_uninterruptible(struct rq *rq_src)
+static void calc_load_migrate(struct rq *rq)
{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
-
- rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
- rq_src->nr_uninterruptible = 0;
-}
-
-/*
- * remove the tasks which were accounted by rq from calc_load_tasks.
- */
-static void calc_global_load_remove(struct rq *rq)
-{
- atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
- rq->calc_load_active = 0;
+ long delta = calc_load_fold_active(rq);
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
}
/*
@@ -5617,9 +5624,18 @@
migrate_tasks(cpu);
BUG_ON(rq->nr_running != 1); /* the migration thread */
raw_spin_unlock_irqrestore(&rq->lock, flags);
+ break;
- migrate_nr_uninterruptible(rq);
- calc_global_load_remove(rq);
+ case CPU_DEAD:
+ {
+ struct rq *dest_rq;
+
+ local_irq_save(flags);
+ dest_rq = cpu_rq(smp_processor_id());
+ raw_spin_lock(&dest_rq->lock);
+ calc_load_migrate(rq);
+ raw_spin_unlock_irqrestore(&dest_rq->lock, flags);
+ }
break;
#endif
}
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 024540f..4b1785a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -436,7 +436,8 @@
if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
static int ratelimit;
- if (ratelimit < 10) {
+ if (ratelimit < 10 &&
+ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
(unsigned int) local_softirq_pending());
ratelimit++;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 2403a63..dacbbe4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -629,6 +629,20 @@
Say N if you are unsure.
+config PROVE_RCU_DELAY
+ bool "RCU debugging: preemptible RCU race provocation"
+ depends on DEBUG_KERNEL && PREEMPT_RCU
+ default n
+ help
+ There is a class of races that involve an unlikely preemption
+ of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
+ been set to INT_MIN. This feature inserts a delay at that
+ point to increase the probability of these races.
+
+ Say Y to increase probability of preemption of __rcu_read_unlock().
+
+ Say N if you are unsure.
+
config SPARSE_RCU_POINTER
bool "RCU debugging: sparse-based checks for pointer usage"
default n
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 45eb621..0de83b4 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1483,13 +1483,11 @@
{
struct kmemleak_object *prev_obj = v;
struct kmemleak_object *next_obj = NULL;
- struct list_head *n = &prev_obj->object_list;
+ struct kmemleak_object *obj = prev_obj;
++(*pos);
- list_for_each_continue_rcu(n, &object_list) {
- struct kmemleak_object *obj =
- list_entry(n, struct kmemleak_object, object_list);
+ list_for_each_entry_continue_rcu(obj, &object_list, object_list) {
if (get_object(obj)) {
next_obj = obj;
break;
